ABSTRACT
The current knowledge on insects feeding on fruits is limited, and some of the scarce existing data on the fruit-associated insects are secluded within the host institutions. Consequently, their value is not fully realized. Moreover, in countries like Kenya, the integration of biocollections data within a digital framework has not been fully exploited. To address these gaps, this article presents a description of the development of a web-based platform for data sharing and integrating biodiversity historical data of wild plants, fruits, associated insects, and their molecular barcodes (WiPFIM) while leveraging data science technologies. The barcodes corresponding to the biocollections data were retrieved from BOLD database. The platform is an online resource about fruit-insect interactions that can be of interest to a worldwide community of users and can be useful in building innovative tools. The platform is accessible online at https://test-dmmg.icipe.org/wpfhi.
ABSTRACT
Crickets (Gryllus bimaculatus) produce sounds as a natural means to communicate and convey various behaviors and activities, including mating, feeding, aggression, distress, and more. These vocalizations are intricately linked to prevailing environmental conditions such as temperature and humidity. By accurately monitoring, identifying, and appropriately addressing these behaviors and activities, the farming and production of crickets can be enhanced. This research implemented a decision support system that leverages machine learning (ML) algorithms to decode and classify cricket songs, along with their associated key weather variables (temperature and humidity). Videos capturing cricket behavior and weather variables were recorded. From these videos, sound signals were extracted and classified such as calling, aggression, and courtship. Numerical and image features were extracted from the sound signals and combined with the weather variables. The extracted numerical features, i.e., Mel-Frequency Cepstral Coefficients (MFCC), Linear Frequency Cepstral Coefficients, and chroma, were used to train shallow (support vector machine, k-nearest neighbors, and random forest (RF)) ML algorithms. While image features, i.e., spectrograms, were used to train different state-of-the-art deep ML models, i,e., convolutional neural network architectures (ResNet152V2, VGG16, and EfficientNetB4). In the deep ML category, ResNet152V2 had the best accuracy of 99.42%. The RF algorithm had the best accuracy of 95.63% in the shallow ML category when trained with a combination of MFCC+chroma and after feature selection. In descending order of importance, the top 6 ranked features in the RF algorithm were, namely humidity, temperature, C#, mfcc11, mfcc10, and D. From the selected features, it is notable that temperature and humidity are necessary for growth and metabolic activities in insects. Moreover, the songs produced by certain cricket species naturally align to musical tones such as C# and D as ranked by the algorithm. Using this knowledge, a decision support system was built to guide farmers about the optimal temperature and humidity ranges and interpret the songs (calling, aggression, and courtship) in relation to weather variables. With this information, farmers can put in place suitable measures such as temperature regulation, humidity control, addressing aggressors, and other relevant interventions to minimize or eliminate losses and enhance cricket production.
ABSTRACT
As the world population continues to grow, there is a need to come up with alternative sources of feed and food to combat the existing challenge of food insecurity across the globe. The use of insects, particularly the black soldier fly (BSF) Hermetia illucens (L.) (Diptera: Stratiomydiae), as a source of feed stands out due to its sustainability and reliability. Black soldier fly larvae (BSFL) have the ability to convert organic substrates to high-quality biomass rich in protein for animal feed. They can also produce biodiesel and bioplastic and have high biotechnological and medical potential. However, current BSFL production is low to meet the industry's needs. This study used machine learning modeling approaches to discern optimal rearing conditions for improved BSF farming. The input variables studied include the cycle time in each rearing phase (i.e., the rearing period in each phase), feed formulation type, length of the beds (i.e, rearing platforms) at each phase, amount of young larvae added in the first phase, purity score (i.e, percentage of BSFL after separating from the substrate), feed depth, and the feeding rate. The output/target variable was the mass of wet larvae harvested (kg per meter) at the end of the rearing cycle. This data was trained on supervised machine learning algorithms. From the trained models, the random forest regressor presented the best root mean squared error (RMSE) of 2.91 and an R-squared value of 80.9%, implying that the model can be used to effectively monitor and predict the expected weight of BSFL to be harvested at the end of the rearing process. The results established that the top five ranked important features that inform optimal production are the length of the beds, feed formulation used, the average number of young larvae loaded in each bed, feed depth, and cycle time. Therefore, in that priority, it is expected that tuning the mentioned parameters to fall within the required levels would result in an increased mass of BSFL harvest. These data science and machine learning techniques can be adopted to understand rearing conditions and optimize the production/farming of BSF as a source of feed for animals e.g., fish, pigs, poultry, etc. A high production of these animals guarantees more food for humans, thus reducing food insecurity.
