Mohammad Ismail

Timely estrus detection determines reproductive efficiency in Hanwoo cattle, yet visual observation is increasingly difficult as herd sizes grow and standing behavior becomes less consistently expressed. Fixed farm cameras offer a non-invasive alternative, but mounting, chin-resting and sniffing involve two overlapping animals and occur rarely, complicating automated detection. This study evaluated how annotation strategy, augmentation policy and detector choice affect detection of these cues. A surveillance dataset of 846 red–green–blue (RGB) frames, containing 200 estrus-interaction instances against 2180 posture instances, was recorded at a commercial farm. Three annotation strategies, partial bounding-box label (PBL), full single bounding-box label (FSBL) and full dual bounding-box label (FDBL), were combined with three augmentation stages and three lightweight detectors (YOLOv5n, YOLOv8n, YOLO11n), giving 27 configurations. Rare-class performance varied approximately twice as widely as overall performance and depended more on annotation and augmentation than on detector family. PBL maximized sensitivity (recall 0.718), FSBL maximized localization quality (average precision, AP50 0.798) and overall accuracy (mean average precision, mAP50 0.864), and FDBL preserved relational context (recall 0.700, AP50 0.775). Annotation and augmentation should be selected according to whether the purpose is screening candidate interactions or supporting expert confirmation. Detections represent a behavioral proxy, not physiological confirmation of estrus.

Reliable individual tracking supports animal behavior monitoring in precision livestock farming. However, tracking cattle using a single camera in high-density barns is challenging because of frequent occlusion, scale variation, and irregular movement. This study presents a lightweight multi-object tracking framework for densely housed Hanwoo cattle, combining a Hanwoo-trained YOLOv8n detector with appearance-free BoT-SORT association. Frame sampling reduces the detection workload, while an offline Multi-Temporal Window Repair (MTW-Repair) procedure reconnects fragmented trajectories. The framework was evaluated using short annotated video clips and a continuous 215 min barn recording. In the short clips, appearance-free BoT-SORT outperformed ByteTrack while maintaining comparable throughput, and MTW-Repair reduced identity switches across all evaluated frame-sampling intervals. In the long recording, MTW-Repair reduced the total number of generated identities for both trackers. Manual verification of 50 randomly sampled ByteTrack merge events yielded a merge precision of 84.0%. Appearance-based re-identification offered only marginal accuracy gains at a higher computational cost. These findings support the potential of frame sampling and offline trajectory repair for computationally efficient cattle monitoring.

The prediction of soil moisture constants (SMCs), including field capacity (FC), permanent wilting point (PWP) and available water content (AWC), is essential for efficient irrigation scheduling and water management in the coastal regions of Bangladesh affected by salinity, flooding and waterlogging. However, the comparative evaluation of machine learning (ML) models for predicting SMCs in these complex coastal soils remains limited. Therefore, this study evaluated five ML models to predict SMCs using soil physicochemical parameters (pH; electrical conductivity; organic matter; bulk density; and sand, silt and clay fractions). The observed ranges were 6.5%–38.4%, 1.3%–15.5% and 5.1%–26.0% for FC, PWP and AWC, respectively. Among the applied models, the multilayer perceptron (MLP) achieved the best predictive performance, with R ² values of 0.926, 0.911 and 0.906 for FC, PWP and AWC, respectively, whereas MLR showed the weakest performance, with corresponding R ² values of 0.804, 0.761 and 0.738. Compared with the other models, MLP improved R ² by 3%–23% and reduced RMSE by 13%–40% across FC, PWP and AWC. Using input combination‐5 (IC‐5), the MLP explained more than 89% of the variability and achieved up to 98% prediction accuracy, highlighting its strong potential for predicting SMCs in coastal soils to support agricultural productivity.

Groundwater quality in floodplain regions is increasingly compromised by combined geogenic and anthropogenic processes enriching potentially toxic elements (PTEs) in aquifers. This study assessed 18 groundwater samples from shallow tube wells in three zones of Chandina Upazila, Bangladesh, including industrial (Z1), semi-industrial (Z2), and residential-agricultural (Z3) areas, to evaluate water quality and health risks of As, Pb, Mn, and Fe. Physicochemical parameters and PTEs were analyzed following standard American Public Health Association (APHA) procedures. Drinking water suitability was assessed using the water quality index (WQI), heavy metal pollution index (HPI), and heavy metal evaluation index (HEI). Contamination sources were identified using Pearson correlation analysis and the absolute principal component scores-multiple linear regression (APCS-MLR) model. Deterministic and probabilistic (Monte Carlo simulation) risk assessment were applied to estimate health risks for children and adults. The mean WQI, HEI, and HPI values were 359.43, 12.66, and 363.93 in Z1; 267.00, 14.75, and 264.59 in Z2; and 203.10, 10.37, and 197.01 in Z3, respectively, suggesting that groundwater is 'strongly affected' and 'unsuitable for drinking'. Correlation analysis revealed significant relationships among physicochemical parameters and PTEs, while the APCS-MLR identified three contamination sources: geogenic (As and Fe), mixed (Mn), and industrial (Pb). Both deterministic and probabilistic health risk assessments revealed non-carcinogenic risk (NCR) and carcinogenic risk (CR) above threshold levels (HI > 1 and TCR > 1.0E-04), mainly due to As exposure. These findings highlight widespread groundwater contamination and underscore the need for groundwater management and public health surveillance to ensure safe drinking water.