Intelligent recognition system for viewpoint variations on gait and speech using CNN-CapsNet

Purpose-The paper aims to introduce an intelligent recognition system for viewpoint variations of gait and speech.It proposes a convolutional neural network-based capsule network(CNN-CapsNet)model and outlining the performance of the system in recognition of gait and speech variations.The proposed intelligent system mainly focuses on relative spatial hierarchies between gait features in the entities of the image due to translational invariances in sub-sampling and speech variations.Design/methodology/approach-This proposed work CNN-CapsNet is mainly used for automatic learning of feature representations based on CNNand used capsule vectors as neurons to encode all the spatial information of an image by adapting equal variances to change in viewpoint.The proposed study will resolve the discrepancies caused by cofactors and gait recognition between opinions based on a model of CNN-CapsNet.Findings-This research work provides recognition of signal,biometric-based gait recognition and sound/speech analysis.Empirical evaluations are conducted on three aspects of scenarios,namely fixed-view,cross-view and multi-view conditions.The main parameters for recognition of gait are speed,change in clothes,subjects walking with carrying object and intensity of light.Research limitations/implications-The proposed CNN-CapsNet has some limitations when considering for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor devices.It can also act as a pre-requisite tool to analyze,identify,detect and verify the malware practices.Practical implications-This research work includes for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor devices.It can also act as a pre-requisite tool to analyze,identify,detect and verify the malware practices.Originality/value-This proposed research work proves to be performing better for the recognition of gait and speech when compared with other techniques.

Integrated dominating and hit set-inspired unequal clusteringbased data aggregation in wireless sensor networks

Purpose-In wireless sensor networks,improving the network lifetime is considered as the prime objective that needs to be significantly addressed during data aggregation.Among the traditional data aggregation techniques,cluster-based dominating set algorithms are identified as more effective in aggregating data through cluster heads.But,the existing cluster-based dominating set algorithms suffer from a major drawback of energy deficiency when a large number of communicating nodes need to collaborate for transferring the aggregated data.Further,due to this reason,the energy of each communicating node is gradually decreased and the network lifetime is also decreased.To increase the lifetime of the network,the proposed algorithm uses two sets:Dominating set and hit set.Design/methodology/approach-The proposed algorithm uses two sets:Dominating set and hit set.The dominating set constructs an unequal clustering,and the hit set minimizes the number of communicating nodes by selecting the optimized cluster head for transferring the aggregated data to the base station.The simulation results also infer that the proposed optimized unequal clustering algorithm(OUCA)is greater in improving the network lifetime to a maximum amount of 22%than the existing cluster head selection approach considered for examination.Findings-In this paper,lifetime of the network is prolonged by constructing an unequal cluster using the dominating set and electing an optimized cluster head using hit set.The dominator set chooses the dominator based on the remaining energy and its node degree of each node.The optimized cluster head is chosen by the hit set to minimize the number of communicating nodes in the network.The proposed algorithm effectively constructs the clusters with a minimum number of communicating nodes using the dominating and hit set.The simulation result confirms that the proposed algorithm prolonging the lifetime of the network efficiently when compared with the existing algorithms.Originality/value-The proposed algorithm effectively constructs the clusters with a minimum number of communicating nodes using the dominating and hit sets.The simulation result confirms that the proposed algorithm is prolonging the lifetime of the network efficiently when compared with the existing algorithms.