Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986443
Somendra Kumar Singh, Satyendra Singh, R. Sharma
This paper presents the performance investigation of a grid-connected WIND-DFIG system with a static synchronous compensator (STATCOM) by including the supercapacitor energy storage system (SESS) under fault (LLL-G) conditions. During a fault condition, the grid connected WIND-DFIG system requires a quick power exchange between active and reactive powers for stability in the system. A general STATCOM does not have active power exchange between grid-connected WING-DFIG systems; it has only reactive power exchange capability. So, the supercapacitor provides active power exchange capability to STATCOM under any dynamic change in the grid-connected WIND-DFIG system. The entire proposed grid-connected WIND-DFIG system was built and tested for performance under fault conditions with and without STATCOM-SESS in MATLAB/SIMULINK Software.
{"title":"Dynamic Performance Analysis of Grid-Connected Wind-DFIG System using STATCOM-SESS","authors":"Somendra Kumar Singh, Satyendra Singh, R. Sharma","doi":"10.1109/UPCON56432.2022.9986443","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986443","url":null,"abstract":"This paper presents the performance investigation of a grid-connected WIND-DFIG system with a static synchronous compensator (STATCOM) by including the supercapacitor energy storage system (SESS) under fault (LLL-G) conditions. During a fault condition, the grid connected WIND-DFIG system requires a quick power exchange between active and reactive powers for stability in the system. A general STATCOM does not have active power exchange between grid-connected WING-DFIG systems; it has only reactive power exchange capability. So, the supercapacitor provides active power exchange capability to STATCOM under any dynamic change in the grid-connected WIND-DFIG system. The entire proposed grid-connected WIND-DFIG system was built and tested for performance under fault conditions with and without STATCOM-SESS in MATLAB/SIMULINK Software.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133750403","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986442
Sameep Sahu, Salauddin Ansari, O. Gupta
To protect microgrids the variation in fault level poses a significant challenge. In this paper, a wavelet energy-based protection scheme is proposed to detect the fault. The sum of the squared differential current in all three phases is passed to DWT (discrete wavelet transform) filter bank. The wavelet coefficients are obtained using the signal processing technique (DWT) and the energy of the extracted wavelet coefficients is calculated. When wavelet energy exceeds the threshold limit, it is considered an internal fault else it is an external fault or external disturbance. The microgrid's performance was estimated by taking several parameters like different fault types, fault locations, fault resistances, and external fault and non-fault conditions (capacitor and load switching). The microgrid was modeled in MATLAB/Simulink environment. A comparison has been done between the differential protection scheme and the proposed wavelet energy-based scheme. The proposed wavelet energy protection scheme detected faults in 6 ms and provided reliable results in detecting faults for low-voltage AC microgrids. The simulation results indicate that a wavelet energy-based scheme can be implemented to enhance the protection of the microgrid.
{"title":"Protection of low voltage AC microgrid using discrete wavelet transform","authors":"Sameep Sahu, Salauddin Ansari, O. Gupta","doi":"10.1109/UPCON56432.2022.9986442","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986442","url":null,"abstract":"To protect microgrids the variation in fault level poses a significant challenge. In this paper, a wavelet energy-based protection scheme is proposed to detect the fault. The sum of the squared differential current in all three phases is passed to DWT (discrete wavelet transform) filter bank. The wavelet coefficients are obtained using the signal processing technique (DWT) and the energy of the extracted wavelet coefficients is calculated. When wavelet energy exceeds the threshold limit, it is considered an internal fault else it is an external fault or external disturbance. The microgrid's performance was estimated by taking several parameters like different fault types, fault locations, fault resistances, and external fault and non-fault conditions (capacitor and load switching). The microgrid was modeled in MATLAB/Simulink environment. A comparison has been done between the differential protection scheme and the proposed wavelet energy-based scheme. The proposed wavelet energy protection scheme detected faults in 6 ms and provided reliable results in detecting faults for low-voltage AC microgrids. The simulation results indicate that a wavelet energy-based scheme can be implemented to enhance the protection of the microgrid.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125133737","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986454
Aditya Raj, Ramesh K. Bhukya
The aim of this study is to automate the detection of COVID-19 patients by analysing the acoustic information embedded in cough samples. COVID-19 is a respiratory disease having cough acoustics as a common symptom and indicator. The primary focus is classification of generated deep features from analytical and mathematical representation of cough acoustics using signal processing techniques Mel-frequency cepstral coefficients (MFCCs) and Mel-spectrogram. MFCCs provides feature vector representation of cough signal and is used as an input for deep neural network (DNN) to generate deep features. Transfer Learning ResNet-50 based Convolutional Neural Network (CNN) model is used to generate deep features from image representation of cough in the form of Mel Spectrogram. Dataset labelling is done with two categories of COVID-19 and Non-COVID-19 classes. Among them, we have used 70% of the dataset for training and 30% for testing purposes. The deep features generated from MFCCs and Mel Spectrograms are concatenated along with a feature value output from a DNN having Metadata as input. The final concatenated feature vector is sent for Softmax based classification. By completing the whole process, we obtained the training AUC (Area Under Curve) (ROC) 95.39%, validation AUC as 88.19% and testing AUC as 88.76%. The analysis of final AUC with epoch curve shows constant increase in training AUC and convergence of validation and testing AUC at certain value representing model training as perfectly fit and no overfitting-underfitting problem.
{"title":"Vocal Biomarker Based COVID-19 Detection Using DNN and Transfer Learning ResNet50","authors":"Aditya Raj, Ramesh K. Bhukya","doi":"10.1109/UPCON56432.2022.9986454","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986454","url":null,"abstract":"The aim of this study is to automate the detection of COVID-19 patients by analysing the acoustic information embedded in cough samples. COVID-19 is a respiratory disease having cough acoustics as a common symptom and indicator. The primary focus is classification of generated deep features from analytical and mathematical representation of cough acoustics using signal processing techniques Mel-frequency cepstral coefficients (MFCCs) and Mel-spectrogram. MFCCs provides feature vector representation of cough signal and is used as an input for deep neural network (DNN) to generate deep features. Transfer Learning ResNet-50 based Convolutional Neural Network (CNN) model is used to generate deep features from image representation of cough in the form of Mel Spectrogram. Dataset labelling is done with two categories of COVID-19 and Non-COVID-19 classes. Among them, we have used 70% of the dataset for training and 30% for testing purposes. The deep features generated from MFCCs and Mel Spectrograms are concatenated along with a feature value output from a DNN having Metadata as input. The final concatenated feature vector is sent for Softmax based classification. By completing the whole process, we obtained the training AUC (Area Under Curve) (ROC) 95.39%, validation AUC as 88.19% and testing AUC as 88.76%. The analysis of final AUC with epoch curve shows constant increase in training AUC and convergence of validation and testing AUC at certain value representing model training as perfectly fit and no overfitting-underfitting problem.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125182234","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986422
Jahnvi Tiwari, D. Dubey, A. Prakash, R. Tripathi
A trustworthy medium access control (MAC) protocol is needed to enable recent advancements in transport systems to broadcast high-priority safety messages. Cognitive radio-based vehicle ad hoc networks (CR-VANETs) are being implemented by researchers to satisfy the rapidly rising spectrum demand with ease. However, fraudulent users may insert false emergency alarms into CR-VANETs, blocking nodes from getting the most recent traffic conditions. To ensure the dependability and credibility of the safety message conveyed over the networks, evaluating the trustworthiness of nodes has become a vital responsibility in CR-VANETs. In this study, to determine the level of trust for each node, several performance metrics of the proposed MAC protocol are evaluated cooperatively. Depending on the trust value, which is determined by the roadside unit (RSU), a malicious user (MU) is eliminated from the contention process. The simulation demonstrates that by identifying and removing malicious nodes, the throughput of the proposed protocol gradually increases.
{"title":"A Trustworthy and Cooperative MAC Protocol for Cognitive Vehicular Networks","authors":"Jahnvi Tiwari, D. Dubey, A. Prakash, R. Tripathi","doi":"10.1109/UPCON56432.2022.9986422","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986422","url":null,"abstract":"A trustworthy medium access control (MAC) protocol is needed to enable recent advancements in transport systems to broadcast high-priority safety messages. Cognitive radio-based vehicle ad hoc networks (CR-VANETs) are being implemented by researchers to satisfy the rapidly rising spectrum demand with ease. However, fraudulent users may insert false emergency alarms into CR-VANETs, blocking nodes from getting the most recent traffic conditions. To ensure the dependability and credibility of the safety message conveyed over the networks, evaluating the trustworthiness of nodes has become a vital responsibility in CR-VANETs. In this study, to determine the level of trust for each node, several performance metrics of the proposed MAC protocol are evaluated cooperatively. Depending on the trust value, which is determined by the roadside unit (RSU), a malicious user (MU) is eliminated from the contention process. The simulation demonstrates that by identifying and removing malicious nodes, the throughput of the proposed protocol gradually increases.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129669707","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986493
Harshit Rathore, Hemant Kumar Meena, P. Jain
As more source of renewable energy are incorporated into the traditional system to fulfil global energy demand and the decarbonization goal, there is growing worry over power excellence. Due to the variable output of renewable energy sources (RES) as well as the interfacing converters, the power quality (PQ) disturbance is observed to be more prevalent as the addition of renewable energy into the network increases. In orderto deliver clean power to end users, it is necessary to notice and reduce power quality disturbance (PQD). In this article, various methods for identifying and categorizing PQ instabilities caused by the penetration of RES in the system are evaluated. This review paper's primary goal is to describe various approachesfor the feature removal and categorization of PQ instabilities, as well as additional strategies for PQ disturbance reduction, such as forecasting for renewable energy sources.
{"title":"Application of Signal Processing and Machine learning on Power Quality Disturbance with RE Penetration: A Review","authors":"Harshit Rathore, Hemant Kumar Meena, P. Jain","doi":"10.1109/UPCON56432.2022.9986493","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986493","url":null,"abstract":"As more source of renewable energy are incorporated into the traditional system to fulfil global energy demand and the decarbonization goal, there is growing worry over power excellence. Due to the variable output of renewable energy sources (RES) as well as the interfacing converters, the power quality (PQ) disturbance is observed to be more prevalent as the addition of renewable energy into the network increases. In orderto deliver clean power to end users, it is necessary to notice and reduce power quality disturbance (PQD). In this article, various methods for identifying and categorizing PQ instabilities caused by the penetration of RES in the system are evaluated. This review paper's primary goal is to describe various approachesfor the feature removal and categorization of PQ instabilities, as well as additional strategies for PQ disturbance reduction, such as forecasting for renewable energy sources.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122254427","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986378
Ashish Singh Patel, Vivek Tiwari, Muneendra Ojha, O. P. Vyas
Analysis of video data generated by surveillance systems requires an efficient way to represent, store, and retrieve for performing reasoning to identify unusual events. The recognition of unusual events is often difficult with existing machine-learning/Deep Learning approaches as they suffer due to lack of training examples. Abandoned luggage identification is one of the critical problem which poses security threat in public places. It may occur in several forms with various scenarios. However training for each possible case is extremely challenging due to limited amount of training examples. In this work, an ontology-based reasoning and analysis for identifying the complex event of left luggage in public places. A novel ontology is presented that represents the public place surveillance video data to represent various scenarios. Moreover, a reasoning is performed using Semantic Web Rule language (SWRL) for inferring relations. The proposed ontology-based approach extracts and represents salient information present in video data as a knowledge graph. The unusual events (Abandoned Luggage) is identified form the knowledge using SPARQL queries. Furthermore, the SPARQL queries can also be formulated to retrieve salient information and for question answering. The proposed framework is validated by identifying the complex events left luggage in PETS 2006, PETS 2007, AVSS 2007 and ABODA Dataset.
{"title":"Abandoned Luggage Detection: An Ontology-based approach for unusual activity recognition","authors":"Ashish Singh Patel, Vivek Tiwari, Muneendra Ojha, O. P. Vyas","doi":"10.1109/UPCON56432.2022.9986378","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986378","url":null,"abstract":"Analysis of video data generated by surveillance systems requires an efficient way to represent, store, and retrieve for performing reasoning to identify unusual events. The recognition of unusual events is often difficult with existing machine-learning/Deep Learning approaches as they suffer due to lack of training examples. Abandoned luggage identification is one of the critical problem which poses security threat in public places. It may occur in several forms with various scenarios. However training for each possible case is extremely challenging due to limited amount of training examples. In this work, an ontology-based reasoning and analysis for identifying the complex event of left luggage in public places. A novel ontology is presented that represents the public place surveillance video data to represent various scenarios. Moreover, a reasoning is performed using Semantic Web Rule language (SWRL) for inferring relations. The proposed ontology-based approach extracts and represents salient information present in video data as a knowledge graph. The unusual events (Abandoned Luggage) is identified form the knowledge using SPARQL queries. Furthermore, the SPARQL queries can also be formulated to retrieve salient information and for question answering. The proposed framework is validated by identifying the complex events left luggage in PETS 2006, PETS 2007, AVSS 2007 and ABODA Dataset.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122296707","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986475
Nandita Das, Bhavya Dhyani, Anjali Singh, Himani Dua Sehgal, Neha Garg, S. Kabra, Naina Gautam
A cost-effective pH sensing system using Ag/Agel glass electrode as a pH-sensitive material for a N-channel Metal Oxide Semiconductor Field Effect Transistor (MOSFETIRFZ44N) has been fabricated. The change in pH is evaluated by finding the change in transfer (IDS Vs VGS) and output characteristics (IDS Vs VDS) of a MOSFET. The gate terminal of MOSFET is connected to a glass electrode providing an electrochemical measurement cell in combination with a reference electrode. This paper presents experimental resultson pH-variation of the solution in contact with the glass electrodethat can be sensed by the MOSFE T. The change is studied through the variation in drain current and threshold voltage. At pH 3, threshold voltage is 2.304 V and at pH 12, threshold voltage is 2.789 V which suggests that as pH increases, threshold voltage also increases. Due to their low cost and ease in processing, such devices are possible candidates to be used as versatile, low-cost pH sensors. Research is being carried out with the aim of developing a pH sensor with high sensitivity and low cost.
利用Ag/Agel玻璃电极作为n沟道金属氧化物半导体场效应晶体管(MOSFETIRFZ44N)的pH敏感材料，制备了一种具有成本效益的pH传感系统。通过寻找MOSFET的转移(IDS Vs VGS)和输出特性(IDS Vs VDS)的变化来评估pH的变化。MOSFET的栅极端连接到玻璃电极，该玻璃电极与参比电极结合，提供电化学测量单元。本文介绍了MOSFE t能检测到与玻璃电极接触的溶液ph值变化的实验结果，并通过漏极电流和阈值电压的变化研究了溶液ph值的变化。pH值为3时，阈值电压为2.304 V, pH值为12时，阈值电压为2.789 V，说明随着pH值的增大，阈值电压也随之增大。由于其低成本和易于加工，这种设备可能被用作多功能，低成本的pH传感器。目前正在进行研究，目的是开发一种高灵敏度和低成本的pH传感器。
{"title":"Low-cost MOSFET based pH-sensor Using Ag/AgCl Glass electrodes","authors":"Nandita Das, Bhavya Dhyani, Anjali Singh, Himani Dua Sehgal, Neha Garg, S. Kabra, Naina Gautam","doi":"10.1109/UPCON56432.2022.9986475","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986475","url":null,"abstract":"A cost-effective pH sensing system using Ag/Agel glass electrode as a pH-sensitive material for a N-channel Metal Oxide Semiconductor Field Effect Transistor (MOSFETIRFZ44N) has been fabricated. The change in pH is evaluated by finding the change in transfer (IDS Vs VGS) and output characteristics (IDS Vs VDS) of a MOSFET. The gate terminal of MOSFET is connected to a glass electrode providing an electrochemical measurement cell in combination with a reference electrode. This paper presents experimental resultson pH-variation of the solution in contact with the glass electrodethat can be sensed by the MOSFE T. The change is studied through the variation in drain current and threshold voltage. At pH 3, threshold voltage is 2.304 V and at pH 12, threshold voltage is 2.789 V which suggests that as pH increases, threshold voltage also increases. Due to their low cost and ease in processing, such devices are possible candidates to be used as versatile, low-cost pH sensors. Research is being carried out with the aim of developing a pH sensor with high sensitivity and low cost.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127319089","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986373
R. S. Kumar, Kshitij Maurya, Muskan Rastogi, Muskan Gupta
This paper presents an overview of upper limb exoskeleton system research and development. These systems can be divided into four categories: assistive devices that replace impaired human function, rehabilitation devices that restore functionality lost due to injury or medical conditions, augmentation exoskeletons that improve users' abilities beyond their normal levels, and other devices like teleoperation and entertainment. The last two categories are typically used in industrial settings. The goal is to create an exoskeleton that is low-cost, streamlined, and wireless. Our solution will be one-of-a-kind since it will be a low-cost, ergonomic device controlled by sensors and buttons.
{"title":"Sensor and Button-Controlled Exoskeleton Arm","authors":"R. S. Kumar, Kshitij Maurya, Muskan Rastogi, Muskan Gupta","doi":"10.1109/UPCON56432.2022.9986373","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986373","url":null,"abstract":"This paper presents an overview of upper limb exoskeleton system research and development. These systems can be divided into four categories: assistive devices that replace impaired human function, rehabilitation devices that restore functionality lost due to injury or medical conditions, augmentation exoskeletons that improve users' abilities beyond their normal levels, and other devices like teleoperation and entertainment. The last two categories are typically used in industrial settings. The goal is to create an exoskeleton that is low-cost, streamlined, and wireless. Our solution will be one-of-a-kind since it will be a low-cost, ergonomic device controlled by sensors and buttons.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133684813","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986461
S. N, C. B. Akki
The usage of internet among user made online social network (OSN) like twitter, facebook, weibo to become popular. Users share their thoughts and perspective on aspects on OSN. In OSN the biggest security threat is the malicious Uniform Resource Locator (URLs) to prevent from privacy. Researchers have found few methods to detect the malicious URL by hard coded eminent features, block listing the URLs. These methods have limitations such as not all malicious URLs are blacklisted and many important features are not considered in hard coding method. Evolution of deep learning techniques have made to extract and analyses the features by own and solutions can be derived easily. In this paper, a novel feature engineering approach and polished up Bidirectional Encoder Representations from Transformers (BERT) is proposed to comprehensively detect the malicious Uniform Resource Locator (URLs). The results show that proposed model gives 98.79% of overall accuracy is achieved which out performs from the state of art models.
{"title":"P-BERT: Polished Up Bidirectional Encoder Representations from Transformers for Predicting Malicious URL to Preserve Privacy","authors":"S. N, C. B. Akki","doi":"10.1109/UPCON56432.2022.9986461","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986461","url":null,"abstract":"The usage of internet among user made online social network (OSN) like twitter, facebook, weibo to become popular. Users share their thoughts and perspective on aspects on OSN. In OSN the biggest security threat is the malicious Uniform Resource Locator (URLs) to prevent from privacy. Researchers have found few methods to detect the malicious URL by hard coded eminent features, block listing the URLs. These methods have limitations such as not all malicious URLs are blacklisted and many important features are not considered in hard coding method. Evolution of deep learning techniques have made to extract and analyses the features by own and solutions can be derived easily. In this paper, a novel feature engineering approach and polished up Bidirectional Encoder Representations from Transformers (BERT) is proposed to comprehensively detect the malicious Uniform Resource Locator (URLs). The results show that proposed model gives 98.79% of overall accuracy is achieved which out performs from the state of art models.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134311983","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 : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986421
Nisheeth Saxena, Akriti Nigam
Quantum Machine Learning (QML) is a newly emerging research area at the intersection of classical machine learning (CML) and quantum computing (QC). Data is becoming voluminous rapidly, so it is challenging for classical computers to train Machine Learning (ML) models over massive datasets. The hope is that quantum physics' intrinsic features, such as entanglement, superposition, and interference, could be exploited as resources for training ML models on big datasets that would otherwise be relatively impossible for classical computers. It is theoretically proven that quantum computers have an exponential-time advantage over their classical counterparts in solving several problems, e.g., complex large dimensional matrix multiplication, factorization problem, unstructured database search, etc. QML models attempt to find a quantum advantage over their classical counterparts. Variational Quantum Classifiers (VQC) are hybrid quantum neural networks to perform the task of classification using QML models. VQC models in the present NISQ (Noisy Intermediate Scale Quantum — 50 to 100 qubits) era can produce comparable and even better results than Classical models. In this article, we examined the performance of a VQC while performing a simple binary classification task. In this article, we use a VQC to evaluate this method's performance empirically. We constructed a VQC to predict the label of fresh input for the typical Iris dataset comprising pairings of target outputs and training inputs. Our quantum classifier can reasonably predict species labels using only four qubits. These levels are fairly good compared to the accuracy levels attained by classical classifiers.
{"title":"Performance Evaluation of a Variational Quantum Classifier","authors":"Nisheeth Saxena, Akriti Nigam","doi":"10.1109/UPCON56432.2022.9986421","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986421","url":null,"abstract":"Quantum Machine Learning (QML) is a newly emerging research area at the intersection of classical machine learning (CML) and quantum computing (QC). Data is becoming voluminous rapidly, so it is challenging for classical computers to train Machine Learning (ML) models over massive datasets. The hope is that quantum physics' intrinsic features, such as entanglement, superposition, and interference, could be exploited as resources for training ML models on big datasets that would otherwise be relatively impossible for classical computers. It is theoretically proven that quantum computers have an exponential-time advantage over their classical counterparts in solving several problems, e.g., complex large dimensional matrix multiplication, factorization problem, unstructured database search, etc. QML models attempt to find a quantum advantage over their classical counterparts. Variational Quantum Classifiers (VQC) are hybrid quantum neural networks to perform the task of classification using QML models. VQC models in the present NISQ (Noisy Intermediate Scale Quantum — 50 to 100 qubits) era can produce comparable and even better results than Classical models. In this article, we examined the performance of a VQC while performing a simple binary classification task. In this article, we use a VQC to evaluate this method's performance empirically. We constructed a VQC to predict the label of fresh input for the typical Iris dataset comprising pairings of target outputs and training inputs. Our quantum classifier can reasonably predict species labels using only four qubits. These levels are fairly good compared to the accuracy levels attained by classical classifiers.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134333881","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：