AI

Evacuation in public places under emergency situations represents a significant area of management research. With the rapid development of the railway industry, the evacuation of railway stations has gradually attracted attention. This article employs the minimization of congestion degree and total evacuation time as primary objectives. In addition, the psychological behavior of individuals and the impact of congestion are sufficiently considered. Moreover, an adaptive Cauchy mutation operator is adopted for flexible population diversity. As a result, a multi-objective optimization model for the evacuation paths is established, with an improved adaptive quantum ant colony algorithm, and a comparison between the model based on adaptive quantum ant colony algorithm and the traditional ant colony model is made. Full article

Stroke is a major global cause of death and disability and necessitates both quick diagnosis and treatment within narrow windows of opportunity. CT scanning is still the first-line imaging in the acute phase, but correct interpretation may not always be readily available and may not be resource-available in poor and rural health systems. Automated stroke classification systems can offer useful diagnostic assistance, but clinical application demands high accuracy and explainable decision-making to maintain physician trust and patient safety. In this paper, a ResNet-18 model was trained on 6653 CT brain scans (hemorrhagic stroke, ischemia, normal) with two-phase fine-tuning and transfer learning, XRAI explainability analysis, and web-based clinical decision support system integration. The model performed with 95% test accuracy with good performance across all classes. This system has great potential for emergency rooms and resource-poor environments, offering quick stroke evaluation when specialists are not available, particularly by rapidly excluding hemorrhagic stroke and assisting in the identification of ischemic stroke, which are critical steps in considering tissue plasminogen activator (tPA) administration within therapeutic windows in eligible patients. The combination of classification, explainability, and clinical interface offers a complete framework for medical AI implementation. Full article

Open-vocabulary object detection (OVOD) aims to localize and recognize objects in images by leveraging category-specific textual inputs, including both known and novel categories. While existing methods excel in general scenarios, their performance significantly deteriorates in domain-specific fine-grained detection because of their heavy reliance on high-quality textual descriptions. In specialized domains, such textual descriptions are often affected by newly introduced terms or subjective human biases, limiting their applicability. In this paper, we propose an attribute decomposition–aggregation approach for the OVOD to address these challenges. By decomposing categories into fine-grained attributes and learning them in a multi-label manner, our method mitigates text quality issues caused by novel terms and human bias. During inference, unseen fine-grained category texts can be effectively represented by combining the decomposed attributes for detection. Even if the model learns the attributes, a key limitation of current methods is the insufficient utilization of textual attributes. To mitigate this issue, we propose an attribute-aggregation module that enhances the discriminative capability by emphasizing critical attributes for distinguishing target objects from foreground elements. To demonstrate the effectiveness of our OVOD framework, we evaluate our method on both our newly constructed military dataset and the public LAD dataset. Experimental results demonstrate that our method outperforms existing methods in domain-specific fine-grained open-vocabulary detection tasks. Full article

Uterine fibroids are one of the leading health concerns for women worldwide, affecting up to 80% of women by the age of 50. While recent advancements have improved the diagnosis and treatment of fibroids, the current standard of care still faces important limitations due to the need for a personalized approach to treatment. Uterine fibroid embolization (UFE) has emerged as a promising minimally invasive alternative to traditional surgery, offering advantages such as shorter recovery times, fewer complications, and the preservation of the uterus. However, despite their highly reported effectiveness, only about 1% of eligible patients are offered UFE. This drastic underutilization is partially due to limited physician confidence in predicting patient-specific outcomes. To address this challenge, in this study, we aim to present an objective analysis of the factors influencing UFE success and introduce a scalable and interpretable machine learning (ML) system designed to support clinical decision-making. We have curated a dataset that includes 74 patients, with a total of 311 fibroids for our analysis. We have also developed two sets of ML models for predicting UFE procedure success based on a pre-operative MRI scan as the input. The first model predicts overall procedure success and the likelihood of relieving specific symptoms, achieving an accuracy of 75% (AUC = 0.74) for procedure outcome and 81–88% (AUC = 0.81–0.87) for different symptoms, respectively. The second set of models predicts the success of each individual fibroid responding to the treatment, achieving a 76% accuracy and 75% F-1 score. The AI models in this study can potentially provide patient-specific prediction of procedure effectiveness on both patient-level and fibroid-level, enhancing procedure referral accuracy. Full article

Timely, objective pain recognition in dairy cattle is essential for welfare assurance, productivity, and ethical husbandry yet remains elusive because evolutionary pressure renders bovine distress signals brief and inconspicuous. Without verbal self-reporting, cows suppress overt cues, so automated vision is indispensable for on-farm triage. Although earlier systems tracked whole-body posture or static grimace scales, frame-level detection of facial micro-expressions has not been explored fully in livestock. We translate micro-expression analytics from automotive driver monitoring to the barn, linking modern computer vision with veterinary ethology. Our two-stage pipeline first detects faces and 30 landmarks using a custom You Only Look Once (YOLO) version 8-Pose network, achieving a 96.9% mean average precision ($mAP$) at an Intersection over the Union (IoU) threshold of 0.50 for detection and 83.8% Object Keypoint Similarity (OKS) for keypoint placement. Cropped eye, ear, and muzzle patches are encoded using a pretrained MobileNetV2, generating 3840-dimensional descriptors that capture millisecond muscle twitches. Sequences of five consecutive frames are fed into a 128-unit Long Short-Term Memory (LSTM) classifier that outputs pain probabilities. On a held-out validation set of 1700 frames, the system records 99.65% accuracy and an F1-score of 0.997, with only three false positives and three false negatives. Tested on 14 unseen barn videos, it attains 64.3% clip-level accuracy (i.e., overall accuracy for the whole video clip) and 83% precision for the pain class, using a hybrid aggregation rule that combines a 30% mean probability threshold with micro-burst counting to temper false alarms. As an early exploration from our proof-of-concept study on a subset of our custom dairy farm datasets, these results show that micro-expression mining can deliver scalable, non-invasive pain surveillance across variations in illumination, camera angle, background, and individual morphology. Future work will explore attention-based temporal pooling, curriculum learning for variable window lengths, domain-adaptive fine-tuning, and multimodal fusion with accelerometry on the complete datasets to elevate the performance toward clinical deployment. Full article

Mass shootings are forms of loosely defined violent crimes typically involving four or more casualties by firearm and have become increasingly more frequent, and organized and speedy responses from police are necessary to mitigate harm and neutralize the perpetrator. Recent, widely publicized police responses to mass shooting events have been criticized by the media, government, and public. With the advancements in artificial intelligence, specifically single-shot detection (SSD) models, computer programs can detect harmful weapons within efficient time frames. We utilized YOLO (You Only Look Once), an SSD with a Convolutional Neural Network, and used versions 5, 7, 8, 9, 10, and 11 to develop our detection system. For our data, we used a Roboflow dataset that contained almost 17,000 images of real-life handgun scenarios, designed to skew towards positive instances. We trained each model on our dataset and exchanged different hyperparameters, conducting a randomized trial. Finally, we evaluated the performance based on precision metrics. Using a Python-based design, we tested our model’s capabilities for surveillance functions. Our experimental results showed that our best-performing model was YOLOv10s, with an mAP-50 (mean average precision 50) of 98.2% on our dataset. Our model showed potential in edge computing settings. Full article

Camouflaged object detection (COD) represents one of the most challenging tasks in computer vision, requiring sophisticated approaches to accurately extract objects that seamlessly blend within visually similar backgrounds. While contemporary techniques demonstrate promising detection performance, they predominantly suffer from computational complexity and resource requirements that severely limit their deployment in real-time applications, particularly on mobile devices and edge computing platforms. To address these limitations, we propose LiteCOD, an efficient lightweight framework that integrates local and global perceptions through holistic feature fusion and specially designed efficient attention mechanisms. Our approach achieves superior detection accuracy while maintaining computational efficiency essential for practical deployment, with enhanced feature propagation and minimal computational overhead. Extensive experiments validate LiteCOD’s effectiveness, demonstrating that it surpasses existing lightweight methods with average improvements of 7.55% in the F-measure and 8.08% overall performance gain across three benchmark datasets. Our results indicate that our framework consistently outperforms 20 state-of-the-art methods across quantitative metrics, computational efficiency, and overall performance while achieving real-time inference capabilities with a significantly reduced parameter count of 5.15M parameters. LiteCOD establishes a practical solution bridging the gap between detection accuracy and deployment feasibility in resource-constrained environments. Full article

Digital livestock farming faces a critical deployment challenge: bridging the gap between cutting-edge AI algorithms and practical implementation in resource-constrained agricultural environments. While deep learning models demonstrate exceptional accuracy in laboratory settings, their translation to operational farm systems remains limited by computational constraints, connectivity issues, and user accessibility barriers. Dairy DigiD addresses these challenges through a novel edge-cloud AI framework integrating YOLOv11 object detection with DenseNet121 physiological classification for cattle monitoring. The system employs YOLOv11-nano architecture optimized through INT8 quantization (achieving 73% model compression with <1% accuracy degradation) and TensorRT acceleration, enabling 24 FPS real-time inference on NVIDIA Jetson edge devices while maintaining 94.2% classification accuracy. Our key innovation lies in intelligent confidence-based offloading: routine detections execute locally at the edge, while ambiguous cases trigger cloud processing for enhanced accuracy. An entropy-based active learning pipeline using Roboflow reduces the annotation overhead by 65% while preserving 97% of the model performance. The Gradio interface democratizes system access, reducing technician training requirements by 84%. Comprehensive validation across ten commercial dairy farms in Atlantic Canada demonstrates robust performance under diverse environmental conditions (seasonal, lighting, weather variations). The framework achieves mAP@50 of 0.947 with balanced precision-recall across four physiological classes, while consuming 18% less energy than baseline implementations through attention-based optimization. Rather than proposing novel algorithms, this work contributes a systems-level integration methodology that transforms research-grade AI into deployable agricultural solutions. Our open-source framework provides a replicable blueprint for precision livestock farming adoption, addressing practical barriers that have historically limited AI deployment in agricultural settings. Full article

Efficient spectrum utilization is critical for meeting the growing data demands of modern wireless communication networks. Automatic Modulation Classification (AMC) plays a key role in enhancing spectrum efficiency by accurately identifying modulation schemes in received signals—an essential capability for dynamic spectrum allocation and interference mitigation, particularly in cognitive radio (CR) systems. With the increasing deployment of smart edge devices, such as IoT nodes with limited computational and memory resources, there is a pressing need for lightweight AMC models that balance low complexity with high classification accuracy. In this study, we propose a low-complexity, lightweight deep learning (DL) AMC model optimized for resource-constrained edge devices. We introduce a dual-path deep residual shrinkage network (DP-DRSN) with garrote thresholding for effective signal denoising, and we designed a compact hybrid CNN-LSTM architecture comprising only 27,072 training parameters. The proposed model achieved average classification accuracies of 61.20%, 63.78%, and 62.13% on the RML2016.10a, RML2016.10b, and RML2018.01a datasets, respectively, demonstrating a strong balance between model efficiency and classification performance. These results highlight the model’s potential for enabling accurate and efficient AMC on edge devices with limited resources, despite not surpassing state-of-the-art accuracy owing to its deliberate emphasis on computational efficiency. Full article

Social media empowers freedom of expression but is often misused for abuse and hate. The detection of such content is crucial, especially in under-resourced languages like Urdu. To address this challenge, this paper designed a comprehensive multilabel dataset, the Urdu toxicity corpus (UTC). Second, the Urdu toxicity detection model is developed, which detects toxic content from an Urdu dataset presented in Nastaliq Font. The proposed framework initially processed the gathered data and then applied feature engineering using term frequency-inverse document frequency, bag-of-words, and N-gram techniques. Subsequently, the synthetic minority over-sampling technique is used to address the data imbalance problem, and manual data annotation is performed to ensure label accuracy. Four machine learning models, namely logistic regression, support vector machine, random forest, and gradient boosting, are applied to preprocessed data. The results indicate that the RF outperformed all evaluation metrics. Deep learning algorithms, including long short-term memory (LSTM), Bidirectional LSTM, and gated recurrent unit, have also been applied to UTC for classification purposes. Random forest outperforms the other models, achieving a precision, recall, F1-score, and accuracy of 0.97, 0.99, 0.98, and 0.99, respectively. The proposed model demonstrates a strong potential to detect rude, offensive, abusive, and hate speech content from user comments in Urdu Nastaliq. Full article

As large language model (LLM) tutors evolve from scripted helpers into adaptive educational partners, their capacity for self-regulation, ethical decision-making, and internal monitoring will become increasingly critical. This paper introduces the Needs-Driven Consciousness Framework (NDCF) as a novel, integrative architecture that combines Dennett’s multiple drafts model, Damasio’s somatic marker hypothesis, and Tulving’s tripartite memory system into a unified motivational design for synthetic consciousness. The NDCF defines three core regulators, specifically Survive (system stability and safety), Thrive (autonomy, competence, relatedness), and Excel (creativity, ethical reasoning, long-term purpose). In addition, there is a proposed supervisory Protect layer that detects value drift and overrides unsafe behaviours. The core regulators compute internal need satisfaction states and urgency gradients, feeding into a softmax-based control system for context-sensitive action selection. The framework proposes measurable internal signals (e.g., utility gradients, conflict intensity Ω), behavioural signatures (e.g., metacognitive prompts, pedagogical shifts), and three falsifiable predictions for educational AI testbeds. By embedding these layered needs directly into AI governance, the NDCF offers (i) a psychologically and biologically grounded model of emergent machine consciousness, (ii) a practical approach to building empathetic, self-regulating AI tutors, and (iii) a testable platform for comparing competing consciousness theories through implementation. Ultimately, the NDCF provides a path toward the development of AI tutors that are capable of transparent reasoning, dynamic adaptation, and meaningful human-like relationships, while maintaining safety, ethical coherence, and long-term alignment with human well-being. Full article

The uncertainty and confrontational nature of war itself pose significant challenges to the collection and storage of aerial battlefield temporal data. To address the issue of insufficient training of intelligent models caused by the scarcity of air battlefield situation data, this paper designs an air battlefield time series data augmentation model based on a lightweight denoising diffusion probabilistic model (LDMKD-DA). Considering the advantages of a denoising diffusion probabilistic model (DDPM) in processing images, this paper transforms 1D time series data into image data. 1D univariate time series data, such as High-resolution Range Profile dataset, are transformed by Gramian angular fields and Markov transition fields. Multivariate time series data, such as the air target intention dataset, are transformed by matrix expansion. Then, the data augmentation model is constructed based on the denoising diffusion probabilistic model. Considering the need for miniaturization and intelligence in future combat platforms, the depthwise separable convolution is introduced to lighten the DDPM, and, at the same time, the improved knowledge distillation method is introduced to accelerate the sampling process. The experimental results show that LDMKD-DA is capable of generating synthetic data similar to real data with high quality while significantly reducing FLOPs and params, while having significant advantages in univariate and multivariate time series data amplification. Full article

Depression is a serious mental health disorder affecting cognition, emotions, and behavior. It impacts over 300 million people globally, with mental health care costs exceeding $1 trillion annually. Traditional diagnostic methods are often expensive, time-consuming, stigmatizing, and difficult to access. This study leverages NLP techniques to identify depressive cues in social media posts, focusing on both standard Urdu and code-mixed Roman Urdu, which are often overlooked in existing research. To the best of our knowledge, a script-conversion and combination-based approach for Roman Urdu and Nastaliq Urdu has not been explored earlier. To address this gap, our study makes four key contributions. First, we created a manually annotated dataset named Ruda-2025, containing posts in code-mixed Roman Urdu and Nastaliq Urdu for both binary and multiclass classification. The binary classes are depression” and not depression, with the depression class further divided into fine-grained categories: Mild, Moderate, and Severe depression alongside not depression. Second, we applied first-time two novel techniques to the RUDA-2025 dataset: (1) script-conversion approach that translates between code-mixed Roman Urdu and Standard Urdu and (2) combination-based approach that merges both scripts to make a single dataset to address linguistic challenges in depression assessment. Finally, we employed 60 different experiments using a combination of traditional machine learning and deep learning techniques to find the best-fit model for the detection of mental disorder. Based on our analysis, our proposed model (mBERT) using custom attention mechanism outperformed baseline (XGB) in combination-based, code-mixed Roman and Nastaliq Urdu script conversions. Full article

In recent years, artificial intelligence (AI) has emerged as a transformative force across various sectors of modern society, reshaping economic landscapes, social interactions, and ethical considerations. This paper explores the multifaceted impact of AI, analyzing its implications for employment, privacy, and decision-making processes. By synthesizing recent research and case studies, we investigate the dual nature of AI as both a catalyst for innovation and a source of potential disruption. The findings highlight the necessity for proactive governance and ethical frameworks to mitigate risks associated with AI deployment while maximizing its benefits. Ultimately, this paper aims to provide a comprehensive understanding of how AI is redefining human experiences and societal norms, encouraging further discourse on the sustainable integration of these technologies in everyday life. Full article

Sign language recognition (SLR) plays a crucial role in bridging the communication gap between deaf individuals and the hearing population. However, achieving subject-independent SLR remains a significant challenge due to variations in signing styles, hand shapes, and movement patterns among users. Traditional Markov Chain-based models struggle with generalizing across different signers, often leading to reduced recognition accuracy and increased uncertainty. These limitations arise from the inability of conventional models to effectively capture diverse gesture dynamics while maintaining robustness to inter-user variability. To address these challenges, this study proposes an adaptive SLR framework that integrates Markov Chains with a Niching Genetic Algorithm (NGA). The NGA optimizes the transition probabilities and structural parameters of the Markov Chain model, enabling it to learn diverse signing patterns while avoiding premature convergence to suboptimal solutions. In the proposed SLR framework, GA is employed to determine the optimal transition probabilities for the Markov Chain components operating across multiple signing contexts. To enhance the diversity of the initial population and improve the model’s adaptability to signer variations, a niche model is integrated using a Context-Based Clearing (CBC) technique. This approach mitigates premature convergence by promoting genetic diversity, ensuring that the population maintains a wide range of potential solutions. By minimizing gene association within chromosomes, the CBC technique enhances the model’s ability to learn diverse gesture transitions and movement dynamics across different users. This optimization process enables the Markov Chain to better generalize subject-independent sign language recognition, leading to improved classification accuracy, robustness against signer variability, and reduced misclassification rates. Experimental evaluations demonstrate a significant improvement in recognition performance, reduced error rates, and enhanced generalization across unseen signers, validating the effectiveness of the proposed approach. Full article

Retrieval-Augmented Generation (RAG) combined with Large Language Models (LLMs) introduces a new paradigm for clinical-trial data analysis that is both real-time and knowledge-traceable. This study targets a multi-site, real-world data environment. It builds a hierarchical RAG pipeline spanning an electronic health record (EHR), National Health Insurance (NHI) billing codes, and image-vector indices. The LLM is optimized through lightweight LoRA/QLoRA fine-tuning and reinforcement-learning-based alignment. The system first retrieves key textual and imaging evidence from heterogeneous data repositories and then fuses these artifacts into the contextual window for clinical report generation. Experimental results show marked improvements over traditional manual statistics and prompt-only models in retrieval accuracy, textual coherence, and response latency while reducing human error and workload. In evaluation, the proposed multimodal RAG-LLM workflow achieved statistically significant gains in three core metrics—recall, factual consistency, and expert ratings—and substantially shortened overall report-generation time, demonstrating clear efficiency advantages versus conventional manual processes. However, LLMs alone often face challenges such as limited real-world grounding, hallucination risks, and restricted context windows. Similarly, RAG systems, while improving factual consistency, depend heavily on retrieval quality and may yield incoherent synthesis if evidence is misaligned. These limitations underline the complementary nature of integrating RAG and LLM architectures in a clinical reporting context. Quantitatively, the proposed system achieved a Composite Quality Index (CQI) of 78.3, outperforming strong baselines such as Med-PaLM 2 (72.6) and PMC-LLaMA (74.3), and reducing the report drafting time by over 75% (p < 0.01). These findings confirm the practical feasibility of the framework to support fully automated clinical reporting. Full article

The protective role of progesterone against estradiol-driven proliferation is essential for preserving endometrial homeostasis. However, the factors that influence the progesterone–estradiol (P4:E2) ratio remain poorly characterized. This study aimed to model this ratio using a machine learning approach to identify key hormonal, anthropometric, demographic, dietary, metabolic, and inflammatory predictors. In addition, it aimed to assess estradiol and progesterone as individual outcomes to clarify whether shared or divergent mechanisms underlie variation in each hormone. NHANES data were used to identify postmenopausal women (n = 1902). An XGBoost model was developed to predict the log-transformed P4:E2 ratio using a 70/30 stratified train–test split. SHAP (SHapley Additive exPlanations) values were computed to interpret feature contributions. The final XGBoost model for the log-transformed P4:E2 ratio achieved an RMSE of 0.746, an MAE of 0.574, and an R² of 0.298 on the test set. SHAP analysis identified FSH (0.213), waist circumference (0.181), and CRP (0.133) as the most influential contributors, followed by total cholesterol (0.085) and LH (0.066). FSH and waist circumference emerged as key predictors of estradiol, while total cholesterol and LH were the most influential for progesterone. By leveraging SHAP-based feature importance to rank predictors of the P4:E2 ratio, this study provides interpretable, data-driven insights into the reproductive hormonal dynamics of postmenopausal women. Full article

We present Liquid Adaptive AI as a theoretical framework and mathematical basis for artificial intelligence systems capable of continuous structural adaptation and autonomous capability development. This work explores the conceptual boundaries of adaptive AI by formalizing three interconnected mechanisms: (1) entropy-guided hyperdimensional knowledge graphs that could autonomously restructure based on information-theoretic criteria; (2) a self-development engine using hierarchical Bayesian optimization for runtime architecture modification; and (3) a federated multi-agent framework with emergent specialization through distributed reinforcement learning. We address fundamental limitations in current AI systems through mathematically formalized processes of dynamic parameter adjustment, structural self-modification, and cross-domain knowledge synthesis, while immediate implementation faces substantial computational challenges requiring infrastructure on the scale of current large language model training facilities, we provide architectural specifications, theoretical convergence bounds, and evaluation criteria as a foundation for future research. This theoretical exploration establishes mathematical foundations for a potential new paradigm in artificial intelligence that would transition from episodic training to persistent autonomous development, offering a long-term research direction for the field. A comprehensive ^{Supplementary Materials} document provides detailed technical analysis, computational requirements, and an incremental development roadmap spanning approximately a decade. Full article

This study investigates global innovation trends in machine learning (ML) and deep learning (DL) technologies within the automotive sector through a patent analysis of 5314 applications filed between 2005 and 2022 across the five major patent offices (IP5). Using Cooperative Patent Classification (CPC) codes and keyword analysis, we identify seven sub-technology domains and examine both geographical and corporate patenting strategies. Our findings show that the United States dominates in overall filings, while Japan demonstrates a notably high share of triadic patents, which reflects a strong global-reach strategy. Patent activity is heavily concentrated in vehicle control and infrastructure traffic control, with emerging growth observed in battery management and occupant analytics. In contrast, security-related technologies remain underrepresented, indicating a potential blind spot in current innovation efforts. Corporate strategies diverge markedly; for example, some firms, such as Toyota and Bosch, pursue balanced tri-regional protection, whereas others, including Ford and GM, focus on dual-market coverage in the United States and China. These patterns illustrate how market priorities, regulatory environments, and technological objectives influence patenting behavior. By mapping the technological and strategic landscape of ML/DL innovation in the automotive industry, this study provides actionable insights for industry practitioners seeking to optimize intellectual property portfolios and for policymakers aiming to address gaps such as automotive cybersecurity in future R&D agendas. Full article