Electromyogram Based Personal Recognition Using Attention Mechanism for IoT Security

As Internet of Things(IoT)technology develops,integrating network functions into diverse equipment introduces new challenges,particularly in dealing with counterfeit issues.Over the past few decades,research efforts have focused on leveraging electromyogram(EMG)for personal recognition,aiming to address security concerns.However,obtaining consistent EMG signals from the same individual is inherently challenging,resulting in data irregularity issues and consequently decreasing the accuracy of personal recognition.Notably,conventional studies in EMG-based personal recognition have overlooked the issue of data irregularities.This paper proposes an innovative approach to personal recognition that combines a siamese fusion network with an auxiliary classifier,effectively mitigating the impact of data irregularities in EMG-based recognition.The proposed method employs empirical mode decomposition(EMD)to extract distinctive features.The model comprises two sub-networks designed to follow the siamese network architecture and a decision network integrated with the novel auxiliary classifier,specifically designed to address data irregularities.The two sub-networks sharing a weight calculate the compatibility function.The auxiliary classifier collaborates with a neural network to implement an attention mechanism.The attention mechanism using the auxiliary classifier solves the data irregularity problem by improving the importance of the EMG gesture section.Experimental results validated the efficacy of the proposed personal recognition method,achieving a remarkable 94.35%accuracy involving 100 subjects from the multisession CU_sEMG database(DB).This performance outperforms the existing approaches by 3%,employing auxiliary classifiers.Furthermore,an additional experiment yielded an improvement of over 0.85%of Ninapro DB,3%of CU_sEMG DB compared to the existing EMG-based recognition methods.Consequently,the proposed personal recognition using EMG proves to secure IoT devices,offering robustness against data irregularities.

Fault Diagnosis of Power Transformer Based on Improved ACGAN Under Imbalanced Data

The imbalance of dissolved gas analysis(DGA)data will lead to over-fitting,weak generalization and poor recognition performance for fault diagnosis models based on deep learning.To handle this problem,a novel transformer fault diagnosis method based on improved auxiliary classifier generative adversarial network(ACGAN)under imbalanced data is proposed in this paper,which meets both the requirements of balancing DGA data and supplying accurate diagnosis results.The generator combines one-dimensional convolutional neural networks(1D-CNN)and long short-term memories(LSTM),which can deeply extract the features from DGA samples and be greatly beneficial to ACGAN’s data balancing and fault diagnosis.The discriminator adopts multilayer perceptron networks(MLP),which prevents the discriminator from losing important features of DGA data when the network is too complex and the number of layers is too large.The experimental results suggest that the presented approach can effectively improve the adverse effects of DGA data imbalance on the deep learning models,enhance fault diagnosis performance and supply desirable diagnosis accuracy up to 99.46%.Furthermore,the comparison results indicate the fault diagnosis performance of the proposed approach is superior to that of other conventional methods.Therefore,the method presented in this study has excellent and reliable fault diagnosis performance for various unbalanced datasets.In addition,the proposed approach can also solve the problems of insufficient and imbalanced fault data in other practical application fields.

COVID-19 Automatic Detection Using Deep Learning

The novel coronavirus disease 2019(COVID-19)is a pandemic disease that is currently affecting over 200 countries around the world and impacting billions of people.The first step to mitigate and control its spread is to identify and isolate the infected people.But,because of the lack of reverse transcription polymerase chain reaction(RT-CPR)tests,it is important to discover suspected COVID-19 cases as early as possible,such as by scan analysis and chest X-ray by radiologists.However,chest X-ray analysis is relatively time-consuming since it requires more than 15 minutes per case.In this paper,an automated novel detection model of COVID-19 cases is proposed to perform real-time detection of COVID-19 cases.The proposed model consists of three main stages:image segmentation using Harris Hawks optimizer,synthetic image augmentation using an enhanced Wasserstein And Auxiliary Classifier Generative Adversarial Network,and image classification using Conventional Neural Network.Raw chest X-ray images datasets are used to train and test the proposed model.Experiments demonstrate that the proposed model is very efficient in the automatic detection of COVID-19 positive cases.It achieved 99.4%accuracy,99.15%precision,99.35%recall,99.25%F-measure,and 98.5%specificity.