Search Results (340)

With the increasing deployment of multi-unmanned aerial vehicle (multi-UAV) systems in dynamic environments, the problem of efficient cooperative path planning has emerged as a critical challenge requiring urgent solutions. To address this issue, this paper proposes a novel joint optimization framework, named spatio-temporal attention-based multi-agent deep deterministic policy gradient (STA-MADDPG). Rather than proposing a new reinforcement learning algorithm in the strict sense, this work integrates advanced spatial-temporal feature extraction with heuristic gradient guidance. First, a cascaded architecture combining multi-head attention and Long Short-Term Memory (LSTM) networks is utilized to extract key local and temporal features, thereby mitigating the dimensionality curse in dense multi-agent observations. Second, an improved dynamic artificial potential field (DAPF) is integrated into the reinforcement learning framework as a state augmentation mechanism, providing heuristic guidance vectors that accelerate convergence and improve obstacle avoidance. Furthermore, to balance computational complexity and adaptive behavior, a rule-based hierarchical formation strategy is designed. The framework maps predefined formations (elliptical, chain, or wedge) to specific environment categories, while the underlying MARL policy governs the dynamic trajectory planning and topology maintenance. Finally, rigorous comparative and ablation experiments are conducted to evaluate path length, search time, and relative position errors. Statistical analysis demonstrates the effectiveness of the proposed framework, achieving up to a 67.3% reduction in search time and a 91.56% search success rate compared with standard MARL baselines in complex environments. Full article

This study considers a 1-m-1 hybrid flow shop scheduling problem that simultaneously incorporates four practical constraints: lot streaming, no-wait, blocking, and sequence-dependent setup times. Although each of these characteristics has been studied individually in the literature, their joint consideration in a single HFS model has received little attention. The problem is motivated by a real-world order sequencing problem in insulation board manufacturing, where all four constraints arise simultaneously from the production process. To formally characterize the problem, we develop a mixed-integer programming formulation that captures all operational constraints. For practical-scale problems, we propose several dispatching heuristics that can obtain sufficiently good solutions within a short computation time. We further develop a genetic algorithm as an independent solution approach to obtain high-quality solutions close to the optimum within a reasonable computation time. Computational experiments on instances generated based on real insulation board production characteristics demonstrate that the proposed algorithms outperform a benchmark greedy rule, and sensitivity analyses reveal the effects of setup time magnitude and the number of parallel machines on scheduling performance. Full article

Flexible job shop scheduling with multiple automated guided vehicles (FJSP-AGV) is a challenging production scheduling problem in intelligent manufacturing, where operation sequencing, machine assignment, AGV allocation, and transportation decisions are tightly coupled. Existing exact and meta-heuristic methods can obtain high-quality solutions, but they usually require considerable computational time for large-scale instances. Meanwhile, conventional dispatching rules can make fast decisions but often fail to capture the complex interactions among operations, machines, and AGVs. To address these challenges, this paper proposes an end-to-end deep reinforcement learning framework based on heterogeneous graph neural networks for solving FJSP-AGV. Specifically, a heterogeneous graph is constructed to represent the scheduling state, where operations, machines, and AGVs are modeled as different types of nodes, and their relationships are described by operation–machine and operation–AGV arcs. Based on this representation, a heterogeneous graph neural network is developed to extract scheduling information from different production resources. In particular, a meta-path aggregation mechanism is introduced to capture the complex interaction patterns among operations, machines, and AGVs. The proximal policy optimization algorithm is then employed to train the scheduling policy in an end-to-end manner. Experimental results on public benchmark instances and real-world cases demonstrate that the proposed method outperforms composite heuristic rules and achieves a favorable balance between solution quality and computational efficiency compared with existing state-of-the-art methods. These results indicate that the proposed HGNN-DRL framework is effective for fast and intelligent scheduling decision-making in FJSP-AGV environments. Full article

Indoor temperature forecasting in large public buildings is affected by heating, ventilation, and air-conditioning (HVAC) control, occupancy, airflow, and zone use, not only by recent temperature histories. This study asks whether operationally derived functional-zone proxy labels—room groupings derived heuristically from HVAC statistics rather than from field-verified building metadata—can provide a useful learnable context for temporal convolutional network (TCN)-based room-level forecasting when verified semantic metadata are unavailable. Using the public BEAR (Building Efficiency and Renewables) multizone building HVAC dataset, we construct a reproducible operational proxy scenario: eighty rooms are grouped from occupancy, airflow, damper, control-command, and temperature-variability statistics, and Niagara-inspired point-naming conventions are used only as structured metadata descriptors, not as tags exported from a deployed system. The proposed SemanticTCN augments a TCN backbone with learnable room, temperature-variability proxy embeddings. Experiments compare persistence, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), TCN, DLinear, PatchTST, a TCNOnly variant, SemanticTCN, and ablations for 1 h, 6 h, and 24 h forecasts, evaluated by mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), and the coefficient of determination ($R^2$). Persistence is strongest at 1 h and 24 h, while DLinear is strongest at 6 h, indicating strong thermal inertia and daily regularity. Within the TCN family, SemanticTCN improves over TCNOnly in the locked run, shows a statistically significant within-distribution MAE improvement across multiple seeds (most consistently at 6 h), and reduces large-error rates; however, a leave-one-zone-out experiment shows that this advantage does not transfer to rooms unseen during training, and a five-seed operational-versus-random-proxy control shows that the specific operational grouping rule is not statistically distinguishable from arbitrary grouping. The bounded conclusion is that providing room/group context to the TCN backbone helps predict rooms whose identity was observed during training, especially at 6 h, but the gain reflects room-identity context rather than generalizable operational semantics: the proxy labels are heuristic operational constructs rather than verified building semantics; they do not outperform arbitrary grouping under multi-seed control, and they do not generalize to unseen rooms under this split. Full article

The problem of efficient AI-assisted design-to-kit transformation for Gablok-layout designs is related to the development of techniques to convert architectural designs into constructible and ready-to-build modular constructions. The current research presents an algorithm based on BIM, rule constraints, and constraint optimization enhanced with AI heuristics, which automatically converts residential layouts into a kit-of-parts design. The proposed framework involves decomposition of wall geometry into discrete block arrangements with respect to the dimensions of the Gablok modular system. In addition to the decomposition procedure, the approach takes into account the structural and geometrical constraints. The constraint optimization model, complemented by AI methods, decreases material waste, optimizes the number of cuts, and maintains the variability of the blocks. The final output includes a construction kit with a bill of materials, cut list, labels for each block, and detailed assembly instructions. Experimental results show that the implementation of the proposed technique allows a decrease in material waste by 25–35% in comparison to manual methods. Also, this framework creates an opportunity to simplify assembly process from the perspective of human interaction. Full article

Industrial Internet of Things (IIoT) networks use on-demand sensing and wireless power transfer (WPT) for self-sustainable operation. Existing scheduling frameworks are fundamentally limited because they react only after energy levels decline. Consequently, IoT nodes enter charging mode only when their residual energy falls below a threshold, causing energy outages, increased latency, and missed sensing tasks while preventing proactive WPT resource allocation. This paper proposes a Digital Twin (DT)-enabled proactive scheduling framework that transforms IIoT scheduling from reactive to proactive. The key innovation is a closed-loop virtual–real integration in which a DT layer, co-located with the control centre, maintains a Kalman filter predictor to forecast node energy over an H-slot horizon, enabling scheduling decisions before energy shortages occur. Physical layer security (PLS) constraints and DT-based anomaly detection protect against eavesdropping, energy depletion, and false data injection attacks. A multi-objective formulation jointly optimises sensing utility and WPT efficiency while accounting for DT synchronisation overhead and uplink bandwidth consumption. The resulting multi-slot Binary Integer Linear Programmes (BILP) are solved using branch-and-bound with a reliability branching rule, and a fast greedy heuristic is also developed. Simulation results over 50 Monte Carlo iterations show that the proposed framework reduces energy outage events by approximately 70% compared with the reactive baseline, activates less than 50% of available sensing nodes, and schedules less than 60% of energy transmitters for WPT. Ablation studies confirm that DT prediction is the primary contributor to the outage reduction. DT-based anomaly detection achieves a false alarm rate below 3% while maintaining a detection rate above 95%. The proposed framework improves the sustainability, efficiency, and security of IIoT networks with practical computational overhead, making it well suited for Industry 5.0 deployments. Full article

Order picking is one of the most time-consuming and cost-intensive operations in distribution centers, particularly when material flow is constrained by fixed transport infrastructure. This paper addresses an order-picking problem in a distribution center equipped with a one-directional transfer conveyor and stop buffers that serve groups of storage racks. Containers move along the conveyor, visit the required buffers, and may reach upstream buffers only by completing a round trip through the depot. The objective is to minimize the makespan of all picking operations while accounting for picker availability, processing times, and conveyor travel times between buffers. Four heuristic algorithms are proposed. They differ in the primary sorting rule used within a two-level ordering procedure and are supported by a permutation-reduction mechanism for medium and large instances. The algorithms were evaluated on 60 generated test instances with 120 storage locations, six buffers, and six pickers. For the 20 small instances, the results were compared with solutions obtained using CP Optimizer in IBM ILOG CPLEX under a fixed computational time limit. Within this prescribed time limit, the proposed heuristics achieved lower makespans than the feasible solutions generated by the CP Optimizer in 18 out of 20 instances, while requiring an average of only 0.22 s. Medium and large instances were solved using the proposed heuristics, with average computational times of 2.10 min and 9.00 min, respectively. The results indicate that the proposed approach provides scalable and computationally efficient decision-support procedures for order-picking systems with one-directional material flow and buffer-based service constraints. Full article

Efficient data dissemination to mobile sink groups with heterogeneous spatial distributions that are globally sparse but locally dense remains a critical challenge in wireless sensor networks (WSNs). To address severe energy inefficiencies in conventional single-strategy approaches, we propose an energy-efficient, strictly lightweight hybrid mobile groupcasting protocol that dynamically integrates unicasting and partial flooding. The proposed protocol eliminates in-network computational overhead by shifting the entire subgrouping burden exclusively to the data source. The source formulates data dissemination as an analytical cost minimization problem and executes a highly scalable heuristic subgrouping algorithm that operates in linear time, $\mathcal{O}\left(\right|M\left|\right)$, relative to the number of member sinks. By embedding this optimal configuration directly into the data packet header, resource-constrained intermediate sensor nodes are completely relieved from heavy clustering calculations and only need to execute simple, predefined geographic forwarding or localized flooding rules. The simulation results using the QualNet 4.0 platform validate that our source-delegated architecture significantly reduces redundant transmissions and unnecessary flooding regions. The proposed protocol achieves up to 24% and 44.5% reductions in communication energy consumption compared to conventional unicasting-based and flooding-based protocols, respectively, while maintaining reliable data delivery under realistic network dynamics. Full article

User experience (UX) evaluation is central to software quality, yet it remains difficult to integrate into software engineering workflows in a systematic, explainable, and early-stage manner. This paper presents TraceUX, a framework for operationalizing UX heuristics and design guidance into a rule-based static evaluation pipeline that combines machine-interpretable formalization, executability-aware assessment, context-sensitive scoring, and actionable reporting. The framework is instantiated using Apple Human Interface Guidelines, Swift abstract syntax trees, and mobile games, and implemented in a proof-of-concept tool named TraceHIG. Evaluation was conducted in four layers: analysis of the full rule repository, controlled synthetic validation with injected violations, baseline assessment of 12 public Swift game projects, and a case study on one project. The full repository contained 206 rules; after excluding non-iOS yet platform-specific rules, 193 rules were retained for the downstream experiments. In controlled validation, 216 injected violations yielded 99.2% precision, 61.6% recall, and an F1-score of 0.760. In baseline analysis, overall project scores ranged from 41.6 to 88.0, reflecting rule-conformance spread under the instantiated rule base rather than direct measures of UX quality. The case study demonstrated that profile-aware scoring can yield materially different UX assessments for the same codebase under different game configurations, highlighting the importance of app profiling in static UX evaluation. These findings show that a meaningful subset of UX knowledge can be operationalized into explainable, context-aware static analysis that provides structured and actionable decision support while complementing, rather than replacing, manual and empirical UX evaluation. Full article

This paper proposes a practical heuristic engineering strategy for automated capacity allocation in a multifunctional parallel active power filter (PAPF) that simultaneously provides harmonic and reactive power compensation. Unlike theoretically optimal methods, our approach prioritizes real-time feasibility and ease of implementation. The key features are: (1) an event-triggered, closed-loop THD-feedback mechanism that dynamically recalculates the minimum active power required for harmonic compensation only when the load harmonic content changes, avoiding periodic computational waste; (2) a strict priority handling that guarantees grid current THD below 5% (IEEE-519 compliant) under all operating conditions, even when capacity is severely insufficient; (3) a closed-loop transition mechanism that uses measured grid current THD and remaining capacity as feedback inputs to continuously adapt power distribution. The proposed rule-based strategy does not claim theoretical optimality but provides a verifiable, ready-to-implement solution with experimental evidence. Simulation and experimental results on a three-level NPC PAPF prototype demonstrate that the strategy maintains grid current THD below 5% while keeping the apparent power within the rated capacity, achieving near-optimal reactive compensation (92–96% of the optimum) without iterative optimization. The experimental validation includes efficiency measurements, switching-loss estimation, DSP timing analysis, and robustness tests under grid disturbances. Future work will extend the concept to multi-inverter systems using multi-objective optimization and AI-based allocation. Full article

Common moving averages (MAs) used for volatility forecasting rely on fixed heuristic weights. We propose a Custom Moving Average (CMA) whose weights are learned to forecast the next-day True Range (TR). Using daily OHLC data for 55 futures contracts with a chronological 60/20/20 train/validation/test split, CMA weights are optimized for each look-back period p by projected subgradient descent against Mean Absolute Error (MAE), with validation-based early stopping. We benchmark CMA against nine standard MAs over 62 look-back periods, selecting the period on validation and reporting accuracy on the held-out test set. Learned weights concentrate on an effective horizon of 15–20 observations regardless of p: about 85% of the mass sits in lags 0–14 for both $p=36$ and $p=120$. EMA is the validation-best method at very short windows; CMA dominates from $p\approx 16$ onwards, winning on 53 of 55 instruments by $p=120$. Under a single-global-period rule, CMA at $p^{*}=36$ attains the lowest test-set geometric-mean MAE, with EMA at $p^{*}=7$ the closest competitor (0.87% higher); per-instrument validation selection does not overturn the ranking, with EMA again closest at 0.53%. Higher-order smoothers (T3, TEMA, DEMA) do not improve on CMA under either rule; CMA’s advantage is robust to the choice of selection granularity. Full article

Accurate dental working posture is essential for clinical performance and patient safety, yet objective and consistent posture training remains challenging. We present a motion-recognition-based posture assessment approach for dental clinical training that computes posture features from skeletal motion data and applies a rule-based (heuristic) posture assessment module based on predefined clinical criteria to generate posture scores, penalty counts, and warning counts. We conducted a comparative feasibility study with five dental residents (40 sessions total; eight procedure states per participant, 5 min/session). Heuristic-based assessment outputs were compared with specialist video-based ratings using paired nonparametric tests and Bland–Altman analysis. Across pooled sessions (n = 40), the heuristic method yielded lower posture scores than the video-based assessment (89.38 ± 5.21 vs. 97.38 ± 2.99) and higher penalty and warning counts (2.13 ± 1.04 vs. 0.53 ± 0.60; 7.23 ± 3.10 vs. 2.48 ± 1.54). Between-method differences were significant (p < 0.001), and Bland–Altman analysis showed a mean bias of 8.00 points (95% limits of agreement: −1.36 to 17.36), indicating limited session-level interchangeability. The proposed approach shows practical feasibility for quantitative posture recording and training support, but larger validation studies and calibration strategies are needed to improve agreement with reference assessments. Full article

Sleep monitoring and analysis are essential for understanding overall health, improving sleep quality, and detecting potential disorders early. This study presents a multimodal approach for automatic sleep staging and quality assessment using a reduced set of bio-signals: a single electroencephalographic (EEG) lead (F4–F3), a single EOG lead, and the photo-plethysmographic (PPG) signal. The proposed methodology includes a hierarchical sleep staging classifier, an automatic sleep staging algorithm, and a subject-specific Sleep Quality Index (SQI) for objective sleep quality assessment. The 5-class sleep staging classifier employs a cascaded architecture of two sequential 3-class models (Wake-REM-NREM and N1-N2-N3), trained and tested on multimodal features derived from physiological signals (EEG, EOG, and PPG) of the BOAS (Bitbrain Open Access Sleep) dataset. The resulting 5-class classifier achieved 90.8% accuracy with a reduced memory footprint (3.14 MB). To assess subject-independent generalization and prevent data leakage between training and test sets, a Leave-One-Subject-Out (LOSO) validation was performed, confirming the robustness of the proposed classifier across unseen subjects. The classifier was subsequently integrated into an automatic sleep staging algorithm. Validation on 14 unseen subjects yielded accuracies ranging from 80.26% to 91.99% using heuristic post-processing rules, while a Hidden Markov Model (HMM)-based approach further improved performance, reaching a peak accuracy of 91.99%. The proposed SQI combines sleep-related metrics extracted from staging, considering multiple sleep aspects (i.e., duration, intensity, and continuity-fragmentation). A calibration strategy was proposed to customize the SQI based on sleep scoring parameters and the subjective quality score derived from sleep diaries and questionnaires (PSQI). This subject-specific strategy was validated on a public dataset, optimizing weights across multiple nights, followed by an independent test on a subsequent night and demonstrating strong alignment between the calculated SQI and the subjective sleep quality score (MAE = 10.81). Finally, the framework provides resource-efficient sleep staging and custom quality estimation, validating its readiness for practical, long-term sleep monitoring. Full article

6G promises ultra-low latency, high data throughput, and seamless global connectivity. However, providing uninterrupted connectivity in remote and underserved regions remains a critical challenge for Terrestrial Networks (TNs), where the cost of deploying infrastructure is difficult to justify against sparse user density. Standardized under 3GPP Release 17, Non-Terrestrial Networks (NTNs) have emerged as a viable solution to close this digital divide. Among NTN platforms, High-Altitude Platform Stations (HAPS) occupy a strategic middle ground, as they deliver lower propagation delays than Low-Earth Orbit (LEO) satellites while achieving far broader coverage than TN-based Base Stations (BS). Despite these advantages, battery-powered Internet of Things (IoT) devices communicating via HAPS face a fundamental energy efficiency (EE) challenge: transmit power must be carefully managed to maximize data throughput while preserving battery life and minimizing packet queuing delays. To address this, we propose a Q-learning-based Reinforcement Learning (RL) framework. The RL agent observes the instantaneous battery level and queue state of the IoT device, and dynamically selects optimal power levels from a discrete action space across successive time slots. Unlike traditional heuristic algorithms, such as Round Robin (RR), Max Single-to-Noise Ratio (Max-SNR), and fixed-power allocation, which rely on static rules or greedy channel-based decisions, the proposed Q-learning agent learns adaptive, long-term optimal policies through direct interaction with the environment, without requiring explicit mathematical modeling of the channel or traffic dynamics. Extensive simulations demonstrate that the proposed framework achieves up to 40% higher average EE compared to all benchmark schemes, maintains consistently lower power consumption, and exhibits superior statistical reliability as evidenced by a right-shifted Cumulative Distribution Function (CDF) of EE. These results demonstrate Q-learning as a promising candidate for scalable, energy-aware power control of next-generation HAPS-assisted IoT deployments in 6G NTN ecosystems. Full article

Advanced Metering Infrastructure (AMI) over 5G New Radio (NR) massive machine-type communication (mMTC) networks require efficient and adaptive communication mechanisms to support reliable data delivery for large numbers of smart meters under dynamic traffic and channel conditions. In this work, we propose a framework in which each smart meter chooses, at runtime, whether to transmit directly to the base station (BS) or via a nearby Data Aggregation Point (DAP). The optimal choice is dynamic and depends on DAP buffer occupancy, periodic congestion, channel quality, and packet deadline pressure. Formulating this as a per-meter binary decision yields an action space of size $2^N$ for N meters, which is intractable for reinforcement learning (RL). We reformulate the problem as regional strategy composition: the RL agent selects one parameterized association strategy for each DAP region from a small library of interpretable rules, and a deterministic mapping expands the regional choice into per-meter modes. It reduces the policy action space from $2^N$ to $K^D$, where D is the number of DAPs and K the number of strategies, while preserving meter-level control granularity. We evaluate Proximal Policy Optimization (PPO) and Deep Q-Network (DQN) controllers against eight meter-level baselines on a 5G NR-calibrated simulator with 1500 m, six DAPs, deadline-bounded delivery, stale channel-state information, and phase-offset congestion cycles. Across three traffic regimes and five random seeds, PPO improves packet delivery ratio (PDR) over the strongest heuristic by +0.63, +2.41, and +2.66 percentage points under baseline, high-load, and bursty-cycle conditions, respectively; all gains are statistically significant (paired t-test, $p<0.001$; Cohen’s d up to 5.12), and the advantage grows with traffic stress. The results show that learned regional composition of classical heuristics outperforms any single fixed heuristic precisely when no individual rule is globally optimal. Full article