One of the challenges of the Internet of Things and smart cities is energy consumption and energy theft. An accurate approach to predicting energy consumption and detecting energy theft in smart cities increases effic...
详细信息
One of the challenges of the Internet of Things and smart cities is energy consumption and energy theft. An accurate approach to predicting energy consumption and detecting energy theft in smart cities increases efficiency and energy efficiency. Forecasting energy consumption makes energy production based on the needs of consumers, and detecting energy theft makes energy consumption forecasting models more accurate. In this manuscript, in the first step, the data set is balanced using the generative adversarial network based on game theory and the synthetic minority oversampling based on sample density method. In the second step, the basic features of the samples are selected with the namibbeetleoptimization (NBO) algorithm to reduce the input of the CNN-LSTM model. In the third step, the hyperparameters of the CNN-LSTM model are optimized to reduce the prediction and classification error rate with the NBO algorithm. In the Benin Electricity Company dataset, the proposed method has fewer errors in predicting energy consumption than the LSTM, GRU, ARIMA-LSTM, and ARIMA-GRU methods. On the Individual Household Electric-Power Consumption dataset, the proposed method provides lower energy consumption prediction errors than convolutional neural network (CNN), long short-term memory (LSTM), and CNN-LSTM. The NBO algorithm optimizer CNN-LSTM hyperparameters more accurately than Coati optimizationalgorithm, jellyfish search optimization, Harris hawks optimization (HHO), and African vultures optimizationalgorithm. Experiments on the State Grid Corporation of China dataset showed that the proposed method's accuracy, sensitivity, and precision in predicting energy theft are 98.93, 98.32, and 96.78%. The proposed method is more accurate than CNN, DeepCNN, CNN-LSTM, and the gated recurrent unit (GRU) method.
Mobile ad hoc network (MANET) plays a major role in wireless devices such as defense and flooding. Despite their smart applications, MANET faces more security issues than traditional wired and wireless networks on acc...
详细信息
Mobile ad hoc network (MANET) plays a major role in wireless devices such as defense and flooding. Despite their smart applications, MANET faces more security issues than traditional wired and wireless networks on account of their distinct features, such as no central coordination, dynamic topology, temporal network life, and the nature of wireless communication. To overcome these issues, this manuscript proposes a Dual Interactive Wasserstein Generative Adversarial Network optimized with namib beetle optimization algorithm is proposed for intrusion detection and preventing attacks in MANET. By utilizing the One Way Hash Chain Function, mobile users first register with the Trusted Authority. Each mobile user sends a finger vein biometric along with their user id, latitude, and longitude for authentication verification. The packet analyzer, feature extraction, preprocessing, and classification are the four parts that make up intrusion detection. To determine if any attack patterns have been identified, the packet analyzer is examined. This is executed using a Type 2 Fuzzy Controller that deems packet header information. Anisotropic diffusion Kuwahara filtering techniques is time series is taken into consideration in the preprocessing unit. The battle royal optimizationalgorithm is utilized in the feature extraction unit to acquire a better collection of features for packet categorization. The classification unit classifies the packets into five categories: DoS, Probe, U2R, R2L, and Anomaly using the proposed technique. Finally, the proposed method provides 26.26%, 15.57%, 32.9% higher accuracy, 33.06%, 23.82%, and 38.84% lesser delay analysed to the existing models.
In general, a number of data types can be sensed, processed, and transmitted over wireless communication networks. Therefore, an Intrusion Detection System in a wireless sensor network using an Optimized Self-Attentio...
详细信息
In general, a number of data types can be sensed, processed, and transmitted over wireless communication networks. Therefore, an Intrusion Detection System in a wireless sensor network using an Optimized Self-Attention-Based Progressive Generative Adversarial Network (IDS-SAPGAN-NBOA-WSN) is proposed in this paper. The input data are gathered through the WSN-DS database. The obtained data are supplied into the pre-processing phase. An Altered Phase Preserving Dynamic Range Compression (APPDRC) is employed to eliminate data redundancy and restoration of missing values in WSN data. Then, War Strategy optimizationalgorithm (WSOA) is applied to select ten features from input data. The selected features are given to Self-Attention-based Progressive Generative Adversarial Network (SAPGAN) for classifying intrusions, like Blackhole, Gray hole, Flooding, Scheduling, and Normal attacks. In general, SAPGAN does not adapt any optimization models to define optimum parameters to ensure the attack classification. That's why;the namib beetle optimization algorithm (NBOA) is proposed to improve the weight parameter of SAPGAN, which precisely categorizes the attacks. The proposed IDS-SAPGAN-NBOA-WSN approach is implemented and the performance metrics, such as accuracy, precision, and sensitivity are examined. The proposed technique attains 21.12%, 29.09%, 10.23%, 15.42%, and 21.05% higher accuracy when compared with existing techniques: IDS using Conditional Generative Adversarial Network in WSN (IDS-CGAN-XGBoost-WSN), Improved binary gray wolf optimizer along support vector machine for IDS in WSN (IDS-SVM-IBGWO-WSN), Intrusion detection scheme depending on a deep neural network (IDS-DNN-WSN), Effectual intrusion detection technique based upon dynamic autoencoder (IDS-LwDAN-WSN) and Enhanced grey wolf optimizer dependent particle swarm optimizer in WSN (IDS-SVM-EGWO-WSN), respectively.
Designing a routing protocol that can against the attacks of malicious nodes is very essential because open wireless channels make a wireless ad hoc network (WAN) affected by different security attacks. To overcome th...
详细信息
Designing a routing protocol that can against the attacks of malicious nodes is very essential because open wireless channels make a wireless ad hoc network (WAN) affected by different security attacks. To overcome this problem, Dual-Discriminator Conditional Generative Adversarial Network Optimized with namib beetle optimization algorithm is proposed in this manuscript for cluster head based secure routing in Wireless Ad-hoc Networks (CH-SR-DDCGAN-NBOA-WAN). Here, the proposed CH-SR-DDCGAN-NBOA-WAN method consists of two phases: (i) to find the optimal CHs (ii) to find optimal trust path. At first, Dual-discriminator conditional generative adversarial network is utilized for selecting Cluster Head (CH) depending on the multi-objective fitness function. The multi-objective fitness function considers the factors, namely set of nodes, determining short security paths connecting sources and destinations, and links schedule with the routes that fulfills the request of all nodes to decrease the energy consumption of whole network, and also increase the defense against spiteful nodes. Therefore, in this work, proposed namib beetle optimization algorithm (NBOA) is utilized for optimizing the Dual-discriminator conditional generative adversarial network, which selects the CH accurately. After CH selection, Nomadic People optimizationalgorithm (NPOA) is used to identify the trust path from that are confirmed by using trust parameters, such as integrity, consistency, forwarding rate, availability factor. The proposed CH-SR-DDCGAN-NBOA-WAN approach is activated in network stimulator NS-2 and its performance is examined under performance metrics, such as drop, normalized network energy, network lifetime, delay, throughput, energy consumption, Packet Delivery Ratio. The proposed CH-SR-DDCGAN-NBOA-WAN approach attains 23.31%, 24.5%, and 30.01% lower packet drop, 12.45%, 17.34% and 24.67% higher network life time and 11.45%, 17.34% and 29.56% lower average delay time compared wit
Automatic, intelligent smoke and fire detection model is developed using an advanced deep learning (DL) algorithm with minimized complexity and improved detection performance for smart city environment. The proposed m...
详细信息
ISBN:
(纸本)9798400716959
Automatic, intelligent smoke and fire detection model is developed using an advanced deep learning (DL) algorithm with minimized complexity and improved detection performance for smart city environment. The proposed model of Cross-Attention Capsule based Optimized Siamese Convolutional Stacked Recurrent Neural Network (CACO-SCSRNN) is a combination of Siamese Convolutional Neural Networks (SCNN), Stacked Recurrent Neural Networks (SRNNs), and namib beetle optimization algorithm (NBOA). This hybrid model also includes fully connected (FC) layers for predicting change probability, cross attention to preserving the saliency correlation, and capsule vectors to acquire the location relationships of features. This hybrid DL model extracts all the spatial and temporal features from input images to detect the smoke and flame events through deep correlated features for early detection of the fire bursts. Evaluated over a real-world database, this proposed CACO-SCSRNN-based method enhances the smoke and fire images accurately with 99.12% accuracy, 100% precision, 97.89% recall, 98.93% F-measure, 0.91% FPR and 0.229 RMSE values, which are better than the existing methods. This ensures reduced model complexity and improves the reliability of fire-safety systems for smart city environments.
In this paper, the Lung Cancer Classification using Convolutional Neural Network with DenseNet-201 Transfer Learning model optimized through namib beetle optimization algorithm on CT image (AtCNN-DenseNet-201 TL-NBOA-...
详细信息
In this paper, the Lung Cancer Classification using Convolutional Neural Network with DenseNet-201 Transfer Learning model optimized through namib beetle optimization algorithm on CT image (AtCNN-DenseNet-201 TL-NBOA-CT) is proposed. The input data are gathered from the CT Lung image. In pre-processing section, it removes the noise and enhances input images by Modified Sage -Husa Kalman Filtering (MSHKF).The preprocessed image is given into feature extraction phase. Then, six statistical features including mean, variance, entropy, energy, Average Amplitude, kurtosis are extracted based on Improved Empirical Wavelet Transforms (IEWT). Then, the extracted features are given to the Attention-based Convolutional Neural Network with DenseNet-201Transfer Learning (AtCNN-DenseNet-201 TL) to classify the Cancer and Non-Cancer of the CT image, where batch normalization layer of At CNN eliminated and added by DenseNet-201 layer. namib beetle optimization algorithm (NBOA) proposed in this work to enhance the AtCNN-DenseNet-201 classifier, which precisely classifies the lung cancer. The proposed AtCNN-DenseNet-201 TL-NBOA-CT method is implemented and the effectiveness is assessed with some performance measures. The proposed AtCNN-DenseNet-201 TLNBOA-CT method attains 18.30 %, 21.37 % and 23.07 % greater precision, 24.84 %, 16.32 % and 31.36 % greater accuracy and 14.32 %, 21.97 % and 23.38 % greater F1-Score compared with existing techniques like detection and categorization of lung cancer CT pictures utilizing improved deep belief network along Gabor filters (CLC-CT-EDBN), presented categorization of lung cancer CT pictures utilizing a three dimensional deep CNN with multi-layer filter (CLC-CT-3D-DCNN), and novel hybrid deep learning technique for early identification of lung cancer utilizing neural networks (CLC-CT-3D-CNN) respectively.
暂无评论