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.

Radial carpet beams are a novel form of structured light that falls under the category of combined half-integer Bessel-like beams. This study introduces the radial carpet beam as a means of information transmission and a solution for expanding the information Encoding freedoms. The method employed for detecting and classifying these beams is the Convolutional neural network (CNN). To conduct the study, a dataset consisting of 16 different classes of radial carpet modes was prepared. These modes were propagated through underwater turbulence conditions over a distance of 120 cm. The Convolutional neural network used in the study was based on the widely recognized DenseNet-201 architecture, utilizing transfer learning techniques. The trained model achieved a 97% accuracy in mode detection and classification. Subsequently, the performance of the proposed model was evaluated by transmitting and receiving a 4-bit grayscale image measuring 150 x 200 pixels through an underwater communication link based on radial carpet modes. The evaluation results clearly demonstrate the potential for achieving new Encoding options with radial carpet beams. Moreover, the Convolutional neural network method proves to be an optimal approach for detecting and classifying structured light beams. This method alleviates the challenges of using multiple optical components in coherent detection techniques, which traditionally rely on diffraction gratings. In addition to simplifying optical system configuration, it also reduces implementation costs and volume, particularly in optical communication applications.

In this paper, a new scheme for serial communication is proposed. In this method, in addition to the pulse states (high and low), either of negative slope or positive slope of the pulse (saw-tooth waveform) is employed as a representative for another digit. Using pulse slope as a representative for a separate digit will result in sending two-bit-digits using a single pulse, which doubles the transfer rate. The proposed scheme can be used in both synchronized and asynchronized communications and can improve communication speed. Through simulating the proposed scheme, it turned out that this method, because of its proper immunity to noise, can be used as a peripheral interface alongside in-chip communication. The main idea in the raised discussion is to obtain four different geometric pulse shapes acting as four different numbers in the quaternary numeric system, in which it can be serialized/desrialized as easy as pulse states. This proposed method and the suggested system for serialization and deserialization of data can be an adequate alternative in high-speed communication approaches.

Nowadays, given the rapid progress in pattern recognition, new ideas such as theoretical mathematics can be exploited to improve the efficiency of these tasks. In this paper, the Discrete Wavelet Transform (DWT) is used as a mathematical framework to demonstrate handwritten digit recognition in spiking neural networks (SNNs). The motivation behind this method is that the wavelet transform can divide the spike information and noise into separate frequency subbands and also store the time information. The simulation results show that DWT is an effective and worthy choice and brings the network to an efficiency comparable to previous networks in the spiking field. Initially, DWT is applied to MNIST images in the network input. Subsequently, a type of time Encoding called constant-current-Leaky Integrate and Fire (LIF) Encoding is applied to the transformed data. Following this, the encoded images are input to the multilayer Convolutional spiking network. In this architecture, various wavelets have been investigated, and the highest classification accuracy of 99.25% is achieved.

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.

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.