Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

Remote Sensing Image Land Classification Based on Deep Learning

Aiming at the problems of high-resolution remote sensing images with many features and low classification accuracy using a single feature description, a remote sensing image land classification model based on deep learning from the perspective of ecological resource utilization is proposed. Firstly, the remote sensing image obtained by Gaofen-1 satellite is preprocessed, including multispectral data and panchromatic data. Then, the color, texture, shape, and local features are extracted from the image data, and the feature-level image fusion method is used to associate these features to realize the fusion of remote sensing image features. Finally, the fused image features are input into the trained depth belief network (DBN) for processing, and the land type is obtained by the Softmax classifier. Based on the Keras and TensorFlow platform, the experimental analysis of the proposed model shows that it can clearly classify all land types, and the overall accuracy, F1 value, and reasoning time of the classification results are 97.86%, 87.25%, and 128 ms, respectively, which are better than other comparative models.

Optimization of an Intelligent Sorting and Recycling System for Solid Waste Based on Image Recognition Technology

In this paper, the technique of image recognition algorithm is used to conduct an in-depth study and analysis of the intelligent classification and recycling system of solid waste and to optimize the design of its system. The network structure and detection principle of the YOLO target detection algorithm based on convolutional neural nets are analysed, images of construction solid waste are collected as a dataset, and the image dataset is expanded using data enhancement techniques, and the target objects in the dataset are labelled and used to train their own YOLO detection models. To facilitate testing the images and to design a YOLO algorithm-based construction solid waste target detection system. Using the detection system for construction solid waste recognition, the YOLO model can accurately detect the location, class, and confidential information of the target object in the image. Image recognition is a technique to recognize images by capturing real-life images through devices and performing feature extraction, and this technique has been widely used since its inception. The deep learning-based classification algorithm for recyclable solid waste studied in this paper can classify solid waste efficiently and accurately, solving the problem that people do not know how to classify solid waste in daily life. The convolutional layer, pooling layer, and fully connected layer in a convolutional neural network are responsible for feature extraction, reducing the number of parameters, integrating features into high-level features, and finally classifying them by SoftMax classifier in turn. However, the actual situation is intricate and often the result is not obtained as envisioned, and the use of migration learning can be a good way to improve the overfitting phenomenon. In this paper, the combination of lazy optimizer and lookahead can improve the generalization ability and fitting speed as well as greatly improve the accuracy and stability. The experimental results are tested, and it is found that the solid waste classification accuracy can be as high as 95% when the VGG19 model is selected and the optimizer is combined.

An Early Breast Cancer Detection System Using Recurrent Neural Network (RNN) with Animal Migration Optimization (AMO) Based Classification Method

Breast cancer can be detected using early signs of it mammograms and digital mammography. For Computer Aided Detection (CAD), algorithms can be developed using this opportunities. Early detection is assisted by self-test and periodical check-ups and it can enhance the survival chance significantly. Due the need of breast cancer’s early detection and false diagnosis impact on patients, made researchers to investigate Deep Learning (DL) techniques for mammograms. So, it requires a non-invasive cancer detection system, which is highly effective, accurate, fast as well as robust. Proposed work has three steps, (i) Pre-processing, (ii) Segmentation, and (iii) Classification. Firstly, preprocessing stage removing noise from images by using mean and median filtering algorithms are used, while keeping its features intact for better understanding and recognition, then edge detection by using canny edge detector. It uses Gaussian filter for smoothening image. Gaussian smoothening is used for enhancing image analysis process quality, result in blurring of fine-scaled image edges. In the next stage, image representation is changed into something, which makes analyses process as a simple one. Foreground and background subtraction is used for accurate breast image detection in segmentation. After completion of segmentation stage, the remove unwanted image in input image dataset. Finally, a novel RNN forclassifying and detecting breast cancer using Auto Encoder (AE) based RNN for feature extraction by integrating Animal Migration Optimization (AMO) for tuning the parameters of RNN model, then softmax classifier use RNN algorithm. Experimental results are conducted using Mini-Mammographic (MIAS) dataset of breast cancer. The classifiers are measured through measures like precision, recall, f-measure and accuracy.

Mask detection as Covid combat using Transfer learning and Haar Cascade

The World is going through a pandemic due to the rapid transmission of COVID-19. According to the several guidelines issued by WHO (World Health Organization), wearing a mask is the most effective preventive measure in public/crowded places. We hope for the future social health and safety of the people around the world with this project. To detect the people who are not following the COVID-19 guidelines in public/crowded areas a convolutional neural network under the framework of the TensorFlow VGG-19 algorithm is proposed which has trained and tested a collection of more than 1350 images. One flat layer and two FC layers with reduced parameters are optimized from three FC layers. The 2-label softmax classifier replaced the softmax classification layer of the original model. Our experimental results show a training accuracy of 99.73% and an accuracy of 98.78% during testing. Keywords: Transfer learning, covid19, mask detection, artificial intelligence, coronavirus

GaitVision: Real-Time Extraction of Gait Parameters Using Residual Attention Network

Gait walking patterns are one of the key research topics in natural biometrics. The temporal information of the unique gait sequence of a person is preserved and used as a powerful data for access. Often there is a dive into the flexibility of gait sequence due to unstructured and unnecessary sequences that tail off the necessary sequence constraints. The authors in this work present a novel perspective, which extracts useful gait parameters regarded as independent frames and patterns. These patterns and parameters mark as unique signature for each subject in access authentication. This information extracted learns to identify the patterns associated to form a unique gait signature for each person based on their style, foot pressure, angle of walking, angle of bending, acceleration of walk, and step-by-step distance. These parameters form a unique pattern to plot under unique identity for access authorization. This sanitized data of patterns is further passed to a residual deep convolution network that automatically extracts the hierarchical features of gait pattern signatures. The end layer comprises of a Softmax classifier to classify the final prediction of the subject identity. This state-of-the-art work creates a gait-based access authentication that can be used in highly secured premises. This work was specially designed for Defence Department premises authentication. The authors have achieved an accuracy of 90 % ± 1.3 % in real time. This paper mainly focuses on the assessment of the crucial features of gait patterns and analysis of gait patterns research.

Deep Learning Technology in Pathological Image Analysis of Breast Tissue

To explore the application value of the multilevel pyramid convolutional neural network (MPCNN) model based on convolutional neural network (CNN) in breast histopathology image analysis, in this study, based on CNN algorithm and softmax classifier (SMC), a sparse autoencoder (SAE) is introduced to optimize it. The sliding window method is used to identify cells, and the CNN + SMC pathological image cell detection method is established. Furthermore, the local region active contour (LRAC) is introduced to optimize it and the LRAC fine segmentation model driven by local Gaussian distribution is established. On this basis, the sparse automatic encoder is further introduced to optimize it and the MPCNN model is established. The proposed algorithm is evaluated on the pathological image data set. The results showed that the Acc value, F value, and Re value of pathological cell detection of CNN + SMC algorithm were significantly higher than those of the other two algorithms ( P < 0.05). The Dice, OL, Sen, and Spe values of pathological image regional segmentation of CNN algorithm were significantly higher than those of the other two algorithms, and the difference was statistically significant ( P < 0.05). The accuracy, recall, and F-measure of the optimized CNN algorithm for detecting breast histopathological images were 85.25%, 89.27%, and 80.09%, respectively. In the two databases with segmentation standards, the segmentation accuracy of MPCNN is 55%, 73.1%, 78.8%, and 82.1%. In the deep convolution network model, the training time of the MPCNN algorithm is about 80 min. It shows that when the feature dimension is low, the feature map extracted by MPCNN is more effective than the traditional feature extraction method.

Neural Network for Intelligent and Efficient Volleyball Passing Training

Passing is a relatively basic technique in volleyball. In volleyball passing teaching, training the correct passing technique plays a very important role. The correct pass can not only accurately grasp the direction of the ball point and the drop point but also effectively connect the defense and the offense. In order to improve the efficiency and quality of volleyball passing training, improve the precise extraction of sport targets, reduce redundant feature information, and improve the generalization performance and nonlinear fitting capabilities of the algorithm, this paper studies volleyball based on the nested convolutional neural network model and passing training wrong movement detection method. The structure of the convolutional neural network is improved by nesting mlpconv layers, and the Gaussian mixture model is used to effectively and accurately extract the foreground objects in the video. The nested multilayer mlpconv layer automatically learns the deep-level features of the foreground target, and the generated feature map is vectorized and input to the Softmax classifier connected to the fully connected layer for passing wrong behavior detection in volleyball training. Based on the detection of nearly 1,000 athletes’ action datasets, the simulation experiment results show that the algorithm reduces the acquisition of redundant information and shortens the calculation time and learning time of the algorithm, and the improved convolutional neural network has generalization performance and nonlinearity. The fitting ability has been improved, and the detection of abnormal volleyball passing behaviors has achieved a higher accuracy rate.

Deep Learnt Features and Machine Learning Classifier for Texture classification

Texture classification plays a vital role in the emerging research field of image classification. This paper approaches the texture classification problem using significant features extracted from pre-trained Convolutional Neural Network (CNN) like Alexnet, VGG16, Resnet18, Googlenet, MobilenetV2, and Darknet19. These features are classified by machine learning classifiers such as Support Vector Machine (SVM), Ensemble, K Nearest Neighbour (KNN), Naïve Bayes (NB), Decision Tree (DT), and Discriminant Analysis (DA). The performance of the work is evaluated with the texture databases namely KTH-TIPS, FMD, UMD-HR, and DTD. Among these CNN features derived from VGG16 classify by SVM provides better classification accuracy rather than using VGG16 with a softmax classifier.

Automatic Depression Detection of Mobile-Based Text-dependent Speech Signals Using a Deep CNN Approach: A Prospective Cohort Study (Preprint)

BACKGROUND In the future, automatic diagnosis of depression based on speech could complement mental health treatment methods. Previous studies have reported that acoustic properties can be used to recognize depression, including mel-frequency cepstrum coefficients (MFCCs) applied to speech recognition. However, there are few studies in which these characteristics allow differential diagnosis of patients with depressive disorder. OBJECTIVE This paper proposes a framework to help with automatic depression detection in a mobile environment where speech data can be easily obtained. Specifically, we recorded speech data by performing a predefined text-based speech reading task on mobile, investigated whether the recorded data can screen for depression, and proposed a deep learning-based framework that helps in automatic depression detection. METHODS We recruited 125 patients who met the criteria for major depressive disorder (MDD) and 113 healthy controls without current or past mental illness. Participants' voices were recorded on smart-phone while performing the task of reading predefined text-based sentences. We investigated the differences in the voice characteristics between MDD and healthy control groups using statistical analysis. We also investigated the possibility of automatic depression detection using the proposed log mel (LM) spectrogram-based deep Convolutional Neural Networks (CNN) architectures and machine learning models. RESULTS We found that there were statistically discernable differences between MDD and control groups in the MFCC features extracted through the utterances of reading predefined text-based sentences. Moreover, the best accuracies achieved with LM spectrogram-based CNN and softmax classifier on the speech data are 80.00% accuracy. Our results show that the deep-learned acoustic characteristics lead to better performances of classifiers than those using the conventional approach. CONCLUSIONS Conclusions: In conclusion, this study suggests that the analysis of speech data recorded while reading text-dependent sentences could help predict depression status automatically by capturing characteristics of depression. Our method can contribute to an approach that allows individuals to easily and automatically assess their depressive state anytime, anywhere, without the need for experts to conduct psychological assessments on-site.