Search

Classifying the images that portray the Human Epithelial cells of type 2 (HEp-2) represents one of the most important steps in the diagnosis procedure of autoimmune diseases. Performing this classification manually represents an extremely complicated task due to the heterogeneity of these cellular images. Hence, an automated classification scheme appears to be necessary. However, the majority of the available methods prefer to utilize the supervised learning approach for this problem. The need for thousands of images labelled manually can represent a difficulty with this approach. The first contribution of this work is to demonstrate that classifying HEp-2 cell images can also be done using the unsupervised learning paradigm. Unlike the majority of the existing methods, we propose here a deep learning scheme that performs both the feature extraction and the cells&rsquo, discrimination through an end-to-end unsupervised paradigm. We propose the use of a deep convolutional autoencoder (DCAE) that performs feature extraction via an encoding&ndash, decoding scheme. At the same time, we embed in the network a clustering layer whose purpose is to automatically discriminate, during the feature learning process, the latent representations produced by the DCAE. Furthermore, we investigate how the quality of the network&rsquo, s reconstruction can affect the quality of the produced representations. We have investigated the effectiveness of our method on some benchmark datasets and we demonstrate here that the unsupervised learning, when done properly, performs at the same level as the actual supervised learning-based state-of-the-art methods in terms of accuracy.

Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines. Generally, it is very difficult to diagnose a machine fault by conventional methods based on mathematical models because of the complexity of the real world systems and the obvious existence of nonlinear factors. This study develops an automatic machine fault diagnosis system that uses pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The sounds emitted by the operating machine, a drill in this case, are obtained and analyzed for the different operating conditions. The specific machine conditions considered in this research are the undamaged drill and the defected drill with wear. Principal component analysis is first used to reduce the dimensionality of the original sound data. The first principal components are then used as the inputs of a neural network based classifier to separate normal and defected drill sound data. The results show that the proposed PCA-ANN method can be used for the sounds based automated diagnosis system.

The complete analysis of the images representing the human epithelial cells of type 2, commonly referred to as HEp-2 cells, is one of the most important tasks in the diagnosis procedure of various autoimmune diseases. The problem of the automatic classification of these images has been widely discussed since the unfolding of deep learning-based methods. Certain datasets of the HEp-2 cell images exhibit an extreme complexity due to their significant heterogeneity. We propose in this work a method that tackles specifically the problem related to this disparity. A dynamic learning process is conducted with different networks taking different input variations in parallel. In order to emphasize the localized changes in intensity, the discrete wavelet transform is used to produce different versions of the input image. The approximation and detail coefficients are fed to four different deep networks in a parallel learning paradigm in order to efficiently homogenize the features extracted from the images that have different intensity levels. The feature maps from these different networks are then concatenated and passed to the classification layers to produce the final type of the cellular image. The proposed method was tested on a public dataset that comprises images from two intensity levels. The significant heterogeneity of this dataset limits the discrimination results of some of the state-of-the-art deep learning-based methods. We have conducted a comparative study with these methods in order to demonstrate how the dynamic learning proposed in this work manages to significantly minimize this heterogeneity related problem, thus boosting the discrimination results.

In computer-aided diagnosis (CAD) systems, the automatic classification of the different types of the human epithelial type 2 (HEp-2) cells represents one of the critical steps in the diagnosis procedure of autoimmune diseases. Most of the methods prefer to tackle this task using the supervised learning paradigm. However, the necessity of having thousands of manually annotated examples constitutes a serious concern for the state-of-the-art HEp-2 cells classification methods. We present in this work a method that uses active learning in order to minimize the necessity of annotating the majority of the examples in the dataset. For this purpose, we use cross-modal transfer learning coupled with parallel deep residual networks. First, the parallel networks, which take simultaneously different wavelet coefficients as inputs, are trained in a fully supervised way by using a very small and already annotated dataset. Then, the trained networks are utilized on the targeted dataset, which is quite larger compared to the first one, using active learning techniques in order to only select the images that really need to be annotated among all the examples. The obtained results show that active learning, when mixed with an efficient transfer learning technique, can allow one to achieve a quite pleasant discrimination performance with only a few annotated examples in hands. This will help in building CAD systems by simplifying the burdensome task of labeling images while maintaining a similar performance with the state-of-the-art methods.

The discussion in this paper aims to introduce an approach to detect drowsiness with Android based smartphones using the OpenCV platform tools. OpenCV for Android actually provides powerful tools for real-time body’s parts tracking. We discuss here about the maximization of the accuracy in real-time eye tracking. Then we try to develop an approach for detecting eye blink by analyzing the structure and color variations of human eyes. Finally, we introduce a time variable to capture drowsiness.

The automated and accurate classification of the images portraying the Human Epithelial cells of type 2 (HEp-2) represents one of the most important steps in the diagnosis procedure of many autoimmune diseases. The extreme intra-class variations of the HEp-2 cell images datasets drastically complicates the classification task. We propose in this work a classification framework that, unlike most of the state-of-the-art methods, uses a deep learning-based feature extraction method in a strictly unsupervised way. We propose a deep learning-based hybrid feature learning with two levels of deep convolutional autoencoders. The first level takes the original cell images as the inputs and learns to reconstruct them, in order to capture the features related to the global shape of the cells, and the second network takes the gradients of the images, in order to encode the localized changes in intensity (gray variations) that characterize each cell type. A final feature vector is constructed by combining the latent representations extracted from the two networks, giving a highly discriminative feature representation. The created features will be fed to a nonlinear classifier whose output will represent the type of the cell image. We have tested the discriminability of the proposed features on two of the most popular HEp-2 cell classification datasets, the SNPHEp-2 and ICPR 2016 datasets. The results show that the proposed features manage to capture the distinctive characteristics of the different cell types while performing at least as well as the actual deep learning-based state-of-the-art methods in terms of discrimination.

Cell counting remains a challenging task especially because of the extreme variation of the size and shape of the microscopy data. Conventional counting methods are mostly based on the utilization of the segmentation masks as the prior information for estimating the number of the cells in the image. We propose in this work a novel cell counting scheme that uses the features provided by a deep convolutional autoencoder (DCAE) as the inputs of a shallow regressor network, instead of using the segmentation masks. First, the cellular image is given to the DCAE whose task is to reconstruct the original input image with an encodingdecoding scheme. The latent representations located in the middle of the DCAE are extracted and used as the final feature representation of the images. The second step consists of using these features as the inputs of a neural network based regressor whose outputs will represent the number of the cells in the image. The results demonstrate how the proposed scheme really manages to recognize the exact number of the cells even in the case of significant overlapping situations, exactly where most of the state-of-the-art cell counting methods fail.

Machine fault diagnosis (MFD) has gained an important enthusiasm since the unfolding of the pattern recognition techniques in the last three decades. It refers to all of the studies that aim to automatically detect the faults on the machines using various kinds of signals that they can generate. The present work proposes a MFD system for the drilling machines that is based on the sounds they produce. The first key contribution of this paper is to present a system specifically designed for the drills, by attempting not only to detect the faulty drills but also to detect whether the sounds were generated during the active or the idling stage of the whole machinery system, in order to provide a complete remote control. The second key contribution of the work is to represent the power spectrum of the sounds as images and apply some transformations on them in order to reveal, expose, and emphasize the health patterns that are hidden inside them. The created images, the so-called power spectrum density (PSD)-images, are then given to a deep convolutional autoencoder (DCAE) for a high-level feature extraction process. The final step of the scheme consists of adopting the proposed PSD-images + DCAE features as the final representation of the original sounds and utilize them as the inputs of a nonlinear classifier whose outputs will represent the final diagnosis decision. The results of the experiments demonstrate the high discrimination potential afforded by the proposed PSD-images + DCAE features. They were also tested on a noisy dataset and the results show their robustness against noises.

Machine fault diagnosis (MFD) recovers all the studies that aim to detect faults automatically in the machines. This study aims to develop a sound based MFD system for drills using the pattern recognition techniques such as principal components analysis (PCA) and artificial neural networks (ANN). The sound signals emitted by healthy and faulty drills are obtained and analyzed. Unlike the conventional methods that focus on the time domain, we explore here the effectiveness of the frequency domain components and demonstrate the ineffectiveness of the time domain based analysis of the sounds produced by the drills. The power spectrum components of the sounds are extracted before using PCA for the purpose of dimensionality reduction and redundancy removal. The first principal components are then selected and given to a neural network based classifier in order to perform the diagnosis. The results show that the proposed method can be used for the sounds based automatic diagnosis system.