Pub Date : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315844
Suman De
Security for every organization in the digital space is of primary focus and to better highlight and define the strategies to keep the systems safe and secure is of prime importance. While unauthorized access and unethical actions by intruders remain a cause of concern, ensuring the right measures through proper Threat Modelling techniques is necessary to create a barrier against them. The intention of getting access to a system or website or server can be born out of multiple threat groups and can be classified into common security threats. This paper looks at a persona-based approach to identify user groups that can be a threat to a system and how we can use the concepts of Design Thinking to model the system and protect it from possible security breaches. Considering the agile methodologies of software development, the paper talks about focusing on a perspective that discusses a design methodology by keeping the individuals and interactions for working models at the top of threat modelling measures.
{"title":"A Novel Perspective to Threat Modelling using Design Thinking and Agile Principles","authors":"Suman De","doi":"10.1109/PDGC50313.2020.9315844","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315844","url":null,"abstract":"Security for every organization in the digital space is of primary focus and to better highlight and define the strategies to keep the systems safe and secure is of prime importance. While unauthorized access and unethical actions by intruders remain a cause of concern, ensuring the right measures through proper Threat Modelling techniques is necessary to create a barrier against them. The intention of getting access to a system or website or server can be born out of multiple threat groups and can be classified into common security threats. This paper looks at a persona-based approach to identify user groups that can be a threat to a system and how we can use the concepts of Design Thinking to model the system and protect it from possible security breaches. Considering the agile methodologies of software development, the paper talks about focusing on a perspective that discusses a design methodology by keeping the individuals and interactions for working models at the top of threat modelling measures.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124819347","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315804
A. Devi, Geetanjali Rathee, H. Saini
The internet of vehicles (IoV) a distributed network to allow the vehicles to communicate and data exchanged in real-time with other vehicles., humans., roadside infrastructures., etc. To communicate vehicles within non-trusted environments is difficult to evaluate the trustworthiness. By integrated blockchain with IoV., we improved the data sharing among vehicles., driving safety., security., and traceability. In this paper., miners are selected through the integration of multi attribute and two-stage auction to increase the trusted security between nodes. Further., to avoid the internal collision between miners., the blocks are selected through the Discrete Particle Swarm Optimization algorithm for miner-centric block validation selection. In every timeslot., the blocks are verified by miners and their positions updated dynamically. The proposed incentive mechanism performance is shown in the experiment results to improve the trustworthiness and security for data sharing in Blockchain-based IoV.
{"title":"Using Optimization and Auction Approach: Security provided to Vehicle network through Blockchain Technology","authors":"A. Devi, Geetanjali Rathee, H. Saini","doi":"10.1109/PDGC50313.2020.9315804","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315804","url":null,"abstract":"The internet of vehicles (IoV) a distributed network to allow the vehicles to communicate and data exchanged in real-time with other vehicles., humans., roadside infrastructures., etc. To communicate vehicles within non-trusted environments is difficult to evaluate the trustworthiness. By integrated blockchain with IoV., we improved the data sharing among vehicles., driving safety., security., and traceability. In this paper., miners are selected through the integration of multi attribute and two-stage auction to increase the trusted security between nodes. Further., to avoid the internal collision between miners., the blocks are selected through the Discrete Particle Swarm Optimization algorithm for miner-centric block validation selection. In every timeslot., the blocks are verified by miners and their positions updated dynamically. The proposed incentive mechanism performance is shown in the experiment results to improve the trustworthiness and security for data sharing in Blockchain-based IoV.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878566","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315802
R. Muzammil, M. Wajid
Rayleigh flat-fading path in wireless-channels leads to errors, and this makes the detection task very difficult. In such cases, forward error correction (FEC) is used to provide good performance. This paper gives the testing of a QPSK-transceiver using threshold detection and FEC in the form of (8, 4) block coding-decoding. The whole system was tested by transmitting a known digital image over a flat-fading channel, and detection was performed using the threshold detection process. Very recently, the advent of programmable graphics processing units (GPUs) as excessive parallel programming system has enabled high-performance computation. NVIDIA GTX 1050 Ti GPU has been used for implementing and testing transceiver in this work. The image is transmitted over a flat-fading channel along with FEC, and the results are obtained in the form of Bit Error Rate (BER) versus signal-to-noise ratio (SNR) curve. All the baseband processing is performed in the NVIDIA GPU, and some of the computation is performed in the CPU. The purpose of this paper is to show that a lot of processing time can be saved using a highly parallel computing machine, the GPU, as compared to a sequentially programming device, the CPU. The speedup is indicated in the results.
无线信道中的瑞利平衰落路径会导致误差，这给检测任务带来了很大的困难。在这种情况下，使用前向纠错(FEC)来提供良好的性能。本文以(8,4)分组编解码的形式，利用阈值检测和FEC对qpsk收发器进行了测试。通过在平坦衰落信道上传输已知数字图像对整个系统进行了测试，并采用阈值检测过程进行了检测。最近，可编程图形处理单元(gpu)作为过度并行编程系统的出现使高性能计算成为可能。本文采用NVIDIA GTX 1050 Ti GPU实现和测试收发器。图像沿FEC在平坦衰落信道上传输，结果以误码率(BER)与信噪比(SNR)曲线的形式得到。所有的基带处理都在NVIDIA GPU中执行，部分计算在CPU中执行。本文的目的是表明，与顺序编程设备CPU相比，使用高度并行计算机器GPU可以节省大量的处理时间。在结果中显示了加速。
{"title":"GPU-accelerated QPSK Transceiver with FEC over a Flat-fading Channel","authors":"R. Muzammil, M. Wajid","doi":"10.1109/PDGC50313.2020.9315802","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315802","url":null,"abstract":"Rayleigh flat-fading path in wireless-channels leads to errors, and this makes the detection task very difficult. In such cases, forward error correction (FEC) is used to provide good performance. This paper gives the testing of a QPSK-transceiver using threshold detection and FEC in the form of (8, 4) block coding-decoding. The whole system was tested by transmitting a known digital image over a flat-fading channel, and detection was performed using the threshold detection process. Very recently, the advent of programmable graphics processing units (GPUs) as excessive parallel programming system has enabled high-performance computation. NVIDIA GTX 1050 Ti GPU has been used for implementing and testing transceiver in this work. The image is transmitted over a flat-fading channel along with FEC, and the results are obtained in the form of Bit Error Rate (BER) versus signal-to-noise ratio (SNR) curve. All the baseband processing is performed in the NVIDIA GPU, and some of the computation is performed in the CPU. The purpose of this paper is to show that a lot of processing time can be saved using a highly parallel computing machine, the GPU, as compared to a sequentially programming device, the CPU. The speedup is indicated in the results.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129692654","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315808
Harmaninder Jit Singh Sidhu, M. Khanna
with the advent of Cloud Computing a new era of computing has come into existence. No doubt, there are numerous advantages associated with the Cloud Computing but, there is other side of the picture too. The challenges associated with it need a more promising reply as far as the security of data that is stored, in process and in transit is concerned. This paper put forth a cloud computing model that tries to answer the data security queries; we are talking about, in terms of the four cryptographic techniques namely Homomorphic Encryption (HE), Verifiable Computation (VC), Secure Multi-Party Computation (SMPC), Functional Encryption (FE). This paper takes into account the various cryptographic techniques to undertake cloud computing security issues. It also surveys these important (existing) cryptographic tools/techniques through a proposed Cloud computation model that can be used for Big Data applications. Further, these cryptographic tools are also taken into account in terms of CIA triad. Then, these tools/techniques are analyzed by comparing them on the basis of certain parameters of concern.
{"title":"Cloud's Transformative Involvement in Managing BIG-DATA ANALYTICS For Securing Data in Transit, Storage And Use: A Study","authors":"Harmaninder Jit Singh Sidhu, M. Khanna","doi":"10.1109/PDGC50313.2020.9315808","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315808","url":null,"abstract":"with the advent of Cloud Computing a new era of computing has come into existence. No doubt, there are numerous advantages associated with the Cloud Computing but, there is other side of the picture too. The challenges associated with it need a more promising reply as far as the security of data that is stored, in process and in transit is concerned. This paper put forth a cloud computing model that tries to answer the data security queries; we are talking about, in terms of the four cryptographic techniques namely Homomorphic Encryption (HE), Verifiable Computation (VC), Secure Multi-Party Computation (SMPC), Functional Encryption (FE). This paper takes into account the various cryptographic techniques to undertake cloud computing security issues. It also surveys these important (existing) cryptographic tools/techniques through a proposed Cloud computation model that can be used for Big Data applications. Further, these cryptographic tools are also taken into account in terms of CIA triad. Then, these tools/techniques are analyzed by comparing them on the basis of certain parameters of concern.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117026910","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315841
Diksha Thakur, V. Baghel, Salman Raiu Talluri
In practical array signal processing environment steering vector uncertainties are present which degrade the performance of adaptive beamforming significantly. The steering vector uncertainty occurs primarily due to mismatch in the direction of signal of interest (SOI). This article presents an efficient approach to enhance the performance of adaptive beamforming in the presence of uncertainty in the steering vector of SOI. The proposed method is based on diagonal loading and utilizes the ellipsoidal constraints to reformulate the optimization problem. The output signal to interference noise ratio (SINR) obtained from the proposed beamforming method shows its superiority over the existing robust beamforming methods. Moreover, the proposed beamforming method accurately estimates the power of SOI.
{"title":"Robust beamforming against mismatched signal steering vector using ellipsoidal constraints","authors":"Diksha Thakur, V. Baghel, Salman Raiu Talluri","doi":"10.1109/PDGC50313.2020.9315841","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315841","url":null,"abstract":"In practical array signal processing environment steering vector uncertainties are present which degrade the performance of adaptive beamforming significantly. The steering vector uncertainty occurs primarily due to mismatch in the direction of signal of interest (SOI). This article presents an efficient approach to enhance the performance of adaptive beamforming in the presence of uncertainty in the steering vector of SOI. The proposed method is based on diagonal loading and utilizes the ellipsoidal constraints to reformulate the optimization problem. The output signal to interference noise ratio (SINR) obtained from the proposed beamforming method shows its superiority over the existing robust beamforming methods. Moreover, the proposed beamforming method accurately estimates the power of SOI.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121414261","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315739
Nidhi Garg, Amod Kumar, H. Ryait
Ayurveda engineering, one of the areas which is getting attention nowadays. In Ayurveda, pulse diagnosis helps to get into the root cause of illness or disease of human body by observing fingertip palpations over the radial artery of a wrist. The Wrist Pulse Signals (WPS) dictate the physiological status of entire human body and a close association is considered between heart and mind. As the association gets weak, it introduces imbalance (vikruti) within body and results in various types of diseases. Emotion plays an important role to study the state of mind of a person. The origin of many diseases is linked with human emotions. Machines with the capability of emotion recognition can look inside the physiological changes in human body. Emotion detection using physiological and peripheral signals like electroencephalogram, electrocardiogram, skin conductance, photoplethysmography, galvanic skin response has been in continuous use. The wrist pulse signals, non-invasive approach of health diagnosis, relies on the understanding and analysis of the characteristics of pulse pressure signals. This paper mainly focuses on the framework to map human emotion with diseases based on the (Vata, Pitta and Kapha) natural imbalance using WPS analysis with modernization.
{"title":"A prospective study to assess the association between emotion and disease: Wrist Pulse Signals","authors":"Nidhi Garg, Amod Kumar, H. Ryait","doi":"10.1109/PDGC50313.2020.9315739","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315739","url":null,"abstract":"Ayurveda engineering, one of the areas which is getting attention nowadays. In Ayurveda, pulse diagnosis helps to get into the root cause of illness or disease of human body by observing fingertip palpations over the radial artery of a wrist. The Wrist Pulse Signals (WPS) dictate the physiological status of entire human body and a close association is considered between heart and mind. As the association gets weak, it introduces imbalance (vikruti) within body and results in various types of diseases. Emotion plays an important role to study the state of mind of a person. The origin of many diseases is linked with human emotions. Machines with the capability of emotion recognition can look inside the physiological changes in human body. Emotion detection using physiological and peripheral signals like electroencephalogram, electrocardiogram, skin conductance, photoplethysmography, galvanic skin response has been in continuous use. The wrist pulse signals, non-invasive approach of health diagnosis, relies on the understanding and analysis of the characteristics of pulse pressure signals. This paper mainly focuses on the framework to map human emotion with diseases based on the (Vata, Pitta and Kapha) natural imbalance using WPS analysis with modernization.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115690869","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315740
Aman Sharma, Rishi Rana
“Human is a social animal” this line itself explains the importance of society in one's life. Society brings stability, a medium to express thoughts. Society leads to social interaction which eventually brings thoughtful minds. Humans have the intrinsic nature of analyzing and opinionating things and persons. This keen nature of humanity has emerged as a new field of analysis that is social data analysis. The Internet has merged the world today and as a result, human social circles have expanded. There are various peculiar social networking sites available on the internet, some of them are on Facebook, Twitter, LinkedIn and many more. Each maintains accounts of billions of active users and the huge amount of data is being produced as a result of interactions over such sites. Hence analyzing this data is a tedious task. But analysis of such online social communities and predicting their behavior is of great importance for businesses and academics. In this paper, we are concentrating more on twitter. This paper aims to develop a research-based application using twitter and R-tool. We have visualized and analyzed the data using R-tool.
{"title":"Analysis and Visualization of Twitter Data using R","authors":"Aman Sharma, Rishi Rana","doi":"10.1109/PDGC50313.2020.9315740","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315740","url":null,"abstract":"“Human is a social animal” this line itself explains the importance of society in one's life. Society brings stability, a medium to express thoughts. Society leads to social interaction which eventually brings thoughtful minds. Humans have the intrinsic nature of analyzing and opinionating things and persons. This keen nature of humanity has emerged as a new field of analysis that is social data analysis. The Internet has merged the world today and as a result, human social circles have expanded. There are various peculiar social networking sites available on the internet, some of them are on Facebook, Twitter, LinkedIn and many more. Each maintains accounts of billions of active users and the huge amount of data is being produced as a result of interactions over such sites. Hence analyzing this data is a tedious task. But analysis of such online social communities and predicting their behavior is of great importance for businesses and academics. In this paper, we are concentrating more on twitter. This paper aims to develop a research-based application using twitter and R-tool. We have visualized and analyzed the data using R-tool.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131463593","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315815
K. Bhangu, Jasminder Kaur Sandhu, Luxmi Sapra
The objective of this study is to improve prediction outcome of breast cancer patients employing Machine Learning techniques so to be able to accurately classify between Benign or Malignant Tumor. The dataset taken for this experiment is an inclusion of extracted features of breast cancer patient cells and normal person cells that are extracted from digitized images of FNA (Fine-needle aspiration) tests performed on breast lumps. The dataset was exposed to Machine Learning models namely Support Vector Machine, Decision Tree, Logistic Regression, K- Nearest Neighbor, Naive Bayes, Random Forest and Neural Network based algorithm- Multilayer Perceptron to analyze the prediction results. The obtained results were also compared with ensemble- based learning techniques such as Gradient Boost, XGBoost and Adaboost classifiers to find the best performing algorithm. Further, this study aims to showcase to the clinicians the methodology of interpretation via Machine Learning and that it's routinely usage would certainly be beneficial to predict outcomes. The long-term goal of this type of study expects a slow and gradual realization of the importance of accurate tumor detection via Machine Learning models, as early detection of breast cancer can greatly improve prognosis and survival chances by promoting clinical treatment to patients as soon as possible.
{"title":"Improving diagnostic accuracy for breast cancer using prediction-based approaches","authors":"K. Bhangu, Jasminder Kaur Sandhu, Luxmi Sapra","doi":"10.1109/PDGC50313.2020.9315815","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315815","url":null,"abstract":"The objective of this study is to improve prediction outcome of breast cancer patients employing Machine Learning techniques so to be able to accurately classify between Benign or Malignant Tumor. The dataset taken for this experiment is an inclusion of extracted features of breast cancer patient cells and normal person cells that are extracted from digitized images of FNA (Fine-needle aspiration) tests performed on breast lumps. The dataset was exposed to Machine Learning models namely Support Vector Machine, Decision Tree, Logistic Regression, K- Nearest Neighbor, Naive Bayes, Random Forest and Neural Network based algorithm- Multilayer Perceptron to analyze the prediction results. The obtained results were also compared with ensemble- based learning techniques such as Gradient Boost, XGBoost and Adaboost classifiers to find the best performing algorithm. Further, this study aims to showcase to the clinicians the methodology of interpretation via Machine Learning and that it's routinely usage would certainly be beneficial to predict outcomes. The long-term goal of this type of study expects a slow and gradual realization of the importance of accurate tumor detection via Machine Learning models, as early detection of breast cancer can greatly improve prognosis and survival chances by promoting clinical treatment to patients as soon as possible.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130929818","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315812
Vikas Srivastavaven, S. Yadav
In this paper, we proposed rotation invariant co-occurrence among adjacent local binary pattern (RIC-LBP) based feature extraction technique for forgery detection. We use Standard Deviation filter (STD) to highlights the image pixel variation, RIC-LBP operator for feature extraction, and Logistic Regression Classifiers (LRC) for forgery detection to know the internal statistics of the image. LRC is a machine learning technique so directly used as a classifier on the entire data set. So it differs from SVM classifier. In this proposed work, we used two datasets, Columbia and DSO-1, to evaluate our proposed work. It gives better results compare to various state of the art.
{"title":"Digital Image splicing Detection Using RIC-LBP Feature Extraction Technique","authors":"Vikas Srivastavaven, S. Yadav","doi":"10.1109/PDGC50313.2020.9315812","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315812","url":null,"abstract":"In this paper, we proposed rotation invariant co-occurrence among adjacent local binary pattern (RIC-LBP) based feature extraction technique for forgery detection. We use Standard Deviation filter (STD) to highlights the image pixel variation, RIC-LBP operator for feature extraction, and Logistic Regression Classifiers (LRC) for forgery detection to know the internal statistics of the image. LRC is a machine learning technique so directly used as a classifier on the entire data set. So it differs from SVM classifier. In this proposed work, we used two datasets, Columbia and DSO-1, to evaluate our proposed work. It gives better results compare to various state of the art.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130866171","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315768
Bhawna Jyoti, A. Sharma
In this transformational era, advancements in computational powers of machine learning applications, data classification task has put its roots from various engineering domains to an explosion of new strategies of data handling in the real-world applications scenario. Therefore, this study describes the implementation of eight classifiers (Logistic Regression, Support Vector Machines, Perceptron, Decision Tree, Random Forest, k-Nearest Neighbor, Gaussian Naïve Bayes and Linear Discriminant Analysis) on the iris dataset. Performance metrics like classification report and accuracy measures are evaluated on the iris dataset and it is observed experimentally that SVM classifier has given good accuracy measure of 99.1% over other classifiers.
{"title":"An Empirical Study of Classification Techniques by using Machine Learning Classifiers","authors":"Bhawna Jyoti, A. Sharma","doi":"10.1109/PDGC50313.2020.9315768","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315768","url":null,"abstract":"In this transformational era, advancements in computational powers of machine learning applications, data classification task has put its roots from various engineering domains to an explosion of new strategies of data handling in the real-world applications scenario. Therefore, this study describes the implementation of eight classifiers (Logistic Regression, Support Vector Machines, Perceptron, Decision Tree, Random Forest, k-Nearest Neighbor, Gaussian Naïve Bayes and Linear Discriminant Analysis) on the iris dataset. Performance metrics like classification report and accuracy measures are evaluated on the iris dataset and it is observed experimentally that SVM classifier has given good accuracy measure of 99.1% over other classifiers.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121496148","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：