Search Results (48)

This study presents the design and evaluation of a multi-model artificial intelligence (AI) framework for proactive quality risk management in projects. A dataset comprising 2000 risk records was developed, containing four columns: Risk Description (input), Risk Category, Trigger, and Impact (outputs). Each output variable was modeled using three independent classifiers, forming a multi-step decision-making pipeline where one input is processed by multiple specialized models. Two feature extraction techniques, Term Frequency–Inverse Document Frequency (TF-IDF) and GloVe100 Word Embeddings, were compared in combination with several machine learning algorithms, including Logistic Regression, Support Vector Machines (SVMs), Random Forest, Multinomial Naive Bayes, and XGBoost. Results showed that model performance varied with task complexity and the number of output classes. Trigger prediction (28 classes), Logistic Regression, and SVM achieved the best performance, with a macro-average F1-score of 0.75, while XGBoost with TF-IDF features produced the highest accuracy for Risk Category classification (five classes). In Impact prediction (15 classes), SVM with Word Embeddings demonstrated superior results. The implementation, conducted in Python (v3.9.12, Anaconda), utilized Scikit-learn, XGBoost, SHAP, and Gensim libraries. SHAP visualizations and confusion matrices enhanced model interpretability. The proposed framework contributes to scalable, text-based, predictive, quality risk management, supporting real-time project decision-making. Full article

Glove fit is crucial for both wear comfort and safety. A well-fitting glove can be realized by combining anthropometric hand measurements from three-dimensional (3D) scanning with the finite element method (FEM). This study reviews how accurate hand measurements and model interactions can be achieved to improve design and enhance protection. A total of 26 articles were selected for an integrated analysis and evaluation. The results indicate an increase in accuracy in 3D scanning with greater resolution, in which the optimum value has not been discovered. While the numbers of landmarks (ranging from 14 to 50) depend on the specific purpose, they do not directly correlate with precision. On the other hand, the authenticity of the FEM is closely related to the number and size of the finite elements, with simulation error decreasing as the applied force increases (R² > 0.78). It is also noteworthy that the image-based approach, motion state, and model used in the FEM do not significantly affect precision. Both technologies provide a comprehensive approach for glove design, as they combine accurate anatomical data with predictive modeling of mechanical performance and fit. Yet, challenges are identified, such as divergent standards in data retrieval and low accessibility, which inhibit the application of these two techniques in glove construction. Future studies should address the issues of improving scanning coverage, standardizing the data collection models, expanding glove application in different fields, and adopting artificial intelligence to improve the design, construction, or manufacture of gloves. Full article

To investigate the characteristic pressure distribution patterns when gripping ski poles during skiing, this study addresses the challenges of measuring grip force on the complex curved surfaces of ski poles. A dataset of experimental samples was established, and grip force data were extracted using deep neural network (DNN) training. To reduce errors caused by dynamic force distribution and domain shifts due to varying hand postures, a hybrid method combining deep neural networks with the bio-inspired Gray Wolf Optimization (GWO) algorithm was proposed. This approach enables the fusion of hand-related feature data, facilitating the development of a high-precision grip force prediction model for skiing. A multi-point flexible array sensor was selected to detect force at key contact points. Through system calibration, grip force data were collected and used to construct a comprehensive database. A backpropagation (BP) neural network was then developed to process the sensor data at these characteristic points using deep learning techniques. The data fusion model was trained and further optimized through the GWO-BPNN (Gray Wolf Optimizer–backpropagation neural network) algorithm, which focuses on correcting and classifying force data based on dominant force-bearing units. Experimental results show that the optimized model achieves a relative error of less than 2% compared to calibration experiments, significantly improving the accuracy of flexible sensor applications. This model has been successfully applied to the development of intelligent skiing gloves, offering a scientific foundation for performance guidance and evaluation in skiing sports. Full article

This research presents a novel, real-time Pakistani Sign Language (PSL) recognition system utilizing a custom-designed sensory glove integrated with advanced machine learning techniques. The system aims to bridge communication gaps for individuals with hearing and speech impairments by translating hand gestures into readable text. At the core of this work is a smart glove engineered with five resistive flex sensors for precise finger flexion detection and a 9-DOF Inertial Measurement Unit (IMU) for capturing hand orientation and movement. The glove is powered by a compact microcontroller, which processes the analog and digital sensor inputs and transmits the data wirelessly to a host computer. A rechargeable 3.7 V Li-Po battery ensures portability, while a dynamic dataset comprising both static alphabet gestures and dynamic PSL phrases was recorded using this setup. The collected data was used to train two models: a Support Vector Machine with feature extraction (SVM-FE) and a Long Short-Term Memory (LSTM) deep learning network. The LSTM model outperformed traditional methods, achieving an accuracy of 98.6% in real-time gesture recognition. The proposed system demonstrates robust performance and offers practical applications in smart home interfaces, virtual and augmented reality, gaming, and assistive technologies. By combining ergonomic hardware with intelligent algorithms, this research takes a significant step toward inclusive communication and more natural human–machine interaction. Full article

Intelligent sensing systems are increasingly used in wearable devices, enabling advanced tasks across various application domains including robotics and human–machine interaction. Ensuring these systems are energy autonomous is highly demanded, despite strict constraints on power, memory and processing resources. To meet these requirements, embedded neural networks must be optimized to achieve a balance between accuracy and efficiency. This paper presents an integrated approach that combines Hardware-Aware Neural Architecture Search (HW-NAS) with optimization techniques—weight reshaping, quantization, and their combination—to develop efficient classifiers for a multisensory glove. HW-NAS automatically derives 1D-CNN models tailored to the NUCLEO-F401RE board, while the additional optimization further reduces model size, memory usage, and latency. Across three datasets, the optimized models not only improve classification accuracy but also deliver an average reduction of 75% in inference time, 69% in flash memory, and more than 45% in RAM compared to NAS-only baselines. These results highlight the effectiveness of integrating NAS with optimization techniques, paving the way towards energy-autonomous wearable systems. Full article

This study investigates the challenges of promoting accessibility for deaf teachers and students in higher education, focusing on the development of inclusive teaching materials. A qualitative case study was conducted in ten teacher training programmes at the Federal University of Alagoas (Brazil), including nine distance learning courses and one face-to-face LIBRAS programme. Analysis of the Virtual Learning Environment revealed a predominance of text-based content, with limited use of Libras videos, visual resources, or assistive technologies. The integration of Brazilian Sign Language into teaching practices was minimal, and digital translation tools were rarely used or contextually appropriate. Educators reported limited training, technical support, and institutional guidance for the creation of accessible materials. Time constraints and resource scarcity further hampered inclusive practices. The results highlight the urgent need for institutional policies, continuous teacher training, multidisciplinary support teams, and the strategic use of digital technologies and Artificial Intelligence (AI). Compared with previous studies, significant progress has been made. The present study highlights the establishment of an Accessibility Centre (NAC) and an Accessibility Laboratory (LAB) at the university. These facilities are designed to support the development of policies for the inclusion of people with disabilities, including deaf students, and to assist teachers in designing educational resources, which is essential for enhancing accessibility and learning outcomes. Artificial intelligence tools—such as sign language translators including Hand Talk, VLibras, SignSpeak, Glove-Based Systems, the LIBRAS Online Dictionary, and the Spreadthesign Dictionary—can serve as valuable resources in the teaching and learning process. Full article

This study presents a human-centric, data-driven modeling framework for the intelligent evaluation and classification of vibration-reducing (VR) gloves used in hand-transmitted vibration environments. Recognizing the trade-offs between protection and functionality, the integrated performance assessment incorporates three critical and often conflicting metrics: manual dexterity, grip strength, and distributed vibration transmissibility at the palm and fingers. Three independent experiments involving fifteen participants were conducted to evaluate the individual performance of ten commercially available VR gloves fabricated from air bladders, polymers, and viscoelastic gels. The effects of VR gloves on manual dexterity, grip strength, and distributed vibration transmission were investigated. The resulting experimental data were used to train and tune seven different machine learning models. The results suggested that the AdaBoost model demonstrated superior predictive performance, achieving 92% accuracy in efficiently evaluating the integrated performance of VR gloves. It is further shown that the proposed data-driven model could be effectively applied to classify the performances of VR gloves in three workplace conditions based on the dominant vibration frequencies (low-, medium-, and high-frequency). The proposed framework demonstrates the potential of AI-enhanced intelligent actuation systems to support personalized selection of wearable protective equipment, thereby enhancing occupational safety, usability, and task efficiency in vibration-intensive environments. Full article

Loess landslide disasters are influenced by a multitude of factors, including slope conditions, triggering mechanisms, and spatial attributes. Extracting these factors from unstructured geological texts is challenging due to nested entities, semantic ambiguity, and rare domain-specific terms. This study proposes a joint extraction framework guided by a domain ontology that categorizes six types of loess landslide influencing factors, including spatial relationships. The ontology facilitates conceptual classification and semi-automatic nested entity annotation, enabling the construction of a high-quality corpus with eight tag types. The model integrates a Soft-Lexicon mechanism that enhances character-level GloVe embeddings with explicit lexical features, including domain terms, part-of-speech tags, and word boundary indicators derived from a domain-specific lexicon. The resulting hybrid character-level representations are then fed into a BiLSTM-CRF architecture to jointly extract entities, attributes, and multi-level spatial and causal relationships. Extracted results are structured using a content-knowledge model to build a spatially enriched knowledge graph, supporting semantic queries and intelligent reasoning. Experimental results demonstrate improved performance over baseline methods, showcasing the framework’s effectiveness in geohazard information extraction and disaster risk analysis. Full article

Sophisticated energy-harvesting technologies have swiftly progressed, expanding energy supply distribution and leveraging advancements in self-sustaining electronic devices. Despite substantial advancements in friction nanomotors within the last decade, a considerable technical obstacle remains for their flawless incorporation using printed electronics and autonomous devices. Integrating advanced triboelectric nanogenerator (TENG) technology with the rapidly evolving field of composite material 3D printing with has resulted in the advancement of three-dimensionally printed TENGs. Triboelectric nanogenerators are an important part of the next generation of portable energy harvesting and sensing devices that may be used for energy harvesting and artificial intelligence tasks. This paper systematically analyzes the continual development of 3D-printed TENGs and the integration of composite materials. The authors thoroughly review the latest material combinations of composite materials and 3D printing techniques for TENGs. Furthermore, this paper showcases the latest applications, such as using a TENG device to generate energy for electrical devices and harvesting energy from human motions, tactile sensors, and self-sustaining sensing gloves. This paper discusses the obstacles in constructing composite-material-based 3D-printed TENGs and the concerns linked to research and methods for improving electrical output performance. The paper finishes with an assessment of the issues associated with the evolution of 3D-printed TENGs, along with innovations and potential future directions in the dynamic realm of composite-material-based 3D-printed TENGs. Full article

Hand motion monitoring plays a vital role in medical rehabilitation, sports training, and human–computer interaction. High-sensitivity wearable biosensors are essential for accurate gesture recognition and precise motion analysis. In this work, we propose a high-sensitivity wearable glove based on a push–pull optical fiber sensor, designed to enhance the sensitivity and accuracy of hand motion biosensing. The sensor employs diagonal core reflectors fabricated at the tip of a four-core fiber, which interconnect symmetric fiber channels to form a push–pull sensing mechanism. This mechanism induces opposite wavelength shifts in fiber Bragg gratings positioned symmetrically under bending, effectively decoupling temperature and strain effects while significantly enhancing bending sensitivity. Experimental results demonstrate superior bending-sensing performance, establishing a solid foundation for high-precision gesture recognition. The integrated wearable glove offers a compact, flexible structure and straightforward fabrication process, with promising applications in precision medicine, intelligent human–machine interaction, virtual reality, and continuous health monitoring. Full article

Glove-based human–machine interfaces (HMIs) offer a natural, intuitive way to capture finger motions for gesture recognition, virtual interaction, and robotic control. However, many existing systems suffer from complex fabrication, limited sensitivity, and reliance on external power. Here, we present a flexible, self-powered glove HMI based on a minimalist triboelectric nanogenerator (TENG) sensor composed of a conductive fabric electrode and textured Ecoflex layer. Surface micro-structuring via 3D-printed molds enhances triboelectric performance without added complexity, achieving a peak power density of 75.02 μW/cm² and stable operation over 13,000 cycles. The glove system enables real-time LED brightness control via finger-bending kinematics and supports intelligent recognition applications. A convolutional neural network (CNN) achieves 99.2% accuracy in user identification and 97.0% in object classification. By combining energy autonomy, mechanical simplicity, and machine learning capabilities, this work advances scalable, multi-functional HMIs for applications in assistive robotics, augmented reality (AR)/(virtual reality) VR environments, and secure interactive systems. Full article

The integration of physical modelling, artificial intelligence (AI), and embedded electronics represents a promising direction in the development of intelligent systems for rehabilitation monitoring. Most existing approaches, however, treat biomechanical simulation and sensor-based AI separately, without leveraging their potential synergy. This study introduces a hybrid framework for upper limb rehabilitation that combines finite element modelling (FEM), AI-based trend classification, and a custom-designed electronic system for real-time signal acquisition and wireless data transmission. A mechanical model, developed in COMSOL 6.2 Multiphysics, simulates the interaction between a robotic glove and a deformable latex sphere. The latex material is described using a two-parameter Mooney–Rivlin hyperelastic formulation to capture large nonlinear deformations under realistic contact conditions. The high-fidelity simulation data are used to validate the signal acquisition chain and to train a supervised AI algorithm capable of classifying rehabilitation progress—whether improving or worsening—based on biomechanical features. An integrated electronic prototype enables seamless data flow to a cloud-based monitoring platform, supporting real-time feedback and adaptability. The classification algorithm demonstrates robust performance across different test conditions, while the electronic system confirms its applicability in rehabilitation settings. The novelty of this paper lies in the closed-loop integration of FEM-based simulation, AI-driven analysis, and embedded electronics into a unified monitoring architecture. This intelligent and non-invasive approach provides a scalable tool for tracking motor recovery and enhancing therapy effectiveness through adaptive, feedback-driven interventions. Full article

Research expands the boundaries of a subject, economy, and civilization. Peer review is at the heart of research and is understandably an expensive process. This work, with human-in-the-loop, aims to support the research community in multiple ways. It predicts quality, and acceptance, and recommends reviewers. It helps the authors and editors to evaluate research work using machine learning models developed based on a dataset comprising 18,000+ research papers, some of which are from highly acclaimed, top conferences in Artificial Intelligence such as NeurIPS and ICLR, their reviews, aspect scores, and accept/reject decisions. Using machine learning algorithms such as Support Vector Machines, Deep Learning Recurrent Neural Network architectures such as LSTM, a wide variety of pre-trained word vectors using Word2Vec, GloVe, FastText, transformer architecture-based BERT, DistilBERT, Google’s Large Language Model (LLM), PaLM 2, and TF-IDF vectorizer, a comprehensive system is built. For the system to be readily usable and to facilitate future enhancements, a frontend, a Flask server in the cloud, and a NOSQL database at the backend are implemented, making it a complete system. The work is novel in using a unique blend of tools and techniques to address most aspects of building a system to support the peer review process. The experiments result in a 86% test accuracy on acceptance prediction using DistilBERT. Results from other models are comparable, with PaLM-based LLM embeddings achieving 84% accuracy. Full article

Flexible electronics is pursuing a new generation of electronic skin and human–computer interaction. However, effectively detecting large dynamic ranges and highly sensitive human movements remains a challenge. In this study, flexible strain sensors with a self-assembled PDMS/MXene/MWCNT structure are fabricated, in which MXene particles are wrapped and bridged by dense MWCNTs, forming complex sliding conductive networks. Therefore, the strain sensor possesses an impressive sensitivity (gauge factor = 646) and 40% response range. Moreover, a fast response time of 280 ms and detection limit of 0.05% are achieved. The high performance enables good prospects in human detection, like human movement and pulse signals for healthcare. It is also applied to wearable smart data gloves, in which the CNN algorithm is utilized to identify 15 gestures, and the final recognition rate is up to 95%. This comprehensive performance strain sensor is designed for a wide array of human body detection applications and wearable intelligent systems. Full article

Communication among hard-of-hearing individuals presents challenges, and to facilitate communication, sign language is preferred. Many people in the deaf and hard-of-hearing communities struggle to understand sign language due to their lack of sign-mode knowledge. Contemporary researchers utilize glove and vision-based approaches to capture hand movement and analyze communication; most researchers use vision-based techniques to identify disabled people’s communication because the glove-based approach causes individuals to feel uncomfortable. However, the glove solution successfully identifies motion and hand dexterity, even though it only recognizes the numbers, words, and letters being communicated, failing to identify sentences. Therefore, artificial intelligence (AI) is integrated with the sign language prediction system to identify disabled people’s sentence-based communication. Here, wearable glove-related sign language information is utilized to analyze the recognition system’s efficiency. The collected inputs are processed using progression learning deep convolutional neural networks (PLD-CNNs). The technique known as progression learning processes sentences by dividing them into words, creating a training dataset. The model assists in efforts to understand sign language sentences. A memetic optimization algorithm is used to calibrate network performance, minimizing recognition optimization problems. This process maximizes convergence speed and reduces translation difficulties, enhancing the overall learning process. The created system is developed using the MATLAB (R2021b) tool, and its proficiency is evaluated using performance metrics. The experimental findings illustrate that the proposed system works by recognizing sign language movements with excellent precision, recall, accuracy, and F1 scores, rendering it a powerful tool in the detection of gestures in general and sign-based sentences in particular. Full article