The main objective of this study is to develop and evaluate an effective integrated learning approach for the automatic classification of Municipal Solid Waste using the TrashBox data set comprising of 17,785 images to enhance the sorting of recyclable waste materials, curb on the use of landfills and enhance the attainment of sustainable environmental practices. Firstly, four deep learning models-DenseNet161, ResNet152, and MobileNetV3 variants are explored to identify the most suitable feature extraction method. In feature selection phase, three metaheuristic algorithms-Whale Optimization Algorithm (WOA), Salp Swarm Algorithm (SSA), and Harris Hawk Optimization (HHO)-are applied to remove the concept of less important features and keep significant features. The selected features are then fed to machine learning classifiers- Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR) and K-Nearest Neighbor (KNN) algorithms- for final predictions. The variant DenseNet161-HHO-SVM performs better than other combinations in this study due to its highest accuracy and lowest execution time. This integrated approach also has better performance (97.45%) than previous state-of-the-art models on the same dataset while data processing and method integration phases make incredible impacts.

Rotating machines are crucial in industries for reliable system operation, but unexpected failures can result in significant financial losses and personnel damage. Hence, fault diagnosis is important. Among the common types of faults in rotating machines, imbalance, and misalignment are important types of faults in operation but are rarely studied. This research utilizes data from four distinct operating conditions: normal operation, imbalanced condition, imbalanced condition combined with horizontal misalignment, and imbalanced condition combined with vertical misalignment. This study proposed a method for fault diagnosis using Continuous Wavelet Transform (CWT) for extracting vibration signals into RGB (Red – Green - Blue) images and using Convolutional Neural Network (CNN) models for fault diagnosis. Additionally, Internet of Things (IoT) integration is implemented using the Message Queuing Telemetry Transport (MQTT) protocol, enabling the update of fault status to the cloud for efficient monitoring. A mobile application provides an intuitive platform for visualizing and interacting with fault data. Moreover, several machine learning (ML) models are also utilized for comparison with the proposed method such as Random Forest (RF), Multilayer Perceptron (MLP), and Xtreme Gradient Boosting (XGBoost). The results indicate that CNN yields an overall accuracy of 93.27% compared to other ML methods.

Zero Re-Burn-In methodology presented in this paper is based on statistical analysis of the historical manufacturing data on burn-in (BI) and re-burn-in (REBI) tests employed in semiconductor devices manufacturing. The goal is to reduce (or, if possible, to eliminate) REBI test so to lower the associated manufacturing cost and time while preserving the required low failure rate of the manufactured devices. The statistical processing and analysis of the production data sets are performed while employing the JMP software. The re-search has led to development of a logistic regression model capable of predicting results of the REBI tests before actually sending integrated circuit (IC) lots for the re-testing.