Search Results (1,370)

There exists an urgent need to improve colorectal cancer (CRC) diagnosis due to limitations in current diagnostic approaches. Systematic characterization of the human T cell receptor (TCR) repertoire, coupled with advanced computational methods, provides a promising opportunity to develop more accurate and less invasive diagnostic strategies for this major malignancy. The main objective of this work is to establish a TCR repertoire-based diagnostic model for CRC using machine learning algorithms and to identify the most significant features contributing to accurate diagnosis. Through comprehensive comparative analysis of several machine learning algorithms, our results demonstrated that the Transformer model exhibited superior performance capabilities. The trained model achieved an area under the receiver operating characteristic curve (AUC) of 0.973 in predicting disease status in the internal test set. Furthermore, TCR repertoire analysis from the independent test set demonstrated robust predictions with an AUC of 0.814. Notably, we identified a panel of 50 TCR repertoire features that showed a diagnostic AUC of 0.869 using these 50 TCR CDR3 sequences. Together, this TCR repertoire-based disease model demonstrates significant potential for clinical applications in CRC diagnosis and treatment response monitoring. Furthermore, similar diagnostic models could be established for other immune-related diseases based on disease-specific TCR repertoire data. Full article

Unmanned Aerial Vehicles (UAVs) have become essential tools in inspection and emergency response operations due to their high maneuverability and ability to access hard-to-reach areas. However, their limited battery life significantly restricts their use in long-duration missions. This paper presents a tethered marsupial robotic system composed of a UAV and an Unmanned Ground Vehicle (UGV), specifically designed for autonomous, long-duration inspection tasks in Global Navigation Satellite System (GNSS)-denied environments. The system extends the UAV’s operational time by supplying power through a tether connected to high-capacity battery packs carried by the UGV. Our work details the hardware architecture based on off-the-shelf components to ensure replicability and describes our full-stack software framework used by the system, which is composed of open-source components and built upon the Robot Operating System (ROS). The proposed software architecture enables precise localization using a Direct LiDAR Localization (DLL) method and ensures safe path planning and coordinated trajectory tracking for the integrated UGV–tether–UAV system. We validate the system through three sets of field experiments involving (i) three manual flight endurance tests to estimate the operational duration, (ii) three experiments for validating the localization and the trajectory tracking systems, and (iii) three executions of an inspection mission to demonstrate autonomous inspection capabilities. The results of the experiments confirm the robustness and autonomy of the system in GNSS-denied environments. Finally, all experimental data have been made publicly available to support reproducibility and to serve as a common open dataset for benchmarking. Full article

In recent years, humanoid robots have made substantial advances in motion control and multimodal interaction. However, full-size humanoid robots face significant technical challenges due to their inherent geometric and physical properties, leading to large inertia of humanoid robots and substantial driving forces. These characteristics result in issues such as limited biomimetic capabilities, low control efficiency, and complex system integration, thereby restricting practical applications of full-size humanoid robots in real-world settings. To address these limitations, this paper incorporates a biomimetic design approach that draws inspiration from biological structures and movement mechanisms to enhance the robot’s human-like movements and overall efficiency. The platform introduced in this paper, Loong, is designed to overcome these challenges, offering a practically viable solution for full-size humanoid robots. The research team has innovatively used highly biomimetic joint designs to enhance Loong’s capacity for human-like movements and developed a multi-level control architecture along with a multi-master high-speed real-time communication mechanism that significantly improves its control efficiency. In addition, Loong incorporates a modular system integration strategy, which offers substantial advantages in mass production and maintenance, which improves its adaptability and practical utility for diverse operational environments. The biomimetic approach not only enhances Loong’s functionality but also enables it to perform better in complex and dynamic environments. To validate Loong’s design performance, extensive experimental tests were performed, which demonstrated the robot’s ability to traverse complex terrains such as 13 cm steps and 20° slopes and its competence in object manipulation and transportation. These innovations provide a new design paradigm for the development of full-size humanoid robots while laying a more compatible foundation for the development of hardware platforms for medium- and small-sized humanoid robots. This work makes a significant contribution to the practical deployment of humanoid robots. Full article

The growing complexity of the contemporary financial systems requires the emergence of sophisticated computational and statistical methods that are capable of managing uncertainty, lack of normality and structural variability of multivariate data. The TS charts defined by Hotelling are widely applicable but have been observed to be susceptible to asymmetrical distributions and outliers and are therefore inapplicable in a dynamic real-world example, such as cryptocurrency markets. We present a computationally efficient ambiguity-aware framework in this work, which generalizes the robust covariance estimation methods, which are MVE and MCD, into a neutrosophic logic-based framework. This adaptation also allows the proposed charts to model and react to the intrinsic data ambiguity and indeterminacy with improved robustness and additional multivariate process monitoring. The methodology is validated by a combination of simulation experiments and empirical research on high-frequency financial data of the Binance Exchange, with the focus on the BTCUSDT and ETHUSDT trading pairs. The evaluation of the performance is performed based on total and generalized variance measures that give a holistic picture of the sensitivity and adaptability of the method to noise in data and complexities arising in the presence of noise and complexity of data. The results demonstrate that the proposed approach is considerably superior to conventional TS charts and their robust variants, particularly in terms of detecting a small shift and trends of multivariate financial procedures. Thus, it is a contribution to the growing body of knowledge about applying computational statistics and data science to a scalable, uncertainty-sensitive system of high-dimensional process monitoring in volatile financial settings. Full article

Pneumonia remains a serious global health issue, particularly affecting vulnerable groups such as children and the elderly, where timely and accurate diagnosis is critical for effective treatment. Recent advances in deep learning have significantly enhanced pneumonia detection using chest X-rays, yet many current methods still face challenges with interpretability, efficiency, and clinical applicability. In this work, we proposed a YOLOv11-based deep learning framework designed for real-time pneumonia detection, strengthened by the integration of Grad-CAM for visual interpretability. To further enhance robustness, the framework incorporated preprocessing techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, region-of-interest extraction, and lung segmentation, ensuring both precise localization and improved focus on clinically relevant features. Evaluation on two publicly available datasets confirmed the effectiveness of the approach. On the COVID-19 Radiography Dataset, the system reached a macro-average accuracy of 98.50%, precision of 98.60%, recall of 97.40%, and F1-score of 97.99%. On the Chest X-ray COVID-19 & Pneumonia dataset, it achieved 98.06% accuracy, with corresponding high precision and recall, yielding an F1-score of 98.06%. The Grad-CAM visualizations consistently highlighted pathologically relevant lung regions, providing radiologists with interpretable and trustworthy predictions. Comparative analysis with other recent approaches demonstrated the superiority of the proposed method in both diagnostic accuracy and transparency. With its combination of real-time processing, strong predictive capability, and explainable outputs, the framework represents a reliable and clinically applicable tool for supporting pneumonia and COVID-19 diagnosis in diverse healthcare settings. Full article

In the environment of modern climate uncertainty, institutional uncertainty, and digital disruption, resilience along the supply chain has become a strategic imperative for organisations operating in large-scale, high-risk infrastructure ecosystems. According to the dynamic capabilities’ theory, the current study examines the degree to which big data analytics management capability (BDMC) supports supply chain resilience (SCR) through three intermediary mechanisms, including fintech adoption (FTA), circular economy activities (CEA), Internet of Things (IoT), and environmental dynamism acts as a moderating factor to determine the effect that external volatility conditions have on such associations. This study addresses several notable research gaps: (1) the insufficient theorization of how digital tools such as BDMC, FTA, IoT, and CEA interact in building SCR; (2) a lack of empirical clarity on the mediating mechanisms that link digital capabilities with resilience; and (3) limited understanding of the moderating role of environmental dynamism in volatile contexts like the CPEC. A survey was conducted among 441 mid and senior level professionals residing in Pakistan and working in industries related to the China-Pakistan economic corridor (CPEC). Structural equation modelling (SEM) revealed that BDMC has a significant, positive impact on SCR, as well as a mediated influence in this direction. Among mediating sets, the significant pathway discovered CEA supported by the next important pathway IoT and FTA, which also explained the layered (complementary) nature of both digital and sustainability targeting skills. Moreover, the factor of environmental dynamism was also found to have a positive moderating effect on the relationship between BDMC and SCR, indicating that the factor of dynamic capabilities becomes more significant in an environment where environmental uncertainty is high. The research questions driving this study are: (1) How does BDMC enable SCR in the CPEC context? (2) What are the mediating roles of FTA, CEA, and IoT in this relationship? (3) How does environmental dynamism moderate the BDMC-SCR nexus? Theoretically, this study extends DCT to an emerging megaproject context and conceptualizes BDMC as an orchestrating capability. The main innovation lies in integrating digital technologies and sustainability practices into a unified capability system, especially within high-risk, underdeveloped regions. The study provides a practical resilience roadmap for policymakers and firms, outlining the strategic integration of digital and circular practices, rather than merely adopting them. However, this study is limited by its cross-sectional survey design and its focus on a single geographic context, which may affect generalizability. Findings offer timely insights for resilience-building strategies in unstable organisational environments. Full article

The scalability of coordination policies is a critical challenge in swarm robotics, where agent numbers may vary substantially between deployment scenarios. Reinforcement learning (RL) offers a promising avenue for learning decentralized policies from local interactions, yet a fundamental question remains: can policies trained on one swarm size transfer to different population scales without retraining? This zero-shot transfer problem is particularly challenging because the traditional RL approaches learn fixed-dimensional representations tied to specific agent counts, making them brittle to population changes at deployment time. While existing work addresses scalability through population-aware training (e.g., mean-field methods) or multi-size curricula (e.g., population transfer learning), these approaches either impose restrictive assumptions or require explicit exposure to varied team sizes during training. Graph Neural Networks (GNNs) offer a fundamentally different path. Their permutation invariance and ability to process variable-sized graphs suggest potential for zero-shot generalization across swarm sizes, where policies trained on a single population scale could deploy directly to larger or smaller teams. However, this capability remains largely unexplored in the context of swarm coordination. For this reason, we empirically investigate this question by combining GNNs with deep Q-learning in cooperative swarms. We focused on well-established 2D navigation tasks that are commonly used in the swarm robotics literature to study coordination and scalability, providing a controlled yet meaningful setting for our analysis. To address this, we introduce Deep Graph Q-Learning (DGQL), which embeds agent-neighbor graphs into Q-learning and trains on fixed-size swarms. Across two benchmarks (goal reaching and obstacle avoidance), we deploy up to three times larger teams. The DGQL preserves a functional coordination without retraining, but efficiency degrades with size. The ultimate goal distance grows monotonically (15–29 agents) and worsens beyond roughly twice the training size ($\approx 20$ agents), with task-dependent trade-offs. Our results quantify scalability limits of GNN-enhanced DQL and suggest architectural and training strategies to better sustain performance across scales. Full article

More than 60% of earth excavation operations have been accomplished by various excavators. However, complex working loads always cause the fracture failure of excavator sticks because of insufficient strength. For prolonging the service life of excavator stick, a structural optimization design method based on the improved mayfly optimization algorithm (TTL-MA) is proposed to improve the stiffness of excavator stick. Firstly, by using the central composite design (CCD) method, 161 sets of simulation samples are obtained with eight selected structural design parameters of excavator stick. Then, relying on the simulation samples, an agent model between the excavator stick’s structural design parameters and the structural quality objectives, deformation, first-order minimum intrinsic frequency, and stress is constructed by using a Backpropagation neural network (BPNN). Finally, to further enhance the optimization search capability of the Mayfly Algorithm (MA), three improvement strategies were incorporated: Tent chaotic mapping for mayfly population initialization, adaptive t-distribution perturbation for velocity updating, and Lévy flight strategy for enhanced position updating. The results show that under the three constraints of the maximum equivalent von Mises stress σ_max ≤ 150 MPa, maximum deformation δ_max ≤ 2.5 mm, and the first-order minimum intrinsic frequency H_min ≥ 55 Hz, the optimized excavator stick reduces the mass and maximum stress by 7.9% and 11.9%, respectively. The improved mayfly optimization algorithm has strong optimization ability for the optimization design of excavator stick structure, which can provide a reference for similar complex engineering machinery structure optimization problems. Full article

In the context of fuzzy logic speed control for switching reluctance motor (SRM) applications, the objective of this work is to propose a unique zone-based simplification technique. Using the procedure that has been outlined, it is made easier to reduce membership functions as well as rule sets in a logical manner. This is accomplished by splitting the error–change-of-error plane into discrete decision zones. This method is separate from heuristic or adaptive reduction strategies since it employs a systematic framework that reduces the number of rules from 49 in the standard design to 9 and 5 without compromising the accuracy of the control. This is accomplished without adversely affecting the performance of the control. The simplified controller that was produced as a consequence of this study decreases the amount of overshoot, enhances the speed at which a dynamic response happens, and makes it simpler to use on digital platforms that are affordable. All of these capabilities were achieved by the controller. Based on simulations and testing carried out in the real world, it has been determined that the zone-based simplified fuzzy controller that was proposed has a superior performance to traditional PID and full-rule fuzzy systems in terms of reaction time, stability, and energy efficiency. Taking all of this into consideration, it is evident that it has the potential to be useful in real-world applications for SRM drives that demand a high level of speed while maintaining a low cost factor. Full article

Modern high-performance network infrastructures must address the challenges of scalability and quantum-resistant security, particularly in multi-tenant and virtualized environments. In this work, we introduce a novel implementation of Post-Quantum Cryptography (PQC)-IPsec using the NVIDIA BlueField-3 Data Processing Unit (Santa Clara, CA, USA), capable of achieving 400 Gbit/s. We demonstrate line-rate performance through quantum-resilient communication channels using Kyber1024 (ML-KEM) and Dilithium5 (ML-DSA). We evaluate our implementation on two experimental setups; a host-to-host configuration and a 16 Virtual Machines (VMs)-to-host setup, both across a direct high-speed link. We set the Data Processing Unit (DPU) on both Network Interface Card (NIC) mode with no/crypto/full packet offload and on DPU mode by configuring Open vSwitch (OvS) on the ARM cores and offloading the packet processing to the hardware. We achieve 97.5% of the available line-rate for 14 VMs and 99.9% for 16 VMs, in DPU mode. Our findings confirm that PQC-enabled IPsec can operate at line-rate speeds in modern data centers, providing a practical and future-proof foundation for secure, high-throughput communication in the post-quantum computing era. Full article

The increasing deployment of islanded microgrids in disaster-prone and infrastructure-constrained regions has elevated the importance of resilient energy storage systems capable of supporting autonomous operation. Grid-forming energy storage (GFES) units—designed to provide frequency reference, voltage regulation, and black-start capabilities—are emerging as critical assets for maintaining both energy adequacy and dynamic stability in isolated environments. However, conventional storage planning models fail to capture the interplay between uncertain renewable generation, time-coupled operational constraints, and control-oriented performance metrics such as virtual inertia and voltage ride-through. To address this gap, this paper proposes a novel distributionally robust optimization (DRO) framework that jointly optimizes the siting and sizing of GFES under renewable and load uncertainty. The model is grounded in Wasserstein-metric DRO, allowing worst-case expectation minimization over an ambiguity set constructed from empirical historical data. A multi-period convex formulation is developed that incorporates energy balance, degradation cost, state-of-charge dynamics, black-start reserve margins, and stability-aware constraints. Frequency sensitivity and voltage compliance metrics are explicitly embedded into the optimization, enabling control-aware dispatch and resilience-informed placement of storage assets. A tractable reformulation is achieved using strong duality and solved via a nested column-and-constraint generation algorithm. The framework is validated on a modified IEEE 33-bus distribution network with high PV penetration and heterogeneous demand profiles. Case study results demonstrate that the proposed model reduces worst-case blackout duration by 17.4%, improves voltage recovery speed by 12.9%, and achieves 22.3% higher SoC utilization efficiency compared to deterministic and stochastic baselines. Furthermore, sensitivity analyses reveal that GFES deployment naturally concentrates at nodes with high dynamic control leverage, confirming the effectiveness of the control-informed robust design. This work provides a scalable, data-driven planning tool for resilient microgrid development in the face of deep temporal and structural uncertainty. Full article

Background: Dementia refers to a spectrum of clinical conditions characterized by impairments in memory, language, and cognitive function. Alzheimer’s Disease (AD) is the most common cause of dementia and it accounted for 60–70% of the estimated 57 million cases worldwide as of 2021. The exact pathology of this neurodegenerative condition is not fully understood. While it is currently incurable, progression to more critical stages can be slowed, and early diagnosis is crucial to alleviate and manage some of its symptoms. Contemporary diagnostic practices hinder early detection due to the high costs and inaccessibility of advanced neuroimaging tools and specialists, particularly for populations with resource-constrained clinical settings. Methods: This paper addresses this challenge by developing and evaluating computationally efficient lightweight deep learning models, MobileNetV2 and EfficientNetV2B0, for early AD detection from 2D slices sourced from standard structural magnetic resonance imaging (MRI). Results: For the challenging multi-class task of distinguishing between Cognitively Normal (CN), Early Mild Cognitive Impairment (EMCI), and Late Mild Cognitive Impairment (LMCI), our best model, EfficientNetV2B0, achieved 88.0% mean accuracy across a 5-fold stratified cross-validation (std = 1.0%). To enhance clinical interpretability and build trust, we integrated explainability methods, Grad-CAM++ and Guided Grad-CAM++, to visualize the anatomical basis for the models’ predictions. Conclusions: This work delivers an accessible and interpretable neuroimaging tool to support early AD diagnosis and extend expert-level capabilities to routine clinical practice. Full article

Magnesium phosphate cement (MPC) has gained attention in specialized construction applications due to its rapid setting and high early strength, though its inherent brittleness limits structural performance. This study developed an innovative toughening strategy through synergistic reinforcement using hybrid fibers and carbon fiber-reinforced polymer (CFRP) fabric capable of multi-scale crack control. The experimental program systematically evaluated the hybrid fiber system, dosage, and CFRP positioning effects through mechanical testing of 7-day cured specimens. The results indicated that 3.5% fiber dosage optimized flexural–compressive balance (45% flexural gain with <20% compressive reduction), while CFRP integration at 19 mm displacement enhanced flexural capacity via multi-scale reinforcement. Fracture analysis revealed that the combined system increases post-cracking strength by 60% through coordinated crack bridging at micro (fiber) and macro (CFRP) scales. These findings elucidated the mechanisms by which fiber–CFRP interaction mitigates MPC’s brittleness through hierarchical crack control while maintaining its rapid hardening advantages. The study established quantitative design guidelines, showing the fiber composition of CF/WSF/CPS15 = 1/1/1 with 19 mm CFRP placement achieves optimal toughness–flexural balance (f_f/f_c > 0.38). The developed composite system reduced brittleness through effective crack suppression across scales, confirming its capability to transform fracture behavior from brittle to quasi-ductile. This work advances MPC’s engineering applicability by resolving its mechanical limitations through rationally designed composite systems, with particular relevance to rapid repair scenarios requiring both early strength and damage tolerance, expanding its potential in specialized construction where conventional cement proves inadequate. Full article

Quantum computing is an emergent field promising the improvement of processing speed in key algorithms by reducing their exponential scaling to polynomial, thus enabling solutions to problems that exceed classical computational capabilities. Gate-based quantum computing is the most common approach but still faces high levels of noise and decoherence. Gates play the role of probability mixers codifying information settled in quantum systems. However, they are deviated from their programmed behaviour due to those decoherent effects as a hidden source modifies the desired probability flux. Their quantification of such unavoidable behaviours becomes crucial for quantum error correction or mitigation. This work presents an approach to decoherence in quantum circuits using the Lindblad master equation to model the impact of noise and thermalisation underlying the ideal programmed behaviour expected for processing gates. The Lindblad approach then provides a comprehensive tool to model both probability fluxes being present in the process, thus regarding the gate and the environment. It analyses the deviation of resulting noisy states from the ideal unitary evolution of some gates considered as universal, setting some operating regimes. Thermalisation considers a radiation bath where gates are immersed as a feasible model of decoherence. Numerical simulations track the information loss as a function of the decay rate magnitude. It also exhibits the minimal impact on decoherence coming from particular quantum states being processed, but a higher impact on the number of qubits being processed by the gate. The methodology provides a unified framework to characterise the processing probability transport in quantum gates, including noise or thermalisation effects. Full article

This scoping review systematically maps the rapidly evolving application of Artificial Intelligence (AI) in Autism Spectrum Disorder (ASD) diagnostics, specifically focusing on computational behavioral phenotyping. Recognizing that observable traits like speech and movement are critical for early, timely intervention, the study synthesizes AI’s use across eight key behavioral modalities. These include voice biomarkers, conversational dynamics, linguistic analysis, movement analysis, activity recognition, facial gestures, visual attention, and multimodal approaches. The review analyzed 158 studies published between 2015 and 2025, revealing that modern Machine Learning and Deep Learning techniques demonstrate highly promising diagnostic performance in controlled environments, with reported accuracies of up to 99%. Despite this significant capability, the review identifies critical challenges that impede clinical implementation and generalizability. These persistent limitations include pervasive issues with dataset heterogeneity, gender bias in samples, and small overall sample sizes. By detailing the current landscape of observable data types, computational methodologies, and available datasets, this work establishes a comprehensive overview of AI’s current strengths and fundamental weaknesses in ASD diagnosis. The article concludes by providing actionable recommendations aimed at guiding future research toward developing diagnostic solutions that are more inclusive, generalizable, and ultimately applicable in clinical settings. Full article