Search

Many important signal processing applications are made possible by automatic modulation classification (AMC). More advanced than traditional machine learning (ML) techniques connected to hand-crafted features, deep learning (DL) methods have recently been employed in modulation recognition. However, several conventional Road-based AMC methods have caused confusion amongst OFDM-based signals because to the differences in usable symbol lengths of OFDM schemes. This research creates a Modulation Recognition System for OFDM wireless optical communication using Tangent Search Optimisation with Deep Belief Networks (TSODBN-MRS). Using a feature extraction procedure based on the communication signals, the described TSODBN-MRS technique identifies and classes modulation signals in an OFDM communication system. The DBN model is used for modulation recognition, and the TSO method is used to improve recognition accuracy. The results of the experiments proved that the TSODBN-MRS model provides effective modulation classification performance and has exhibited improved performance with greater pf 99.95%. [ABSTRACT FROM AUTHOR]

Lower limb activity recognition utilizing body sensor data has attracted researchers due to its practical applications, such as neuromuscular disease detection and kinesiological investigations. The employment of wearable sensors including accelerometers, gyroscopes, and surface electromyography has grown due to their low cost and broad applicability. Electromyography (EMG) sensors are preferable for automated control of a lower limb exoskeleton or prosthesis since they detect the signal beforehand and allow faster movement detection. The study presents hybrid deep learning models for lower limb activity recognition. Noise is suppressed using discrete wavelet transform, and then the signal is segmented using overlapping windowing. Convolutional neural network is used for temporal learning, whereas long short-term memory or gated recurrent unit is used for sequence learning. After that, performance indices of the models such as accuracy, sensitivity, specificity, and F-score are calculated. The findings indicate that the suggested hybrid model outperforms the individual models. [ABSTRACT FROM AUTHOR]

Offensive communications have made their way into social media posts. Using computational algorithms to distinguish objectionable content is one of the most effective ways to deal with this problem. One of the most effective approaches to deal with this issue is to use computational methods to distinguish undesirable content. This research aims to tackle MOLD_DL (Multilingual Offensive Language Detection using deep learning) techniques and natural language processing used in feature selection and classification. Here the dataset has been collected from YouTube, Twitter and Facebook, which has been pre-processed for noise removal, filtering and removing the stop words and segmented. The feature selection has been carried out for segmented data using Fuzzy based convolutional neural network (FCNN). Then the extraction of selected features and classification has been carried out using ensemble architecture of Bi-LSTM model with Naïve Bayes architecture hybrid with Support Vector Machines (SVM). Evaluation of offensive language detection is classified automatically based on the emotions of the text. Here the experimental analysis has been carried out for YouTube, Twitter and Facebook datasets in terms of accuracy of 98%, precision of 95%, recall of 90%, F-1 score of 92.5% and RMSE of 45% with the confusion matrix in detecting offensive text of various languages. • Offensive communications have made their way into social media posts. • This research aims to tackle MOLD_DL (Multilingual Offensive Language Detection using deep learning) techniques and natural language processing used in feature selection and classification. • Here the dataset has been collected from Social Networks. • Finally, these extracted features have been classified using ensemble architecture of Bi-LSTM model with Support Vector Machines (SVM) which is hybrid with Naïve Bayes architecture. [ABSTRACT FROM AUTHOR]

Cyber-Physical System (CPS) is an emerging technique that focuses on the integration of computation applications as a network of communicating physical and cyber components which controls real time physical substructures of the industrial automation. Since implementation, operation and design of CPS and management of automation substructures are plays major significance in the various industrial applications. This study presents a Deep learning (DL) based intrusion controlling and monitoring management system (DL-ICMMS) for CPS in the automation industry for the detection of the occurrence of intrusions. To transform the input data in a compatible manner, data normalization is carried out and the Adam optimizer is applied to handle hyperparameter values of Restricted Boltzmann Machine (RBM) method. Experimental results analysis stated that the DL-ICMMS method increased a c c u y of 98.80% whereas the Multilayer Perceptron (MLP), K Nearest Neighbor (KNN), Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Long short-term memory (LSTM) approaches have shown reduced a c c u y of 93.10%, 93.62%, 91.60%, 90.88%, and 91.75%, correspondingly. [ABSTRACT FROM AUTHOR]

Land surface data is one of the entry points for a enormous resource management and human activity such as to monitor farming, ecology, urban management, and territories. This research aimed to improve the performance of the multispectral image processing technique using a novel deep learning based classification approaches used in classifying the surfaces in multispectral satellite images. The monitoring of Internet of Things (IoT) based wireless communication using secure locations sensor network protocol (SLSNP). The multispectral satellite images are collected based on developing and developed countries. Upon the collection of multispectral image data using deep convolution neural network (DCNN) deep learning system landmarks of the multispectral images are estimated. This will be effective for the identification of resources in a particular location. The simulation results show classification accuracy, precision, recall and the network lifetime, efficiency, throughput based on data transmission from satellite for secure location based wireless sensor networks (WSNs). [ABSTRACT FROM AUTHOR]