METHODS: The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed.

RESULTS: The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23 MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone.

METHODS: Three object detection networks of DL algorithms, namely SSD-MobileNetV2, EfficientDet, and YOLOv4, were developed to automatically detect Escherichia coli (E. coli) bacteria from microscopic images. The multi-task DL framework is developed to classify the bacteria according to their respective growth stages, which include rod-shaped cells, dividing cells, and microcolonies. Data preprocessing steps were carried out before training the object detection models, including image augmentation, image annotation, and data splitting. The performance of the DL techniques is evaluated using the quantitative assessment method based on mean average precision (mAP), precision, recall, and F1-score. The performance metrics of the models were compared and analysed. The best DL model was then selected to perform multi-task object detections in identifying rod-shaped cells, dividing cells, and microcolonies.

RESULTS: The output of the test images generated from the three proposed DL models displayed high detection accuracy, with YOLOv4 achieving the highest confidence score range of detection and being able to create different coloured bounding boxes for different growth stages of E. coli bacteria. In terms of statistical analysis, among the three proposed models, YOLOv4 demonstrates superior performance, achieving the highest mAP of 98% with the highest precision, recall, and F1-score of 86%, 97%, and 91%, respectively.

METHODS: Samples were subjected to microscopy examination and serological test (only for Strongyloides). Speciation for parasites on microscopy-positive samples and seropositive samples for Strongyloides were further determined via polymerase chain reaction. SPSS was used for statistical analysis.

RESULTS: A total of 294 stool and blood samples each were successfully collected, involving 131 HIV positive and 163 HIV negative adult male inmates whose age ranged from 21 to 69-years-old. Overall prevalence showed 26.5% was positive for various IPIs. The IPIs detected included Blastocystis sp., Strongyloides stercoralis, Entamoeba spp., Cryptosporidium spp., Giardia spp., and Trichuris trichiura. Comparatively, the rate of IPIs was slightly higher among the HIV positive inmates (27.5%) than HIV negative inmates (25.8%). Interestingly, seropositivity for S. stercoralis was more predominant in HIV negative inmates (10.4%) compared to HIV-infected inmates (6.9%), however these findings were not statistically significant. Polymerase chain reaction (PCR) confirmed the presence of Blastocystis, Strongyloides, Entamoeba histolytica and E. dispar.

METHODS: A randomized 4 × 4 Latin square designed experiment was conducted to compare the efficiency of the Mosquito Magnet against three other common trapping methods: human landing catch (HLC), CDC light trap and human baited trap (HBT). The experiment was conducted over six replicates where sampling within each replicate was carried out for 4 consecutive nights. An additional 4 nights of sampling was used to further evaluate the Mosquito Magnet against the "gold standard" HLC. The abundance of Anopheles sampled by different methods was compared and evaluated with focus on the Anopheles from the Leucosphyrus group, the vectors of knowlesi malaria.

METHODS: We conducted a double-blinded, randomised controlled trial involving 651 rural primary schoolchildren (8-12 years) with VAD in Malaysia. The schoolchildren were randomised to receive either RPO-enriched biscuits (experimental group, n = 334) or palm olein-enriched biscuits (control group, n = 317) for 6-month duration.