Search Results (19,221)

Accurate and energy-efficient localization of autonomous underwater vehicles (AUVs) remains a fundamental challenge due to the complex, bandwidth-limited, and highly dynamic nature of underwater acoustic environments. This paper proposes a fully adaptive deep reinforcement learning (DRL)-driven localization framework for AUVs operating in Underwater Acoustic Sensor Networks (UAWSNs). The localization problem is formulated as a Markov Decision Process (MDP) in which an intelligent agent jointly optimizes beacon selection and transmit power allocation to minimize long-term localization error and energy consumption. A hierarchical learning architecture is developed by integrating four actor–critic algorithms, which are (i) Twin Delayed Deep Deterministic Policy Gradient (TD3), (ii) Soft Actor–Critic (SAC), (iii) Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and (iv) Distributed DDPG (D2DPG), enabling robust learning under non-stationary channels, cooperative multi-AUV scenarios, and large-scale deployments. A round-trip time (RTT)-based geometric localization model incorporating a depth-dependent sound speed gradient is employed to accurately capture realistic underwater acoustic propagation effects. A multi-objective reward function jointly balances localization accuracy, energy efficiency, and ranging reliability through a risk-aware metric. Furthermore, the Cramér–Rao Lower Bound (CRLB) is derived to characterize the theoretical performance limits, and a comprehensive complexity analysis is performed to demonstrate the scalability of the proposed framework. Extensive Monte Carlo simulations show that the proposed DRL-based methods achieve significantly lower localization error, lower energy consumption, faster convergence, and higher overall system utility than classical TD3. These results confirm the effectiveness and robustness of DRL for next-generation adaptive underwater localization systems. Full article

Prader–Willi (PWS) and Angelman (AS) syndromes were the first examples in humans with errors in genomic imprinting, usually from de novo 15q11-q13 deletions of different parent origin (paternal in PWS and maternal in AS). Dozens of genes and transcripts are found in the 15q11-q13 region, and may play a role in PWS, specifically paternally expressed SNURF-SNRPN and MAGEL2 genes, while AS is due to the maternally expressed UBE3A gene. These three causative genes, including their encoding proteins, were targeted. This review article summarizes and illustrates the current understanding and cause of both PWS and AS using strategies to include the literature sources of key words and searchable web-based programs with databases for integrated gene and protein interactions, biological processes, and molecular mechanisms available for the two imprinting disorders. The SNURF-SNRPN gene is key in developing complex spliceosomal snRNP assemblies required for mRNA processing, cellular events, splicing, and binding required for detailed protein production and variation, neurodevelopment, immunodeficiency, and cell migration. The MAGEL2 gene is involved with the regulation of retrograde transport and promotion of endosomal assembly, oxytocin and reproduction, as well as circadian rhythm, transcriptional activity control, and appetite. The UBE3A gene encodes a key enzyme for the ubiquitin protein degradation system, apoptosis, tumor suppression, cell adhesion, and targeting proteins for degradation, autophagy, signaling pathways, and circadian rhythm. PWS is characterized early with infantile hypotonia, a poor suck, and failure to thrive with hypogenitalism/hypogonadism. Later, growth and other hormone deficiencies, developmental delays, and behavioral problems are noted with hyperphagia and morbid obesity, if not externally controlled. AS is characterized by seizures, lack of speech, severe learning disabilities, inappropriate laughter, and ataxia. This review captures the clinical presentation, natural history, causes with genetics, mechanisms, and description of established laboratory testing for genetic confirmation of each disorder. Three separate searchable web-based programs and databases that included information from the updated literature and other sources were used to identify and examine integrated genetic findings with predicted gene and protein interactions, molecular mechanisms and functions, biological processes, pathways, and gene-disease associations for candidate or causative genes per disorder. The natural history, review of pathophysiology, clinical presentation, genetics, and genetic-phenotypic findings were described along with computational biology, molecular mechanisms, genetic testing approaches, and status for each disorder, management and treatment options, clinical trial experiences, and future strategies. Conclusions and limitations were discussed to improve understanding, clinical care, genetics, diagnostic protocols, therapeutic agents, and genetic counseling for those with these genomic imprinting disorders. Full article

Data classification tasks based on deep neural networks and machine learning are increasingly used in different fields, such as medicine, finance, and data circulation. However, in these applications, the accuracy of predictions must be guaranteed, and the privacy and security of prediction data and models must be guaranteed. In an unsafe cloud environment, cloud users are reluctant to use the classification prediction tasks provided by the cloud. To solve these problems, this paper researches the data oversampling method and proposes the G-MSMOTE method, which can solve the oversampling problem of multiple minority classes in the data set, generate more diverse data, and solve the data imbalance problem. By improving the traditional FV and using CRT technology to improve coding efficiency, the cloud receives the user’s encrypted ciphertext, and the neural network completes the data prediction task in the ciphertext, thereby providing confidentiality for user data and model parameters under the semi-honest adversarial model, assuming the security of the underlying fully homomorphic encryption scheme and accepting the leakage of model architecture and ciphertext sizes. The feasibility of our method was demonstrated through experimental comparative analysis. We created unbalanced cases based on the MNIST dataset and performed comparative analysis in plain and ciphertext. In the balanced dataset, the model’s prediction accuracy in ciphertext reached 93.44%. In the unbalanced case, after preprocessing with our improved G-MSMOTE algorithm, the model’s prediction accuracy in ciphertext increased by at least 10%. These results show that our scheme can efficiently, accurately, and securely (under the semi-honest model) complete the data classification prediction task. Full article

High-precision temperature prediction is crucial for dealing with extreme weather events under the background of global warming. However, due to the limitations of computing resources, numerical weather prediction models are difficult to directly provide high spatio-temporal resolution data that meets the specific application requirements of a certain region. This problem is particularly prominent in areas with complex terrain. The use of remote sensing data, especially high-resolution terrain data, provides key information for understanding and simulating the interaction between land and atmosphere in complex terrain, making the integration of remote sensing and NWP outputs to achieve high-precision meteorological element downscaling a core challenge. Aiming at the challenge of temperature scaling in complex terrain areas of Southwest China, this paper proposes a novel deep learning model—Terrain Adaptive U-Net Transformer (TAUT). This model takes the encoder–decoder structure of U-Net as the skeleton, deeply integrates the global attention mechanism of Swin Transformer and the local spatiotemporal feature extraction ability of three-dimensional convolution, and innovatively introduces the multi-branch terrain adaptive module (MBTA). The adaptive integration of terrain remote sensing data with various meteorological data, such as temperature fields and wind fields, has been achieved. Eventually, in the complex terrain area of Southwest China, a spatio-temporal high-resolution downscaling of 2 m temperature was realized (from 0.1° in space to 0.01°, and from 3 h intervals to 1 h intervals in time). The experimental results show that within the 48 h downscaling window period, the TAUT model outperforms the comparison models such as bilinear interpolation, SRCNN, U-Net, and EDVR in all evaluation metrics (MAE, RMSE, COR, ACC, PSNR, SSIM). The systematic ablation experiment verified the independent contributions and synergistic effects of the Swin Transformer module, the 3D convolution module, and the MBTA module in improving the performance of each model. In addition, the regional terrain verification shows that this model demonstrates good adaptability and stability under different terrain types (mountains, plateaus, basins). Especially in cases of high-temperature extreme weather, it can more precisely restore the temperature distribution details and spatial textures affected by the terrain, verifying the significant impact of terrain remote sensing data on the accuracy of temperature downscaling. The core contribution of this study lies in the successful construction of a hybrid architecture that can jointly leverage the local feature extraction advantages of CNN and the global context modeling capabilities of Transformer, and effectively integrate key terrain remote sensing data through dedicated modules. The TAUT model offers an effective deep learning solution for precise temperature prediction in complex terrain areas and also provides a referential framework for the integration of remote sensing data and numerical model data in deep learning models. Full article

Falls are a prominent issue in society and the second leading cause of unintentional death globally. Traditional gait analysis is a process that can aid in identifying factors that increase a person’s risk of falling through determining their gait parameters in a controlled environment. Advances in wearable sensor technology and analytical methods such as deep learning can enable remote gait analysis, increasing the quality of the collected data, standardizing the process between centers, and automating aspects of the analysis. Real-world gait analysis requires two problems to be solved: high-accuracy Human Activity Recognition (HAR) and high-accuracy terrain classification. High accuracy HAR has been achieved through the application of powerful novel classification techniques to various HAR datasets; however, terrain classification cannot be approached in this way due to a lack of suitable datasets. In this study, we present the Context-Aware Human Activity Recognition (CAHAR) dataset: the first activity- and terrain-labeled dataset that targets a full range of indoor and outdoor terrains, along with the common gait activities associated with them. Data were captured using Inertial Measurement Units (IMUs), Force-Sensing Resistor (FSR) insoles, color sensors, and LiDARs from 20 healthy participants. With this dataset, researchers can develop new classification models that are capable of both HAR and terrain identification to progress the capabilities of wearable sensors towards remote gait analysis. Full article

The widespread adoption of electric vehicles (EVs) has posed significant challenges to the security of distribution grid loads. To address issues such as increased grid load fluctuations, rising user charging costs, and rapid load surges around midnight caused by uncoordinated nighttime charging of household electric vehicles in communities, this paper first models electric vehicle charging behavior as a Markov Decision Process (MDP). By improving the state-space sampling mechanism, a continuous space mapping and a priority mechanism are designed to transform the charging scheduling problem into a continuous decision-making framework while optimizing the dynamic adjustment between state and action spaces. On this basis, to achieve synergistic load forecasting and charging scheduling decisions, a forecast-augmented deep reinforcement learning method integrating Gated Recurrent Unit and Twin Delayed Deep Deterministic Policy Gradient (GRU-TD3) is proposed. This method constructs a multi-objective reward function that comprehensively considers time-of-use electricity pricing, load stability, and user demands. The method also applies a single-objective pre-training phase and a model-specific importance-sampling strategy to improve learning efficiency and policy stability. Its effectiveness is verified through extensive comparative and ablation validation. The results show that our method outperforms several benchmarks. Specifically, compared to the Deep Deterministic Policy Gradient (DDPG) and Particle Swarm Optimization (PSO) algorithms, it reduces user costs by 11.7% and the load standard deviation by 12.9%. In contrast to uncoordinated charging strategies, it achieves a 42.5% reduction in user costs and a 20.3% decrease in load standard deviation. Moreover, relative to single-objective cost optimization approaches, the proposed algorithm effectively suppresses short-term load growth rates and mitigates the “midnight peak” phenomenon. Full article

Intrinsic motivation provides a principled mechanism for driving exploration in reinforcement learning when external rewards are sparse or delayed. A central challenge, however, lies in defining meaningful novelty signals in high-dimensional and combinatorial state spaces, where observation-level density estimation and prediction-error heuristics often become unreliable. In this work, we propose an information-theoretic framework for intrinsically motivated reinforcement learning grounded in the Information Bottleneck principle. Our approach learns compact latent state representations by explicitly balancing the compression of observations and the preservation of predictive information about future state transitions. Within this bottlenecked latent space, intrinsic rewards are defined through information-theoretic quantities that characterize the novelty of state–action transitions in terms of mutual information, rather than raw observation dissimilarity. To enable scalable estimation in continuous and high-dimensional settings, we employ neural mutual information estimators that avoid explicit density modeling and contrastive objectives based on the construction of positive–negative pairs. We evaluate the proposed method on two representative combinatorial routing problems, the Travelling Salesman Problem and the Split Delivery Vehicle Routing Problem, formulated as Markov decision processes with sparse terminal rewards. These problems serve as controlled testbeds for studying exploration and representation learning under long-horizon decision making. Experimental results demonstrate that the proposed information bottleneck-driven intrinsic motivation improves exploration efficiency, training stability, and solution quality compared to standard reinforcement learning baselines. Full article

Education in entrepreneurship offers university students the opportunity to develop sound problem-solving and critical-thinking dexterity, which are crucial for navigating contemporary higher education. This research explores the opportunities and challenges of education in entrepreneurship within universities based in Lebanon, focusing on the role of fostering entrepreneurial alertness/awareness. This paper further examines how emerging technologies—specifically Generative Artificial Intelligence (Gen-AI)—impact these relationships. In spite of the increasing relevance of entrepreneurship, the results reveal constant limitations in students’ innovation and creativity, together with a lack of mentorship and training prospects for teachers. The study underlines the importance of integrating innovative systems, digital technological means, and sustainable education values to support SDG 4 (Quality Education) and reinforce learning quality environments. To empirically explore the relationships between the variables, the research uses a quantitative research design, using SmartPLS4 to investigate the structural paths between entrepreneurship education, student innovative behavior, entrepreneurial alertness, and the use of Gen-AI. Our data was collected from 197 participants through a validated survey scheme, together with insights received from instructors and students. The results indicate that instructors consider entrepreneurship education positively and recognize the potential of Gen-AI to improve teaching quality, encourage entrepreneurial alertness, and strengthen quality learning practices. Students also highlighted their requirement to acquire new skills and access new opportunities to enhance their decision-making abilities. Generally, the results/findings suggest that entrepreneurship education—emboldened by entrepreneurial alertness and moderated by Gen-AI—plays a vital role in improving students’ innovative behaviors and progressing SDG 4 through high-quality, inclusive, and transformative higher education. Full article

This paper aims to understand the teaching and learning practices and perceptions regarding the subject of Differential and Integral Calculus 1 (DIC1) based on the current French model, as implemented at Université Claude Bernard Lyon 1 (LYON 1), and the Brazilian model, as observed at the Federal University of Technology—Paraná (UTFPR). Five tutorial groups were studied at LYON 1. At UTFPR, four classes of DIC1 were analyzed. Teaching activities were observed, and teachers responded to a questionnaire regarding the frequency with which they implemented certain activities and their beliefs about which activities contribute most to student learning. Students responded to the same questionnaire, reflecting on how often their instructors employed these activities and which ones they believed were most beneficial for learning. There was general agreement between teachers and students about the instructional methodologies used in class; however, discrepancies emerged between observed practices, stated methodologies, and the activities considered essential for learning. In engineering programs, the time allocated to problem-solving—individually or on the board—emerged as a key aspect that may inspire changes and improvements in the Brazilian model. In contrast, group work and mathematical software may serve as avenues for improvement in the French model. Full article

The Aquila Optimizer (AO), inspired by the hunting behavior of Aquila birds, is a recent nature-inspired metaheuristic algorithm recognized for its simplicity and low computational cost. However, the conventional AO often suffers from premature convergence and an imbalance between exploration and exploitation when applied to complex engineering optimization problems. To overcome these limitations, this study proposes a modified Aquila Optimizer (m-AO) incorporating three enhancement strategies: an adaptive chaotic reverse learning mechanism to improve population diversity, an elite alternative pooling strategy to balance global exploration and local exploitation, and a shifted distribution estimation strategy to accelerate convergence toward promising regions of the search space. The performance of the proposed m-AO is evaluated using 23 classical benchmark functions, IEEE CEC 2022 benchmark problems, and a practical plate–fin heat exchanger (PFHE) design optimization problem. Numerical simulations demonstrate that m-AO achieves faster convergence, higher solution accuracy, and improved robustness compared with the original AO and several state-of-the-art metaheuristic algorithms. In the PFHE application, the proposed method yields a significant improvement in thermal performance, accompanied by a reduction in entropy generation and pressure drop under prescribed design constraints. Statistical analyses further confirm the superiority and stability of the proposed approach. These results indicate that the modified Aquila Optimizer is an effective and reliable tool for solving complex thermal system design optimization problems. Full article

This paper proposes the Quantum-behaved Loser Reverse-learning Differential Evolution (QLRDE) algorithm to address the inherent limitations of the standard Differential Evolution (DE) algorithm, including slow convergence speed and the premature stagnation in local optima. QLRDE incorporates three innovations: quantum-behaved mutation strategies suppress premature convergence by leveraging quantum mechanics, the Loser Reverse-Learning Mechanism enhances diversity by reconstructing inferior individuals through opposition-based learning, and an adaptive parameter adjustment mechanism balances exploration and exploitation to improve robustness and convergence efficiency. Experimental evaluations on twelve benchmark functions confirm that QLRDE demonstrates better performance than existing algorithms in terms of search capability and convergence speed. Furthermore, QLRDE is employed for the 3D UAV path planning problem. QLRDE can generate B-Spline-based smooth flight paths and incorporate real-world constraints into the cost function. Simulation results confirm that QLRDE outperforms several competing algorithms with respect to path quality, computational efficiency, and robustness. Full article

Tomato leaf diseases cause substantial yield and quality losses worldwide, yet reliable detection in real fields remains challenging. Two practical bottlenecks dominate current research: (i) limited data, including small samples for rare diseases, class imbalance, and noisy field images, and (ii) multimodal heterogeneity, where RGB images, textual symptom descriptions, spectral cues, and optional molecular assays provide complementary but hard-to-align evidence. This review summarizes recent advances in tomato leaf disease detection under these constraints. We first formalize the problem settings of limited and multimodal data and analyze their impacts on model generalization. We then survey representative solutions for limited data (transfer learning, data augmentation, few-/zero-shot learning, self-supervised learning, and knowledge distillation) and multimodal fusion (feature-, decision-, and hybrid-level strategies, with attention-based alignment). Typical model–dataset pairs are compared, with emphasis on cross-domain robustness and deployment cost. Finally, we outline open challenges—including weak generalization in complex field environments, limited interpretability of multimodal models, and the absence of unified multimodal benchmarks—and discuss future opportunities toward lightweight, edge-ready, and scalable multimodal systems for precision agriculture. Full article

Deep reinforcement learning (DRL) has been widely adopted to solve decision-making problems in complex environments, demonstrating high performance across various domains. However, DRL-based FPS agents are typically trained with a traditional, monolithic policy that integrates heterogeneous functionalities into a single network. This design hinders policy interpretability and severely limits structural flexibility, since even minor design changes in the action space often necessitate complete retraining of the entire network. These constraints are particularly problematic in game development, where behavioral characteristics are distinct and design updates are frequent. To address these issues, this study proposes a Modular Reinforcement Learning (MRL) framework. Unlike monolithic approaches, this framework decomposes complex agent behaviors into semantically distinct action modules, such as movement and attack, which are optimized in parallel with specialized reward structures. Each module learns a policy specialized for its own behavioral characteristics, and the final agent behavior is obtained by combining the outputs of these modules. This modular design enhances structural flexibility by allowing selective modification and retraining of specific functions, thereby reducing the inefficiency associated with retraining a monolithic policy. Experimental results on the 1-vs-1 training map show that the proposed modular agent achieves a maximum win rate of 83.4% against a traditional monolithic policy agent, demonstrating superior in-game performance. In addition, the retraining time required for modifying specific behaviors is reduced by up to 30%, confirming improved efficiency for development environments that require iterative behavioral updates. Full article

High sample complexity presents a major challenge in applying multi-agent reinforcement learning (MARL) to dynamic, high-dimensional sports such as basketball. To address this problem, we proposed the knowledge-embedded modular framework (KEMF), which partitions the environment into offense, defense, and loose-ball modules. Each module employs specialized policies and a knowledge-based observation layer enriched with basketball-specific metrics such as shooting success and defensive accuracy. These metrics are also incorporated into a dynamic and dense reward scheme that offers more direct and situation-specific feedback than sparse win/loss signals. We integrated these components into a multi-agent proximal policy optimization (MAPPO) algorithm to enhance training speed and improve sample efficiency. Evaluations using the commercial basketball game Freestyle indicate that KEMF outperformed previous methods in terms of the average points, winning rate, and overall training efficiency. An ablation study confirmed the synergistic effects of modularity, knowledge-embedded observations, and dense rewards. Moreover, a real-world deployment in 1457 live matches demonstrated the robustness of the framework, with trained agents achieving a 52.43% win rate against experienced human players. These results underscore the promise of the KEMF to enable efficient, adaptive, and strategically coherent MARL solutions in complex sporting environments. Full article

Industrial gateways serve as critical data aggregation points within the Industrial Internet of Things (IIoT), enabling seamless data interoperability that empowers enterprises to extract value from equipment data more efficiently. However, their role exposes a fundamental trade-off between computational efficiency and prediction accuracy—a contradiction yet to be fully resolved by existing approaches. The rapid proliferation of IoT devices has led to a corresponding surge in network traffic, posing significant challenges for traffic forecasting methods, while deep learning models like Transformers and GNNs demonstrate high accuracy in traffic prediction, their substantial computational and memory demands hinder effective deployment on resource-constrained industrial gateways, while simple linear models offer relative simplicity, they struggle to effectively capture the complex characteristics of IIoT traffic—which often exhibits high nonlinearity, significant burstiness, and a wide distribution of time scales. The inherent time-varying nature of traffic data further complicates achieving high prediction accuracy. To address these interrelated challenges, we propose the lightweight and theoretically grounded DOA-MSDI-CrossLinear framework, redefining traffic forecasting as a hierarchical decomposition–interaction problem. Unlike existing approaches that simply combine components, we recognize that industrial traffic inherently exhibits scale-dependent temporal correlations requiring explicit decomposition prior to interaction modeling. The Multi-Scale Decomposable Mixing (MDM) module implements this concept through adaptive sequence decomposition, while the Dual Dependency Interaction (DDI) module simultaneously captures dependencies across time and channels. Ultimately, decomposed patterns are fed into an enhanced CrossLinear model to predict flow values for specific future time periods. The Dream Optimization Algorithm (DOA) provides bio-inspired hyperparameter tuning that balances exploration and exploitation—particularly suited for the non-convex optimization scenarios typical in industrial forecasting tasks. Extensive experiments on real industrial IoT datasets thoroughly validate the effectiveness of this approach. Full article