Search Results (411)

Deploying visual anomaly detection in industrial production requires retraining models for each product domain, leading to substantial costs in data collection, computational resources, and energy consumption that scale poorly across diverse manufacturing environments. This paper proposes PFAD, a parameter-efficient framework for cross-domain anomaly detection without retraining, enabling the direct deployment of a source model trained on a benchmark dataset to unseen industrial settings in a zero-shot manner. PFAD leverages a frozen vision transformer backbone and introduces Soft Anomaly-Aware Feature Selection (Soft AFS), which assigns continuous weights to feature channels based on anomaly discriminability, preserving information while enhancing cross-domain generalization without relying on synthetic anomalies or target-domain data. Extensive experiments on both public benchmarks and real-world industrial datasets demonstrate that PFAD achieves strong cross-domain performance, including an image-level AUROC of 0.945 for semiconductor PCB inspection using only a public dataset for training. Furthermore, PFAD supports an optional one-shot inference extension, where a single normal reference image improves detection performance in scenarios with large domain gaps (up to $+10.4$ pp), most effectively when zero-shot transfer leaves meaningful headroom. These results demonstrate that PFAD provides a practical and scalable solution for industrial anomaly detection by eliminating repeated retraining cycles and reducing associated computational and energy overhead, while maintaining high performance across heterogeneous domains. Full article

The ceramic and refractory industries are undergoing a progressive transition toward more sustainable and resource-efficient manufacturing systems driven by increasing environmental regulations, rising energy demands, and the need to reduce dependence on virgin raw materials. In this context, artificial intelligence (AI) has emerged as a promising tool for improving material design, process optimization, predictive maintenance, and circular manufacturing strategies. This review provides a comprehensive analysis of recent advances in AI applications within ceramic and refractory systems, with particular emphasis on their role in enabling circular economy approaches and intelligent manufacturing environments. The study examines the integration of machine learning, deep learning, computer vision, digital twins, and Industry 4.0 technologies across multiple domains, including materials discovery, defect detection, waste classification, process control, and sustainability assessment. In addition, the review discusses the incorporation of secondary raw materials such as fly ash, slag, waste glass, ceramic sludge, and spent refractories into circular ceramic production systems. The analysis highlights the potential of AI-driven methodologies to improve resource efficiency, reduce environmental impact, and enhance process adaptability under complex industrial conditions. Furthermore, current limitations associated with data availability, model interpretability, industrial scalability, and integration with life cycle assessment frameworks are critically discussed. Finally, future research directions are identified, emphasizing the development of standardized datasets, hybrid experimental–AI methodologies, digital manufacturing ecosystems, and intelligent decision-making systems for next-generation sustainable ceramic and refractory technologies. Full article

Background: We aimed to evaluate the feasibility, safety, and efficiency of Corneal Lenticule Extraction for Advanced Refractive Correction (CLEAR) enhancement performed after primary CLEAR. Methods: Six eyes from five patients underwent enhancement to correct residual myopic error. All procedures were carried out with the low-energy FEMTO LDV Z8 laser platform (Ziemer Ophthalmic Systems AG, Port, Switzerland) equipped with integrated optical coherence tomography enabling precise lenticule positioning. Results: The myopic residual refractive sphere was fully corrected in all cases, with refraction remaining stable over the follow-up period. All eyes showed improvement in uncorrected distance visual acuity after retreatment with CLEAR and achieved 20/20 vision or better at the final follow-up visit. Conclusions: Our results suggest that CLEAR enhancement is a safe and effective option for treating residual myopic refractive error after primary CLEAR, keeping the procedure flapless. Full article

This review analyses and logically structures modern intelligent sensor technologies in the context of animal husbandry, feed production, and veterinary medicine. The main research discussed in the article focuses on machine learning based on modern neural network models, computer vision, and sensor systems that are transforming the methods for assessing the health, behavior, and nutrition of farm animals. The first part examines modern approaches to quality control and optimization of mineral and vitamin premixes, including visual inspection using visual sensors and neural networks. Key roles are played by precise dosing, component stability (minerals, vitamins), and the transition to more bioefficient organic forms of micronutrients to reduce environmental impact. Improvements in feed and premix production are analyzed, including automation, energy management, and the use of machine learning for non-destructive quality control, defect detection, mixing homogeneity assessment, and vitamin stability prediction. The second part analyzes methods for animal location and behavior detection. This article presents computer vision-based systems, including modifications of YOLO, for automatically tracking and classifying key behavioral patterns (lying down, standing, feeding, and aggression) in cattle and pigs, even in crowded conditions. It also discusses the use of ultra-wideband (UWB) systems and accelerometers combined with machine learning for high-precision positioning and detection of specific behavioral anomalies, such as lameness and playfulness. The third section focuses on the application of machine learning in veterinary diagnostics, including the automated interpretation of medical images (X-ray, ultrasound, and MRI) as sensor data streams for the diagnosis of cardiovascular, oncological, and orthopedic diseases in farm and small animals. Furthermore, the article examines the use of machine learning models for proactive disease diagnosis in farm animals and poultry based on multimodal data and image analysis. Considerable attention is given to methods and tools for radiometric diagnosis of animal diseases at an early stage using microwave sensors, as well as laser therapy and surgery in veterinary medicine. The review concludes that the integration of intelligent systems enables a transition to data-driven livestock management, significantly improving animal welfare and, consequently, the efficiency and sustainability of agricultural production. Full article

Ports combine clusters of operational buildings, shared energy infrastructure, and structurally critical assets requiring coordinated management to ensure safety and efficiency. Nevertheless, existing Digital Twin (DT) frameworks for building energy management rarely integrate Structural Health Monitoring (SHM) with energy performance assessment, while port-specific implementations remain scarce. This paper presents a pre-operational energy-aware DT architecture for port building clusters, structured in a unified five-layer framework integrating three capabilities: (i) EGMS/InSAR-based SHM screening with planned in situ sensing and computer-vision inspection workflows; (ii) smart metering and measurement and verification (M&V) protocols aligned with ISO 50001/50015 and IPMVP standards; and (iii) weighted multi-criteria prioritization considering structural condition, energy saving potential, service continuity, and cost. The framework is applied to the Port of Formia (Italy), a brownfield district comprising nine buildings (3371 m²), 16 high-mast lighting towers, shore power infrastructure, and 90 kWp of planned photovoltaics. In the absence of operational metering, energy and carbon values are reported as bounded ex-ante scenario estimates, not as verified performance outcomes. The analysis estimates photovoltaic generation of 116–137 MWh/year and lighting retrofit savings of 31.5–36.8 MWh/year; the related carbon values are treated as gross grid-displacement upper bounds pending measured self-consumption and export data. A four-phase validation roadmap with quantitative acceptance criteria supports the transition from feasibility assessment to verified performance. Full article

Conventional fire monitoring systems frequently exhibit high false alarm rates, delayed response times, and a lack of closed-loop control capabilities, which severely constrain their deployment in complex real-world environments. To address these issues, this paper proposes an embedded fire detection, tracking, and extinguishing system based on multimodal information fusion and a lightweight neural model. The system follows a “Perception–Decision–Execution–Feedback” closed-loop paradigm and is implemented on a heterogeneous cooperative computing architecture comprising OpenMV4 H7 Plus and STM32F103C8T6 microcontrollers. The perception layer implements a decision-level RGB-infrared fusion mechanism that incorporates a pruned, INT8-quantized lightweight FOMO model, enabling real-time fire detection with an inference latency of 210 ms and a model size of merely 1.8 MB under resource-constrained embedded conditions. The decision layer employs a Bayesian inference-based multimodal fusion framework that effectively suppresses spurious fire interference. The vision-only false detection rate is 15.3%. After infrared fusion verification, the system-level false alarm rate is reduced to 2.0% on the interference test set. In the execution layer, a sixth-degree polynomial jet trajectory model was established and combined with an improved PID–PI dual-loop controller to enable dynamic optimization of spray angle and flow rate in real time. Experimental results demonstrate that the proposed system achieves an average fire recognition accuracy of 95.6% with a false alarm rate as low as 1.4%. Furthermore, it realizes an extinguishing accuracy better than ±5 cm within an effective operating range of 10–60 cm and completes the entire perception-to-extinguishing cycle within 8.5 s under illumination conditions ranging from 50 to 100,000 lux. These results demonstrate the excellent real-time capability, robustness, and energy efficiency of the proposed system, providing a practical and scalable solution for autonomous embedded fire-fighting applications in household, industrial, and warehouse environments. Full article

The rapid scaling of large language model (LLM) training has intensified demand for Graphics Processing Unit (GPU) clusters balancing throughput with energy efficiency. While NVIDIA’s H100 and B200 architectures are increasingly deployed in production datacenters, their comparative behavior under distributed training remains insufficiently characterized beyond vendor specifications, leaving datacenter operators without empirical guidance on metrics such as TFLOPs/kW and tokens-per-kilojoule. This work presents a system-level evaluation of single-node 8× H100 and 8× B200 configurations using Distributed Data Parallel (DDP) training across LLMs and vision–language models (VLMs) ranging from 7B to 32B parameters, spanning various real AI workload scenarios. We benchmark end-to-end throughput, utilization, power, energy, TFLOPs/kW, and tokens-per-kilojoule, complemented by architectural analysis explaining observed behavioral differences. Across LLM workloads, B200 achieves higher utilization (1–6%), faster training (up to 15%), and greater compute efficiency (up to 32% higher TFLOPs/GPU), attributable to higher memory bandwidth and large streaming multiprocessor (SM) count. However, B200 exhibits lower TFLOPs/kW and tokens-per-kilojoule, revealing a fundamental trade-off: throughput gains come at a measurable energy cost per useful token. VLM results further expose model-dependent asymmetries, with B200 consuming disproportionately more energy for lighter compute kernels due to elevated baseline power draw. These findings provide an empirical framework distinguishing compute efficiency from energy efficiency across next-generation GPU nodes, offering practical guidance for energy-aware AI datacenter design. Full article

Visual performance (VP) models have played a foundational role in architectural lighting design, informing illuminance standards intended to support safety, efficiency, and task performance across diverse occupant populations. This paper provides a critical historical review of VP models, tracing their development from early retinal response research and threshold visibility functions to contemporary applications in lighting standards. Key physiological and perceptual factors, including retinal illuminance, contrast, task size, and observer characteristics such as age, are examined through landmark studies that shaped suprathreshold VP modeling. Attention is given to the evolution and adoption of the Relative Visual Performance (RVP) model, which remains central to current Illuminating Engineering Society (IES) illuminance recommendations. The review further synthesizes theory-based, applied, and human-centered experimental approaches, highlighting how VP research expanded to include reaction time, reading performance, chromatic contrast, spectral power distribution, mesopic vision, and virtual reality environments. Despite this extensive body of work, VP models have seen limited revision in response to advances in lighting technology, digital displays, and LED spectral control. Based on gaps identified in prior research, this paper proposes a future modeling framework using linear mixed-effects models to independently assess and assign weights to factors influencing VP. Such an approach may support updated illuminance standards better aligned with modern lighting conditions, occupant needs, and energy efficiency goals. Full article

To address the risks of cross-border transmission of pathogenic microorganisms posed by the failure or non-compliance of shipboard ballast water treatment systems, ports urgently require efficient and flexible emergency response solutions. This study presents a novel, containerized, integrated ship-to-shore emergency response system specifically designed for the rapid inactivation of pathogenic microorganisms in ballast water. The core innovation lies in the integration of a three-degree-of-freedom (3-DOF) hydraulic robotic arm, a vision and positioning system, and a dynamic inflatable sealing structure designed for rapid, automated docking with a ship’s ballast water discharge outlet (DN250), thereby enhancing operational safety and efficiency. The system employs a purely physical treatment process of “ultrasound (US) pre-treatment + dual-stage ultraviolet (UV) disinfection,” allowing for reception and treatment without secondary chemical pollution. The integrated treatment train, consisting of US (30 kHz, 7.6–12 kW, minimum acoustic energy density ≥ 0.45 J/cm²) followed by dual-stage UV disinfection (minimum UV dose: 147 mJ/cm²), maintained effective microbial inactivation at turbidity levels of 15, 125, 250, and 500 NTU. US alone showed little direct bactericidal effect, whereas the first UV stage achieved log reduction values (LRVs) of 3.31–4.13, and the complete US + UV + UV process achieved total LRVs of 5.07–7.34 for Escherichia coli. The results showed that dual-stage UV disinfection was key to achieving high inactivation efficacy (p < 0.001), while ultrasound, despite its limited direct bactericidal effect, may have facilitated downstream UV disinfection within the sequential treatment train. This system not only fills a critical gap in port biosecurity emergency infrastructure but also provides an experimentally validated, efficient, environmentally friendly, and flexibly deployable shore-based solution. Full article

Fruit harvesting systems are undergoing a paradigm shift toward sustainable and energy-efficient mechanized platforms driven by robotics, artificial intelligence, and advanced sensing technologies. This review synthesizes recent engineering developments in fruit harvesting, focusing on system architecture, fruit detachment mechanics, and mechanized harvesting strategies. It examines harvesting classifications, mechanical principles governing detachment, and pre-harvest factors affecting performance, along with principal mechanisms including shaking, cutting, and alternative detachment techniques. Post-detachment handling and fruit recovery processes are also analyzed, together with economic and sustainability-related trade-offs between manual and mechanized harvesting systems. Recent progress in robotic harvesting systems, machine vision, and multi-sensor fusion is evaluated within the framework of smart orchard engineering, with increasing emphasis on energy-efficient design, resource optimization, reduced postharvest losses, and environmental sustainability as key performance drivers. Despite these advancements, current technologies remain constrained by fruit damage susceptibility, biological variability, limited cross-crop adaptability, and high implementation costs, limiting large-scale adoption in commercial orchards. The novelty of this review lies in establishing a unified engineering framework that links mechanical detachment principles with robotic systems and intelligent sensing technologies under an energy-efficient sustainability perspective, enabling a system-level understanding of harvesting performance and supporting the development of next-generation adaptive and sustainable fruit harvesting systems. Full article

This review provides a comprehensive synthesis of robotic fruit harvesting systems, with a particular focus on the system-level integration of perception, manipulation, and fruit detachment within autonomous harvesting environments. Recent advances in machine vision, deep learning, sensor fusion, robotic end-effectors, grasping strategies, and motion planning are critically analyzed alongside cutting, pulling, and vibration-based detachment mechanisms under unstructured orchard conditions. Beyond component-level analysis, this review emphasizes the critical role of perception–action coupling and highlights key system integration challenges, including localization errors, perception-to-action latency, and environmental variability, which continue to limit reliable field deployment. In addition, orchard and pre-harvest-related factors such as canopy structure, fruit distribution, and detachment force variability are examined in relation to their direct impact on system performance, robustness, and harvesting efficiency. Furthermore, the review extends toward system-level considerations by incorporating performance evaluation metrics, economic feasibility, and scalability constraints, which are essential for transitioning robotic harvesting systems from experimental prototypes to commercially viable solutions, including practical field deployment in distributed and multi-robot harvesting systems. Emerging technologies, including artificial intelligence, advanced sensing, digital agriculture, and energy-aware system design, are discussed as key enablers for achieving adaptive, data-driven, and scalable autonomous harvesting. The novelty of this work lies in proposing an integrated framework that explicitly links perception, manipulation, and detachment with orchard-level constraints and deployment requirements, thereby bridging the gap between algorithmic advancements and real-world implementation of autonomous fruit harvesting systems. Full article

Cascaded H-bridge (CHB) multilevel inverters are pivotal in high-power applications, such as renewable energy subsystems and motor drives, due to their superior modularity and harmonic performance. However, selecting the optimal number of levels remains a complex engineering trade-off between power quality, switching losses, and system complexity. This study presents a systematic investigation into CHB inverters ranging from three to twenty-one levels under carrier-phase-shifted sinusoidal pulse width modulation (CPS-SPWM) control. A detailed MATLAB/Simulink framework in version R2023a was established, incorporating a zero-order hold (ZOH) data synchronization protocol and parameterized macro-model MOSFETs to accurately quantify total harmonic distortion (THD) and individual switching energy dissipation. To evaluate the efficiency–quality equilibrium, a novel comprehensive evaluation index, the performance-to-loss ratio (PLR), is proposed. Simulation results indicate that while THD improves significantly with higher level counts, the marginal gains diminish beyond the 13-level configuration. Utilizing the PLR framework, the nine-level configuration is identified as a local optimum for cost-sensitive modularity, whereas the twenty-one-level setup provides the global optimum for high-performance scenarios where spectral purity is paramount. Accordingly, this proof-of-concept study provides a quantitative roadmap for designers and experimentalists to navigate the complex design space of multilevel inverters, enabling optimal allocation of hardware resources toward the net-zero vision while guiding future experimental efforts away from costly, exhaustive hardware characterization. Full article

The built environment in Saudi Arabia accounts for approximately 78% of the country’s total electricity consumption, positioning building energy performance as one of the most consequential levers available to policymakers pursuing the kingdom’s net-zero greenhouse gas emissions target for 2060 and Vision 2030’s sustainability agenda. Despite the progressive introduction of the Saudi Building Code (SBC) energy chapters SBC 601, SBC 602, and the Saudi Green Building Code (SgBC 1001), a persistent gap remains between regulatory intent and measurable outcomes across Saudi Arabia’s five distinct climatic zones. Building codes are, by design, generic policy instruments encompassing structural, fire, accessibility, and energy provisions; this paper focuses specifically on the energy and sustainability dimensions and critically examines how the SBC’s update cycle and prescriptive compliance architecture shape actual performance outcomes. This study presents three explicit research questions: (RQ1) What zone-differentiated energy savings does SBC implementation deliver across residential typologies? (RQ2) How does the Mostadam national rating system compare with international benchmarks in the Saudi context, and what caveats govern that comparison? (RQ3) What evidence-based policy interventions are needed to transition from compliance-led to performance-led building energy governance? Drawing on a systematic synthesis of 53 building energy simulation models (2018–2025), official programme data, and a structured comparative analysis of Mostadam against LEED v4.1 and BREEAM, the study finds EUI reductions of 5–25% from SBC compliance, with the largest savings in the hot–humid coastal zone. Seven prioritised policy recommendations are proposed, addressing code revision, financial incentives, digital monitoring, renewable energy thresholds, and capacity building. Full article

The vision for global net-zero carbon emissions by 2050 has intensified the demand for sustainable and low-carbon energy resources. Within this context, recent discoveries of substantial methane (CH₄) reserves, coupled with the rapidly growing interest in hydrogen (H₂) as a clean energy carrier, have underscored the strategic importance of developing efficient and economically viable technologies for methane conversion. This current review investigates hydrogen production specifically from coalbed methane (CBM), a methane-rich unconventional gas resource embedded in coal seams. Both catalytic and non-catalytic pathways for hydrogen generation are reviewed, including steam methane reforming (SMR), partial oxidation (POX), autothermal reforming (ATR), direct methane decomposition (DMD), and plasma-assisted pyrolysis. Catalytic processes such as SMR remain the most mature and cost-effective, though they emit significant CO₂ unless integrated with carbon capture and storage (CCS) technologies. Non-catalytic routes, including thermal and plasma-based decomposition, offer CO₂-free hydrogen generation while producing solid carbon byproducts with potential commercial value. Hybrid coal–CBM systems are also discussed as integrated approaches for improving energy efficiency and resource utilization. The techno-economic assessment compares hydrogen yield, production cost, and environmental impact across methods, emphasizing the advantages of CBM as a high-purity methane source. Case studies, particularly from China, highlight the practical potential of CBM in supporting hydrogen infrastructure. The paper concludes that catalytic routes such as SMR are the most commercially mature and cost-effective but remain CO₂-intensive unless coupled with carbon capture and storage. Non-catalytic approaches, including direct methane decomposition and plasma pyrolysis, enable CO₂-free hydrogen generation while yielding solid carbon byproducts of potential commercial value, though they are less developed. Hybrid coal–CBM systems offer a balanced pathway to improve efficiency, resource utilization, and sustainability in future hydrogen production strategies. Full article

Rigid mechanisms (RMs) are widely adopted in the vision-based measurement (VBM) system of laser direct imaging (LDI) machines. Constant-stiffness compliant mechanisms (CMs) improve the performance of traditional RMs. Unfortunately, constant-stiffness CMs still exhibit high energy consumption and limited adaptability during fast focusing. Inspired by the hierarchical structure and mechanical behavior of ligaments and tendons, this paper proposes a bionic bistable compliant mechanism (BBCM) to replace constant-stiffness CMs. The BBCM exhibits dynamic stiffness characteristics throughout the focusing stroke, with low stiffness in the transition phase to reduce energy consumption during rapid focusing and high local stiffness near the stable positions to maintain focusing stability. A numerical model is established to analyze the variable-stiffness and bistable characteristics of the proposed BBCM. Prototype tests demonstrate the bistable response, dynamic feasibility, and energy-saving potential of the mechanism. Under the tested camera-loaded flying-shot condition, compared with the constant-stiffness CM, the BBCM reduces electrical and mechanical energy consumption by 12.37% and 9.74%, respectively. The target recognition results indicate that the BBCM-based system maintains comparable visual measurement performance. These results demonstrate that the proposed BBCM provides a feasible mechanism-level solution for energy-efficient dual-position focusing in LDI machines. Full article