A Case Study of Quantizing Convolutional Neural Networks for Fast Disease Diagnosis on Portable Medical Devices

Automated Machine Learning System for Defect Detection on Cylindrical Metal Surfaces

Metal workpieces are indispensable in the manufacturing industry. Surface defects affect the appearance and efficiency of a workpiece and reduce the safety of manufactured products. Therefore, products must be inspected for surface defects, such as scratches, dirt, and chips. The traditional manual inspection method is time-consuming and labor-intensive, and human error is unavoidable when thousands of products require inspection. Therefore, an automated optical inspection method is often adopted. Traditional automated optical inspection algorithms are insufficient in the detection of defects on metal surfaces, but a convolutional neural network (CNN) may aid in the inspection. However, considerable time is required to select the optimal hyperparameters for a CNN through training and testing. First, we compared the ability of three CNNs, namely VGG-16, ResNet-50, and MobileNet v1, to detect defects on metal surfaces. These models were hypothetically implemented for transfer learning (TL). However, in deploying TL, the phenomenon of apparent convergence in prediction accuracy, followed by divergence in validation accuracy, may create a problem when the image pattern is not known in advance. Second, our developed automated machine-learning (AutoML) model was trained through a random search with the core layers of the network architecture of the three TL models. We developed a retraining criterion for scenarios in which the model exhibited poor training results such that a new neural network architecture and new hyperparameters could be selected for retraining when the defect accuracy criterion in the first TL was not met. Third, we used AutoKeras to execute AutoML and identify a model suitable for a metal-surface-defect dataset. The performance of TL, AutoKeras, and our designed AutoML model was compared. The results of this study were obtained using a small number of metal defect samples. Based on TL, the detection accuracy of VGG-16, ResNet-50, and MobileNet v1 was 91%, 59.00%, and 50%, respectively. Moreover, the AutoKeras model exhibited the highest accuracy of 99.83%. The accuracy of the self-designed AutoML model reached 95.50% when using a core layer module, obtained by combining the modules of VGG-16, ResNet-50, and MobileNet v1. The designed AutoML model effectively and accurately recognized defective and low-quality samples despite low training costs. The defect accuracy of the developed model was close to that of the existing AutoKeras model and thus can contribute to the development of new diagnostic technologies for smart manufacturing.

Enabling Intelligent IoTs for Histopathology Image Analysis Using Convolutional Neural Networks

Medical imaging is an essential data source that has been leveraged worldwide in healthcare systems. In pathology, histopathology images are used for cancer diagnosis, whereas these images are very complex and their analyses by pathologists require large amounts of time and effort. On the other hand, although convolutional neural networks (CNNs) have produced near-human results in image processing tasks, their processing time is becoming longer and they need higher computational power. In this paper, we implement a quantized ResNet model on two histopathology image datasets to optimize the inference power consumption. We analyze classification accuracy, energy estimation, and hardware utilization metrics to evaluate our method. First, the original RGB-colored images are utilized for the training phase, and then compression methods such as channel reduction and sparsity are applied. Our results show an accuracy increase of 6% from RGB on 32-bit (baseline) to the optimized representation of sparsity on RGB with a lower bit-width, i.e., <8:8>. For energy estimation on the used CNN model, we found that the energy used in RGB color mode with 32-bit is considerably higher than the other lower bit-width and compressed color modes. Moreover, we show that lower bit-width implementations yield higher resource utilization and a lower memory bottleneck ratio. This work is suitable for inference on energy-limited devices, which are increasingly being used in the Internet of Things (IoT) systems that facilitate healthcare systems.

HybridGBN-SR: A Deep 3D/2D Genome Graph-Based Network for Hyperspectral Image Classification

The successful application of deep learning approaches in remote sensing image classification requires large hyperspectral image (HSI) datasets to learn discriminative spectral–spatial features simultaneously. To date, the HSI datasets available for image classification are relatively small to train deep learning methods. This study proposes a deep 3D/2D genome graph-based network (abbreviated as HybridGBN-SR) that is computationally efficient and not prone to overfitting even with extremely few training sample data. At the feature extraction level, the HybridGBN-SR utilizes the three-dimensional (3D) and two-dimensional (2D) Genoblocks trained using very few samples while improving HSI classification accuracy. The design of a Genoblock is based on a biological genome graph. From the experimental results, the study shows that our model achieves better classification accuracy than the compared state-of-the-art methods over the three publicly available HSI benchmarking datasets such as the Indian Pines (IP), the University of Pavia (UP), and the Salinas Scene (SA). For instance, using only 5% labeled data for training in IP, and 1% in UP and SA, the overall classification accuracy of the proposed HybridGBN-SR is 97.42%, 97.85%, and 99.34%, respectively, which is better than the compared state-of-the-art methods.