Search

Electricity theft presents a substantial threat to distributed power networks, leading to non-technical losses (NTLs) that can significantly disrupt grid functionality. As power grids supply centralized electricity to connected consumers, any unauthorized consumption can harm the grids and jeopardize overall power supply quality. Detecting such fraudulent behavior becomes challenging when dealing with extensive data volumes. Smart grids provide a solution by enabling two-way electricity flow, thereby facilitating the detection, analysis, and implementation of new measures to address data flow issues. The key objective is to provide a deep learning-based amalgamated model to detect electricity theft and secure the smart grid. This research introduces an innovative approach to overcome the limitations of current electricity theft detection systems, which predominantly rely on analyzing one-dimensional (1-D) electric data. These approaches often exhibit insufficient accuracy when identifying instances of theft. To address this challenge, the article proposes an ensemble model known as the RNN-BiLSTM-CRF model. This model amalgamates the strengths of recurrent neural network (RNN) and bidirectional long short-term memory (BiLSTM) architectures. Notably, the proposed model harnesses both one-dimensional (1-D) and two-dimensional (2-D) electricity consumption data, thereby enhancing the effectiveness of the theft detection process. The experimental results showcase an impressive accuracy rate of 93.05% in detecting electricity theft, surpassing the performance of existing models in this domain.

The Federated learning (FL) technique resolves the issue of training machine learning (ML) techniques on distributed networks, including the huge volume of modern smart devices. FL clients frequently use Wi-Fi and have to interact in unstable network surroundings. However, as the present FL aggregation approaches receive and send a large number of weights, accuracy can be decreased considerably in unstable network surroundings. Therefore, this study presents a Quantum with Metaheuristics Algorithm Based Minimization of Communication Costs in Federated Learning (QMAMCC-FL) technique. The presented QMAMCC-FL technique is designed a federated hybrid convolutional neural network with a gated recurrent unit (HCNN-GRU) model with a quantum Aquila optimization (QAO) algorithm. The QMAMCC-FL technique upgrades the global model via weight collection of the learned model, which is commonly used in FL. The proposed model can be employed to increase the performance of network communication and reduce the size of data transmitted from clients to servers such as smartphones and tablets. The experimental analysis of the QMAMCC-FL approach is tested, and the outcomes show better performance over other existing models.

Smart farming helps to increase yield by smartly deciding the steps that should be practised in the season. A few components of precision farming are recommending the crops for cultivation, predicting the weather conditions, examining the soil; determining the pesticides, and fertilizers that have to be used. Smart Farming utilizes advanced technologies namely data mining (DM), machine learning (ML), the Internet of Things (IoT), and data analytics for collecting the data, predicting the outcomes and training the system. One of the most significant parameters is proper soil prediction which decides the proper crop and is manually executed by the agriculturalists. Hence, the farmer’s efficacy can be improved by producing automated tools for soil type classification. This study presents a Chaotic Jaya Optimization Algorithm with Computer Vision based Soil Type Classification (CJOCV-STC) for smart farming. The presented CJOCV-STC technique applies CV with metaheuristic algorithms for the automated soil classification process, which identifies the soil into distinct types. To accomplish this, the presented CJOCV-STC technique uses the SqueezeNet model for producing a set of feature vectors. To improve the performance of the SqueezeNet model, the CJO algorithm is used for the hyperparameter tuning process. Moreover, the Elman neural network (ENN) technique is applied for soil type classification and the parameters related to it can be adjusted by the chicken swarm algorithm (CSA). The soil classification performance of the CJOCV-STC method can be studied on the Kaggle dataset and the outcomes stated the better performance of the CJOCV-STC algorithm over other recent approaches with increased accuracy of 98.47%.

Unmanned aerial vehicles (UAVs) are assumed to be a promising model of automatic emergency tasks in dynamic marine ecosystems. But, the real-time communication efficacy betwixt UAVs and base platforms is developing a serious challenge. The compact-sized powerful flying robots can be wirelessly controlled and accomplish end tasks with and without human involvement. UAVs still face severe challenges that limit the dream of completely autonomous unmanned flying machines. The main difficulties contain path planning and hindrance avoidance of such unmanned flying robots, which are mandatory but carry out the application-specific functionality in either indoor or outdoor environments. This study introduces a new Dispersal Foraging Strategy with Cuckoo Search Optimization based Path Planning (DFSCSO-PP) technique for UAV networks. In the presented DFSCSO-PP technique, the identification of optimal paths for data transmission is performed in the UAV network. In addition, the presented DFSCSO-PP technique involves the optimal allocation of resources while finding the optimal paths in the network. Moreover, the DFSCSO technique can be designed by integrating the DFS concept into the CSO method to avoid local optima problems. A widespread simulation analysis is performed to exhibit the enhanced outcome of the DFSCSO-PP approach. A detailed set of comparative studies assured the improved performance of the DFSCSO-PP technique over other approaches.

Cloud computing technology is a new computing paradigm phenomenon that has recently received a significant attention by several research studies. However, the previous works have concentrated on the adoption of this technology and limited studies focused on the factors influencing the intention to use it. Therefore, the proposed study developed a model to figure out these factors. This study used an online questionnaire to collect data. A total of 712 responses were received. Structural equation modelling was employed by using SmartPLS 3 software to analyse the collected data. The findings of this study indicate that awareness, user readiness, and satisfaction are important factors related to the use of cloud computing, while privacy seems to have no significant influence on the use of this technology. Thus, this study recommends users to attend courses and workshops to garner knowledge and understanding of cloud computing and hence become appropriately qualified to use it. Moreover, such courses and workshops will provide users with methods and techniques to protect their privacy, which should be given priority attention.

The journal retracts the article “Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments” [...]

Continuous data stream analysis primarily focuses on the unanticipated changes in the transmission of data distribution over time. Conceptual change is defined as the signal distribution changes over the transmission of continuous data streams. A drift detection scenario is set forth to develop methods and strategies for detecting, interpreting, and adapting to conceptual changes over data streams. Machine learning approaches can produce poor learning outcomes in the conceptual change environment if the sudden change is not addressed. Furthermore, due to developments in concept drift, learning methodologies have been significantly systematic in recent years. The research introduces a novel approach using the fully connected committee machine (FCM) and different activation functions to address conceptual changes in continuous data streams. It explores scenarios of continual learning and investigates the effects of over-learning and weight decay on concept drift. The findings demonstrate the effectiveness of the FCM framework and provide insights into improving machine learning approaches for continuous data stream analysis. We used a layered neural network framework to experiment with different scenarios of continual learning on continuous data streams in the presence of change in the data distribution using a fully connected committee machine (FCM). In this research, we conduct experiments in various scenarios using a layered neural network framework, specifically the fully connected committee machine (FCM), to address conceptual changes in continuous data streams for continual learning under a conceptual change in the data distribution. Sigmoidal and ReLU (Rectified Linear Unit) activation functions are considered for learning regression in layered neural networks. When the layered framework is trained from the input data stream, the regression scheme changes consciously in all scenarios. A fully connected committee machine (FCM) is trained to perform the tasks described in continual learning with M hidden units on dynamically generated inputs. In this method, we run Monte Carlo simulations with the same number of units on both sides, K and M, to define the advancement of intersections between several hidden units and the calculation of generalization error. This is applied to over-learnability as a method of over-forgetting, integrating weight decay, and examining its effects when a concept drift is presented.

Radio spectrum awareness, including understanding radio signal activities, is crucial for improving spectrum utilization, detecting security vulnerabilities, and supporting adaptive transmissions. Related tasks include spectrum sensing, identifying systems and terminals, and understanding various protocol layers. In this paper, we investigate various identification and classification tasks related to fading channel parameters, signal distortions, Medium Access Control (MAC) protocols, radio signal types, and cellular systems. Specifically, we utilize deep learning methods in those identification and classification tasks. Performance evaluations demonstrate the effectiveness of deep learning in those radio spectrum awareness tasks.