Pub Date : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688098
Madam Chakradar, Alok Aggarwal
T2DM is a large challenge because it's predicted to affect 693 million people by 2045. There is currently no simple or non-invasive method to measure and quantify insulin resistance. Following the release of non-invasive devices that track glucose levels, one might be able to identify insulin resistance without having to use invasive medical tests. In this work, insulin resistance is recognized based on non-invasive techniques. Eighteen parameters are used to identify a person with a high likelihood of insulin resistance: consisting of age, gender, waist size, height, etc., and an aggregate of those parameters. Each output of a function choices technique is modeled using a range of algorithms, including logistic regression, CARTs, SVM, LDA, KNN, etc on CALERIE study dataset and the findings are verified over stratified cross-validation. And in comparison, to 66% Bernardini et al & Stawiski et al, 61% Zheng et al, and 83% Farran et al, the accuracy of different variations for the identification of insulin resistance. Another advantage of the proposed approach is that an individual can also predict insulin resistance daily, which in turn will allow physicians to monitor diabetes risk more accurately. While the identical isn't always almost feasible with medical procedures.
2型糖尿病是一个巨大的挑战，因为预计到2045年将有6.93亿人受到影响。目前还没有简单或无创的方法来测量和量化胰岛素抵抗。随着追踪血糖水平的非侵入性设备的发布，人们可能能够在不使用侵入性医学测试的情况下识别胰岛素抵抗。在这项工作中，胰岛素抵抗是基于非侵入性技术识别的。18个参数用于识别胰岛素抵抗可能性高的人:包括年龄、性别、腰围大小、身高等，以及这些参数的总和。函数选择技术的每个输出都使用一系列算法建模，包括CALERIE研究数据集上的逻辑回归，cart, SVM, LDA, KNN等，并通过分层交叉验证验证结果。相比之下，66% Bernardini et al & Stawiski et al, 61% Zheng et al, 83% Farran et al，不同变异对胰岛素抵抗识别的准确性。该方法的另一个优点是，个人还可以每天预测胰岛素抵抗，从而使医生能够更准确地监测糖尿病风险。然而，在医疗过程中，这并不总是可行的。
{"title":"A Machine Learning Model to Identify Insulin Resistance in Humans","authors":"Madam Chakradar, Alok Aggarwal","doi":"10.1109/CENTCON52345.2021.9688098","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688098","url":null,"abstract":"T2DM is a large challenge because it's predicted to affect 693 million people by 2045. There is currently no simple or non-invasive method to measure and quantify insulin resistance. Following the release of non-invasive devices that track glucose levels, one might be able to identify insulin resistance without having to use invasive medical tests. In this work, insulin resistance is recognized based on non-invasive techniques. Eighteen parameters are used to identify a person with a high likelihood of insulin resistance: consisting of age, gender, waist size, height, etc., and an aggregate of those parameters. Each output of a function choices technique is modeled using a range of algorithms, including logistic regression, CARTs, SVM, LDA, KNN, etc on CALERIE study dataset and the findings are verified over stratified cross-validation. And in comparison, to 66% Bernardini et al & Stawiski et al, 61% Zheng et al, and 83% Farran et al, the accuracy of different variations for the identification of insulin resistance. Another advantage of the proposed approach is that an individual can also predict insulin resistance daily, which in turn will allow physicians to monitor diabetes risk more accurately. While the identical isn't always almost feasible with medical procedures.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129725444","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688114
P. William, Pardeep Kumar, Gurpreet Singh Chhabra, K. Vengatesan
In the 21st century, agile software development (ASD) has emerged as one of the prominent software development techniques. Every major global company has moved to ASD as a means of reducing costs. In pursuit of huge markets and cheap cost of labour, the industry has shifted to a Distributed Agile Software Development (DASD) environment. As a consequence of improper job allocation, clients may refuse to accept the project, team members may be demonized, and the project may collapse. Numerous scholars have spent the past decade researching different techniques for work allocation in Distributed Agile settings, and the results have been promising. Ontologies and Bayesian networks were among the techniques they employed. This is a list of brute force techniques that may be useful in certain situations. Additionally, these methods have not been used to distributed Agile software development job allocation. The purpose of this article is to design and implement a method for job allocation in distributed Agile software development that is based on machine learning. The findings indicate that the suggested model is more accurate in terms of task assignment.
{"title":"Task Allocation in Distributed Agile Software Development using Machine Learning Approach","authors":"P. William, Pardeep Kumar, Gurpreet Singh Chhabra, K. Vengatesan","doi":"10.1109/CENTCON52345.2021.9688114","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688114","url":null,"abstract":"In the 21st century, agile software development (ASD) has emerged as one of the prominent software development techniques. Every major global company has moved to ASD as a means of reducing costs. In pursuit of huge markets and cheap cost of labour, the industry has shifted to a Distributed Agile Software Development (DASD) environment. As a consequence of improper job allocation, clients may refuse to accept the project, team members may be demonized, and the project may collapse. Numerous scholars have spent the past decade researching different techniques for work allocation in Distributed Agile settings, and the results have been promising. Ontologies and Bayesian networks were among the techniques they employed. This is a list of brute force techniques that may be useful in certain situations. Additionally, these methods have not been used to distributed Agile software development job allocation. The purpose of this article is to design and implement a method for job allocation in distributed Agile software development that is based on machine learning. The findings indicate that the suggested model is more accurate in terms of task assignment.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128904562","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688193
S. Vadlamudi, Jenifer Sam
Large enterprises work upon countless strategies for creating value with acquisitions as they enter a transformational merger. Cloud-native applications, being loosely coupled and designed to deliver user requirements at the pace a business needs are the natural choice for enterprise acquisitions. Culture change management and process compliance are some key areas where acquisitions find it difficult to adapt to the enterprise standards. To make this journey smooth, it is important to have a guided journey methodology with simplified engagement between both parties. One of the key dimensions where such a collaboration-centric approach is required is in security. In this paper, we examine the current challenges in onboarding cloud-native acquisitions to bring their security compliance posture at par with the current enterprise standards. We explore areas such as secure software development lifecycle management, tools and processes followed and provide recommendations around improving the overall security stance of the acquired product.
{"title":"A Novel Approach to Onboarding Secure Cloud-Native Acquisitions into Enterprise Solutions","authors":"S. Vadlamudi, Jenifer Sam","doi":"10.1109/CENTCON52345.2021.9688193","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688193","url":null,"abstract":"Large enterprises work upon countless strategies for creating value with acquisitions as they enter a transformational merger. Cloud-native applications, being loosely coupled and designed to deliver user requirements at the pace a business needs are the natural choice for enterprise acquisitions. Culture change management and process compliance are some key areas where acquisitions find it difficult to adapt to the enterprise standards. To make this journey smooth, it is important to have a guided journey methodology with simplified engagement between both parties. One of the key dimensions where such a collaboration-centric approach is required is in security. In this paper, we examine the current challenges in onboarding cloud-native acquisitions to bring their security compliance posture at par with the current enterprise standards. We explore areas such as secure software development lifecycle management, tools and processes followed and provide recommendations around improving the overall security stance of the acquired product.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133925704","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688246
Burak Taşcı
The number of people dying from brain tumors is increasing day by day. Early diagnosis is very important in the treatment planning and evaluation of the treatment outcome of brain tumors. A patient with a brain tumor may be more likely to survive by applying the right treatment methods if the disease is diagnosed early. Medical imaging methods have an important role in the identification and diagnosis of brain tumors. One of the most popular medical imaging methods is Magnetic Resonance Imaging, MRI. Determining the presence of tumors and tumor characteristics from MRI is done by specialists. In today's technology, computer-assisted detection applications make great contributions to the field of medicine. Computer-Assisted Detection (CAD) software helps radiologists to detect abnormalities in medical images by using advanced pattern recognition and image processing methods. This software not only saves time for radiologists but also minimizes possible errors in the decision-making phase. In this study, deep features were extracted from a total of 942 MRIs with 599 tumor and 343 normal class labels using the AleXNet-based deep learning model, and classification was performed with the K Nearest Neighbor Classifier (KNN) algorithms. In this study, 1000 deep features were extracted from the MRI data with the trained weights of the fully connected layer named “fc8” of the AlexNet model. Then, these features were reduced by Relieff feature selection algorithm, and the performance of the proposed method was increased. A weighted KNN classifier was used in the classification phase. With the proposed method, 87% classification accuracy was achieved.
{"title":"A Classification Method for Brain MRI via AlexNet","authors":"Burak Taşcı","doi":"10.1109/CENTCON52345.2021.9688246","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688246","url":null,"abstract":"The number of people dying from brain tumors is increasing day by day. Early diagnosis is very important in the treatment planning and evaluation of the treatment outcome of brain tumors. A patient with a brain tumor may be more likely to survive by applying the right treatment methods if the disease is diagnosed early. Medical imaging methods have an important role in the identification and diagnosis of brain tumors. One of the most popular medical imaging methods is Magnetic Resonance Imaging, MRI. Determining the presence of tumors and tumor characteristics from MRI is done by specialists. In today's technology, computer-assisted detection applications make great contributions to the field of medicine. Computer-Assisted Detection (CAD) software helps radiologists to detect abnormalities in medical images by using advanced pattern recognition and image processing methods. This software not only saves time for radiologists but also minimizes possible errors in the decision-making phase. In this study, deep features were extracted from a total of 942 MRIs with 599 tumor and 343 normal class labels using the AleXNet-based deep learning model, and classification was performed with the K Nearest Neighbor Classifier (KNN) algorithms. In this study, 1000 deep features were extracted from the MRI data with the trained weights of the fully connected layer named “fc8” of the AlexNet model. Then, these features were reduced by Relieff feature selection algorithm, and the performance of the proposed method was increased. A weighted KNN classifier was used in the classification phase. With the proposed method, 87% classification accuracy was achieved.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131870962","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688324
Suraj Ajjampur, Vishnu Shridhar, K. P. Shashikala
The exponential growth of football all around the world has caused the exactness of every single innovation included in the game to be of immense value. Basic circumstances emerge when the referee can't separate a goal or no goal by fine margins because of human visual limitations. In the modern era popular football leagues have adopted the use of hawk-eye technology which is unaffordable by the local football leagues. In this project, we have designed and developed a prototype of an efficient and cost-effective goal-line technology system. The proposed framework utilizes object detection techniques i.e. HSV model and contours. We identify the color of the ball and use line-axis detection to reference the position of the ball with respect to the goal line. If the goal is scored, the updated score line is sent to the referee through an email. The result is also broadcasted to the live audience through a speaker system and LCD screen. This system helps in decision-making, in this manner making the framework quicker to help the referees in quick decision-making and keeping up the momentum of the game.
{"title":"Goal Line Technology Using Line axis detection","authors":"Suraj Ajjampur, Vishnu Shridhar, K. P. Shashikala","doi":"10.1109/CENTCON52345.2021.9688324","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688324","url":null,"abstract":"The exponential growth of football all around the world has caused the exactness of every single innovation included in the game to be of immense value. Basic circumstances emerge when the referee can't separate a goal or no goal by fine margins because of human visual limitations. In the modern era popular football leagues have adopted the use of hawk-eye technology which is unaffordable by the local football leagues. In this project, we have designed and developed a prototype of an efficient and cost-effective goal-line technology system. The proposed framework utilizes object detection techniques i.e. HSV model and contours. We identify the color of the ball and use line-axis detection to reference the position of the ball with respect to the goal line. If the goal is scored, the updated score line is sent to the referee through an email. The result is also broadcasted to the live audience through a speaker system and LCD screen. This system helps in decision-making, in this manner making the framework quicker to help the referees in quick decision-making and keeping up the momentum of the game.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133251996","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9687881
P. S, A. R., Chaithra A, S. S
Vedic Mathematics, an ancient system of Indian mathematics discovered in the early twentieth century, is based on the sixteen formulas called as sutras. These methods have the capability to speed up the processor performance. The proposed work is a design for Vedic multiplier using the Vedic sutra to speed up the operation of the processor to calculate the roots of the quadratic equation. The third sutra “Urdhva Tiragbhyam” is adopted for the solving quadratic equations. The design is implemented using Xilinx Tool Suite and the performance is analysed.
{"title":"A Newer Vedic Module to Solve Quadratic Equations","authors":"P. S, A. R., Chaithra A, S. S","doi":"10.1109/CENTCON52345.2021.9687881","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9687881","url":null,"abstract":"Vedic Mathematics, an ancient system of Indian mathematics discovered in the early twentieth century, is based on the sixteen formulas called as sutras. These methods have the capability to speed up the processor performance. The proposed work is a design for Vedic multiplier using the Vedic sutra to speed up the operation of the processor to calculate the roots of the quadratic equation. The third sutra “Urdhva Tiragbhyam” is adopted for the solving quadratic equations. The design is implemented using Xilinx Tool Suite and the performance is analysed.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123313061","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688192
B. Sowmiya, E. Poovammal
In recent years, securely sharing personal information between two parties involves high risk. Most of the medical health records and financial transactions includes huge uncertainty while storing and retrieving from cloud for query processing. Blockchain is an open platform where each transaction is tampered proof. Various methods like zero knowledge proof or hashing methods used to hide the sensitive information from the real world. When associating blockchain with cloud this uncertainty is reduced. The user information is segregated into two categories sensitive and non-sensitive using linear regression method before processing in cloud. To improve security and increase privacy from various attacks, the sensitive part of data is encrypted using ECC and non- sensitive part of data is encrypted using RSA algorithm. Using Ethereum blockchain the policy of the user is verified and query processing is done. The performance of the model is compared with the existing techniques and results are evaluated using the classification error rate and performance of security against manual attacks.
{"title":"Improving Cloud Security and Privacy Using Blockchain","authors":"B. Sowmiya, E. Poovammal","doi":"10.1109/CENTCON52345.2021.9688192","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688192","url":null,"abstract":"In recent years, securely sharing personal information between two parties involves high risk. Most of the medical health records and financial transactions includes huge uncertainty while storing and retrieving from cloud for query processing. Blockchain is an open platform where each transaction is tampered proof. Various methods like zero knowledge proof or hashing methods used to hide the sensitive information from the real world. When associating blockchain with cloud this uncertainty is reduced. The user information is segregated into two categories sensitive and non-sensitive using linear regression method before processing in cloud. To improve security and increase privacy from various attacks, the sensitive part of data is encrypted using ECC and non- sensitive part of data is encrypted using RSA algorithm. Using Ethereum blockchain the policy of the user is verified and query processing is done. The performance of the model is compared with the existing techniques and results are evaluated using the classification error rate and performance of security against manual attacks.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115820414","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9687919
K. P. B. Madavi, P. Karthick
Data security is a key concern for organizations considering a transfer of their on-premises applications to the cloud. Organizations must shift their security controls from historical perimeter and detection-based technologies to a focus on establishing enhanced protection at the application and data levels to ensure the confidentiality, integrity, and availability of these various systems and datasets. Data integrity is a critical component of cloud data security, preventing unauthorized alteration or removal and guaranteeing that data stays as it was when it was initially uploaded. This article presents a compacting with steganography technique which is used to hide data with substantial security and also perfect invisibility while utilizing a combination of DES, AES, and RC4 encryption methods. The objective of this study is to provide data security using steganography with the Least Significant Bit (LSB) Algorithm and Hybrid Encryption that encrypts user input and conceals it in an image file to provide the highest level of security for messages sent and received.
{"title":"Enhanced Cloud Security using Cryptography and Steganography Techniques","authors":"K. P. B. Madavi, P. Karthick","doi":"10.1109/CENTCON52345.2021.9687919","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9687919","url":null,"abstract":"Data security is a key concern for organizations considering a transfer of their on-premises applications to the cloud. Organizations must shift their security controls from historical perimeter and detection-based technologies to a focus on establishing enhanced protection at the application and data levels to ensure the confidentiality, integrity, and availability of these various systems and datasets. Data integrity is a critical component of cloud data security, preventing unauthorized alteration or removal and guaranteeing that data stays as it was when it was initially uploaded. This article presents a compacting with steganography technique which is used to hide data with substantial security and also perfect invisibility while utilizing a combination of DES, AES, and RC4 encryption methods. The objective of this study is to provide data security using steganography with the Least Significant Bit (LSB) Algorithm and Hybrid Encryption that encrypts user input and conceals it in an image file to provide the highest level of security for messages sent and received.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117095560","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 : 2021-11-19DOI: 10.1109/CENTCON52345.2021.9688115
Priyesh Kumar, K. Varalakshmi
Due to the obvious exponential growth in the usage of the internet by individuals of all ethnicities and educational backgrounds, dangerous internet media has become a serious concern in today's society. In the automated identification of hazardous text material, distinguishing between offensive speech and offensive language is a major problem. Most of the current approaches revolve around TF-IDF feature extraction, followed by the traditional classification techniques like Support Vector Machines (SVM), Decision Trees etc., As a result, there is a scope of improvement in the Accuracy of Emotion Detection and long training times. Most of the works considered only tweet data only. But in this work, we would like to include image characters and image components also. We propose a technique in this study for automatically classifying tweets on Twitter into two categories: Hate speech, Offensive speech and non-hate speech. A training and testing step are included in the suggested technique. Traditional Tweet preparation procedures such as removing Twitter handles, URLs, punctuation, stop words, and stemming were used. In both testing and training, we pad each tweet to its maximum length based on the vocabulary. This padding can have an impact on how the network works and can have a significant impact on performance and accuracy. The normalized characteristics are supplied into Bi-directional Long Short-Term Memory, which learns bidirectional long-term relationships between time steps in a time series or sequential twitter data. In comparison research, we compare the models utilizing each of these approaches. We used the Kaggle data set to predict Hate, offensive and Neutral Messages. After conducting many tests, we discovered that the suggested technique outperforms state-of-the-art algorithms by more than 90 percent.
{"title":"Hate Speech Detection using Text and Image Tweets Based On Bi-directional Long Short-Term Memory","authors":"Priyesh Kumar, K. Varalakshmi","doi":"10.1109/CENTCON52345.2021.9688115","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688115","url":null,"abstract":"Due to the obvious exponential growth in the usage of the internet by individuals of all ethnicities and educational backgrounds, dangerous internet media has become a serious concern in today's society. In the automated identification of hazardous text material, distinguishing between offensive speech and offensive language is a major problem. Most of the current approaches revolve around TF-IDF feature extraction, followed by the traditional classification techniques like Support Vector Machines (SVM), Decision Trees etc., As a result, there is a scope of improvement in the Accuracy of Emotion Detection and long training times. Most of the works considered only tweet data only. But in this work, we would like to include image characters and image components also. We propose a technique in this study for automatically classifying tweets on Twitter into two categories: Hate speech, Offensive speech and non-hate speech. A training and testing step are included in the suggested technique. Traditional Tweet preparation procedures such as removing Twitter handles, URLs, punctuation, stop words, and stemming were used. In both testing and training, we pad each tweet to its maximum length based on the vocabulary. This padding can have an impact on how the network works and can have a significant impact on performance and accuracy. The normalized characteristics are supplied into Bi-directional Long Short-Term Memory, which learns bidirectional long-term relationships between time steps in a time series or sequential twitter data. In comparison research, we compare the models utilizing each of these approaches. We used the Kaggle data set to predict Hate, offensive and Neutral Messages. After conducting many tests, we discovered that the suggested technique outperforms state-of-the-art algorithms by more than 90 percent.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115447373","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}
Wireless Sensor network (WSN) is widely used in many applications such as Defense, Agriculture, Road Transport and Highways, Healthcare, Shopping Malls. The usage of IoT devices has risen rapidly with the advancement of WSN techniques. WSN is the dominant techniques over low-cost, easy to use, scalability and portability. The major concern that arise with WSN are battery lifetime, energy consumption and short lifetime of sensor nodes. Hence, different routing network sensor protocols improve the ways of data aggregation and transmission to Base Station in the wireless sensor network. The Low Energy Adaptive Clustering Hierarchy (LEACH) is well used routing protocol based on hierarchical network flow. Researchers improves the traditional LEACH over years. In this work, traditional and integrated LEACH protocol are considered which integrated LEACH improves the threshold equation of sensor nodes for selecting cluster head. A* search algorithm is used with integrated LEACH protocol to form the tree of the sensor nodes that searches the shortest path for selecting the cluster head. This minimizes dead sensor nodes and improve the average energy residual of the sensor nodes. Using MATLAB application, simulation of the protocol is observed that finds 30 percent reduce the dead sensor nodes over integrated LEACH and improve average energy residual.
{"title":"Improved Energy Lifetime of Integrated LEACH Protocol for Wireless Sensor Network","authors":"Chongtham Pankaj, Gurumayum Nirmal Sharma, Khoirom Rajib Singh","doi":"10.1109/CENTCON52345.2021.9688050","DOIUrl":"https://doi.org/10.1109/CENTCON52345.2021.9688050","url":null,"abstract":"Wireless Sensor network (WSN) is widely used in many applications such as Defense, Agriculture, Road Transport and Highways, Healthcare, Shopping Malls. The usage of IoT devices has risen rapidly with the advancement of WSN techniques. WSN is the dominant techniques over low-cost, easy to use, scalability and portability. The major concern that arise with WSN are battery lifetime, energy consumption and short lifetime of sensor nodes. Hence, different routing network sensor protocols improve the ways of data aggregation and transmission to Base Station in the wireless sensor network. The Low Energy Adaptive Clustering Hierarchy (LEACH) is well used routing protocol based on hierarchical network flow. Researchers improves the traditional LEACH over years. In this work, traditional and integrated LEACH protocol are considered which integrated LEACH improves the threshold equation of sensor nodes for selecting cluster head. A* search algorithm is used with integrated LEACH protocol to form the tree of the sensor nodes that searches the shortest path for selecting the cluster head. This minimizes dead sensor nodes and improve the average energy residual of the sensor nodes. Using MATLAB application, simulation of the protocol is observed that finds 30 percent reduce the dead sensor nodes over integrated LEACH and improve average energy residual.","PeriodicalId":103865,"journal":{"name":"2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116856154","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：