Search Results (3,321)

Underwater object detection is critical for marine resource utilization, ecological monitoring, and maritime security, yet it remains constrained by optical degradation, high energy consumption, and vulnerability to adversarial perturbations. To address these challenges, this study proposes an Adaptive Vision Transformer (A-ViT)-based detection framework. At the hardware level, a systematic power-modeling and endurance-estimation scheme ensures feasibility across shallow- and deep-water missions. Through the super-resolution reconstruction based on the Hybrid Attention Transformer (HAT) and the staged enhancement with the Deep Initialization and Deep Inception and Channel-wise Attention Module (DICAM), the image quality was significantly improved. Specifically, the Peak Signal-to-Noise Ratio (PSNR) increased by 74.8%, and the Structural Similarity Index (SSIM) improved by 375.8%. Furthermore, the Underwater Image Quality Measure (UIQM) rose from 3.00 to 3.85, while the Underwater Color Image Quality Evaluation (UCIQE) increased from 0.550 to 0.673, demonstrating substantial enhancement in both visual fidelity and color consistency. Detection accuracy is further enhanced by an improved YOLOv11-Coordinate Attention–High-order Spatial Feature Pyramid Network (YOLOv11-CA_HSFPN), which attains a mean Average Precision at Intersection over Union 0.5 (mAP@0.5) of 56.2%, exceeding the baseline YOLOv11 by 1.5 percentage points while maintaining 10.5 ms latency. The proposed A-ViT + ROI reduces inference latency by 27.3% and memory usage by 74.6% when integrated with YOLOv11-CA_HSFPN and achieves up to 48.9% latency reduction and 80.0% VRAM savings in other detectors. An additional Image-stage Attack QuickCheck (IAQ) defense module reduces adversarial-attack-induced latency growth by 33–40%, effectively preventing computational overload. Full article

Energy efficiency is widely recognized as a critical strategy for reducing energy consumption in industrial systems. Improving energy efficiency has become a central point in industrial systems aiming to reduce energy consumption and operational costs. Industrial air compressors are among the most energy-intensive assets and often operate under static control policies that fail to adapt to real-time dynamics. This paper proposes a cognitive digital twin (CDT) framework that integrates reinforcement learning as, especially, a Proximal Policy Optimization (PPO) agent into the virtual replica of the air compressor system. CDT learns continuous from multidimensional telemetry which includes power, outlet pressure, air flow, and intake temperature, enabling autonomous decision-making, fault adaptation, and dynamic energy optimization. Simulation results demonstrate that PPO strategy reduces average SEC by 12.4%, yielding annual energy savings of approximately 70,800 kWh and a projected payback period of one year. These findings highlight the CDT potential to transform industrial asset management by bridging intelligent control. Full article

Electric Submersible Pumps (ESPs) are widely deployed in high-flowrate wells but are constrained by frequent failures and the need for rig-based interventions. This study presents the development and field validation of a rigless cable-deployed ESP (CDESP) system designed to enhance operational uptime and reduce intervention costs. The system features a corrosion-resistant metal-jacketed power cable, an inverted ESP configuration that eliminates the motor lead extension (MLE), and a vertical cable hanger spool (VCHS) for surface integration without removing the production tree. A field trial in a high-H₂S well demonstrated successful rigless deployment using coiled tubing (CT), achieving over two years of continuous runtime. Post-retrieval inspection revealed minimal wear, validating the system’s mechanical durability and reusability. Operational performance demonstrated reduced non-productive time (NPT), enhanced safety, and cost savings, with deployment completed in under 24 h, compared to the typical 10–14 days for rig-based methods. The CDESP system’s compatibility with digital monitoring and its potential for redeployment across wells positions it as a transformative solution for offshore and mature field operations. These findings support the broader adoption of CDESP as a scalable, efficient, and safer alternative to conventional ESP systems. Full article

The sun tracker plays a major role in improving the energy efficiency of a solar power system. To address this role, this study experimentally explores the energy efficiency of three sun-tracking systems with three types of degrees of freedom (DOFs)—namely, single-axis for both elevation (1DOF_Elev) and azimuth (1DOF_Azim), and dual-axis (2DOF)—integrated in photovoltaic (PV) panels. The three sun-tracking configurations are assessed and compared with the fixed system (0DOF), considering both the net electricity output of the studied photovoltaic system and the energy consumption of each configuration during operation. To accomplish this objective, hardware and software tools were deployed to create a prototype. The sun-tracking techniques are based on the sun position algorithm (astronomical calculations). The different data (time, voltage, current, power, azimuth, and elevation) are stored in real time within a locally developed database which represents crucial data within SCADA systems embedded in smart grids. The results revealed that the 2DOF system exhibits the highest energy efficiency (37.23%), followed by 1DOF_Azim (12.86%), and then by 1DOF_Elev (10.05%), when compared to 0DOF. Overall, this study provides solutions for optimizing photovoltaic energy production and could be integrated into battery-powered devices to accelerate battery recharging, achieving time savings of over 30%. Full article

The electrification of non-road mobile machinery is advancing to enhance sustainability and reduce emissions. This study investigates how to maximize the efficiency of the retrofitting of a material handler from an internal combustion engine to a battery-powered electric motor, while keeping the hydraulic system unchanged. Using a previously validated model, this study proposes three control strategies for the electric motor and hydraulic pump to enhance efficiency and performance. The first control strategy optimizes hydraulic pump performance within its most efficient displacement range. The second strategy maximizes powertrain efficiency by considering both efficiencies of the electric motor and hydraulic pump. The third strategy uses a servo-actuated valve to adjust the load-sensing margin and exhibits energy savings up to 14.2% and an 11.5% increase in efficiency. The proposed strategies avoid complex optimization algorithms, ensuring practical applicability for small- and medium-sized enterprises, which often face cost constraints and limited scalability. Full article

The utilization of high millimeter wave (mmWave, 30–100 GHz) in 5G New Radio (NR) systems and sub-terahertz (sub-THz, 100–300 GHz) in future 6G requires dense deployments of base stations (BSs) to provide uninterrupted connectivity to the users. 3GPP Integrated Access and Backhaul (IAB) deployments that utilize wireless relay nodes offer cost-efficient densification options for these systems. However, the infrastructure that is often scaled and deployed for busy-hour traffic conditions is not used efficiently during periods when traffic demands are lower, resulting in excessive power consumption. In this work, we consider the IAB roadside deployment option and demonstrate that the deployment designed to meet traffic demands during busy-hour traffic conditions can be efficiently controlled to provide large power savings during other times of the day. To demonstrate the feasibility of the solution, we will utilize the tools of stochastic geometry and queuing theory. Our numerical results show that the dynamic switching of IAB nodes may lead to power savings of up to 40% depending on the traffic and deployment specifics. The proposed methodology also allows us to maintain the specified upper bound on the transit delay and improve the utilization of active IAB nodes. Full article

The maritime industry faces increasing pressure to improve energy efficiency, a challenge that extends to the luxury yacht sector. This study presents a comprehensive hydrodynamic assessment for retrofitting a bespoke Energy Saving Device (ESD) onto a 45 m motor yacht. A full-scale self-propulsion Computational Fluid Dynamics (CFD) model was developed and validated directly against dedicated sea trial data, ensuring high fidelity and bypassing traditional scaling uncertainties. The validated model was then utilized to design and optimize a custom pre-propeller duct system. A parametric study varying the duct’s angle of attack identified an optimal configuration of ${20}^{\circ }$, which achieves a definitive power saving of 4.7% at the vessel’s cruise speed of 12.3 knots. Analysis of the propulsive factors reveals that the gain is primarily driven by a substantial increase in the hull efficiency, ${\eta }_H$, achieved by conditioning the propeller inflow. This improvement successfully compensates for the corresponding decrease in the propeller’s open-water efficiency, ${\eta }_o$. This work demonstrates a successful end-to-end numerical workflow for designing and verifying an effective, retrofittable ESD, highlighting a practical solution for reducing fuel consumption in existing motor yachts. Full article

Emissions reduction and energy saving at thermal power plants are crucial for energy development. This paper presents the results of thermodynamic analysis and optimization of thermal circuits of combined-cycle power plants incorporating an organic Rankine cycle and supplementary burners. It is established that at a power unit with GTE-170, the transition from a binary cycle with a double-circuit waste heat boiler to a trinary one leads to an increase in net efficiency by 0.79%. It is established that in the trinary cycle, fuel afterburning in the exhaust-gas environment leads to an increase in the net capacity of the power plant: the increase is up to 4.1% with an increase in the degree of afterburning by 0.1 at a steam temperature of 515 °C. It was revealed that the introduction of intermediate superheat provides an increase in the efficiency of the binary cycle by an average of 0.2–3%, and of the trinary cycle by 2–4%, with a change in the degree of afterburning from 0 to 0.5 at an initial steam temperature of 515 °C. The use of supplementary combustion and the organic Rankine cycle make it possible to reduce carbon dioxide emissions in combined-cycle power plants. Compared to a single-pressure combined cycle, the ORC-integrated configuration reduces specific CO₂ emissions by more than 7.5%, while supplementary fuel combustion with an increased steam inlet temperature results in a reduction of up to 10%. Full article

Renewable energy sources provide environmental and economic benefits by replacing conventional energy sources. In Korea, photovoltaic (PV) systems are increasingly deployed in apartment complexes and residential buildings. In self-consumption PV systems, surplus generation exceeding local demand often leads to a reverse power flow. This phenomenon becomes more frequent in microgrid environments where multiple distributed energy resources are interconnected. Accordingly, inverter control strategies based on generation forecasting have emerged as critical challenges. In this paper, we propose an on-device artificial intelligence model for inverter control that integrates net power forecasting with time-series neural networks. Two novel forecasting methods were proposed and introduced: Prediction-to-Prediction (P–P) and Net-Power Prediction (N–P). Various neural network models were trained and evaluated using multiple performance metrics. A novel threshold adjustment mechanism based on the mean absolute error was designed for inverter control. The control scenarios were analyzed by comparing the actual power losses with the forecast-based power losses, and the energy savings were quantified by adjusting the correction factor. The proposed forecasting methods achieved a reduction of approximately 40–70% in energy losses compared with the actual loss levels. The threshold adjustment strategy enhances flexibility in balancing the number of on/off switching events and the power loss, contributing to improved energy efficiency and system stability. Full article

The assessment of energy savings is not a trivial matter, as we have direct meters for consumption, but not for the absence of consumption. Calculating a simple difference between consumption before and after the implementation of an energy saving measure is also an incomplete assessment. The only way to determine energy savings is to compare the consumption that would have occurred in the absence of the saving measure with the actual consumption, with reference to the same external conditions and the same period. This is what the international IPMVP^® protocol establishes. This study, based on two case studies of industrial energy saving measures, explores the aspects of the calculation related to decarbonization and economic evaluation. In particular, sensitivity analyses of energy and economic indicators are carried out based on factors that evolve over time, such as the rate of inflation and discounting of investments and the variation in the carbon dioxide emission factor for electricity production. The main results highlight that the assumption of a constant electricity emission factor leads to an overestimation of the total CO₂ savings from energy efficiency interventions that can be more than 40%. The uniqueness of this paper is the application of a standardized savings evaluation procedure (IPMVP^®) in order to analyze the sensitivity of economic savings towards some key financial parameters, and the specific fitting of an electricity emission model to the Italian power sector in order to correct the carbon savings evaluation to the projected emission factor evolution. Full article

We propose a novel hybrid deep learning framework that synergistically integrates Convolutional Neural Networks (CNNs), Spiking Neural Networks (SNNs), and Generative Adversarial Networks (GANs) for robust and accurate classification of high-resolution frontal and sagittal human gait video sequences—capturing both lower-limb kinematics and upper-body posture—from subjects with Knee Osteoarthritis (KOA), Parkinson’s Disease (PD), and healthy Normal (NM) controls, classified into three disease-type categories. Our approach first employs a tailored CNN backbone to extract rich spatial features from fixed-length clips (e.g., 16 frames resized to 128 × 128 px), which are then temporally encoded and processed by an SNN layer to capture dynamic gait patterns. To address class imbalance and enhance generalization, a conditional GAN augments rare severity classes with realistic synthetic gait sequences. Evaluated on the controlled, marker-based KOA-PD-NM laboratory public dataset, our model achieves an overall accuracy of 99.47%, a sensitivity of 98.4%, a specificity of 99.0%, and an F1-score of 98.6%, outperforming baseline CNN, SNN, and CNN–SNN configurations by over 2.5% in accuracy and 3.1% in F1-score. Ablation studies confirm that GAN-based augmentation yields a 1.9% accuracy gain, while the SNN layer provides critical temporal robustness. Our findings demonstrate that this CNN–SNN–GAN paradigm offers a powerful, computationally efficient solution for high-precision, gait-based disease classification, achieving a 48.4% reduction in FLOPs (1.82 GFLOPs to 0.94 GFLOPs) and 9.2% lower average power consumption (68.4 W to 62.1 W) on Kaggle P100 GPU compared to CNN-only baselines. The hybrid model demonstrates significant potential for energy savings on neuromorphic hardware, with an estimated 13.2% reduction in energy per inference based on FLOP-based analysis, positioning it favorably for deployment in resource-constrained clinical environments and edge computing scenarios. Full article

This study evaluates indoor thermal comfort and the energy performance of HVAC control strategies in the Congo Zone of a zoological facility located in Poland. The main objective in this zone is to maintain adequate relative humidity, which is more critical for plants and animals than the indoor air temperature range. Long-term measurements were carried out to determine the variation of air system heat transfer as a function of outdoor air temperature. To determine the energy demand for heating, cooling, and air transport, eight control algorithms were analysed, each differing in a single detail but potentially affecting overall energy use and thermal comfort. The algorithms combined the following features: maintaining a constant supply or indoor air temperature; operating with a constant or modulated recirculation damper position; maintaining a constant or variable airflow (CAV or VAV); operating within the normal setpoint range or with an extended range of 1 °C; controlling temperature only or both temperature and humidity; and utilising or not utilising free cooling. The control algorithm operating in the facility maintained indoor humidity within acceptable limits for 98% of the year but failed to meet temperature requirements for 28% of the time. Refined strategies achieved energy savings of up to 74% in fan power and 80% in cooling demand, though often at the cost of reduced humidity control. Full article

Background: Breast cancer remains the most diagnosed cancer in European countries, with diverse screening modalities requiring economic evaluation for optimal resource allocation. This systematic review evaluated the cost-effectiveness of breast cancer screening strategies across European healthcare contexts. Methods: We conducted a comprehensive search across PubMed, ScienceDirect, Cochrane Library, Scopus, and Google Scholar following PRISMA guidelines (1990–2024). Studies were evaluated using the Consolidated Health Economic Evaluation Reporting Standards (CHEERS) checklist. Economic standardization employed healthcare-specific inflation indices and purchasing power parity adjustments, with costs converted to 2020 EUR. Results: From 1449 studies, 23 met inclusion criteria, with significant geographic imbalance (74% from North-Western/Central Europe, 4% from South-Eastern Europe). Mammography screening for women aged 50–69 years demonstrated consistent cost-effectiveness (EUR 3000–8000 per quality-adjusted life year (QALY)) with high confidence. For women under 50, screening showed substantially higher costs (EUR 105,000 per year of life saved). Magnetic resonance imaging (MRI) screening showed cost-effectiveness for high-risk populations (EUR 18,201–33,534 per QALY) with moderate confidence. Conclusions: Biennial mammography screening for women aged 50–69 demonstrates consistent cost-effectiveness across European contexts. Findings have highest applicability to North-Western and Central European healthcare systems, with limited generalizability to Southern and Eastern Europe due to evidence gaps. Full article

This article presents the accumulated technical and scientific knowledge from energy performance upgrade work in emblematic and essential municipal and public buildings in Crete and the Greek islands, such as the Venetian historical building Loggia, which is used as the Heraklion City Hall, the Natural History Museum of Crete, Pancretan Stadium, the municipal swimming pool of the municipality of Minoa Pediadas, the indoor sports hall in Leros, primary schools, high schools and a cultural center. Each one of the aforementioned buildings has a distinct use, thus covering almost all different categories of municipal or public buildings and facilities. The applied energy performance upgrade process in general terms is: (1) Mapping of the current situation, regarding the existing infrastructure and final energy consumption. (2) Formulation and sizing of the proposed passive measures and calculation of the new indoor heating and cooling loads. (3) Selection, sizing and siting of the proposed active measures and calculation of the new expecting energy sources consumption. (4) Sizing and siting of power and heat production systems from renewable energy sources (RES). Through the work accomplished and presented in this article, practically all the most technically and economically feasible passive and active measures were studied: insulation of opaque surfaces, opening overhangs, natural ventilation, replacement of openings, daylighting solar tubes, open-loop geo-exchange plants, refrigerant or water distribution networks, air-to-water heat pumps, solar thermal collectors, lighting systems, automation systems, photovoltaics etc. The main results of the research showed energy savings through passive and active systems that can exceed 70%, depending mainly on the existing energy performance of the facility. By introducing photovoltaic plants operating under the net-metering mode, energy performance upgrades up to zero-energy facilities can be achieved. The payback periods range from 12 to 45 years. The setup budgets of the presented projects range from a few hundred thousand euros to 7 million euros. Full article

With the increasing adoption of lithium-ion batteries (LIBs) as the batteries of choice in electromobility, personal electronic devices, and so on, comes the challenge of ageing, which prevents the batteries from performing optimally and meeting the design intent. This is observed in the form of declining power capability due to the increase in resistance and the reduction in capacity that can be stored or discharged from them. Unfortunately, the cost of assessing batteries after the first use remains a daunting challenge. In our work, we propose an approach that carries out fast preliminary grading based on resistance and capacity by first connecting old cells of the same chemistry and model in series with resistors to limit the branch current, then connecting the branches in parallel to equalise the voltages. A Simulink model of NCR18650PF Panasonic cells with adaptive-series resistance is compared with a fixed-series resistance and found to improve the balancing time from over 24 h to just 8 h. Electrochemical impedance spectroscopy (EIS) was carried out on the individual balanced cells between 0.1 Hz and 5 kHz so that the real impedance, imaginary impedance, absolute impedance, and phase were compared with the SOH of the cells at each frequency. Results show that the imaginary impedance in the 6.6 Hz frequency range shows a good correlation coefficient > 0.98 with the SOH, especially with a state of charge (SOC) of about 75–85% for the LCO cells. By selecting only a sample from all the cells that covers a wide range of ages and carrying out a full-capacity checkup on them, a simple correlation with the SOH and the EIS measurements for different frequencies can be used to estimate the SOH of the other cells that were connected in the same parallel connection. This is a considerable time saving in the charge and discharge time on the other cells in facilities that lack the capacity for simultaneous cycling of all cells. There are also huge energy savings in not having to cycle all the cells. Therefore, it offers a more efficient approach to grading spent cells than carrying out full capacity tests. Full article