Search Results (881)

The rapid development of the Artificial Intelligence of Things (AIoT) has created unprecedented demands for distributed, long-term, and maintenance-free sensing systems. Conventional battery-powered sensors suffer from inherent drawbacks such as limited lifetime, high maintenance costs, and environmental concerns, which hinder large-scale deployment. Self-powered sensing technologies provide a transformative pathway by integrating energy harvesting and sensing into a single platform, thereby eliminating the reliance on external power supplies. This review systematically summarizes the key components of self-powered wireless sensing systems, with a particular focus on different energy harvesting technologies, self-powered sensing technologies, and the latest advances in low-power intelligent computation for diverse application scenarios. The integration of energy harvesting, self-sensing, and intelligent computation will make self-powered wireless sensing systems an inevitable direction for the evolution of AIoT, enabling sustainable, scalable, and intelligent monitoring networks. Full article

Dynamic social and legal transformations drive technological innovation and the transition of energy and heating sectors toward renewable sources and higher efficiency. Ensuring the reliable operation of these systems requires regular inspections, fault detection, and infrastructure maintenance. Unmanned Aerial Vehicles (UAVs) are increasingly being used for monitoring and diagnostics of photovoltaic and wind farms, power transmission lines, and urban heating networks. Based on literature from 2015 to 2025 (Scopus database), this review compares UAV platforms, sensors, and inspection methods, including thermal, RGB/multispectral, LiDAR, and acoustic, highlighting current challenges. The analysis of legal regulations and resulting operational limitations for UAVs, based on the frameworks of the EU, the US, and China, is also presented. UAVs offer high-resolution data, rapid coverage, and cost reduction compared to conventional approaches. However, they face limitations related to flight endurance, weather sensitivity, regulatory restrictions, and data processing. Key trends include multi-sensor integration, coordinated multi-UAV missions, on-board edge-AI analytics, digital twin integration, and predictive maintenance. The study highlights the need to develop standardised data models, interoperable sensor systems, and legal frameworks that enable autonomous operations to advance UAV implementation in energy and heating infrastructure management. Full article

This paper presents an energy-aware Artificial Intelligence of Things framework designed for intelligent remote device control in residential settings. The system architecture is grounded in the Power Administration Device (PAD), a cost-effective and non-intrusive smart plug prototype that measures real-time electricity consumption and actuates appliance power states. The PAD transmits data to a scalable, cross-platform cloud infrastructure, which powers a web-based interface for monitoring, configuration, and multi-device control. Central to this framework is Cross-Feature Time-MoE, a novel neural forecasting model that processes the ingested data to predict consumption patterns. Integrating a Transformer Decoder with a Top-K Mixture-of-Experts (MoE) layer for temporal reasoning and a Bilinear Interaction Layer for capturing complex cross-time and cross-feature dependencies, the model generates accurate multi-horizon energy forecasts. These predictions drive actionable recommendations for device shut-off times, facilitating automated energy efficiency. Simulation results indicate that this system yields substantial reductions in energy consumption, particularly for high-wattage appliances, providing a user-friendly, scalable solution for household cost savings and environmental sustainability. Full article

Market power remains a persistent challenge in liberalized electricity spot markets, where generators can manipulate bids to distort prices and extract rents. Traditional monitoring approaches—such as structural indices or simulation-based models—offer partial insights but fail to capture the nonlinear, spatially correlated propagation of strategic behavior across transmission-constrained networks. This paper develops a diffusion neural learning framework for market power risk assessment that integrates welfare optimization, nodal pricing dynamics, and graph-based deep learning. Specifically, a Graph Diffusion Network (GDN) is trained on simulated spot market scenarios to learn how localized strategic deviations spread through the network, distort locational marginal prices, and alter system welfare. The modeling framework combines a system-wide welfare maximization objective with multi-constraint market clearing, while the GDN embeds network topology into predictive learning. Results from a case study on an IEEE 118-bus system demonstrate that the proposed method achieves an R² of 0.91 in predicting market power indices, outperforming multilayer perceptrons, recurrent neural networks, and Transformer baselines. Welfare analysis reveals that distributionally robust optimization safeguards up to 3.3 million USD in adverse scenarios compared with baseline stochastic approaches. Further, congestion mapping highlights that strategic bidding concentrates distortions at specific nodes, amplifying rents by up to 40 percent. The proposed approach thus offers both predictive accuracy and interpretability, enabling regulators to detect emerging risks and design targeted mitigation strategies. Overall, this work establishes diffusion-based learning as a novel and effective paradigm for electricity market power assessment under high uncertainty and renewable penetration. Full article

Precision agriculture increasingly recognizes the transformative potential of unmanned aerial systems (UASs) for crop monitoring and field assessment, yet research consistently highlights significant usability barriers as the main constraints to widespread adoption. Complex mission planning processes, including detailed flight plan creation and way point management, pose substantial technical challenges that mainly affect non-expert operators. Farmers and their teams generally prefer user-friendly, straightforward tools, as evidenced by the rapid adoption of GPS guidance systems, which underscores the need for simpler mission planning in UAS operations. To enhance accessibility and safety in UAS control, especially for non-expert operators in agriculture and related fields, we propose a Secure UAS Control Framework (SAUCF): a comprehensive system for natural-language-driven UAS mission management with integrated dual-factor biometric authentication. The framework converts spoken user instructions into executable flight plans by leveraging a language-model-powered mission planner that interprets transcribed voice commands and generates context-aware operational directives, including takeoff, location monitoring, return-to-home, and landing operations. Mission orchestration is performed through a large language model (LLM) agent, coupled with a human-in-the-loop supervision mechanism that enables operators to review, adjust, or confirm mission plans before deployment. Additionally, SAUCF offers a manual override feature, allowing users to assume direct control or interrupt missions at any stage, ensuring safety and adaptability in dynamic environments. Proof-of-concept demonstrations on a UAS plat-form with on-board computing validated reliable speech-to-text transcription, biometric verification via voice matching and face authentication, and effective Sim2Real transfer of natural-language-driven mission plans from simulation environments to physical UAS operations. Initial evaluations showed that SAUCF reduced mission planning time, minimized command errors, and simplified complex multi-objective workflows compared to traditional waypoint-based tools, though comprehensive field validation remains necessary to confirm these preliminary findings. The integration of natural-language-based interaction, real-time identity verification, human-in-the-loop LLM orchestration, and manual override capabilities allows SAUCF to significantly lower the technical barrier to UAS operation while ensuring mission security, operational reliability, and operator agency in real-world conditions. These findings lay the groundwork for systematic field trials and suggest that prioritizing ease of operation in mission planning can drive broader deployment of UAS technologies. Full article

Legal regulation and practical implementation of artificial intelligence (AI) in Kazakhstan’s criminal procedure are considered within the context of judicial digital transformation. Risks arise for fundamental procedural principles, including the presumption of innocence, adversarial process, and protection of individual rights and freedoms. Legislative mechanisms ensuring lawful and rights-based application of AI in criminal proceedings are required to maintain procedural balance. Comparative legal analysis, formal legal research, and a systemic approach reveal gaps in existing legislation: absence of clear definitions, insufficient regulation, and lack of accountability for AI use. Legal recognition of AI and the establishment of procedural safeguards are essential. The novelty of the study lies in the development of concrete approaches to the introduction of artificial intelligence technologies into criminal procedure, taking into account Kazakhstan’s practical experience with the digitalization of criminal case management. Unlike existing research, which examines AI in the legal profession primarily from a theoretical perspective, this work proposes detailed mechanisms for integrating models and algorithms into the processing of criminal cases. The implementation of AI in criminal justice enhances the efficiency, transparency, and accuracy of case handling by automating document preparation, data analysis, and monitoring compliance with procedural deadlines. At the same time, several constraints persist, including dependence on the quality of training datasets, the impossibility of fully replacing human legal judgment, and the need to uphold the principles of the presumption of innocence, the right to privacy, and algorithmic transparency. The findings of the study underscore the potential of AI, provided that procedural safeguards are strictly observed and competent authorities exercise appropriate oversight. Two potential approaches are outlined: selective amendments to the Criminal Procedure Code concerning rights protection, privacy, and judicial powers; or adoption of a separate provision on digital technologies and AI. Implementation of these measures would create a balanced legal framework that enables effective use of AI while preserving core procedural guarantees. Full article

Accurate fault diagnosis of power transformers is critical for maintaining grid reliability, yet conventional dissolved gas analysis (DGA) methods face challenges in feature representation and high-dimensional data processing. This paper presents an intelligent diagnostic framework that synergistically integrates systematic feature engineering, tensor decomposition-based feature selection, and a sparrow search algorithm (SSA)-optimized multi-kernel support vector machine (MKSVM) for transformer fault classification. The proposed approach first expands the original five-dimensional gas concentration measurements to a twelve-dimensional feature space by incorporating domain-driven IEC 60599 ratio indicators and statistical aggregation descriptors, effectively capturing nonlinear interactions among gas components. Subsequently, a novel Tucker decomposition framework is developed to construct a three-way tensor encoding sample–feature–class relationships, where feature importance is quantified through both discriminative power and structural significance in low-rank representations, successfully reducing dimensionality from twelve to seven critical features while retaining 95% of discriminative information. The multi-kernel SVM architecture combines radial basis function, polynomial, and sigmoid kernels with optimized weights and hyperparameters configured through SSA’s hierarchical producer–scrounger search mechanism. Experimental validation on DGA samples across seven fault categories demonstrates that the proposed method achieves 98.33% classification accuracy, significantly outperforming existing methods, including kernel PCA-based approaches, deep learning models, and ensemble techniques. The framework establishes a reliable and accurate solution for transformer condition monitoring in power systems. Full article

To address the challenges of insufficient robustness and limited feature extraction in photovoltaic module image segmentation under complex scenarios, we propose a high-precision PV module segmentation model (Pv-UNet) that integrates Transformer and improved U-Net architecture. The model introduces a MultiScale Transformer in the encoding path to achieve cross-scale feature correlation and semantic enhancement, combines residual structure with dynamic channel adaptation mechanism in the DoubleConv module to improve feature transfer stability, and incorporates an Attention Gate module in the decoding path to suppress complex background interference. Experimental data were obtained from UAV visible light images of a photovoltaic power station in Yuezhe Town, Qiubei County, Yunnan Province. Compared with U-Net, BatchNorm-UNet, and Seg-UNet, Pv-UNet achieved significant improvements in IoU, Dice, and Precision metrics to 97.69%, 93.88%, and 97.99% respectively, while reducing the Loss value to 0.0393. The results demonstrate that our method offers notable advantages in both accuracy and robustness for PV module segmentation, providing technical support for automated inspection and intelligent monitoring of photovoltaic power stations. Full article

Understanding how soil organic matter (SOM) responds to agricultural management at the molecular scale remains a central challenge, particularly in semi-arid Mediterranean systems where long-term monitoring is limited, and soils face marked seasonal fluctuations, salinity constraints, and sustained cultivation pressure. In this study, lignin and lipid biomarkers were combined to provide complementary views of SOM dynamics in the agricultural soils of Oued Rhiou (Algeria), enabling the simultaneous assessment of plant-derived inputs, microbial processing, and stabilization pathways under cultivation and subsequent rest periods. Depth-dependent patterns showed that lignin indicators responded strongly to shifts between crop residue inputs and root-derived material, while lipid proxies captured changes in microbial activity, biosynthesis, and OM stabilization. Surface soils exhibited enhanced microbial turnover during cultivation, whereas deeper layers were characterized by selective preservation of recalcitrant compounds. Principal Component Analysis (PCA) further highlighted these processes by distinguishing vegetation-driven variability from microbial reworking patterns, with subset analyses (lignin-only and lipid-only) providing clearer explanatory power than the combined dataset. Collectively, the findings underscore the importance of integrating rest periods into agricultural cycles to promote SOM stabilization, highlight the complementarity of lignin and lipid proxies for deciphering SOM transformation pathways, and offer molecular-level insights that can guide sustainable soil management strategies aimed at balancing productivity, soil resilience, and long-term carbon sequestration. Full article

Modern power grids face increasing stress from volatile, high-dynamics loads, such as Electric Vehicle (EV) charging clusters and intermittent renewable energy sources. Accurate transformer thermal monitoring via the International Electrotechnical Commission (IEC) 60076-7 and the Institute of Electrical and Electronics Engineers (IEEE) C57.91 standards is crucial, yet their methodologies differ significantly. This study develops a comprehensive MATLAB simulation framework to quantify these differences. The analysis compares physical thermal models across multi-stage cooling—Oil Natural Air Natural (ONAN), Oil Natural Air Forced (ONAF), and Oil Forced Air Forced (OFAF)—and insulation aging models. It is demonstrated that divergence in transformer life estimation stems primarily from the physical thermal models. A ‘reversal of conservatism’ is identified, where ‘conservative’ is defined as predicting higher hot-spot temperatures and enforcing a larger safety margin. Results prove that while the IEC model is thermally more conservative during cooling failures (static mode), the IEEE model is consistently more conservative during normal active cooling. Additionally, 2D “heat maps” are presented to define safe operational zones, and the catastrophic impact of cooling system failures is quantified. These findings provide a quantitative outline for managing transformer state under increasingly demanding loading schemes. Full article

The safe and stable operation of distribution networks relies on the real-time monitoring, analysis, and feedback of power quality data. However, with the continuous advancement of distribution network construction, the number of distributed power electronic devices has increased significantly, leading to frequent power quality issues such as voltage fluctuations, harmonic pollution, and three-phase unbalance in distribution terminals. Therefore, the augmentation and processing of power quality data have become crucial for ensuring the stable operation of distribution networks. Traditional methods for augmenting and processing power quality data fail to consider the differentiated characteristics of burrs in signal sequences and neglect the comprehensive consideration of both time-domain and frequency-domain features in disturbance identification. This results in the distortion of high-frequency fault information, and insufficient robustness and accuracy in identifying Power Quality Disturbance (PQD) against the complex noise background of distribution networks. In response to these issues, we propose a power quality data augmentation and processing method for distribution terminals considering high-frequency sampling. Firstly, a burr removal method of the sampling waveform based on a high-frequency filter operator is proposed. By comprehensively considering the characteristics of concavity and convexity in both burr and normal waveforms, a high-frequency filtering operator is introduced. Additional constraints and parameters are applied to suppress sequences with burr characteristics, thereby accurately eliminating burrs while preserving the key features of valid information. This approach avoids distortion of high-frequency fault information after filtering, which supports subsequent PQD identification. Secondly, a PQD identification method based on a dual-channel time–frequency feature fusion network is proposed. The PQD signals undergo an S-transform and period reconfiguration to construct matrix image features in the time–frequency domain. Finally, these features are input into a Convolutional Neural Network (CNN) and a Transformer encoder to extract highly coupled global features, which are then fused through a cross-attention mechanism. The identification results of PQD are output through a classification layer, thereby enhancing the robustness and accuracy of disturbance identification against the complex noise background of distribution networks. Simulation results demonstrate that the proposed algorithm achieves optimal burr removal and disturbance identification accuracy. Full article

In this work, we report a compact and highly sensitive photoacoustic spectroscopy (PAS) system based on a cone–sphere coupled photoacoustic cell (CSC-PAC) for real-time detection of trace acetylene (C₂H₂) dissolved in transformer oil. The sensing module integrates a conical resonator with a spherical cavity, forming a hybrid structure that effectively enhances photoacoustic confinement and energy coupling efficiency. Finite element thermo-viscoelastic simulations were employed to optimize the cavity geometry and resonance conditions for maximum signal generation. Experimental results demonstrate a strong linear correlation between the photoacoustic signal and C₂H₂ concentration (R² > 0.999), with a sensitivity of 2.45 µV·ppm⁻¹. Allan deviation confirms a detection limit of 18.6 ppb is achieved at a 400 s averaging time, confirming excellent system stability. The miniaturized light-acoustic spectroscopy sensor, with a total volume of 7.5 mL and a rapid response time of 25.5 s, provides a high-performance and field-deployable platform for on-site monitoring of high-voltage power equipment and other industrial applications. Full article

Circulating tumor DNA (ctDNA) analysis has emerged as a powerful and minimally invasive approach for genomic profiling of metastatic castration-resistant prostate cancer (mCRPC), enabling real-time detection of tumor-derived mutations that guide therapy. Approximately 20% of mCRPC patients harbor alterations in homologous recombination repair (HRR) genes, most commonly BRCA1/2 and ATM, which are actionable with different poly-(ADP-ribose) polymerase inhibitors (PARPIs) used as monotherapy or in combination with androgen receptor signaling inhibitors (ARSIs). A smaller subset of patients with mismatch repair deficiency (MMRd) or microsatellite instability-high (MSI-high) tumors may benefit from immune checkpoint blockade with pembrolizumab. Different FDA-approved liquid biopsy assays detect these actionable alterations when tissue biopsies are unavailable or insufficient. This review summarizes current evidence on ctDNA-based genotyping in mCRPC, highlighting clinically actionable mutations, corresponding targeted therapies, and technical and analytical considerations for clinical implementation. By capturing DNA shed from multiple metastatic sites, ctDNA profiling provides a comprehensive view of tumor heterogeneity and enables serial monitoring of molecular evolution. Overall, ctDNA analysis represents a transformative advance in precision oncology, supporting personalized treatment selection and ongoing assessment of therapeutic response in mCRPC. Full article

Artificial Intelligence (AI) is rapidly transforming surgical care by enabling more accurate diagnosis and risk prediction, personalized decision-making, real-time intraoperative support, and postoperative management. Ongoing trends such as multi-task learning, real-time integration, and clinician-centered design suggest AI is maturing into a safe, pragmatic asset in surgical care. Yet, significant challenges, such as the complexity and opacity of many AI models (particularly deep learning), transparency, bias, data sharing, and equitable deployment, must be surpassed to achieve clinical trust, ethical use, and regulatory approval of AI algorithms in healthcare. Explainable Artificial Intelligence (XAI) is an emerging field that plays an important role in bridging the gap between algorithmic power and clinical use as surgery becomes increasingly data-driven. The authors reviewed current applications of XAI in the context of surgery—preoperative risk assessment, surgical planning, intraoperative guidance, and postoperative monitoring—and highlighted the absence of these mechanisms in Generative AI (e.g., ChatGPT). XAI will allow surgeons to interpret, validate, and trust AI tools. XAI applied in surgery is not a luxury: it must be a prerequisite for responsible innovation. Model bias, overfitting, and user interface design are key challenges that need to be overcome and will be explored in this review to achieve the integration of XAI into the surgical field. Unveiling the algorithm is the first step toward a safe, accountable, transparent, and human-centered surgical AI. Full article

Optical fiber biosensors have evolved into powerful tools for non-invasive biomedical analysis. While foundational principles are well-established, recent years have marked a paradigm shift, driven by advancements in nanomaterials, fabrication techniques, and data processing. This review provides a focused overview of these emerging trends, critically analyzing the innovations that distinguish the current generation of optical fiber biosensors from their predecessors. We begin with a concise summary of fundamental sensing principles, including Surface Plasmon Resonance (SPR) and Fiber Bragg Gratings (FBGs), before delving into the latest breakthroughs. Key areas of focus include integrating novel 2D materials and nanostructures to dramatically enhance sensitivity and advancing synergy with Lab-on-a-Chip (LOC) platforms. A significant portion of this review is dedicated to the rapid expansion of clinical applications, particularly in early cancer detection, infectious disease diagnostics, and continuous glucose monitoring. We highlight the pivotal trend towards wearable and in vivo sensors and explore the transformative role of artificial intelligence (AI) and machine learning (ML) in processing complex sensor data to improve diagnostic accuracy. Finally, we address the persistent challenges—biocompatibility, long-term stability, and scalable manufacturing—that must be overcome for widespread clinical adoption and commercialization, offering a forward-looking perspective on the future of this dynamic field. Full article