Engineering Proceedings

Editorial

Jump to: Other

4 pages, 4595 KB

Open AccessEditorial

Preface: The 2025 IEEE International Conference on Computation, Big-Data and Engineering (IEEE ICCBE 2025)

by Teen-Hang Meen, Wei Chien and Cheng-Fu Yang

Eng. Proc. 2026, 128(1), 51; https://doi.org/10.3390/engproc2026128051 - 29 Apr 2026

Viewed by 628

Abstract

This volume represents the proceedings of the 2025 IEEE International Conference on Computation, Big-Data and Engineering (IEEE ICCBE 2025) [...] Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

2 pages, 287 KB

Open AccessEditorial

Statement of Peer Review

by Teen-Hang Meen, Wei Chien and Cheng-Fu Yang

Eng. Proc. 2026, 128(1), 52; https://doi.org/10.3390/engproc2026128052 - 3 Jun 2026

Viewed by 130

Abstract

In submitting conference proceedings from the 2025 IEEE International Conference on Computation, Big-Data and Engineering (IEEE ICCBE 2025) to Engineering Proceedings, the volume editors of the proceedings certify to the publisher that all papers published in this volume have been subjected to [...] Read more.

In submitting conference proceedings from the 2025 IEEE International Conference on Computation, Big-Data and Engineering (IEEE ICCBE 2025) to Engineering Proceedings, the volume editors of the proceedings certify to the publisher that all papers published in this volume have been subjected to peer review administered by the volume editors [...] Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

Other

Jump to: Editorial

8 pages, 1242 KB

Open AccessProceeding Paper

Ginger Leaf Diseases Detection Using Deep Learning: A Comparative Study of Pre-Trained Models

by Wai Zhong Wong, Yiqi Tew and Chi Wee Tan

Eng. Proc. 2026, 128(1), 1; https://doi.org/10.3390/engproc2026128001 - 4 Mar 2026

Viewed by 828

Abstract

Ginger (Zingiber officinale) is an essential crop that is widely cultivated for its medical and culinary value. In 2023, ginger was considered one of the highest value herbs, with approximately 9089.85 tons produced in Malaysia. However, the ginger cultivation suffers from [...] Read more.

Ginger (Zingiber officinale) is an essential crop that is widely cultivated for its medical and culinary value. In 2023, ginger was considered one of the highest value herbs, with approximately 9089.85 tons produced in Malaysia. However, the ginger cultivation suffers from plant diseases, which lead to plant death and eventually cause crop losses. Furthermore, the lack of studies in ginger leaf disease detection using deep learning techniques is a limitation that hinders the early diagnosis and management of ginger diseases. To address this limitation, we collected 968 ginger plant images cropped into single leaf images and labelled into 4 classes: leaf blight, dehydrated, damaged pest, and healthy, using the Encordplatform. The generated dataset consisted of 4033 leaf images. Through data augmentation, the dataset was expanded into 10,910 leaf images to improve the model’s generalization. As deep learning techniques are popular in plant disease detection, we evaluated several popular pre-trained models using TensorFlow and PyTorch libraries and compared the performance with that of other models. For all of these models, the same settings were applied with minimal modification to the model’s layers. Among the compared models, EfficientNetB3 achieved the highest accuracy of 94.3% in detecting ginger leaf diseases. It surpassed other models and exceeded the next-best model in this experiment, MobileNetV2, which achieved 89.66% accuracy, by 4.64%. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 589 KB

Open AccessProceeding Paper

Optimization of Biodiesel Production from Palm Oil via Sodium-Hydroxide-Catalyzed Transesterification in a Tubular Microreactor

by Aloisiyus Yuli Widianto, Jonathan Brian, Muhammad Erfan Zawawi and Edy Purwanto

Eng. Proc. 2026, 128(1), 2; https://doi.org/10.3390/engproc2026128002 - 5 Mar 2026

Cited by 1 | Viewed by 1057

Abstract

Biodiesel production can be improved using new microdevice technologies that increase reaction efficiency and yield. Biodiesel synthesis from palm oil was conducted through transesterification using a sodium hydroxide catalyst, and a compact polytetrafluoroethylene microreactor with a 1 mm diameter was used. The effect [...] Read more.

Biodiesel production can be improved using new microdevice technologies that increase reaction efficiency and yield. Biodiesel synthesis from palm oil was conducted through transesterification using a sodium hydroxide catalyst, and a compact polytetrafluoroethylene microreactor with a 1 mm diameter was used. The effect of methanol-to-oil ratio, temperature, and catalyst concentration was explored to determine the optimal conditions for producing fatty acid methyl esters (FAME). The highest FAME yield reached 90.30%, with a short residence time of 10.85 min. The final product had a density of 0.848 to 0.909 g/mL and a viscosity of 4.038 to 24.987 CSt, showing the method’s effectiveness. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 929 KB

Open AccessProceeding Paper

Optimizing Factory Layout Through Systematic Layout Planning and Multi-Criteria Decision-Making Approaches: A Case Study at Textile Company

by Nguyen Thi Bich Thu, Ta Nguyen Minh Duc, Yung-Tsan Jou, Luong Ngoc Hieu and Le Duy Thanh

Eng. Proc. 2026, 128(1), 3; https://doi.org/10.3390/engproc2026128003 - 5 Mar 2026

Viewed by 1742

Abstract

We enhance the operational performance of a textile factory by optimizing its production layout. The optimized layout improves operational time and increases overall productivity through strategic layout planning and workflow adjustments. The systematic layout planning method, combined with the analytical hierarchy process and [...] Read more.

We enhance the operational performance of a textile factory by optimizing its production layout. The optimized layout improves operational time and increases overall productivity through strategic layout planning and workflow adjustments. The systematic layout planning method, combined with the analytical hierarchy process and technique for order of preference by similarity to an ideal solution from the multi-criteria decision-making process, is used to develop and select the optimal layout solution. The results show that the implementation of the improved layout design in alternative 1 led to a 45% reduction in average travel time and a 34% reduction in travel distance. This proposed solution optimizes production space while improving flexibility, safety, and competitiveness. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

21 pages, 915 KB

Open AccessProceeding Paper

Human Resource Management Task Tracking Management System Based on Blockchain Technology

by Chin-Ling Chen, Yung-She Lin, Chin-Feng Lee, Ling-Chun Liu and Kuang-Wei Zeng

Eng. Proc. 2026, 128(1), 4; https://doi.org/10.3390/engproc2026128004 - 6 Mar 2026

Viewed by 651

Abstract

We explore the problems encountered by today’s enterprises when using traditional human resource management systems and task tracking management systems to propose the use of blockchain technology as an innovative solution for internal human resource management and task tracking management. To ensure the [...] Read more.

We explore the problems encountered by today’s enterprises when using traditional human resource management systems and task tracking management systems to propose the use of blockchain technology as an innovative solution for internal human resource management and task tracking management. To ensure the security, transparency, non-repudiation, and traceability of the information submitted by various parties in the entire life cycle of task tracking management, we propose a task tracking management system based on blockchain technology. The system architecture integrates the key stakeholders in the entire value chain of task tracking management in human resource management, including internal employees, department managers, and human resource management departments. The architecture integrates the internal work tracking and management process of the enterprise through blockchain technology, ensuring data non-repudiation through digital signatures. Asymmetric encryption and decryption technology are employed to prevent data leakage and resist ransomware attacks. Based on the above features, it is highly suitable for enterprise introduction and use. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

8 pages, 990 KB

Open AccessProceeding Paper

Optimization of Coal Distribution System to Minimize Export Shipment Delays

by Adinda Nathania Perangin Angin, Muhammad Nashir Ardiansyah, Nova Indah Saragih and Wawan Tripiawan

Eng. Proc. 2026, 128(1), 5; https://doi.org/10.3390/engproc2026128005 - 6 Mar 2026

Viewed by 696

Abstract

Coal distribution is crucial in Indonesia’s mining industry. Due to the country’s complex archipelagic geography, coal distribution has become a challenge for the mining industry. As one of the coal mining companies, XYZ company, which is located in South Sumatera, Indonesia, has experienced [...] Read more.

Coal distribution is crucial in Indonesia’s mining industry. Due to the country’s complex archipelagic geography, coal distribution has become a challenge for the mining industry. As one of the coal mining companies, XYZ company, which is located in South Sumatera, Indonesia, has experienced export shipment delays due to the reliance on transportation modes in the area. Therefore, we developed a coal distribution system which considers multimode transportation options using mixed integer linear programming to minimize delays and transportation cost. Based on the results, the distribution delays were reduced, as well as the transportation cost related to penalty of the delays. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 414 KB

Open AccessProceeding Paper

Integrating Retrieval-Augmented Generation with Fine-Tuned TinyLlama for Domain-Specific Applications: Enhancing Data Sovereignty and Localised Compliance

by Kenneth Meng Yong Wong, Wei Jie Wong and Chi Wee Tan

Eng. Proc. 2026, 128(1), 6; https://doi.org/10.3390/engproc2026128006 - 6 Mar 2026

Viewed by 801

Abstract

Human resource (HR) departments in small and medium enterprises face challenges such as high operational costs, regulatory compliance, and routine task management, compounded by limited computing resources and data privacy concerns. To address these issues, we introduce a lightweight, on-premises language solution using [...] Read more.

Human resource (HR) departments in small and medium enterprises face challenges such as high operational costs, regulatory compliance, and routine task management, compounded by limited computing resources and data privacy concerns. To address these issues, we introduce a lightweight, on-premises language solution using a fine-tuned TinyLlama model integrated with a retrieval-augmented generation model for HR applications. Leveraging parameter-efficient methods, such as low-rank adaptation, the model shows excellent performance with a single graphics processing unit. The retrieval system is accurate in accessing local legal documents, complying with Malaysia’s regulations, while preserving data sovereignty. This approach provides SMEs with cost-effective, transparent, and scalable HR support. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 2656 KB

Open AccessProceeding Paper

New Variable-Structure Floating Linkage Mechanism

by Ren-Chung Soong

Eng. Proc. 2026, 128(1), 7; https://doi.org/10.3390/engproc2026128007 - 6 Mar 2026

Viewed by 281

Abstract

A new three-degree-of-freedom (3-DOF) variable-structure floating linkage mechanism is presented in this article. The proposed mechanism consists of six links, five revolute joints, and one rolling or sliding joint. In the mechanism, the fixed link of a traditional five-bar linkage and its adjacent [...] Read more.

A new three-degree-of-freedom (3-DOF) variable-structure floating linkage mechanism is presented in this article. The proposed mechanism consists of six links, five revolute joints, and one rolling or sliding joint. In the mechanism, the fixed link of a traditional five-bar linkage and its adjacent links serve as the driving links. The mechanism is a fully rotatable five-bar linkage relative to a fixed link. Depending on which links are driven, the mechanism’s structure transforms among four-bar linkage, five-bar linkage, floating four-bar linkage, and floating five-bar linkage. A key advantage of this mechanism is its adjustable structure and workspace, and its ability to solve all planar path generation and motion generation problems within a specified workspace. Structural and positional analysis results of the mechanism developed are presented in this article, along with examples and experimental validations demonstrating its feasibility for planar path and motion generation tasks. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

8 pages, 754 KB

Open AccessProceeding Paper

Intelligent Analysis and Prediction of Building Energy Consumption in Cloud Computing

by Lan Huang, Xiaoli Zhu and Xiangfeng Ren

Eng. Proc. 2026, 128(1), 8; https://doi.org/10.3390/engproc2026128008 - 9 Mar 2026

Viewed by 327

Abstract

We researched, analyzed and predicted building energy consumption data using cloud computing and constructed an intelligent model. A local outlier factor outlier discovery algorithm was created to monitor abnormal energy consumption. A random forest algorithm was used for high-dimensional data to predict building [...] Read more.

We researched, analyzed and predicted building energy consumption data using cloud computing and constructed an intelligent model. A local outlier factor outlier discovery algorithm was created to monitor abnormal energy consumption. A random forest algorithm was used for high-dimensional data to predict building energy consumption and analyze data in the Commercial Building Energy Consumption Survey database. The degree of importance of independent variables was evaluated to analyze how the architectural attributes of office buildings affect energy consumption. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

8 pages, 787 KB

Open AccessProceeding Paper

Production System Analysis and Scenario Development Using FlexSim: A Case-Based Study

by Stefani Prima Dias Kristiana, Vivi Triyanti, Nova Eka Budiyanta and Riana Magdalena Silitonga

Eng. Proc. 2026, 128(1), 9; https://doi.org/10.3390/engproc2026128009 - 9 Mar 2026

Viewed by 1039

Abstract

A production system comprises a series of interconnected processes involving planning, processing, and product distribution. The effectiveness and efficiency of such systems play a vital role in reducing operational costs, enhancing productivity, and improving product quality. As such, regular evaluation of production systems [...] Read more.

A production system comprises a series of interconnected processes involving planning, processing, and product distribution. The effectiveness and efficiency of such systems play a vital role in reducing operational costs, enhancing productivity, and improving product quality. As such, regular evaluation of production systems is essential to identify inefficiencies, waste, and bottlenecks, and to develop targeted strategies for improvement. This research aims to construct a simulation model of a production system using FlexSim software as a decision-support tool to facilitate performance evaluation and the development of scenario-based solutions. By employing a simulation-based approach, this study enables the analysis of the production process without interfering with actual operations, thereby minimizing associated risks and reducing the consumption of time and resources. Furthermore, simulation allows for virtual testing of various operational scenarios, including modifications in production capacity, workforce allocation, workflow configurations, and the implementation of emerging technologies. In this case study, the production process was predominantly constrained by operator waiting time, which constituted approximately 30% of the total processing time. In response, an alternative scenario was developed wherein operators with lower utilization rates were reassigned to workstations characterized by high operator wait times. The implementation of this scenario yielded a 29.5% reduction in average queue waiting time and a 31.7% decrease in total production time. These findings demonstrate a substantial improvement in production efficiency. Therefore, the outcomes of this study are expected to provide valuable insights for strategic decision-making and support the optimization of production systems in industrial environments. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 399 KB

Open AccessProceeding Paper

Modelling Helmet Manufacturing System Using Discrete Event Simulation

by Khoong Tai Wai, Wan Laailatul Hanim Mat Desa, Lim Li Li, Houng Chien Tan, Chan Ling Meng and Kumara Adji Kusuma

Eng. Proc. 2026, 128(1), 10; https://doi.org/10.3390/engproc2026128010 - 9 Mar 2026

Viewed by 603

Abstract

We simulated the manufacturing production line in a micro, small, and medium enterprise (MSME) to assess the efficiency of a helmet product organization, using ARENA simulation modelling software version 15.10.00000. The process and standard time for each process in the production line were [...] Read more.

We simulated the manufacturing production line in a micro, small, and medium enterprise (MSME) to assess the efficiency of a helmet product organization, using ARENA simulation modelling software version 15.10.00000. The process and standard time for each process in the production line were estimated from data provided by the enterprise’s management and direct observation. The enterprise line was engaged in six different processes to manufacture a singular product type. ARENA was used to analyse data. The simulation results showed an increase in workers’ utilization and reduced production duration for restructuring worker allocations, while maintaining a constant throughput rate. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 2909 KB

Open AccessProceeding Paper

Sea Turtle Recognition with Multiple Data Augmentation Methods Suitable for Marine Scenarios

by Yi-Chieh Hung, Jhih-Ya Chan, Wei-Cheng Lien, Yan-Tsung Peng and Li-Shu Chen

Eng. Proc. 2026, 128(1), 11; https://doi.org/10.3390/engproc2026128011 - 9 Mar 2026

Viewed by 539

Abstract

The sea turtle is an indicator organism used in marine conservation to identify the health status of ecosystems in various marine regions. In the past, researchers had to review an 8 h underwater video every day to monitor and count sea turtle appearances. [...] Read more.

The sea turtle is an indicator organism used in marine conservation to identify the health status of ecosystems in various marine regions. In the past, researchers had to review an 8 h underwater video every day to monitor and count sea turtle appearances. However, since sea turtles often appear for only short periods, traditional approaches of manual searching and counting require significant labor and time to ensure accurate periods of their appearance. To address this issue, we adopted the You Only Look Once (YOLO) model for object detection, utilizing real underwater videos captured from three different areas in the Taiwan Keelung City Chaojing Bay Aquatic Plants and Animals Conservation Area for training and testing. To overcome limitations, such as underwater blur, sediment interference, obstructions from other fish, and distant targets that are challenging to identify, we applied data augmentation techniques, including scaling, rotation, and depth blur, with labeled data of different fish species to improve generalization capability. The experimental results of this study showed that this method achieves a 99.4% accuracy in sea turtle detection. After 60 days of deployment across the three areas, the model reduced search time by over 99%, significantly improving efficiency and reducing workload. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

17 pages, 4034 KB

Open AccessProceeding Paper

Spatial Load Disparities in Cellular Networks: Integrating Geographic Information System, Minimum Spanning Tree, and Signal-Weighted K-Nearest Neighbor for Telkomsel Towers in Banten, Indonesia

by Riny Nurhajati, Fikri Armia Fahmi, Dava Ferdian Hadiputra, Ida Nurhaida and Edi Purwanto

Eng. Proc. 2026, 128(1), 12; https://doi.org/10.3390/engproc2026128012 - 6 Mar 2026

Viewed by 470

Abstract

The differential distribution of cellular towers of Telkomsel, Indonesia’s largest mobile network operator, in Banten Province, Indonesia, poses challenges to network performance and service reliability. Therefore, we developed a novel hybrid framework that integrates geographic information systems, minimum spanning tree modeling, and signal-weighted [...] Read more.

The differential distribution of cellular towers of Telkomsel, Indonesia’s largest mobile network operator, in Banten Province, Indonesia, poses challenges to network performance and service reliability. Therefore, we developed a novel hybrid framework that integrates geographic information systems, minimum spanning tree modeling, and signal-weighted k-nearest neighbor classification to assess tower utilization and signal coverage. Leveraging geospatial data from 110 Telkomsel cellular towers and 1000 simulated user nodes, it was found that 2.73% of towers were overloaded and 189 signal blank spots were identified in rural and topographically complex areas. By incorporating both spatial topology and signal strength sensitivity, the developed method outperforms conventional spatial or machine learning approaches in preserving spatial fidelity and supporting infrastructure planning. Despite the use of simulated user data, the framework demonstrates high scalability and adaptability for integration with real-time network performance metrics, enabling dynamic and location-specific telecommunication optimization. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 514 KB

Open AccessProceeding Paper

Predictive Analytics for Inventory Backorder Optimization Using Machine Learning

by Thean Pheng Lim, Shi Yean Wong, Wei Chien Ng and Guat Guan Toh

Eng. Proc. 2026, 128(1), 13; https://doi.org/10.3390/engproc2026128013 - 9 Mar 2026

Viewed by 858

Abstract

The need for effective inventory management in the transition from “Just-in-Time” to “Just-in-Case” supply chain strategies was addressed by developing a machine learning model to predict inventory backorders. Using a large store keeping unit dataset, five supervised learning algorithms, namely, logistic regression, random [...] Read more.

The need for effective inventory management in the transition from “Just-in-Time” to “Just-in-Case” supply chain strategies was addressed by developing a machine learning model to predict inventory backorders. Using a large store keeping unit dataset, five supervised learning algorithms, namely, logistic regression, random forest, k-nearest neighbours, Naïve Bayes, and gradient boosting, were implemented with Python 3.13 Data imbalance was managed using the synthetic minority over-sampling technique, while power transformation was applied to improve data distribution and model performance. Among the models, random forest demonstrated the highest prediction accuracy at 98% and a strong receiver operating characteristic score of 0.897, making it the best model for backorder prediction. This approach enhances supply chain resilience and proactive inventory control, enabling manufacturers to mitigate risks of stockouts and optimize resource planning. It is necessary to incorporate advanced balancing techniques, hyperparameter tuning, and cross-validation methods to improve predictive performance further. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 1273 KB

Open AccessProceeding Paper

Hexagonal Green Pavement Design Based on Digital Simulation for Sustainable Urban Drainage Optimization

by Hari Nugraha Ranudinata, Tri Nugraha Adikesuma, Frederik Josep Putuhena, Rizka Arbaningrum, Galih Wulandari Subagyo, Fredy Jhon Philip and Teddy Mohamad Darajat

Eng. Proc. 2026, 128(1), 14; https://doi.org/10.3390/engproc2026128014 - 9 Mar 2026

Viewed by 404

Abstract

The application of computational simulation in industrial engineering plays a critical role in designing sustainable infrastructure solutions. We applied a hexagonal green pavement system developed through digital simulation to address challenges in urban stormwater management. The system comprises an upper base layer that [...] Read more.

The application of computational simulation in industrial engineering plays a critical role in designing sustainable infrastructure solutions. We applied a hexagonal green pavement system developed through digital simulation to address challenges in urban stormwater management. The system comprises an upper base layer that bears structural loads and a lower support layer designed for water infiltration and drainage. Structural performance was evaluated using SolidWorks simulations under static loads of up to 1100 N. The results indicate that stress values remain within the material’s yield strength, ensuring structural reliability. Hydraulic performance was also assessed using various valve opening scenarios to simulate different rainfall intensities. The system demonstrated effective infiltration capability, with flow retardation coefficients ranging from 0.66 to 0.80. These findings validate the system’s potential to reduce surface runoff and mitigate urban flooding. The study results highlight how digital simulation, as part of a digital twin framework, can support the development of resilient, modular infrastructure for sustainable urban drainage. This approach represents a practical application of industrial engineering computation to advance smart and eco-friendly urban systems. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

11 pages, 575 KB

Open AccessProceeding Paper

Parameter-Efficient Adaptation of Qwen2.5 for Aspect-Based Sentiment Analysis Using Low-Rank Adaptation and Parameter-Efficient Fine-Tuning

by Pei Ying Lim, Chuk Fong Ho and Chi Wee Tan

Eng. Proc. 2026, 128(1), 15; https://doi.org/10.3390/engproc2026128015 - 9 Mar 2026

Viewed by 974

Abstract

Aspect-based sentiment analysis (ABSA) plays a vital role in deriving fine-grained sentiment from textual content. As large language models (LLMs) are increasingly adopted for automated data annotation in natural language processing (NLP), concerns have emerged regarding the accuracy of their outputs. Despite their [...] Read more.

Aspect-based sentiment analysis (ABSA) plays a vital role in deriving fine-grained sentiment from textual content. As large language models (LLMs) are increasingly adopted for automated data annotation in natural language processing (NLP), concerns have emerged regarding the accuracy of their outputs. Despite their capacity to generate large volumes of labeled data, LLMs often suffer from overconfidence in predictions, high uncertainty in complex contexts, and difficulty capturing nuanced meanings, which compromise the quality of annotations and, in turn, the performance of downstream models. This underscores the need to enhance LLM adaptability while maintaining annotation accuracy. To address these limitations, we integrated low-rank adaptation (LoRA) with parameter-efficient fine-tuning (PEFT) for adapting Qwen2.5 to ABSA. LoRA reduces the number of trainable parameters by decomposing weight updates into low-rank matrices, while PEFT introduces modular adapter layers with scaled gradient updates and dynamic rank allocation. Using the standard SemEval 2014 Laptop dataset, Qwen2.5-3B fine-tuned with LoRA and PEFT achieves 64.50% accuracy, outperforming its baseline of 24.05%. Likewise, Qwen2.5-7B attains 77.50%, compared with a baseline of 34.63%. These results highlight the potential of parameter-efficient methods to improve the accuracy of LLMs in ABSA annotation tasks, especially under resource constraints. Such results lay the groundwork for scalable, reproducible LLM deployment and open avenues for future research in cross-domain adapter transferability and dynamic rank optimization. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 1532 KB

Open AccessProceeding Paper

Optimizing Steaming Line Layout for Manufacturing Plant Using ProModel Simulation

by Mark Lexter Reyes, Klint Allen Mariñas, Rene Estember, Michael Nayat Young and Rachel C. Villanueva

Eng. Proc. 2026, 128(1), 16; https://doi.org/10.3390/engproc2026128016 - 10 Mar 2026

Viewed by 461

Abstract

Plant layout significantly influences manufacturing performance by optimizing the placement of machines and resources to enhance output and minimize operational costs. We redesigned the layout for the steaming line of a food manufacturing facility to improve line efficiency and labor productivity without compromising [...] Read more.

Plant layout significantly influences manufacturing performance by optimizing the placement of machines and resources to enhance output and minimize operational costs. We redesigned the layout for the steaming line of a food manufacturing facility to improve line efficiency and labor productivity without compromising product quality. We used the define-measure-analyze-design-verify six sigma methodology to identify problems and develop solutions. Layout modifications were validated using ProModel 2016. Results demonstrated reduced process bottlenecks and improved workflow. The results offered actionable insights into food manufacturing and similar industries, promoting the adoption of data-driven, technology-enabled approaches to enhance operational efficiency and productivity. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 195 KB

Open AccessProceeding Paper

Failure Mode and Its Effects on Enhancing Operational Reliability in Water-Treatment Facilities: A Case Study of Regional Public Water Company

by Debrina Puspita Andriani, Imam Santoso, Sabrina Mujahidah and Muhammad Rizki Ardiansah

Eng. Proc. 2026, 128(1), 17; https://doi.org/10.3390/engproc2026128017 - 10 Mar 2026

Viewed by 663

Abstract

Access to safe and reliable drinking water is essential for public health. However, regional public water companies often face challenges that compromise service quality, such as equipment failure, water contamination, and inconsistent treatment processes. This study applies the failure mode and effects analysis [...] Read more.

Access to safe and reliable drinking water is essential for public health. However, regional public water companies often face challenges that compromise service quality, such as equipment failure, water contamination, and inconsistent treatment processes. This study applies the failure mode and effects analysis (FMEA) method to systematically identify, evaluate, and prioritize operational risks in a water treatment facility. By analyzing 17 potential failure modes across the treatment process, five modes were classified as critical, prompting targeted mitigation strategies. The results demonstrate FMEA’s effectiveness in enhancing reliability and supporting continuous improvement efforts in water treatment operations. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

7 pages, 378 KB

Open AccessProceeding Paper

Optimizing Document Interaction Using Large Language Models by Integrating Retrieval-Augmented Generation, Facebook AI Similarity Search, and Human-like Performance Metrics

by Edwina Hon Kai Xin, Zhi Wei Tan, Ling Hue Wee and Chi Wee Tan

Eng. Proc. 2026, 128(1), 18; https://doi.org/10.3390/engproc2026128018 - 10 Mar 2026

Viewed by 492

Abstract

We developed an intelligent conversational system that enhances document interaction using advanced language models and embedding techniques. The system integrates retrieval-augmented generation, Facebook AI similarity search-based retrieval, and cosine similarity for efficient information extraction from Portable Document Format documents. It employs three embedding [...] Read more.

We developed an intelligent conversational system that enhances document interaction using advanced language models and embedding techniques. The system integrates retrieval-augmented generation, Facebook AI similarity search-based retrieval, and cosine similarity for efficient information extraction from Portable Document Format documents. It employs three embedding models, namely All-MiniLM L6 v2, All-MPNet Base v2, and Instructor Large, with three large language models including LLaMA 3.3 70B, Gemma 2-9B IT, and Mixtral 8x7B-32768. System performance is evaluated using ROUGE-1, BERTScore, and a novel human-like performance (HLP) metric, showing improved retrieval accuracy, response coherence, and efficiency for academic and enterprise applications. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 2733 KB

Open AccessProceeding Paper

Mild Cognitive Impairment Identification System Based on Physiological Characteristics and Interactive Games

by Ming-An Chung, Zhi-Xuan Zhang, Jun-Hao Zhang, Chia-Chun Hsu, Yi-Ju Yao, Jin-Hong Chou, Ming-Chun Hsieh, Sung-Yun Chai, Shang-Jui Huang, Kai-Xiang Chen, Chia-Wei Lin and Pin-Han Chen

Eng. Proc. 2026, 128(1), 19; https://doi.org/10.3390/engproc2026128019 - 10 Mar 2026

Viewed by 1268

Abstract

As the global aging population increases, the early detection and prevention of Alzheimer’s disease (AD) have become important in public health. To solve the problems of subjectivity and low timeliness of traditional assessment methods, this paper proposes a multimodal dementia prevention system that [...] Read more.

As the global aging population increases, the early detection and prevention of Alzheimer’s disease (AD) have become important in public health. To solve the problems of subjectivity and low timeliness of traditional assessment methods, this paper proposes a multimodal dementia prevention system that combines physiological sensing, a gamification interface, and a classification model. The system includes an interactive joystick to measure pulse and blood pressure. A Chinese music game app increases the participation of the elderly and reduces their sense of rejection through gamification interaction. After the physiological data were standardized by Z-score, they were input into three small sample classifiers (Gaussian Naïve Bayes, Fisher Linear Discriminant Analysis, and Logistic Regression) for the binary classification of AD. The system performance was evaluated using the Leave-One-Out cross-validation method. Experimental results show that Logistic Regression performed best in situations with extremely small samples and class imbalance, with an F1-score of 0.700, which was higher than the other two. Dynamic features and model fusion technologies need to be integrated to further enhance the clinical application potential of the system in the early prediction of dementia. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 924 KB

Open AccessProceeding Paper

Multi-Class Electroencephalography Motor Imagery Classification of Limb Movements Using Convolutional Neural Network

by Yean Ling Chan, Yiqi Tew, Ching Pang Goh and Choon Kit Chan

Eng. Proc. 2026, 128(1), 20; https://doi.org/10.3390/engproc2026128020 - 11 Mar 2026

Viewed by 576

Abstract

We classified essential motor actions, dorsal and plantar flexion (lower limb), and arm movement (upper limb) from electroencephalography (EEG)-based brain–computer interface (BCI) signals, using a convolutional neural network (CNN). Different from previous research on upper or lower limb motor imagery in isolation, we [...] Read more.

We classified essential motor actions, dorsal and plantar flexion (lower limb), and arm movement (upper limb) from electroencephalography (EEG)-based brain–computer interface (BCI) signals, using a convolutional neural network (CNN). Different from previous research on upper or lower limb motor imagery in isolation, we integrated both categories in a unified framework to explore a broader range of movements for broader applications. These motor actions are fundamental to daily activities such as walking, running, maintaining balance, lifting, reaching, and exercising. Upper limb EEG data were provided by INTI International University, whereas lower limb data were obtained from a publicly available dataset, recorded using 16-channel Emotiv and OpenBCI systems, respectively, each with distinct sampling rates and signal formats. To improve signal quality and facilitate joint model training, all signals were downsampled to 125 Hz, standardized to 16 channels, segmented using sliding windows, normalized via StandardScaler, and labelled according to action class. The processed data were used to train a CNN model configured with a kernel size of 3 and rectified linear unit activation functions. Training was terminated early at epoch 11 using an early stopping strategy, resulting in approximately 67% accuracy for both training and validation sets. Although this accuracy was moderate for deep learning, a promising outcome for EEG-based multi-class motor imagery classification was obtained, with the challenges posed by limited data availability, low inter-class feature discriminability, and the inherently noisy nature of non-invasive EEG signals. The results of this study underscore the potential of CNN-based models for future real-time BCI applications. By expanding the dataset, deep learning architectures can be refined to improve signal preprocessing techniques. Prosthetic devices need to be integrated to validate the system in practical scenarios. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 963 KB

Open AccessProceeding Paper

Analysis of Self-Checkout Operations of Taiwanese Retail Store: A Simulation Modeling Approach

by Victor James C. Escolano, Shang-Yun Lin and Wei-Jung Shiang

Eng. Proc. 2026, 128(1), 21; https://doi.org/10.3390/engproc2026128021 - 12 Mar 2026

Viewed by 783

Abstract

Checkout service is crucial in ensuring customer satisfaction and enhancing retail efficiency. In recent years, self-checkout has become increasingly popular in modern retail operations. However, despite its growing adoption, there is limited quantitative evidence on its effectiveness in reducing operational costs and improving [...] Read more.

Checkout service is crucial in ensuring customer satisfaction and enhancing retail efficiency. In recent years, self-checkout has become increasingly popular in modern retail operations. However, despite its growing adoption, there is limited quantitative evidence on its effectiveness in reducing operational costs and improving overall efficiency. In this study, a discrete-event simulation model based on real-world scenarios of a retail store in Taoyuan City, Taiwan, was developed using ARENA (version 16) simulation software. Four checkout scenarios were modeled and compared through statistical tests to evaluate checkout performance. The results showed that the proposed self-checkout model with improved service time enhanced operational efficiency and contributed to reducing operational costs. These findings suggest that retail managers should implement strategic measures to optimize self-checkout operations to achieve efficient and cost-effective store performance. Finally, practical and managerial implications are discussed at the end of the study. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

8 pages, 224 KB

Open AccessProceeding Paper

Evaluation of Healthcare Waste Treatment Methods Using Multiple Criteria

by Richard Li, Nicklaus Dionisio, Aizel Lee and Megan Daryl Sio

Eng. Proc. 2026, 128(1), 22; https://doi.org/10.3390/engproc2026128022 - 12 Mar 2026

Viewed by 408

Abstract

Hospitals generating waste daily need to identify efficient, cost-effective, and sustainable alternatives to conventional disposal methods. Therefore, we formulated a mathematical model to evaluate emerging healthcare waste treatment (HCW) methods by developing a multiple-criteria framework. The framework enables an evidence-based evaluation that supports [...] Read more.

Hospitals generating waste daily need to identify efficient, cost-effective, and sustainable alternatives to conventional disposal methods. Therefore, we formulated a mathematical model to evaluate emerging healthcare waste treatment (HCW) methods by developing a multiple-criteria framework. The framework enables an evidence-based evaluation that supports better HCW management-related decisions in resource-limited settings. Results found that ozone is the optimal method for hospitals with a waste profile mostly made up of infectious and pathological wastes. Methods such as promession, for stricter environmental priorities, and superheated steam, for better performance on all evaluation criteria, may be preferred if hospital priorities shift. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

8 pages, 1580 KB

Open AccessProceeding Paper

Effect of Design Styles of User Interface on User Experience

by Patricia Jasmin Baluyot, Ken Roi Ramos, Christian Adrian Tan, Raphael Iñaki Valenzuela, Charmine Saflor-Balmes and Ezekiel Bernardo

Eng. Proc. 2026, 128(1), 23; https://doi.org/10.3390/engproc2026128023 - 12 Mar 2026

Viewed by 1015

Abstract

User interfaces (UIs) have become prevalent and dominant to maximize overall user experience. In order to enhance UI design, the effects of their base properties must be mapped out. Therefore, we constructed a structural equation model, considering the direct effects of design properties [...] Read more.

User interfaces (UIs) have become prevalent and dominant to maximize overall user experience. In order to enhance UI design, the effects of their base properties must be mapped out. Therefore, we constructed a structural equation model, considering the direct effects of design properties and the mediating effects of user performance, with the specific goal of maximizing the UI for users. A total of thirty-six participants were surveyed with different random combinations of UIs while using an eye tracker and measuring their final perception. Significant direct, mediating, and moderating effects were found in this study. Design guidelines were made for maximizing user experience in this study. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 706 KB

Open AccessProceeding Paper

AI-Driven Predictive Analytics for Kapok Supply Chain Governance

by Nila Firdausi Nuzula and Sopyan

Eng. Proc. 2026, 128(1), 24; https://doi.org/10.3390/engproc2026128024 - 12 Mar 2026

Viewed by 512

Abstract

The kapok (Ceiba pentandra) fiber industry plays a vital role in Indonesia’s rural bioeconomy, particularly in regions with high production intensity such as Pasuruan Regency. Despite its economic potential and alignment with the green economy agenda, the industry faces increasing volatility [...] Read more.

The kapok (Ceiba pentandra) fiber industry plays a vital role in Indonesia’s rural bioeconomy, particularly in regions with high production intensity such as Pasuruan Regency. Despite its economic potential and alignment with the green economy agenda, the industry faces increasing volatility due to seasonal harvest cycles, climate-induced disruptions, global demand fluctuations, and exchange rate instability. These conditions necessitate an adaptive and predictive approach to supply chain risk governance. We evaluated the performances of predictive analytics models, including linear regression, random forest, gradient boosting, XGBoost 3.2.0 libraries, K-nearest neighbors, and stacking regressor. Using multi-year monthly data on production volume, residual stock, and exchange rates, the stacking regressor was the most accurate model, achieving the lowest root mean square error and highest R² values. The results bridge the gap by applying predictive analytics to a resource-based, seasonal small industry sector. Practically, the results also enable leveraging AI in strengthening the long-term sustainability of agribusiness supply chains. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 2762 KB

Open AccessProceeding Paper

AdjusTABLE: Improved Attachable, Height-Adjustable, and Portable Wheelchair Tray

by Cheryl Patricia C. Uy, Kiersten Dominique L. Hing, Riana Nadine E. Santiago, Ruzel Khyvin Marc J. Te, Anicka Beatriz H. Teves, Mateo Q. Urera, Jazmin Tangsoc and Ezekiel Bernardo

Eng. Proc. 2026, 128(1), 25; https://doi.org/10.3390/engproc2026128025 - 12 Mar 2026

Viewed by 500

Abstract

Ensuring accessibility for wheelchair users is essential in promoting inclusivity and equal opportunities, yet challenges remain, especially regarding infrastructure and public furniture. One common issue is the incompatibility of standard public tables with wheelchair heights, which often results in discomfort or discourages use. [...] Read more.

Ensuring accessibility for wheelchair users is essential in promoting inclusivity and equal opportunities, yet challenges remain, especially regarding infrastructure and public furniture. One common issue is the incompatibility of standard public tables with wheelchair heights, which often results in discomfort or discourages use. While various wheelchair trays have been introduced, many lack stability, ergonomic design, and ease of attachment. To address these shortcomings, we developed AdjusTABLE—a portable, height-adjustable, and foldable tray designed with ergonomic comfort and user convenience. Using empathy maps and focus group discussions, we created a tray that holds drinks, pens, phones, and personal belongings, improving usability and independence. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 1884 KB

Open AccessProceeding Paper

Smart Community Energy Forecasting and Management System Based on Two-Layer Model Architecture

by Ming-An Chung, Jun-Hao Zhang, Zhi-Xuan Zhang, Chia-Chun Hsu, Yi-Ju Yao, Jin-Hong Chou, Pin-Han Chen, Ming-Chun Hsieh, Chia-Wei Lin, Yun-Han Shen and Rui-Qun Liu

Eng. Proc. 2026, 128(1), 26; https://doi.org/10.3390/engproc2026128026 - 12 Mar 2026

Viewed by 498

Abstract

Here, we develop a digital community management application (APP) and an energy prediction and analysis system for smart communities. The system integrates the internet of things (IoT) technology and multiple prediction models to improve the intelligence and automation of community energy management. The [...] Read more.

Here, we develop a digital community management application (APP) and an energy prediction and analysis system for smart communities. The system integrates the internet of things (IoT) technology and multiple prediction models to improve the intelligence and automation of community energy management. The developed APP has the following functions: user classification, announcement notification, express delivery management, GPS positioning navigation, calendar, and energy forecast. The hardware architecture of the system consists of a voltage/current sensing module, a Wireless Fidelity (Wi-Fi) module, and an Arduino platform, allowing real-time feedback and display of power consumption data. The energy forecasting part proposes a two-layer hybrid model architecture. This architecture combines Seasonal Trend decomposition using Loess (STL) time series decomposition, extreme gradient boosting (XGBoost), and Seasonal Autoregressive Integrated Moving Average (SARIMA) models to predict residential electricity consumption trends over the next 3 years. The results of the model prediction are verified using the data on Taiwan’s electricity consumption. The model accurately predicts the average monthly residential electricity consumption with a relative error of 5.8%, an acceptable energy management accuracy. This system integrates APP applications and efficient prediction models, demonstrating its great potential in smart community energy management and enhanced resident interaction. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 1774 KB

Open AccessProceeding Paper

Three-Dimensional Simulation Framework of a Vision-Based Autonomous System for Unmanned Underwater Vehicle

by Muhammad Ikhsan Suryadarma and Yuda Apri Hermawan

Eng. Proc. 2026, 128(1), 27; https://doi.org/10.3390/engproc2026128027 - 12 Mar 2026

Viewed by 766

Abstract

In training vision-based autonomous system algorithms, simulation plays a pivotal role in enhancing and expediting system recognition and development. However, creating a realistic virtual underwater environment is particularly difficult. To address the need for advanced control system modeling, we developed an integrated simulation [...] Read more.

In training vision-based autonomous system algorithms, simulation plays a pivotal role in enhancing and expediting system recognition and development. However, creating a realistic virtual underwater environment is particularly difficult. To address the need for advanced control system modeling, we developed an integrated simulation framework that combines a 3D computer graphics engine, Unreal Engine, with Simulink. This integration facilitates the design and visualization of complex control systems. The framework was evaluated using an autonomous system tasked with tracking underwater cables, employing YOLO-based object detection for visual guidance. The results demonstrate the effectiveness of the proposed simulation environment in accurately replicating the behavior of vision-based autonomous systems operating in underwater conditions. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 242 KB

Open AccessProceeding Paper

Airline Crew Scheduling Using Fatigue-Score-Based Optimization Model for Minimizing Pilot Fatigue

by Johann David Ong, Eliana Patricia Buhain, Xander Ilmedo, Richard Li, Nicole Lopez and Ingrid Matias

Eng. Proc. 2026, 128(1), 28; https://doi.org/10.3390/engproc2026128028 - 12 Mar 2026

Viewed by 1006

Abstract

Pilot fatigue, driven by irregular schedules and long duty hours, remains a major aviation concern. This study aims to minimize pilot fatigue and optimize crew scheduling through a mixed integer linear programming model, considering flight duration, rest periods, fatigue thresholds, and regulations. The [...] Read more.

Pilot fatigue, driven by irregular schedules and long duty hours, remains a major aviation concern. This study aims to minimize pilot fatigue and optimize crew scheduling through a mixed integer linear programming model, considering flight duration, rest periods, fatigue thresholds, and regulations. The optimized 7-day schedule minimized pilot fatigue, reflecting effective management and workload balance. Scenario analysis results showed that reducing rest hours was infeasible, while adding flights required more pilots. The results confirmed the model’s effectiveness in enhancing safety and ensuring balanced workloads, highlighting the need for adequate pilot resources under increasing operational demands. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

6 pages, 348 KB

Open AccessProceeding Paper

Optimizing Fleet Composition for Electric Vehicle Integration: A Case Study in the Philippines

by Lance Gabriel O. Ramos, Liam Alec M. Rapada, Dennis L. Umlas and Yoshiki B. Kurata

Eng. Proc. 2026, 128(1), 29; https://doi.org/10.3390/engproc2026128029 - 13 Mar 2026

Viewed by 562

Abstract

As the Philippines aims to electrify its vehicle fleet by 2030, it seeks to be a leading example for other government agencies adopting electric and hybrid electric vehicles. This study addresses the challenge of optimizing budget allocation to support this transition under fiscal [...] Read more.

As the Philippines aims to electrify its vehicle fleet by 2030, it seeks to be a leading example for other government agencies adopting electric and hybrid electric vehicles. This study addresses the challenge of optimizing budget allocation to support this transition under fiscal constraints. A hybrid decision-making approach is employed, integrating the analytic hierarchy process (AHP) and linear programming (LP) to guide procurement strategy. AHP is used to establish a hierarchy of decision criteria, and LP is used to translate these into the most favorable outcome constrained by budget limitations. This framework supports rational and criteria-driven decision-making for public fleet planning. The resulting model enables the Philippines to maximize the impact of electrification while adhering to financial and operational constraints. The findings contribute to policy-oriented planning models that align sustainability goals with real-world budgetary conditions. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 2677 KB

Open AccessProceeding Paper

From Manual to Intelligence: Enhancing Electricity Meter Accuracy Using Computer Vision

by Ida Nurhaida, Muhammad Mughni Firdaus and Edi Purwanto

Eng. Proc. 2026, 128(1), 30; https://doi.org/10.3390/engproc2026128030 - 13 Mar 2026

Viewed by 543

Abstract

This article presents a digit detection system for analogue electricity meters using the YOLOv9 algorithm integrated with EasyOCR. One hundred thirty-seven images from Plaza XYZ were used for training and testing, with an accuracy of 89.8%. The system enables real-time detection and export [...] Read more.

This article presents a digit detection system for analogue electricity meters using the YOLOv9 algorithm integrated with EasyOCR. One hundred thirty-seven images from Plaza XYZ were used for training and testing, with an accuracy of 89.8%. The system enables real-time detection and export of meter readings, significantly reducing human error and recording time. The user-friendly interface allows technicians to upload images, detect digits, and export results to Microsoft Excel or CSV format. These findings demonstrate the model’s readiness for commercial deployment and advance the development of computer vision applications in energy management. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 890 KB

Open AccessProceeding Paper

Extreme Rainfall Analysis and Return Period Estimation Based on Extreme Value Theory

by Jieling Wu

Eng. Proc. 2026, 128(1), 31; https://doi.org/10.3390/engproc2026128031 - 13 Mar 2026

Viewed by 956

Abstract

Climate change has resulted in frequent extreme weather events such as heavy rainfall and heat waves in Japan, making accurate forecasting and countermeasures an urgent issue. Therefore, it is urgently required to analyze the statistical characteristics of extreme rainfall events using the extreme [...] Read more.

Climate change has resulted in frequent extreme weather events such as heavy rainfall and heat waves in Japan, making accurate forecasting and countermeasures an urgent issue. Therefore, it is urgently required to analyze the statistical characteristics of extreme rainfall events using the extreme value theory (EVT). The generalized extreme value (GEV) distribution, a core model for EVT, was applied in this study to rainfall data collected in Kakunodate, Akita Prefecture, Japan, spanning May 1976 to December 2023. The analysis results confirm the presence of extreme rainfall events. Through model fitting, the GEV parameters representing location, scale, and shape were accurately estimated. The model demonstrated a good fit, particularly for moderate-intensity rainfall. However, notable uncertainties emerged in the prediction of the most extreme events. Return period analysis results indicated that extreme rainfall events occur at intervals ranging from 2 to 100 years, suggesting the necessity of incorporating safety margins into long-term forecasting frameworks. Considering the increasing frequency of such events, cross-validation with alternative statistical methods and the potential adoption of non-smooth GEV models are recommended to enhance predictive reliability. Overall, the results of this study highlight the need for adaptive and flexible revisions to infrastructure design criteria in response to evolving patterns of extreme weather. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

19 pages, 8824 KB

Open AccessProceeding Paper

High Selectivity of Dipeptidyl Peptidase 4 Receptor Towards 13 Aromatic Compounds in Cinnamomi ramulus Extract: Molecular Docking and Molecular Dynamics

by Vo Van On, Ho Anh Kiet, Nguyen Thi Thanh Thao and Nguyen Thi Lien Thuong

Eng. Proc. 2026, 128(1), 32; https://doi.org/10.3390/engproc2026128032 - 13 Mar 2026

Viewed by 479

Abstract

Dipeptidyl peptidase 4 (DPP4) plays a pivotal role in the treatment of type 2 diabetes as an important glucose-regulating enzyme. We evaluated the molecular interactions between 13 major aromatic compounds from Cinnamomi ramulus and DPP4 enzyme through molecular docking simulation and molecular dynamics. [...] Read more.

Dipeptidyl peptidase 4 (DPP4) plays a pivotal role in the treatment of type 2 diabetes as an important glucose-regulating enzyme. We evaluated the molecular interactions between 13 major aromatic compounds from Cinnamomi ramulus and DPP4 enzyme through molecular docking simulation and molecular dynamics. The results showed that the studied compounds exhibited a wide range of docking energies with DPP4, in which benzyl benzoate was the most promising compound with a docking energy of −7.4 kcal/mol, which was comparable with that of saxagliptin and alogliptin. Detailed analysis revealed that hydrophobic interactions (three–eight interactions/complex) and hydrogen bonds (three–five bonds in some complexes) played major roles in stabilizing the complexes. Molecular dynamics simulation results demonstrated ligand selectivity for the DPP4 receptor, with only four out of 13 tested compounds stabilizing at the interaction site. Evaluation results of the method using Lipinski’s rule showed that all compounds met four–five criteria for drug-likeness, indicating potential for drug development. These results provide the first scientific evidence of the potential molecular mechanism of cinnamon bark in the treatment of type 2 diabetes through DPP4 inhibition. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 654 KB

Open AccessProceeding Paper

Common Vulnerabilities and Exposure Data Analysis and Visualization: Building Cybersecurity Awareness and Validating Risks

by Chin-Ling Chen, Zhen-Hong Peng, Ling-Chun Liu and Chin-Feng Lee

Eng. Proc. 2026, 128(1), 33; https://doi.org/10.3390/engproc2026128033 - 13 Mar 2026

Viewed by 566

Abstract

Cybersecurity vulnerabilities are rapidly increasing, but public understanding and awareness remain limited. Since most vulnerabilities are common, they continue to exist and to be exploited. Although there are tools, including the Open Worldwide Application Security project and the common weakness enumeration method, that [...] Read more.

Cybersecurity vulnerabilities are rapidly increasing, but public understanding and awareness remain limited. Since most vulnerabilities are common, they continue to exist and to be exploited. Although there are tools, including the Open Worldwide Application Security project and the common weakness enumeration method, that provide extensive information on known security problems, their information is not structured and visually shown. The tools are ineffective in speed assessment and response. We analyzed large-scale common vulnerabilities and exposures JavaScript object notation datasets to recognize key threats, to understand the underlying cause of data breaches, and to analyze vulnerability trends. Implementing keyword gate-filling techniques and better data visualization enhances the clarity and usefulness of vulnerability information. These tools enable stakeholders to make quicker and more informed decisions and implement stronger encryption and defensive measures. Finally, the results of this study lead to broad awareness, active security, and a reactive strategy to evolving cyber threats that simplifies both governmental and average-day user recognition and response to emerging attack patterns and risks across digital platforms. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

12 pages, 2509 KB

Open AccessProceeding Paper

Multi-Level Feature-Matching System for Counterfeit Seal Image Recognition

by Tsung-Yueh Lai, I-Chau Wang, Yin-Kuan Lee, Wei-Cheng Lien, Yan-Tsung Peng, Kuan-Chun Chen, Yuan-Te Chen, Ya-Ping Chuang, Yu-Ping Cheng, Ya-Chi Lin and Pei-Hung Shie

Eng. Proc. 2026, 128(1), 34; https://doi.org/10.3390/engproc2026128034 - 12 Mar 2026

Viewed by 550

Abstract

As document forgery schemes become increasingly sophisticated, organizations face mounting challenges in authenticating seals found on official documents. In this study, we collaborated with law enforcement agencies in Taiwan to develop an AI-driven system that supports the rapid identification of forged seals. Instead [...] Read more.

As document forgery schemes become increasingly sophisticated, organizations face mounting challenges in authenticating seals found on official documents. In this study, we collaborated with law enforcement agencies in Taiwan to develop an AI-driven system that supports the rapid identification of forged seals. Instead of relying on manual inspection, the system leverages deep neural networks to analyze overall and fine visual features of seal images. By integrating advanced image enhancement, similarity measurement, and feature comparison modules, the system efficiently filters and ranks potential matches from a dedicated police database. Evaluation on a dataset containing several hundred forged seal images demonstrates that the system achieves greater than 90% accuracy for detecting counterfeit seals. The solution not only reduces the time and effort required for verification but also provides investigators with immediate access to relevant case histories, thereby strengthening the overall fraud prevention workflow. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

14 pages, 2108 KB

Open AccessProceeding Paper

Recognition of Knee Osteoarthritis Using Deep Learning: A Review

by Dilan Jameel Sulaiman and Baraa Wasfi Salim

Eng. Proc. 2026, 128(1), 35; https://doi.org/10.3390/engproc2026128035 - 16 Mar 2026

Viewed by 1007

Abstract

Knee osteoarthritis is one of the most common disorders and afflicts millions of patients, particularly in older age groups. The degenerative joint disease significantly compromises the quality of life through disability. We explore the various deep learning and machine learning techniques to classify [...] Read more.

Knee osteoarthritis is one of the most common disorders and afflicts millions of patients, particularly in older age groups. The degenerative joint disease significantly compromises the quality of life through disability. We explore the various deep learning and machine learning techniques to classify knee osteoarthritis using convolutional neural networks. We examined the validity and limitations of the recent studies with multivariate classification of knee osteoarthritis using magnetic resonance imaging and X-ray data. Diagnosis accuracy improves with machine learning techniques, and transfer learning in particular leads to better diagnosis and earlier detection, which subsequently yields better patient outcomes. There are challenges to be addressed, such as dataset bias and model interpretability, which need to be further investigated for more promising results. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 294 KB

Open AccessProceeding Paper

Application of Analytic Hierarchy Process for Evaluating Service Quality of Subscription Video on Demand Services Based on Weighted Values in the Philippines

by Maria Sabrina Cantos, Nathan Tyler Quach, Sean Bradley Ruy, Patricia Santiago, Richard Li and Madeline Tee

Eng. Proc. 2026, 128(1), 36; https://doi.org/10.3390/engproc2026128036 - 16 Mar 2026

Viewed by 431

Abstract

Streaming services have gained popularity due to their vast content library and convenience. To ensure continued patronage, service quality measurement is important. In this study, we ranked and determined how to maintain the competitiveness of streaming services using the analytic hierarchy process. Using [...] Read more.

Streaming services have gained popularity due to their vast content library and convenience. To ensure continued patronage, service quality measurement is important. In this study, we ranked and determined how to maintain the competitiveness of streaming services using the analytic hierarchy process. Using focus group discussions and questionnaire administration, Netflix was found to have the highest perceived service quality, as measured by the consistency ratio and rating scales. Content library, quality of experience, and system availability were the top three service quality dimensions, while the top three sub-dimensions were quality of content, frequency of video freezing, and picture quality. These results allow companies to adjust their service strategies to suit the Philippine market. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

12 pages, 3058 KB

Open AccessProceeding Paper

AI Facial Acupuncture Point Interactive Voice Health Care Teaching System

by Wen-Cheng Chen, Yu-Hsuan Chen, Yu-Hsing Chen, Jiu-Wen Wang, Hung-Jen Chen and Jr-Wei Tsai

Eng. Proc. 2026, 128(1), 37; https://doi.org/10.3390/engproc2026128037 - 16 Mar 2026

Viewed by 967

Abstract

We developed an AI-based system for facial acupoint recognition and healthcare support, integrating MediaPipe facial and hand tracking technologies to address the problems of inaccurate and non-standardized acupoint identification in traditional Chinese medicine (TCM). By leveraging facial landmark detection and fingertip tracking, the [...] Read more.

We developed an AI-based system for facial acupoint recognition and healthcare support, integrating MediaPipe facial and hand tracking technologies to address the problems of inaccurate and non-standardized acupoint identification in traditional Chinese medicine (TCM). By leveraging facial landmark detection and fingertip tracking, the system enables accurate localization of facial acupoints to ensure precise stimulation. The system contributes to the standardization of acupoint recognition, intelligent health consultation, and the digital transformation of TCM practices. Further enhancements are necessary by expanding acupoint recognition to other body parts (e.g., ears, hands, feet, and back) and integrating with wearable devices to further promote personalized and precise TCM healthcare. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

12 pages, 1413 KB

Open AccessProceeding Paper

Comparison and Optimization of Intelligent Control for a Two-Link Robot Manipulator

by Chia-Chen Fang and Shuo-Feng Chiu

Eng. Proc. 2026, 128(1), 38; https://doi.org/10.3390/engproc2026128038 - 16 Mar 2026

Viewed by 532

Abstract

We investigate the control of a two-link robot manipulator through the application of sliding mode control (SMC), proportional–integral–derivative (PID) control, and their hybrid control strategy. Firstly, a mathematical model incorporating nonlinear coupling effects is derived based on the Lagrangian method. Then, SMC, PID, [...] Read more.

We investigate the control of a two-link robot manipulator through the application of sliding mode control (SMC), proportional–integral–derivative (PID) control, and their hybrid control strategy. Firstly, a mathematical model incorporating nonlinear coupling effects is derived based on the Lagrangian method. Then, SMC, PID, and hybrid controllers are compared based on disturbance rejection, stability, and time-domain responses. In addition, a genetic algorithm (GA) is employed for PID parameter optimization, improving system performance and efficiency. Overall, the PID-SMC controller achieves an effective balance between stability and response tracking accuracy. The results of this study provide a reference for control strategy development in robotic systems, aligning with smart manufacturing applications. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

9 pages, 480 KB

Open AccessProceeding Paper

Design of an STM32 Coaxial Cable Length and Terminal Load Monitoring System

by Chuan Yang, Wenge Huang and Shulin Yu

Eng. Proc. 2026, 128(1), 39; https://doi.org/10.3390/engproc2026128039 - 16 Mar 2026

Viewed by 637

Abstract

Coaxial cable plays a vital role in the wide application of telecommunications, network, and television broadcasting and other fields, with its transmission performance directly affecting signal quality and transmission efficiency. In practical applications, the length of the cable and the terminal load state [...] Read more.

Coaxial cable plays a vital role in the wide application of telecommunications, network, and television broadcasting and other fields, with its transmission performance directly affecting signal quality and transmission efficiency. In practical applications, the length of the cable and the terminal load state of the connection often affect the stability of the signal. In order to solve this problem, we used STMicroelectronics STM32F407VET6 (STMicroelectronics, Geneva, Switzerland) as the master controller in this system, and deduced the length of the cable by analyzing the functional relationship between the length of the cable and the open circuit frequency. An open cable is regarded as a capacitor, and any two core wires are regarded as two plates of a flat capacitor. The linear relationship between open frequency and length is used to detect the length of the coaxial cable. The system then determines whether the terminal load is capacitance or resistance based on the detected frequency. If no frequency is detected, then the load is considered resistance. The system detects the resistance value of the resistor through series voltage division. If a frequency is detected, this indicates that the load is capacitance. At this time, the system uses an RC oscillation circuit composed of HGSEMI ICL8038 (Huagao Semiconductor Co., Ltd., Wuxi, China) for testing, and provides the phase shift required by the corresponding signal through the RC network, so as to detect the capacitance value. Finally, we successfully designed a coaxial cable length and terminal load detection system based on STM32F407VET6. Through this system, the user can accurately understand the length of the coaxial cable and the load of the connection terminal, which provides a reliable guarantee for the stability of signal transmission. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 421 KB

Open AccessProceeding Paper

Scenario-Based Simulation for Evaluating Trade-Offs Among Efficiency, Effectiveness, and Equity in Emergency Response Routing: A Monte Carlo Approach and MATLAB

by Charmine Sheena Saflor, Anton Luis Martin Espina, Marlon Era, Samantha Louise Jarder, Francisco Emmanuel Munsayac Jr. III and Ronnel Agulto

Eng. Proc. 2026, 128(1), 40; https://doi.org/10.3390/engproc2026128040 - 17 Mar 2026

Cited by 1 | Viewed by 543

Abstract

In disaster response logistics, it is critical to evaluate strategies for operational speed and efficiency and fairness in aid distribution. Therefore, we developed a simulation-based framework for assessing emergency delivery performance using the efficiency, effectiveness, and equity (3E) model under uncertainty. Using the [...] Read more.

In disaster response logistics, it is critical to evaluate strategies for operational speed and efficiency and fairness in aid distribution. Therefore, we developed a simulation-based framework for assessing emergency delivery performance using the efficiency, effectiveness, and equity (3E) model under uncertainty. Using the Monte Carlo simulation v4.4.9 and MATLAB v4.4.9, the model tests a greedy resource allocation strategy across 100 randomized scenarios involving variable regional demand and travel times. Each scenario is evaluated based on total fulfillment, distribution balance, and delivery effort. The results indicate that under ideal conditions with sufficient supply and no logistical constraints, the strategy achieves full effectiveness and perfect equity, with consistent efficiency outcomes. While the system performs optimally in the base case, the model also highlights the importance of testing strategies under more constrained or disrupted environments. The proposed approach enables planners to assess performance trade-offs, providing a robust foundation for future extensions involving optimization, real-time data integration, or prioritization schemes. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

13 pages, 2221 KB

Open AccessProceeding Paper

Improving Preventive Maintenance Efficiency in University Laboratories Using Radio Frequency Identification-Based Decision Support System and Rapid Application Development Method

by Rizky Fajar Ahmad Gurnita, Rayinda Pramuditya Soesanto, Amelia Kurniawati and Fahmy Habib Hasanudin

Eng. Proc. 2026, 128(1), 41; https://doi.org/10.3390/engproc2026128041 - 18 Mar 2026

Viewed by 632

Abstract

Laboratory asset maintenance in higher education institutions often suffers from inefficiencies due to incomplete data and reactive maintenance practices. We designed a radio frequency identification (RFID)-based information system that supports preventive maintenance and decision-making for laboratory asset management. Utilizing the rapid application development [...] Read more.

Laboratory asset maintenance in higher education institutions often suffers from inefficiencies due to incomplete data and reactive maintenance practices. We designed a radio frequency identification (RFID)-based information system that supports preventive maintenance and decision-making for laboratory asset management. Utilizing the rapid application development method, the system was developed through iterative prototyping and stakeholder engagement. The system integrates RFID-based asset identification with a web-based interface for real-time monitoring and log management. A decision-support module was also implemented, allowing stakeholders to prioritize maintenance tasks based on asset age, repair frequency, and usage patterns. Evaluation results of user acceptance testing showed an average score of 82%, indicating strong usability and relevance. The results demonstrate that integrating RFID with decision-support features significantly improve maintenance planning, reduce operational risk, and optimize resource allocation in academic laboratory environments. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

13 pages, 1059 KB

Open AccessProceeding Paper

Stock Market Analysis, Forecasting, and Automated Trading Using Deep Learning

by Chin-Chih Chang, Chi-Hung Wei, Jo-Tzu Weng, Pei-Hsuan Cho and Sean Hsiao

Eng. Proc. 2026, 128(1), 42; https://doi.org/10.3390/engproc2026128042 - 23 Mar 2026

Viewed by 4628

Abstract

Stock price prediction remains a prominent area of interest among investors due to its potential impact on financial decision making. We developed a deep learning-based system for stock market analysis, forecasting, and automated trading. Utilizing historical financial data, technical indicators, and sentiment information, [...] Read more.

Stock price prediction remains a prominent area of interest among investors due to its potential impact on financial decision making. We developed a deep learning-based system for stock market analysis, forecasting, and automated trading. Utilizing historical financial data, technical indicators, and sentiment information, long short-term memory (LSTM) networks were employed to model and predict stock price movements. The predicted outcomes were integrated into a rule-based automated trading system to simulate real-time buy and sell decisions. Experimental evaluations conducted on the Taiwan Stock Exchange (TWSE) indicate that the developed model surpasses baseline models in both prediction accuracy and trading profitability. The system presents the capability of deep learning to improve forecasting precision and facilitate intelligent, automated trading strategies within contemporary financial markets. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

7 pages, 1199 KB

Open AccessProceeding Paper

Dynamics of Molecular Reorientation in Freely Suspended Smectic Liquid–Crystal Films Caused by Heat Flux

by Nopphadon Seniwong-Na-Ayuttaya, Tanawut Rittidach, Natthaphol Kamosiriwat, Tedat Noppapak and Nattaporn Chattham

Eng. Proc. 2026, 128(1), 43; https://doi.org/10.3390/engproc2026128043 - 24 Mar 2026

Viewed by 275

Abstract

We investigated the dynamics of molecular reorientation in freely suspended smectic liquid–crystal films (FSLCFs) under the influence of heat flux. We also examined how external thermal gradients affect molecular alignment in these ultra-thin films. FSLCFs were fabricated in a temperature-controlled chamber in this [...] Read more.

We investigated the dynamics of molecular reorientation in freely suspended smectic liquid–crystal films (FSLCFs) under the influence of heat flux. We also examined how external thermal gradients affect molecular alignment in these ultra-thin films. FSLCFs were fabricated in a temperature-controlled chamber in this study. When heat flux was applied perpendicular to the film plane, rotation of line defects, known as 2π walls, was observed. This rotation resulted from thermomechanical torque acting on the molecular director, a phenomenon referred to as the Lehmann effect. By analyzing the changes in defect evolution, how heat flux drives the self-organization of liquid–crystal structures can be understood. In this study, we combined experimental observations and computational simulations to model and interpret the results. The results enhance the understanding of the underlying mechanisms governing molecular reorientation and defect dynamics in FSLCFs, particularly in non-equilibrium conditions, to study this mechanism in the microgravity environment. The results also contribute to the development of advanced liquid–crystal technologies, with potential applications in energy-efficient devices, adaptive materials, and space technology systems. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

11 pages, 1126 KB

Open AccessProceeding Paper

Electric Vehicle Charging and Discharging Control Management Strategy Based on Deep Reinforcement Learning

by Chuan Yang, Wenge Huang and Xin Li

Eng. Proc. 2026, 128(1), 44; https://doi.org/10.3390/engproc2026128044 - 24 Mar 2026

Viewed by 592

Abstract

With the widespread adoption of electric vehicles (EVs), the management and scheduling of charging and discharging play a crucial role in the performance of both the electricity grid and electric vehicles. Particularly in the context of peak shaving, valley filling, and the promotion [...] Read more.

With the widespread adoption of electric vehicles (EVs), the management and scheduling of charging and discharging play a crucial role in the performance of both the electricity grid and electric vehicles. Particularly in the context of peak shaving, valley filling, and the promotion of the energy internet infrastructure, efficient management of the EV charging and discharging process is vital. This study investigates the control and management issues surrounding EV charging and discharging, proposing a management strategy based on deep reinforcement learning. By constructing an intelligent decision-making model, it integrates factors such as the operating conditions of the electrical grid, user behavioral preferences, EV battery characteristics, and renewable energy outputs. The study collects real-world EV usage data from a city, establishing an experimental environment to simulate the interaction between the electricity grid and electric vehicles. Using techniques such as Deep Q-Network (DQN) and policy gradients, it constructs a decision network to explore charging and discharging strategies across different time scales and load situations. Experimental results show that this strategy, compared to traditional charging schedule methods, can effectively reduce energy loss during charging, enhance battery life, and balance the grid load, while suppressing demand peaks, thus achieving intelligent optimization and reliability enhancement of the charging and discharging process. Particularly, an adaptive charging power adjustment technique within the strategy can dynamically adjust the charging power according to the real-time status of the EV and grid load without affecting the user’s daily use, thereby achieving the dual objectives of efficient energy saving and economy. The research also quantitatively analyzes battery degradation characteristics and the continuity of charging to ensure the long-term sustainability of the charging strategy. The research findings are significant for understanding and guiding the practical management of EV charging and discharging. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 169 KB

Open AccessProceeding Paper

Design and Realization of an Intelligent Production Line for Particle-Containing Bottled Product

by Yinqiao Zhang, Liping Ma and Min Xu

Eng. Proc. 2026, 128(1), 45; https://doi.org/10.3390/engproc2026128045 - 26 Mar 2026

Viewed by 636

Abstract

The research explored the automation production lines for the bottling of particulate materials in the pharmaceutical industries, covering the integrated processes of loading bottles, filling with particles, sealing, screwing on caps, quality inspection, and storage. The hardware system of the project consists of [...] Read more.

The research explored the automation production lines for the bottling of particulate materials in the pharmaceutical industries, covering the integrated processes of loading bottles, filling with particles, sealing, screwing on caps, quality inspection, and storage. The hardware system of the project consists of programmable logic controllers(PLCs), edge servers, motion control equipment, industrial cameras, and mechanical grippers for handling and storage. The aim of this research is to assist the manufacturing industry in transitioning from traditional production models to digital and intelligent production methods. From the perspective of core components, it analyzed and expounded the key technologies for building a digital production line; at the same time, from the perspective of data collection and processing, it clarified the role and advantages of the cloud platform. The product packaging process simulation covers loading bottles, filling with particle materials, sealing, screwing on caps, quality inspection, and storage. The production line issues production instructions and scheduling plans through the human-machine interaction interface and the cloud platform. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

12 pages, 1638 KB

Open AccessProceeding Paper

Fine-Tuning MobileNet for Durian Variety Classification

by Nyuk Mee Voo, Tong Ming Lim and Yee Mei Lim

Eng. Proc. 2026, 128(1), 46; https://doi.org/10.3390/engproc2026128046 - 27 Mar 2026

Viewed by 558

Abstract

Durian, often referred to as the king of fruits, is widely consumed in Southeast Asia. However, the classification of its varieties is complicated by the lack of distinct visual differences between them. In this study, a fine-tuned MobileNet, a lightweight deep learning model, [...] Read more.

Durian, often referred to as the king of fruits, is widely consumed in Southeast Asia. However, the classification of its varieties is complicated by the lack of distinct visual differences between them. In this study, a fine-tuned MobileNet, a lightweight deep learning model, is applied for the classification of durian varieties. Transfer learning techniques are employed to adapt the MobileNet architecture using a custom dataset of durian images, enabling accurate differentiation between multiple varieties. First, the original MobileNet model is evaluated, which is found to yield low accuracy (8.22%) and a high loss (2.0553). A durian-specific classification layer is then added, and the model is trained for 100 epochs (2 min 21 s), achieving 76.28% training accuracy (0.5985 loss) and 73.20% validation accuracy (0.7606 loss). Further fine-tuning is performed, resulting in 100% training accuracy (4.9623 × 10⁻⁴ loss) and 93.69% validation accuracy (0.2281 loss) after 100 epochs (3 min 55 s). The findings demonstrate that the fine-tuned MobileNet model is capable of high classification accuracy while maintaining computational efficiency, making it suitable for real-time durian variety identification in agricultural and commercial settings. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

6 pages, 251 KB

Open AccessProceeding Paper

Simulation and Real-Time Testing of Photoplethysmogram Signal-Based Biometric Recognition System

by Nilo Bugtai, Francisco Emmanuel Munsayac III, Lea Alonzo, Charmine Sheena Saflor, Samantha Louise Jarder, Homer Co and Edison Anit

Eng. Proc. 2026, 128(1), 47; https://doi.org/10.3390/engproc2026128047 - 3 Apr 2026

Viewed by 406

Abstract

This study aims to develop a biometric recognition system based on photoplethysmogram (PPG) signals. Two testing approaches were employed: simulation and real-time evaluation. The simulations utilized both publicly available data from the IEEE Transactions on Biomedical Engineering database and locally collected data from [...] Read more.

This study aims to develop a biometric recognition system based on photoplethysmogram (PPG) signals. Two testing approaches were employed: simulation and real-time evaluation. The simulations utilized both publicly available data from the IEEE Transactions on Biomedical Engineering database and locally collected data from volunteers. The best-performing simulation model was subsequently applied in real-time testing with the same volunteer group. The results indicate that PPG signals provide a reliable foundation for biometric recognition systems, and further reveal that the use of raw PPG data enhances accuracy. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

12 pages, 3707 KB

Open AccessProceeding Paper

Optimization of Tool Path Planning in Additive Manufacturing Using Euler Transformation

by Shanmukha Ram Peri

Eng. Proc. 2026, 128(1), 48; https://doi.org/10.3390/engproc2026128048 - 7 Apr 2026

Viewed by 269

Abstract

Additive manufacturing, particularly extrusion-based 3D printing, has emerged as a transformative technology in various industries. This study aims to explore the challenges associated with tool path planning in dense-fill 3D printing, emphasizing the significance of optimizing extruder movements to enhance print quality and [...] Read more.

Additive manufacturing, particularly extrusion-based 3D printing, has emerged as a transformative technology in various industries. This study aims to explore the challenges associated with tool path planning in dense-fill 3D printing, emphasizing the significance of optimizing extruder movements to enhance print quality and efficiency. A novel Euler transformation method is presented for polyhedral complexes, which ensures that all vertices in the resulting graph have an even degree, thereby facilitating the existence of Eulerian tours. This method improves the contiguous coverage of the printed object and minimizes non-print movements of the extruder. This article details the implications of tool path design on mechanical properties and introduces an optimization framework that addresses the NP-hardness of the tool path planning problem. Furthermore, the relationship between geometric tool path patterns and print quality is highlighted, revealing the potential for significant advancements in the efficiency of additive manufacturing processes. The proposed methods are illustrated through various applications, demonstrating their effectiveness in achieving. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 1696 KB

Open AccessProceeding Paper

Artificial Intelligence-Powered Breast Cancer Prognosis: Optimizing Deep Learning with Image Normalization

by Chang Yeou Yong, Dennis Jia Wang Pang, Sheng Mou Leong and Chi Wee Tan

Eng. Proc. 2026, 128(1), 49; https://doi.org/10.3390/engproc2026128049 - 16 Apr 2026

Viewed by 284

Abstract

Breast cancer is one of the most fatal cancers for women and requires accurate cancer diagnosis technology. In this research, we incorporated advanced image preprocessing methods, including histogram equalization (HE), stain normalization, intensity normalization, and Richard normalization, along with deep learning, to enhance [...] Read more.

Breast cancer is one of the most fatal cancers for women and requires accurate cancer diagnosis technology. In this research, we incorporated advanced image preprocessing methods, including histogram equalization (HE), stain normalization, intensity normalization, and Richard normalization, along with deep learning, to enhance invasive ductal carcinoma prognosis. Additionally, we evaluated the effectiveness of HE for different image contrast enhancement and model performance optimization methods. The Residual network with 50 layers, the densely connected convolutional network, and the efficient neural network architecture were tested on a publicly available histopathological image dataset. DenseNet showed an accuracy of 0.5523 with Richard normalization and Stain Normalization. ResNet-50 showed an accuracy of 0.5500 when using histogram equalization as a pre-processing step. The results proved that histogram equalization is effective in relieving contrast and feature extraction, which are important in class medical image analysis and dealing with class imbalance problems. The results demonstrate the feasibility of artificial intelligence-based solutions in improving breast cancer prognosis through these inexpensive and efficient prognosis tools. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

10 pages, 3678 KB

Open AccessProceeding Paper

Evaluating Ergonomic Considerations in Redesigning Sustainable Menstrual Product

by Sharine Ablao, Caeniel Esteban, Johanna Mae Garma, Nina Jocson, Ma. Janice Gumasing, Charmine Saflor, Jazmin Tangsoc and Ezekiel Bernardo

Eng. Proc. 2026, 128(1), 50; https://doi.org/10.3390/engproc2026128050 - 21 Apr 2026

Viewed by 590

Abstract

With an estimated 1.8 billion individuals menstruating globally, menstrual product selection plays a critical role in health, comfort, and overall well-being. This study aims to address a gap in menstrual health and hygiene by examining ergonomic considerations in the redesign of a sustainable [...] Read more.

With an estimated 1.8 billion individuals menstruating globally, menstrual product selection plays a critical role in health, comfort, and overall well-being. This study aims to address a gap in menstrual health and hygiene by examining ergonomic considerations in the redesign of a sustainable menstrual product. A comprehensive needs assessment was conducted through focus group discussions and online surveys to identify user preferences and challenges. The design methodology incorporated quality function deployment (QFD) and design failure mode and effects analysis (DFMEA), followed by CAD-based prototyping and expert evaluation. Findings supported a tampon-shaped menstrual cup design, integrating ease of use with the environmental benefits of menstrual cups. Full article

(This article belongs to the Proceedings of The 2025 IEEE International Conference on Computation, Big-Data and Engineering (ICCBE))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Eng. Proc., 2026, IEEE ICCBE 2025

Editorial

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI