Search

Defect detection is an important step in industrial production of monocrystalline silicon. Through the study of deep learning, this work proposes a framework for classifying monocrystalline silicon wafer defects using deep transfer learning (DTL). An existing pre-trained deep learning model was used as the starting point for building a new model. We studied the use of DTL and the potential adaptation of MobileNetV2 that was pre-trained using ImageNet for extracting monocrystalline silicon wafer defect features. This has led to speeding up the training process and to improving performance of the DTL-MobileNetV2 model in detecting and classifying six types of monocrystalline silicon wafer defects (crack, double contrast, hole, microcrack, saw-mark and stain). The process of training the DTL-MobileNetV2 model was optimized by relying on the dense block layer and global average pooling (GAP) method which had accelerated the convergence rate and improved generalization of the classification network. The monocrystalline silicon wafer defect classification technique relying on the DTL-MobileNetV2 model achieved the accuracy rate of 98.99% when evaluated against the testing set. This shows that DTL is an effective way of detecting different types of defects in monocrystalline silicon wafers, thus being suitable for minimizing misclassification and maximizing the overall production capacities.

Electromyography (EMG) signals are muscles signals that enable the identification of human movements without the need of complex human kinematics calculations. Researchers prefer EMG signals as input signals to control prosthetic arms and exoskeleton robots. However, the proper algorithm to classify human movements from raw EMG signals has been an interesting and challenging topic to researchers. Various studies have been carried out to produce EMG-based human movement classification that gives high accuracy and high reliability. In this paper, the methods used in EMG signal acquisition and processing are reviewed. The different types of feature extraction techniques preferred by researchers are also discussed, including some combination and comparison of feature extraction techniques. This paper also reviews the different types of classifiers favored by researchers to recognize human movements based on EMG signals. The current applications of EMG signals are also reviewed.