Application of computer vision and deep learning models to automatically classify medically important mosquitoes in North Borneo, Malaysia.

Mosquito-borne diseases have emerged in North Borneo in Malaysia due to rapid changes in the forest landscape, and mosquito surveillance is key to understanding disease transmission. However, surveillance programmes involving sampling and taxonomic identification require well-trained personnel, are time-consuming and labour-intensive. In this study, we aim to use a deep leaning model (DL) to develop an application capable of automatically detecting mosquito vectors collected from urban and suburban areas in North Borneo, Malaysia. Specifically, a DL model called MobileNetV2 was developed using a total of 4880 images of Aedes aegypti, Aedes albopictus and Culex quinquefasciatus mosquitoes, which are widely distributed in Malaysia. More importantly, the model was deployed as an application that can be used in the field. The model was fine-tuned with hyperparameters of learning rate 0.0001, 0.0005, 0.001, 0.01 and the performance of the model was tested for accuracy, precision, recall and F1 score. Inference time was also considered during development to assess the feasibility of the model as an app in the real world. The model showed an accuracy of at least 97%, a precision of 96% and a recall of 97% on the test set. When used as an app in the field to detect mosquitoes with the elements of different background environments, the model was able to achieve an accuracy of 76% with an inference time of 47.33 ms. Our result demonstrates the practicality of computer vision and DL in the real world of vector and pest surveillance programmes. In the future, more image data and robust DL architecture can be explored to improve the prediction result.

Population genetic structure of tropical bed bug (Hemiptera: Cimicidae) populations and their breeding pattern in Iraq.

A study was conducted to investigate the population genetic structure and breeding pattern of 140 tropical bed bugs, Cimex hemipterus (F.) (Hemiptera: Cimicidae), collected from 14 infested sites in major cities in Iraq. The samples were genotyped using a set of 7 polymorphic microsatellite markers. High genetic variety was seen among populations, with an average of 2-9 alleles per locus. The number of alleles across 7 microsatellite loci was between 6 and 18. There was a notable disparity in the alleles per loci when comparing the overall population to those within it. The overall population exhibited an average observed heterozygosity of 0.175 and an average expected heterozygosity of 0.730. Among the population, the average observed heterozygosity was 0.173, while the average expected heterozygosity was 0.673. Analysis of molecular variance (AMOVA) revealed that 93% of the genetic variability was within the populations, and 7% was among them. The genetic differentiation coefficient (FST = 0.045), indicates a low degree of genetic differentiation and a high degree of inbreeding (FIS = 0.761), as indicated by notably significant positive inbreeding coefficients. Admixed individuals were revealed using STRUCTURE and neighbor-joining phylogenetic trees, demonstrating moderate gene flow between populations and a lack of genetic structure in the regional groups. Thus, both active dispersion and human-mediated dispersion possess the potential to influence the low population genetic structure of tropical bed bug C. hemipterus populations in Iraq, which can have implications toward tropical bed bug and management strategies.

Phylogenetic relationship of subterranean termite Coptotermes gestroi (Blattodea: Rhinotermitidae) inhabiting urban and natural habitats.

Coptotermes termites were collected from forestry habitats at University Sains Malaysia, Penang, while urban samples were collected from residentials from Penang and Kedah, Malaysia. Mitochondrial DNA markers, Cytochrome Oxidase 1 (CO1), and 16S ribosomal RNA (16S rRNA) genes were amplified and sequenced to confirm the species of the termite samples as Coptotermes gestroi. Through Blastn, all 25 CO1 and 16S rRNA sequences, respectively from urban and natural habitats were found to be 99.54-100.00 % similar to C. gestroi reference sequences from previous studies in Peninsular Malaysia. The phylogenetic trees constructed using Neighboring-joining (NJ) and Maximum Likelihood (ML) methods resulted in CO1 sequences clustering in two clades and 16S rRNA sequences clustering in a single clade. The overall mean distance was low for the C. gestroi populations from natural habitats and urban settings (FST = 0.004). Analysis of natural habitat populations using CO1 sequences revealed two haplotypes within the population, with a haplotype diversity (Hd) of 0.045 ± 0.005, while the urban population shared a common haplotype with the natural habitat populations and there was no haplotype diversity recorded between the populations. Urban and natural habitats included only one haplotype for 16S rRNA sequences, indicating a lack of nucleotide diversity. Based on the findings, a non-significant difference between the natural habitat and urban population suggests C. gestroi inhabiting both regions likely originated from a similar source and underwent population homogeneity in different settings facilitated by anthropogenic dispersal.

Public Awareness, Perception, and Knowledge of Bed Bug Infestation Prevalence in Iraq.

Background: Bed bugs are blood-feeding insects and are an important urban pest. Bed bugs are nocturnal insects and hide in cracks in walls and beds during the day. The study aims to: (1) determine the bed bugs species that infest Iraq, their infestation source, and their distribution; (2) determine the level of awareness and concern regarding bed bugs among the Iraqi community. Methods: Between 2020 and 2021, a survey of bed bug infestation dynamics was conducted in 18 infested sites located in major cities across eight governorates. The 23-item online survey was distributed over social media to Iraqi citizens between June and July 2022 to survey on their familiarity with bed bug habitat, medical significance, transmission, prevention, control measures, and concerns. Results: There were a total of 1104 bed bugs collected. Based on the morphological characteristics, bed bugs collected from eight Iraqi governorates are identified as Cimex hemipterus. Besides, a high rate of bed bug infestation was observed in workers' dormitories. The online questionnaire was answered by 1843 respondents and based on the feedback, most respondents (55.3%) have no awareness of bed bug infestations, while around 43.8% are somewhat concerned about bed bug infestations in Iraq. Conclusion: Only tropical bed bugs, C. hemipterus were found in all sampled sites. Bed bug infestations are mainly caused by migrant workers and the reuse of second-hand furniture and clothing. The results suggest that the Iraqi government should organize more proper demonstrations on bed bug awareness for the public.