Search Results (1,087)

Measuring interfacial roughness is essential in evaluating the adhesion of coatings and thermally grown oxides. Conventional contact methods are often impractical for such analyses, especially when the interface lies beneath a nonremovable layer. This study proposes a semi-automated method combining an ImageJ macro and an R-language script to assess interfacial roughness from images obtained through scanning electron microscopy (SEM), leveraging chemical contrast between substrate and oxide. The approach preserves user input where interpretation is critical while standardizing measurement to reduce variability. Applied to 21 images from seven experimental conditions, the algorithm successfully reproduced the roughness ranking obtained from manual measurement while also significantly reducing measurement dispersion. Though it underestimates absolute roughness values compared with the user measurements (which should also happen with conventional contact methods), it offers a robust, flexible, and reproducible alternative for interface characterization. Full article

The wide availability of sensor data stored in multiple formats makes it difficult to reuse in other applications. We consider the problem of extracting sensor data from unstructured and semi-structured texts using Large Language Models. With careful prompt crafting, we have been able to establish a strict JSON structure which can be further processed with automated ease. We establish a workflow that enables the extraction of data using GPT-4, Llama 3, Mistral and Falcon models, and we show that while the closed-source GPT-4 model is generally leading in conversion efficiency, other open-source models can follow this if given appropriate data structures. We define new measures to simplify the comparison, and we present a multi-purpose workflow for sensor data extraction. We observe that some of the smaller models are incapable of correctly extracting data from freeform text but are skilled in processing tabular data. On the other hand, larger models are more robust and avoid conversion mistakes more easily. Full article

Achieving cost-effective energy performance while meeting sustainability goals is a challenge in retrofitting decisions within the construction industry. To enhance the decision-making process, this study introduces an IFC-based approach that integrates cost estimation and energy analysis directly within BIM. This approach supports more structured and data-informed retrofit planning by structuring cost and energy data within a semi-automated IFC-based workflow. The methodology follows a structured approach that includes three phases. The first focuses on developing a BIM model that captures the physical and semantic attributes of an existing building. This is followed by parametric energy simulations to evaluate retrofit scenarios, with cost data integrated and energy analysis reports linked to IFC elements. The final phase involves a post-retrofit cost assessment to identify the optimal scenario based on total cost, with potential for extension to other performance indicators. The framework was applied in a residential case study to evaluate the model’s functionality. The results show that IFC-based integration improves transparency, interoperability, and reliability in cost–energy assessments. By structuring data as linked IFC entities, the approach enhances BIM’s role as a decision-support tool for sustainable and economically efficient retrofitting. Full article

Process control and quality assurance of wire + arc additive manufacturing (WAAM) and automated welding rely heavily on in-process monitoring videos to quantify variables such as melt pool geometry, location and size of droplet transfer, arc characteristics, etc. To enable feedback control based upon this information, an automatic and robust segmentation method for monitoring of videos and images is required. However, video segmentation in WAAM and welding is challenging due to constantly fluctuating arc brightness, which varies with deposition and welding configurations. Additionally, conventional computer vision algorithms based on greyscale value and gradient lack flexibility and robustness in this scenario. Deep learning offers a promising approach to WAAM video segmentation; however, the prohibitive time and cost associated with creating a well-labelled, suitably sized dataset have hindered its widespread adoption. The emergence of large computer vision models, however, has provided new solutions. In this study a semi-automatic annotation tool for WAAM videos was developed based upon the computer vision foundation model SAM and the video object tracking model XMem. The tool can enable annotation of the video frames hundreds of times faster than traditional manual annotation methods, thus making it possible to achieve rapid quantitative analysis of WAAM and welding videos with minimal user intervention. To demonstrate the effectiveness of the tool, three cases are demonstrated: online wire position closed-loop control, droplet transfer behaviour analysis, and assembling a dataset for dedicated deep learning segmentation models. This work provides a broader perspective on how to exploit large models in WAAM and weld deposits. Full article

Interest in explainable machine learning has grown, particularly in healthcare, where transparency and trust are essential. We developed a semi-automated evaluation framework within a clinical decision support system (CDSS-EQCM) that integrates LIME and SHAP explanations with multi-criteria decision-making (TOPSIS and Borda count) to rank model interpretability. After two-phase preprocessing of 2934 COVID-19 patient records spanning four epidemic waves, we applied five classifiers (Random Forest, Decision Tree, Logistic Regression, k-NN, SVM). Five infectious disease physicians used a Streamlit interface to generate patient-specific explanations and rate models on accuracy, separability, stability, response time, understandability, and user experience. Random Forest combined with SHAP consistently achieved the highest rankings in Borda count. Clinicians reported reduced evaluation time, enhanced explanation clarity, and increased confidence in model outputs. These results demonstrate that CDSS-EQCM can effectively streamline interpretability assessment and support clinician decision-making in medical diagnostics. Future work will focus on deeper electronic medical record integration and interactive parameter tuning to further enhance real-time diagnostic support. Full article

The adoption of AI vision models in specialized industries is often hindered by the substantial requirement for extensive, manually annotated image datasets. Even when employing transfer learning, robust model development typically necessitates tens of thousands of such images, a process that is time-consuming, costly, and demands consistent expert annotation. This technical note introduces a semi-automated method to significantly reduce this annotation burden. The proposed approach utilizes two general-purpose vision-transformer-to-caption (GP-ViTC) models to generate descriptive text from images. These captions are then processed by a custom-developed semantic classifier (SC), which requires only minimal training to predict the correct image class. This GP-ViTC + SC system demonstrated exemplary classification rates in test cases and can subsequently be used to automatically annotate large image datasets. While the inference speed of the GP-ViTC models is not suited for real-time applications (approximately 10 s per image), this method substantially lessens the labor and expertise required for dataset creation, thereby facilitating the development of new, high-speed, custom AI vision models for niche applications. This work details the approach and its successful application, offering a cost-effective pathway for generating tailored image training sets. Full article

Background/Objectives: Artificial intelligence (AI) offers opportunities to enhance healthcare accessibility for people with disabilities (PwDs). However, their application in Saudi Arabia remains limited. This study explores PwDs’ experiences with AI technologies within the Kingdom’s Vision 2030 digital health framework to inform inclusive healthcare innovation strategies. Methods: Semi-structured interviews were conducted with nine PwDs across Riyadh, Al-Jouf, and the Northern Border region between January and February 2025. Participants used various AI-enabled technologies, including smart home assistants, mobile health applications, communication aids, and automated scheduling systems. Thematic analysis following Braun and Clarke’s six-phase framework was employed to identify key themes and patterns. Results: Four major themes emerged: (1) accessibility and usability challenges, including voice recognition difficulties and interface barriers; (2) personalization and autonomy through AI-assisted daily living tasks and medication management; (3) technological barriers such as connectivity issues and maintenance gaps; and (4) psychological acceptance influenced by family support and cultural integration. Participants noted infrastructure gaps in rural areas, financial constraints, limited disability-specific design, and digital literacy barriers while expressing optimism regarding AI’s potential to enhance independence and health outcomes. Conclusions: Realizing the benefits of AI for disability healthcare in Saudi Arabia requires culturally adapted designs, improved infrastructure investment in rural regions, inclusive policymaking, and targeted digital literacy programs. These findings support inclusive healthcare innovation aligned with Saudi Vision 2030 goals and provide evidence-based recommendations for implementing AI healthcare technologies for PwDs in similar cultural contexts. Full article

Background: Automated semi-solid extrusion (SSE) material deposition is a promising new technology for preparing personalized medicines for different patient groups and veterinary applications. The technology enables the preparation of custom-made oral elastic gel tablets of active pharmaceutical ingredient (API) by using a semi-solid polymeric printing ink. Methods: An automated SSE material deposition method was used for generating chewable gel tablets loaded with propranolol hydrochloride (-HCl) at three different API content levels (3.0 mg, 4.0 mg, 5.0 mg). The physical appearance, surface morphology, dimensions, mass and mass variation, process-derived solid-state changes, mechanical properties, and in-vitro drug release of the gel tablets were studied. Results: The inclusion of API (1% w/w) in the semi-solid CuraBlend^TM printing mixture decreased viscosity and increased fluidity, thus promoting the spreading of the mixture on the printed (material deposition) bed and the printing performance of the gel tablets. The printed gel tablets were elastic, soft, jelly-like, chewable preparations. The mechanical properties of the gel tablets were dependent on the printing ink composition (i.e., with or without propranolol HCl). The maximum load for the final deformation of the CuraBlend™-API (3.0 mg) gel tablets was very uniform, ranging from 73 N to 80 N. The in-vitro dissolution test showed that more than 85% of the drug load was released within 15–20 min, thus verifying the immediate-release behavior of these drug preparations. Conclusions: Automated SSE material deposition as a modified 3D printing method is a feasible technology for preparing customized oral chewable gel tablets of propranolol HCl. Full article

Indoor environmental quality (IEQ) of higher education (HE) buildings significantly impacts the built environment sector. This research aimed to optimize learning environments and enhance student comfort, especially post-COVID-19. The study adopts the principles of Post-occupancy Evaluation (POE) to collect and analyze various quantitative and qualitative data through environmental data monitoring, a user perceptions survey, and semi-structured interviews with professionals. Although the environmental conditions generally met existing standards, the findings indicated opportunities for further improvements to better support university communities’ comfort and health. A significant challenge identified by this research is the inability of the facility management to physically manage and operate the vast and complex spaces within HE buildings with contemporary IEQ standards. In response to these findings, this research developed a BIM-based prototype for the real-time monitoring and automated control of IEQ. The prototype integrates a BIM model with Arduino-linked sensors, motors, and traffic lights, with the latter visually indicating IEQ status, while motors automatically adjust environmental conditions based on sensor inputs. The outcomes of this study not only contribute to the ongoing discourse on sustainable building management, especially post-pandemic, but also demonstrate an advancement in the application of BIM technologies to improve IEQ and by extension, occupant wellbeing in HE buildings. Full article

This study investigates the operational performance of fruit-picking robots under varying terrain slopes and soil moisture conditions, with a focus on comparing wheeled and tracked locomotion systems. A modular robot platform was designed and tested in both controlled environments and actual mountainous orchards in Shandong, China. The experiments assessed key performance metrics—average speed, slip rate, and path deviation—under combinations of four slope levels (0°, 8°, 18°, 28°) and three soil moisture levels (dry 10%, moderate 20%, wet 35%). Results reveal that wheeled robots perform optimally on dry and flat terrain but experience significant slippage and path deviation under steep and wet conditions. In contrast, tracked robots maintain better stability and terrain adaptability, demonstrating lower slip rates and more consistent trajectories across a wide range of conditions. A synergistic deterioration effect was observed when high slope and high soil moisture co-occur, significantly degrading the performance of wheeled systems, while tracked systems mitigated these effects. Complementary semi-structured interviews with 20 orchard stakeholders—including farmers, growers, and hired pickers—highlighted key user expectations: robust traction, terrain adaptability, reduced physical labor, and operational safety. The findings suggest that future agricultural robots should adopt adaptive hybrid mobility systems and integrate environmental perception capabilities to enhance performance in complex agricultural scenarios. These insights contribute practical and theoretical guidance for the design and deployment of intelligent fruit-picking robots in diverse field environments. Full article

This paper presents a human-in-the-loop interactive framework for skeleton-based posture recognition, designed to support model training and artistic education. A total of 4870 labeled images are used for training and validation, and 500 images are reserved for testing across five core posture categories: standing, sitting, jumping, crouching, and lying. From each image, comprehensive skeletal features are extracted, including joint coordinates, angles, limb lengths, and symmetry metrics. Multiple classification algorithms—traditional (KNN, SVM, Random Forest) and deep learning-based (LSTM, Transformer)—are compared to identify effective combinations of features and models. Experimental results show that deep learning models achieve superior accuracy on complex postures, while traditional models remain competitive with low-dimensional features. Beyond classification, the system integrates posture recognition with a visual recommendation module. Recognized poses are used to retrieve matched examples from a reference library, allowing instructors to browse and select posture suggestions for learners. This semi-automated feedback loop enhances teaching interactivity and efficiency. Among all evaluated methods, the Transformer model achieved the best accuracy of 92.7% on the dataset, demonstrating the effectiveness of our closed-loop framework in supporting pose classification and model training. The proposed framework contributes both algorithmic insights and a novel application design for posture-driven educational support systems. Full article

Background: Machine learning methods are increasingly being used in mobile network optimization systems, especially next-generation mobile networks. The need for enhanced radio resource allocation schemes, improved user mobility and increased throughput, driven by a rising demand for data, has necessitated the development of diverse algorithms that optimize output values based on varied input parameters. In this context, we identify the main topics related to cellular networks and machine learning algorithms in order to pinpoint areas where the optimization of parameters is crucial. Furthermore, the wide range of available algorithms often leads to confusion and disorder during classification processes. It is crucial to note that next-generation networks are expected to require reduced latency times, especially for sensitive applications such as Industry 4.0. Research Question: An analysis of the existing literature on mobile network load balancing methods was conducted to identify systems that operate using semi-automatic, automatic and hybrid algorithms. Our research question is as follows: What are the automatic, semi-automatic and hybrid load balancing algorithms that can be applied to next-generation mobile networks? Contribution: This paper aims to present a comprehensive analysis and classification of the algorithms used in this area of study; in order to identify the most suitable for load balancing optimization in next-generation mobile networks, we have organized the classification into three categories, automatic, semi-automatic and hybrid, which will allow for a clear and concise idea of both theoretical and field studies that relate these three types of algorithms with next-generation networks. Figures and tables illustrate the number of algorithms classified by type. In addition, the most important articles related to this topic from five different scientific databases are summarized. Methodology: For this research, we employed the PRISMA method to conduct a systematic literature review of the aforementioned study areas. Findings: The results show that, despite the scarce literature on the subject, the use of load balancing algorithms significantly influences the deployment and performance of next-generation mobile networks. This study highlights the critical role that algorithm selection should play in 5G network optimization, in particular to address latency reduction, dynamic resource allocation and scalability in dense user environments, key challenges for applications such as industrial automation and real-time communications. Our classification framework provides a basis for operators to evaluate algorithmic trade-offs in scenarios such as network fragmentation or edge computing. To fill existing gaps, we propose further research on AI-driven hybrid models that integrate real-time data analytics with predictive algorithms, enabling proactive load management in ultra-reliable 5G/6G architectures. Given this background, it is crucial to conduct further research on the effects of technologies used for load balancing optimization. This line of research is worthy of consideration. Full article

Human corneal endothelial cell therapy has recently emerged as a novel solution to treat corneal endothelial diseases. We previously demonstrated the potential of utilizing non-cultured primary corneal endothelial cells (CEnCs) isolated from donor corneas with low endothelial cell density for simple non-cultured endothelial cell injection (SNEC-I) therapy. This study aimed to develop a robust and semi-automated approach for cell counting, characterize the extent of cellular manipulation, and evaluate the translational workflow. To address this, we evaluated manual and automated cell counting approaches and characterized the extent of manipulation of CEnCs through the analysis of cell cycle status, gene expressions, and transcriptomic profiles with single-cell RNA-sequencing. The translational feasibility and functionality of SNEC-I therapy were examined using an established rabbit model of bullous keratopathy. Manual hemocytometry and automated cell-counters exhibited comparable accuracy and reproducibility. Analysis of cell cycle status, cell cycle genes (n = 11), and transcriptomic profiles revealed close resemblance between the native corneal endothelium and its donor-matched SNEC-I-harvested cells. Successful resolution of bullous keratoplasty in the pre-clinical model supports the feasibility, efficacy, and safety of SNEC-I therapy. In conclusion, SNEC-I therapy serves as an attractive corneal endothelial therapeutic approach (from a regulatory standpoint) in view of the minimal extent of cellular manipulation. Full article

We present a semi-automatic framework for transcribing foreign personal names into Lithuanian, aimed at reducing pronunciation errors in text-to-speech systems. Focusing on noisy, web-crawled data, the pipeline combines rule-based filtering, morphological normalization, and manual stress annotation—the only non-automated step—to generate training data for character-level transcription models. We evaluate three approaches: a weighted finite-state transducer (WFST), an LSTM-based sequence-to-sequence model with attention, and a Transformer model optimized for character transduction. Results show that word-pair models outperform single-word models, with the Transformer achieving the best performance (19.04% WER) on a cleaned and augmented dataset. Data augmentation via word order reversal proved effective, while combining single-word and word-pair training offered limited gains. Despite filtering, residual noise persists, with 54% of outputs showing some error, though only 11% were perceptually significant. Full article

Peat fires are a major hazard to human and animal health and can negatively impact livelihoods. Once peat fires start to burn, they are difficult to extinguish and can continue to burn for months, destroying biomass and contributing to carbon emissions globally. In areas with limited accessibility and periods of thick haze and fog, these fires are difficult to detect, localize, and tackle. To address this problem, thermal infrared cameras mounted on drones can provide a potential solution since they allow large areas to be surveyed relatively quickly and can detect thermal radiation from fires above and below the peat surface. This paper describes a deep learning pipeline that detects and segments peat fires in thermal images. Controlled peat fires were constructed under varying environmental conditions and thermal images were taken to form a dataset for our pipeline. A semi-automated approach was adopted to label images using Otsu’s adaptive thresholding technique, which significantly reduces the required effort often needed to tag objects in images. The proposed method uses a pre-trained ResNet-50 model as a backbone (encoder) for feature extraction and is augmented with a set of up-sampling layers and skip connections, like the UNet architecture. The experimental results show that the model can achieve an IOU score of 87.6% on an unseen test set of thermal images containing peat fires. In comparison, a MobileNetV2 model trained under the same experimental conditions achieved an IOU score of 57.9%. In addition, the model is robust to false positives, which is indicated by a precision equal to 94.2%. To demonstrate its practical utility, the model was also tested on real peat wildfires, and the results are promising, as indicated by a high IOU score of 90%. Finally, a geolocation algorithm is presented to identify the GNSS location of these fires once they are detected in an image to aid fire-fighting responses. The proposed scheme was built using a web-based platform that performs offline detection and allows peat fires to be geolocated. Full article