Waste from non-degradable packaging materials poses a serious environmental risk and has led to interest in developing sustainable bio-based packaging materials. Sustainable packaging materials have been made from diverse naturally derived materials such as bamboo, sugarcane, and corn starch. In this study, we made a sustainable packaging film using chitosan extracted from the biomass of yellow mealworm (Tenebrio molitor) shell waste. The extracted chitosan was used to create films, cross-linked with citric acid (CA) and with the addition of glycerol to impart flexibility, using the solvent casting method. The successful cross-linking was evaluated using Fourier-Transform Infrared (FTIR) analysis. The CA cross-linked mealworm chitosan (CAMC) films exhibited improved water resistance with moisture content reduced from 19.9 to 14.5%. Improved barrier properties were also noted, with a 28.7% and 10.2% decrease in vapor permeability and vapor transmission rate, respectively. Bananas were selected for food preservation, and significant changes were observed over a duration of 10 days. Compared to the control sample, bananas packaged in CAMC pouches exhibited a lesser loss in weight because of excellent barrier properties against water vapor. Moreover, the quality and texture of bananas packaged in CAMC pouch remained intact over the duration of the experiment. This indicates that adding citric acid and glycerol to the chitosan structure holds promise for effective food wrapping and contributes to the enhancement of banana shelf life. Through this study, we concluded that chitosan film derived from mealworm biomass has potential as a valuable resource for sustainable packaging solutions, promoting the adoption of environmentally friendly practices in the food industry.

Depression is a common mental health disorder and a leading contributor to mortality and morbidity. Despite several advancements, the current screening methods have limitations in enabling the robust and automated detection of depression, thereby hindering early diagnosis and timely intervention. This study aimed to develop explainable artificial intelligence (AI) models to predict depression using polysomnographic phenotype data, ensuring high predictive performance while providing clear insights into the importance of features influencing the risk of depression. Advanced machine learning algorithms such as random forest, extreme gradient boosting, categorical boosting, and light gradient boosting machines were employed to train and validate the predictive AI models. Phenotype data from subjective health questionnaires, clinical assessments, and demographic factors were analyzed. The explainable AI models identified the important features, and their performance was evaluated using cross-validation. The study population, comprising 114 control participants and 39 individuals with depression, was stratified based on validated depression-scoring methods. The proposed explainable AI models achieved an F1-score of 85%, verifying their high reliability in predicting depression. Key features influencing the risk of depression, such as anxiety disorders, sleep efficiency, and demographic factors, offer actionable insights for clinical practice, highlighting the transparency of these models. This study proposed and developed explainable AI models based on polysomnographic phenotype data for the automated detection of depression and verified that these models help improve mental health diagnostics, enabling timely interventions.