Nowadays the cloud computing environment is widely utilized for transmitting and receiving data securely. Inorder to secure the data the encryption method is used but still due to some limitations the security process is diminished. Therefore, this paper proposes a new algorithm to provide better security while transmitting data through the network. At first, the sensitivity of data is determined using a Lightweight convolutional neural network (LWCNN) model which is used to categorize the unclassified data into two categories normal sensitive data and highly sensitive data. After determining the level of data sensitivity, the encryption process is performed further. The efficient hash function-based duplication detection approach is employed to maintain confidential information before outsourcing it to a cloud server. Subsequently, the ideal keys are generated for each data based on its sensitivity level using the proposed fuzzy tuna swarm (FTS) algorithm. Finally, the data is encrypted by converting plain text into ciphertext which is only visible to authorized users. The experimental results show that the LWCNN model utilized for data sensitivity classification achieved 94% accuracy and the FTS algorithm proposed for optimal key generation took much less communication time of about 1800μs than other compared techniques.

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.

The Alzheimer's disease, a progressive brain disorder, necessitates timely detection for effective management due to the current diagnostic methods' limitations. The study presents an efficient convolutional neural network (CNN) designed for classifying brain magnetic resonance imaging (MRI) images into four categories related to Alzheimer's disease. To enhance diagnosis, this study proposes two distinct approaches at different stages: (1) using optimized data pre-processing; and (2) designing a Lightweight CNN architecture with low complexity and fewer parameters that simultaneously possesses good accuracy, computational efficiency, and excellent performance. The proposed method achieved outstanding results, with a final accuracy of 99.22%, a macro average F1 score of 0.99, an MCC of 0.9870, and a Cohen kappa score (CKS) of 0.9870. In addition to accuracy, the complexity of the proposed model, including the comparison of model size, time elapsed, the number of FLOPs, and the trainable and non-trainable parameters of the proposed method were also thoroughly investigated. This model, with the advantages of high accuracy, reduced FLOPs, faster execution time, and lower memory requirements outperforms other deep learning methods used in recent studies.

Speaker recognition is a process of recognizing persons based on their voice which is widely used in many applications. Although many researches have been performed in this domain, there are some challenges that have not been addressed yet. In this research, Neutrosophic (NS) theory and convolutional neural networks (CNN) are used to improve the accuracy of speaker recognition systems. To do this, at first, the spectrogram of the signal is created from the speech signal and then transferred to the NS domain. In the next step, the alpha correction operator is applied repeatedly until reaching constant entropy in subsequent iterations. Finally, a convolutional neural networks architecture is proposed to classify spectrograms in the NS domain. Two datasets TIMIT and Aurora2 are used to evaluate the effectiveness of the proposed method. The precision of the proposed method on two datasets TIMIT and Aurora2 are 93.79% and 95.24%, respectively, demonstrating that the proposed model outperforms competitive models.

Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov model (HMM) leads to considerable performance achievement in speech recognition problem because deep networks model complex correlations between features. The main aim of this paper is to achieve a better acoustic modeling by changing the structure of deep convolutional neural network (CNN) in order to adapt speaking variations. In this way, existing models and corresponding inference task have been improved and extended. Here, we propose adaptive windows convolutional neural network (AWCNN) to analyze joint temporal-spectral features variation. AWCNN changes the structure of CNN and estimates the probabilities of HMM states. We propose adaptive windows convolutional neural network in order to make the model more robust against the speech signal variations for both single speaker and among various speakers. This model can better model speech signals. The AWCNN method applies to the speech spectrogram and models time-frequency varieties. This network handles speaker feature variations, speech signal varieties, and variations in phone duration. The obtained results and analysis on FARSDAT and TIMIT datasets show that, for phone recognition task, the proposed structure achieves 1. 2%, 1. 1% absolute error reduction with respect to CNN models respectively, which is a considerable improvement in this problem. Based on the results obtained by the conducted experiments, we conclude that the use of speaker information is very beneficial for recognition accuracy.