Wireless Sensor Networks(WSNs)comprises low power devices that are randomly distributed in a geographically isolated region.The energy consumption of nodes is an essential factor to be considered.Therefore,an improved...Wireless Sensor Networks(WSNs)comprises low power devices that are randomly distributed in a geographically isolated region.The energy consumption of nodes is an essential factor to be considered.Therefore,an improved energy management technique is designed in this investigation to reduce its consumption and to enhance the network’s lifetime.This can be attained by balancing energy clusters using a meta-heuristic Firefly algorithm model for network communication.This improved technique is based on the cluster head selection technique with measurement of the tour length of fireflies.Time Division Multiple Access(TDMA)scheduler is also improved with the characteristics/behavior of fireflies and also executed.At last,the development approach shows the progression of the network lifetime,the total number of selected Cluster Heads(CH),the energy consumed by nodes,and the number of packets transmitted.This approach is compared with Ad hoc On-Demand Distance Vector(AODV),Dynamic Source Routing(DSR)and Low Energy Adaptive Clustering Hierarchy(LEAH)protocols.Simulation is performed in MATLAB with the numerical outcomes showing the efficiency of the proposed approach.The energy consumption of sensor nodes is reduced by about 50%and increases the lifetime of nodes by 78%more than AODV,DSR and LEACH protocols.The parameters such as cluster formation,end to end delay,percentage of nodes alive and packet delivery ratio,are also evaluated...The anticipated method shows better trade-off in contrast to existing techniques.展开更多
The latest advancements in highway research domain and increase in the number of vehicles everyday led to wider exposure and attention towards the development of efficient Intelligent Transportation System(ITS).One of...The latest advancements in highway research domain and increase in the number of vehicles everyday led to wider exposure and attention towards the development of efficient Intelligent Transportation System(ITS).One of the popular research areas i.e.,Vehicle License Plate Recognition(VLPR)aims at determining the characters that exist in the license plate of the vehicles.The VLPR process is a difficult one due to the differences in viewpoint,shapes,colors,patterns,and non-uniform illumination at the time of capturing images.The current study develops a robust Deep Learning(DL)-based VLPR model using Squirrel Search Algorithm(SSA)-based Convolutional Neural Network(CNN),called the SSA-CNN model.The presented technique has a total of four major processes namely preprocessing,License Plate(LP)localization and detection,character segmentation,and recognition.Hough Transform(HT)is applied as a feature extractor and SSA-CNN algorithm is applied for character recognition in LP.The SSA-CNN method effectively recognizes the characters that exist in the segmented image by optimal tuning of CNN parameters.The HT-SSA-CNN model was experimentally validated using the Stanford Car,FZU Car,and HumAIn 2019 Challenge datasets.The experimentation outcome verified that the presented method was better under several aspects.The projected HT-SSA-CNN model implied the best performance with optimal overall accuracy of 0.983%.展开更多
Wireless Sensor Networks(WSN)has been extensively utilized as a communication model in Internet of Things(IoT).As well,to offer service,numerous IoT based applications need effective transmission over unstable locatio...Wireless Sensor Networks(WSN)has been extensively utilized as a communication model in Internet of Things(IoT).As well,to offer service,numerous IoT based applications need effective transmission over unstable locations.To ensure reliability,prevailing investigations exploit multiple candidate forwarders over geographic opportunistic routing in WSNs.Moreover,these models are affected by crucial denial of service(DoS)attacks,where huge amount of invalid data are delivered intentionally to the receivers to disturb the functionality of WSNs.Here,secure localization based authentication(SLA)is presented to fight against DoS attack,and to fulfil the need of reliability and authentication.By examining state information,SLA projects a trust model to enhance efficacy of data delivery.Indeed,of the prevailing opportunistic protocols,SLA guarantees data integrity by modelling a trust based authentication,providing protection against DoS attackers and diminishing computational costs.Specifically,this model acts as a verification strategy to accelerate?attackers and to handle isolation.This strategy helps SLA in eliminating duplicate transmission and by continuous verification that results from conventional opportunistic routing.Simulation is performed in a MATLAB environment that offers authentic and reliable delivery by consuming approximately 50%of the cost in contrast to other approaches.The anticipated model shows better trade off in comparison to the prevailing ones.展开更多
The perfect image retrieval and retrieval time are the two major challenges inCBIR systems. To improve the retrieval accuracy, the whole database is searched basedon many image characteristics such as color, shape, te...The perfect image retrieval and retrieval time are the two major challenges inCBIR systems. To improve the retrieval accuracy, the whole database is searched basedon many image characteristics such as color, shape, texture and edge information whichleads to more time consumption. This paper presents a new fuzzy based CBIR method,which utilizes colour, shape and texture attributes of the image. Fuzzy rule based systemis developed by combining color, shape, and texture feature for enhanced image recovery.In this approach, DWT is used to pull out the texture characteristics and the region basedmoment invariant is utilized to pull out the shape features of an image. Color similarityand texture attributes are extorted using customized Color Difference Histogram (CDH).The performance evaluation based on precision and BEP measures reveals the superiorityof the proposed method over renowned obtainable approaches.展开更多
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 pe...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.展开更多
文摘Wireless Sensor Networks(WSNs)comprises low power devices that are randomly distributed in a geographically isolated region.The energy consumption of nodes is an essential factor to be considered.Therefore,an improved energy management technique is designed in this investigation to reduce its consumption and to enhance the network’s lifetime.This can be attained by balancing energy clusters using a meta-heuristic Firefly algorithm model for network communication.This improved technique is based on the cluster head selection technique with measurement of the tour length of fireflies.Time Division Multiple Access(TDMA)scheduler is also improved with the characteristics/behavior of fireflies and also executed.At last,the development approach shows the progression of the network lifetime,the total number of selected Cluster Heads(CH),the energy consumed by nodes,and the number of packets transmitted.This approach is compared with Ad hoc On-Demand Distance Vector(AODV),Dynamic Source Routing(DSR)and Low Energy Adaptive Clustering Hierarchy(LEAH)protocols.Simulation is performed in MATLAB with the numerical outcomes showing the efficiency of the proposed approach.The energy consumption of sensor nodes is reduced by about 50%and increases the lifetime of nodes by 78%more than AODV,DSR and LEACH protocols.The parameters such as cluster formation,end to end delay,percentage of nodes alive and packet delivery ratio,are also evaluated...The anticipated method shows better trade-off in contrast to existing techniques.
文摘The latest advancements in highway research domain and increase in the number of vehicles everyday led to wider exposure and attention towards the development of efficient Intelligent Transportation System(ITS).One of the popular research areas i.e.,Vehicle License Plate Recognition(VLPR)aims at determining the characters that exist in the license plate of the vehicles.The VLPR process is a difficult one due to the differences in viewpoint,shapes,colors,patterns,and non-uniform illumination at the time of capturing images.The current study develops a robust Deep Learning(DL)-based VLPR model using Squirrel Search Algorithm(SSA)-based Convolutional Neural Network(CNN),called the SSA-CNN model.The presented technique has a total of four major processes namely preprocessing,License Plate(LP)localization and detection,character segmentation,and recognition.Hough Transform(HT)is applied as a feature extractor and SSA-CNN algorithm is applied for character recognition in LP.The SSA-CNN method effectively recognizes the characters that exist in the segmented image by optimal tuning of CNN parameters.The HT-SSA-CNN model was experimentally validated using the Stanford Car,FZU Car,and HumAIn 2019 Challenge datasets.The experimentation outcome verified that the presented method was better under several aspects.The projected HT-SSA-CNN model implied the best performance with optimal overall accuracy of 0.983%.
文摘Wireless Sensor Networks(WSN)has been extensively utilized as a communication model in Internet of Things(IoT).As well,to offer service,numerous IoT based applications need effective transmission over unstable locations.To ensure reliability,prevailing investigations exploit multiple candidate forwarders over geographic opportunistic routing in WSNs.Moreover,these models are affected by crucial denial of service(DoS)attacks,where huge amount of invalid data are delivered intentionally to the receivers to disturb the functionality of WSNs.Here,secure localization based authentication(SLA)is presented to fight against DoS attack,and to fulfil the need of reliability and authentication.By examining state information,SLA projects a trust model to enhance efficacy of data delivery.Indeed,of the prevailing opportunistic protocols,SLA guarantees data integrity by modelling a trust based authentication,providing protection against DoS attackers and diminishing computational costs.Specifically,this model acts as a verification strategy to accelerate?attackers and to handle isolation.This strategy helps SLA in eliminating duplicate transmission and by continuous verification that results from conventional opportunistic routing.Simulation is performed in a MATLAB environment that offers authentic and reliable delivery by consuming approximately 50%of the cost in contrast to other approaches.The anticipated model shows better trade off in comparison to the prevailing ones.
文摘The perfect image retrieval and retrieval time are the two major challenges inCBIR systems. To improve the retrieval accuracy, the whole database is searched basedon many image characteristics such as color, shape, texture and edge information whichleads to more time consumption. This paper presents a new fuzzy based CBIR method,which utilizes colour, shape and texture attributes of the image. Fuzzy rule based systemis developed by combining color, shape, and texture feature for enhanced image recovery.In this approach, DWT is used to pull out the texture characteristics and the region basedmoment invariant is utilized to pull out the shape features of an image. Color similarityand texture attributes are extorted using customized Color Difference Histogram (CDH).The performance evaluation based on precision and BEP measures reveals the superiorityof the proposed method over renowned obtainable approaches.
文摘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.
