Intensive aquaculture antibiotic use contributes to resistance gene proliferation. We surveyed antimicrobial resistance patterns across Vietnamese shrimp and fish farms examining water, sediment, and animal samples. Multi-drug resistant bacteria prevalence reached 45% with resistance genes detected in downstream water bodies. Farm-level antibiotic use intensity correlated with resistance prevalence. Probiotic alternatives showed promise reducing therapeutic antibiotic requirements. Our surveillance data supports antimicrobial stewardship program development for aquaculture sectors.

Heritage building conservation requires accurate documentation of complex architectural features. We integrated terrestrial laser scanning with building information modeling for Byzantine church restoration in Greece. Point cloud processing captured millimeter-accuracy geometric data including deterioration patterns. BIM models enabled structural analysis and intervention planning. Digital twins facilitated remote expert collaboration during pandemic restrictions. Standardized workflows reduced documentation time by 60% compared to traditional methods. Our methodology supports systematic heritage management and disaster preparedness.

Microfinance promises economic empowerment for women in developing countries yet evidence remains mixed. We conducted longitudinal tracking of 600 women borrowers across Bangladeshi microfinance institutions over five years. Business survival rates reached 72% with average income increases of 45% for successful enterprises. Group lending mechanisms provided social support beyond financial services. Over-indebtedness affected 15% of borrowers highlighting program design importance. Our findings inform microfinance product development targeting sustainable women entrepreneurship.

Timely crop health assessment enables targeted interventions reducing agrochemical inputs. We deployed multispectral drone surveys across Mexican maize and bean farms throughout growing seasons. Vegetation indices identified nitrogen deficiency and water stress weeks before visible symptoms appeared. Variable rate application maps reduced fertilizer use by 28% while maintaining yields. Cloud-based processing enabled farmer access through mobile applications. Our system demonstrates affordable precision agriculture for smallholder farms in developing regions.

Traditional noise metrics inadequately capture human perception of urban soundscapes. We developed psychoacoustic assessment frameworks incorporating loudness, sharpness, and fluctuation strength measures. Field studies in Swedish cities revealed sound quality factors predicted annoyance better than decibel levels alone. Green infrastructure integration reduced perceived noise impact even when physical levels remained unchanged. Design guidelines incorporating psychoacoustic principles improved outdoor public space quality. Our methodology enhances noise management strategies for urban planners and architects.

Textile industry generates substantial environmental impacts through linear production models. We conducted material flow analysis of Egyptian textile manufacturing tracking fiber inputs through production, consumption, and disposal. Only 12% of textile waste entered recycling streams despite available technologies. Extended producer responsibility schemes in Europe increased collection rates but export to developing countries shifted environmental burdens. Chemical recycling showed promise for blended fabrics unsuitable for mechanical processing. Our analysis informs circular economy policy development for textile sectors.

Healthcare AI development requires large datasets while protecting patient privacy. We implemented federated learning across five Chinese hospitals for chest X-ray classification. Decentralized training achieved 94% of centralized model accuracy while keeping data on-premises. Differential privacy mechanisms added computational overhead but prevented model inversion attacks. Non-IID data distributions across hospitals required adaptive aggregation strategies. Our framework enables collaborative medical AI development without centralizing sensitive health records.

Maintaining water quality is crucial for both public health and environmental sustainability. This study proposes a machine-learning- (ML-) and Internet-of-Things- (IoT-) based approach to water quality prediction that utilizes explainable artificial intelligence (XAI) and data classification techniques. The proposed approach integrates IoT devices to enhance real-time data collection, facilitating continuous monitoring and early anomaly detection. Ten different ML classifiers—Decision Trees, K-Nearest Neighbors, XGBoost, Naïve Bayes, Logistic Regression, AdaBoost, Random Forests, Support Vector Machines, Voting, and Multi-Layer Perceptron—were evaluated to find out which one works best for predicting water quality. We used three distinct approaches for feature selection: analysis of variance (ANOVA), mutual information (MI), and chi-square, to ensure the most relevant features. We assessed the predictive model using three datasets of varying sizes (5000, 3600, and 1850 records), employing multiple cross-validation techniques to enhance reliability. The Synthetic Minority Oversampling Technique (SMOTE) was used to fix the data imbalance. Experimental findings showed that XGBoost outperformed other classifiers, achieving the highest accuracy across all dataset sizes. Specifically, for the largest dataset, XGBoost achieved 97.12% accuracy, 99.67% AUC (Area under the Curve), 97.95% specificity, 95.95% precision, 95.50% sensitivity, and an F1 score of 95.73%. Similarly, for the mid-sized dataset, XGBoost attained 93.22% accuracy, and for the smallest dataset, it reached 95.46% accuracy. The key contribution of this work is the application of an XAI method using SHAP (SHapley Additive exPlanations), which enhances the model\'s interpretability by emphasizing key water quality factors that influence predictions. Unlike traditional black-box ML models, this approach provides transparency and facilitates informed decision-making for environmental scientists and policymakers. An efficient, scalable, and time-saving method for predicting water quality is provided by the proposed model, making it suitable for large-scale environmental monitoring and resource-limited settings. This study improves how we manage water resources by providing a clear and accurate prediction model that uses real-time monitoring from IoT and analytics from ML. To promote environmental sustainability and guarantee safer water resources, the results show that AI-powered water quality assessment can support proactive interventions

Dengue fever is a rapidly emerging mosquito-borne viral infection that poses a significant public health threat across tropical and subtropical regions. Climatic and environmental factors play a critical role in shaping the transmission dynamics of Dengue. This study investigates the influence of key climatic variables on Dengue incidence in Puducherry, a coastal Union Territory in southern India that has witnessed a marked rise in Dengue cases over the past decade. Monthly data on reported Dengue cases and climatic variables including rainfall, temperature, and humidity were collected from 2012 to 2020. Statistical modelling approaches, including Poisson and negative binomial regression, were applied to examine the relationship between climatic indicators and Dengue transmission rates. The results revealed a strong association between increased Dengue incidence and rainfall levels (with a 1-month lag), as well as minimum temperatures below 25°C. The negative binomial model outperformed the Poisson model in capturing over-dispersion in the data, yielding a better model fit (AIC = 524.92; RMSE = 68.38) and high predictive accuracy (correlation between observed and predicted cases: r = 0.75, p < 0.001). These findings underscore the importance of incorporating climatic predictors into early warning systems to enhance Dengue surveillance and inform targeted public health interventions in vulnerable regions like Puducherry.