Deep neural networks are a class of powerful machine learning model that uses successive layers of non-linear processing units to extract features from data. However, the training process of such networks is quite computationally intensive and uses commonly used optimization methods that do not guarantee optimum performance. Furthermore, deep learning methods are often sensitive to noise in data and do not operate well in areas where data are incomplete. An alternative, yet little explored, method in enhancing deep learning performance is the use of fuzzy systems. Fuzzy systems have been previously used in conjunction with neural networks. This survey explores the different ways in which deep learning is improved with fuzzy logic systems. The techniques are classified based on how the two paradigms are combined. Finally, the real-life applications of the models are also explored.

No abstract

In the innovative concept of the “Social Internet of Things” (IoT), the IoT is combined with social platforms so that inanimate devices can form their interactions with one another. Still, customers have a wary attitude toward this new standard. They worry that their privacy will be invaded and their information will be made public. IoT won't become a frontrunner technology until we have tried true techniques to improve trustworthy connections between nodes. As a result, data privacy becomes extremely difficult, further increasing the difficulty of providing high-quality services and absolute safety. Several articles have attempted to analyze this issue. To categorize safe nodes in the IoT network, they suggested many models based on various attributes and aggregation techniques. In contrast, prior works failed to provide a means of identifying fraudulent nodes or distinguishing between different forms of assaults. To identify attacks carried out by hostile nodes and separate them from the network, we propose a novel Multi-hop Convolutional Neural Network with an attention mechanism (MH-CNN-AM). To achieve the best performance in the suggested research, performance measures including accuracy, precision, recall, F 1-score, and MAE are studied and compared with the of existing methodologies.

Deep learning (DL) technology has shown to be the most effective method of completing class assignments in the last several years. Specifically, these approaches were used for segmentation, classification, and prediction of retinal blood vessels, which was previously unattainable. U-Net deep learning technology has been hailed as one of the most significant technological advances in recent history. In the proposed work, improved segmentation of retinal images using U-Net, bidirectional ConvLSTM U-Net (BiDCU-Net), and fully connected convolutional layers, such as absolute U-Net, BiConvLSTM preferences, and also the fully connected convolutional layer method are proposed. Three well-known datasets were subjected to the suggested technique’s evaluation: the DRIVE, STARE, and CHASE DB1 databases. This suggested technique was tested using the required precise measures in percentage of accuracy, F1 score, sensitivity, and specificity in DRIVE, 97.32, 83.85, 82.56, and 98.68 in CHASE, 97.44, 81.94, 83.92, and 98.45 in STARE, 97.33, 82.3, 82.12, and 98.57 in STARE, respectively. Furthermore, we assert that the strategy outperforms three other similar strategies in terms of effectiveness.

Malignancy is one of the leading causes of death globally. It is on the rise in the developed and low-income countries with survival rates of less than 40%. However, early diagnosis may increase survival chances. Histopathology images acquired from the biopsy are a popular method for cancer diagnosis. In this article, we propose a deep convolutional neural network-based method that helps classify breast cancer tumor subtypes from histopathology images. The model is trained on the BreakHis dataset but is also tested on images from other datasets. The model is trained to recognized eight different tumor subtypes, and also to perform binary classification (malignant/non-malignant). The CNN model uses an encoder-decoder architecture as well as a parallel feed-forward network. The proposed model provides higher cumulative training accuracy and statistical scoring after five-fold cross-validation. Comparing with the other models, the accuracy of the proposed model