soumen kanrar - Academia.edu (original) (raw)
Papers by soumen kanrar
2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 2016
This paper presents Fast load balancing technique inspired by Bioinformatics is a special case to... more This paper presents Fast load balancing technique inspired by Bioinformatics is a special case to assign a particular patient with a specialist physician cluster at real time. The work is considered soft presentation of the Gaussian mixture model based on the extracted features supplied by patients. Based on the likelihood ratio test, the patient is assigned to a specialist physician cluster. The presented algorithms efficiently handle any size and any numbers of incoming patient requests and rapidly placed them to the specialist physician cluster. Hence it smoothly balances the traffic load of patients even at a hazard situation in the case of natural calamities. The simulation results are presented with variable size of specialist physician clusters that well address the issue for randomly growing patient size.
A Study on Image Restoration and Analysis
Transactions on Computer Systems and Networks, 2022
Dimension Compactness in Speaker Identification
Proceedings of the International Conference on Informatics and Analytics, 2016
The automatic speaker identification procedure is used to extract features that help to identify ... more The automatic speaker identification procedure is used to extract features that help to identify the components of the acoustic signal by discarding all the other stuff like background noise, emotion, hesitation, etc. The acoustic signal is generated by a human that is filtered by the shape of the vocal tract, including tongue, teeth, etc. The shape of the vocal tract determines and produced, what signal comes out in real time. The analytically develops shape of the vocal tract, which exhibits envelop for the short time power spectrum. The ASR needs efficient way of extracting features from the acoustic signal that is used effectively to makes the shape of the individual vocal tract. To identify any acoustic signal in the large collection of acoustic signal i.e. corpora, it needs dimension compactness of total variability space by using the GMM mean supervector. This work presents the efficient way to implement dimension compactness in total variability space and using cosine distance scoring to predict a fast output score for small size utterance.
Video traffic analytics for large scale surveillance
Multimedia Tools and Applications, 2016
The video traffic analysis is the most important issue for large scale surveillance. In the large... more The video traffic analysis is the most important issue for large scale surveillance. In the large scale surveillance system, huge amount of live digital video data is submitted to the storage servers through the number of externally connected scalable components. The system also contains huge amount of popular and unpopular old videos in the archived storage servers. The video data is delivered to the viewers, partly or completely on demand through a compact system. In real time, huge amount of video data is imported to the viewer’s node for various analysis purposes. The viewers use a number of interactive operations during the real time tracking suspect. The compact video on demand system is used in peer to peer mesh type hybrid architecture. The chunk of video objects move fast through the real time generated compact topological space. Video traffic analytics is required to transfer compressed multimedia data efficiently. In this work, we present a dynamically developed topological space, using mixed strategy by game approach to move the video traffic faster. The simulation results are well addressed in real life scenario.
Multimedia Tools and Applications, 2016
In order to enhance the healthcare system, we have designed and developed a system prototype whic... more In order to enhance the healthcare system, we have designed and developed a system prototype which remotely monitors patient's vital parameters by using mobile based android application. Proposed E-health care system collects patient's biological and personal information with the corresponding vital parameters and stores this Meta data information into the health care database servers. The distributed servers are connected with GSP system. So the extracted information from the server is directly feed to the doctor's mobile device as well as to the patient's mobile devices in a presentable format. This system also uses Frontline SMS as an SMS service which is used to send SMS to the doctor's mobile device automatically, when any one of the patient's vital parameter goes out of normal range. In this paper, we present the GMM (Gaussian mixture model) based on extracted features of the patient information and assign it to the specialized doctor. In this work, we have shown that by GMM based algorithm efficiently balances the patient load to the doctor. This novel approach enhances the E-health monitoring system for normal situations as well as in the case of Natural disaster. The proposed load balancing approach gives relief to the patient for unnecessary long delay to receive medical advice. The presented result in this work shown that, the doctors from all category and specialization are loaded rationally and uniformly. According to our knowledge GMM based approach is the new additional component to enhance the E-health care system.
Efficient Video Streaming for Interactive Session
Proceedings of the 8th Annual ACM India Conference on - Compute '15, 2015
Over the decades, researchers are trying to find an effective methodology for smooth uninterrupte... more Over the decades, researchers are trying to find an effective methodology for smooth uninterrupted multimedia data streaming through the broad band network in video on demand system. The problem is directly related to the efficiently use of methodology in the next generation network. The performance of the data streaming is largely depended upon the adaptability of the methodology to the user dynamic requirement for bandwidth in any interactive session. The users are largely interested to use interactive operation during the real-time video watching at user ends. The bandwidth utilization be good, if the data stream is served from the local site, if the local site cannot serve, then that will be served from the remotely distributed storage architecture. The submitted requests are exponentially increased with respect to the geographic location for any interactive session. In this work, we have presented the multimedia storage architecture in the distributed system environment, i.e. local proxy servers, remote data storages clusters and the role of a cluster switch. The proposed methodology is working for proxy server with a total bandwidth capacity divided into the number of sections.
Dynamic Page Replacement at the Cache Memory for the Video on Demand Server
Smart Innovation, Systems and Technologies, 2014
The audio/video stream retrieves from the storage server depends upon the cache refreshment polic... more The audio/video stream retrieves from the storage server depends upon the cache refreshment polices. The replacement policy depends upon the efficiency of handle the cache hit ratio and cache miss ratio at real time. The cache size is limited with compare to the auxiliary memory size, and it is only the fraction of the auxiliary memory. The cache memory maintains two blocks one for the Least Recently Used (LRU) and other for the Least Frequency Used (LFU). The Least Recently Frequency used (LRFU) pages store into the cache memory. Since the size of the cache is limited by using the exponential smoothing parameter, dynamically the cache replaces the page with the smallest hit count from the LRU. The request page from the submitted request stream increment the hit counts for the already listed pages. In this paper, we present the LRFU polices and the impact of that polices for the limited cache size with a huge submitted stream of requests in a very small interval of time.
Detect Mimicry by Enhancing the Speaker Recognition System
Advances in Intelligent Systems and Computing, 2015
Mimicry voice sample is a potential challenge to the speaker verification system. The system perf... more Mimicry voice sample is a potential challenge to the speaker verification system. The system performance is highly depended on the equal error rate. If the false accept to reduce, then the equal error rate decrease. The speaker verification process, verifies the claim voice is originally produced by the said speaker or not. The verification process is highly depended upon the biometric features carried out by the acoustic signal. The pitch count, phoneme recognition, cepstral coefficients are the major components to verify the claim voice signal. This paper shows a novel frame work to verify the mimicry voice signal through the two-stage testing. The first stage is GMM based speaker identification. The second stage of testing filters the identification through the various biometric feature’s comparisons.
ArXiv, 2017
Speaker Identification process is to identify a particular vocal cord from a set of existing spea... more Speaker Identification process is to identify a particular vocal cord from a set of existing speakers. In the speaker identification processes, unknown speaker voice sample targets each of the existing speakers present in the system and gives a predication. The predication may be more than one existing known speaker voice and is very close to the unknown speaker voice. The model is a Gaussian mixture model built by the extracted acoustic feature vectors from voice. The i-vector based dimension compression mapping function of the channel depended speaker, and super vector give better predicted scores according to cosine distance scoring associated with the order pair of speakers. In the order pair, the first coordinate is the unknown speaker i.e. test speaker, and the second coordinates is the existing known speaker i.e. target speaker. This paper presents the enhancement of the prediction based on i- vector in compare to the normalized set of predicted score. In the simulation, know...
Robust Threshold Selection for Environment Specific Voice in Speaker Recognition
Wireless Personal Communications
Optimize Flooding in Wireless Mesh Cloud
Abstract:- The Wireless mesh Network (WMN) is an emerging multi hop, heterogeneous, scalable, low... more Abstract:- The Wireless mesh Network (WMN) is an emerging multi hop, heterogeneous, scalable, low cost, with easy main-tenance robust network providing reliable service coverage. The architecture of WMNs is a connectionless –oriented, and consists of mesh routers and mesh clients. In this architecture, static mesh routers form the wireless backbone, mesh clients access the network through mesh routers as well as directly meshing with each other. The WMN is dynamically self-organized and self-configured and self heal. To maintain the efficient performance and the connectivity in the wireless mesh cloud, The design architecture is important reduce the redundant packet in the wireless mesh cloud.
Research Journal of Information Technology, 2017
Vehicle Detection and Count in the Captured Stream Video Using Machine Learning
Women facing Colonial Justice. Criminal women in Belgian Congo during the interwar
Text and Language Independent Speaker Identification by GMM based i Vector
Speaker Identification process is to identify a particular vocal cord from a set of existing spea... more Speaker Identification process is to identify a particular vocal cord from a set of existing speakers. In the speaker identification processes, unknown speaker voice sample targets each of the existing speakers present in the system and gives a predication. The predication may be more than one existing known speaker voice and is very close to the unknown speaker voice. The model is a Gaussian mixture model built by the extracted acoustic feature vectors from voice. The i-vector based dimension compression mapping function of the channel depended speaker, and super vector give better predicted scores according to cosine distance scoring associated with the order pair of speakers. In the order pair, the first coordinate is the unknown speaker i.e. test speaker, and the second coordinates is the existing known speaker i.e. target speaker. This paper presents the enhancement of the prediction based on i- vector in compare to the normalized set of predicted score. In the simulation, know...
2017 International Conference on Intelligent Computing and Control Systems (ICICCS), 2017
Bandwidth optimization for real-time video traffic transmission through the proxy server is a cha... more Bandwidth optimization for real-time video traffic transmission through the proxy server is a challenging issue for the next-generation network. The self — control of the traffic rate at the proxy server is based on the relative data present in the proxy server or to import the require data from the remote data center node. The smoothness of traffic transmission is highly depended on the self-configuration in the cache memory at the proxy server by used of optimized page replacement procedure. The web proxy cache memory is finite in size. The system performance is highly depended upon the self-optimization of the traffic rate at the proxy server. This paper presents the effect of zipf-distribution parameters to the outbound request and the effect of the parameters to measure the bandwidth requirement for the desire video file. This paper presents some of the relevant results for bandwidth optimization and the effect of traffic control during active transmission for various sizes of ...
Skin Cancer Detection Using Convolutional Neural Network
Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence - ICCAI '19, 2019
Skin cancer is an alarming disease for mankind. The necessity of early diagnosis of the skin canc... more Skin cancer is an alarming disease for mankind. The necessity of early diagnosis of the skin cancer have been increased because of the rapid growth rate of Melanoma skin cancer, itś high treatment costs, and death rate. This cancer cells are detected manually and it takes time to cure in most of the cases. This paper proposed an artificial skin cancer detection system using image processing and machine learning method. The features of the affected skin cells are extracted after the segmentation of the dermoscopic images using feature extraction technique. A deep learning based method convolutional neural network classifier is used for the stratification of the extracted features. An accuracy of 89.5% and the training accuracy of 93.7% have been achieved after applying the publicly available data set.
Pedestrian localisation in the typical indoor environments
Multimedia Tools and Applications, 2020
The world is adopting complete wireless infrastructure to cover small size buildings as well as l... more The world is adopting complete wireless infrastructure to cover small size buildings as well as large geographical regions. Indoor Positioning System (IPS) is used to locate stationary as well as non-stationary objects in the wireless domain. The indoor localisation of a pedestrian remains an open problem in the noisy environment. Researchers are trying to develop low-complexity approach without depending on building infrastructure to achieve accurate and reliable results for pedestrian localisation in noisy environment. We are proposed the problem associated with improving localisation scalability and accuracy by considering the noisy environment. Our propose methodology exhibits robustness and portability with respect to the number of experiments in noisy environment with the help of captured signal strength. The propose methodology is easily applied in various indoor environments (i.e. different building designs) to locate the stationary and non-stationary object. The collected multimodal data of non-stationary targets in the noisy environment is required to enhance further. The collected multimodal data is used to explore specific movement of the pedestrian in the noisy environment. We consider numerical methods to make the shape of hot-spot contour for a specific target. Principal Component Analysis (PCA) based data science is used to obtain the predominant components in the collected information and make a compact contour in the noisy environment. The generated model depicts a highly sensitive region in the noisy environment due to the presence of thick walls inside the building and multipath fading. Our novel methodology exhibits efficient localisation of the non-stationary target or precisely identifies the moving object, on the floor of a multi- storey building. Our novel approach enhances the technique to improve surveillance and security for the noisy indoor environment.
Optimize Task Allocation in Cloud Environment Based on Big-Bang Big-Crunch
Wireless Personal Communications, 2020
Efficient resource allocation is indispensable in the current scenario of a service-oriented comp... more Efficient resource allocation is indispensable in the current scenario of a service-oriented computing paradigm. Instance allocation to the host and the task allocation to the instance depends on the efficiency of scheduling technique. In this work, we exhibit the provisioning of tasks or cloudlets on a virtual machine. The Big-Bang Big-Crunch-cost model is proposed for efficient resource allocation. The proposed technique supports the principle of optimization method and performance is measured using makespan and resource cost. Our proposed cost-aware Big-Bang- Big-Crunch model, provides an optimal solution using the IaaS (Infrastructure as a service) model. It supports dynamic and independent task allocation on virtual machines. The proposed technique proclaims an evolution scheme that measures an objective function depends on performance metrics cost and time respectively. The input dataset defines the number of host nodes and datacenter configuration. The learning, evolution-based on BB-BC cost-aware method provides a globally optimal solution in a dynamic resource provisioning environment. Our approach effectively finds optimal simulation results than existing static, dynamic, and bio-inspired evolutionary provisioning techniques. Simulation results are exhibited that the cost-aware Big-Bang Big-Crunch method illustrates an adequate schedule of tasks on respective virtual machines. Reliability is measured using the operational cost of the resources in execution duration. Efficient resource utilization and the global optimum solution depends on the fitness function. The simulation results illustrate that our cost-aware astrology based soft computing methodology provides better results than time aware and cost-aware scheduling approaches. From simulation results, it is observed that Big-Bang Big-Crunch Cost aware proposed methodology improves average finish time by 15.23% with user requests 300, and average finish time improves by 19.18% with population size 400. The performance metric average resource cost enhancement by 30.46% with population size 400. The infrastructure cloud is considered for the performance measurement of the proposed cost-aware model which is constituted using static, dynamic, and meta-heuristic bio-inspired resource allocation techniques.
Before squamous cell lung cancer develops, pre-cancerous lesions can be found in the airways. Fro... more Before squamous cell lung cancer develops, pre-cancerous lesions can be found in the airways. From longitudinal monitoring, we know that only half of such lesions become cancer, whereas a third spontaneously regress. While recent studies have described the presence of an active immune response in high-grade lesions, the mechanisms underpinning clinical regression of pre-cancerous lesions remain unknown. Here, we show that host immune surveillance is strongly implicated in lesion regression. Using bronchoscopic biopsies from human subjects, we find that regressive carcinoma in-situ lesions harbour more infiltrating immune cells than those that progress to cancer. Moreover, molecular profiling of these lesions identifies potential immune escape mechanisms specifically in those that progress to cancer: antigen presentation is impaired by genomic and epigenetic changes, TGF-beta signalling is overactive, and the immunomodulator TNFSF9 is downregulated. Changes appear intrinsic to the CI...
2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 2016
This paper presents Fast load balancing technique inspired by Bioinformatics is a special case to... more This paper presents Fast load balancing technique inspired by Bioinformatics is a special case to assign a particular patient with a specialist physician cluster at real time. The work is considered soft presentation of the Gaussian mixture model based on the extracted features supplied by patients. Based on the likelihood ratio test, the patient is assigned to a specialist physician cluster. The presented algorithms efficiently handle any size and any numbers of incoming patient requests and rapidly placed them to the specialist physician cluster. Hence it smoothly balances the traffic load of patients even at a hazard situation in the case of natural calamities. The simulation results are presented with variable size of specialist physician clusters that well address the issue for randomly growing patient size.
A Study on Image Restoration and Analysis
Transactions on Computer Systems and Networks, 2022
Dimension Compactness in Speaker Identification
Proceedings of the International Conference on Informatics and Analytics, 2016
The automatic speaker identification procedure is used to extract features that help to identify ... more The automatic speaker identification procedure is used to extract features that help to identify the components of the acoustic signal by discarding all the other stuff like background noise, emotion, hesitation, etc. The acoustic signal is generated by a human that is filtered by the shape of the vocal tract, including tongue, teeth, etc. The shape of the vocal tract determines and produced, what signal comes out in real time. The analytically develops shape of the vocal tract, which exhibits envelop for the short time power spectrum. The ASR needs efficient way of extracting features from the acoustic signal that is used effectively to makes the shape of the individual vocal tract. To identify any acoustic signal in the large collection of acoustic signal i.e. corpora, it needs dimension compactness of total variability space by using the GMM mean supervector. This work presents the efficient way to implement dimension compactness in total variability space and using cosine distance scoring to predict a fast output score for small size utterance.
Video traffic analytics for large scale surveillance
Multimedia Tools and Applications, 2016
The video traffic analysis is the most important issue for large scale surveillance. In the large... more The video traffic analysis is the most important issue for large scale surveillance. In the large scale surveillance system, huge amount of live digital video data is submitted to the storage servers through the number of externally connected scalable components. The system also contains huge amount of popular and unpopular old videos in the archived storage servers. The video data is delivered to the viewers, partly or completely on demand through a compact system. In real time, huge amount of video data is imported to the viewer’s node for various analysis purposes. The viewers use a number of interactive operations during the real time tracking suspect. The compact video on demand system is used in peer to peer mesh type hybrid architecture. The chunk of video objects move fast through the real time generated compact topological space. Video traffic analytics is required to transfer compressed multimedia data efficiently. In this work, we present a dynamically developed topological space, using mixed strategy by game approach to move the video traffic faster. The simulation results are well addressed in real life scenario.
Multimedia Tools and Applications, 2016
In order to enhance the healthcare system, we have designed and developed a system prototype whic... more In order to enhance the healthcare system, we have designed and developed a system prototype which remotely monitors patient's vital parameters by using mobile based android application. Proposed E-health care system collects patient's biological and personal information with the corresponding vital parameters and stores this Meta data information into the health care database servers. The distributed servers are connected with GSP system. So the extracted information from the server is directly feed to the doctor's mobile device as well as to the patient's mobile devices in a presentable format. This system also uses Frontline SMS as an SMS service which is used to send SMS to the doctor's mobile device automatically, when any one of the patient's vital parameter goes out of normal range. In this paper, we present the GMM (Gaussian mixture model) based on extracted features of the patient information and assign it to the specialized doctor. In this work, we have shown that by GMM based algorithm efficiently balances the patient load to the doctor. This novel approach enhances the E-health monitoring system for normal situations as well as in the case of Natural disaster. The proposed load balancing approach gives relief to the patient for unnecessary long delay to receive medical advice. The presented result in this work shown that, the doctors from all category and specialization are loaded rationally and uniformly. According to our knowledge GMM based approach is the new additional component to enhance the E-health care system.
Efficient Video Streaming for Interactive Session
Proceedings of the 8th Annual ACM India Conference on - Compute '15, 2015
Over the decades, researchers are trying to find an effective methodology for smooth uninterrupte... more Over the decades, researchers are trying to find an effective methodology for smooth uninterrupted multimedia data streaming through the broad band network in video on demand system. The problem is directly related to the efficiently use of methodology in the next generation network. The performance of the data streaming is largely depended upon the adaptability of the methodology to the user dynamic requirement for bandwidth in any interactive session. The users are largely interested to use interactive operation during the real-time video watching at user ends. The bandwidth utilization be good, if the data stream is served from the local site, if the local site cannot serve, then that will be served from the remotely distributed storage architecture. The submitted requests are exponentially increased with respect to the geographic location for any interactive session. In this work, we have presented the multimedia storage architecture in the distributed system environment, i.e. local proxy servers, remote data storages clusters and the role of a cluster switch. The proposed methodology is working for proxy server with a total bandwidth capacity divided into the number of sections.
Dynamic Page Replacement at the Cache Memory for the Video on Demand Server
Smart Innovation, Systems and Technologies, 2014
The audio/video stream retrieves from the storage server depends upon the cache refreshment polic... more The audio/video stream retrieves from the storage server depends upon the cache refreshment polices. The replacement policy depends upon the efficiency of handle the cache hit ratio and cache miss ratio at real time. The cache size is limited with compare to the auxiliary memory size, and it is only the fraction of the auxiliary memory. The cache memory maintains two blocks one for the Least Recently Used (LRU) and other for the Least Frequency Used (LFU). The Least Recently Frequency used (LRFU) pages store into the cache memory. Since the size of the cache is limited by using the exponential smoothing parameter, dynamically the cache replaces the page with the smallest hit count from the LRU. The request page from the submitted request stream increment the hit counts for the already listed pages. In this paper, we present the LRFU polices and the impact of that polices for the limited cache size with a huge submitted stream of requests in a very small interval of time.
Detect Mimicry by Enhancing the Speaker Recognition System
Advances in Intelligent Systems and Computing, 2015
Mimicry voice sample is a potential challenge to the speaker verification system. The system perf... more Mimicry voice sample is a potential challenge to the speaker verification system. The system performance is highly depended on the equal error rate. If the false accept to reduce, then the equal error rate decrease. The speaker verification process, verifies the claim voice is originally produced by the said speaker or not. The verification process is highly depended upon the biometric features carried out by the acoustic signal. The pitch count, phoneme recognition, cepstral coefficients are the major components to verify the claim voice signal. This paper shows a novel frame work to verify the mimicry voice signal through the two-stage testing. The first stage is GMM based speaker identification. The second stage of testing filters the identification through the various biometric feature’s comparisons.
ArXiv, 2017
Speaker Identification process is to identify a particular vocal cord from a set of existing spea... more Speaker Identification process is to identify a particular vocal cord from a set of existing speakers. In the speaker identification processes, unknown speaker voice sample targets each of the existing speakers present in the system and gives a predication. The predication may be more than one existing known speaker voice and is very close to the unknown speaker voice. The model is a Gaussian mixture model built by the extracted acoustic feature vectors from voice. The i-vector based dimension compression mapping function of the channel depended speaker, and super vector give better predicted scores according to cosine distance scoring associated with the order pair of speakers. In the order pair, the first coordinate is the unknown speaker i.e. test speaker, and the second coordinates is the existing known speaker i.e. target speaker. This paper presents the enhancement of the prediction based on i- vector in compare to the normalized set of predicted score. In the simulation, know...
Robust Threshold Selection for Environment Specific Voice in Speaker Recognition
Wireless Personal Communications
Optimize Flooding in Wireless Mesh Cloud
Abstract:- The Wireless mesh Network (WMN) is an emerging multi hop, heterogeneous, scalable, low... more Abstract:- The Wireless mesh Network (WMN) is an emerging multi hop, heterogeneous, scalable, low cost, with easy main-tenance robust network providing reliable service coverage. The architecture of WMNs is a connectionless –oriented, and consists of mesh routers and mesh clients. In this architecture, static mesh routers form the wireless backbone, mesh clients access the network through mesh routers as well as directly meshing with each other. The WMN is dynamically self-organized and self-configured and self heal. To maintain the efficient performance and the connectivity in the wireless mesh cloud, The design architecture is important reduce the redundant packet in the wireless mesh cloud.
Research Journal of Information Technology, 2017
Vehicle Detection and Count in the Captured Stream Video Using Machine Learning
Women facing Colonial Justice. Criminal women in Belgian Congo during the interwar
Text and Language Independent Speaker Identification by GMM based i Vector
Speaker Identification process is to identify a particular vocal cord from a set of existing spea... more Speaker Identification process is to identify a particular vocal cord from a set of existing speakers. In the speaker identification processes, unknown speaker voice sample targets each of the existing speakers present in the system and gives a predication. The predication may be more than one existing known speaker voice and is very close to the unknown speaker voice. The model is a Gaussian mixture model built by the extracted acoustic feature vectors from voice. The i-vector based dimension compression mapping function of the channel depended speaker, and super vector give better predicted scores according to cosine distance scoring associated with the order pair of speakers. In the order pair, the first coordinate is the unknown speaker i.e. test speaker, and the second coordinates is the existing known speaker i.e. target speaker. This paper presents the enhancement of the prediction based on i- vector in compare to the normalized set of predicted score. In the simulation, know...
2017 International Conference on Intelligent Computing and Control Systems (ICICCS), 2017
Bandwidth optimization for real-time video traffic transmission through the proxy server is a cha... more Bandwidth optimization for real-time video traffic transmission through the proxy server is a challenging issue for the next-generation network. The self — control of the traffic rate at the proxy server is based on the relative data present in the proxy server or to import the require data from the remote data center node. The smoothness of traffic transmission is highly depended on the self-configuration in the cache memory at the proxy server by used of optimized page replacement procedure. The web proxy cache memory is finite in size. The system performance is highly depended upon the self-optimization of the traffic rate at the proxy server. This paper presents the effect of zipf-distribution parameters to the outbound request and the effect of the parameters to measure the bandwidth requirement for the desire video file. This paper presents some of the relevant results for bandwidth optimization and the effect of traffic control during active transmission for various sizes of ...
Skin Cancer Detection Using Convolutional Neural Network
Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence - ICCAI '19, 2019
Skin cancer is an alarming disease for mankind. The necessity of early diagnosis of the skin canc... more Skin cancer is an alarming disease for mankind. The necessity of early diagnosis of the skin cancer have been increased because of the rapid growth rate of Melanoma skin cancer, itś high treatment costs, and death rate. This cancer cells are detected manually and it takes time to cure in most of the cases. This paper proposed an artificial skin cancer detection system using image processing and machine learning method. The features of the affected skin cells are extracted after the segmentation of the dermoscopic images using feature extraction technique. A deep learning based method convolutional neural network classifier is used for the stratification of the extracted features. An accuracy of 89.5% and the training accuracy of 93.7% have been achieved after applying the publicly available data set.
Pedestrian localisation in the typical indoor environments
Multimedia Tools and Applications, 2020
The world is adopting complete wireless infrastructure to cover small size buildings as well as l... more The world is adopting complete wireless infrastructure to cover small size buildings as well as large geographical regions. Indoor Positioning System (IPS) is used to locate stationary as well as non-stationary objects in the wireless domain. The indoor localisation of a pedestrian remains an open problem in the noisy environment. Researchers are trying to develop low-complexity approach without depending on building infrastructure to achieve accurate and reliable results for pedestrian localisation in noisy environment. We are proposed the problem associated with improving localisation scalability and accuracy by considering the noisy environment. Our propose methodology exhibits robustness and portability with respect to the number of experiments in noisy environment with the help of captured signal strength. The propose methodology is easily applied in various indoor environments (i.e. different building designs) to locate the stationary and non-stationary object. The collected multimodal data of non-stationary targets in the noisy environment is required to enhance further. The collected multimodal data is used to explore specific movement of the pedestrian in the noisy environment. We consider numerical methods to make the shape of hot-spot contour for a specific target. Principal Component Analysis (PCA) based data science is used to obtain the predominant components in the collected information and make a compact contour in the noisy environment. The generated model depicts a highly sensitive region in the noisy environment due to the presence of thick walls inside the building and multipath fading. Our novel methodology exhibits efficient localisation of the non-stationary target or precisely identifies the moving object, on the floor of a multi- storey building. Our novel approach enhances the technique to improve surveillance and security for the noisy indoor environment.
Optimize Task Allocation in Cloud Environment Based on Big-Bang Big-Crunch
Wireless Personal Communications, 2020
Efficient resource allocation is indispensable in the current scenario of a service-oriented comp... more Efficient resource allocation is indispensable in the current scenario of a service-oriented computing paradigm. Instance allocation to the host and the task allocation to the instance depends on the efficiency of scheduling technique. In this work, we exhibit the provisioning of tasks or cloudlets on a virtual machine. The Big-Bang Big-Crunch-cost model is proposed for efficient resource allocation. The proposed technique supports the principle of optimization method and performance is measured using makespan and resource cost. Our proposed cost-aware Big-Bang- Big-Crunch model, provides an optimal solution using the IaaS (Infrastructure as a service) model. It supports dynamic and independent task allocation on virtual machines. The proposed technique proclaims an evolution scheme that measures an objective function depends on performance metrics cost and time respectively. The input dataset defines the number of host nodes and datacenter configuration. The learning, evolution-based on BB-BC cost-aware method provides a globally optimal solution in a dynamic resource provisioning environment. Our approach effectively finds optimal simulation results than existing static, dynamic, and bio-inspired evolutionary provisioning techniques. Simulation results are exhibited that the cost-aware Big-Bang Big-Crunch method illustrates an adequate schedule of tasks on respective virtual machines. Reliability is measured using the operational cost of the resources in execution duration. Efficient resource utilization and the global optimum solution depends on the fitness function. The simulation results illustrate that our cost-aware astrology based soft computing methodology provides better results than time aware and cost-aware scheduling approaches. From simulation results, it is observed that Big-Bang Big-Crunch Cost aware proposed methodology improves average finish time by 15.23% with user requests 300, and average finish time improves by 19.18% with population size 400. The performance metric average resource cost enhancement by 30.46% with population size 400. The infrastructure cloud is considered for the performance measurement of the proposed cost-aware model which is constituted using static, dynamic, and meta-heuristic bio-inspired resource allocation techniques.
Before squamous cell lung cancer develops, pre-cancerous lesions can be found in the airways. Fro... more Before squamous cell lung cancer develops, pre-cancerous lesions can be found in the airways. From longitudinal monitoring, we know that only half of such lesions become cancer, whereas a third spontaneously regress. While recent studies have described the presence of an active immune response in high-grade lesions, the mechanisms underpinning clinical regression of pre-cancerous lesions remain unknown. Here, we show that host immune surveillance is strongly implicated in lesion regression. Using bronchoscopic biopsies from human subjects, we find that regressive carcinoma in-situ lesions harbour more infiltrating immune cells than those that progress to cancer. Moreover, molecular profiling of these lesions identifies potential immune escape mechanisms specifically in those that progress to cancer: antigen presentation is impaired by genomic and epigenetic changes, TGF-beta signalling is overactive, and the immunomodulator TNFSF9 is downregulated. Changes appear intrinsic to the CI...
Mimicry voice sample is a potential challenge to the speaker verification system. The system perf... more Mimicry voice sample is a potential challenge to the speaker verification system. The system performance is highly depended on the equal error rate. If the false accept to reduce, then the equal error rate decrease. The speaker verification process, verifies the claim voice is originally produced by the said speaker or not. The verification process is highly depended upon the biometric features carried out by the acoustic signal. The pitch count, phoneme recognition, cepstral coefficients are the major components to verify the claim voice signal. This paper shows a novel frame work to verify the mimicry voice signal through the two-stage testing. The first stage is GMM based speaker identification. The second stage of testing filters the identification through the various biometric feature's comparisons.