Pub Date : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696563
Jian Teck Hau, R. Tan, Jing En Chin
A modern DC electric railway traction power supply system consists of a twelve-pulse rectifier which will cause 11th and 13th order harmonics to be injected into the power system. A shunt active harmonic filter (SAHF) is proposed to mitigate the harmonics at medium voltage (MV) line. SAHF control strategy usually consists of three core elements which include reference current generation, DC-link feedback control, and current control and gate signal generation. This paper proposed a distinct time domain-based control strategy with DC-linked feedback reference current compensation method which has a simple topology, low mathematical complexity, and fast response time. Detailed performance analysis of SAHF is carried out in the parameter selection process whereby the effects of each parameter are discussed. The implementation of SAHF in traction power supply substation (TPSS) is simulated using MATLAB/Simulink. The harmonic analysis result has shown the effectiveness of the proposed SAHF in reducing THDv, TDDi, 11th order IHDi, and 13th order IHDi of TPSS MV line to levels lower than 4.61%, 1.03%, 0.96%, and 0.67% respectively which are compliant with the limits recommended by IEEE std. 519–2014.
{"title":"DC-Linked Feedback Compensated Shunt Active Harmonic Filter for Traction Power Supply Substation Medium Voltage Line","authors":"Jian Teck Hau, R. Tan, Jing En Chin","doi":"10.1109/i-PACT52855.2021.9696563","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696563","url":null,"abstract":"A modern DC electric railway traction power supply system consists of a twelve-pulse rectifier which will cause 11th and 13th order harmonics to be injected into the power system. A shunt active harmonic filter (SAHF) is proposed to mitigate the harmonics at medium voltage (MV) line. SAHF control strategy usually consists of three core elements which include reference current generation, DC-link feedback control, and current control and gate signal generation. This paper proposed a distinct time domain-based control strategy with DC-linked feedback reference current compensation method which has a simple topology, low mathematical complexity, and fast response time. Detailed performance analysis of SAHF is carried out in the parameter selection process whereby the effects of each parameter are discussed. The implementation of SAHF in traction power supply substation (TPSS) is simulated using MATLAB/Simulink. The harmonic analysis result has shown the effectiveness of the proposed SAHF in reducing THDv, TDDi, 11th order IHDi, and 13th order IHDi of TPSS MV line to levels lower than 4.61%, 1.03%, 0.96%, and 0.67% respectively which are compliant with the limits recommended by IEEE std. 519–2014.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134103389","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696880
Srisailam Sreedhar, V. Srinivasan, Arulmozhivarman P, T. Selvaraj
With growing concerns due to climate change, lightning has become a perceptible natural disaster that has triggered large-scale damages to tall structures, including heritage monuments. Several researchers have implemented and utilized various methods of Lightning Protection Systems (LPS) to safeguard the structures from direct lightning strokes. However, several occurrences of damages caused due to lightning strokes on heritage monuments and structures of significance continue to be reported worldwide. The main objectives of this research are to analyze the adequacy and reliability of the existing LPS installed in a famous ‘renaissance architecture’ heritage church i.e., Sé Cathedral, Goa and carry out detailed lightning protection studies for gable roofs using variants of electro-geometric methods. Further, recommendations are summarized wherein locations of critical points of strikes to the structure from direct lightning strikes are identified to avoid consequent damages.
{"title":"Reliability Assessment of Lightning Protection of Renaissance Architecture Based Heritage Church in India Using Electrogeometric Methods","authors":"Srisailam Sreedhar, V. Srinivasan, Arulmozhivarman P, T. Selvaraj","doi":"10.1109/i-PACT52855.2021.9696880","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696880","url":null,"abstract":"With growing concerns due to climate change, lightning has become a perceptible natural disaster that has triggered large-scale damages to tall structures, including heritage monuments. Several researchers have implemented and utilized various methods of Lightning Protection Systems (LPS) to safeguard the structures from direct lightning strokes. However, several occurrences of damages caused due to lightning strokes on heritage monuments and structures of significance continue to be reported worldwide. The main objectives of this research are to analyze the adequacy and reliability of the existing LPS installed in a famous ‘renaissance architecture’ heritage church i.e., Sé Cathedral, Goa and carry out detailed lightning protection studies for gable roofs using variants of electro-geometric methods. Further, recommendations are summarized wherein locations of critical points of strikes to the structure from direct lightning strikes are identified to avoid consequent damages.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"63 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134224755","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696859
S. Kalpana Devi, K. Samy Durai, Karthik M Shri Balaji, J. Ravi Kumar
Blockchain has gotten a lot of publicity recently, and there are a lot of applications that have come out of it. The cryptocurrency, Bitcoin is a well-known Blockchain technology which effectively solves the double-spending issue, can validate the validity of transactional history without depending on a centralised framework to do the same. As a result, the application which uses Blockchain technology as its foundation guarantees that the data is tamper-free. The paper employs a decentralised Blockchain based proposal to verify that customers do not solely depend on retailers to decide whether or not goods are original. We define a decentralised Blockchain framework without fake goods, so that producers can use it to produce legitimate products without directly handling stores, lowering product quality assurance costs significantly.
{"title":"Fake Product Identification with the Help Of Block Chain Technology","authors":"S. Kalpana Devi, K. Samy Durai, Karthik M Shri Balaji, J. Ravi Kumar","doi":"10.1109/i-PACT52855.2021.9696859","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696859","url":null,"abstract":"Blockchain has gotten a lot of publicity recently, and there are a lot of applications that have come out of it. The cryptocurrency, Bitcoin is a well-known Blockchain technology which effectively solves the double-spending issue, can validate the validity of transactional history without depending on a centralised framework to do the same. As a result, the application which uses Blockchain technology as its foundation guarantees that the data is tamper-free. The paper employs a decentralised Blockchain based proposal to verify that customers do not solely depend on retailers to decide whether or not goods are original. We define a decentralised Blockchain framework without fake goods, so that producers can use it to produce legitimate products without directly handling stores, lowering product quality assurance costs significantly.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134449021","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696470
S. Manoharan, V. Govindaraj, P. Palpandian, G. Sureshkumaar, B. Mahalakshmi
In India, there is an increasing demand for electrical energy to meet irrigation needs. Many states electrical utilities have been experiencing severe power outages, causing farmers to become dissatisfied. It has been observed that underground water levels have dropped dramatically over the last few decades, while cultivated land has increased due to forest clearing. As a result, demand for electrical energy for irrigation is increasing. Agriculture receives free electricity in many Indian states. So, despite the fact that there is a lot of savings potential in pump sets, the poor farmer has no interest in replacing inefficient pump sets, incorporating capacitors, or spending money on existing pump sets other than rewinding burnout motors, etc. Subsidized or free power greatly encourages this mindset to choose a slightly more expensive efficient pump set. This paper examines the various factors that can impact a pump set's efficiency, as well as initiatives undertaken by the Indian government to improve energy efficiency in the agricultural sector. The article also discusses obstacles/difficulties encountered while replacing inefficient pump sets with energy efficient pump sets, as well as policy recommendations for improving overall efficiency in this sector.
{"title":"A Study on Energy Efficiency of Agriculture Pumpsets in India","authors":"S. Manoharan, V. Govindaraj, P. Palpandian, G. Sureshkumaar, B. Mahalakshmi","doi":"10.1109/i-PACT52855.2021.9696470","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696470","url":null,"abstract":"In India, there is an increasing demand for electrical energy to meet irrigation needs. Many states electrical utilities have been experiencing severe power outages, causing farmers to become dissatisfied. It has been observed that underground water levels have dropped dramatically over the last few decades, while cultivated land has increased due to forest clearing. As a result, demand for electrical energy for irrigation is increasing. Agriculture receives free electricity in many Indian states. So, despite the fact that there is a lot of savings potential in pump sets, the poor farmer has no interest in replacing inefficient pump sets, incorporating capacitors, or spending money on existing pump sets other than rewinding burnout motors, etc. Subsidized or free power greatly encourages this mindset to choose a slightly more expensive efficient pump set. This paper examines the various factors that can impact a pump set's efficiency, as well as initiatives undertaken by the Indian government to improve energy efficiency in the agricultural sector. The article also discusses obstacles/difficulties encountered while replacing inefficient pump sets with energy efficient pump sets, as well as policy recommendations for improving overall efficiency in this sector.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131994025","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696586
Raghav Khattar, S. Srinivas, A. Sharmila, S. Balaganapathy
In this paper, we present the design, implementation and the authentication of a novel Internet of Things (IoT) Anaesthesia drug control system for the online continuous and mutinous controlling of Anaesthesia drugs by detecting two vital body parameters, i.e., body temperature and pulse rate. The mentioned complete system comprises a NodeMCU based control system that drives and reads out the signal from the sensors. When the sensors sense readings of heart rate, body temperature and sweat from the patient's body, which are out of the normal range, the system is designed to drive the servomotor and hence control the Anaesthesia drugs injection in the body according to the patient's current state. The IoT network is upheld by a Cloud framework, which permits the specialist to monitor all the patient's information through Ubidots Cloud. The real time readings of the body parameters of the patient and the position of servo motor, hence the status of the Anaesthesia drug delivery is sent to the hospital cloud from where an anesthetist can observe the readings. If abnormal body temperature and heart rate is observed, the concerned personnel are alerted. Anaesthesia delivery is stopped until the state of the patient becomes normal. The approval closes with the check that this framework effectively works for the concurrent observing and controlling of sedation and the system is turned off manually with a switch. This work is focused on automating the process of Anaesthesia delivery and making the process more economical and efficient.
{"title":"Non-Invasive IoT-Based Anaesthesia Control System","authors":"Raghav Khattar, S. Srinivas, A. Sharmila, S. Balaganapathy","doi":"10.1109/i-PACT52855.2021.9696586","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696586","url":null,"abstract":"In this paper, we present the design, implementation and the authentication of a novel Internet of Things (IoT) Anaesthesia drug control system for the online continuous and mutinous controlling of Anaesthesia drugs by detecting two vital body parameters, i.e., body temperature and pulse rate. The mentioned complete system comprises a NodeMCU based control system that drives and reads out the signal from the sensors. When the sensors sense readings of heart rate, body temperature and sweat from the patient's body, which are out of the normal range, the system is designed to drive the servomotor and hence control the Anaesthesia drugs injection in the body according to the patient's current state. The IoT network is upheld by a Cloud framework, which permits the specialist to monitor all the patient's information through Ubidots Cloud. The real time readings of the body parameters of the patient and the position of servo motor, hence the status of the Anaesthesia drug delivery is sent to the hospital cloud from where an anesthetist can observe the readings. If abnormal body temperature and heart rate is observed, the concerned personnel are alerted. Anaesthesia delivery is stopped until the state of the patient becomes normal. The approval closes with the check that this framework effectively works for the concurrent observing and controlling of sedation and the system is turned off manually with a switch. This work is focused on automating the process of Anaesthesia delivery and making the process more economical and efficient.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"417 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131526993","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696523
R. Kapoor, M. Sushama, Bhavani Reddy Andem, Akhila Sri Phani Sai Sindhura S.
The deep neural network architectures can be utilized to detect and recognize the text in natural or camera images. If this text can be converted to voice signals it will be very helpful for persons with partial or no vision. Selective search-based segmentation along with VGG architecture of Deep neural networks is utilized in this work for text detection. The Py-Tesseract Optimal character recognizer is then utilized for recognizing the detected text, which is then converted to voice signals. The system can beneficial for recognizing road side or corridor boards, thus adding some independence to the life of people with special needs. The system can be modified with a search mode for a particular text in the nearby location.
{"title":"Natural Scene Text to Voice Signal Conversion for Visually Impaired using Deep Neural Network","authors":"R. Kapoor, M. Sushama, Bhavani Reddy Andem, Akhila Sri Phani Sai Sindhura S.","doi":"10.1109/i-PACT52855.2021.9696523","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696523","url":null,"abstract":"The deep neural network architectures can be utilized to detect and recognize the text in natural or camera images. If this text can be converted to voice signals it will be very helpful for persons with partial or no vision. Selective search-based segmentation along with VGG architecture of Deep neural networks is utilized in this work for text detection. The Py-Tesseract Optimal character recognizer is then utilized for recognizing the detected text, which is then converted to voice signals. The system can beneficial for recognizing road side or corridor boards, thus adding some independence to the life of people with special needs. The system can be modified with a search mode for a particular text in the nearby location.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132460077","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696935
S. Nagaraj, B. Krishna, Botta Chakradhar, Debanjan Sarkar
Semiconductor devices has been undergoing large improvement in terms of performance, speed of the device because of large scaling of devices, simultaneously the power dissipation has been one of the major concern. As the scaling of device has been reached its limits the break through could be the emerging technology i.e., Reversible computing in VLSI industry. As this technology has zero power dissipation, this is a major advantage in the reversible logic circuits. The ALU is major component in the system and it is used in the applications such as computers, mobiles, and calculators. The 32 Bit arithmetic logic unit is designed using Verilog Hardware Description Language with operations such as AND logic, OR logic, FullAdder using One bit ALU. The reversible ALU can work fast as compared with irreversible ALU. Reversible logic gates decreases power dissipation, delay and area. So reversible gates are used in VLSI design techniques. This paper presents an ALU designed of reversible logic gates using Toffoli, Fredkin, and Peres Gate which replaces the AND and OR gate for each one bit ALU. All the logics are performed using the softwares Modelsim Altera 6.3g and the synthesis using Xilinx ISE 14.7. The designed ALU using reversible logic reduces the area about 34% and delay about 48.91%.
由于器件的规模化，半导体器件在性能、速度等方面都有了很大的提高，同时其功耗也一直是人们关注的主要问题之一。随着器件的规模已经达到极限，突破口可能是超大规模集成电路行业的新兴技术，即可逆计算。由于该技术具有零功耗，这是可逆逻辑电路的主要优势。ALU是系统的主要组成部分，主要用于计算机、手机、计算器等应用。采用Verilog硬件描述语言设计32位算术逻辑单元，采用1位ALU实现与逻辑、或逻辑、全阶梯等运算。与不可逆ALU相比，可逆ALU工作速度快。可逆逻辑门降低功耗，延迟和面积。因此，可逆门被用于超大规模集成电路的设计技术中。本文提出了一种采用Toffoli门、Fredkin门和Peres门设计的可逆逻辑门的ALU，它代替了每个位ALU的与或门。所有的逻辑都是使用Modelsim Altera 6.3g软件执行的，合成使用Xilinx ISE 14.7。采用可逆逻辑设计的ALU可减少约34%的面积和48.91%的延迟。
{"title":"Comparison of 32-bit ALU for Reversible Logic and Irreversible Logic","authors":"S. Nagaraj, B. Krishna, Botta Chakradhar, Debanjan Sarkar","doi":"10.1109/i-PACT52855.2021.9696935","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696935","url":null,"abstract":"Semiconductor devices has been undergoing large improvement in terms of performance, speed of the device because of large scaling of devices, simultaneously the power dissipation has been one of the major concern. As the scaling of device has been reached its limits the break through could be the emerging technology i.e., Reversible computing in VLSI industry. As this technology has zero power dissipation, this is a major advantage in the reversible logic circuits. The ALU is major component in the system and it is used in the applications such as computers, mobiles, and calculators. The 32 Bit arithmetic logic unit is designed using Verilog Hardware Description Language with operations such as AND logic, OR logic, FullAdder using One bit ALU. The reversible ALU can work fast as compared with irreversible ALU. Reversible logic gates decreases power dissipation, delay and area. So reversible gates are used in VLSI design techniques. This paper presents an ALU designed of reversible logic gates using Toffoli, Fredkin, and Peres Gate which replaces the AND and OR gate for each one bit ALU. All the logics are performed using the softwares Modelsim Altera 6.3g and the synthesis using Xilinx ISE 14.7. The designed ALU using reversible logic reduces the area about 34% and delay about 48.91%.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133383606","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696965
Kishore Bingi, B. Prusty
This paper focuses on developing an analytical model for rational approximation of time-delay systems. The proposed model's attractiveness is in its simplicity and ease of implementation. The technique uses frequency response data of the pure time-delay model during the least square iteration while minimizing the Levy's cost function. The step-response characteristics of the proposed method have shown the best performance on various integer and fractional-order time-delay systems compared to the frequently used Padé approach. The numerical analysis in integral absolute error has further confirmed the best result of the proposed technique. This is true for all the considered integer and fractional-order time-delay systems.
{"title":"Approximation of Time-Delay Systems Using Curve Fitting Technique","authors":"Kishore Bingi, B. Prusty","doi":"10.1109/i-PACT52855.2021.9696965","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696965","url":null,"abstract":"This paper focuses on developing an analytical model for rational approximation of time-delay systems. The proposed model's attractiveness is in its simplicity and ease of implementation. The technique uses frequency response data of the pure time-delay model during the least square iteration while minimizing the Levy's cost function. The step-response characteristics of the proposed method have shown the best performance on various integer and fractional-order time-delay systems compared to the frequently used Padé approach. The numerical analysis in integral absolute error has further confirmed the best result of the proposed technique. This is true for all the considered integer and fractional-order time-delay systems.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133946509","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696588
Shubhi Rawat, Damini Kashyap, Aman Kumar, Gopal Rawat
Data segregation is a vital task to label the class of data. Attributes are part of knowledge working in a math task. In this paper, we report the comparative study of various classifiers, i.e., K-Nearest Neighbor (K-NN), Decision Tree, Nave Bayes, Support Vector Machine (SVM) and Random Forest, analyze that which classifier works well beneath what conditions. For this purpose, medical datasets, i.e., UCI datasets have been selected. The performance of these classifiers have been evaluated in terms of Recall, Precision, Accuracy, and F1-Score. The accuracy for Decision Tree, K-NN, Nave Bayes, SVM and Random Forest, are observed to be 95.85%, 100%, 100%, 87.46% and 98.32%, respectively. The present study illustrates that the K-NN and Nave Bayes classifiers outperformed as compared to Decision Tree, SVM and Random Forest. Therefore, KNN and Nave Bayes classifiers can be used in automatic ailment and ascertaining diseases detection.
{"title":"Comparative Analysis of Various Classification Models on Disease Symptom Prediction Dataset","authors":"Shubhi Rawat, Damini Kashyap, Aman Kumar, Gopal Rawat","doi":"10.1109/i-PACT52855.2021.9696588","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696588","url":null,"abstract":"Data segregation is a vital task to label the class of data. Attributes are part of knowledge working in a math task. In this paper, we report the comparative study of various classifiers, i.e., K-Nearest Neighbor (K-NN), Decision Tree, Nave Bayes, Support Vector Machine (SVM) and Random Forest, analyze that which classifier works well beneath what conditions. For this purpose, medical datasets, i.e., UCI datasets have been selected. The performance of these classifiers have been evaluated in terms of Recall, Precision, Accuracy, and F1-Score. The accuracy for Decision Tree, K-NN, Nave Bayes, SVM and Random Forest, are observed to be 95.85%, 100%, 100%, 87.46% and 98.32%, respectively. The present study illustrates that the K-NN and Nave Bayes classifiers outperformed as compared to Decision Tree, SVM and Random Forest. Therefore, KNN and Nave Bayes classifiers can be used in automatic ailment and ascertaining diseases detection.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132798426","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 : 2021-11-27DOI: 10.1109/i-PACT52855.2021.9696930
B. K. P., Derick Mathew, R. C, R. M.
Replay attack is vulnerable to automatic speaker verification system, where the frauds get the access by replaying the pre-recorded speech utterances of the genuine speakers. In this proposed work, we mainly concentrated on high frequency band and classification part. This paper shows the importance of higher frequency band (6 kHz to 8 kHz). The huge difference between genuine and spoofed speech spectrum is also explained which is caused due to imperfection occurred by using multiple anti-aliasing filters. Alongside, Constant-Q Cepstral Coefficients (CQCC) technique is used to extract magnitude discrimination power features set to detect the replayed spoof attack for speaker verification. Further the ELM based BiLSTM is proposed to improve the system performance. The proposed framework shows better results of Equal Error Rate (EER) to 05.26% for development set and 8.44% for evaluation set.
{"title":"New Approach to Detect Replay Attack for Speaker Verification System Using High Frequency Features and ELM Based BiLSTM","authors":"B. K. P., Derick Mathew, R. C, R. M.","doi":"10.1109/i-PACT52855.2021.9696930","DOIUrl":"https://doi.org/10.1109/i-PACT52855.2021.9696930","url":null,"abstract":"Replay attack is vulnerable to automatic speaker verification system, where the frauds get the access by replaying the pre-recorded speech utterances of the genuine speakers. In this proposed work, we mainly concentrated on high frequency band and classification part. This paper shows the importance of higher frequency band (6 kHz to 8 kHz). The huge difference between genuine and spoofed speech spectrum is also explained which is caused due to imperfection occurred by using multiple anti-aliasing filters. Alongside, Constant-Q Cepstral Coefficients (CQCC) technique is used to extract magnitude discrimination power features set to detect the replayed spoof attack for speaker verification. Further the ELM based BiLSTM is proposed to improve the system performance. The proposed framework shows better results of Equal Error Rate (EER) to 05.26% for development set and 8.44% for evaluation set.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122243994","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：