Applied System Innovation

Industries are rapidly moving toward mitigating errors and manual interventions by automating their process. The same motivation is carried out in this research which targets to study a conveyor system installed in soda ash manufacturing plants. Our aim is to automate the determination of optimal parameters, which are chosen by identifying the flow rate of the materials available on the conveyor belt for maintaining the ratio between raw materials being carried. The ratio is essential to produce 40% pure carbon dioxide gas needed for soda ash production. A visual sensor mounted on the conveyor belt is used to estimate the flow rate of the raw materials. After selecting the region of interest, a segmentation algorithm is defined based on a voting-based technique to segment the most confident region. Moments and contour features are extracted and passed to machine learning algorithms to estimate the flow rate of different experiments. An in-depth analysis is completed on various techniques and convincing results are achieved on the final data split with the best parameters using the Bagging regressor. Each step of the process is made resilient enough to work in a challenging environment even if the belt is placed in an outdoor environment. The proposed solution caters to the current challenges and serves as a practical solution for estimating material flow without manual intervention. Full article

In this study, we delve into the realm of image segmentation, a field characterized by a multitude of approaches; one frequently used technique is thresholding-based image segmentation. This process divides intensity levels into different regions based on a specified threshold value. Minimum Cross-Entropy Thresholding (MCET) stands out as an independent objective function that can be applied with any distribution and is regarded as a mean-based thresholding method. In certain cases, images exhibit diverse structures that result in different histogram distributions. Some images possess symmetric histograms, while others feature asymmetric ones. Traditional mean-based thresholding methods are well-suited for symmetric image histograms, relying on Gaussian distribution definitions for mean estimations. However, in situations involving asymmetric distributions, such as left and right-skewed histograms, a different approach is required. In this paper, we propose the utilization of a Maximum Likelihood Estimation (MLE) of Gumbel’s distribution or Extreme Value Type I (EVI) distribution for the objective function of an MCET. Our goal is to introduce a dedicated image-thresholding model designed to enhance the accuracy and efficiency of image-segmentation tasks. This model determines optimal thresholds for image segmentation, facilitating precise data analysis for specific image types and yielding improved segmentation results by considering the impact of mean values on thresholding objective functions. We compare our proposed model with original methods and related studies in the literature. Our model demonstrates better performance in terms of segmentation accuracy, as assessed through both unsupervised and supervised evaluations for image segmentation. Full article

The utilization of data mining techniques for the prompt prediction of academic success has gained significant importance in the current era. There is an increasing interest in utilizing these methodologies to forecast the academic performance of students, thereby facilitating educators to intervene and furnish suitable assistance when required. The purpose of this study was to determine the optimal methods for feature engineering and selection in the context of regression and classification tasks. This study compared the Boruta algorithm and Lasso regression for regression, and Recursive Feature Elimination (RFE) and Random Forest Importance (RFI) for classification. According to the findings, Gradient Boost for the regression part of this study had the least Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE) of 12.93 and 18.28, respectively, in the case of the Boruta selection method. In contrast, RFI was found to be the superior classification method, yielding an accuracy rate of 78% in the classification part. This research emphasized the significance of employing appropriate feature engineering and selection methodologies to enhance the efficacy of machine learning algorithms. Using a diverse set of machine learning techniques, this study analyzed the OULA dataset, focusing on both feature engineering and selection. Our approach was to systematically compare the performance of different models, leading to insights about the most effective strategies for predicting student success. Full article

Retailers must have accurate sales forecasts to efficiently and effectively operate their businesses and remain competitive in the marketplace. Global forecasting models like RNNs can be a powerful tool for forecasting in retail settings, where multiple time series are often interrelated and influenced by a variety of external factors. By including covariates in a forecasting model, we can often better capture the various factors that can influence sales in a retail setting. This can help improve the accuracy of our forecasts and enable better decision making for inventory management, purchasing, and other operational decisions. In this study, we investigate how the accuracy of global forecasting models is affected by the inclusion of different potential demand covariates. To ensure the significance of the study’s findings, we used the M5 forecasting competition’s openly accessible and well-established dataset. The results obtained from DeepAR models trained on different combinations of features indicate that the inclusion of time-, event-, and ID-related features consistently enhances the forecast accuracy. The optimal performance is attained when all these covariates are employed together, leading to a 1.8% improvement in RMSSE and a 6.5% improvement in MASE compared to the baseline model without features. It is noteworthy that all DeepAR models, both with and without covariates, exhibit a significantly superior forecasting performance in comparison to the seasonal naïve benchmark. Full article

The promising research on flexible and tactile sensors requires conducting polymer materials and an accurate system for the transduction of pressure into electrical signals. In this paper, the intelligent sensitive mat, based on Velostat, which is a polymeric material impregnated with carbon black, is investigated. Various designs and geometries for home-made sensor mats have been proposed, and their electrical and mechanical properties, including reproducibility, have been studied through the tests performed. The mat pressure sensors have been interfaced with an Arduino microcontroller in order to monitor, read with high precision, and control the variation of the resistance under applied pressure. An approximation method was then developed based on a neural network algorithm to explore the relationship between different mat shapes, the pressure and stresses applied on the mat, the resistance of the conductive Velostat material, and the number of active sensing cells in order to control system input signal management. Full article

Online learning is quickly becoming a popular choice instead of traditional education. One of its key advantages lies in the flexibility it offers, allowing individuals to tailor their learning experiences to their unique schedules and commitments. Moreover, online learning enhances accessibility to education, breaking down geographical and economical boundaries. In this study, we propose the use of advanced natural language processing techniques to design and implement a recommender that supports e-learning students by tailoring materials and reinforcement activities to students’ needs. When a student posts a query in the course forum, our recommender system provides links to other discussion threads where related questions have been raised and additional activities to reinforce the study of topics that have been challenging. We have developed a content-based recommender that utilizes an algorithm capable of extracting key phrases, terms, and embeddings that describe the concepts in the student query and those present in other conversations and reinforcement activities with high precision. The recommender considers the similarity of the concepts extracted from the query and those covered in the course discussion forum and the exercise database to recommend the most relevant content for the student. Our results indicate that we can recommend both posts and activities with high precision (above 80%) using key phrases to represent the textual content. The primary contributions of this research are three. Firstly, it centers on a remarkably specialized and novel domain; secondly, it introduces an effective recommendation approach exclusively guided by the student’s query. Thirdly, the recommendations not only provide answers to immediate questions, but also encourage further learning through the recommendation of supplementary activities. Full article

The issue of Automated Meter Management (AMM), an integral part of modern energy smart grid systems, has become a hot topic in recent years. With the current energy crisis, and given the new approaches to smart energy and its regulation, implemented at the level of the European Union, the gradual introduction of AMM as a standard for the regulation and management of the distribution system is an absolute necessity. Modern smart grids incorporate elements of smart regulation that rely heavily on the availability and quality of the data generated or used during AMM as part of the smart grid. In this paper, based on an analytical view of AMM as a whole and guided interviews with the sponsors of each service and owners of each dataset, criteria are proposed and a Business Impact Analysis (BIA) is implemented, the results of which are used to determine security measures for the safe and reliable running of the AMM system. This paper offers a unique view of the AMM system as an integral part of modern smart grid networks from a data-driven perspective that enables the subsequent implementation and fulfillment of security requirements by ISO/IEC 27001 and national security standards, as the AMM system is also a critical information system under the EU directive regarding the cybersecurity of network and information systems, which are subject to newly defined security requirements in the field of cybersecurity. Full article

Recent developments in electromagnetic launchers have created potential applications in transportation, space, and defense systems. However, the total efficiency of these launchers has yet to be fully realized and optimized. Therefore, this paper introduces a new design idea based on increasing the magnetic flux lines that facilitate high output velocity without adding any excess energy. This design facilitates obtaining a mathematical equation for the launcher inductance which is difficult to analytically represent. This modification raises the launcher efficiency to 36% higher than that of the ordinary launcher at low operating voltage. The proposed design has proven its superiority to traditional launchers, which are limited in their ability to accelerate microsatellites from the ground to low Earth orbit due to altitude and velocity constraints. Therefore, an aircraft is used as a flying launchpad to carry the launcher and bring it to the required height to launch. Meanwhile, it is demonstrated experimentally that magnetic dipoles in the projectile material allow the launcher coil’s magnetic field to accelerate the projectile. This system consists of the launcher coil that must be triggered with a high amplitude current from the high DC voltage capacitor bank. In addition, a microcontroller unit controls all processes, including the capacitor bank charging, triggering, and velocity measurement. Full article

In this paper, we propose a novel methodology that combines the opposition Nelder–Mead algorithm and the selection phase of the genetic algorithm. This integration aims to enhance the performance of the overall algorithm. To evaluate the effectiveness of our methodology, we conducted a comprehensive comparative study involving 11 state-of-the-art algorithms renowned for their exceptional performance in the 2022 IEEE Congress on Evolutionary Computation (CEC 2022). Following rigorous analysis, which included a Friedman test and subsequent Dunn’s post hoc test, our algorithm demonstrated outstanding performance. In fact, our methodology exhibited equal or superior performance compared to the other algorithms in the majority of cases examined. These results highlight the effectiveness and competitiveness of our proposed approach, showcasing its potential to achieve state-of-the-art performance in solving optimization problems. Full article

Wearable devices, such as smartwatches integrating heart rate and activity sensors, have the potential to transform health monitoring by enabling continuous, near real-time data collection and analytics. In this paper, we present a novel modular architecture for collecting and end-to-end processing of high-resolution signals from wearable sensors. The system obtains minimally processed data directly from the smartwatch and further processes and analyzes the data stream without transmitting it to the device vendor cloud. The standalone operation is made possible by a software stack that provides data cleaning, extraction of physiological metrics, and standardization of the metrics to enable person-to-person and rest-to-activity comparisons. To illustrate the operation of the system, we present examples of datasets from volunteers wearing Garmin Fenix smartwatches for several weeks in free-living conditions. As collected, the datasets contain time series of each interbeat interval and the respiration rate, blood oxygen saturation, and step count every 1 min. From the high-resolution datasets, we extract heart rate variability metrics, which are a source of information about the heart’s response to external stressors. These biomarkers can be used for the early detection of a range of diseases and the assessment of physical and mental performance of the individual. The data collection and analytics system has the potential to broaden the use of smartwatches in continuous near to real-time monitoring of health and well-being. Full article

The healthcare industry has recently faced the issues of enhancing patient care, streamlining healthcare operations, and offering high-quality services at reasonable costs. These crucial issues include general healthcare administration, resource allocation, staffing, patient care priorities, and effective scheduling. Therefore, efficient staff scheduling, resource allocation, and patient assignments are required to address these challenges. To address these challenges, in this paper, we developed a mixed-integer linear programming (MILP) model employing the Gurobi optimization solver. The model includes staff assignments, patient assignments, resource allocations, and overtime hours to minimize healthcare expenditures and enhance patient care. We experimented with the robustness and flexibility of our model by implementing two distinct scenarios, each resulting in two unique optimal solutions. The first experimental procedure yielded an optimal solution with an objective value of 844.0, with an exact match between the best-bound score and the objective value, indicating a 0.0% solution gap. Similarly, the second one produced an optimal solution with an objective value of 539.0. The perfect match between this scenario’s best-bound score and objective value resulted in a 0.0% solution gap, further affirming the model’s reliability. The best-bound scores indicated no significant differences in these two procedures, demonstrating that the solutions were ideal within the allowed tolerances. Full article

Planning and managing the production process are key challenges faced by every manufacturing organization. The main contribution of this article lies in the analysis and design of a planning algorithm that takes into consideration the specifics of this environment. The proposed algorithm encompasses elements of batch production, including a just-in-time approach. The article focuses on scenarios within batch production. Managers of manufacturing and supply companies must ensure smooth fulfillment and uninterrupted production of the agreed-upon quantity of parts. However, this task presents complex challenges. The product portfolio requires meticulous sequencing of production batches, and subsequent parts need to be temporarily stored in their raw state for further processing. Moreover, product variability necessitates frequent adjustments to the production line, resulting in delays. Shortages in manpower additionally place demands on shift organization. The company’s primary objective is to increase production efficiency while simultaneously reducing inventory and minimizing non-standard shift work. The challenge was to reconcile seemingly conflicting company requirements and to concentrate on solutions with swift implementation and minimal costs. Ensuring seamless production operation can be addressed by expanding supporting technologies or by increasing production capacity, such as acquiring an additional production line. However, these options entail costs and do not align with the company’s expectation for immediate impact and cost savings. However, improving production efficiency can also be achieved by altering the approach to production planning, which is the central theme of this article. The key element is ensuring that the customer plan is adhered to while working with a fixed production logic and variable input factors that must account for various non-standard situations. Full article

According to the European Green Deal, excessive carbon emissions are the origin of global warming and must be drastically reduced. Given that the building sector is one of the major sources of carbon emissions, results imperative to limit these emissions, especially in a city context where the density of buildings is commonly higher and rapidly increasing. All stages of the life cycle of a building, including raw material harvesting, manufacturing of products, use phase of the building, end of life, all generate or reduce carbon. The manufacture of construction materials accounts for 11% of all energy and process-related emissions annually. Additionally, recent estimates indicate that over 80% of all product-related environmental impacts of a building are determined during the design phase of the building. These indicators reflect the urgent need to explore a low-carbon measure method for building design. This is here done using a linear regression Reverse Engineering model and percentage calculation. One of the hypotheses formulated relates Global Warming Potential (GWP) of −30.000 CO₂eq or lower (around −165 CO₂eq/m²) in the 25% of a block of houses, to carbon further reductions by 11%. This paper has identified barriers in terms of the databases needed to achieve this task. Full article

Change and innovation are increasingly exerting a significant influence on the daily activities of companies. To ensure optimal control, innovative solutions are employed that are encapsulated in the concept of change management. In the engineering change sector, the proposed approach involves developing solutions and making continuous adjustments to the manufacturing process to enhance productivity and to meet customer needs. Within the automotive industry, companies utilize innovations and process change management to continuously improve and strengthen their position in the market, such as KPI/KPRS and PCI. To achieve this, the present study gathers real digital data from the Romanian branches of two renowned automotive companies. The data regarding change requests include 215 registrations for the first company and 734 registrations for the second company. By employing complex statistical methods such as ANOVA, Student’s t-test, the Mann–Whitney test, and a regression model, the primary objective of this study is to model and to identify the best predictor of change request status. Additionally, this study aims to explore how this change process influences the economic performances of the companies and the performance indicators of change management in manufacturing processes. The findings indicate that, both in the organizations in general and within the automotive industry, when products experience high demand in the market, the number of change requests increases. This highlights the importance of internal optimization of the automation system. Moreover, the study results underscore the crucial role of an effective smart manufacturing and optimal change management system to uphold and to enhance the economic performance of automotive companies. Full article

The modern tourist industry is characterized by an abundance of applied multicriteria decision-making tasks. Several researchers have demonstrated that such tasks can be effectively resolved using aggregation operators based on fuzzy integrals and fuzzy measures. At the same time, the implementation of this mathematical tool is limited by weak intuitive understanding by the practicing specialists of the aggregation process as well as fuzzy measures in general. Some researchers have proposed different aggregation visualization methods, but these methods have several properties that block their wide implementation in decision-making practice. The purpose of this study is to develop a decision-making approach that will allow practitioners to have a clear intuitive vision of the aggregation process and fuzzy measures. This article proposes an approach to decision making in the tourist industry based on the synthesis of the aggregation operator that includes 3D visualization graphics in virtual reality. Firstly, some research devoted to decision-making methods in tourism was assessed along with “smart” tourism, aggregation operators and their visualization. Secondly, a 3D visualization in the form of a balance model was introduced. Thirdly, the method of aggregation-operator synthesis based on the 3D balance model and the 2-order Choquet integral was developed. Finally, an illustrational example of implementing such an approach for resolving the task of assessing and choosing a hotel was described. Full article

A scheme for solving the problem of determining the probability of failure and probabilistic (statistical) characteristics of the failure loading magnitude of a composite material plate is considered. The plate structure is a flat homogeneous matrix with stochastically distributed rigid rod inclusions. The geometric parameters of inclusions are considered independent random variables with given probability distribution laws. The expressions for the failure loading distribution function, the probability of failure, the mean value, and the dispersion of the failure loading were received and presented. Their dependence on the type of stress state, the inclusion number, and matrix Poisson’s ratio were studied graphically. Full article

Mechatronics as a science is a synergic combination of mechanical engineering, electronic control, and software design in product development and manufacturing processes. To understand how the field of knowledge that incorporates mechatronics in innovative products, given that it is not in itself a basic engineering discipline but an integration of fields of knowledge, has advanced, it was developed a bibliometric and qualitative study through systematic review with an analytical framework for the establishment of variables to subsidize the construction of the selected theoretical body. The results and conclusions of the sampled publications show that mechatronics performs one of the principal roles in innovation due to the multidisciplinary integration that the scope of innovation in product engineering is propitiating. The study classified five global scenarios: practical approaches aimed at product development, research that studies curricula and education in engineering, studies involving components of a mechatronic system, use of artificial intelligence, and methodologies for designing mechatronic systems. In addition to underscoring that the use of the term innovation associated with mechatronics in a large proportion of the publications extrapolates the operational level, characterizing an attribution to the term that is always associated with the applications, ramifications, and perspectives that the respective product, design, robot, or system could offer to the market or future research. Similarly, it was found that the results of many publications associate the term innovation with a return on investments or operational costs and emphasize the advantages of using the technology for commercial ends. Full article

The exploitation of solar irradiation is a critical weapon for facing the energy crisis and critical environmental problems. One of the most emerging solar technologies is the use of solar towers (or central receiver systems) coupled with high-performance thermodynamic cycles. In this direction, the present investigation examines a solar tower coupled to a closed-loop Brayton cycle which operates with supercritical CO₂ (sCO₂) as the working medium. The system also includes a storage system with two molten salt tanks for enabling proper thermal storage. The sCO₂ is an efficient fluid that presents significant advancements, mainly reduced compression work when it is compressed close to the critical point region. The novelty of the present work is based on the detailed dynamic investigation of the studied configuration for the year period using adjustable time step and its sizing for achieving a continuous operation, something that makes possible the establishment of this renewable technology as a reliable one. The analysis is conducted with a developed model in the Modelica programming language by also using the Dymola solver. According to the simulation results, the yearly solar thermal efficiency is 50.7%, the yearly thermodynamic cycle efficiency is 42.9% and the yearly total system efficiency is 18.0%. Full article

Voting is a democratic process that allows individuals to choose their leaders and voice their opinions. However, the current situation with physical voting involves long queues, paper-based ballots, and security challenges. Blockchain-based voting models have appeared as a method to address the limitations of traditional voting methods. As blockchain is distributed and decentralized, which uses hash functions for securing transactions, it dramatically improves the existing voting system. These digital platforms eliminate the need for physical presence, reduce paperwork, and ensure the integrity of votes through transparent and tamper-proof blockchain technology. This paper introduces a blockchain-based voting model to enhance accessibility, security, and efficiency in the voting process. The research focuses on developing a robust and user-friendly voting system by leveraging the advantages of decentralized technology. The proposed model employs Ethereum as the underlying blockchain platform through an innovative and iterative approach. The model uses Smart contracts to record and validate votes, while AI-based facial recognition technology is integrated to verify the identity of voters. Rigorous testing and analysis are conducted to validate the effectiveness and reliability of the proposed blockchain-based voting model. The system underwent extensive simulation scenarios and stress tests to evaluate its performance, security, and usability. Full article