Search Results (147)

With the rapid development of artificial intelligence (AI) technologies, machine learning (ML) has been widely applied in concrete material design, performance prediction, and intelligent structural engineering. Compared with traditional empirical approaches, ML can efficiently establish complex nonlinear relationships among concrete mix proportions, environmental factors, and performance indicators, thereby improving prediction efficiency, reducing experimental costs, and enabling multi-objective optimization of mix proportions. This paper systematically reviews the recent research progress of ML technologies in the field of concrete engineering, with particular emphasis on typical algorithms, including supervised learning, unsupervised learning, and reinforcement learning. Their applications in predicting workability, mechanical properties, durability performance, and mix proportion optimization are comprehensively summarized. In addition, recent advances in ML applications for crack detection and digital twin technologies are also discussed. Moreover, deep learning and computer vision (CV) technologies have significantly promoted the development of crack identification and structural health monitoring, whereas the integration of digital twin and Internet of Things (IoT) technologies has further expanded the application of ML in smart infrastructure. Finally, the current challenges associated with data quality, model interpretability, and engineering applications are summarized, and future research directions are discussed. Overall, by linking algorithm choice to specific concrete performance-prediction tasks, this review clarifies the conditions under which ML delivers reliable results and provides a structured reference for both researchers and practitioners. The comparative analysis indicates that ensemble tree-based models—particularly random forest and gradient-boosting variants such as XGBoost—together with well-tuned neural networks consistently achieve the highest predictive accuracy across most concrete properties, with reported test-set coefficients of determination commonly between 0.90 and 0.99, whereas limited data availability, inconsistent validation protocols, and restricted model interpretability remain the principal obstacles to engineering deployment. Full article

As generative artificial intelligence (GenAI) increasingly permeates educational contexts, understanding the factors driving learners’ Behavioral Intention (BI) toward GenAI-powered tools has become critical. This study integrates the Technology Acceptance Model (TAM), the Task-Technology Fit (TTF) framework, and privacy and ethical risk considerations to explore the determinants of Chinese higher education students’ Behavioral Intention to adopt these tools. Data were collected from 716 students via a structured self-reported questionnaire. A multi-stage analytical approach was employed by integrating structural equation modeling (SEM) with artificial neural networks (ANN) and support vector regression (SVR). SEM was first utilized to validate the theoretical hypotheses and the measurement model. Subsequently, ANN and SVR models were constructed to explore non-linear relationships and rank the importance of core predictors for Behavioral Intention, including Perceived Ease of Use (PEU), Privacy and Ethical Concerns (PEC), Perceived Technical Features (PTF), and TTF. The modeling performance of the two algorithms was then rigorously compared. The SEM results indicate that PTF exerts an indirect impact on Behavioral Intention via the sequential mediation of Task-Technology Fit and Perceived Usefulness (PU), while PEU positively influences both Perceived Usefulness and Behavioral Intention. Notably, PEC did not exhibit a significant negative effect on users’ Attitude (ATT) or Behavioral Intention. These findings were further elucidated by the machine learning analyses, where PTF and PEU emerged as the dominant predictors, whereas the non-linear contribution of PEC was marginal. Furthermore, SVR outperformed ANN in terms of predictive accuracy and model stability. This study demonstrates the efficacy of combining theoretical modeling with machine learning techniques to elucidate the adoption mechanisms of GenAI in higher education. In addition, preliminary teaching observations in undergraduate mathematics and logistics management courses link quantitative results with actual learning scenarios. We acknowledge that future research should validate these patterns using observed behavioral data. Full article

Background: Dengue fever remains a major public health challenge in endemic regions, where recovery duration varies considerably across patients due to a combination of clinical, demographic, and contextual factors. Although machine learning (ML) approaches have increasingly been applied to dengue related prediction tasks, many existing models operate as black boxes, limiting their interpretability and practical usefulness in healthcare settings. This study presents an Explainable Artificial Intelligence (XAI) based machine learning framework for analyzing dengue recovery duration using a multi-center clinical dataset collected from healthcare institutions across Khyber Pakhtunkhwa, Pakistan. Methods: Clinical records from 100 laboratory-confirmed dengue patients treated across multiple healthcare institutions were analyzed. The dataset included demographic, socio-economic, and clinical variables. Four machine learning models: Linear Regression, Decision Tree, Random Forest, and Neural Network, were developed and evaluated using 10-fold cross-validation. Explainability techniques, including Partial Dependence Plots (PDP), Individual Conditional Expectation (ICE), and Local Interpretable Model-Agnostic Explanations (LIME), were employed to investigate global and patient specific factors influencing recovery duration. Results: Among the evaluated models, Random Forest demonstrated the best overall predictive performance, achieving the lowest Root Mean Square Error (RMSE; 11.29 days) and Mean Absolute Error (MAE; 9.09 days), corresponding to a 40.4% reduction in prediction error compared with Linear Regression. Decision Tree also showed substantial improvement, reducing RMSE by 37%, whereas the Neural Network achieved a more modest improvement of 8.6%. Although all models exhibited relatively low coefficient of determination (R²) values (maximum R² = 0.026), the explainability analyses consistently identified age and platelet count as the most influential predictors of recovery duration. Older age and lower platelet counts were generally associated with longer recovery periods, while hospital type, education level, and blood group also contributed to prediction outcomes. ICE and LIME analyses further revealed considerable patient level heterogeneity, indicating that recovery trajectories are shaped by complex interactions among clinical, demographic, and contextual factors rather than a single dominant predictor. Full article

Background: Elongated styloid processes and ossifications of the stylohyoid chain can be observed on dental imaging modalities. In this study, we assessed the performance of artificial intelligence (AI) in identifying elongated styloid processes and ossifications of the stylohyoid chain. Methods: We performed a systematic review of relevant studies published between April 2020 and April 2026 on PubMed, Scopus, and Web of Science. Relevant data were extracted using predefined criteria. We assessed the risk of bias using categories derived from QUADAS-2, CLAIM and STARD-AI. Results: Four original studies met the inclusion criteria. Of these, only two specifically addressed elongated styloid processes on panoramic images (OPGs). For one study that utilized ML algorithms, both logistic regression and neural networks achieved 100% performance, while naive Bayes demonstrated substantially lower performance than either model. Another study using deep learning algorithms observed accuracy rates of 97.49% and 84.11%, and area under the curve values of 0.9825 and 0.8943 for EfficientNetB5 and InceptionV3 models. A broader study using OPG anomaly detection reported target-level data for stylohyoid ligament ossification. The fourth study used cone-beam computed tomography images, including stylohyoid ligament ossification as part of a multi-class soft tissue calcification/ossification detection task. Due to significant variability in target definitions, imaging modalities, validation methods, and performance metrics across studies, a meta-analysis was not feasible. Conclusions: The use of AI-based systems for detecting elongated styloid processes and stylohyoid chain ossification shows potential for future clinical utility; however, current evidence is insufficient to support independent clinical practice. Future research should incorporate larger-scale prospective multicenter validations as well as external validation on a patient-by-patient basis when possible. Additional research into the clinical implications associated with both false-positive and false-negative results is warranted. Full article

Cyber-physical smart infrastructures integrate sensing devices, communication networks, control components, and service platforms, which makes them vulnerable to malicious activities that may evolve gradually through several attack stages. The objective of this study is to develop and evaluate a simulation-based cybersecurity framework capable of detecting a proposed novel multi-stage cyber attack and identifying its internal progression within a realistic smart infrastructure environment. To achieve this objective, a NetSim-based cyber-physical smart infrastructure was modeled to generate both normal operational traffic and staged malicious traffic. The generated traffic was captured, processed, labeled, and transformed into a stage-aware cybersecurity dataset. An artificial neural network (ANN) model was then trained and evaluated for two detection tasks: binary classification of normal versus attack traffic and multi-class classification of compromise, coordination, and execution attack stages. Twenty experimental configurations were designed to examine the model under progressively broader infrastructure contexts, including sensing, service, gateway, control, backbone, and full-span operational scenarios. The best binary testing performance was achieved in the eighteenth experimental configuration, representing a broad full-span infrastructure scenario, with 97.96% accuracy, 97.80% precision, 97.65% recall, 97.72% F1-score, and 1.06% false positive rate. For stage-aware multi-class detection, the ANN model achieved 96.97% accuracy, 96.36% macro-averaged precision, 96.20% macro-averaged recall, 96.28% macro-averaged F1-score, and 96.55% weighted F1-score. Macro-averaged metrics report the unweighted average performance across classes, while weighted F1-score accounts for class support. These results show that the proposed simulation-based framework can generate realistic attack-aware traffic data and support reliable ANN-based detection of both attack presence and attack-stage progression. Full article

An electroencephalogram (EEG) signals provide vital insights for stroke rehabilitation, yet analyzing these complex, high-dimensional data to detect gait anomalies remains challenging. Artificial intelligence offers a promising solution to precisely identify abnormal movements, assisting physicians in optimizing personalized treatments. This exploratory pilot study aims to evaluate multi-class deep learning frameworks for classifying eight distinct normal and abnormal motor activities in stroke patients using EEG data. EEG signals from eight stroke patients were utilized to train and evaluate a customized Convolutional Neural Network (CNN), DeepConvNet, and EEGNet. Furthermore, channel reduction configurations (32, 22, and 15 channels) were investigated to determine optimal clinical setups. In the Leave-One-Out Cross-Validation (LOOCV) evaluation involving seven patients, EEGNet attained the highest descriptive average F1-score of 0.810. Moreover, when assessed independently on an unseen patient, it achieved an F1-score of 0.915, indicating its potential in accommodating individual differences within this limited cohort. Moreover, EEGNet exhibited a low false positive rate of 0.175, minimizing false alarms. While the 32-channel setup yielded the highest consistency, reduced configurations served as hypothesis-generating for specific tasks. In conclusion, EEGNet demonstrated superior average performance in differentiating complicated gait patterns in this exploratory pilot study, underscoring its promise for real-time, non-invasive monitoring in stroke neurorehabilitation. Full article

Gliomas constitute the majority of primary brain tumors, and accurate diagnosis through MRI is essential for patient management. Existing computer-aided diagnosis approaches frequently rely on tumor segmentation frameworks. In this study, a segmentation-independent framework for volumetric low-grade versus high-grade glioma (LGG/HGG) classification is proposed using a Convolutional Neural Network (CNN) designed through task-oriented Neural Architecture Search (NAS). The proposed method was evaluated on a multi-center dataset comprising 1194 patients with pre-operative MRI scans, including T1-CE and FLAIR sequences from four publicly available cohorts. NAS was conducted within a controlled search space to optimize a 3D U-Net–based backbone using Tree-structured Parzen Estimator (TPE) combined with Hyperband pruning. The optimized backbone was enhanced with residual connections and Squeeze-and-Excitation (SE) attention mechanisms to improve feature representation and training stability. Internal validation employed repeated 5-fold cross-validation across all four multi-center datasets. An external experiment used REMBRANDT as a test cohort (49 LGG, 19 HGG). The proposed model achieved 88.25% internal accuracy and 75.51% external accuracy (macro-F1: 87.37% internal, 73.77% external), outperforming benchmark 3D CNNs. Explainable Artificial Intelligence (XAI) analysis based on Grad-CAM revealed robust tumor localization without segmentation supervision, validated against available ground-truth masks. Additional experiments demonstrated the model’s generalization capacity, achieving 89.51% accuracy for IDH mutation prediction and 78.74% for multi-grade classification. Full article

The question of verification of food quality has stood before scientists since ancient times, and, nowadays, the advances in science and technology have made it a very challenging task. Laser-induced fluorescence (LIF) spectroscopy has become a very useful instrument for sample characterization. Nevertheless, analysis of complex multi-component spectra is difficult to approach. In recent years, the capabilities of artificial intelligence have attracted a lot of attention, as they open doors to efficient solutions of many problems that otherwise require a lot of time, effort, expenses and often inspiration. In the present work, we use LIF spectra of mixtures of sunflower and extra virgin olive oils with different concentrations and apply neural network (NN) algorithms with the aim of improving the strategies for concentration determination. Two different approaches have been applied and their output has been compared and commented. More specifically, the task of concentration recognition has been targeted as a classification and as a fitting problem. We formulate four diagnostic parameters with biochemical meaning and compare the NN performance when training with raw spectra and with the diagnostic parameters. The correct choice of appropriate diagnostic parameters is of importance from the point of view of biochemical interpretability and analysis, whereas “black box” full-spectra training might be beneficial for end-user applications. Our results show that these methods perform well even with very scarce data and outline preliminary strategies for defining diagnostic criteria. Full article

Recently, artificial neural networks (ANNs) have shown impressive performance in the compressive hyperspectral imaging (CHI) reconstruction task, but the high energy consumption limits their deployment on energy-constrained devices. This paper develops a novel spiking neural network (SNN), termed spiking spectral-weighting reconstruction network (SSWR-Net), to significantly improve the energy–efficiency ratio in CHI reconstruction. Firstly, a spiking spectral-weighting convolution block is proposed to adaptively modulate the spiking signals, enabling the SNN to fit continuous spectral correlation curves. Secondly, a residual feature reuse module with more direct connections is designed to achieve efficient and lightweight spatial–spectral feature extraction. Thirdly, customized feature scaling architectures are introduced to resolve the dimensional mismatch issue and enhance information flow. Finally, we propose a novel temporal-wise progressive training method to optimize the multi-timestep SSWR-Net, which can significantly improve both training efficiency and reconstruction quality. Both simulation and real experiments demonstrate the superiority of the proposed method in both CHI reconstruction performance and energy efficiency. Specifically, SSWR-Net outperforms its ANN-based counterpart by 0.87 dB at a 19.74% energy cost. Full article

Many machine learning and deep learning algorithms based on Artificial Neural Networks (ANNs) have been implemented on software platforms for handwritten digit and character recognition. However, an ANN is difficult to deploy on an embedded platform based on a Central Processing Unit (CPU) because of its large computation, complex structure, and frequent memory access. However, Field Programmable Gate Array (FPGA) devices facilitate this task and offer the capability to design fully customizable hardware architectures. Additionally, they provide high flexibility and high parallel computations based on parallel processing techniques, and they contain sufficient on-chip Digital Signal Processing (DSP) blocks useful for complicated multiplications. In this paper, we present a detailed FPGA-based implementation of a handwritten digit recognition system based on a Multi-Layer Perceptron (MLP) model. The internal modules of the network are designed using the VHSIC Hardware Description Language (VHDL) to achieve a high-level optimization on the hardware platform, and the functionality is simulated and tested using Vivado ISIM Tools. The system has been characterized to reach acceptable performance compared to previous approaches. After implementing the whole neural network on a Xilinx Pynq-Z2 board, it occupies in the device 20758 LUTs, 4426 FFs, 3.50 blocks of random-access memory (BRAM), and 42 DSPs. It reaches an execution time of 2.192 µs to recognize a handwritten number, while consuming only 0.36 Watts, and it achieves a classification accuracy of 97%. Additionally, the proposed architecture can be easily scaled on different FPGA devices thanks to its regularity. Therefore, it offers more portability of the architecture and can be used on different real embedded applications. Full article

As artificial intelligence (AI) increasingly reshapes the global technological and economic landscape, understanding and forecasting national AI competitiveness has become an important yet challenging task. Unlike conventional Analytic Hierarchy Process (AHP)–Entropy-based evaluation methods and machine learning approaches that treat indicators as isolated or weakly connected features, this study proposes an integrated framework that explicitly represents inter-indicator dependencies as a structured global topology. Based on an Input–Process–Output–Environment (IPOE) system with 24 indicators for 10 major economies during 2016–2025, AHP–Entropy, XGBoost, Design of Experiments (DOE), and Bayesian networks are combined to identify dependency pathways among indicators. These structural relations are embedded into a graph neural network (GNN) for competitiveness assessment, while a Dynamic GNN-ARIMA module is developed to project future competitiveness trajectories under limited samples. Building on these projections, a multi-objective fund allocation optimization model is constructed and solved via the NSGA-II algorithm to reduce policy volatility while maintaining future AI competitiveness with a strategic investment of RMB 500 billion. Results show that the U.S. remains the clear leader, followed by China, while mid-tier economies show noticeable reshuffling. Under the Min-Variance strategy with the investment, China is projected to significantly narrow the gap with the United States, reaching a comparable level of competitiveness. Full article

Pig weighing is an essential procedure for monitoring growth and animal health; however, conventional methods are often labor-intensive, costly, and potentially stressful. In this context, this study proposes a non-invasive approach for estimating the body weight of pigs during the growing stage based on computer vision and the YOLOv11 algorithm, enabling automatic segmentation and individual identification in multi-animal environments. The study used RGB images of 10 group-housed pigs captured throughout the growing phase, in which automatic dorsal segmentation was combined with individual identification through numerical markings. From the generated binary masks, the segmented dorsal area was extracted and used as a predictor variable in Linear Regression and a Multilayer Perceptron (MLP) Artificial Neural Network. The YOLOv11 model showed consistent performance in the segmentation task, achieving test-set metrics of Precision = 0.849, Recall = 0.886, mAP@0.50 = 0.936, and mAP@0.50–0.95 = 0.819, demonstrating good generalization capability in scenarios with intense animal interaction. In the weight prediction stage, Linear Regression and the MLP achieved high coefficients of determination (R² = 0.96 and 0.95, respectively) with low errors (RMSE = 1.52 kg and 1.63 kg; MAE = 1.20 kg and 1.25 kg), indicating a strong correlation between segmented dorsal area and actual body weight. Class-wise analysis revealed superior performance for classes 7 and 9, with R² values up to 0.98 and RMSE below 1.1 kg, whereas class 8 showed greater error dispersion, associated with higher morphological variability and a smaller number of available samples. These results demonstrate that the direct use of morphometric information extracted from segmented masks in 2D images constitutes a robust, accurate, and low-cost approach for automatic pig body-weight estimation. Moreover, this study is among the few addressing this task specifically during the growing stage, highlighting its potential for future deployment in embedded systems and intelligent monitoring platforms for precision pig farming, although further evaluation of computational efficiency and real-time performance is still required. Full article

Brain–computer interfaces (BCIs) are essential in assistive technologies to restore mobility in individuals with motor impairments. Although electroencephalography (EEG)-based brain-controlled wheelchairs have been extensively studied, most tongue-controlled systems rely on physical tongue movements, intraoral devices, or limited offline commands, which reduces the usability and comfort. This study introduces an EEG-based tongue motor imagery (MI) BCI for intuitive and entirely mental wheelchair control. By leveraging preserved motor function and the cortical representation of the tongue, the system enables natural four-directional control through imagined tongue movements. Six imagined tongue actions—touching the left and right mouth corners, the upper and lower lips, and producing left and right cheek bulges—were designed to elicit alpha-band event-related desynchronization (ERD) patterns over the tongue motor cortex. EEG data were collected from 15 healthy participants using a 14-channel consumer-grade EMOTIV EPOC X headset. Alpha-band ERD features were extracted and classified using linear discriminant analysis, support vector machine, naïve Bayes, and artificial neural networks (ANNs). Simpler command sets yielded the highest accuracy: two-class tasks achieved 76.19%, while the performance decreased with increasing task complexity. The ANN achieved superior results in multi-class scenarios. The proposed tongue MI method offers initial support for developing a BCI control strategy for assistive technology; however, further improvements in classification techniques, user training, and real-time validation are needed to improve the robustness and practical usability. Full article

Background/Objectives: The rise of artificial intelligence is injecting intelligence into the healthcare sector, including surgery. Vision-based intelligent systems that assist surgical procedures can significantly increase productivity, safety, and effectiveness during surgery. Surgical instruments are central components of any surgical intervention, yet detecting and locating them during live surgeries remains challenging due to adverse imaging conditions such as blood occlusion, smoke, blur, glare, low-contrast, instrument scale variation, and other artifacts. Methods: To address these challenges, we developed an advanced segmentation architecture termed the frozen-filters-based morphology-aware segmentation network (FFMS-Net). Accurate surgical instrument segmentation strongly depends on edge and morphology information; however, in conventional neural networks, this spatial information is progressively degraded during spatial processing. FFMS-Net introduces a frozen and learnable feature pipeline (FLFP) that simultaneously exploits frozen edge representations and learnable features. Within FLFP, Sobel and Laplacian filters are frozen to preserve edge and orientation information, which is subsequently fused with learnable initial spatial features. Moreover, a tri-atrous blending (TAB) block is employed at the end of the encoder to fuse multi-receptive-field-based contextual information, preserving instrument morphology and improving robustness under challenging conditions such as blur, blood occlusion, and smoke. Datasets focused on surgical instruments often suffer from severe class imbalance and poor instrument visibility. To mitigate these issues, FFMS-Net incorporates a progressively structure-preserving decoder (PSPD) that aggregates dilated and standard spatial information after each upsampling stage to maintain class structure. Multi-scale spatial features from different encoder levels are further fused using light skip paths (LSPs) to project channels with task-relevant patterns. Results/Conclusions: FFMS-Net is extensively evaluated on three challenging datasets: UW-Sinus-surgery-live, UW-Sinus-cadaveric, and CholecSeg8k. The proposed method demonstrates promising performance compared with state-of-the-art approaches while requiring only 1.5 million trainable parameters. In addition, an open-source large language model is integrated for non-clinical summarization of the surgical scene based on the predicted mask and deterministic descriptors derived from it. Full article

Background: Artificial intelligence (AI) shows promising results in lymphoma detection, prediction, and classification. However, translating these findings into practice requires a rigorous assessment of potential biases, clinical utility, and further validation of research models. Objective: The goal of this study was to summarize existing studies on artificial intelligence models for the histopathological detection of lymphoma. Design: This study adhered to the PRISMA Extension for Scoping Reviews (PRISMA-ScR) guidelines. A systematic search was conducted across three major databases (Scopus, PubMed, Web of Science) for English-language articles and reviews published between 2016 and 2025. Seven precise search queries were applied to identify relevant publications, accounting for variations in study modality, algorithmic architectures, and disease-specific terminology. Results: The search identified 612 records, of which 36 articles met the inclusion criteria. These studies presented 36 AI models, comprising 30 diagnostic and six prognostic applications, with Convolutional Neural Networks (CNNs) being the predominant architecture. Regarding data sources, 83% (30/36) of datasets utilized Hematoxylin and Eosin (H&E)-stained images, while the remainder relied on diverse modalities, including IHC-stained slides, bone marrow smears, and other tissue preparations. Studies predominantly utilized retrospective, private cohorts with sample sizes typically ranging from 50 to 400 patients; only a minority leveraged open-access repositories (e.g., Kaggle, TCGA). The primary application was slide-level multi-class classification, distinguishing between specific lymphoma subtypes and non-neoplastic controls. Beyond diagnosis, a subset of studies explored advanced prognostic tasks, such as predicting chemotherapy response and disease progression (e.g., in CLL), as well as automated biomarker quantification (c-MYC, BCL2, PD-L1). Reported diagnostic performance was generally high, with accuracy ranging from 60% to 100% (clustering around 90%) and AUC values spanning 0.70 to 0.99 (predominantly >0.90). Conclusions: While AI models demonstrate high diagnostic accuracy, their translation into practice is limited by unstandardized protocols, morphological complexity, and the “black box” nature of algorithms. Critical issues regarding data provenance, image noise, and lack of representativeness raise risks of systematic bias, hence the need for rigorous validation in diverse clinical environments. Full article