ABSTRACT Rapid urban development and climate change reveal limits of traditional construction, highlighting a need to integrate adaptive and innovative technologies in architecture. A systematic review of sustainable projects and technologies connects architectural strategies with remote sensing data. Case studies, including Malakoff, Tianbao, Roskilde, and Macau, assess spatial, structural, and functional flexibility to evaluate adaptive, energy-efficient solutions and long-term environmental performance. Key principles of adaptive design are highlighted, encompassing genetic algorithms, parametric methods, machine learning, intelligent and bio-inspired systems, AI-based technologies such as micro-GAs (exemplified by a building façade in Boston, U.S.A.), evolutionary computation, artificial neural networks, generative design, ML algorithms, digital twins for urban forecasting, a bio-inspired ventilation system at the Eastgate Centre in Harare, Zimbabwe, and energy-efficient façade and spatial systems at the Vancouver Convention Centre West in Canada, while factors limiting widespread application of these intelligent technologies are identified. Achieving sustainable architecture goals requires a comprehensive approach integrating intelligent and adaptive systems tailored to specific conditions, thereby creating harmonious buildings that meet societal demands and support environmental sustainability.

Robust prediction of Listeria monocytogenes, Listeria innocua and aerobic spoilage bacteria growth in food systems using Multilayer Perceptron Artificial Neural Networks.

Geometry parameters estimation in Monte Carlo simulation using machine learning.

Advancing bioprocess monitoring: data fusion and ANN-based prediction of arginine concentration in monoclonal antibody-producing CHO cell cultures.

ABSTRACT The rapid digital transformation in the fashion industry has increased the demand for graduates with industry-relevant digital fashion skills. This study aims to develop a data-driven Digital Fashion Skills Framework for Fashion Education, using Principal Component Analysis (PCA), Artificial Neural Networks (ANN), and cluster analysis. When PCA was applied, it was evident that Digital Design Skills, CAD Skills, and VR Proficiency were the most influential, with the first two components accounting for 30.2% of the total variance. Furthermore, ANN also demonstrated its relevance in predicting digital skills readiness. Then, cluster analysis separated students into three learner profiles (low, medium, and high skill groups), indicating different levels of readiness for the digital fashion workflow. These findings provide evidence that digital fashion skills development is not homogeneous and requires different learning pathways. The proposed framework offers practical guidance for curriculum development, digital learning design, and workforce preparation in contemporary fashion education.

Hybrid and explainable machine learning for predicting water penetration depth in seawater based self-compacting concrete

The increasing complexity of urban traffic, driven by rapid urbanization and unpredictable vehicular behavior, poses a significant challenge to traditional traffic control systems. (Zheng et al., 2014; Kwon et al., 2004) These conventional systems often lack adaptability, memory-awareness, and the ability to handle uncertainty in real time. (Englund et al., 2021) To address these limitations, this study proposes a novel hybrid intelligent traffic control framework that integrates Caputo fractional-order modeling, Fermatean Neutrosophic Soft Sets (FNSS), and Artificial Neural Networks (ANNs). The Caputo system models traffic dynamics with memory, enabling accurate forecasting of congestion patterns by considering historical data. (Podlubny, 1998; Diethelm, 2010; Li & Zeng, 2015; Machado et al., 2018) FNSS logic handles real-time uncertainty, vagueness, and sensor ambiguity, while the neural network layer learns and optimizes signal control decisions through historical and real-time data. (Ye, 2020; Broumi & Smarandache, 2021; Çelik et al., 2022)<br /> <br /> Simulation and implementation were conducted using the SUMO traffic simulator and Python-based TraCI API, enhanced by reinforcement learning modules for adaptive control. (Krajzewicz et al., 2012; Behrisch et al., 2011; Mannion et al., 2016; Wei et al., 2019; van der Pol & Oliehoek, 2016) The results showed that traffic got a bit better — there was around 6.27% less congestion, waiting times improved by 4.81%, and cars passed through intersections about 7.2% faster. Also, there was a clear drop in CO₂ emissions and the time people had to wait to cross the street. (Sun et al., 2017; Barth & Boriboonsomsin, 2009)<br /> <br /> This study proves that mixing memory-based models with smart AI that can deal with uncertain data works well. (Machado et al., 2018; Englund et al., 2021) But it's not just about numbers — the system we built could help connect with smart city tools, live traffic screens, and even future self-driving car systems. (Zheng et al., 2014; Englund et al., 2021; Zhang et al., 2018) All of this together can lead to safer roads, less pollution, and smoother traffic in busy cities. (Sun et al., 2017; Barth & Boriboonsomsin, 2009)

High-energy particle accelerators and their associated experiments contribute significantly to our understanding of the nature of matter. In this context, calorimeters are key components employed to measure the energy of the outgoing particles produced in the collisions. For this, a high-density structure of sensors organized around the beam axis and comprising several superimposed detection layers is used. Calorimeter information is essential for particle characterization and triggering. A high-energy sampling calorimeter is split into electromagnetic and hadronic sections and constructed using an alternate structure of sensitive and absorber materials. One possible configuration for electromagnetic calorimeters is to use liquid Argon (LAr) and lead (Pb) for sensitive and absorber materials, respectively. The high-density granular structure of sensor cells, combined with high energy values of the particles to collide, can produce parasitic effects that distort the signal of interest in each cell. One of these effects is crosstalk (XT), a spurious signal induced from neighboring sensor cells. Consequently, particle characterization is affected, introducing errors in energy and particle time-of-flight estimation. This work proposes a machine-learning method for crosstalk mitigation in an ATLAS-like LAr+Pb electromagnetic calorimeter. For this, a study based on a framework to simulate particle interaction on an LAr calorimeter that accounts for the crosstalk effect as observed experimentally was proposed. The results show that a supervised learning neural network model for time regression reduces the estimation error by 31 times for cells with the highest energy and 182 times for cells with low energy. For energy estimation, the neural estimator reduces the error by 1.09 times at high-energy cells and 12 times at low-energy cells. The results also indicate that the proposed model is capable of reducing the crosstalk distortion in shower-shape variables, which are traditionally used for particle identification in calorimetry. The implementation of such a method at LHC experiments could provide a very interesting improvement to identify particles not associated with a collision of interest (pileup) based on an enhanced time of flight measurement. • A simulation modeling for crosstalk in an ATLAS-like calorimeter is proposed. • Crosstalk signal distortion is significantly reduced with a machine learning solution. • The proposed method reduces the time-of-flight estimation error by up to 182 times. • Energy estimation error is reduced by up to 12 times for low-energy cells. • The method significantly reduces the shower-shapes distortion caused by crosstalk.

This study provides an in-depth evaluation of newly developed oilseed and confectionery sunflower hybrids through the characterization of seed morphology, physical properties, oil and moisture content, and mechanical strength. The seeds were cultivated in Serbia and Argentina over two seasons, and cold pressed under controlled conditions to evaluate oil yield, pressing capacity, and processing behavior. Significant differences were observed among hybrids and cultivation locations in terms of seed traits and oil content. Oilseed hybrids exhibited substantially higher oil extraction efficiency (41.63-75.61%) and pressing capacities (up to 30 kg h-1) compared to confectionery hybrids (20.10-48.40% yield; ~15 kg h-1 capacity), aligning with their higher seed oil content. An artificial neural network (ANN) model was developed using measured seed morphological, compositional and physical characteristics, seed and press cake moisture and oil content, and seed mass as input variables (18 inputs) to predict oil and seed yields, oil and seed flow rates, oil outlet temperature, pressing time, obtained oil mass, and press cake mass (eight outputs). The optimal MLP 18-11-8 model demonstrated excellent predictive ability, with R2 values of 0.970, 0.898, and 0.924 for training, testing, and validation datasets, respectively. Sensitivity analysis highlighted seed oil content and input mass as the most influential factors for oil yield and capacity, while residual oil in press cake negatively affected oil recovery. This integrative approach, combining comprehensive physical and mechanical seed evaluation with data-driven artificial neural network modeling, provides a novel framework for predicting and optimizing cold-pressing performance in sunflower hybrids. The findings offer valuable insights for breeding programs, industrial processing, and machine design tailored to specific hybrid profiles. © 2026 Society of Chemical Industry.

Stimulus reliability but not boundary distance manipulations violate the folded-X pattern of confidence.

Interpretable artificial neural network reveals region-specific controls of chlorophyll-a in the Yellow River Estuary and adjacent sea.

Calibration-free and drift-robust AlGaN/GaN HEMT sensor arrays for intelligent pH detection.

Computational and machine learning approach for nanoparticles-enhanced bio-heat transport with coupled effects of interparticle spacing and particles radius.

Finite element simulation-driven artificial neural network modeling for performance prediction in the split-sleeve cold expansion process of aluminum 2024-T3

Ordinal evolutionary artificial neural networks for predicting diabetic nephropathy progression

Microplastic contamination in locally and industrially produced organic fertilizers: Implications for sustainable agriculture and risk mitigation.

Deep learning and hyperspectral imaging for non-destructive amino acid detection in live carp fillets.

Mix design optimisation for concrete with alternative binders and aggregates incorporating environmental, mechanical and durability performance

Prediction models of polycyclic aromatic hydrocarbons in urban road dust via magnetic properties, particle size, and urban environmental features.

Efficient recovery of phenolic compounds is critical for valorizing Crataegus songarica K. Koch for food and nutraceutical applications. Conventional maceration (CM) is often limited by low extraction efficiency and prolonged processing time, whereas energy-assisted techniques may enhance extraction performance but still lack comprehensive data-driven assessment. In this study, conventional maceration, ultrasound-assisted extraction (UAE), microwave-assisted extraction (MAE), and infrared-assisted extraction (IRAE) were comparatively evaluated using total identified phenolics and individual flavonoids as response variables. Under the investigated extraction conditions, MAE achieved the highest phenolic recovery (158.82 ± 4.37mg 100 g- 1) following 0.5min of microwave irradiation combined with a subsequent reflux-assisted extraction stage, compared with 70.15 ± 2.14mg 100 g- 1 obtained by CM after 60min, while IRAE and UAE yielded 129.77 ± 3.18 and 83.32 ± 2.11mg 100 g- 1, respectively. Chemometric analyses, including principal component analysis and hierarchical cluster analysis, clearly differentiated extraction modes, primarily according to temperature, solvent concentration, and dry-matter content. Predictive modeling was performed using Ridge regression, random forest, support vector machine, XGBoost, and multilayer-perceptron artificial neural network models under nested cross-validation conditions. Among the tested approaches, XGBoost provided the strongest predictive performance (cross-validated R2 ≈ 0.76, RMSE ≈ 27mg 100 g- 1, MeanAE ≈ 21mg 100 g- 1) and identified temperature and dry matter as the dominant variables controlling phenolic recovery. The results demonstrate that integrating controlled extraction experiments with interpretable machine learning approaches provides a scalable and potentially resource-efficient framework for optimizing phenolic extraction from hawthorn and related bioactive plant materials.