This research proposes the use of hybrid machine learning methods to mimic dye removal efficiency. Hyperparameter tuning via differential evolution (DE), genetic algorithm (GA), random search (RS), and grid search (GS) with the XGBoost model was conducted to achieve more accurate results. This study focused on the relationships between the initial dye concentrations of Fast Green, Eosin Y, and Quinine Yellow dyes, their initial pH, ACMOF adsorbent dosage (activated carbons: metal‒organic frameworks), and sonication time as input variables, with the removal percentage as the output data. The analysis emphasized the correlation between the inputs and outputs, resulting in the generation of four scenarios: 4 inputs, 3 inputs, 2 inputs, and 1 input. The correlation analysis revealed a weak input‒output relationship and the presence of outliers in the data. The use of advanced models, such as XGBoost, improved model performance and accurately predicted dye removal efficiency. The models performed well across different input scenarios, demonstrating their reliability and effectiveness. The results also revealed the importance of data preprocessing techniques in improving the structure and relationships within the data. The DE_XGBoost model outperforms all the other methods in terms of R2 (R2 values of 0.977, 0.958, 0.924, and 0.997 for 4-input, 3-input, 2-input, and 1-input, respectively), demonstrating its DE effectiveness in generalizing the model and enhancing its predictivity. This research contributes to the development of more efficient techniques for dye removal and environmental pollution mitigation, addressing the challenges of traditional testing methods. These findings have implications for industries that use dyes and can help mitigate the environmental pollution caused by dye effluents.

This study presents an in-depth analysis of machine learning (ML) techniques for predicting water quality index and water quality classification using a dataset containing water quality metrics such as temperature, specific conductance, salinity, dissolved oxygen, depth, pH, and turbidity from multiple monitoring stations. Data preprocessing included imputation for missing values, feature scaling, and categorical encoding, ensuring balanced input features. This research evaluated artificial neural networks, decision trees, support vector machines, random forests, XGBoost, and long short-term memory (LSTM) networks. Results demonstrate that XGBoost and LSTM significantly outperformed other models, with XGBoost achieving an accuracy range of 99.07–99.99% and LSTM attaining an R2 of 0.9999. Compared with prior studies, our approach enhances predictive accuracy and robustness, showcasing advanced generalization capabilities. The proposed models exhibit significant improvements over traditional methods in handling complex, multivariate water quality data, positioning them as promising tools for water quality prediction and environmental management. These findings underscore the potential of ML for developing reliable, scalable water quality monitoring solutions, providing valuable insights for policymakers and environmental managers dedicated to sustainable water resource management.

Groundwater prediction in data-scarce and environmentally sensitive regions presents a persistent challenge due to limited observational data, spatial heterogeneity, and the nonlinear nature of hydrogeological processes. In this study, we propose HydroPredictor, a hybrid machine learning framework that integrates the categorical handling efficiency of CatBoost with the nonlinear feature learning capacity of a regularized Multi-Layer Perceptron (MLP). The model was trained on a geo- referenced dataset of 315 samples from the Feija Basin in southeastern Morocco, incorporating ten environmental predictors such as elevation, rainfall, soil permeability, NDVI, and topographic wetness index. The pipeline includes Optuna-based hyperparameter optimization and 5-fold cross-validation to ensure robustness and generalization. HydroPredictor achieved a testing accuracy of 89.23%, with an F1-score of 0.8937 and Area Under the Curve (AUC) values exceeding 0.90 across all groundwater potential classes. Statistical validation using the Friedman and Wilcoxon signed-rank tests (p < 0.05) confirmed its significant outperformance over conventional models, including Random Forest, Support Vector Machine (SVM), and standalone MLP. Furthermore, HydroPredictor demonstrated superior generalization compared to prior models in the literature (e.g., RF-SSA: AUC = 0.840; GBDT: AUC = 0.88), while maintaining minimal overfitting (∆Accuracy = 0.35%). By combining interpretable tree-based embeddings with deep neural representations, HydroPredictor provides a robust and scalable solution for groundwater classification in data-limited settings, offering a reproducible and operationally relevant tool for sustainable groundwater resource management under climatic and environmental uncertainty.

This study introduces a coalesce forecasting model tailored for flood-prone regions, specifically focusing on Bihar, India. Research has revealed significant disparities in rainfall patterns across various zones such as Tirhut, Patna, and Munger zones experiencing greater mean rainfall than Bhagalpur and Kosi. To evaluate the forecasting capabilities, coalescing methods were applied which includes the autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), neural network autoregressive (NNAR), and seasonal-trend decomposition. Moreover, Loess (STL) methods, and trigonometric seasonality, Box‒Cox transformation, ARMA errors, and trend and seasonal components (TBATS) were also employed to contrast the benchmark models such as the seasonal naïve, naïve, and mean methods. These methods were evaluated using error evaluators such as residual error, root mean square error (RMSE), mean absolute error (MAE), mean absolute scaled error (MASE), and autocorrelation of errors at lag 1 (ACF1) to determine the performance of these techniques. Additionally, statistical tests, such as the Box–Pierce and Box–Ljung tests, supported these findings. Among the error evaluators and forecasting models, the ETS and NNAR models remain the top choices for Saran-Tirhut-Bhagalpur and Munger-Magadh-Kosi, respectively, effectively capturing rainfall patterns and minimizing residual errors, as indicated by low RMSE values. Moreover, ARIMA and TBATS remain the top choices for Patna, Purnia and Darbhanga, respectively, followed by ETS model. In addition, the STL model secured the second position for Saran, Tirhut, Bhagalpur, and Purnia zones. This research emphasizes the importance of understanding regional rainfall dynamics for effective flood risk management and climate adaptation strategies. This study provides valuable tools for water resource management and agricultural planning in Bihar amidst climate variability challenges. It advocates for rainfall trend analysis followed by forecasting to achieve more precise water resource management and planning.

Microplastic contamination of terrestrial and aquatic environment has gained immense research attention due to their potential ecotoxicity and biomagnification property when enterer into food chain. Heterogenous nature of microplastics coupled with their ability to combine with other emerging pollutants have increased the severity of this crisis. Existing detection methods often fails to accurately quantify the amount of microplastic components present in environmental and biological samples. Thus, a great deal of research gap always exists in our current understanding about microplastics including the limitations in screening, detection and mitigation. This review work presents a comprehensive out look on the impact of microplastics on both terrestrial and aquatic environment. Furthermore, an in-depth discussion on various microplastic detection techniques recently used for microplastic quantification along with their significance and limitations is summarised in this review. The review also elaborates various physical, chemical and biological methods used for the mitigation of microplastics from environmental samples.

The mandates of safety standards in manual material handling tasks have spurred the development and commercialization of many back-assist exoskeletons. These devices prevent back pain injuries by redistributing the applied loads, reducing the effort and fatigue in heavy and repetitive loading tasks. The majority of them employ passive and active actuation paradigms. The passive ones are known for better transparency and energy efficiency, while the active ones provide a higher degree of assistance and quickly adapt to task severities. The present work investigates the feasibility of a hybrid actuation paradigm for load-carriage under symmetric loading conditions. The preliminary results suggest that the proposed modifications to an existing passive exoskeleton effectively economize energy expenditure and improve adaptability.

The objective of the present study is to investigate the application of artificial intelligence tools in dephenolization of simulated wastewater. The adsorbent was waste corncob activated and impregnated with tetraoxophosphate V acid (H3PO4). The adsorbent was characterized via SEM and FTIR analysis. Artificial intelligence models such as adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and response surface methodology (RSM) were used in modeling the dephenolization process. Genetic algorithm (GA) was used to optimize the best models. The results indicated that H3PO4-assisted impregnation enhanced the adsorptive dephenolization capability of the adsorbent. The BET surface area analysis of the modified adsorbent showed a surface area of 903.7 m2/g, average pore width of 5.55 nm and micropore volume of 0.389 cm2/g. SEM micro-graph showed that the modified activated carbon has asymmetrical and interspatial pores which indicated desirable sorption properties of the adsorbent. The correlation coefficient (R2) of the ANFIS, ANN and RSM models were 0.9998, 0.9998, and 0.9430 respectively while the Adjusted R2 were 0.9339, 0.9998, and 0.9998 respectively. This implied that ANN and ANFIS models were more significant than RSM. Further statistical analysis suggested that ANFIS and ANN have almost equal capability in modeling the dephenolization process. The ANN-GA and ANFIS-GA optimization gave maximum percentage of phenol removal as 92.44% and 92.34% respectively under optimum process conditions. The maximum adsorption capacity of 121 mg/g obtained from the GA optimization was comparably higher than most reported works. The point of zero charge was 5.65 while the regeneration with 0.2M NaOH showed best adsorbent reusable capacity. These results suggest that these waste corn cob activated carbon can be utilized as a high performance and efficient adsorbent in dephenolization of waste water. This is in addition to the reduction of the huge environmental waste associated with corn cobs. Furthermore there is no harmful environmental impact and no generation of toxic by-products during the adsorption process.

This study investigates the use of novel flattened-end nylon fibres (FENF) as reinforcement in concrete to improve its mechanical properties. The research addresses inadequate circumferential bonding between macro synthetic fibres and concrete matrix, which can lead to fibre slippage or failure. Through experiments involving 19 concrete mixes with varying fibre dosages (0.5%, 1% and 1.5%), aspect ratios (35, 55 and 75), and shapes (straight and flattened-end), the study examines the impact of FENF on concrete workability and mechanical strengths. The mechanical strength tests illustrate the significance of fibre dosage, aspect ratio and especially the shape as the compressive, split-tensile strength and flexural strengths of the FENF concrete are respectively showing an increase in strength of up to 10.3%, 25.1% and 26.1% when compared with conventional concrete. Similarly, the straight nylon fibre-reinforced concrete also achieved comparable strength increments up to 11.8%, 13.9% and 15.9% respectively for compressive, split-tensile and flexural strengths. This indicates that the positive effect of fibre shape on circumferential bonding helped the better performance of the FENF in split-tensile and flexural strengths. Further, the statistical methods, including regression analysis, Principal Components Analysis, and Response Surface Methodology, are employed to analyse the complex relationships between fibre characteristics and identify optimal fibre configurations. Using the Scanning Electron Microscope (SEM) the microstructural view has been studied to evaluate the interaction between FENF and the concrete matrix.

The primary objective is to select an appropriate aerator that maximizes the benefits while minimizing the operational costs of the aeration system in aquaculture operations. The choice of suitable aerators significantly impacts the cost of aquaculture operations. Therefore, this study focuses on the economic analysis of the paddle wheel aerator (PWA) and its modified counterpart, the spiral aerator (SA). The efficiency of the PWA and SA was assessed with respect to rotational speed (N), based on the efficiency a comparative economic analysis was conducted. The economics of aerators depends on the various pond sizes, initial dissolved oxygen (DO), and aerators running hours. Therefore, the total aeration cost for the chosen aerators was determined at various pond volumes (100, 200, 300, 700, 1000, 5000, and 10,000 m3 with depth of water 1.0 m) and initial DO of pond water denoted as CP = 1 to 4 mg/L. According to market rates, the primary cost for PWA was ₹32,000, while that for SA was ₹42,000. From the findings, pond sizes in the range of 100 to 10,000 m3 PWA are more economical than SA. Therefore, a new selection method of economically feasible aerators in aquaculture pond was developed in this study.

Deep learning techniques have demonstrated early advancements in addressing the challenges of complex Visual Speech Recognition (VSR) tasks. Nonetheless, a persistent issue arises when distinguishing characters or words with similar pronunciations, known as homophones, which results in ambiguity. Existing VSR systems also face technical constraints due to insufficient visual data for learning short-duration phonemes like “at”, “an”, “a”, and “eight”. Moreover, cutting-edge VSR techniques perform exceptionally well when interpreting overlapping speakers. However, extending these methods to unseen speakers leads to a significant performance decline due to the limited diversity in the training dataset and substantial variations in physical attributes, such as lip shape and color, across different speakers. To address the existing challenges in VSR, we propose a multi-modal approach that leverages visual and landmark information to capture complex spatio-temporal patterns for the model generalization capabilities. The model employs a multi-layered Three-Dimensional Convolutional Neural Network (3D-CNN) that extracts visual features, while a Graph Convolutional Network (GCN) captures precise landmark information for accurate lip shape localization. The extracted features are then fused for further processing using a Sequence-to-Sequence (Seq2Seq) model based on the attention mechanism. The proposed model achieved a WER of 0.53% and 8.21% for the overlap and unseen speakers category. Notably, these results surpass the performance of existing models, demonstrating remarkable accuracy for VSR on the GRID dataset in both the unseen and overlapping speaker scenarios.

Artificial intelligence (AI) offers innovative and efficient solutions to contemporary challenges in sustainable aquaculture. Machine learning (ML) and deep learning (DL) are integral components of smart aquaculture, driving significant advancements in the field. The integration of AI with ML, and DL technologies is transforming traditional aquaculture practices by enhancing operational efficiency, optimizing fish health management, improving environmental conditions, monitoring water quality and supporting advanced decision-making processes. This review highlights the latest applications of AI, including ML, and DL in aquaculture, emphasizing their roles in real-time water quality monitoring, disease detection, and automated estimation of fish biomass etc. Key techniques, including predictive modeling, image and video processing, and sensor data integration, are enabling these breakthroughs. Moreover, DL algorithms, such as convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, have emerged as powerful tools for processing complex data and predicting critical events within aquaculture systems. Despite the notable progress, challenges such as the need for large, labeled datasets, high computational costs, and issues related to model interpretability continue to limit broader adoption. The current review aims to offer researchers and practitioners with a comprehensive overview of AI and its subfields such as ML and DL applications in smart aquaculture, discussing both the opportunities and challenges while suggesting future research directions to overcome existing limitations and expand AI-driven innovations in the industry.

A critical requirement for rehabilitation robots is achieving high transparency in user interaction to minimize interference when assistance is unnecessary. Cable-driven systems are a compelling alternative to rigid-link robots due to their lighter weight and reduced inertia, enhancing transparency. However, controlling cable tension forces remains a significant challenge, as these forces directly affect the interaction between the user and the robot. Effective strategies must maintain low tension during non-assistive phases while preventing slackness. This paper introduces PACE-R (Passive Active CablE Robot), a novel lightweight actuation system for cable-driven rehabilitation devices. The PACE-R module utilizes remote actuation and an open-loop, discrete state control, where the cable is coupled to the motor only during active intervention. When not assisting, the cable is passively decoupled from the motor, and a low-stiffness spring maintains minimal tension, enabling high transparency. Benchtop tests showed that the module consistently produced force impulses proportional to motor input with delays not exceeding 15 ms. In the treadmill push-off assistance demonstration, PACE-R contributed about 20% to total ankle moment and power. Transparency analysis revealed negligible interference, with only 1% and 0.5% contributions to peak total ankle moment and power, respectively.

Facial biometric systems are extensively applied in diverse sectors for the purposes of person authentication and verification, primarily due to the distinctive nature of individual facial characteristics. Deep learning models are typically used in face authentication to validate people with excellent recognition accuracy. However, these systems are susceptible to a variety of cyber attacks that manipulate the digital representations of real-world faces to cheat the models. In the contemporary landscape of digital identity theft, liveness detection stands as a crucial technology. The need for enhanced security prompts the demand for a resilient system that can effectively counter face spoofing attempts and prevent unauthorized access. A Binary Authentication Protocol (BAP) technique is proposed to enhance facial biometric security in combination with Visual Speech Recognition (VSR). In the proposed method, the first verification step entails face authentication. Further, the authentication protocol involves a challenge-response-based method using VSR. The proposed method achieved a word error rate of 2.7% and a word recognition rate of 97.3%, surpassing existing state-of-the art methods in VSR. The proposed scheme offers practical and effective solutions to prevent face spoofing through active liveness detection in face-based authentication systems.

Morocco’s oases, critical agroecological systems in arid regions, face escalating water scarcity due to climate variability, groundwater depletion, and a historic decline in palm groves from 15 million to 4 million trees over the past century. This study introduces a machine learning (ML)-based precipitation forecasting framework to enhance water resource management in four semi-arid Moroccan regions: Errachidia, Figuig, Tata, and Zagora. Leveraging a 1981–2025 dekadal rainfall dataset from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS v2), we developed and compared four ML models: XGBoost, CatBoost, Long Short-Term Memory (LSTM), and Temporal Convolutional Network (TCN). CatBoost emerged as the most effective, achieving a testing  of 0.9818 and a mean squared error (MSE) of 0.5430 mm on historical data (2019–2025), and a fine-tuned 90-day forecast (March 5–June 3, 2025) with  of  and MSE of 0.3364 mm. Historical trends revealed declining precipitation post-2015, underscoring the need for predictive tools. These findings demonstrate CatBoost’s superior ability to capture nonlinear rainfall dynamics, offering a scalable solution for climate-resilient water management in water-scarce regions. However, challenges such as data sparsity and model interpretability highlight the need for enhanced observational networks and explainable AI approaches to maximize practical adoption.

Identity verification is essential in both an individual’s personal and professional life. It confirms a person’s identity for various services and establishes their legitimacy as an employee within an organization. As cybercrime evolves and becomes more sophisticated, ensuring robust, and secure personal authentication methods has become a critical challenge. Existing face-based authentication systems typically employ deep learning models for user verification. However, these systems are susceptible to various attacks, such as presentation attacks, 3D mask attacks, and adversarial attacks that exploit and deceive the models by manipulating digital representations of human faces. Although various liveness detection techniques have been proposed to combat face spoofing in face-based authentication systems. However, these systems remain vulnerable and can be exploited by sophisticated techniques. To counteract face spoofing in a face-based authentication system, we have proposed an advanced liveness detection technique using Visual Speech Recognition (VSR). The proposed VSR model is designed to integrate seamlessly with face-based authentication systems, forming a dual authentication framework for enhanced liveness detection. The VSR model decodes silently pronounced speech from video by analyzing unique, unforgeable lip motion patterns into textual representation. Although, various liveness detection techniques have been proposed to combat face spoofing in face-based authentication systems. However, these systems remain vulnerable and can be exploited by sophisticated techniques. To counteract face spoofing in a face-based authentication system, we have proposed an advanced liveness detection technique using VSR. The proposed VSR model is designed to integrate seamlessly with face-based authentication systems, forming a dual authentication framework for enhanced liveness detection. The VSR model decodes silently pronounced speech from video by analyzing unique, unforgeable lip motion patterns into textual representation. To achieve effective liveness detection using VSR, we need to enhance the accuracy of the VSR system. The proposed work employs an encoder-decoder technique to extract more robust features from lip motion. The encoder employs a three-dimensional convolution neural network (3D-CNN) combined with a fusion of bi-directional gated recurrent units and long short-term memory (BiGRU-BiLSTM) to effectively capture spatial-temporal patterns from lip movement. The decoder integrates Multi-Head Attention (MHA) with BiGRU-BiLSTM to effectively focus on relevant features and enhance contextual understanding for more accurate text prediction. The proposed VSR system achieved a word error rate (WER) of 0.79%, demonstrating a significant reduction in error rate and outperforming compared to the existing VSR models.

This review explores the multifaceted benefits of Myrica species, commonly known as bayberry, highlighting their therapeutic, nutritional, and environmental value. The fruit of the Myrica tree is very good for you. It’s full of important nutrients and bioactive compounds, like myricetin, that help your immune system and your overall health. Tree bark, in addition to fruit, contains essential oils, and locals use the wood for construction. Various species of Myrica, including Myrica esculenta (Myrica Nagi), which is found in India, are distributed across several countries, including China, Nepal, Japan, Singapore, and Malaysia. Although the industrial uses of bayberry have received limited research, its pharmacological and medicinal properties have been the subject of extensive studies. The high nutritional content of fruit includes iron, magnesium, sodium, potassium, calcium, and copper. Additionally, it contains bioactive compounds such as tannins, flavonoids, volatile compounds, saponins, and phenolic acids. his study looks at how research trends changed from 2014 to 2024 using bibliographic tools that discuss the fruit’s uses and its health, nutrition, and environmental benefits. The study also maps the species’ distributions around the world. Despite its numerous benefits, bayberry faces threats from overexploitation and urbanization, leading to its decline. There is a pressing need to explore and develop sustainable uses and byproducts of these wild fruits to preserve their value and ensure their availability for future generations.

This study investigates the use of novel flattened-end nylon fibres (FENF) as reinforcement in concrete to improve its mechanical properties. The research addresses inadequate circumferential bonding between macro synthetic fibres and concrete matrix, which can lead to fibre slippage or failure. Through experiments involving 19 concrete mixes with varying fibre dosages (0.5%, 1% and 1.5%), aspect ratios (35, 55 and 75), and shapes (straight and flattened-end), the study examines the impact of FENF on concrete workability and mechanical strengths. The mechanical strength tests illustrate the significance of fibre dosage, aspect ratio and especially the shape as the compressive, split-tensile strength and flexural strengths of the FENF concrete are respectively showing an increase in strength of up to 10.3%, 25.1% and 26.1% when compared with conventional concrete. Similarly, the straight nylon fibre-reinforced concrete also achieved comparable strength increments up to 11.8%, 13.9% and 15.9% respectively for compressive, split-tensile and flexural strengths. This indicates that the positive effect of fibre shape on circumferential bonding helped the better performance of the FENF in split-tensile and flexural strengths. Further, the statistical methods, including regression analysis, Principal Components Analysis, and Response Surface Methodology, are employed to analyse the complex relationships between fibre characteristics and identify optimal fibre configurations. Using the Scanning Electron Microscope (SEM) the microstructural view has been studied to evaluate the interaction between FENF and the concrete matrix.

The rise in the production, utilization and disposal of mobile phones has created a global concern for environmental sustainability. In the present research, environmental impact evaluation for the different life stages of mobile phones was performed using the life cycle assessment (LCA) approach. The study was focused mainly on raw materials extraction and network utilization phase as these two stages are responsible for creating most of the environmental pollution and health hazards. A comparative life cycle assessment was performed to evaluate impacts associated with button- and touch types mobile phones. IMPACT 2002 + ® method was considered to evaluate the environmental impacts. Fifteen mid-point and four damage assessment categories were evaluated. The production phase is the major emission contributing stage to human health, ecosystem quality, climate change and resources categories followed by its utilization phase. Printed circuit board manufacturing contributes to the emission in production phase while electricity consumption in utilization phase. Avoidance of virgin material for the production of mobile phones and its charging is identified as key parameters for improving the environmental performance. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2024.