This paper proposes an image inpainting method based on Whale integrated Monarch Butterfly Optimization-based Deep Convolutional Neural network (Whale-MBO-DCNN) model. Initially, the patch... Show More

This paper proposes an image inpainting method based on Whale integrated Monarch Butterfly Optimization-based Deep Convolutional Neural network (Whale-MBO-DCNN) model. Initially, the patch extraction and mapping are applied to the input image to extract the patches of the image followed by image reconstruction in order to map the patches. The patch with minimum distance is selected using the concept of Bhattacharya distance in patch extraction. On the other hand, the construction of the residual image form the input image is done using Deep CNN, which is trained with the proposed Whale-MBO algorithm. The proposed Whale-MBO algorithm is developed from the integration of Monarch Butterfly Optimization (MBO) and (WOA. Finally, the residual image and the reconstructed image are fused using Holoentropy to obtain the reconstructed image. The experimentation is performed using the evaluation metrics, such as PSNR, SDME, and SSIM. The effectiveness of the proposed image inpainting method is revealed through a higher PSNR, SDME, and SSIM of 33.0585, 74.4249, and 0.9479, respectively.

This paper intents to develop an intelligent facial emotion recognition model by following four major processes like (a) Face detection (b) Feature extraction (c) Optimal feature selection and (d)... Show More

This paper intents to develop an intelligent facial emotion recognition model by following four major processes like (a) Face detection (b) Feature extraction (c) Optimal feature selection and (d) Classification. In the face detection model, the face of the human is detected using the viola-Jones method. Then, the resultant face detected image is subjected to feature extraction via (a) LBP (b) DWT (c) GLCM. Further, the length of the features is large in size and hence it is essential to choose the most relevant features from the extracted image. The optimally chosen features are classified using NN. The outcome of NN portrays the type of emotions like Normal, disgust, fear, angry, smile, surprise or sad. As a novelty, this research work enhances the classification accuracy of the facial emotions by selecting the optimal features as well as optimizing the weight of NN. These both tasks are accomplished by hybridizing the concept of FF and JA together referred as MF-JFF. The resultant of NN is the accurate recognized facial emotion and the whole model is simply referred as MF-JFF-NN.

This paper presents deep RNN based FBF approach for the detection of moving target using the radar signatures. The FBF method is developed by the integration of fuzzy concept in the Bayesian fusion... Show More

This paper presents deep RNN based FBF approach for the detection of moving target using the radar signatures. The FBF method is developed by the integration of fuzzy concept in the Bayesian fusion method. The FBF combines the results from the deep RNN, STFT, Fourier transform and matching filter to generate the final detection output from the received radar signal. The radar signatures are given as the input to the deep RNN for the detection of the target. Finally, the FBF combines the results from the deep RNN, STFT, Fourier transform and the matched filter to obtain the final decision regarding the detected target. The performance of the proposed deep RNN based FBF method is evaluated based on the metrics, like detection time, MSE and Missing target by varying the number of targets, antenna turn velocity, pulse repetition level, and the number of iterations. The proposed deep RNN based FBF method obtained a minimal detection time of 2.9551s, minimal MSE of 2683.80 and minimal Missing target rate of 0.0897, respectively.

This paper intends to propose a new model for detecting the patch based inpainting operation using Enhanced Deep Belief Network (E-DBN). The proposing model makes strong supervising of DBN that will... Show More

This paper intends to propose a new model for detecting the patch based inpainting operation using Enhanced Deep Belief Network (E-DBN). The proposing model makes strong supervising of DBN that will capture the manipulated information. In fact, the enhancement is done under optimization concept, where the activation function and weight of DBN is optimally tuned by a new hybrid algorithm termed as Swarm Mutated Lion Algorithm (SM-LA). The hybridization model combines two conventional models: Group Search Optimizer (GSO) and Lion Algorithm (LA). Finally, the performance of proposed model is compared over other conventional models with respect to certain performance measures.

This paper designed the intrusion detection systems for determining the intrusions. Here, Adam Improved rider optimization approach (Adam IROA) is newly developed for detecting the intrusion in... Show More

This paper designed the intrusion detection systems for determining the intrusions. Here, Adam Improved rider optimization approach (Adam IROA) is newly developed for detecting the intrusion in intrusion detection. Accordingly, the training of DeepRNN is done by proposed Adam IROA, which is designed by combining the Adam optimization algorithm with IROA. Thus, the newly developed Adam IROA is applied for intrusion detection. Overall, two phases are included in the proposed intrusion detection system, which involves feature selection and classification. Here, the features selection is done using proposed WWIROA to select significant features from the input data. The proposed WWIROA is developed by combining WWO and IROA. The obtained features are fed to the classification module for discovering the intrusions present in the network. Here, the classification is progressed using Adam IROA-based DeepRNN. The proposed Adam IROA-based DeepRNN achieves maximal accuracy of 0.937, maximal sensitivity of 0.952, and maximal specificity of 0.908 based on SCADA dataset.

Video summarization is used to generate a short summary video for providing the users a very useful visual and synthetic abstract of the video content. There are various methods are developed for... Show More

Video summarization is used to generate a short summary video for providing the users a very useful visual and synthetic abstract of the video content. There are various methods are developed for video summarization in existing, still an effective method is required due to some drawbacks, like cost and time. The ultimate goal of the research is to concentrate on an effective video summarization methodology that represents the development of short summary from the entire video stream in an effective manner. At first, the input cricket video consisting of number of frames is given to the keyframe generation phase, which is performed based on Discrete Cosine Transform (DCT) and Euclidean distance for obtaining the keyframes. Then, the residual keyframe generation is carried out based on Deep Convolutional Neural Network (DCNN), which is trained optimally using the proposed Exponential weighed moving average-Jaya (EWMA-Jaya) optimization.