Pub Date : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697505
R. Mangrulkar
Paralyzed person or the person with physical disorders wont be able to move their body parts viz. hand or arm because of abnormal behavior of spinal cord or its injuries. This movement inabilities may result to mental, moral or physical disorder resulting into sometimes cardiovascular diseases, bone demineralization. In such cases, the surgical solution is to use neuroprosthetic arm replacing paralyzed arm. This is expensive and also impact normal human behavior and demoralize him or her. The proposed neuroprosthetics approach avoids the need of replacing the arm and also avoids critical surgery which increase the moral and confidence of patient. The approach involves designing a model that interfaces with living neurons to control a device or for sensory substitution. In proposed approach, human to human interaction using model is required to setup. The design is developed to supervise the parallelised arm under the control of normal human arm. For this, it creates an interface which works in directions given by normal human arm with patients's arm. This interface is designed using microprocessor to compute and process signals and transfer to electrode attached to electrical muscle to stimulate the damaged arm. The electrical signals are generated in controlled manner with effective and enough strength level equivalent to the brain signals required for motor nerves in collaboration with sensor nerves. This helps patient with paralyzed arm to perform directed operations under the governed movement of normal human being. This avoids the use of traditional prosthetic arm surgery and can use proposed nervous bypass system without any surgery.
{"title":"Design of Neuromuscular Stimulation to Supervise Parallelized Arm Using Human-Machine-Human Interaction","authors":"R. Mangrulkar","doi":"10.1109/ICCUBEA.2018.8697505","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697505","url":null,"abstract":"Paralyzed person or the person with physical disorders wont be able to move their body parts viz. hand or arm because of abnormal behavior of spinal cord or its injuries. This movement inabilities may result to mental, moral or physical disorder resulting into sometimes cardiovascular diseases, bone demineralization. In such cases, the surgical solution is to use neuroprosthetic arm replacing paralyzed arm. This is expensive and also impact normal human behavior and demoralize him or her. The proposed neuroprosthetics approach avoids the need of replacing the arm and also avoids critical surgery which increase the moral and confidence of patient. The approach involves designing a model that interfaces with living neurons to control a device or for sensory substitution. In proposed approach, human to human interaction using model is required to setup. The design is developed to supervise the parallelised arm under the control of normal human arm. For this, it creates an interface which works in directions given by normal human arm with patients's arm. This interface is designed using microprocessor to compute and process signals and transfer to electrode attached to electrical muscle to stimulate the damaged arm. The electrical signals are generated in controlled manner with effective and enough strength level equivalent to the brain signals required for motor nerves in collaboration with sensor nerves. This helps patient with paralyzed arm to perform directed operations under the governed movement of normal human being. This avoids the use of traditional prosthetic arm surgery and can use proposed nervous bypass system without any surgery.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128709878","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697509
S. Tiwaskar, Rutuja U. Gosavi, Riddhima Dubey, S. Jadhav, K. Iyer
India is one of the leading countries facing deaths due to Heart Failure. Prediction of this disease in early stages could be helpful but is posing challenges for researchers. Our purpose is to detect the condition earlier so that the health outcomes of people can be changed in turn improving lifestyle. Whenever doctors know which patients have chances of developing risk of heart failure, medications can be prescribed or lifestyle changes can be recommended that could remit the inception or avoid it entirely. Our goal is to accurately and efficiently classify records into: Presence or Absence of Heart Failure Risk. We aim at presenting a comparative study of Statistical, Machine Learning and Data Mining based techniques for prognosis of Heart Failure Risk. The performance of Statistical evaluation, Decision Tree Classifier, Random forest classifier and Convolution Neural Network (CNN) are compared. The accuracies provided by the models are 85%, 80.1%, 85.38% and 93% respectively. As CNN has not been applied to the Cleveland dataset, it adds value to our empirical study. It is observed that Prediction Accuracy is enhanced by using CNN.
{"title":"Comparison of Prediction Models for Heart Failure Risk: A Clinical Perspective","authors":"S. Tiwaskar, Rutuja U. Gosavi, Riddhima Dubey, S. Jadhav, K. Iyer","doi":"10.1109/ICCUBEA.2018.8697509","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697509","url":null,"abstract":"India is one of the leading countries facing deaths due to Heart Failure. Prediction of this disease in early stages could be helpful but is posing challenges for researchers. Our purpose is to detect the condition earlier so that the health outcomes of people can be changed in turn improving lifestyle. Whenever doctors know which patients have chances of developing risk of heart failure, medications can be prescribed or lifestyle changes can be recommended that could remit the inception or avoid it entirely. Our goal is to accurately and efficiently classify records into: Presence or Absence of Heart Failure Risk. We aim at presenting a comparative study of Statistical, Machine Learning and Data Mining based techniques for prognosis of Heart Failure Risk. The performance of Statistical evaluation, Decision Tree Classifier, Random forest classifier and Convolution Neural Network (CNN) are compared. The accuracies provided by the models are 85%, 80.1%, 85.38% and 93% respectively. As CNN has not been applied to the Cleveland dataset, it adds value to our empirical study. It is observed that Prediction Accuracy is enhanced by using CNN.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125647625","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697367
Subhash Kumar Ram, A. Abhishek, B. K. Verma, Sachin Devassy, A. Dhakar
This paper describes simulation and design of single-phase to three-phase UPF system for agricultural/household applications. The average current mode control (ACMC) technique is used for Unity Power Factor (UPF) correction of single phase AC-DC boost converter. A comprehensive study and analysis of single-phase to three-phase converter with UPF operation is presented. Closed loop control of single phase AC-DC UPF boost converter is designed. The three phase voltage source inverter with Sinusoidal Pulse Width Modulation (SPWM) technique has been used for dc to 3-phase ac conversion. The voltage mode control of three-phase voltage source SPWM inverter have been designed and simulated. The complete system with the integration of single-phase and three-phase converter has been simulated. The simulation results with their performance such as power factor (pf), Total Harmonic Distortion (THD) and efficiency have been analysed. The simulation results on resistive load is presented in this paper.
{"title":"Study and Simulation of Single-Phase to Three-Phase UPF System for Agricultural Applications","authors":"Subhash Kumar Ram, A. Abhishek, B. K. Verma, Sachin Devassy, A. Dhakar","doi":"10.1109/ICCUBEA.2018.8697367","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697367","url":null,"abstract":"This paper describes simulation and design of single-phase to three-phase UPF system for agricultural/household applications. The average current mode control (ACMC) technique is used for Unity Power Factor (UPF) correction of single phase AC-DC boost converter. A comprehensive study and analysis of single-phase to three-phase converter with UPF operation is presented. Closed loop control of single phase AC-DC UPF boost converter is designed. The three phase voltage source inverter with Sinusoidal Pulse Width Modulation (SPWM) technique has been used for dc to 3-phase ac conversion. The voltage mode control of three-phase voltage source SPWM inverter have been designed and simulated. The complete system with the integration of single-phase and three-phase converter has been simulated. The simulation results with their performance such as power factor (pf), Total Harmonic Distortion (THD) and efficiency have been analysed. The simulation results on resistive load is presented in this paper.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130565958","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697464
Hitanshu A. Patel, Ritesh D. Rajput
In today's world, everything is transforming into automation. From basic households work to major industries work, from basic machinery to steering and stabilization of ships, aircraft and other applications and vehicles. Our main objective of this project is to control surveillance system completely without human intervention not only in steady or particular allotted or settled area but which can move to remote places and restricted area where human entry is not feasible. We have demonstrated our idea using a moving car with a mounted camera and processor and which can move autonomously or can be controlled remotely via remote/website/android app. The images which are captured by a camera can be processed by a processor and digital image processing (DIP) algorithms can be done for human detection or object detection. Boosted cascade, Haar cascade, anisotropic diffusion, Hausdorff distance, colour processing, background subtraction statistics of parts, pulse coupled neural networks, single correlation filter, these are various algorithms used for human/object detection.
{"title":"Smart Surveillance System Using Histogram of Oriented Gradients (HOG) Algorithm and Haar Cascade Algorithm","authors":"Hitanshu A. Patel, Ritesh D. Rajput","doi":"10.1109/ICCUBEA.2018.8697464","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697464","url":null,"abstract":"In today's world, everything is transforming into automation. From basic households work to major industries work, from basic machinery to steering and stabilization of ships, aircraft and other applications and vehicles. Our main objective of this project is to control surveillance system completely without human intervention not only in steady or particular allotted or settled area but which can move to remote places and restricted area where human entry is not feasible. We have demonstrated our idea using a moving car with a mounted camera and processor and which can move autonomously or can be controlled remotely via remote/website/android app. The images which are captured by a camera can be processed by a processor and digital image processing (DIP) algorithms can be done for human detection or object detection. Boosted cascade, Haar cascade, anisotropic diffusion, Hausdorff distance, colour processing, background subtraction statistics of parts, pulse coupled neural networks, single correlation filter, these are various algorithms used for human/object detection.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127821186","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697808
Pallavi K. Tathe, M. Sharma
This paper proposes, an Actor-Critic Reinforcement learning based radio resource scheduling policy in downlink Transmission for Long Term Evaluation Advanced (LTE-A) radio resource technology. The scheduling technique uses the neural network (NN) based actor critic architecture in order to propose proper scheduling rules at each Transmission Time Interval (TTI). The objective is to improve system capacity, system throughput and spectral efficiency. NN based Actor-critic Reinforcement learning is proposed to accomplish the resource scheduling efficiently by maintaining best QoS capabilities and user fairness. The simulation results indicate that the proposed method achieves desired throughput and increased convergence capability.
{"title":"Dynamic Actor-Critic: Reinforcement Learning Based Radio Resource Scheduling for LTE-Advanced","authors":"Pallavi K. Tathe, M. Sharma","doi":"10.1109/ICCUBEA.2018.8697808","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697808","url":null,"abstract":"This paper proposes, an Actor-Critic Reinforcement learning based radio resource scheduling policy in downlink Transmission for Long Term Evaluation Advanced (LTE-A) radio resource technology. The scheduling technique uses the neural network (NN) based actor critic architecture in order to propose proper scheduling rules at each Transmission Time Interval (TTI). The objective is to improve system capacity, system throughput and spectral efficiency. NN based Actor-critic Reinforcement learning is proposed to accomplish the resource scheduling efficiently by maintaining best QoS capabilities and user fairness. The simulation results indicate that the proposed method achieves desired throughput and increased convergence capability.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126618392","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697424
Sunayana Suryawanshi, S. Danve
This implementation is step ahead for the current image processing applications which captures degraded contrast and establishes error prone images in fog condition. Long distance images has low visibility. The variation in fog density with distance is responsible for atmospheric veil factor. The implementation includes the single image processing for quantifiable and approximate calculations to construct fog-free images with the use of atmospheric veil to rebuild the contrast the in homogeneous or heterogeneous conditions.
{"title":"Fog Correction Using Exponential Contrast Restoration","authors":"Sunayana Suryawanshi, S. Danve","doi":"10.1109/ICCUBEA.2018.8697424","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697424","url":null,"abstract":"This implementation is step ahead for the current image processing applications which captures degraded contrast and establishes error prone images in fog condition. Long distance images has low visibility. The variation in fog density with distance is responsible for atmospheric veil factor. The implementation includes the single image processing for quantifiable and approximate calculations to construct fog-free images with the use of atmospheric veil to rebuild the contrast the in homogeneous or heterogeneous conditions.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123232006","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697346
Vrushali Tajane, Deepak H. Sharma
Due to expansion of Internet and huge dataset, many organizations started to use cloud. But in the cloud it has to face many security issues like distributed denial of service attack (DDoS). This attack makes a network or system unavailable to legitimate users. DDoS attack over cloud does not any changes in data but bring out a correspondent attacks in cloud resource, cloud service, framework to absorb it. This paper discusses various defence mechanisms to prevent these attacks. This work gives exhaustive study on advanced confidence based filtering called N-CBF method to detect and prevent DDoS in cloud. It collects the packets, extract their attributes and then make pairs of attributes. It adjusts weight dynamically for each attribute pair and threshold value for each attribute. It increases the detection rate and also provides more security in cloud. This paper gives simulation for N-CBF method and provides more security by adding RSA algorithm.
{"title":"Effective Detection and Prevention of DDoS in Cloud Computing Environment","authors":"Vrushali Tajane, Deepak H. Sharma","doi":"10.1109/ICCUBEA.2018.8697346","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697346","url":null,"abstract":"Due to expansion of Internet and huge dataset, many organizations started to use cloud. But in the cloud it has to face many security issues like distributed denial of service attack (DDoS). This attack makes a network or system unavailable to legitimate users. DDoS attack over cloud does not any changes in data but bring out a correspondent attacks in cloud resource, cloud service, framework to absorb it. This paper discusses various defence mechanisms to prevent these attacks. This work gives exhaustive study on advanced confidence based filtering called N-CBF method to detect and prevent DDoS in cloud. It collects the packets, extract their attributes and then make pairs of attributes. It adjusts weight dynamically for each attribute pair and threshold value for each attribute. It increases the detection rate and also provides more security in cloud. This paper gives simulation for N-CBF method and provides more security by adding RSA algorithm.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404379","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697635
Swapnali Londhe, Rupesh Mahajan
Value of the item set is considered as a utility of that item set and find out the high utility of the item set is the aim of utility mining. Some time database parameters are considered to find out high utility pattern eg. Profit, cost etc. In proposed approach utility value of particular items used for utility mining. In day to day life high utility pattern mining play important role in applications. It's current hot topic in today's research area. Different existing algorithms are present in this area. It first of all identify the candidate itemset's by using their utilities, and simultaneously identify the exact utility of that candidate pattern. Problem of using this algorithm is large number of candidate itemset's are generated. But after computing exact utility it's clear that most of the candidate having no high utility. For generating profitable product manufacturing plan it's very important to understanding the customer preferences in industrial area. Sliding Window based pattern mining approach which considering the quantity, quality and cost of each product for generating high profitable product set, which employed to find out high utility pattern. For establishing highly profitable manufacturing plan, which allow corporation to maximize its revenue, high utility pattern mining is important aspect. Large amount of stream data related to customer purchase behavior used for establishing manufacturing plan. Recent preference of the customers also helps in generating manufacturing plans. This paper contains Two Sliding Windows Pattern mining Algorithm (TSW) scans complete dataset And divide it in to two parts. Both parts scan simultaneously in order to improve the search space. The proposed algorithm (TSW) scans the text using two sliding windows, allowing multiple alignments in the searching process. Introducing A list structure and a novel algorithm for generating high utility pattern over large data, with the help of Sliding Window Control Method. This approach avoid the generation of candidate pattern. Due to reducing candidate pattern, algorithm not required large amount of memory space as well as computational resources for verifying candidate patterns. By considering all this parameters, it's an efficient approach.
{"title":"Two Sliding Window Control Based High Utility Pattern Mining","authors":"Swapnali Londhe, Rupesh Mahajan","doi":"10.1109/ICCUBEA.2018.8697635","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697635","url":null,"abstract":"Value of the item set is considered as a utility of that item set and find out the high utility of the item set is the aim of utility mining. Some time database parameters are considered to find out high utility pattern eg. Profit, cost etc. In proposed approach utility value of particular items used for utility mining. In day to day life high utility pattern mining play important role in applications. It's current hot topic in today's research area. Different existing algorithms are present in this area. It first of all identify the candidate itemset's by using their utilities, and simultaneously identify the exact utility of that candidate pattern. Problem of using this algorithm is large number of candidate itemset's are generated. But after computing exact utility it's clear that most of the candidate having no high utility. For generating profitable product manufacturing plan it's very important to understanding the customer preferences in industrial area. Sliding Window based pattern mining approach which considering the quantity, quality and cost of each product for generating high profitable product set, which employed to find out high utility pattern. For establishing highly profitable manufacturing plan, which allow corporation to maximize its revenue, high utility pattern mining is important aspect. Large amount of stream data related to customer purchase behavior used for establishing manufacturing plan. Recent preference of the customers also helps in generating manufacturing plans. This paper contains Two Sliding Windows Pattern mining Algorithm (TSW) scans complete dataset And divide it in to two parts. Both parts scan simultaneously in order to improve the search space. The proposed algorithm (TSW) scans the text using two sliding windows, allowing multiple alignments in the searching process. Introducing A list structure and a novel algorithm for generating high utility pattern over large data, with the help of Sliding Window Control Method. This approach avoid the generation of candidate pattern. Due to reducing candidate pattern, algorithm not required large amount of memory space as well as computational resources for verifying candidate patterns. By considering all this parameters, it's an efficient approach.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126364260","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697365
W. Kulkarni, Sai Ramtirth, M. Ambaskar, Sanika Patki, Milind Kulkarni
Studies show that reason behind 20% of the road accidents is because of driver fatigue and almost 50% of those are fatal. Over a period of time, a certain amount of nonintrusive systems have been developed for the detection of the driver's alertness. Most of them showed about 80% success rate. The presented work describes a novel method for the detection of driver's alertness. Since the eyelid movement is vertical, the change is vertical. The proposed algorithm uses Fourier Transform to detect this vertical change along the y-axis. Using Fourier Transform, unique features for all the three cases considered - full open eyelids, half-open eyelids, and full closed eyelids - are obtained. Thus, eyelid positions can be differentiated effectively. The testing and cross-validation for real-time data against trained images are done using real-time environment in Python2.7. The proposed algorithm produces 96% of accuracy.
{"title":"Driver Alertness Detection Algorithm","authors":"W. Kulkarni, Sai Ramtirth, M. Ambaskar, Sanika Patki, Milind Kulkarni","doi":"10.1109/ICCUBEA.2018.8697365","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697365","url":null,"abstract":"Studies show that reason behind 20% of the road accidents is because of driver fatigue and almost 50% of those are fatal. Over a period of time, a certain amount of nonintrusive systems have been developed for the detection of the driver's alertness. Most of them showed about 80% success rate. The presented work describes a novel method for the detection of driver's alertness. Since the eyelid movement is vertical, the change is vertical. The proposed algorithm uses Fourier Transform to detect this vertical change along the y-axis. Using Fourier Transform, unique features for all the three cases considered - full open eyelids, half-open eyelids, and full closed eyelids - are obtained. Thus, eyelid positions can be differentiated effectively. The testing and cross-validation for real-time data against trained images are done using real-time environment in Python2.7. The proposed algorithm produces 96% of accuracy.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"9 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120894478","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 : 2018-08-01DOI: 10.1109/ICCUBEA.2018.8697606
Prajakta Ghavare, Prashant G. Ahire
Digital marketing is growing faster to increase business and sale products. All Ecommerce sites send recommendations of products or newly updated product list to the user. They also send exciting offers to users. We need to study and understand behavior and interest of user to recommend products, this is important to adapt to requirements of customer in ecommerce website. The information about users behavior is stored into server log file. We extract log file to get behavior and do pre-processing to get session action details. To analyze log files, proposed system implements a linear-temporal logic to analyze web server logs of ecommerce website. Web server logs are mapped to event logs by process of mapping log records, to capture behavior of customer. To find different behavioral patterns that refers to different action performed by users in session, different predefined queries are performed. We proposed the use of Temporal Logic and model checking approach as an alternative to traditional data mining techniques using and to use it in structured e-commerce websites. The goal of system is to analyze the usage of e-commerce websites and to extract customers behavioral patterns with the use of temporal logic formulas and to describe user behavior against the log model. The system can determine user behavior and interests, it will associate users with each other for better recommendation system.
{"title":"Big Data Classification of Users Navigation and Behavior Using Web Server Logs","authors":"Prajakta Ghavare, Prashant G. Ahire","doi":"10.1109/ICCUBEA.2018.8697606","DOIUrl":"https://doi.org/10.1109/ICCUBEA.2018.8697606","url":null,"abstract":"Digital marketing is growing faster to increase business and sale products. All Ecommerce sites send recommendations of products or newly updated product list to the user. They also send exciting offers to users. We need to study and understand behavior and interest of user to recommend products, this is important to adapt to requirements of customer in ecommerce website. The information about users behavior is stored into server log file. We extract log file to get behavior and do pre-processing to get session action details. To analyze log files, proposed system implements a linear-temporal logic to analyze web server logs of ecommerce website. Web server logs are mapped to event logs by process of mapping log records, to capture behavior of customer. To find different behavioral patterns that refers to different action performed by users in session, different predefined queries are performed. We proposed the use of Temporal Logic and model checking approach as an alternative to traditional data mining techniques using and to use it in structured e-commerce websites. The goal of system is to analyze the usage of e-commerce websites and to extract customers behavioral patterns with the use of temporal logic formulas and to describe user behavior against the log model. The system can determine user behavior and interests, it will associate users with each other for better recommendation system.","PeriodicalId":422920,"journal":{"name":"2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115952677","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：