Background: The most common types of non-melanoma skin cancer are basal cell carcinoma (BCC), and squamous cell carcinoma (SCC). AKIEC-Actinic keratoses (Solar keratoses) and intraepithelial carcinoma (Bowen’ s disease)-are common noninvasive precursors of SCC, which may progress to invasive SCC, if left untreated. Due to the importance of early detection in cancer treatment, this study aimed to propose a computer-based model for identification non-melanoma malignancies. Methods: In this analytic study, 327 AKIEC, 513 BCC, and 840 benign keratosis images from human against machine with 10000 training dermoscopy images (HAM10000) were extracted. From each of these three types, 90% of the images were designated as the training set and the remaining images were considered as the test set. A deep learning Convolutional neural network (CNN) was developed for skin cancer detection by using AlexNet (Krizhevsky, et al., 2012) as a pretrained network. First, the model was trained on the training images to discriminate between benign and malignant lesions. In comparison with conventional methods, the main advantage of the proposed approach is that it does not need cumbersome and time-consuming procedures of lesion segmentation and feature extraction. This is because CNNs have the capability of learning useful features from the raw images. Once the system was trained, it was validated with test data to assess the performance. Study was carried out at Shahid Beheshti University of Medical Sciences, Tehran, Iran, in January and February, 2020. Results: The proposed deep learning network achieved an AUC (area under the ROC curve) of 0. 97. Using a confidence score threshold of 0. 5, a classification accuracy of 90% was attained in the classification of images into malignant and benign lesions. Moreover, a sensitivity of 94% and specificity of 86% were obtained. It should be noted that the user can change the threshold to adjust the model performance based on preference. For example, reducing the threshold increase sensitivity while decreasing specificity. Conclusion: The results highlight the efficacy of deep learning models in detecting non-melanoma skin cancer. This approach can be employed in computer-aided detection systems to assist dermatologists in identification of malignant lesions.

Object tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. This paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining Convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a Convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. The weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the particle filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.

Speech recognition representing a communication between computers and human as a sub eld of computational linguistics or natural language processing has a long history. Automatic Speech Recognition (ASR), Text To Speech (TTS), speech to text, Continuous Speech Recognition (CSR), and interactive voice response systems are dierent approaches to solving problems in this area. The performance improvement is partially attributed to the ability of the Deep Neural Network (DNN) to model complex correlations in speech features. In this paper, unlike the use of conventional model for sequential data like voice that employs Recurrent Neural Networks (RNNs) with the emergence of dierent architectures in deep networks and good performance of Conventional Neural Networks (CNNs) in image processing and feature extraction, the application of CNNs was developed in other domains. It was shown that prosodic features for Persian language could be extracted via CNNs for segmentation and labeling speech for short texts. By using 128 and 200 lters for CNN and special architectures, 19. 46 error in detection rate and better time consumption than RNNs were obtained. In addition, CNN simplies the learning procedure. Experimental results show that CNN networks can be a good feature extractor for speech recognition in various languages.

Deep Convolutional neural networks (CNNs) have attained remarkable success in numerous visual recognition tasks. There are two challenges when adopting CNNs in real-world applications: a) Existing CNNs are computationally expensive and memory intensive, impeding their use in edge computing; b) there is no standard methodology for designing the CNN architecture for the intended problem. Network pruning/compression has emerged as a research direction to address the first challenge, and it has proven to moderate CNN computational load successfully. For the second challenge, various evolutionary algorithms have been proposed thus far. The algorithm proposed in this paper can be viewed as a solution to both challenges. Instead of using constant predefined criteria to evaluate the filters of CNN layers, the proposed algorithm establishes evaluation criteria in online manner during network training based on the combination of each filter’s profit in its layer and the next layer. In addition, the novel method suggested that it inserts new filters into the CNN layers. The proposed algorithm is not simply a pruning strategy but determines the optimal number of filters. Training on multiple CNN architectures allows us to demonstrate the efficacy of our approach empirically. Compared to current pruning algorithms, our algorithm yields a network with a remarkable prune ratio and accuracy. Despite the relatively high computational cost of an epoch in the proposed algorithm in pruning, altogether it achieves the resultant network faster than other algorithms.

In this paper, we consider a class of column-weight two quasi-cyclic low-density parity check codes in which the girth can be large enough, as an arbitrary multiple of 8. Then we devote a Convolutional form to these codes, such that their generator matrix can be obtained by elementary row and column operations on the parity-check matrix. Finally, we show that the free distance of the Convolutional codes is equal to the minimum distance of their block counterparts.

Distinguishing P300 signals from other components of the EEG is one of the most challenging issues in Brain Computer Interface (BCI) applications, and machine learning methods have vastly been utilized as effective tools to perform such separation. Although in recent years deep neural networks have significantly improved the quality of the above detection, the significant similarity between P300 and other components of EEG in parallel with their unrepeatable nature have led to P300 detection, which are still an open problem in BCI domain. In this study, a novel architecture is proposed in order to detect P300 signal among EEG, in which the temporal learning concept is engaged as a new substructure inside the main Convolutional Neural Network (CNN). The above Temporal Convolutional Network (TCN) may better address the problem of P300 detection, thanks to its potential in involving time sequence properties in modelling of these signals. The performance of the proposed method is evaluated on the EPFL BCI dataset, and the obtained results are compared in two inter-subject and intra-subject scenarios with the results of classical CNN in which temporal properties of input are not considered. Increased True Positive Rate of the proposed method (an average of 4 percent) and its accuracy (an average of 2. 9 percent) in parallel with the decrease in its False Positive Rate (averagely 3. 1 percent) shows the effectiveness of the TCN structure in promoting the detection procedure of P300 signals in BCI applications.

Personal identification based on vein pattern is one of the latest biometric approaches that have attracted lots of attention. Besides, Convolutional Sparse Coding (CSC) is a popular model in the signal and image processing communities, resolving some limitations of the traditional patch-based sparse representations. As most existing CSC algorithms are suited for image restoration, we present a novel discriminative model based on CSC for dorsal hand vein recognition in this paper. The proposed method, discriminative local block coordinate descent (D-LoBCoD), is based on extending the LoBCoD algorithm by incorporating the classification error into the objective function that considers the performance of a linear classifier and the representational power of the filters simultaneously. Thus, for training, in each iteration, after updating the sparse coefficients and Convolutional filters, we minimize the classification error by updating the classifier’s parameters according to the label information. Finally, after training, the label of the query image will be determined by the trained classifier. One thousand two hundred dorsal hand vein images taken from 100 individuals are used to verify the validity of the proposed methods. The experimental results show that our method outperforms other competing methods. Further, we demonstrate that our proposed method is less dependent on the number of training samples because of capturing more representative information from the corresponding images.