Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987917
S. Barath, K. Abhiram, B. Nithin, B. Y. Reddy, V. Kumar
Optimization protocols aim to achieve best data delivery mechanisms, thereby improving the overall network throughout. Optimization also tries to reduce data computations ratio in the entire network aiming to reduce redundant data transmission and avoid mitigating network delay. It involves seamless steps to improve the stabilization and lifetime of the entire network. Optimal ways (paths) could be ascertained using colony strategies or hierarchical clustering. It tries to avoid data loss due to collision and improves the performance.
{"title":"A Survey of path reconstruction approaches by using optimization protocols in WSN","authors":"S. Barath, K. Abhiram, B. Nithin, B. Y. Reddy, V. Kumar","doi":"10.1109/ICSSIT46314.2019.8987917","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987917","url":null,"abstract":"Optimization protocols aim to achieve best data delivery mechanisms, thereby improving the overall network throughout. Optimization also tries to reduce data computations ratio in the entire network aiming to reduce redundant data transmission and avoid mitigating network delay. It involves seamless steps to improve the stabilization and lifetime of the entire network. Optimal ways (paths) could be ascertained using colony strategies or hierarchical clustering. It tries to avoid data loss due to collision and improves the performance.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"286 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123866975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987894
Yanambakkam Hemanth Teja, V. Bhardwaj, Srikanth Kini
The aim of this research is to build an autonomous robot by integrating hardware components such as PIC microcontroller, APR voice module, RSSI module, ultrasonic sensors, GSM module, and DC motor. The proposed robot represents a boat node that is integrated with the Zigbee technology. The ZigBee technology measures the received signal strength (RSSI), which is used to determine the location of the boat node. Furthermore, the autonomous robot node also utilizes ultrasonic sensors in detecting obstacles and avoiding them. The robot is also integrated with computational logic and artificial intelligence that help the robot node in its autonomous path identification. Our proposed work integrates the concepts of embedded systems, internet of things and artificial intelligence to provide a continuous monitoring system that can be useful for maritime purposes.
{"title":"Path Planning and Robot Localization using Internet of Things and Machine Intelligence","authors":"Yanambakkam Hemanth Teja, V. Bhardwaj, Srikanth Kini","doi":"10.1109/ICSSIT46314.2019.8987894","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987894","url":null,"abstract":"The aim of this research is to build an autonomous robot by integrating hardware components such as PIC microcontroller, APR voice module, RSSI module, ultrasonic sensors, GSM module, and DC motor. The proposed robot represents a boat node that is integrated with the Zigbee technology. The ZigBee technology measures the received signal strength (RSSI), which is used to determine the location of the boat node. Furthermore, the autonomous robot node also utilizes ultrasonic sensors in detecting obstacles and avoiding them. The robot is also integrated with computational logic and artificial intelligence that help the robot node in its autonomous path identification. Our proposed work integrates the concepts of embedded systems, internet of things and artificial intelligence to provide a continuous monitoring system that can be useful for maritime purposes.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129169118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987786
Sindhya K. Nambiar, Antony Leons, Soniya Jose, Arunsree
The NLP applications uses the parts of speech tagging as the preprocessing step. For making POS tagging accurate, various techniques have been explored. But in Indian languages, not much work has been done. This paper describes Part of Speech Tagger by incorporating Hidden Markov Model is built. Supervised learning approach is implemented in which, already tagged sentences in Malayalam is used to build Hidden Markov Model.
{"title":"POS Tagger for Malayalam using Hidden Markov Model","authors":"Sindhya K. Nambiar, Antony Leons, Soniya Jose, Arunsree","doi":"10.1109/ICSSIT46314.2019.8987786","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987786","url":null,"abstract":"The NLP applications uses the parts of speech tagging as the preprocessing step. For making POS tagging accurate, various techniques have been explored. But in Indian languages, not much work has been done. This paper describes Part of Speech Tagger by incorporating Hidden Markov Model is built. Supervised learning approach is implemented in which, already tagged sentences in Malayalam is used to build Hidden Markov Model.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129710637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987766
Jabeen Sultana, M. Rani, M. Farquad
Knowledge discovery of educational data plays prominent role in the process of making decisions in order to deliver correct educational reforms. knowledge discovery can be done to extract students' sentiments towards learning behavior of the course, difficulties faced, time spent for the course duration in learning the concepts and worries or fears of students like whether they may pass or fail the final exam. As student feedback is essential to assess the effectiveness of learning technologies, the hidden knowledge of students can be discovered by conducting survey or feedback form or online course satisfaction survey at the end of the courses in order to obtain the meaningful information so that, necessary steps can be taken to improve the learning process. The prime motto of our research is to discover the knowledge from the twitter data and analyze public sentiments towards education using deep learning techniques and discovering the best technique which yields optimal results. Therefore, we propose a model based on deep learning approach to discover knowledge from educational tweets. In this paper efficiency of knowledge learnt by MLP and CNN is compared with DTREE.
{"title":"Knowledge Discovery from Recommender Systems using Deep Learning","authors":"Jabeen Sultana, M. Rani, M. Farquad","doi":"10.1109/ICSSIT46314.2019.8987766","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987766","url":null,"abstract":"Knowledge discovery of educational data plays prominent role in the process of making decisions in order to deliver correct educational reforms. knowledge discovery can be done to extract students' sentiments towards learning behavior of the course, difficulties faced, time spent for the course duration in learning the concepts and worries or fears of students like whether they may pass or fail the final exam. As student feedback is essential to assess the effectiveness of learning technologies, the hidden knowledge of students can be discovered by conducting survey or feedback form or online course satisfaction survey at the end of the courses in order to obtain the meaningful information so that, necessary steps can be taken to improve the learning process. The prime motto of our research is to discover the knowledge from the twitter data and analyze public sentiments towards education using deep learning techniques and discovering the best technique which yields optimal results. Therefore, we propose a model based on deep learning approach to discover knowledge from educational tweets. In this paper efficiency of knowledge learnt by MLP and CNN is compared with DTREE.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129741538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987854
G. Nagaraja, H. Rameshbabu, Gowrishankar
The development of high density and highly dynamic heterogeneous wireless network (HWN) is anticipated to give an wide range of application to end client. This wide range of application presents diverse contextual criteria prerequisites. In future generation high speed, dynamic, and dense mobile network, the end clients will have wide range of radio access technology (RAT) for selection to transmit and receive information. In order to achieve moderate cost of end user, high data rate and better Quality of service (QoS), end client can select wireless local area network (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), Universal Mobile Telecommunications System (UMTS) respectively. Therefore, seamless mobility must be appropriately figured out to accomplish the objective of the next generation wireless access frameworks and offer clients with the comfort of consistent moving between HWNs. To accomplish this objective, the aid of handovers (HO) of multi-rate traffics in versatile and dynamic mobility management is essential. Thus, this work aims to conduct survey of an intelligent approach for handoff decision mechanism for LTE heterogeneous multi-service wireless networks considering multiple parameters like signaling overhead, network communication cost, location and mobility management, QoS, and connection time, user quality of experience on HWN for HO decision making.
{"title":"A Survey of Intelligent approach for Handoff Decision making for Long Term Evolution Heterogeneous Network","authors":"G. Nagaraja, H. Rameshbabu, Gowrishankar","doi":"10.1109/ICSSIT46314.2019.8987854","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987854","url":null,"abstract":"The development of high density and highly dynamic heterogeneous wireless network (HWN) is anticipated to give an wide range of application to end client. This wide range of application presents diverse contextual criteria prerequisites. In future generation high speed, dynamic, and dense mobile network, the end clients will have wide range of radio access technology (RAT) for selection to transmit and receive information. In order to achieve moderate cost of end user, high data rate and better Quality of service (QoS), end client can select wireless local area network (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), Universal Mobile Telecommunications System (UMTS) respectively. Therefore, seamless mobility must be appropriately figured out to accomplish the objective of the next generation wireless access frameworks and offer clients with the comfort of consistent moving between HWNs. To accomplish this objective, the aid of handovers (HO) of multi-rate traffics in versatile and dynamic mobility management is essential. Thus, this work aims to conduct survey of an intelligent approach for handoff decision mechanism for LTE heterogeneous multi-service wireless networks considering multiple parameters like signaling overhead, network communication cost, location and mobility management, QoS, and connection time, user quality of experience on HWN for HO decision making.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129821799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987888
Mukesh Mishra, G. Sen Gupta, X. Gui
Clustering sensor nodes in a wireless sensor network is a key technique to reduce the energy consumption of sensors which extends the lifetime of the network. The head of the cluster plays a key role in a network and serves as a router. In addition, the head of the cluster is responsible for collecting and transmitting sensed information from their cluster members to a destination node or base station/sink. Hence, an efficient clustering approach is required to safely elect a cluster head. It remains a critical task for overall network performance. As a result, in this research approach, we proposed a scheme for selection of cluster head method based on a trust factor that ensures all nodes are trustworthy and authentic during communication. To achieve this, direct trust is calculated using parameters such as the residual energy and the distance between the nodes, along with the use of the k-means clustering algorithm. The simulation results show that in terms of network lifetime, packet delivery ratio, packet drop rate, and energy consumption, the proposed solution outperforms the LEACH protocol. In addition, this strategy can significantly improve performance while discriminating against the network's legitimate and malicious (or compromised) nodes.
{"title":"Trust-Based Cluster Head Selection Using the K-Means Algorithm for Wireless Sensor Networks","authors":"Mukesh Mishra, G. Sen Gupta, X. Gui","doi":"10.1109/ICSSIT46314.2019.8987888","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987888","url":null,"abstract":"Clustering sensor nodes in a wireless sensor network is a key technique to reduce the energy consumption of sensors which extends the lifetime of the network. The head of the cluster plays a key role in a network and serves as a router. In addition, the head of the cluster is responsible for collecting and transmitting sensed information from their cluster members to a destination node or base station/sink. Hence, an efficient clustering approach is required to safely elect a cluster head. It remains a critical task for overall network performance. As a result, in this research approach, we proposed a scheme for selection of cluster head method based on a trust factor that ensures all nodes are trustworthy and authentic during communication. To achieve this, direct trust is calculated using parameters such as the residual energy and the distance between the nodes, along with the use of the k-means clustering algorithm. The simulation results show that in terms of network lifetime, packet delivery ratio, packet drop rate, and energy consumption, the proposed solution outperforms the LEACH protocol. In addition, this strategy can significantly improve performance while discriminating against the network's legitimate and malicious (or compromised) nodes.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126333870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987805
A. Arjuna, R. R. Rose
Retinal diseases are the source for blindness in human eyes. These diseases are diagnosed by examining the fundus images of the retina. People who are affected by eye diseases have different types of lesions on their retina and some abnormalities in the retinal blood vessels as well as in optic disc. An automatic computerized retinal disease detection system requires the retinal structures to be segmented properly. In order to do it, quality of the image is to be enhanced to eliminate the image acquisition issues so as to separate easily the dark and bright retinal structures from its background. This can be done through various contrast enhancement and illumination equalization techniques in the preprocessing steps. Hence, this paper analyzes the performance of three different contrast enhancement techniques without illumination equalization and with illumination equalization for retinal fundus images on three benchmark datasets namely, diaretdb1, drive and ROC. Mean Square Error and Peak Signal-Noise Ratio are the two performance metrics considered.
{"title":"Performance Analysis of Various Contrast Enhancement techniques with Illumination Equalization on Retinal Fundus Images","authors":"A. Arjuna, R. R. Rose","doi":"10.1109/ICSSIT46314.2019.8987805","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987805","url":null,"abstract":"Retinal diseases are the source for blindness in human eyes. These diseases are diagnosed by examining the fundus images of the retina. People who are affected by eye diseases have different types of lesions on their retina and some abnormalities in the retinal blood vessels as well as in optic disc. An automatic computerized retinal disease detection system requires the retinal structures to be segmented properly. In order to do it, quality of the image is to be enhanced to eliminate the image acquisition issues so as to separate easily the dark and bright retinal structures from its background. This can be done through various contrast enhancement and illumination equalization techniques in the preprocessing steps. Hence, this paper analyzes the performance of three different contrast enhancement techniques without illumination equalization and with illumination equalization for retinal fundus images on three benchmark datasets namely, diaretdb1, drive and ROC. Mean Square Error and Peak Signal-Noise Ratio are the two performance metrics considered.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127881267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987896
H. K. Joy, Manjunath R. Kounte
Video processing is a significant field of research interest in recent years. Before going into the recent advancement of video processing, an overview about the traditional video processing is a matter of interest. Knowing about this, its advantages and limitations help to give a strong base and invoke an insight into the further development of this research area. This paper introduces the concept of video processing in early era followed by hybrid video processing, MJPEG and describes the traditional video processing methodologies in hierarchal order. Also, the paper summarizes the recent trends in video processing with NN, CNN, deep learning and focus on the applications in this area. It focus mainly on the video processing development and its application till current era.
{"title":"An Overview of Traditional and Recent Trends in Video Processing","authors":"H. K. Joy, Manjunath R. Kounte","doi":"10.1109/ICSSIT46314.2019.8987896","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987896","url":null,"abstract":"Video processing is a significant field of research interest in recent years. Before going into the recent advancement of video processing, an overview about the traditional video processing is a matter of interest. Knowing about this, its advantages and limitations help to give a strong base and invoke an insight into the further development of this research area. This paper introduces the concept of video processing in early era followed by hybrid video processing, MJPEG and describes the traditional video processing methodologies in hierarchal order. Also, the paper summarizes the recent trends in video processing with NN, CNN, deep learning and focus on the applications in this area. It focus mainly on the video processing development and its application till current era.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121062943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987821
Ritu Bhargava, Abhishek Kumar, Sweta Gupta
The process of semantic web mining is very much applicable in social media and networking sites which will mostly result in overloading of the content. The personalized system is required basically to deal with large information system in order to perform information filteration. The user through internet and web media are considered as content therefore internet and social networking media are the optimal way to express bulk of contents. The collaborative filtering techniques compute the ratings and recommendations which is purely based on information about similar user items and their content. The proposed work is a combined technique which results into hybrid approach, where the feature of the content extracted from open linked dataset, and result in better accuracy in the prediction and analysis. A hybrid prototype is proposed and will be implemented in Weka as extension of the work. The work discusses the role and social media in web mining and advantages of content feature retrieval for semantic web mining methodology.
{"title":"Collaborative methodologies for pattern evaluation for web personalization using Semantic Web Mining","authors":"Ritu Bhargava, Abhishek Kumar, Sweta Gupta","doi":"10.1109/ICSSIT46314.2019.8987821","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987821","url":null,"abstract":"The process of semantic web mining is very much applicable in social media and networking sites which will mostly result in overloading of the content. The personalized system is required basically to deal with large information system in order to perform information filteration. The user through internet and web media are considered as content therefore internet and social networking media are the optimal way to express bulk of contents. The collaborative filtering techniques compute the ratings and recommendations which is purely based on information about similar user items and their content. The proposed work is a combined technique which results into hybrid approach, where the feature of the content extracted from open linked dataset, and result in better accuracy in the prediction and analysis. A hybrid prototype is proposed and will be implemented in Weka as extension of the work. The work discusses the role and social media in web mining and advantages of content feature retrieval for semantic web mining methodology.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115626602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICSSIT46314.2019.8987886
Suman Goyat, Shri Kant, Neha S Dhariwal
The technology has been growing in the field of computation so fast that the operation which takes days in old time now can be completed within few seconds. The basic need of such computing is fastest processing time of any operation by the system. The performance of any computing device is dependent on processor, memory and hardware/ software behavior. Central Processing Unit (CPU) is known to be the brain of computer. In any case, progressively, that brain can be raised by additional piece of Personal Computer with the GPU (Graphics Processing Unit), which is alluded to as the aforementioned spirit. The fusion of a CPU with a GPU can convey the ideal estimation of framework cost, execution and power. It tends to be expressed that GPUs vary from CPUs as GPU is improved for throughput rather than idleness which can work quicker and more expense effectively than CPUs. GPUs are equipped for taking a lot of information and playing out a similar task again and again rapidly, in contrast to CPU, which will in general skip activities everywhere. Distributed processing comprises of utilizations successively over a stage which have more than one computational device with various designs, for example, a manycore GPU and a multi-core CPU. By and large, the kernel performs well on the GPU as they are enhanced for a GPU's exceedingly with parallel engineering and GPU regularly provide higher pinnacle throughput per unit of time. The exploration says that GPU is definitely more superior to CPU because of its parallel design as it is made out of hundreds of cores which can deal with a huge number of threads when contrasted with CPU. Here, we will demonstrate this fact that GPU is growing its importance in High-Performance Computing (HPC) era. In this paper, we will take few applications with the historical information about the runtime of particular application taken on CPU and GPU. This historical information created from benchmarks will let help us to decide whether the tasks are GPU bound or CPU bound and schedule them accordingly to reduce the waiting time of other applications. Our approach immensely takes dynamic decision to schedule the tasks. Earlier approaches are not as impactful as our approach because here the greedy decision taken to reduce overall execution time and improve processor utilization.
{"title":"Dynamic Heterogeneous scheduling of GPU-CPU in Distributed Environment","authors":"Suman Goyat, Shri Kant, Neha S Dhariwal","doi":"10.1109/ICSSIT46314.2019.8987886","DOIUrl":"https://doi.org/10.1109/ICSSIT46314.2019.8987886","url":null,"abstract":"The technology has been growing in the field of computation so fast that the operation which takes days in old time now can be completed within few seconds. The basic need of such computing is fastest processing time of any operation by the system. The performance of any computing device is dependent on processor, memory and hardware/ software behavior. Central Processing Unit (CPU) is known to be the brain of computer. In any case, progressively, that brain can be raised by additional piece of Personal Computer with the GPU (Graphics Processing Unit), which is alluded to as the aforementioned spirit. The fusion of a CPU with a GPU can convey the ideal estimation of framework cost, execution and power. It tends to be expressed that GPUs vary from CPUs as GPU is improved for throughput rather than idleness which can work quicker and more expense effectively than CPUs. GPUs are equipped for taking a lot of information and playing out a similar task again and again rapidly, in contrast to CPU, which will in general skip activities everywhere. Distributed processing comprises of utilizations successively over a stage which have more than one computational device with various designs, for example, a manycore GPU and a multi-core CPU. By and large, the kernel performs well on the GPU as they are enhanced for a GPU's exceedingly with parallel engineering and GPU regularly provide higher pinnacle throughput per unit of time. The exploration says that GPU is definitely more superior to CPU because of its parallel design as it is made out of hundreds of cores which can deal with a huge number of threads when contrasted with CPU. Here, we will demonstrate this fact that GPU is growing its importance in High-Performance Computing (HPC) era. In this paper, we will take few applications with the historical information about the runtime of particular application taken on CPU and GPU. This historical information created from benchmarks will let help us to decide whether the tasks are GPU bound or CPU bound and schedule them accordingly to reduce the waiting time of other applications. Our approach immensely takes dynamic decision to schedule the tasks. Earlier approaches are not as impactful as our approach because here the greedy decision taken to reduce overall execution time and improve processor utilization.","PeriodicalId":330309,"journal":{"name":"2019 International Conference on Smart Systems and Inventive Technology (ICSSIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114259240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：