Search Results (60)

With the rapid advancement of artificial intelligence (AI) technology, training deep neural networks has become a core computational task that consumes significant energy in data centers. Researchers often employ various methods to estimate the energy usage of data center clusters or servers to enhance energy management and conservation efforts. However, accurately predicting the energy consumption and carbon footprint of a specific AI task throughout its entire lifecycle before execution remains challenging. In this paper, we explore the energy consumption characteristics of AI model training tasks and propose a simple yet effective method for predicting neural network training energy consumption. This approach leverages training task metadata and applies genetic programming-based symbolic regression to forecast energy consumption prior to executing training tasks, distinguishing it from time series forecasting of data center energy consumption. We have developed an AI training energy consumption environment using the A800 GPU and models from the ResNet{18, 34, 50, 101}, VGG16, MobileNet, ViT, and BERT families to collect data for experimentation and analysis. The experimental analysis of energy consumption reveals that the consumption curve exhibits waveform characteristics resembling square waves, with distinct peaks and valleys. The prediction experiments demonstrate that the proposed method performs well, achieving mean relative errors (MRE) of 2.67% for valley energy, 8.42% for valley duration, 5.16% for peak power, and 3.64% for peak duration. Our findings indicate that, within a specific data center, the energy consumption of AI training tasks follows a predictable pattern. Furthermore, our proposed method enables accurate prediction and calculation of power load before model training begins, without requiring extensive historical energy consumption data. This capability facilitates optimized energy-saving scheduling in data centers in advance, thereby advancing the vision of green AI. Full article

Generative Agent (GA) has emerged as a promising framework for simulating human-like behaviors. However, it is required for GA to generate a schedule that consistently reflects the agent’s E-I trait particularly in the extroversion–introversion (E-I) category to improve the realism of GA. We propose an E-I evaluation and rescheduling method that adjusts the agent’s schedule. Specifically, our method takes as input a one-hour schedule segmented into five-minute tasks and a corresponding E-I trait classified into seven degrees ranging from extremely high extroversion to extremely high introversion. Using the Evaluator powered by GPT-4o mini, each task is assessed for the alignment with the E-I traits. Each task that fails to meet a threshold is regenerated using few-shot prompting based on a collected successful schedule. This process is repeated until all tasks are aligned with the corresponding traits. Finally, the evaluator accesses the overall E-I consistency of the schedule that contains the tasks. Therefore, it is possible for the proposed method to enable E-I-consistent schedule generation in GA without retraining any models. In experiments, the proposed framework improved E-I alignment from an average of 14.7% to that of 78.4% with only 1.38 iterations on average, demonstrating both practical effectiveness and computational efficiency. Full article

Aiming at the problems that traditional heuristic algorithms struggle to capture the complex correlations between damaged equipment and dynamically adjust maintenance task requirements in different task scenarios, the Graph Neural Network (GNN) and Deep Reinforcement Learning (DRL) optimization scheduling method for damaged equipment maintenance tasks is proposed, the purpose is to enhance the efficiency of optimization scheduling in dynamic scenarios. By constructing an attribute graph of damaged equipment and maintenance units, Graph Convolutional Network (GCN) and Graph Attention Network (GAT) are utilized to mine the correlations between nodes. A hierarchical reward function is designed in conjunction with DRL to dynamically adjust the multi-objective weights of maximizing importance, minimizing maintenance time. Hard and soft constraints such as maintenance skill matching, spare parts inventory, and threat thresholds are incorporated into the multi-objective optimization model to achieve real-time scheduling of maintenance tasks in an uncertain task environment. Case studies show that this method can effectively balance multi-objective conflicts through dynamic weight adjustment and online re-optimization mechanisms, making it suitable for multi-constraint task scenarios, compared with the Discrete Particle Swarm Optimization (DPSO) algorithm. GNN-DRL reduces the number of convergence iterations by 40%, improves the learning efficiency by 40%, and enhances the quality of the optimal solution by 11%, effectively improving the efficiency of maintenance task scheduling for damaged equipment. Full article

Deploying deep learning (DL) models in real-world environments remains a major challenge, particularly under resource-constrained conditions where achieving both high accuracy and compact architectures is essential. While effective, Conventional pruning methods often suffer from high computational overhead, accuracy degradation, or disruption of the end-to-end training process, limiting their practicality for embedded and real-time applications. We present Dynamic Attention-Guided Pruning (DAGP), a Dynamic Attention-Guided Soft Channel Pruning framework that overcomes these limitations by embedding learnable, differentiable pruning masks directly within convolutional neural networks (CNNs). These masks act as implicit attention mechanisms, adaptively suppressing non-informative channels during training. A progressively scheduled L1 regularization, activated after a warm-up phase, enables gradual sparsity while preserving early learning capacity. Unlike prior methods, DAGP is retraining-free, introduces minimal architectural overhead, and supports optional hard pruning for deployment efficiency. Joint optimization of classification and sparsity objectives ensures stable convergence and task-adaptive channel selection. Experiments on CIFAR-10 (VGG16, ResNet56) and PlantVillage (custom CNN) achieve up to 98.82% FLOPs reduction with accuracy gains over baselines. Real-world validation on an enhanced PlantDoc dataset for agricultural monitoring achieves 60 ms inference with only 2.00 MB RAM on a Raspberry Pi 4, confirming efficiency under field conditions. These results illustrate DAGP’s potential to scale beyond agriculture to diverse edge-intelligent systems requiring lightweight, accurate, and deployable models. Full article

Maintaining operational efficiency in distributed solar energy systems requires intelligent coordination of inspection tasks and workforce resources to handle diverse fault conditions. This study presents a bi-level multi-objective optimization framework that addresses two tightly coupled problems: dynamic job scheduling and skill-based team formation. The job scheduling component assigns geographically dispersed inspection tasks to mobile teams while minimizing multiple conflicting objectives, including travel distance, tardiness, and workload imbalance. Concurrently, the team formation component ensures that each team satisfies fault-specific skill requirements by optimizing team cohesion and compactness. To solve the bi-objective team formation problem, we propose HMOO-AOS, a hybrid algorithm integrating six metaheuristic operators under an NSGA-II framework with an Upper Confidence Bound-based Adaptive Operator Selection. Experiments on datasets of up to seven instances demonstrate statistically significant improvements ($p<0.05$) in solution quality, skill coverage, and computational efficiency compared to NSGA-II, NSGA-III, and MOEA/D variants, with computational complexity $\mathcal{O}\left(G·N·(M+logN)\right)$ (time complexity), $\mathcal{O}(N·L)$ (space complexity). A cloud-integrated system architecture is also proposed to contextualize the framework within real-world solar inspection operations, supporting real-time data integration, dynamic rescheduling, and mobile workforce coordination. These contributions provide scalable, practical tools for solar operators, maintenance planners, and energy system managers, establishing a robust and adaptive approach to intelligent inspection planning in renewable energy operations. Full article

In modern amphibious operations, the dynamic scheduling of shipborne unmanned helicopters faces challenges including highly uncertain operational environments, complex and variable mission requirements, and stringent resource constraints. To tackle this issue, this paper presents an integrated solution encompassing modeling, scheduling strategies, and optimization algorithms. First, a Dynamic Scheduling Model for Integrated Operation-Support Activities of Shipborne Unmanned Helicopters (SUH-DSMIOSA) is developed, which integrates mission temporal constraints, heterogeneous unmanned helicopter resources, and deck support resource constraints to achieve integrated modeling of operational tasks and support operations. Second, a Multi-Modal Disturbance-Aware Adaptive Rescheduling Strategy (MDAARS) is designed, which adaptively selects targeted rescheduling schemes by identifying disturbance types and establishes a differentiated evaluation system to quantify their effects. And then, an Improved Tabu Search algorithm (I-TS) is proposed, enhancing search efficiency and solution quality through adaptive tabu length adjustment, enhanced neighborhood operations, and an intelligent restart strategy. The results show that the I-TS algorithm achieved an average convergence speed improvement of 40.2% and a solution quality enhancement of 1.76%. The algorithm reaches a normalized efficiency of 0.98 within 10 iterations and maintains excellent stability throughout the entire convergence process. When facing disturbance events, the proposed algorithm reduces the mission change rate by an average of 20.1% and improves the rescheduling success rate by 2.8% compared to other algorithms. This research provides theoretical support and technical pathways for efficient dynamic scheduling of unmanned helicopters in amphibious operations. Full article

Background/Objective: The global acceleration of population aging presents profound challenges to the physical, psychological, and social well-being of older adults. As traditional exercise programs face limitations in accessibility, personalization, and sustained social support, there is a critical need for innovative, inclusive, and community-integrated digital movement solutions. This study aimed to develop and evaluate Movement Poomasi, a hybrid digital healthcare application designed to promote physical activity, improve digital accessibility, and strengthen social connectedness among older adults. Methods: From March 2023 to November 2023, Movement Poomasi was developed through an iterative user-centered design process involving domain experts in physical therapy and sports psychology. In this study, the term UI/UX—short for user interface and user experience—refers to the overall design and interaction framework of the application, encompassing visual layout, navigation flow, accessibility features, and user engagement optimization tailored to older adults’ sensory, cognitive, and motor characteristics. The application integrates adaptive exercise modules, senior-optimized UI/UX, voice-assisted navigation, and peer-interaction features to enable both home-based and in-person movement engagement. A two-phase usability validation was conducted. A 4-week pilot test with 15 older adults assessed the prototype, followed by a formal 6-week study with 50 participants (≥65 years), stratified by digital literacy and activity background. Quantitative metrics—movement completion rates, session duration, and engagement with social features—were analyzed alongside semi-structured interviews. Statistical analysis included ANOVA and regression to examine usability and engagement outcomes. The application has continued iterative testing and refinement until May 2025, and it is scheduled for re-launch under the name Wello! in August 2025. Results: Post-implementation UI refinements significantly increased navigation success rates (from 68% to 87%, p = 0.042). ANOVA revealed that movement selection and peer-interaction tasks posed greater cognitive load (p < 0.01). A strong positive correlation was found between digital literacy and task performance (r = 0.68, p < 0.05). Weekly participation increased by 38%, with 81% of participants reporting enhanced social connectedness through group challenges and hybrid peer-led meetups. Despite high satisfaction scores (mean 4.6 ± 0.4), usability challenges remained among low-literacy users, indicating the need for further interface simplification. Conclusions: The findings underscore the potential of hybrid digital platforms tailored to older adults’ physical, cognitive, and social needs. Movement Poomasi demonstrates scalable feasibility and contributes to reducing the digital divide while fostering active aging. Future directions include AI-assisted onboarding, adaptive tutorials, and expanded integration with community care ecosystems to enhance long-term engagement and inclusivity. Full article

Task scheduling in data relay satellite networks (DRSNs) is subject to dynamic disruptions such as resource failures, sudden surges in task demands, and variations in service duration requirements. These disturbances may degrade the performance of pre-established scheduling plans. To improve adaptability and robustness under such uncertainties, this paper presents a dynamic scheduling model for DRSN that integrates comprehensive task constraints and link connectivity requirements. The model aims to maximize overall task utility while minimizing deviations from the original schedule. To efficiently solve this problem, an ensemble heuristic adaptive contract net protocol (EH-ACNP) is developed, which supports dynamic scheduling strategy adaptation and efficient rescheduling through iterative negotiations. Extensive simulation results show that, in scenarios with sudden task surges, the proposed method achieves a 3.1% improvement in yield compared to the state-of-the-art dynamic scheduling algorithm HMCNP, and it also outperforms HMCNP in scenarios involving resource interruptions. Sensitivity analysis further indicates that the algorithm maintains strong robustness when the disposal rate parameter exceeds 0.2. These results highlight the practical potential of the EH-ACNP for dynamic scheduling in complex and uncertain DRSN environments. Full article

This paper presents a novel risk-based maintenance (RBM) approach for the development of a structured maintenance strategy for the power-generating (PG) unit at the gas plant of the Sirte Oil Company (SOC). The proposed approach comprises three key aspects: estimated risk (ER), risk evaluation (RV), and maintenance planning (MP). To identify and prioritize critical components, the methodology integrates fault tree analysis (FTA) with Monte Carlo simulations, enabling the probabilistic modeling of failure scenarios and the accurate quantification of risk. High-pressure (HP) water systems were selected as a case study due to their significant role and failure consequences within the PG unit. Through this RBM methodology, risk levels—based on the probability of failure (PoF) and consequence of failure (CoF)—were quantified, and maintenance tasks were rescheduled to target the most vulnerable components. The results demonstrate that implementing the RBM strategy reduced unplanned shutdowns and optimized uptime, achieving 348 operational days per year, compared to the baseline 365-day mean time to failure (MTTF) cycle (reduction in downtime of around 4.65%). This translated into a measurable improvement in system reliability and operational efficiency. The approach is especially applicable to processing units operating under harsh conditions, offering a preventive tool for the reduction of risk exposure and improvements in asset performance. Full article

Edge computing (EC) plays a critical role in advancing the next-generation Industrial Internet of Things (IIoT) by enhancing production, maintenance, and operational outcomes across heterogeneous network boundaries. This study builds upon EC intelligence and integrates graph-based learning to propose a Cross-Layer Controller Tasking Scheme (CLCTS). The scheme operates through two primary phases: task grouping assignment and cross-layer control. In the first phase, controller nodes executing similar tasks are grouped based on task timing to achieve monotonic and synchronized completions. The second phase governs controller re-tasking both within and across these groups. Graph structures connect the groups to facilitate concurrent tasking and completion. A learning model is trained on inverse outcomes from the first phase to mitigate task acceptance errors (TAEs), while the second phase focuses on task migration learning to reduce task prolongation. Edge nodes interlink the groups and synchronize tasking, migration, and re-tasking operations across IIoT layers within unified completion periods. Departing from simulation-based approaches, this study presents a fully implemented framework that combines learning-driven scheduling with coordinated cross-layer control. The proposed CLCTS achieves an 8.67% reduction in overhead, a 7.36% decrease in task processing time, and a 17.41% reduction in TAEs while enhancing the completion ratio by 13.19% under maximum edge node deployment. Full article

Recent advancements in deep learning have spurred significant research interest in fault diagnosis for elevator systems. However, conventional approaches typically require substantial labeled datasets that are often impractical to obtain in real-world industrial environments. This limitation poses a fundamental challenge for developing robust diagnostic models capable of performing reliably under data-scarce conditions. To address this critical gap, we propose MetaRes-DMT-AS (Meta-ResNet with Dynamic Meta-Training and Adaptive Scheduling), a novel meta-learning framework for few-shot fault diagnosis. Our methodology employs Gramian Angular Fields to transform 1D raw sensor data into 2D image representations, followed by episodic task construction through stochastic sampling. During meta-training, the system acquires transferable prior knowledge through optimized parameter initialization, while an adaptive scheduling module dynamically configures support/query sets. Subsequent regularization via prototype networks ensures stable feature extraction. Comprehensive validation using the Case Western Reserve University bearing dataset and proprietary elevator acceleration data demonstrates the framework’s superiority: MetaRes-DMT-AS achieves state-of-the-art few-shot classification performance, surpassing benchmark models by 0.94–1.78% in overall accuracy. For critical few-shot fault categories—particularly emergency stops and severe vibrations—the method delivers significant accuracy improvements of 3–16% and 17–29%, respectively. Full article

Although dynamic, energy-efficient container-supply hybrid flow shops have attracted increasing attention, most existing research overlooks how transportation within container production affects makespan, resilience, and sustainability. To bridge this gap, we frame a resilient, energy-efficient container-supply hybrid flow shop (TDEHFSP) scheduling model that utilizes vehicle transportation to maximize operational efficiency. To address the TDEHFSP model, the study proposes a Q-learning-based multi-swarm collaborative optimization algorithm (Q-MGCOA). The algorithm integrates a time gap left-shift scheduling strategy with a machine on–off control mechanism to construct an energy-saving optimization framework. Additionally, a predictive–reactive dynamic rescheduling model is introduced to address unexpected task disturbances. To validate the algorithm’s effectiveness, 36 benchmark test cases with varying scales are designed for horizontal comparison. Results show that the proposed Q-MGCOA outperforms benchmarks on convergence, diversity, and supply-chain resilience while lowering energy utilization. Moreover, it achieves about an 8% reduction in energy consumption compared to traditional algorithms. These findings reveal actionable insights for next-generation intelligent, low-carbon container production. Full article

Unmanned Aircraft Systems (UASs) have undergone rapid development over recent years, but have also became vulnerable to security attacks and the volatile external environment. Ensuring that the performance of UASs is safe and secure no matter how the environment changes is challenging. Runtime Verification (RV) is a lightweight formal verification technique that could be used to monitor UAS performance to guarantee safety and security, while reactive synthesis is a methodology for automatically synthesizing a correct-by-construction controller. This paper addresses the problem of the generation and design of a secure UAS controller by introducing a unified monitor and controller synthesis method based on RV and reactive synthesis. First, we introduce a novel methodological framework, in which RV monitors is applied to guarantee various UAS properties, with the reactive controller mainly focusing on the handling of tasks. Then, we propose a specification pattern to represent different UAS properties and generate RV monitors. In addition, a detailed priority-based scheduling method to schedule monitor and controller events is proposed. Furthermore, we design two methods based on specification generation and re-synthesis to solve the problem of task generation using metrics for reactive synthesis. Then, to facilitate users using our method to design secure UAS controllers more efficiently, we develop a domain-specific language (UAS-DL) for modeling UASs. Finally, we use F Prime to implement our method and conduct experiments on a joint simulation platform. The experimental results show that our method can generate secure UAS controllers, guarantee greater UAS safety and security, and require less synthesis time. Full article

Designing an efficient task offloading system is essential in the Industrial Internet of Things (IIoT). Owing to the limited computational capability of IIoT devices, offloading tasks to edge servers enhances computational efficiency. When an edge server is overloaded, it may experience interruptions, preventing it from serving local devices. Existing studies mainly address interruptions by rerouting, rescheduling, or implementing reactive strategies to mitigate their impact. In this study, we introduce an interruption-aware proactive task offloading framework for IIoT. We develop a load-based interruption model in which the probability of server interruption is formulated as an exponential function of the total computational load, which provides a more realistic estimation of service availability. This framework employs Multi-Agent Advantage Actor–Critic (MAA2C)—a simple yet efficient approach that enables decentralized decision-making while handling large action spaces and maintaining coordination through the centralized critic to make adaptive offloading decisions, taking into account edge availability, resource limitations, device cooperation, and interruptions. Experimental results show that our approach effectively reduces the average total service delay by optimizing the tradeoff between system delay and availability in IIoT networks. Additionally, we investigate the impact of various system parameters on performance under an interruptible edge task offloading scenario, providing valuable insights into how these parameters influence the overall system behavior and efficiency. Full article

Maceral identification in images obtained with an immersive microscopy is one of the most important techniques for coal quality characterization. The objective of this paper is to explore the potential of semantic segmentation for the classification of liptinite macerals within microscope images. The following U-Net-based architectures were proposed for the task: a U-Net with a varying depth and feature map numbers, a U-Net extended with a proposed feature map attention mechanism, and a U-Net architecture with an encoder part replaced with a ResNet backbone. Two resolutions of input images were examined: 256 × 256 and 512 × 512 pixels. The training was conducted using constant and scheduled learning rate values. The results show a superior performance of the networks using a ResNet-based encoder, with the best IoU measure, equal 0.91, obtained with ResNet50. The other networks achieved worse results, but attention-supported U-Nets were considerably better than the basic versions. Both training approaches (constant and scheduled learning rates) yielded comparable results. The best results were better than those reported in the literature for other architectures of deep neural networks. It was also observed that the images presenting the greatest challenges to the networks were highly imbalanced, with the liptinite present only in a small area of the image. The architectures employing ResNet-based encoders were the only ones capable of surmounting these challenges. Full article