Pub Date : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032671
S. Panda
This paper presents an intelligible voice based authentication system for IoT devices. As voice changes over time due to different characteristics and other environmental effects, limited features based training approaches may not provide the desire level of performance. The accuracy of the system is also dependent on several other factors like- the control over recording equipment, recording conditions, cooperation from speaker, etc. Therefore, this work analyzes the voice variation of the speech over varied conditions to address the long term speaker variability to enhance the performance of the voice based authentication system. The integration of IoT technology with voice based communication technology may help users to make their systems work based on voice commands instead of typed commands. A number of tests were also conducted to show the effectiveness of the presented model under varied conditions.
{"title":"Intelligent Voice-based Authentication System","authors":"S. Panda","doi":"10.1109/I-SMAC47947.2019.9032671","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032671","url":null,"abstract":"This paper presents an intelligible voice based authentication system for IoT devices. As voice changes over time due to different characteristics and other environmental effects, limited features based training approaches may not provide the desire level of performance. The accuracy of the system is also dependent on several other factors like- the control over recording equipment, recording conditions, cooperation from speaker, etc. Therefore, this work analyzes the voice variation of the speech over varied conditions to address the long term speaker variability to enhance the performance of the voice based authentication system. The integration of IoT technology with voice based communication technology may help users to make their systems work based on voice commands instead of typed commands. A number of tests were also conducted to show the effectiveness of the presented model under varied conditions.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130950944","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032677
L. M. Therase, T. Jayanthy
In this paper, a complementary triangular split ring resonator (CTSRR) based inset feed circular microstrip patch antenna (CMPA) loaded at the center of the ground plane is designed on epoxy resin dielectric material. The physical dimensions of the the antenna is (24x24x0.8) mm3 and the impedance bandwidth of the proposed antenna for $mathrm{S}_{11} < -10 text{dB}$ exhibits between 8 and 12 GHz (X band) which is useful for vehicular satellite applications. Finite integration technique-based CST Microwave studio 19 has been used for optimization. The characteristics of the proposed antenna such as return loss, VSWR, impedance bandwidth, gain and radiation pattern are observed and compared with the conventional antenna. The simulated results show improved performance compared to conventional CMPA.
{"title":"Design of High Gain and Wideband Microstrip Antenna using Complementary Split Ring Resonator on Epoxy Resin Material","authors":"L. M. Therase, T. Jayanthy","doi":"10.1109/I-SMAC47947.2019.9032677","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032677","url":null,"abstract":"In this paper, a complementary triangular split ring resonator (CTSRR) based inset feed circular microstrip patch antenna (CMPA) loaded at the center of the ground plane is designed on epoxy resin dielectric material. The physical dimensions of the the antenna is (24x24x0.8) mm3 and the impedance bandwidth of the proposed antenna for $mathrm{S}_{11} < -10 text{dB}$ exhibits between 8 and 12 GHz (X band) which is useful for vehicular satellite applications. Finite integration technique-based CST Microwave studio 19 has been used for optimization. The characteristics of the proposed antenna such as return loss, VSWR, impedance bandwidth, gain and radiation pattern are observed and compared with the conventional antenna. The simulated results show improved performance compared to conventional CMPA.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125370231","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032430
S. Jeevitha, S.Vengatesh Kumar
Image processing and IoT based monitoring network has taken the sensors to a completely different level. The conflicts between human and animal become a major problem in the agriculture field by resulting the human life in danger and loss of huge quantity of resources. To overcome these challenges, an animal intrusion alert system is designed by employing wireless sensors for sending an automatic alert message to both the landowner and forest officials with an image. This can make an early warning notification to take a suitable action based on the type of intruder. The sensor will detect the movement of the animal and the camera will capture the image, then the image is classified via a microcontroller, and further the GSM module will send the alert notification SMS to the forest department and the landowner. This survey is used to understand various steps, tools, and experimental setups employed to save human life from animal intrusion. Keywords: IoT (Internet of Thing), Sensors, Image processing, Microcontroller, GSM module.
{"title":"A Study on Sensor Based Animal Intrusion Alert System Using Image Processing Techniques","authors":"S. Jeevitha, S.Vengatesh Kumar","doi":"10.1109/I-SMAC47947.2019.9032430","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032430","url":null,"abstract":"Image processing and IoT based monitoring network has taken the sensors to a completely different level. The conflicts between human and animal become a major problem in the agriculture field by resulting the human life in danger and loss of huge quantity of resources. To overcome these challenges, an animal intrusion alert system is designed by employing wireless sensors for sending an automatic alert message to both the landowner and forest officials with an image. This can make an early warning notification to take a suitable action based on the type of intruder. The sensor will detect the movement of the animal and the camera will capture the image, then the image is classified via a microcontroller, and further the GSM module will send the alert notification SMS to the forest department and the landowner. This survey is used to understand various steps, tools, and experimental setups employed to save human life from animal intrusion. Keywords: IoT (Internet of Thing), Sensors, Image processing, Microcontroller, GSM module.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126779299","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032490
S. Gowri, P. Anitha, D. Srivaishnavi, M. Nithya
Drowsiness and accident detection system is an equipment gadget that expects to expand street wellbeing. This framework includes the establishment of an equipment unit that comprises of vibration sensor and heartbeat rate sensor to identify the accident and eye flicker sensor in order to distinguish the sleepiness of the driver. It utilizes GPS to follow the area and GSM to send the message. The primary motivation behind this framework is to alert the unfortunate casualty's family about the incident and it can distinguish the status of the vehicle driver as for sleepiness or weariness conditions progressively. The vibration sensor detects the accident and the beat rate sensor checks the heartbeat of the driver. At the point when the vibration happens and the heartbeat level is high, it will be expected that accident has been happened and message revealing the driver's heartbeat rate and his area will be sent to his relative. The eye flicker sensor is fitted in a wearable glass. When it recognizes the eyes are shut, the alarm bell starts to beep. On the off chance that the bell is turned off inside 20 sec, the condition is ordinary else the condition will be regarded as unusual and message detailing something strange will be sent to his relative.
{"title":"Internet of Things based Accident Detection System","authors":"S. Gowri, P. Anitha, D. Srivaishnavi, M. Nithya","doi":"10.1109/I-SMAC47947.2019.9032490","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032490","url":null,"abstract":"Drowsiness and accident detection system is an equipment gadget that expects to expand street wellbeing. This framework includes the establishment of an equipment unit that comprises of vibration sensor and heartbeat rate sensor to identify the accident and eye flicker sensor in order to distinguish the sleepiness of the driver. It utilizes GPS to follow the area and GSM to send the message. The primary motivation behind this framework is to alert the unfortunate casualty's family about the incident and it can distinguish the status of the vehicle driver as for sleepiness or weariness conditions progressively. The vibration sensor detects the accident and the beat rate sensor checks the heartbeat of the driver. At the point when the vibration happens and the heartbeat level is high, it will be expected that accident has been happened and message revealing the driver's heartbeat rate and his area will be sent to his relative. The eye flicker sensor is fitted in a wearable glass. When it recognizes the eyes are shut, the alarm bell starts to beep. On the off chance that the bell is turned off inside 20 sec, the condition is ordinary else the condition will be regarded as unusual and message detailing something strange will be sent to his relative.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123233744","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032438
A. Nduka, Joshua Samual, S. Elango, Sajilal Divakaran, Umar Umar, R. SenthilPrabha
In recent times, the advent of technology such as Internet of Things (IoT), Cloud technology, Artificial Intelligence (AI), computing etc., information technology has witnessed a paradigm shift in tackle problems, live our daily lives, interact with each other and respond to issues of our daily lives. Generally, the IoT is a network of interconnected nodes or computers that sense gather and transmit/communicate data to relevant nodes for action and decision making. Even though we have a series of vital sign monitors ranging from manually operated to analogue and digital sensors, they are all stand-alone devices which are not connected to the patient's doctor in real-time. In this paper, the Remote Health Monitoring (RHM) system can sense certain human vital signs such as, temperature, respiration and heartbeat (pulse) which is connected in real time environment. RHM system is built on Arduino UNO board which houses other microcontrollers and sensor paired with IOT Gecko, which is further designed in a way that physicians can view patient's vital sign reading in real-time irrespective of their geographical location. When these body vital signs fall below or above normal parameters, the system triggers an alarm, giving physicians the opportunity to carry out timely individualized intervention on patients in crisis. Two different devices (Omron digital Temperature monitor, ChoiceMMed heart rate monitor) were taken for study and the results were compared with RHM system. The accuracy of the system was evaluated and it was found that +/−0.5 degrees. Hence we can conclusively say that RHM delivers accurate reading with better functionality.
{"title":"Internet of Things Based Remote Health Monitoring System Using Arduino","authors":"A. Nduka, Joshua Samual, S. Elango, Sajilal Divakaran, Umar Umar, R. SenthilPrabha","doi":"10.1109/I-SMAC47947.2019.9032438","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032438","url":null,"abstract":"In recent times, the advent of technology such as Internet of Things (IoT), Cloud technology, Artificial Intelligence (AI), computing etc., information technology has witnessed a paradigm shift in tackle problems, live our daily lives, interact with each other and respond to issues of our daily lives. Generally, the IoT is a network of interconnected nodes or computers that sense gather and transmit/communicate data to relevant nodes for action and decision making. Even though we have a series of vital sign monitors ranging from manually operated to analogue and digital sensors, they are all stand-alone devices which are not connected to the patient's doctor in real-time. In this paper, the Remote Health Monitoring (RHM) system can sense certain human vital signs such as, temperature, respiration and heartbeat (pulse) which is connected in real time environment. RHM system is built on Arduino UNO board which houses other microcontrollers and sensor paired with IOT Gecko, which is further designed in a way that physicians can view patient's vital sign reading in real-time irrespective of their geographical location. When these body vital signs fall below or above normal parameters, the system triggers an alarm, giving physicians the opportunity to carry out timely individualized intervention on patients in crisis. Two different devices (Omron digital Temperature monitor, ChoiceMMed heart rate monitor) were taken for study and the results were compared with RHM system. The accuracy of the system was evaluated and it was found that +/−0.5 degrees. Hence we can conclusively say that RHM delivers accurate reading with better functionality.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123412933","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}
This paper deals with the implementation approach for the feature detection for the images obtained from satellites using deep convolutional neural network. The aim of this paper is to accurately segment different images of different classes of the satellite imagery. Our method for the implementation is confined to the adaptation of CNN for multispectral data processing. We have also stated and developed several changes for the training objective and the training pipeline our method of implementation of the above model secured 3rd place from 419 entries that were submitted. The accuracy of the model implemented can be compared to the methods that secured the first 2 places in the competition, but unlikely this satellite image analysis does not depend on the complex assembling schemes so can be utilized in the automatic featuring at ease.
{"title":"Feature Detection for Satellite Imagery Using Deep-Convolutional Neural Network","authors":"Vaibhav Gupta, Vaibhav Aggarwal, Parakram Singh Chauhan, K. Sharma, Neetu Sharma","doi":"10.1109/I-SMAC47947.2019.9032563","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032563","url":null,"abstract":"This paper deals with the implementation approach for the feature detection for the images obtained from satellites using deep convolutional neural network. The aim of this paper is to accurately segment different images of different classes of the satellite imagery. Our method for the implementation is confined to the adaptation of CNN for multispectral data processing. We have also stated and developed several changes for the training objective and the training pipeline our method of implementation of the above model secured 3rd place from 419 entries that were submitted. The accuracy of the model implemented can be compared to the methods that secured the first 2 places in the competition, but unlikely this satellite image analysis does not depend on the complex assembling schemes so can be utilized in the automatic featuring at ease.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126475628","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032509
N. Shah, Vedvyas Dwivedi, B. Sedani
Free Space Optics (FSO) has attracted the attention of researches in the last decade for developing low cost, high data rate and security in fiber optic cables. We compare different relay selection schemes with free space optics K channel and gamma channel. We also compare the performance of PSO and DE algorithm in free space optical communication. So, it will give details of the performance of free space optical communication in different channel with different algorithm for different relay selection schemes.
{"title":"Comparative Analysis of Relay Selection Techniques in Free Space Optics","authors":"N. Shah, Vedvyas Dwivedi, B. Sedani","doi":"10.1109/I-SMAC47947.2019.9032509","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032509","url":null,"abstract":"Free Space Optics (FSO) has attracted the attention of researches in the last decade for developing low cost, high data rate and security in fiber optic cables. We compare different relay selection schemes with free space optics K channel and gamma channel. We also compare the performance of PSO and DE algorithm in free space optical communication. So, it will give details of the performance of free space optical communication in different channel with different algorithm for different relay selection schemes.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114212835","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032688
Anjali Deshpande, V. Kulkarni
As the stocks of conventional fuels are limited, their prices are increasing every day. The use of conventional fuels creates the problem in emission of greenhouse gases followed by global warming. At the same time the growing industrialization and modernization demands more electricity. Increased demand of electricity makes it necessary to go for alternative sources of energy like solar and wind. The potential of wind energy has made its power plant installation worldwide but along with conventional generation. The wind generators operate very differently from traditional generators. Their share in the power system is considerable, that forces us to study interaction between power systems and wind power plants and study how power system performs along with wind energy conversion systems. Though wind is great natural source speed unpredictability is a major challenge. So, technologies evolved as constant speed and variable speed wind turbines. The paper explains various types of wind energy conversion systems using squirrel cage induction generator (SCIG), synchronous generator (SG) and doubly fed induction generator (DFIG) and explains how they can be used as constant speed and variable speed systems. The paper also describes popularly used DFIG for adjustable speed operation. When DFIG based wind generation is included in power network on a large scale there is a need to control the power that is supplied by wind power plant to grid. These generators should be capable of controlling and regulating the power. There are many issues of concern like stability, power quality which are being researched. So, a DFIG model in simplest form is also described with its equivalent network.
{"title":"Doubly Fed Induction Generator-A Wind Technology in the Power System","authors":"Anjali Deshpande, V. Kulkarni","doi":"10.1109/I-SMAC47947.2019.9032688","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032688","url":null,"abstract":"As the stocks of conventional fuels are limited, their prices are increasing every day. The use of conventional fuels creates the problem in emission of greenhouse gases followed by global warming. At the same time the growing industrialization and modernization demands more electricity. Increased demand of electricity makes it necessary to go for alternative sources of energy like solar and wind. The potential of wind energy has made its power plant installation worldwide but along with conventional generation. The wind generators operate very differently from traditional generators. Their share in the power system is considerable, that forces us to study interaction between power systems and wind power plants and study how power system performs along with wind energy conversion systems. Though wind is great natural source speed unpredictability is a major challenge. So, technologies evolved as constant speed and variable speed wind turbines. The paper explains various types of wind energy conversion systems using squirrel cage induction generator (SCIG), synchronous generator (SG) and doubly fed induction generator (DFIG) and explains how they can be used as constant speed and variable speed systems. The paper also describes popularly used DFIG for adjustable speed operation. When DFIG based wind generation is included in power network on a large scale there is a need to control the power that is supplied by wind power plant to grid. These generators should be capable of controlling and regulating the power. There are many issues of concern like stability, power quality which are being researched. So, a DFIG model in simplest form is also described with its equivalent network.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125183192","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032493
Rahul, R. Katarya
The most important issue concerning the country's development is education. By taking into consideration of different attributes used by various researchers, the main focus of this paper is to present a review in an organised way of different classification techniques in predicting the performance of students (POS). This review will be helpful for the teachers of the university or college to find out the weak students, which will help in increasing their performance and enhance their learning, as well as this growth of the student, also reflects on the student background.
{"title":"A Review: Predicting the Performance of Students Using Machine learning Classification Techniques","authors":"Rahul, R. Katarya","doi":"10.1109/I-SMAC47947.2019.9032493","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032493","url":null,"abstract":"The most important issue concerning the country's development is education. By taking into consideration of different attributes used by various researchers, the main focus of this paper is to present a review in an organised way of different classification techniques in predicting the performance of students (POS). This review will be helpful for the teachers of the university or college to find out the weak students, which will help in increasing their performance and enhance their learning, as well as this growth of the student, also reflects on the student background.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132345694","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032492
V. M. Yazhmozhi, B. Janet
Because of the colossal growth of internet, most of the users have changed their preference from traditional shopping, banking etc. to online mode. This paved the way for a lot of cybercrimes including phishing into existence. The attackers try to extract sensitive/personal details such as user ID, passwords and debit card/credit card information by disguising themselves as reliable websites. Identifying whether the Uniform Resource Locator (URL) of a website is legitimate or phishing is a difficult task because it exploits the user's vulnerabilities. Although many products are available for detecting phishing websites, they are just making use of heuristic approach and black lists and hence they can't prevent phishing in a more effective way. A system that detects phishing websites in real time has been proposed in this paper. It uses five different classification algorithms with two different feature sets using natural language processing and word vectors to identify which performs better. After analyzing the accuracy of different machine learning classification algorithms like naive bayes, logistic regression, support vector machine, decision tree and random forest using different features, it has been found that random Forest algorithm with features based on natural language processing has performed better with an accuracy of 97.99.
{"title":"Natural language processing and Machine learning based phishing website detection system","authors":"V. M. Yazhmozhi, B. Janet","doi":"10.1109/I-SMAC47947.2019.9032492","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032492","url":null,"abstract":"Because of the colossal growth of internet, most of the users have changed their preference from traditional shopping, banking etc. to online mode. This paved the way for a lot of cybercrimes including phishing into existence. The attackers try to extract sensitive/personal details such as user ID, passwords and debit card/credit card information by disguising themselves as reliable websites. Identifying whether the Uniform Resource Locator (URL) of a website is legitimate or phishing is a difficult task because it exploits the user's vulnerabilities. Although many products are available for detecting phishing websites, they are just making use of heuristic approach and black lists and hence they can't prevent phishing in a more effective way. A system that detects phishing websites in real time has been proposed in this paper. It uses five different classification algorithms with two different feature sets using natural language processing and word vectors to identify which performs better. After analyzing the accuracy of different machine learning classification algorithms like naive bayes, logistic regression, support vector machine, decision tree and random forest using different features, it has been found that random Forest algorithm with features based on natural language processing has performed better with an accuracy of 97.99.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114290526","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：