This study investigates unsupervised machine learning (ML) for anomaly detection in solar photovoltaic (PV) power generation data from 2019 to 2023. An unsupervised approach is selected to overcome the absence of pre-labeled fault data, enabling the autonomous identification of operational patterns. Following data preparation, K-means clustering (k=3) identifies distinct operational patterns, specifically characterizing regimes such as optimal performance (Cluster 2) and low energy output attributed to adverse weather conditions (Cluster 1). These clusters are subsequently visualized using principal component analysis (PCA) to validate their distinct separation. An isolation forest model is then employed for anomaly detection, identifying 17 significant deviations. These anomalies occur most frequently in 2020, coinciding with the COVID-19 pandemic period. Many fall outside the typical energy range of 2.0–3.2 kWh/day and are associated with non-ideal weather conditions. This finding demonstrates that unsupervised ML provides a scalable framework for monitoring PV system health, enhancing reliability, and supporting preventive strategies.
Although natural light is the standard reference for color rendering evaluation, limited efforts have been made to develop a lighting system that achieves high color rendering while replicating the spectral characteristics of natural light. This paper proposes a method for developing LED lighting that mimics the spectral ratio characteristics of natural light and achieves high color rendering. Based on the analysis of measured natural light spectra, spectral ratio characteristics are derived according to changes in color temperature. Simulations are conducted by adding light sources with specific peak wavelengths (405 nm, 630 nm) to commercial LED lighting. Based on the simulation results, a development approach for natural light LED lighting with high color rendering is proposed. Experimental results demonstrate that a color rendering index (CRI) of 90 or higher (including R9 and R12 ≥ 80) can be achieved for lighting systems with baseline CRI values of 80, 85, and 90.
Illegal nighttime fishing remains difficult to monitor because vessels often deactivate the Automatic Identification System (AIS). This study presents a supervised deep neural network (DNN) approach for detecting nighttime fishing vessel lights using the Day/Night Band (DNB) data from the Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi NPP and NOAA-20 satellites. The model integrates DNB radiance features with lunar illumination information to reduce false detections caused by moonlight. The dataset comprises summer-season observations (2020–2021) in waters near Jeju Island, South Korea, with labels derived from temporally matched AIS records. The proposed DNN is evaluated using a stratified train–test split and compared with conventional machine-learning baselines. Experimental results demonstrate improved performance, achieving an F1 score above 0.90, indicating the robust detection capability under low-light maritime conditions. These findings highlight the potential of VIIRS DNB data combined with deep learning for large-scale nighttime maritime monitoring beyond AIS-dependent systems.
This research aims to enhance the physical-layer security (PLS) of multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) wireless communication systems. The proposed method integrates Rivest–Shamir–Adleman (RSA)-based subcarrier index scrambling with secure hash algorithm (SHA)-256 hashing to ensure both confidentiality and integrity without altering the transmitted waveform. The scheme is implemented on a 2×2 Universal Software Radio Peripheral (USRP)-based MIMO-OFDM software-defined radio (SDR) testbed and evaluated using symbol distribution analysis, bit-error-rate (BER) performance, and security assessment. Experimental results indicate that RSA-based scrambling substantially increases symbol randomness while preserving Shannon-consistent BER performance across multiple modulation orders, with minimal penalty in signal-to-noise ratio (SNR). Additionally, security analysis demonstrates that the combination of RSA-2048 and SHA-256 is resistant to Wiener’s attack and the common modulus attack, thereby supporting efficient and secure real-time MIMO-OFDM communication.
This study aims to analyze the influence of inter-electrode spacing on grounding resistance in high-voltage transmission networks. A simplified analytical model is applied to a case study on the Djiri-Ngo 220 kV line (Republic of the Congo), considering two representative soil types: clayey and siliceous sand. The grounding resistance is calculated by varying the number of electrodes and their spacing. The results show that increasing electrode spacing reduces grounding resistance. In certain configurations, the improvement exceeding 50 % when the spacing is increased from 5 m to 25 m. A saturation threshold is identified, beyond which further increases in spacing yields diminishing returns. Electrode spacing proves to be a key design factor, sometimes more influential than the number of electrodes. The proposed parametric geometric analysis offers a practical and cost-effective strategy for grounding system design, emphasizing the importance of adapting configurations to local geotechnical conditions.
Fiber-reinforced polymer (FRP) bars have emerged as a promising alternative to conventional steel reinforcement for improving the durability of reinforced concrete (RC) members in corrosive environments. Despite increasing experimental research, analytical models capable of capturing the pure torsional response of FRP bar-reinforced concrete beams remain scarce. This study presents a modified softened membrane model for torsion (SMMT) for solid FRP-RC beams. The proposed formulation incorporates an FRP-compatible strain-coupling relationship through a modified Hsu/Zhu approach to account for poisson’s effect. The model is validated against sixteen rectangular FRP-RC beam tests reported in the literature. Predicted cracking torque, ultimate torque, torque-twist response, and selected stirrup strain responses show good agreement with experimental results. A parametric study is further conducted to quantify the influences of concrete strength, FRP elastic modulus, and longitudinal and transverse FRP reinforcement ratios. The proposed model provides a reliable analytical framework for evaluating the torsional behavior of FRP-RC beams.
This study aims to develop metakaolin-based geopolymers reinforced with sugarcane bagasse fiber (BF) and to evaluate the effect of BF treatment on the composite's performance. The BF is pretreated with hot water and sodium hydroxide before being incorporated into the geopolymer matrix. Metakaolin-based geopolymer specimens containing 0%, 3%, 4%, and 5% BF by weight are prepared, and their mechanical properties and water absorption are analyzed. Scanning electron microscopy and Fourier transform infrared spectroscopy analyses reveal that the combined hot-water-alkali treatment significantly modifies the fiber surface. The treatment removes impurities and increases surface roughness, thereby enhancing fiber–matrix bonding. As a result, this treatment improves compressive and splitting tensile strength (STS) while reducing water absorption compared to untreated BF. Furthermore, machine learning algorithms, including random forest, AdaBoost, and XGBoost, are applied to predict STS. Among the three models, XGBoost demonstrates the highest predictive accuracy (R^² = 0.95, MAE = 0.28), indicating reliable predictions of mechanical strength.
This study investigates the effects of different lateral load-resisting systems on engineering demand parameters (EDPs) and evaluates the suitability of spectral acceleration (Sa) as an intensity measure for predicting their seismic response. Eight-story reinforced concrete buildings with four configurations—fixed-base moment-resisting frame, fixed-base dual system with shear walls, base-isolated moment-resisting frame, and base-isolated dual system with shear walls—were analyzed. The seismic responses are obtained through nonlinear time-history analyses using 11 ground motion records scaled to match the site conditions. Four key response parameters are examined: maximum lateral displacement, interstory drift, floor acceleration, and base shear. Overall, the base-isolated dual system exhibited the best performance across all response parameters. In addition, Sa can be reasonably used to estimate floor acceleration in frame structures. However, the use of Sa to estimate floor acceleration in dual systems with shear walls tends to underestimate the actual response.
As Taiwan faces the challenge of reducing per capita carbon emissions from 12 tons per year—twice the global average—to achieve the “net zero by 2050” goal, understanding the factors influencing the adoption of sustainable transportation becomes crucial. This study examines how sustainable value and economic value affect TPASS usage intention, using an integrated model based on the value-attitude-behavior theory and the theory of reasoned action. The model investigates how perceived economic value, perceived sustainable value, along with attitude and subjective norms, shape consumers’ intentions to use TPASS commuter passes. Data are collected through online surveys, yielding 302 valid responses, and analyzed using structural equation modeling. Results show that both sustainable and economic values significantly influence TPASS attitude, with economic value having a stronger effect. Furthermore, attitude and subjective norms both positively affect usage intention, with subjective norms demonstrating a notably stronger impact, providing insights for sustainable transportation policies.
Undershot water wheel turbines are suitable for operation in low-elevation regions and locations with very low water head. Turbines with curved blade configurations are commonly implemented to optimize efficiency. This research examines how variations in weir height influence the performance of undershot turbines when operating under limited water flow conditions. A turbine with six blades is tested experimentally and numerically using seven weir heights ranging from 0.02 m to 0.14 m. The study used both experimental and computational fluid dynamics approaches, employing the dynamic mesh model. The results indicate that applying a curved weir as a passive flow-control device can significantly enhance turbine efficiency. At a weir height of 0.10 m, the maximum efficiency reached 80.83% based on the experimental approach and 84.69% based on the computational approach. These findings demonstrate the potential of weir-assisted undershot turbines for energy harvesting in shallow rivers under low-flow conditions.
An irrigation system stands as one of the most efficient real systems of sustainable water and farming fields. This work aims to enhances the proportional-integral-derivative (PID) controller by using particle swarm optimisation (PSO), which relies on the internet of things (IoT) for a smart irrigation system. The system employs a PID controller to dynamically adjust water flow by integrating environmental data, including humidity, soil moisture, and temperature, gathered by IoT sensors. PSO is utilised to optimize the PID parameters and overcome the limitations of traditional PID tuning. Furthermore, the proposed work improved stability, reduced overshoot, and provided faster response times. The experimental results indicated significant gains in crop health and water use efficiency. The moisture stabilizes and maintains the target of 60% with the optimized PID parameters in the case study. The smart system assisted in managing water resources sustainably by providing a scalable and energy-efficient precision agriculture solution.
To improve the accuracy of remaining useful life (RUL) prediction for milling tools, this study proposes an enhanced PSO-MultiAM-BiLSTM model integrating particle swarm optimization (PSO), multi-head attention mechanism (MultiAM), and bidirectional long short-term memory (BiLSTM). The model captures key information in input sequences, alleviating early feature attenuation in BiLSTM from “chain propagation.” A logarithmic decreasing strategy adjusts PSO inertia weights, balancing global and local searches while optimizing BiLSTM parameters. Validated on the PHM2010 dataset, the model attains an average coefficient of determination of 0.97, with average root-mean-square error and mean absolute error of 0.062 and 0.045, improving prediction accuracy by 9.64% and 4.06% over MultiAM-BiLSTM and PSO-AM-BiLSTM, respectively. Such a result attests to the effective extraction of degradation features of tools and provides a valuable reference for predicting the RUL of milling tools.
This study aims to develop a material from waste low-density polyethylene (LDPE) and high-density polyethylene (HDPE) into a medium-density board and assess its mechanical and physical properties. The development starts with degreasing the upcycled plastic sheets, stacking using premixed polyester resin as an adhesive, pressing, and laminating. The specimens are sent to the Department of Science and Technology Industrial Technology Development Institute (DOST-ITDI) standards and testing division to determine the material’s mechanical and physical properties. The findings reveal that the medium-density board successfully combines LDPE and HDPE waste, achieving tensile, flexural, and compressive strengths of 12.1 MPa, 24.2 MPa, and 14.5 MPa, respectively. The board is suitable for shaded outdoor use but not for continuous immersion as it shows a heat deflection temperature of 57.8 ℃ and 1.27% water absorption after 24 hours. Therefore, it is a potential substitute for furniture, home decor, and light construction materials.
Construction waste is a significant contributor to global solid waste, underscoring the need for effective sustainable management strategies. This study aims to assess the quality and environmental impact of paving blocks manufactured from two different sizes of recycled aggregates. Two categories, CA1 (12.5–4.75 mm) and CA2 (37.5–4.75 mm), were used as constituent materials. The paving blocks were assessed based on compressive strength, water absorption, and wear resistance. Experimental results indicate that paving blocks incorporating CA2 recycled aggregates performed better than those with CA1. The tested paving blocks meet grade D standards for garden paving (CA1) and grade C standards for pedestrian pathways (CA2). Additionally, utilizing recycled aggregates from concrete waste enables 48.1% rubble recycling and reduces carbon dioxide emissions by 64.7%, thereby contributing to sustainable waste management.
An effective Feeding Management System (FMS) is crucial in shrimp farming, as both overfeeding and underfeeding can adversely affect shrimp growth. To ensure optimal nutrition, an accurate FMS must account for factors such as shrimp size, weight, age, and leftover feed. This study presents a method for detecting leftover shrimp feed using custom-designed lift nets equipped with paired ultrasonic sensors. Two critical aspects are examined: the optimal timing for measurement and the ideal placement of the transmitter. Results show that measurements should be taken within 10 minutes of feed immersion to avoid feed disintegration. Additionally, placing the transmitter on the outer side of the lift net improves measurement accuracy. Ultrasonic echoes are analyzed to classify leftover feed using the k-Nearest Neighbors algorithm. Root Mean Square voltage-based classification effectively groups leftover feed into five classes, highlighting its potential to improve aquaculture feed management.
This study aims to develop an analytical model for evaluating the load-carrying capacity of rectangular fiber-reinforced polymer (FRP) reinforced concrete columns under eccentric loading. In the proposed model, the contribution of FRP bars in compression is considered, with their compressive strength estimated as a fraction of tensile strength. Meanwhile, the effects of confinement, tension stiffening, and second-order effects are conservatively neglected. Two main failure modes, namely concrete crushing and FRP rupture, are distinguished by the balanced failure condition. This model applies strain compatibility with the plane section and constitutive laws to derive stress-strain distributions across the cross-section. Then, the model is validated against 91 experimental results covering diverse sections, strengths, and eccentricities (e/h = 0.1-1.0), showing high accuracy (mean: 0.932; RMSE: 0.154; COV: 22.9%; SD: 0.145; r: 0.84) and outperforming ACI CODE-440.11. Analysis results also show that compressive FRP reinforcement contributed between 0.94% and 22.3% to the column strength.
With the rapid growth of the global cruise tourism industry and its increasing environmental impact, there is an urgent need to address sustainability challenges in line with the SDGs, especially in Taiwan. Despite the growing research on environmental education, there is a lack of a theoretical framework from the perspective of the stimulus-organism-response (S-O-R) paradigm that examines the relationships between external stimuli, internal organisms, and individual responses to environmental education in the context of cruise tourism. The proposed framework includes attention to environmental issues and awareness of consequences as external stimuli. These stimuli influence affective and cognitive processes, which are internal states of the organism. In turn, the affective and cognitive states drive pro-environmental behavioral responses. Additionally, the proposed framework incorporates two potential moderating factors: cultural differences and environmental education with emerging technologies. Implications for environmental education in cruise tourism are provided.
This paper aims to optimize a small vertical-axis wind turbine (VAWT) by analyzing chord length, hub radius, and circular angle, and establishing a relationship between design parameters and performance. The approach involves evaluating five airfoils and identifying the best airfoil using QBlade, based on comparisons of the power coefficient (CP), tip speed ratio (TSR), and the power output (P). Mathematical relationships are developed through extrapolation using polynomial, logarithmic, and modified Avrami equations. The result shows that the 'S1046 17%' is the best-performing airfoil among the five. The optimum chord length to hub radius ratio yields the highest power output, and the impact of circular angle on performance is negligible. The Avrami equation shows better fitness to the original data than the polynomial equation. The Troposkien variant shows a higher CP over a wide range of TSR, while the straight blade produces higher power output across varying wind speed (V).
As artificial intelligence (AI) technologies continue to spread into human life, developers must ensure benefits while minimizing the risk of adverse impacts. This study aims to evaluate risks in real-world AI applications using the AI Incident Database. It employs Failure Mode and Effect Analysis and the National Institute of Standards and Technology AI Risk Management Framework to identify failures, their causes and effects, and assess how current systems address them. A total of 100 incident reports were analyzed. The findings indicate frequent failures in autonomous systems and biased predictions. Seven cases were classified in the highest risk categories, including those involving physical harm and loss of life. Over 80% failures originated from algorithmic flaws or poor data quality. The method employed successfully evaluates the risks in current AI applications, revealing critical gaps in risk management and emphasizing the urgent need for targeted safeguards and proactive mitigation strategies.
Delayed identification of crop diseases, which significantly impact agricultural yields, remains a critical challenge. Crop diseases are a major factor contributing to reducing productivity. Since leaves are the mirrors of crop health, by investigating the leaves, a prediction of crop health can be made. This study aims to predict crop disease in the vegetative growth phase with greater efficiency. The two most prominent features, color and texture of the leaves, are extracted with different techniques, followed by fuzzification of these features. Two machine learning models, the bootstrap model and the multi-class support vector machine (MSVM), are employed for disease prediction. The findings show that for multi-class disease prediction, the bootstrap model with histogram and modified co-occurrence matrix features obtains a superior average accuracy of 98.07%, while the MSVM with fuzzy features delivers an average accuracy of 80.11% in the potato crop with early blight disease.
