MyMedR

Displaying all 6 publications

Abstract:

Sort:

Development of a deep learning model from breeding substrate images: a novel method for estimating the abundance of house fly (Musca domestica L.) larvae

Ong SQ, Ahmad H, Majid AHA

Pest Manag Sci, 2021 Dec;77(12):5347-5355.
PMID: 34309999 DOI: 10.1002/ps.6573

BACKGROUND: The application of computer vision and deep learning to pest monitoring has recently received much attention. Although several studies have demonstrated the application of object detection to the number of pests on a substrate, for house flies (Musca domestica L.), in which the larvae were aggregated and overlapped together, the object detection technique was difficult to implement. We demonstrate a novel method for estimating larval abundance by using computer vision on larval breeding substrate, in which the reflective color and topography are affected by the size of the population.
RESULTS: We demonstrate a method using a web-based tool to construct a deep learning model and later export the model for deployment. We train the model by using breeding substrate images with different spectra of illumination on known densities of larvae and evaluate the training model in both the test set and field-collected samples. In general, the model was able to predict the larval abundance by the laboratory-prepared breeding substrate with 87.56% to 94.10% accuracy, precision, recall, and F-score on the unseen test set, and white and green illumination performed significantly higher compared to other illuminations. For field samples, the model was able to obtain at least 70% correct predictions by using white and infrared illumination.
CONCLUSION: Larval abundance can be monitored with computer vision and deep learning, and the monitoring can be improved by using more biochemistry parameters as the predictors and examples of field samples included building a more robust model. © 2021 Society of Chemical Industry.
Fulltext Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

Ong SQ, Ahmad H, Nair G, Isawasan P, Majid AHA

Sci Rep, 2021 05 10;11(1):9908.
PMID: 33972645 DOI: 10.1038/s41598-021-89365-3

Classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.
Sweet waste extract uptake by a mosquito vector: Survival, biting, fecundity responses, and potential epidemiological significance

Dieng H, Satho T, Abang F, Meli NKKB, Ghani IA, Nolasco-Hipolito C, et al.

Acta Trop, 2017 May;169:84-92.
PMID: 28174057 DOI: 10.1016/j.actatropica.2017.01.022

In nature, adult mosquitoes typically utilize nectar as their main energy source, but they can switch to other as yet unidentified sugary fluids. Contemporary lifestyles, with their associated unwillingness to consume leftovers and improper disposal of waste, have resulted in the disposal of huge amounts of waste into the environment. Such refuse often contains unfinished food items, many of which contain sugar and some of which can collect water from rain and generate juices. Despite evidence that mosquitoes can feed on sugar-rich suspensions, semi-liquids, and decaying fruits, which can be abundant in garbage sites, the impacts of sweet waste fluids on dengue vectors are unknown. Here, we investigated the effects of extracts from some familiar sweet home waste items on key components of vectorial capacity of Aedes aegypti. Adult mosquitoes were fed one of five diets in this study: water (WAT); sucrose (SUG); bakery product (remnant of chocolate cake, BAK); dairy product (yogurt, YOG); and fruit (banana (BAN). Differences in survival, response time to host, and egg production were examined between groups. For both males and females, maintenance on BAK extract resulted in marked survival levels that were similar to those seen with SUG. Sweet waste extracts provided better substrates for survival compared to water, but this superiority was mostly seen with BAK. Females maintained on BAK, YOG, and BAN exhibited shorter response times to a host compared to their counterparts maintained on SUG. The levels of egg production were equivalent in waste extract- and SUG-fed females. The findings presented here illustrate the potential of sweet waste-derived fluids to contribute to the vectorial capacity of dengue vectors and suggest the necessity of readdressing the issue of waste disposal, especially that of unfinished sweet foods. Such approaches can be particularly relevant in dengue endemic areas where rainfall is frequent and waste collection infrequent.
Presence of a predator image in potential breeding sites and oviposition responses of a dengue vector

Dieng H, Satho T, Suradi NFB, Hakim H, Abang F, Aliasan NE, et al.

Acta Trop, 2017 Dec;176:446-454.
PMID: 28865898 DOI: 10.1016/j.actatropica.2017.08.033

In dengue vector control, attempts to minimize or replace the use of pesticides have mostly involved use of predators, but success has been severely impeded by difficulties associated with financial and environmental costs, predator mass production, and persistence in target habitats. Visual deterrents have been used successfully to control animal pests, in some cases in an effort to replace pesticide use. Despite evidence that visual signals are crucial in site choice for egg deposition by dengue vectors, and that female mosquitoes respond to artificial predation, the role of predator intimidation as it affects the oviposition behavior of dengue vectors remains largely unexplored. Here, we examined the oviposition responses of Aedes aegypti exposed to various mosquito predator pictures. Gravid females were presented with equal opportunities to oviposit in two cups with predator images [Toxorhynchites splendens-TXI, Goldfish (Carassius auratus)-small (SFI) and large (LFI) and Tx. splendens+Goldfish-TXFI] and two others without pictures. Differences in egg deposition were examined between sites with and without these images. When given a chance to oviposit in cups with and without TXI, Ae. aegypti females were similarly attracted to both sites. When provided an opportunity to oviposit in cups displaying pictures of fish (SFI or LFI) and blank cups, egg deposition rates were much lower in the fish picture sites. Females showed a preference for blank cups over TXFI for egg deposition. They also equally avoided cups with pictures of fish, regardless of the size of the picture. Our results indicate that the presence of images of goldfish and their association with Tx. larvae significantly reduced egg deposition by Ae. aegypti, and this was not the case with the predatory larvae alone. The observations that the images of natural predators can repel gravid females of a dengue vector provide novel possibilities to develop effective and inexpensive alternative tools to harmful insecticides.
Anti-oviposition activities of used sock media against a dengue vector: prospects of eco-friendly control and solutions to pollution

Dieng H, Satho T, Abang F, Miake F, Ghani IA, Latip NA, et al.

Environ Sci Pollut Res Int, 2017 Sep;24(26):21375-21385.
PMID: 28744676 DOI: 10.1007/s11356-017-9624-y

Yearly, huge amounts of sock refuse are discarded into the environment. Socks contain many molecules, and worn ones, which are rich in smell-causing bacteria, have a strong influence on animals' behaviors. But the impacts of sock odor on the oviposition behavior of dengue vectors are unknown. We assessed whether Aedes albopictus changes its oviposition activity in response to the presence of used socks extract (USEx) in potential breeding grounds, using choice and no-choice bioassays (NCB). When furnished even chances to oviposit in two sites holding USEx and two others containing water (control), Ae. albopictus deposited significantly less eggs in USEx than in water sites. A similar pattern of oviposition preference was also observed when there were more oviposition options in water. When there were greater oviposition opportunities in USEx sites, Ae. albopictus oviposited preferentially in water. Females laid significantly more eggs during the NCB involving water than USEx. Also, significantly more mature eggs were retained by females in the NCB with USEx than in that with water. These observations strongly suggest the presence of molecules with either repellent or deterrent activities against Ae. albopictus females and provide an impetus to advocate the integration of used socks in dengue control programs. Such applications could be a realistic end-of-life recourse to reroute this waste from landfills.
Fulltext Courtship activity, copulation & insemination success in a mosquito vector fed a herbal aphrodisiac: Implications for sterile insect technology

Dieng H, Satho T, Abang F, Miake F, Azman FAB, Latip NA, et al.

Indian J Med Res, 2018 Sep;148(3):334-340.
PMID: 30425225 DOI: 10.4103/ijmr.IJMR_1604_16

Background & objectives: In sterile insect technology (SIT), mating competitiveness is a pre-condition for the reduction of target pest populations and a crucial parameter for judging efficacy. Still, current SIT trials are being hindered by decreased effectiveness due to reduced sexual performance of released males. Here, we explored the possible role of a herbal aphrodisiac in boosting the mating activity of Aedes aegypti.
Methods: Males were fed one of two diets in this study: experimental extract of Eurycoma longifolia (MSAs) and sugar only (MSOs). Differences in life span, courtship latency, copulation activity and mating success were examined between the two groups.
Results: No deaths occurred among MSA and MSO males. Life span of MSOs was similar to that of MSAs. The courtship latency of MSAs was shorter than that of MSOs (P<0.01). MSAs had greater copulation success than MSOs (P<0.001). In all female treatments, MSAs mated more than MSOs, but the differences in rate were significant only in the highest female density (P<0.05). In MSAs, mating success varied significantly with female density (P<0.01), with the 20-female group (P<0.01) having the lowest rate. Single MSA had better mating success at the two lowest female densities. In MSOs, there were no significant differences in mating success rate between the different female densities.
Interpretation & conclusions: Our results suggested that the herbal aphrodisiac, E. longifolia, stimulated the sexual activity of Ae. aegypti and may be useful for improving the mating competitiveness of sterile males, thus improving SIT programmes.