Search Results (2,738)

Accurate prediction of geopolymer concrete compressive strength is vital for sustainable construction. Traditional experiments are time-consuming and costly; therefore, computer-aided systems enable rapid and accurate estimation. This study evaluates three ensemble learning algorithms (Extreme Gradient Boosting (XGB), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM)), as well as two baseline models (Support Vector Regression (SVR) and Artificial Neural Network (ANN)), for this task. To improve performance, hyperparameter tuning was conducted using Bayesian Optimization (BO). Model accuracy was measured using R², RMSE, MAE, and MAPE. The results demonstrate that the XGB model outperforms others under both default and optimized settings. In particular, the XGB-BO model achieved high accuracy, with RMSE of 0.3100 ± 0.0616 and R² of 0.9997 ± 0.0001. Furthermore, Shapley Additive Explanations (SHAP) analysis was used to interpret the decision-making of the XGB model. SHAP results revealed the most influential features for compressive strength of geopolymer concrete were, in order, coarse aggregate, curing time, and NaOH molar concentration. The graphical user interface (GUI) developed for compressive strength prediction demonstrates the practical potential of this research. It contributes to integrating the approach into construction practices. This study highlights the effectiveness of explainable machine learning in understanding complex material behaviors and emphasizes the importance of model optimization for making sustainable and accurate engineering predictions. Full article

A novel closed loop visual positioning system, termed YOLO–LaserGalvo (YLGS), is proposed for precise localization of welding torch tips in industrial welding automation. The proposed system integrates a monocular camera, an infrared laser distance sensor with a galvanometer scanner, and a customized deep learning detector based on an improved YOLOv11 model. In operation, the vision subsystem first detects the approximate image location of the torch tip using the YOLOv11-based model. Guided by this detection, the galvanometer steers the IR laser beam to that point and measures the distance to the torch tip. The distance feedback is then fused with the vision coordinates to compute the precise 3D position of the torch tip in real-time. Under complex illumination, the proposed YLGS system exhibits superior robustness compared with color-marker and ArUco baselines. Experimental evaluation shows that the system outperforms traditional color-marker and ArUco-based methods in terms of accuracy, robustness, and processing speed. This marker-free method provides high-precision torch positioning without requiring structured lighting or artificial markers. Its pedagogical implications in engineering education are also discussed. Potential future work includes extending the method to full 6-DOF pose estimation and integrating additional sensors for enhanced performance. Full article

In South Korea, sunlight rights and daylight rights are legally distinguished, yet no standardized methodology exists for their quantitative assessment. Current evaluations of sunlight rights are narrowly defined, relying on the duration of direct solar penetration at the window center during the winter solstice, while excluding reflected and diffuse light. This restrictive approach has led to confusion among both researchers and legal practitioners, as it diverges from daylighting evaluations that account for indoor brightness and energy performance. The recent enactment of regulations to secure solar access in schools has further intensified disputes between educational institutions striving to protect students’ visual comfort and developers seeking to maximize building potential. To address this gap, this study proposes an evaluation framework tailored to the Korean context. A reference classroom model representative of standard Korean schools was developed, and simulations were conducted by introducing obstructing building masses to block direct sunlight. The methodology evaluated key variables, including time of day and solar altitude, and analyzed daylighting performance and lighting-related energy consumption under obstructed conditions. The results show that blocking sunlight through south-facing windows reduces daylighting performance by 89% to 98%, leading to additional reliance on artificial lighting, with energy use increasing between 128 Wh and 768 Wh. These findings underscore the limitations of current legal interpretations based solely on sunlight duration and highlight the necessity of adopting performance-based evaluation methods. Protecting school sunlight rights through such approaches is essential to enhancing classroom visual environments and reducing energy demand. Full article

Educational data mining (EDM) plays a crucial role in developing intelligent early warning systems that enable timely interventions to improve student outcomes. This study presents a novel approach to student performance prediction by integrating metaheuristic hyperparameter optimization with explainable artificial intelligence for enhanced learning analytics. While Light Gradient Boosting Machine (LightGBM) demonstrates efficiency in educational prediction tasks, achieving optimal performance requires sophisticated hyperparameter tuning, particularly for complex educational datasets where accuracy, interpretability, and actionable insights are paramount. This research addressed these challenges by implementing and evaluating five nature-inspired metaheuristic algorithms: Fox Algorithm (FOX), Giant Trevally Optimizer (GTO), Particle Swarm Optimization (PSO), Sand Cat Swarm Optimization (SCSO), and Salp Swarm Algorithm (SSA) for automated hyperparameter optimization. Using rigorous experimental methodology with 5-fold cross-validation and 20 independent runs, we assessed predictive performance through comprehensive metrics including Coefficient of Determination (R²), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Relative Absolute Error (RAE), and Mean Error (ME). Results demonstrate that metaheuristic optimization significantly enhances educational prediction accuracy, with SCSO-LightGBM achieving superior performance with R² of 0.941. SHapley Additive exPlanations (SHAP) analysis provides crucial interpretability, identifying Attendance, Hours Studied, Previous Scores, and Parental Involvement as dominant predictive factors, offering evidence-based insights for educational stakeholders. The proposed SCSO-LightGBM framework establishes an intelligent, interpretable system that supports data-driven decision-making in educational environments, enabling proactive interventions to enhance student success. Full article

With a history spanning over two thousand years, the Beijing Road historic and cultural zone marks the origin of Guangzhou’s traditional central axis and serves as one of the earliest commercial centers in the Lingnan region, characterized by a rich historical and cultural heritage and unique Lingnan features. Through a combination of literature collection and review, field observation, and photographic documentation, the research examines the historical natural, artificial, and folk lightscapes of the Beijing Road zone, highlighting the diversity of its lightscape features from past to present. As the city developed and modern technology advanced, the representative lightscapes in the Beijing Road zone have evolved from traditional forms to modern expressions, including 3D projection, multimedia interaction, and LED lighting. These advancements breathe new life into the pedestrian street and enhance its cultural significance within the contemporary commercial environment. By comparing the characteristics and categories of historical and contemporary lightscapes, the paper reveals the transformation of historical lightscapes, the innovation in modern lightscape techniques, and the remnants of vanished lightscapes. It also proposes strategies for the restoration and preservation of historical lightscapes, the innovation and integration of contemporary lightscapes, and the development of sustainable lighting design, while it discusses the direction of work for future research. It underscores the need for further protection and optimization of lightscape resources in the Beijing Road historic and cultural zone, to enhance cultural heritage and commercial appeal, providing valuable insights for the preservation of historic zones and the development of cultural tourism in Guangzhou and the Lingnan region. Full article

Canada goldenrod (Solidago canadensis L.), a short-day plant commonly cultivated as a cut flower, depends on proper lighting management to obtain long stems and higher commercial value. Thus, this study aimed to determine the effect of modifying the light spectrum through the installation of light-emitting diodes (LEDs) and the use of colored shade nets on the production and quality of Canada goldenrod stems. The treatments used were colored shade nets and different LED lighting treatments. Production per plant and productivity per square meter were determined. Twenty stems were selected and evaluated for: stem length; inflorescence length and width; number of floral ramets per inflorescence; number of leaves; stem base diameter (mm); and fresh stem biomass (g). Canada goldenrod plants require an extension of the light period with artificial lighting to produce higher-quality stems, regardless of whether the bulbs emit red or white light. The use of nets with 50% red and white shading promoted higher production and elongation of Canada goldenrod stems, with a production that reached up to 4.2 floral stems per plant and 100.3 floral stems per square meter using the red shade net and white LED. These floral stems were of high commercial standard, with a length of up to 81.35 cm with the red shade net and red LED, and were 31 cm in diameter for the inflorescences, approximately, under black or white shade nets and white or red LEDs. More robust floral stems with greater biomass were observed using any shade net color and LED lamps. Full article

The poultry red mite (PRM) feeds on hens’ blood at night, disrupting sleep, harming welfare, and reducing productivity. Effective control may lie in dynamic Integrated Pest Management (IPM), which relies on routine monitoring and adaptation to farm conditions. This study investigated how PRM infestations affect the night-time activity of hens. Three groups of eight hens, housed in enriched cages, were monitored with night-vision cameras over a two-month period, both before and after artificial PRM introduction, while PRM levels were simultaneously recorded. To quantify changes in behaviour, we developed an activity-monitoring algorithm that extracts both group-level and individual night-time activity patterns from video recordings. Group activity between 18:00 and 03:00 was analyzed hourly, and individual activity between 21:00 and 00:00 was classified into four activity categories. Before infestation, group activity declined after 19:00, remained low from 20:00 to 01:00, and peaked just before the end of the dark period. After infestation, activity remained elevated with no anticipatory activity peak towards the end of the dark period. Individual data showed an increase in time spent in the most active activity category from 24% to 67% after infestation. The rise in calculated activity was supported by a nearly 23-fold increase in annotated PRM-related behaviours, specifically head shaking and head scratching. These findings suggest that PRM mostly disrupted sleep from two hours after lights-off to two hours before lights-on and may have acted as a chronic stressor. Automated video-based monitoring could strengthen dynamic IPM in commercial systems. Full article

In this study, nanostructured ferberites (FeWO₄) were synthesized via hydrothermal routes in an acidic medium. It was then investigated as an efficient photocatalyst for degrading organic dye molecules, with methylene blue (MB) as a model pollutant. The formation mechanism of ferberite revealed that the physical form of the precursor, FeSO₄·7H₂O, acts as a decisive factor in morphological evolution. Depending on whether it is in a solid or dilute solution form, two distinct nanostructures are produced: nanoplatelets and self-organized microspheres. Both structures are composed of stoichiometric FeWO₄ (Fe: 49%, W: 51%) in a single monoclinic phase (space group P2/c:1) with high purity and crystallinity. The p-type semiconductor behavior was confirmed using Mott–Schottky model and the optical analysis, resulting in small band gap energies (≈1.7 eV) favoring visible absorption light. Photocatalytic tests under simulated solar irradiation revealed rapid and efficient degradation in less than 10 min under near-industrial conditions (pH 5). This was achieved using only a ferberite catalyst and a low concentration of H₂O₂ (4 mM) without additives, dopants, or artificial light sources. Advanced studies based on photocurrent measurements, trapping and stability tests were carried out to identify the main reactive species involved in the photocatalytic process and better understanding of photodegradation mechanisms. These results demonstrate the potential of nanostructured FeWO₄ as a sustainable and effective photocatalyst for water purification applications. Full article

Artificial light at night (ALAN) is now considered as a driver of evolution, possibly harmful to biodiversity, which constitutes a threat to the terrestrial and marine environment, and as such falls under Sustainable Development Goals (SDGs) 14 and 15. One way of mitigating its impact on the environment is to select an environment-friendly light spectrum, which is made more easily with current LED technologies. In this paper, we propose to adapt the spectrum of the lamps to that of the immediate environment. It makes it possible not to disturb the light environment of animals and plants at night and during the twilight period, at least from a spectral point of view, while ensuring the usual functions of lighting for humans. Apart from its own merit, the proposed concept may also contribute to SDG 13 by saving energy compared to current approaches based on long wavelengths light. The proposed idea may be implemented in various ways and deserves to be discussed in the lighting community and tested in real settings. Full article

Typical fertilizer applicators are often restricted in performance due to non-uniformity in distribution, required labor and time intensiveness, high discharge rate, chemical input wastage, and fostering weed proliferation. To address this gap in production agriculture, an automated variable-rate fertilizer applicator was developed for the cotton crop that is based on deep learning-initiated electronic control unit (ECU). The applicator comprises (a) plant recognition unit (PRU) to capture and predict presence (or absence) of cotton plants using the YOLOv7 recognition model deployed on-board Raspberry Pi microprocessor (Wale, UK), and relay decision to a microcontroller; (b) an ECU to control stepper motor of fertilizer metering unit as per received cotton-detection signal from the PRU; and (c) fertilizer metering unit that delivers precisely metered granular fertilizer to the targeted cotton plant when corresponding stepper motor is triggered by the microcontroller. The trials were conducted in the laboratory on a custom testbed using artificial cotton plants, with the camera positioned 0.21 m ahead of the discharge tube and 16 cm above the plants. The system was evaluated at forward speeds ranging from 0.2 to 1.0 km/h under lighting levels of 3000, 5000, and 7000 lux to simulate varying illumination conditions in the field. Precision, recall, F1-score, and mAP of the plant recognition model were determined as 1.00 at 0.669 confidence, 0.97 at 0.000 confidence, 0.87 at 0.151 confidence, and 0.906 at 0.5 confidence, respectively. The mean absolute percent error (MAPE) of 6.15% and 9.1%, and mean absolute deviation (MAD) of 0.81 g/plant and 1.20 g/plant, on application of urea and Diammonium Phosphate (DAP), were observed, respectively. The statistical analysis showed no significant effect of the forward speed of the conveying system on fertilizer application rate (p > 0.05), thereby offering a uniform application throughout, independent of the forward speed. The developed fertilizer applicator enhances precision in site-specific applications, minimizes fertilizer wastage, and reduces labor requirements. Eventually, this fertilizer applicator placed the fertilizer near targeted plants as per the recommended dosage. Full article

Management of smart greenhouses represents a transformative advancement in precision agriculture, enabling sustainable intensification of food production through the integration of multi-sensor networks, intelligent control, and sophisticated data filtering techniques. Unlike conventional greenhouses that rely on manual monitoring, smart greenhouses combine environmental sensors, Internet of Things (IoT) platforms, and artificial intelligence (AI)-driven decision making to optimize microclimates, improve yields, and enhance resource efficiency. This review systematically investigates three key technological pillars, multi-sensor monitoring, intelligent control, and data filtering techniques, for smart greenhouse environment management. A structured literature screening of 114 peer-reviewed studies was conducted across major databases to ensure methodological rigor. The analysis compared sensor technologies such as temperature, humidity, carbon dioxide (CO₂), light, and energy to evaluate the control strategies such as IoT-based automation, fuzzy logic, model predictive control, and reinforcement learning, along with filtering methods like time- and frequency-domain, Kalman, AI-based, and hybrid models. Major findings revealed that multi-sensor integration enhanced precision and resilience but faced changes in calibration and interoperability. Intelligent control improved energy and water efficiency yet required robust datasets and computational resources. Advanced filtering strengthens data integrity but raises concerns of scalability and computational cost. The distinct contribution of this review was an integrated synthesis by linking technical performance to implementation feasibility, highlighting pathways towards affordable, scalable, and resilient smart greenhouse systems. Full article

Artificial intelligence-based image processing is critical for sensor fusion and image transformation in mobility systems. Advanced driver assistance functions such as forward monitoring and digital side mirrors are essential for driving safety. Degradation due to raindrops, fog, and high-dynamic range (HDR) imbalance caused by lighting changes impairs visibility and reduces object recognition and distance estimation accuracy. This paper proposes a diffusion framework to enhance visibility under multi-degradation conditions. The denoising diffusion probabilistic model (DDPM) offers more stable training and high-resolution restoration than the generative adversarial networks. The DDPM relies on large-scale paired datasets, which are difficult to obtain in raindrop scenarios. This framework applies the Palette diffusion model, comprising data augmentation and raindrop-removal modules. The data augmentation module generates raindrop image masks and learns inpainting-based raindrop synthesis. Synthetic masks simulate raindrop patterns and HDR imbalance scenarios. The raindrop-removal module reconfigures the Palette architecture for image-to-image translation, incorporating the augmented synthetic dataset for raindrop removal learning. Loss functions and normalization strategies improve restoration stability and removal performance. During inference, the framework operates with a single conditional input, and an efficient sampling strategy is introduced to significantly accelerate the process. In post-processing, tone adjustment and chroma compensation enhance visual consistency. The proposed method preserves fine structural details and outperforms existing approaches in visual quality, improving the robustness of vision systems under adverse conditions. Full article

Cooperative Intelligent Transport Systems (C-ITS) have emerged as a key enabler of more efficient, safer, and environmentally sustainable road traffic by allowing vehicles and infrastructure to exchange information and coordinate behavior. To evaluate their benefits, impact assessment studies are essential. However, most existing studies focus on individual C-ITS services in isolation, overlooking how combined deployments influence outcomes. This study addresses this gap by presenting the first systematic evaluation of individual and joint deployments of Cooperative Adaptive Cruise Control (CACC) and Green Light Optimal Speed Advisory (GLOSA) under diverse conditions. A dual-model simulation framework is applied, combining controlled artificial networks with calibrated real-world corridors in Upper Austria. This allows both statistical testing and validation of plausibility in real-world contexts. Key performance indicators include travel time and CO₂ emissions, evaluated across varying lane configurations, numbers of traffic lights, demand levels, and equipment rates. The results demonstrate that C-ITS effectiveness is strongly context-dependent: while CACC generally provides larger efficiency gains, GLOSA yields consistent emission reductions, and the combined deployment offers conditional synergies but may also diminish benefits at high demand. The study contributes a guideline for selecting service configurations based on site conditions, thereby providing practical recommendations for future C-ITS rollouts. Full article

Artificial intelligence (AI), when integrated with photocatalysis, has demonstrated high predictive accuracy in optimizing photocatalytic processes for wastewater treatment using a variety of catalysts such as TiO₂, ZnO, CdS, Zr, WO₂, and CeO₂. The progress of research in this area is greatly enhanced by advancements in data science and AI, which enable rapid analysis of large datasets in materials chemistry. This article presents a comprehensive review and critical assessment of AI-based supervised learning models, including support vector machines (SVMs), artificial neural networks (ANNs), and tree-based algorithms. Their predictive capabilities have been evaluated using statistical metrics such as the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE), with numerous investigations documenting R² values greater than 0.95 and RMSE values as low as 0.02 in forecasting pollutant degradation. To enhance model interpretability, Shapley Additive Explanations (SHAP) have been employed to prioritize the relative significance of input variables, illustrating, for example, that pH and light intensity frequently exert the most substantial influence on photocatalytic performance. These AI frameworks not only attain dependable predictions of degradation efficiency for dyes, pharmaceuticals, and heavy metals, but also contribute to economically viable optimization strategies and the identification of novel photocatalysts. Overall, this review provides evidence-based guidance for researchers and practitioners seeking to advance wastewater treatment technologies by integrating supervised machine learning with photocatalysis. Full article

Aflatoxin (AF) contamination in pistachios remains a critical food safety and trade challenge, given the potent carcinogenicity of AF-B₁ and the nut’s high susceptibility to Aspergillus infection throughout production and storage. Traditional decontamination methods such as roasting, irradiation, ozonation, and acid/alkaline treatments can reduce AF levels but often degrade sensory and nutritional quality, implying the need for more sustainable approaches. In recent years, innovative nonthermal interventions, including pulsed light, cold plasma, nanomaterial-based adsorbents, and bioactive coatings, have demonstrated significant potential to decrease fungal growth and AF accumulation while preserving product quality. Biosensing technologies such as electrochemical immunosensors, aptamer-based systems, and optical or imaging tools are advancing rapid, portable, and sensitive detection capabilities. Combining these experimental strategies with artificial intelligence (AI) and machine learning (ML) models can increasingly be applied to integrate spectral, sensor, and imaging data for predicting fungal development and AF risk in real time. This review brings together progress in nonthermal reduction strategies, biosensing innovations, and data-driven approaches, presenting a comprehensive perspective on emerging tools that could transform pistachio safety management and strengthen compliance with global regulatory standards. Full article