Search Results (1,472)

Background/Objectives: Melanoma is an aggressive type of skin cancer that poses serious health risks if not detected in its early stages. Although early diagnosis enables effective treatment, delays can result in life-threatening consequences. Traditional diagnostic processes predominantly rely on the subjective expertise of dermatologists, which can lead to variability and time inefficiencies. Consequently, there is an increasing demand for automated systems that can accurately classify melanoma lesions and retrieve visually similar cases to support clinical decision-making. Methods: This study proposes a transfer learning (TL)-based deep learning (DL) framework for the classification of melanoma images and the enhancement of content-based image retrieval (CBIR) systems. Pre-trained models including DenseNet121, InceptionV3, Vision Transformer (ViT), and Xception were employed to extract deep feature representations. These features were integrated using a weighted fusion strategy and classified through an Ensemble learning approach designed to capitalize on the complementary strengths of the individual models. The performance of the proposed system was evaluated using classification accuracy and mean Average Precision (mAP) metrics. Results: Experimental evaluations demonstrated that the proposed Ensemble model significantly outperformed each standalone model in both classification and retrieval tasks. The Ensemble approach achieved a classification accuracy of 95.25%. In the CBIR task, the system attained a mean Average Precision (mAP) score of 0.9538, indicating high retrieval effectiveness. The performance gains were attributed to the synergistic integration of features from diverse model architectures through the ensemble and fusion strategies. Conclusions: The findings underscore the effectiveness of TL-based DL models in automating melanoma image classification and enhancing CBIR systems. The integration of deep features from multiple pre-trained models using an Ensemble approach not only improved accuracy but also demonstrated robustness in feature generalization. This approach holds promise for integration into clinical workflows, offering improved diagnostic accuracy and efficiency in the early detection of melanoma. Full article

This paper presents a simulation-based investigation into control strategies for mitigating the consequences of cyber-assault on the steering systems of the Maritime Autonomous Surface Ships (MASS). The study focuses on two simulation experiments conducted within the Simulink/MATLAB environment, utilizing the catamaran “Nymo” MASS mathematical model to represent vessel dynamics. Cyber-attacks are modeled as external disturbances affecting the rudder control signal, emulating realistic interference scenarios. To assess control resilience, two configurations are compared during a representative turning maneuver to a specified heading: (1) a Proportional–Integral–Derivative (PID) regulator augmented with a Least Mean Squares (LMS) adaptive filter, and (2) a Nonlinear Autoregressive Moving Average with Exogenous Input (NARMA-L2) neural network regulator. The PID and LMS configurations aim to enhance the disturbance rejection capabilities of the classical controller through adaptive filtering, while the NARMA-L2 approach represents a data-driven, nonlinear control alternative. Simulation results indicate that although the PID and LMS setups demonstrate improved performance over standalone PID in the presence of cyber-induced disturbances, the NARMA-L2 controller exhibits superior adaptability, accuracy, and robustness under adversarial conditions. These findings suggest that neural network-based control offers a promising pathway for developing cyber-resilient steering systems in autonomous maritime vessels. Full article

This study presents a breakthrough in sustainable injection molding by uniquely combining a backpropagation neural network (BPNN) with particle swarm optimization (PSO) to overcome traditional optimization challenges. The BPNN’s exceptional ability to learn complex nonlinear relationships between six key process parameters (including melt temperature and holding pressure) and product quality is amplified by PSO’s intelligent search capability, which efficiently navigates the high-dimensional parameter space. Together, this hybrid approach achieves what neither method could accomplish alone: the BPNN accurately models the intricate process-quality relationships, while PSO rapidly converges on optimal parameter sets that simultaneously meet strict quality targets (66–70 g weight, 3–5 mm thickness) and minimize energy consumption. The significance of this integration is demonstrated through three key outcomes: First, the BPNN-PSO combination reduced optimization time by 40% compared to traditional trial-and-error methods. Second, it achieved remarkable prediction accuracy (RMSE 0.8229 for thickness, 1.5123 for weight) that surpassed standalone BPNN implementations. Third, the method’s efficiency enabled SMEs to achieve CAE-level precision without expensive software, reducing setup costs by approximately 25%. Experimental validation confirmed that the optimized parameters decreased energy use by 28% and material waste by 35% while consistently producing parts within specifications. This research provides manufacturers with a practical, scalable solution that transforms injection molding from an experience-dependent craft to a data-driven science. The BPNN-PSO framework not only delivers superior technical results but does so in a way that is accessible to resource-constrained manufacturers, marking a significant step toward sustainable, intelligent production systems. For SMEs, this framework offers a practical pathway to achieve both economic and environmental sustainability, reducing reliance on resource-intensive CAE tools while cutting production costs by an estimated 22% through waste and energy savings. The study provides a replicable blueprint for implementing data-driven sustainability in injection molding operations without compromising product quality or operational efficiency. Full article

Background/Objectives: The demand for accessible and reliable digital health services has increased significantly in recent years, particularly in regions facing physician shortages. HomeDOCtor, a conversational AI platform developed in Slovenia, addresses this need with a nationally adapted architecture that combines retrieval-augmented generation (RAG) and a Redis-based vector database of curated medical guidelines. The objective of this study was to assess the performance and impact of HomeDOCtor in providing AI-powered healthcare assistance. Methods: HomeDOCtor is designed for human-centered communication and clinical relevance, supporting multilingual and multimedia citizen inputs while being available 24/7. It was tested using a set of 100 international clinical vignettes and 150 internal medicine exam questions from the University of Ljubljana to validate its clinical performance. Results: During its six-month nationwide deployment, HomeDOCtor received overwhelmingly positive user feedback with minimal criticism, and exceeded initial expectations, especially in light of widespread media narratives warning about the risks of AI. HomeDOCtor autonomously delivered localized, evidence-based guidance, including self-care instructions and referral suggestions, with average response times under three seconds. On international benchmarks, the system achieved ≥95% Top-1 diagnostic accuracy, comparable to leading medical AI platforms, and significantly outperformed stand-alone ChatGPT-4o in the national context (90.7% vs. 80.7%, p = 0.0135). Conclusions: Practically, HomeDOCtor eases the burden on healthcare professionals by providing citizens with 24/7 autonomous, personalized triage and self-care guidance for less complex medical issues, ensuring that these cases are self-managed efficiently. The system also identifies more serious cases that might otherwise be neglected, directing them to professionals for appropriate care. Theoretically, HomeDOCtor demonstrates that domain-specific, nationally adapted large language models can outperform general-purpose models. Methodologically, it offers a framework for integrating GDPR-compliant AI solutions in healthcare. These findings emphasize the value of localization in conversational AI and telemedicine solutions across diverse national contexts. Full article

The specific features of the phase diagrams of aqueous Pluronic systems, and particularly those of reverse Pluronics, are critically important for their broad range of applications, notably as nanocarriers for anticancer molecules. This work aims to investigate the effect of increasing hydrophobicity, achieved by varying the PPO/PEO ratio and the molecular weight, on the phase behavior of three reverse Pluronics: 10R5 [(PPO)₈–(PEO)₂₂–(PPO)₈], 17R4 [(PPO)₁₄–(PEO)₂₄–(PPO)₁₄] and 31R1 [(PPO)₂₆–(PEO)₇–(PPO)₂₆]. A broad set of physical measurements, including density, sound velocity, viscosity, and surface tension, was used to characterize the physical properties of the solutions. These data were complemented by additional techniques such as direct observation, dynamic light scattering, and rheological measurements. Based on the primary measurements, molar volume, apparent adiabatic compressibility, and hydration profiles were subsequently derived. Phase diagrams were constructed for each system over concentration ranges of 0.1–90 wt.% and temperatures between 6 and 70 °C, identifying distinct regions corresponding to random networks, flower-like micelles, and micellar networks. Notably, the 31R1/water system does not form flower-like micelles, whereas both the 17R4/water and 10R5/water systems display such structures, albeit in a narrow interval, that shift toward higher concentrations and temperatures with increasing PPO/PEO ratio. Altogether, the present study provides new insights into the physicochemical behavior of reverse Pluronic systems, offering a foundation for their rational design as hydrophobic nanocarriers, either as standalone entities or in conjunction with other copolymers. Full article

The shikimate pathway is the fundamental metabolic route for aromatic amino acid biosynthesis in bacteria, plants, and fungi, but is absent in mammals. This review explores how multi-enzyme synergy and allosteric regulation coordinate metabolic flux through this pathway by focusing on three key enzymes: 3-deoxy-d-arabino-heptulosonate-7-phosphate synthase, chorismate mutase, and tryptophan synthase. We examine the structural diversity and distribution of these enzymes across evolutionary domains, highlighting conserved catalytic mechanisms alongside species-specific regulatory adaptations. The review covers directed evolution strategies that have transformed naturally regulated enzymes into standalone biocatalysts with enhanced activity and expanded substrate scope, enabling synthesis of non-canonical amino acids and complex organic molecules. Industrial applications demonstrate the pathway’s potential for sustainable production of pharmaceuticals, polymer precursors, and specialty chemicals through engineered microbial platforms. Additionally, we discuss the therapeutic potential of inhibitors targeting pathogenic organisms, particularly their mechanisms of action and antimicrobial efficacy. This comprehensive review establishes the shikimate pathway as a paradigmatic system where understanding allosteric networks enables the rational design of biocatalytic platforms, providing blueprints for biotechnological innovation and demonstrating how evolutionary constraints can be overcome through protein engineering to create superior industrial biocatalysts. Full article

Falls are a major safety concern in physically demanding occupations such as roofing, where workers operate on inclined surfaces under unstable postures. While inertial measurement units (IMUs) are widely used in wearable fall detection systems, they often fail to capture early indicators of instability related to foot–ground interactions. This study evaluates the effectiveness of plantar pressure sensors, alone and combined with IMUs, for fall detection on sloped surfaces. We collected data in a controlled laboratory environment using a custom-built roof mockup with incline angles of 0°, 15°, and 30°. Participants performed roofing-relevant activities, including standing, walking, stooping, kneeling, and simulated fall events. Statistical features were extracted from synchronized IMU and plantar pressure data, and multiple machine learning models were trained and evaluated, including traditional classifiers and deep learning architectures, such as MLP and CNN. Our results show that integrating plantar pressure sensors significantly improves fall detection. A CNN using just three IMUs and two plantar pressure sensors achieved the highest F1 score of 0.88, outperforming the full 17-sensor IMU setup. These findings support the use of multimodal sensor fusion for developing efficient and accurate wearable systems for fall detection and physical health monitoring. Full article

This study presents the first combined techno-economic and environmental analysis of IPA dehydration using HybSi^® membranes across three configurations, offering a low-emission alternative to conventional azeotropic distillation. The processes are simulated in Aspen Plus, and include two hybrid separation processes (i.e., distillation–pervaporation and distillation–pervaporation–distillation) and one standalone pervaporation process. The pervaporation module uses data from experiments that were performed using HybSi^® AR membranes at 130 °C and two vacuum pressures (20 and 50 mbar). The separation processes were systematically compared using a comprehensive set of performance indicators covering technical, economic, and environmental aspects. A new cost-efficiency metric, COPCO, is introduced, alongside updated modeling under 2024 market conditions. The isopropanol recovery and water selectivity were >99.5% and >98.7%, respectively, in all pervaporation-based processes. It was found that the hybrid distillation–pervaporation process resulted in a 42% reduction in the levelized cost of the benchmark azeotropic distillation process, while standalone pervaporation resulted in a 38% reduction. The CO₂ footprint was also reduced significantly in all cases, up to 86% in the case of standalone pervaporation compared to azeotropic distillation. The COPCO analysis revealed that the distillation–pervaporation configuration offers the highest cost-efficiency among the evaluated systems. Sensitivity analysis revealed that feed flow rate, average water flux, membrane module price, membrane lifetime, and steam price significantly impact the levelized cost. Lower vacuum pressure and feed water near the azeotropic composition enhance economic performance. Full article

This study presents a hybrid method for state-of-charge (SOC) estimation of lithium-ion batteries using LSTM neural networks optimized with genetic algorithms (GA), combined with Coulomb Counting (CC) as an initial estimator. Experimental tests were conducted using medium-voltage (48–72 V) lithium-ion battery packs under standardized driving cycles (NEDC and WLTP). The proposed method enhances prediction accuracy under dynamic conditions by recalibrating the LSTM output with CC estimates through a dynamic fusion parameter $\alpha$. The novelty of this approach lies in the integration of machine learning and physical modeling, optimized via evolutionary algorithms, to address limitations of standalone methods in real-time applications. The hybrid model achieved a mean absolute error (MAE) of 0.181%, outperforming conventional estimation strategies. These findings contribute to more reliable battery management systems (BMS) for electric vehicles and second-life applications. Full article

This paper presents a standalone system that utilizes a capacitive isolated series resonant converter using an extremum-seeking control algorithm to extract the maximum power from PV panels. While resonant converters have been used for battery charging applications, series resonant converters that utilize capacitive galvanic isolation have not been sufficiently explored, and their design considerations for battery charging have not been established. In addition, extremum-seeking control algorithms have been explored for maximum power point tracking using PWM converters, but not using PFM converters such as resonant converters. This paper lays out the advantages of using an extremum-seeking-based control algorithm with resonant converters, specifically series resonant converters, and it presents simulation results of a 200 W standalone battery charging system to validate the stated benefits. Full article

The integration of renewable energy sources (RESs) into power systems, particularly in microgrids, is becoming a prominent trend aimed at reducing dependence on traditional energy sources. Replacing conventional synchronous generators with grid-connected RESs through power electronic converters has significantly reduced the inertia of microgrids. This reduction negatively impacts the dynamics and operational performance of microgrids when confronted with uncertainties, posing challenges to frequency and voltage stability, especially in a standalone operating mode. To address this issue, this research proposes enhancing microgrid stability through frequency control based on virtual inertia (VI). Additionally, the Iterative Learning Control (ILC) method is employed, leveraging iterative learning strategies to improve the quality of output response control. Accordingly, the ILC-VI control method is introduced, integrating the iterative learning mechanism into the virtual inertia controller to simultaneously enhance the system’s inertia and damping coefficient, thereby improving frequency stability under varying operating conditions. The effectiveness of the ILC-VI method is evaluated in comparison with the conventional VI (C-VI) control method through simulations conducted on the MATLAB/Simulink platform. Simulation results demonstrate that the ILC-VI method significantly reduces the frequency nadir, the rate of change of frequency (RoCoF), and steady-state error across iterations, while also enhancing the system’s robustness against substantial variations from renewable energy sources. Furthermore, this study analyzes the effects of varying virtual inertia values, shedding light on their role in influencing response quality and convergence speed. This research underscores the potential of the ILC-VI control method in providing effective support for low-inertia microgrids. Full article

This study presents preliminary findings from an experimental campaign conducted on a pilot-scale green hydrogen production plant powered by a photovoltaic (PV) system. The integrated setup, implemented at the University “Mediterranea” of Reggio Calabria, includes renewable energy generation, hydrogen production via electrolysis, on-site storage, and reconversion through fuel cells. The investigation assessed system performance under different configurations (on-grid and selective stand-alone modes), focusing on key operational phases such as inerting, purging, pressurization, hydrogen generation, and depressurization. Results indicate a strong linear correlation between the electrolyser’s power setpoint and the pressure rise rate, with a maximum gradient of 0.236 bar/min observed at 75% power input. The system demonstrated robust and stable operation, efficient control of shutdown sequences, and effective integration with PV input. These outcomes support the technical feasibility of small-scale hydrogen systems driven by renewables and offer valuable reference data for calibration models and future optimization strategies. Full article

Robots are increasingly emerging as effective platforms to overcome a wide range of challenges in agriculture. Beyond functioning as standalone systems, agricultural robots are proving valuable as collaborative platforms, capable of supporting and integrating with humans and other technologies and agricultural activities. In this study, we designed and implemented an automated system embedded in a ground-based robotic platform to support spraying drone operations. The system consists of a robotic platform that carries the spraying drone along with all necessary support devices, including a water tank, chemical reservoirs, a mixer, generators for drone battery charging, and a top landing pad. The system is controlled with a mobile app that calculates the total amount of water and chemicals required and sends commands to the platform to prepare the application mixture. The input information in the app includes the field area, application rate, and up to three chemical dosages simultaneously. Additionally, the platform allows the drone to take off from and land on it, enhancing both safety and operability. A set of pumps was used to deliver water and chemicals as specified in the mobile app. To automate pump control, we used Arduino technology, including both the microcontroller and a programming environment for coding and designing the mobile app. To validate the system’s effectiveness, we individually measured the amount of water and chemical delivered to the mixer tank and compared it with conventional manual methods for calculating chemical quantities and preparation time. The system demonstrated consistent results, achieving high precision and accuracy in delivering the correct amount. This study advances the field of agricultural robotics by highlighting the role of collaborative platforms. Particularly, the system presents a valuable and low-cost solution for small farms and experimental research. Full article

The evaluation of open-ended questions is typically performed by human instructors using predefined criteria to uphold academic standards. However, manual grading presents challenges, including high costs, rater fatigue, and potential bias, prompting interest in automated essay scoring systems. While automated essay scoring tools can assess content, coherence, and grammar, discrepancies between human and automated scoring have raised concerns about their reliability as standalone evaluators. Large language models like ChatGPT offer new possibilities, but their consistency and fairness in feedback remain underexplored. This study investigates whether ChatGPT can provide stable and fair essay scoring—specifically, whether identical student responses receive consistent evaluations across multiple AI interactions using the same criteria. The study was conducted in two marketing courses at an engineering school in Chile, involving 40 students. Results showed that ChatGPT, when unprompted or using minimal guidance, produced volatile grades and shifting criteria. Incorporating the instructor’s rubric reduced this variability but did not eliminate it. Only after providing an example-rich rubric, a standardized output format, low temperature settings, and a normalization process based on decision tables did ChatGPT-4o demonstrate consistent and fair grading. Based on these findings, we developed a scalable algorithm that automatically generates effective grading rubrics and decision tables with minimal human input. The added value of this work lies in the development of a scalable algorithm capable of automatically generating normalized rubrics and decision tables for new questions, thereby extending the accessibility and reliability of automated assessment. Full article

Earthquakes are sudden and highly destructive events that severely disrupt infrastructure and logistics systems, making accurate and timely emergency material demand forecasting a critical challenge in disaster response. However, the scarcity of reliable data during the early stages of an earthquake limits the effectiveness of traditional forecasting methods. To address this issue, this study proposes a hybrid forecasting framework that integrates the Grey Model (GM(1,1)) with Bayesian Dynamic Linear Models (BDLMs), aiming to improve both the accuracy and adaptability of demand predictions. The approach operates in two phases: first, GM(1,1) generates preliminary forecasts using limited initial observations; second, BDLMs dynamically update these forecasts in real time as new data become available. The model is validated through a case study of the 2010 M7.1 Yushu earthquake in Qinghai Province, China. The results indicate that the hybrid method produces reliable forecasts even at the earliest stages of the disaster, with increasing accuracy as more observational data are incorporated. Our case study demonstrates that the integrated GM(1,1)-BDLM framework substantially reduces prediction errors compared to standalone GM(1,1). Using the first five days’ data to forecast fatalities and emergency material demand for days 6–10, the hybrid model achieves a 4.01% error rate—a 19.62 percentage point improvement over GM(1,1)’s 23.63% error rate. This adaptive forecasting mechanism offers robust support for evidence-based decision-making in emergency material allocation, enhancing the efficiency and responsiveness of post-disaster relief operations. Full article