Applied System Innovation

To address the challenges of compressing large-scale, multi-channel temperature data from aluminum alloy heating furnaces—and the limitations of traditional methods in preserving fidelity for critical tasks like energy accounting and process playback—this paper proposes an elastic, task-aware time-series compression method based on semantic segmentation. The method automatically segments data and annotates anchor points according to key process stages and significant operational events. Data are grouped by furnace number and alloy grade into segment-level buckets. Within this structure, an enhanced PCA model is built using channel-specific weights and amplified anchor points. The optimal principal component dimension is selected automatically under explained variance constraints, with channel-wise DCT used as a fallback for small samples. Compression accuracy is evaluated using combined rRMSE metrics (overall and per temperature channel) and key event recall rate. Experiments show the method achieves an average overall rRMSE of 0.11624, a temperature channel rRMSE of 0.08860, and a compression ratio of 1.18, outperforming Standard-PCA, PAA, and RP-Gauss. Notably, the proposed method achieves 100% recall for key events during heat preservation, demonstrating superior performance. Further analysis shows performance varies significantly across process stages, furnace IDs, and alloy grades, offering valuable insights for fine-grained evaluation and real-world deployment. Full article

This article presents a hybrid optimization model designed to determine the optimal location and operation of capacitor banks in medium-voltage distribution networks, aiming to reduce energy losses and enhance the system’s economic efficiency. The use of reactive power compensation through fixed-step capacitor banks is highlighted as an effective and cost-efficient solution; however, their optimal placement and sizing pose a mixed-integer nonlinear programming optimization challenge of a combinatorial nature. To address this issue, a multi-objective optimization methodology based on the Sine Cosine Algorithm (SCA) is proposed to identify the ideal location and capacity of capacitor banks within distribution networks. This model simultaneously focuses on minimizing technical losses while reducing both investment and operational costs, thereby producing a Pareto front that facilitates the analysis of trade-offs between technical performance and economic viability. The methodology is validated through comprehensive testing on the 33- and 69-bus reference systems. The results demonstrate that the proposed SCA-based approach is computationally efficient, easy to implement, and capable of effectively exploring the search space to identify high-quality Pareto-optimal solutions. These characteristics render the approach a valuable tool for the planning and operation of efficient and resilient distribution networks. Full article

Hybrid supercapacitors possess high power and energy density, while the cascaded H-bridge converter features rapid response capability. Integrating these two components leads to an energy storage system capable of swiftly responding to power demands, effectively mitigating voltage and frequency instability in weak-grid renewable energy stations. Based on this system, in this paper, a novel automatic frequency–voltage regulation strategy is proposed. First, a fast fault severity detection method is proposed. It evaluates the system’s fault condition by monitoring the voltage response and generates auxiliary signals to enable subsequent rapid compensation of voltage and frequency. Subsequently, fast automatic voltage and frequency regulation strategies are developed. These strategies leverage real-time fault assessment to deliver immediate power support to weak-grid renewable stations following a disturbance, thereby effectively stabilizing the terminal voltage magnitude and system frequency. The effectiveness of the proposed method is validated through simulations. A grid-connected model of a weak-grid renewable energy station is established in MATLAB (2023b)/Simulink. Tests under various fault scenarios with different short-circuit ratios and voltage sag depths demonstrate that the proposed strategy can rapidly stabilize both voltage and frequency after large disturbances. Full article

This work develops a methodology for operating Battery Energy Storage Systems (BESSs) in distribution networks, connected in parallel with a medium- and small-scale photovoltaic Distributed Generator (PMGD), focusing on a real project located in the O’Higgins region of Chile. The objective is to increase energy sales by the PMGD while ensuring compliance with operational constraints related to the grid, PMGD, and BESSs, and optimizing renewable energy use. A real distribution network from Compañía General de Electricidad (CGE) comprising 627 nodes was simplified into a validated three-node, two-line equivalent model to reduce computational complexity while maintaining accuracy. A mathematical model was designed to maximize economic benefits through optimal energy dispatch, considering solar generation variability, demand curves, and seasonal energy sales and purchasing prices. An energy management system was proposed based on a master–slave methodology composed of Particle Swarm Optimization (PSO) and an hourly power flow using the successive approximation method. Advanced optimization techniques such as Monte Carlo (MC) and the Genetic Algorithm (GAP) were employed as comparison methods, supported by a statistical analysis evaluating the best and average solutions, repeatability, and processing times to select the most effective optimization approach. Results demonstrate that BESS integration efficiently manages solar generation surpluses, injecting energy during peak demand and high-price periods to maximize revenue, alleviate grid congestion, and improve operational stability, with PSO proving particularly efficient. This work underscores the potential of BESS in PMGD to support a more sustainable and efficient energy matrix in Chile, despite regulatory and technical challenges that warrant further investigation. Full article

The conventional reactive cooling strategy, which relies on static thresholds, has become inadequate for managing dynamically changing heat loads, often resulting in energy inefficiency and increased risk of local hot spots. In this study, we develop a data center cooling optimization system that integrates distributed sensor arrays for predictive analysis. By deploying high-density temperature and humidity sensors both inside and outside server racks, a real-time, high-fidelity three-dimensional digital twin of the data center’s thermal environment is constructed. Time-series analysis combined with Long Short-Term Memory algorithms is employed to forecast temperature and humidity based on the extensive environmental data collected, achieving high predictive accuracy with a root mean square error of 0.25 and an R² value of 0.985. Building on these predictions, a proactive cooling control strategy is formulated to dynamically adjust fan speeds and the opening degree of chilled-water valves in computer room air conditioning units, changing the cooling approach from passive to preemptive prevention of overheating. Compared with conventional proportional–integral–differential control, the developed system significantly reduces overall energy consumption and maintains all equipment within safe operating temperatures. Specifically, the framework has reduced the energy consumption of the cooling system by 37.5%, lowered the overall power usage effectiveness of the data center by 12% (1.48 to 1.30), and suppressed the cumulative hotspot duration (temperature 27 °C) by nearly 96% (from 48 to 2 h). Full article

The acceptance or rejection of a measurement is determined based on its associated measurement uncertainty. In this procedure, there is a risk of making incorrect decisions, including the potential rejection of compliant measurements or the acceptance of non-conforming ones. This study introduces a mathematical model for the spatial evaluation of the global producer’s and global consumer’s risk, predicated on Bayes’ theorem and a decision rule that includes a guard band. The proposed model is appropriate for risk assessment within the framework of multivariate linear regression. Its applicability is demonstrated through an example involving the flatness of the workbench table surface of a coordinate measuring machine. The least-risk direction on the workbench was identified, and risks were quantified under varying selections of reference planes and differing measurement uncertainties anticipated in future measurement processes. Model evaluation was performed using confusion matrix-based metrics. The spaces of the commonly used metrics, constrained by the dimensions of the coordinate measuring machine workbench, were constructed. Using the evaluated metrics, the optimal guard band width was specified to ensure the minimum values of both the global producer’s and the global consumer’s risk. Full article

An intrusion into the operational network (OT) of a production site can cause serious damage by affecting productivity, reliability, and quality. The presence of embedded neural networks (NNs), such as classifiers, in physical devices opens the door to new attack vectors. Due to the stochastic behavior of the classifier and the difficulty of reproducing results, the Artificial Intelligence (AI) Act requires the NN’s behavior to be explainable. For this purpose, the platform HistoTrust enables tracing NN behavior, thanks to secure hardware components issuing attestations registered in a blockchain ledger. This solution helps to build trust between independent actors whose devices perform tasks in cooperation. This paper proposes going further by integrating a mechanism for detecting tampering of embedded NN, and using smart contracts executed on the blockchain to propagate the alert to the peer devices in a distributed manner. The use case of a bit-flip attack, targeting the weights of the NN model, is considered. This attack can be carried out by repeatedly injecting very small messages that can be missed by the Intrusion Detection System (IDS). Experiments are being conducted on the HistoTrust platform to demonstrate the feasibility of our distributed approach and to qualify the time required to detect intrusion and propagate the alert, in relation to the time it takes for the attack to impact decisions made by the AI. As a result, the blockchain may be a relevant technology to complement traditional IDS in order to face distributed attacks. Full article

The AC Optimal Power Flow (AC-OPF) problem remains a major computational bottleneck for real-time power system operation. Conventional solvers are accurate but time-consuming, while Graph Neural Networks (GNNs) offer faster approximations yet struggle to capture long-range dependencies and handle topological variations. To address these limitations, we propose a Heterogeneous Graph Transformer with bus-centric Local–Global Message Passing (LG-HGNN). The model performs type-specific local message passing over heterogeneous power graphs and applies a global Transformer only on bus nodes to capture system-wide correlations efficiently. Effective-resistance positional encodings and resistance-biased attention enhance electrical awareness, whereas bounded decoders and physics-informed regularization preserve operational feasibility. Experiments on IEEE 14-, 30-, and 118-bus systems show that LG-HGNN achieves near-optimal results within a few percent of the AC-OPF optimum and generalizes to thousands of unseen N-1 contingency topologies without retraining. Compared with interior-point solvers, it attains up to $190\times$ speedup before power-flow correction and over $10\times$ afterward on GOC 2000-bus systems, providing a scalable and physically consistent surrogate for real-time AC-OPF. Full article

This paper reports a design-rationale account of building and deploying a small ecosystem of AI-driven educational conversational agents with distinct pedagogical personas. Two strands target school contexts: (i) Talk to Bill, a historically grounded Shakespeare interlocutor intended to support close reading, contextual understanding, and interpretive dialogue; and (ii) Here to Help, a set of UK GCSE subject- and exam-board-specific tutors designed for formative practice in recognised question formats with feedback and iterative improvement. The third strand comprises six complementary assistants for an undergraduate Human–Computer Interaction (HCI) module, each bounded to a workflow-aligned role (e.g., empathise-stage coaching, study planning, course operations), with guardrails to privilege process quality over answer generation. We describe how persona differentiation is mapped to established learning, engagement, and motivation theories; how retrieval-augmented generation and provenance cues are used to reduce hallucination risk; and what early deployment observations suggest about orchestration, integration, and incentives. The contribution is a transferable, auditable rationale linking theory to concrete dialogue and UI moves for multi-persona tutoring ecosystems, rather than a claim of causal learning gains. Full article

The integration of IT services is a critical challenge for public organizations that seek to modernize their operational ecosystems and strengthen mission-oriented processes. In the field of fiscal oversight, supreme audit institutions (SAIs) increasingly require systematized and interoperable service architectures to ensure transparency, accountability, and effective public resource control. However, existing literature reveals persistent gaps concerning how service integration models can be deployed and validated within complex government environments. This study describes an enterprise architecture-driven service integration model designed and evaluated within the Office of the General Comptroller of the Republic of Colombia (Contraloría General de la República, CGR). The study tests the hypothesis that an Enterprise Architecture-driven integration model provides the necessary structural coupling to align technical IT performance with the legal requirements of fiscal oversight, which is an alignment that typically does not appear in generic governance frameworks. The methodological approach followed in this study combines an IT service management maturity assessment, process analysis, architecture repository review, and iterative validation sessions with institutional stakeholders. The model integrates ITILv4 (Information Technology Infrastructure Library), TOGAF (The Open Group Architecture Framework), COBIT (Control Objectives for Information and Related Technologies), and ISO20000 into a coherent framework tailored to the operational and regulatory requirements of an SAI. Results show that the proposed model reduces service fragmentation, improves process standardization, strengthens information governance, and enables a unified service catalog aligned with fiscal oversight functions. The empirical validation demonstrates measurable improvements in service delivery, transparency, and organizational responsiveness. The study contributes to the field of applied system innovation by: (i) providing an integration model, which is scientifically grounded and evidence-based, (ii) demonstrating how hybrid governance and architecture frameworks can be adapted to complex public-sector environments, and (iii) offering a replicable approach for SAIs that seek to modernize their technological service ecosystems through enterprise architecture principles. Future research directions are also discussed to provide guidelines to advance integrated governance and digital transformation in oversight institutions. Full article

Wastewater management plays a critical role in advancing the circular economy, as wastewater is increasingly considered a recoverable resource rather than a waste product. This paper reviews physical, chemical, biological, and combined treatment methodologies, highlighting a lack of a holistic framework in current research which includes both the operational phases of wastewater treatment and proper risk analysis tools. To address this gap, an innovative methodological framework for wastewater recovery and risk management within an integrated logistic–production process is proposed. The framework is structured in five steps: description of the logistic–production process, hazard identification, risk assessment through the Failure Modes, Effects, and Criticality Analysis (FMECA), prioritization of interventions using the Action Priority (AP) method, and definition of corrective actions. The application of the proposed methodology can optimize the usage of available resources across various sectors while minimizing waste products, thus supporting environmental sustainability. Furthermore, political, economic and social implications of adopting the proposed approach in the field of energy transition are discussed. Full article

Mixed palletizing remains a core challenge in distribution centers and modern warehouse operations, particularly within robotic handling and automation systems. Progress in this domain has been hindered by the lack of realistic, freely available datasets for rigorous algorithmic benchmarking. This work addresses this gap by introducing MixedPalletBoxes, a family of seven synthetic datasets designed to evaluate algorithm scalability, adaptability and performance variability across a broad spectrum of workload sizes (500–100,000 records) generated via an open source Python script. These datasets enable the assessment of algorithmic behavior under varying operational complexities and scales. Each box instance is richly annotated with geometric dimensions, material properties, load capacities, environmental tolerances and handling flags. To support dynamic experimentation, the dataset is accompanied by a FastAPI-based tool that enables the on-demand creation of randomized daily picking lists simulating realistic inbound orders. Performance is analyzed through metrics such as pallet count, volume utilization, item distribution per pallet and runtime. Across all dataset sizes, the distributions of the physical attributes remain consistent, confirming stable generation behavior. The proposed framework combines standardization, feature richness and scalability, offering a transparent and extensible platform for benchmarking and advancing robotic mixed palletizing solutions. All datasets, generation code and evaluation scripts are publicly released to foster open collaboration and accelerate innovation in data-driven warehouse automation research. Full article

Accurate recognition of lower limb activities is essential for wearable rehabilitation systems and assistive robotics like exoskeletons and prosthetics. This study introduces SDALLE, a custom hardware data acquisition system that integrates surface electromyography sensors (EMGs) and inertial measurement sensors (IMUs) into a wireless, portable platform for locomotor monitoring. Using this system, data were collected from nine healthy subjects performing four fundamental locomotor activities: walking, jogging, stair ascent, and stair descent. The recorded signals underwent an offline structured preprocessing pipeline consisting of time-series augmentation (jittering and scaling) to increase data diversity, followed by wavelet-based denoising to suppress high-frequency noise and enhance signal quality. A temporal one-dimensional convolutional neural network (1D-TCNN) with three convolutional blocks and fully connected layers was trained on the prepared dataset to classify the four activities. Classification using IMU sensors achieved the highest performance, with accuracies ranging from 0.81 to 0.95. The gyroscope X-axis of the left Rectus Femoris achieved the best performance (0.95), while accelerometer signals also performed strongly, reaching 0.93 for the Vastus Medialis in the Y direction. In contrast, electromyography channels showed lower discriminative capability. These results demonstrate that the combination of SDALLE hardware, appropriate data preprocessing, and a temporal CNN provides an effective offline sensing and activity classification pipeline for lower limb activity recognition and offers an open-source dataset that supports further research in human activity recognition, rehabilitation, and assistive robotics. Full article

Drowning remains the third leading cause of accidental injury-related deaths worldwide, disproportionately affecting low- and middle-income countries where lifeguard coverage is limited or absent. To address this critical gap, we present Robobuoy, an intelligent real-time rescue system that integrates deep learning-based object detection with an unmanned surface vehicle (USV) for autonomous intervention. The system employs a monitoring station equipped with two specialized object detection models: YOLO12m for recognizing drowning individuals and YOLOv5m for tracking the USV. These models were selected for their balance of accuracy, efficiency, and compatibility with resource-constrained edge devices. A geometric navigation algorithm calculates heading directions from visual detections and guides the USV toward the victim. Experimental evaluations on a combined open-source and custom dataset demonstrated strong performance, with YOLO12m achieving an mAP@0.5 of 0.9284 for drowning detection and YOLOv5m achieving an mAP@0.5 of 0.9848 for USV detection. Hardware validation in a controlled water pool confirmed successful target-reaching behavior in all nine trials, achieving a positioning error within 1 m, with traversal times ranging from 11 to 23 s. By combining state-of-the-art computer vision and low-cost autonomous robotics, Robobuoy offers an affordable and low-latency prototype to enhance water safety in unsupervised aquatic environments, particularly in regions where conventional lifeguard surveillance is impractical. Full article

The rapid growth of online chess has intensified the challenge of distinguishing engine-assisted from authentic human play, exposing the limitations of existing approaches that rely solely on deterministic evaluation metrics. This study introduces a proof-of-concept hybrid framework for discriminating between engine-like and human-like chess play patterns, integrating Stockfish’s deterministic evaluations with stylometric behavioral features derived from the Maia engine. Key metrics include Centipawn Loss (CPL), Mismatch Move Match Probability (MMMP), and a novel Curvature-Based Stability (ΔS) indicator. These features were incorporated into a convolutional neural network (CNN) classifier and evaluated on a controlled benchmark dataset of 1000 games, where ‘suspicious’ gameplay was algorithmically generated to simulate engine-optimal patterns, while ‘clean’ play was modeled using Maia’s human-like predictions. Results demonstrate the framework’s ability to discriminate between these behavioral archetypes, with the hybrid model achieving a macro F1-score of 0.93, significantly outperforming the Stockfish-only baseline (F1 = 0.87), as validated by McNemar’s test (p = 0.0153). Feature ablation confirmed that Maia-derived features reduced false negatives and improved recall, while ΔS enhanced robustness. This work establishes a methodological foundation for behavioral pattern discrimination in chess, demonstrating the value of combining deterministic and human-centric modeling. Beyond chess, the approach offers a template for behavioral anomaly analysis in cybersecurity, education, and other decision-based domains, with real-world validation on adjudicated misconduct cases identified as the essential next step. Full article

In the digital era, rapid urban growth and the demand for sustainable mobility are placing increasing pressure on transport systems, where congestion, energy consumption, and schedule variability complicate intermodal journey planning. This work proposes an AI-enhanced transfer-graph framework that models each transport mode as an independent subnetwork connected through explicit transfer arcs. This modular structure captures modal interactions while reducing graph complexity, enabling algorithms to operate more efficiently in time-dependent contexts. A Deep Q-Network (DQN) agent is further introduced as an exploratory alternative to exact and meta-heuristic methods for learning adaptive routing strategies. Exact (Dijkstra) and meta-heuristic (ACO, DFS, GA) algorithms were evaluated on synthetic networks reflecting Casablanca’s intermodal structure, achieving coherent routing with favorable computation and memory performance. The results demonstrate the potential of combining transfer-graph decomposition with learning-based components to support scalable intermodal routing. Full article

The flourishing of the Internet of Things (IoT) has not only improved our lives in smart homes and healthcare but also made us more susceptible to cyberattacks. Legacy intrusion detection systems are simply overwhelmed by the scale and diversity of IoT traffic, which is why there is a need for more intelligent forensic solutions. In this paper, we present a statistical technique, the Averaging Detection Method (ADM), for detecting attack traffic. Furthermore, the five deep learning models SimpleRNN, LSTM, GRU, BLSTM, and BGRU are compared for malicious traffic detection in IoT network forensics. A smart home dataset with a simulated DoS attack was used for performance analysis of accuracy, precision, recall, F1-score, and training time. The results indicate that all models achieve high accuracy, above 97%. BiGRU achieves the best performance, 99% accuracy, precision, recall, and F1-score, at the cost of high training time. GRU achieves perfect precision and recall (100%) with faster training, which can be considered for resource-constrained scenarios. SimpleRNN trains faster with comparable accuracy, while LSTMs and their bidirectional counterparts are better at capturing long-term dependencies but are computationally more expensive. In summary, deep learning, especially BiGRU and GRU, holds great promise for boosting IoT forensic investigation by enabling real-time DoS detection and reliable evidence collection. Meanwhile, the proposed ADM is simpler and more efficient at classifying DoS traffic than deep learning models. Full article

Ship lock zones represent bottlenecks and a particular challenge for authorities managing vessel traffic. Traditionally, the control strategy of such systems has relied heavily on the subjective judgment, experience, and tacit knowledge of ship lock operators. To address the inherent uncertainty and imprecision associated with these subjective assessments, fuzzy logic and fuzzy set theory have been adopted as appropriate mathematical frameworks. In this work, the control strategy and the Fuzzy Decision Support System (FDSS) of a single-chamber ship lock designed for two vessels on a two-way waterway are analyzed and modeled. The input data is generated based on a synthesized dataset reflecting the annual schedule of vessel arrivals. The software is based on proposals and suggestions of experienced ship lock operators, and it is further validated through vessel traffic simulations. Moreover, the development of an appropriate Supervisory Control and Data Acquisition (SCADA) system integrated with a Programmable Logic Controller (PLC) is detailed, providing the necessary infrastructure for real-time deployment of the fuzzy control algorithm. The proposed control system represents an original contribution and offers practical applications both as a decision-support tool for real-time lock management and as a training platform for novice or less experienced operators. Full article

Swarm unmanned surface vehicles (USVs) have been increasingly explored for maritime defense and security operations, particularly in scenarios requiring the rapid detection and interception of multiple attackers. The target detection reliability and defender–target assignment stability are significantly crucial to ensure quick responses and prevent mission failure. A key challenge in such missions lies in the assignment of targets among multiple defenders, where frequent reassignment can cause instability and inefficiency. This paper proposes a novel ETA-hysteresis-guided reinforcement learning (RL) framework for continuous multi-target hunting with swarm USVs. The approach integrates estimated time of arrival (ETA)-based task allocation with a dual-threshold hysteresis mechanism to balance responsiveness and stability in multi-target assignments. The ETA module provides an efficient criterion for selecting the most suitable defender–target pair, while hysteresis prevents oscillatory reassignments triggered by marginal changes in ETA values. The framework is trained and evaluated in a 3D-simulated water environment with multiple continuous targets under static and dynamic water environments. Experimental results demonstrate that the proposed method achieves substantial measurable improvements compared to basic MAPPO and MAPPO-LSTM, including faster convergence speed (+20–30%), higher interception rates (improvement of +9.5% to +20.9%), and reduced mean time-to-capture (by 9.4–19.0%), while maintaining competitive path smoothness and energy efficiency. The findings highlight the potential of integrating time-aware assignment strategies with reinforcement learning to enable robust, scalable, and stable swarm USV operations for maritime security applications. Full article