Pub Date : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973017
Tej. C. Hiremath, J. Mallapur
The major obstacles in cloud usage is its non-flexible attribute with respect to portability of applications and congestion due to enormous usage of cloud applications by users. Customers of cloud computing are unable to access the services offered by one cloud over the other. Applications running on one cloud environment is bound to the ordinance and principles of provisioning of the same. The customers we are referring here are mobile in nature. The non-flexible attribute we are referring here is cloud vendor lock-in. We have proposed a new scheme called Cloud Application Migration Management Model (CAM3) that encompasses service Cloning for flexible and versatile usage. In this scheme, we plan to clone the application proffered by cloud vendor and install in another homogeneous hybrid cloud environment. The service application migrated can be made accessible by Application Re-engineering and Code Re-factoring techniques, thus making the cloud environment elastic and versatile.
{"title":"Congestion Control in Cloud Computing Network for Load balancing using Portability","authors":"Tej. C. Hiremath, J. Mallapur","doi":"10.1109/IBSSC47189.2019.8973017","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973017","url":null,"abstract":"The major obstacles in cloud usage is its non-flexible attribute with respect to portability of applications and congestion due to enormous usage of cloud applications by users. Customers of cloud computing are unable to access the services offered by one cloud over the other. Applications running on one cloud environment is bound to the ordinance and principles of provisioning of the same. The customers we are referring here are mobile in nature. The non-flexible attribute we are referring here is cloud vendor lock-in. We have proposed a new scheme called Cloud Application Migration Management Model (CAM3) that encompasses service Cloning for flexible and versatile usage. In this scheme, we plan to clone the application proffered by cloud vendor and install in another homogeneous hybrid cloud environment. The service application migrated can be made accessible by Application Re-engineering and Code Re-factoring techniques, thus making the cloud environment elastic and versatile.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123071261","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973073
Prof. Rajveer Singh Yaduvanshi, Msit Nishtha
Wireless communication has eased out human life by eradicated wires jargons running around electronic systems for extending connections. Wireless sensors have made human life comfortable. Self-driving cars will be the era of next generation vehicles. These vehicles will be housing many integrated sensors for taking autonomous decisions while in route. These vehicles have communication capability with infrastructure as well as self. They are equipped with facilities of infotainment and entertainment. Communication wirelessly with self and surrounding have utmost need of compact and efficient integrated antennas for these automotive vehicles. MIMO based antenna has been proposed for diversity reception along with compact size and futuristic aesthetic design. Experimental results have been compared with simulated with close proximity. Self-reliance vehicles embedded with Nano DRA have been unique features of this research. Futuristic design of automotive vehicles should be self-driving and self-charging with possible integration of Nano antennas and Long Range Radar (LRR) as sensor. Overview of smart vehicle antennas has also been included. Possible efficient and compact antennas for use of smart vehicles have been proposed.
{"title":"Smart Antenna Design And Implementation For Vehicles","authors":"Prof. Rajveer Singh Yaduvanshi, Msit Nishtha","doi":"10.1109/IBSSC47189.2019.8973073","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973073","url":null,"abstract":"Wireless communication has eased out human life by eradicated wires jargons running around electronic systems for extending connections. Wireless sensors have made human life comfortable. Self-driving cars will be the era of next generation vehicles. These vehicles will be housing many integrated sensors for taking autonomous decisions while in route. These vehicles have communication capability with infrastructure as well as self. They are equipped with facilities of infotainment and entertainment. Communication wirelessly with self and surrounding have utmost need of compact and efficient integrated antennas for these automotive vehicles. MIMO based antenna has been proposed for diversity reception along with compact size and futuristic aesthetic design. Experimental results have been compared with simulated with close proximity. Self-reliance vehicles embedded with Nano DRA have been unique features of this research. Futuristic design of automotive vehicles should be self-driving and self-charging with possible integration of Nano antennas and Long Range Radar (LRR) as sensor. Overview of smart vehicle antennas has also been included. Possible efficient and compact antennas for use of smart vehicles have been proposed.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123877337","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8972979
A. Bakshi, S. Kopparapu
Indian languages are phonetic in nature; phonetics is branch of linguistics which studies the structure of human language sound. Acoustic phonetic features associated with languages play an important role in spoken language identification. In this paper, Gaussian Mixture Model supervectors is used to capture acoustic phonetic variation in Indian languages. Mel frequency cepstral coefficient (MFCC) with delta coefficients is used to represent the language specific acoustic phonetic information of speech and artificial neural network ANN is used as a classifier for language identification. In the present work, we have conducted extensive experiments for three different datasets created from the news broadcast in different Indian languages from All India Radio. The performance of ANN classifier using GMM supervectors is evaluated on these three datasets.
{"title":"Spoken Indian Language Classification using GMM supervectors and Artificial Neural Networks","authors":"A. Bakshi, S. Kopparapu","doi":"10.1109/IBSSC47189.2019.8972979","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8972979","url":null,"abstract":"Indian languages are phonetic in nature; phonetics is branch of linguistics which studies the structure of human language sound. Acoustic phonetic features associated with languages play an important role in spoken language identification. In this paper, Gaussian Mixture Model supervectors is used to capture acoustic phonetic variation in Indian languages. Mel frequency cepstral coefficient (MFCC) with delta coefficients is used to represent the language specific acoustic phonetic information of speech and artificial neural network ANN is used as a classifier for language identification. In the present work, we have conducted extensive experiments for three different datasets created from the news broadcast in different Indian languages from All India Radio. The performance of ANN classifier using GMM supervectors is evaluated on these three datasets.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116285433","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973086
Himanshu Jaiswal, Karmali Radha P, Ram Singuluri, S. Sampson
With the rapid evolution of technology, automation has taken over almost all fields of operation. The change in human-computer interaction has accelerated over the years. Greenhouses have come a long way in terms of technological advances. For 100% yields, it is essential to constantly monitor the optimal parameters for plant growth. Here in this work, different parameters that impact the yield of crops like humidity, CO2 levels, light intensity, soil moisture, temperature are being monitored, controlled and coordinated using Raspberry Pi and Arduino. Internet of Things has enabled real-time data collection from the Smart Greenhouse and visualization on ThingSpeak platform. This paper proposes a fully automated greenhouse embedded with hydroponics and vertical farming and with excellent security provisions and surveillance to become a highly advanced and diverse version of currently prevailing models.
{"title":"IoT and Machine Learning based approach for Fully Automated Greenhouse","authors":"Himanshu Jaiswal, Karmali Radha P, Ram Singuluri, S. Sampson","doi":"10.1109/IBSSC47189.2019.8973086","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973086","url":null,"abstract":"With the rapid evolution of technology, automation has taken over almost all fields of operation. The change in human-computer interaction has accelerated over the years. Greenhouses have come a long way in terms of technological advances. For 100% yields, it is essential to constantly monitor the optimal parameters for plant growth. Here in this work, different parameters that impact the yield of crops like humidity, CO2 levels, light intensity, soil moisture, temperature are being monitored, controlled and coordinated using Raspberry Pi and Arduino. Internet of Things has enabled real-time data collection from the Smart Greenhouse and visualization on ThingSpeak platform. This paper proposes a fully automated greenhouse embedded with hydroponics and vertical farming and with excellent security provisions and surveillance to become a highly advanced and diverse version of currently prevailing models.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123953771","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973083
P. Tiwari, T. Velayutham
Popularity and openness of Android platform has attracted developers and attackers to find the loopholes in the Android based systems for exploitation. Listed Android vulnerabilities are the result of the sincere efforts made by Android users to make the platform robust. In this paper, we try to find the reasons, which causes this vulnerabilities to occur and become exploitable. We characterize the vulnerabilities based on their attributes and map them with specific issues. We have utilized the National Vulnerability Database (NVD) and crawled the CVEs (Common Vulnerability Exposures) specific to Android, from 2008 to 2018. This database helped in deducing and implicating the taxonomy of the Android vulnerabilities. In the end, we also propose a next generation Android ecosystem to protect and deter from the vulnerabilities.
{"title":"Android Vulnerabilities: Taxonomy and nextGen Ecosystem","authors":"P. Tiwari, T. Velayutham","doi":"10.1109/IBSSC47189.2019.8973083","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973083","url":null,"abstract":"Popularity and openness of Android platform has attracted developers and attackers to find the loopholes in the Android based systems for exploitation. Listed Android vulnerabilities are the result of the sincere efforts made by Android users to make the platform robust. In this paper, we try to find the reasons, which causes this vulnerabilities to occur and become exploitable. We characterize the vulnerabilities based on their attributes and map them with specific issues. We have utilized the National Vulnerability Database (NVD) and crawled the CVEs (Common Vulnerability Exposures) specific to Android, from 2008 to 2018. This database helped in deducing and implicating the taxonomy of the Android vulnerabilities. In the end, we also propose a next generation Android ecosystem to protect and deter from the vulnerabilities.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126848826","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973044
Aum Patil, Amey Wadekar, Tanishq Gupta, Rohit Vijan, F. Kazi
Anomaly detection has always been of utmost importance especially in log file systems. Many different supervised techniques have been explored to deal with this problem. Deep Learning approaches have shown huge promise in log file anomaly detection systems due to their superior ability to learn high level features and non-linearities eliminating the need for any domain specific knowledge or special pre-processing. But this increased performance comes at the cost of inexplicability of the outcomes resulting from the black-box nature of such models. In this paper, we propose a solution utilizing a LSTM-LRP (Long Short Term Memory - Layerwise Relevance Propagation) architecture for discrete event sequences which are obtained by processing log files using log keys derived from individual entries. We extend the idea of LSTM-LRP, used in NLP problems to Log file Systems. The model is evaluated on Hadoop Distributed File System (HDFS) logs where an interpretation for every timestep and every feature is provided. Our major concern in this paper is the interpretation of the results over accuracy of the model. This not only offers an interpretation of the outcomes but also helps build trust in the model by making sure that spurious correlations are avoided making it suitable for real life applications.
{"title":"Explainable LSTM Model for Anomaly Detection in HDFS Log File using Layerwise Relevance Propagation","authors":"Aum Patil, Amey Wadekar, Tanishq Gupta, Rohit Vijan, F. Kazi","doi":"10.1109/IBSSC47189.2019.8973044","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973044","url":null,"abstract":"Anomaly detection has always been of utmost importance especially in log file systems. Many different supervised techniques have been explored to deal with this problem. Deep Learning approaches have shown huge promise in log file anomaly detection systems due to their superior ability to learn high level features and non-linearities eliminating the need for any domain specific knowledge or special pre-processing. But this increased performance comes at the cost of inexplicability of the outcomes resulting from the black-box nature of such models. In this paper, we propose a solution utilizing a LSTM-LRP (Long Short Term Memory - Layerwise Relevance Propagation) architecture for discrete event sequences which are obtained by processing log files using log keys derived from individual entries. We extend the idea of LSTM-LRP, used in NLP problems to Log file Systems. The model is evaluated on Hadoop Distributed File System (HDFS) logs where an interpretation for every timestep and every feature is provided. Our major concern in this paper is the interpretation of the results over accuracy of the model. This not only offers an interpretation of the outcomes but also helps build trust in the model by making sure that spurious correlations are avoided making it suitable for real life applications.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123424970","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973008
M. Sarode, Ayush Ghanekar, Sahil Krishnadas, Y. Patil, Manish Parmar
This paper presents an efficient method for a smart blood management system, called Intelligent Blood Management System (IBMS) that intends to provide a efficient and a real time coordination of blood management within a blood bank as well as to establish great communication amongst multiple blood banks. This system uses an unique and a economical concept of using the weight detecting sensors along with image processing that can efficiently track the quantity of the different blood groups (using colour coding mechanism) in all the associated blood banks, using Cloud connectivity. It uses an internal management analytic that always takes care of the availability of blood and using predetermined logic that can pre populate a blood bank based on the highest frequency of the need of a certain blood in an area. This system has an integration of user interaction also, where users and even hospitals can make requests for blood through the app (including app verification). The mobile application helps users to connect with the system including the fastest way to reach the blood bank and even live tracking if the blood is to be delivered from the bank to the hospital and more.
{"title":"Intelligent Blood Management System","authors":"M. Sarode, Ayush Ghanekar, Sahil Krishnadas, Y. Patil, Manish Parmar","doi":"10.1109/IBSSC47189.2019.8973008","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973008","url":null,"abstract":"This paper presents an efficient method for a smart blood management system, called Intelligent Blood Management System (IBMS) that intends to provide a efficient and a real time coordination of blood management within a blood bank as well as to establish great communication amongst multiple blood banks. This system uses an unique and a economical concept of using the weight detecting sensors along with image processing that can efficiently track the quantity of the different blood groups (using colour coding mechanism) in all the associated blood banks, using Cloud connectivity. It uses an internal management analytic that always takes care of the availability of blood and using predetermined logic that can pre populate a blood bank based on the highest frequency of the need of a certain blood in an area. This system has an integration of user interaction also, where users and even hospitals can make requests for blood through the app (including app verification). The mobile application helps users to connect with the system including the fastest way to reach the blood bank and even live tracking if the blood is to be delivered from the bank to the hospital and more.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134060337","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973071
Akhilesh Vilas Kashikar, Prof. Jyoti Ramteke
Whenever a person wants to buy some new thing, watch a movie or go to an unknown place, he/she searches for online reviews. People who have watched that particular movie or have been to that place in the past post these reviews, which leads to huge volumes of user-oriented textual data which is rendered useless if it is not thoroughly analyzed and put into some techniques as input and derive some application-specific and meaningful results. Hence, in this paper, we propose a sentiment classification model named as Dual Sentiment Classification (DSC) with Sarcasm Identification. This model will first perform sarcasm identification on the user reviews and classify them as sarcastic and non-sarcastic and then sentiment classification will be performed using dual sentiment analysis concept, to classify the reviews as positive or negative.
{"title":"Dual Sentiment Classification with Sarcasm Identification","authors":"Akhilesh Vilas Kashikar, Prof. Jyoti Ramteke","doi":"10.1109/IBSSC47189.2019.8973071","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973071","url":null,"abstract":"Whenever a person wants to buy some new thing, watch a movie or go to an unknown place, he/she searches for online reviews. People who have watched that particular movie or have been to that place in the past post these reviews, which leads to huge volumes of user-oriented textual data which is rendered useless if it is not thoroughly analyzed and put into some techniques as input and derive some application-specific and meaningful results. Hence, in this paper, we propose a sentiment classification model named as Dual Sentiment Classification (DSC) with Sarcasm Identification. This model will first perform sarcasm identification on the user reviews and classify them as sarcastic and non-sarcastic and then sentiment classification will be performed using dual sentiment analysis concept, to classify the reviews as positive or negative.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130288868","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973106
Advait Ambeskar, A. Bondre, V. Turkar, Hetal Gosavi
Path finding is an important problem in robot design and automation that requires quick error-free solutions that rely on external environment. Automated mobile robotic systems employ various techniques to determine the path that the robot needs to follow to reach the destination to perform its function. Path finding problems can utilize various algorithms to solve the problem. Sensor data can be used as a reference to determine the path to be followed from the start point to the destination. However, this technique is highly localized and does not provide the ability to make decisions by taking global constraints or conditions into consideration. Image processing techniques are employed extensively to provide a solution based on global conditions. The proposed method involves use of image processing to process the acquired image of the maze from a mounted camera system. The processing steps are used to provide steps which the robot can follow to reach from its current position to the final position. This project implements a universal algorithm to allow the robot to maneuver autonomously.
{"title":"Intuitive solution for Robot Maze Problem using Image Processing","authors":"Advait Ambeskar, A. Bondre, V. Turkar, Hetal Gosavi","doi":"10.1109/IBSSC47189.2019.8973106","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973106","url":null,"abstract":"Path finding is an important problem in robot design and automation that requires quick error-free solutions that rely on external environment. Automated mobile robotic systems employ various techniques to determine the path that the robot needs to follow to reach the destination to perform its function. Path finding problems can utilize various algorithms to solve the problem. Sensor data can be used as a reference to determine the path to be followed from the start point to the destination. However, this technique is highly localized and does not provide the ability to make decisions by taking global constraints or conditions into consideration. Image processing techniques are employed extensively to provide a solution based on global conditions. The proposed method involves use of image processing to process the acquired image of the maze from a mounted camera system. The processing steps are used to provide steps which the robot can follow to reach from its current position to the final position. This project implements a universal algorithm to allow the robot to maneuver autonomously.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115190209","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973075
Manisha Kalra, Satish Kumar, Bhargab Das
A novel approach is proposed to detect moving ground target using empirical wavelet transform (EWT) as a time-frequency technique. In order to analyze the performance of EWT, the seismic dataset is generated by acquiring the seismic signature of the moving vehicle, i.e., bus. EWT based time-frequency coefficients have been computed from the seismic signals. The number of statistical features has been calculated from EWT based time-frequency coefficients. With the statistical features, bus and noise have been classified using SVM as a classifier. Accuracy, true positive rate, and area under the curve (AUC) have been used as the performance parameters of the algorithm. The AUC of approximately 95%, true positive rate, and accuracy of about 89% have been achieved.
{"title":"Target Detection on the basis of Empirical Wavelet Transform using Seismic Signal","authors":"Manisha Kalra, Satish Kumar, Bhargab Das","doi":"10.1109/IBSSC47189.2019.8973075","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973075","url":null,"abstract":"A novel approach is proposed to detect moving ground target using empirical wavelet transform (EWT) as a time-frequency technique. In order to analyze the performance of EWT, the seismic dataset is generated by acquiring the seismic signature of the moving vehicle, i.e., bus. EWT based time-frequency coefficients have been computed from the seismic signals. The number of statistical features has been calculated from EWT based time-frequency coefficients. With the statistical features, bus and noise have been classified using SVM as a classifier. Accuracy, true positive rate, and area under the curve (AUC) have been used as the performance parameters of the algorithm. The AUC of approximately 95%, true positive rate, and accuracy of about 89% have been achieved.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132032896","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：