Pub Date : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136048
R. Prasad, A. Krishnamachari
Unveiling lncRNA and mRNA gene differences at the sequence level is one of the important challenges in molecular and disease biology. In the context of DNA sequence, this difference in a physicochemical signature parameter is very important. In this study, we have proposed a machine learning-based computational approach for the classification of these genomic features. we have considered three important physicochemical properties,solvation energy, hydrogen bonding ensrgy and stacking energy of dinucleotide and trinucleotide of lncRNA and mRNA sequence as well as dinucleotide and trinucleotide composition in their sequences.We have considered lncRNA and mRNA sequences from seven model organisms namely Arabidopsis thliana, C.elegans, Chicken, Chimpanzee, Cow, Platypus, and Zebrafish.
{"title":"Classification of lncRNA and mRNA of Eukaryotic model organism using physicochemical properties and composition of dineuclotides and trineuclotides","authors":"R. Prasad, A. Krishnamachari","doi":"10.1109/PCEMS58491.2023.10136048","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136048","url":null,"abstract":"Unveiling lncRNA and mRNA gene differences at the sequence level is one of the important challenges in molecular and disease biology. In the context of DNA sequence, this difference in a physicochemical signature parameter is very important. In this study, we have proposed a machine learning-based computational approach for the classification of these genomic features. we have considered three important physicochemical properties,solvation energy, hydrogen bonding ensrgy and stacking energy of dinucleotide and trinucleotide of lncRNA and mRNA sequence as well as dinucleotide and trinucleotide composition in their sequences.We have considered lncRNA and mRNA sequences from seven model organisms namely Arabidopsis thliana, C.elegans, Chicken, Chimpanzee, Cow, Platypus, and Zebrafish.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124361863","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136057
P. Kaur, L. Ragha
Online teaching has taken up its importance post-pandemic period. Today, online teaching is considered to be one of the teaching pedagogy. This means every teacher and professor is generating online lecture videos and sharing them for students’ later use. Mostly, the environment for the video creation is in real time either in the live classroom or at home, various environmental noises interfere with the actual speech of the presenter. Therefore, there is a need for identifying the various noises that may be part of the lecture video to assess the quality of the video. Towards this, very few research works are observed. Researchers have worked on additive noises, but identifying convolutional noises is a challenge. We propose to work on the audio signal of the video lectures to identify the positions and durations of various convolutional noises and measure the amount of noise present in the audio part of the video lectures. We used various filters for identifying simultaneous talks, long silences, baby crying, kitchen sounds, and vehicle noises. The average accuracy of the proposed solution in identifying the noises and the noise positions is 97.37%. The MSE of the noise in the audio of each clip varies depending on the various noises present. This defines the quality of the audio in the lecture video.
{"title":"Audio de-noising and quality assessment for various noises in lecture videos","authors":"P. Kaur, L. Ragha","doi":"10.1109/PCEMS58491.2023.10136057","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136057","url":null,"abstract":"Online teaching has taken up its importance post-pandemic period. Today, online teaching is considered to be one of the teaching pedagogy. This means every teacher and professor is generating online lecture videos and sharing them for students’ later use. Mostly, the environment for the video creation is in real time either in the live classroom or at home, various environmental noises interfere with the actual speech of the presenter. Therefore, there is a need for identifying the various noises that may be part of the lecture video to assess the quality of the video. Towards this, very few research works are observed. Researchers have worked on additive noises, but identifying convolutional noises is a challenge. We propose to work on the audio signal of the video lectures to identify the positions and durations of various convolutional noises and measure the amount of noise present in the audio part of the video lectures. We used various filters for identifying simultaneous talks, long silences, baby crying, kitchen sounds, and vehicle noises. The average accuracy of the proposed solution in identifying the noises and the noise positions is 97.37%. The MSE of the noise in the audio of each clip varies depending on the various noises present. This defines the quality of the audio in the lecture video.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127453337","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136081
Lokesh M. Heda, Parul Sahare
The main concern of human detection using computer vision is to correctly identify people in an image and video. Human detection has been a topic of intensive study over the last decade. YOLO being single stage algorithms happen to offer better speed than two stage algorithms hence making them a better choice for real time object detection. This strategy has the benefit of offering a comprehensive study of contemporary human detection techniques as well as a manual for selecting the best ones for actual applications. In addition, Real-time human detection and occlusion issues are also looked at. In this paper, experimentation is done on real time image to verify the performance of different models of YOLO family i.e YOLOv3, YOLOv4 and YOLOv5. The experiment shows that YOLOv5 is best performer in terms of mAP with precision of 0.84 while YOLO v3 is the fastest but with a slightly less precision of 0.71. The mAP of the three algorithms were 0.86, 0.89 and 0.91 respectively.
{"title":"Performance Evaluation of YOLOv3, YOLOv4 and YOLOv5 for Real-Time Human Detection","authors":"Lokesh M. Heda, Parul Sahare","doi":"10.1109/PCEMS58491.2023.10136081","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136081","url":null,"abstract":"The main concern of human detection using computer vision is to correctly identify people in an image and video. Human detection has been a topic of intensive study over the last decade. YOLO being single stage algorithms happen to offer better speed than two stage algorithms hence making them a better choice for real time object detection. This strategy has the benefit of offering a comprehensive study of contemporary human detection techniques as well as a manual for selecting the best ones for actual applications. In addition, Real-time human detection and occlusion issues are also looked at. In this paper, experimentation is done on real time image to verify the performance of different models of YOLO family i.e YOLOv3, YOLOv4 and YOLOv5. The experiment shows that YOLOv5 is best performer in terms of mAP with precision of 0.84 while YOLO v3 is the fastest but with a slightly less precision of 0.71. The mAP of the three algorithms were 0.86, 0.89 and 0.91 respectively.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126128618","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136124
Bharti Dakhale, K. Vipinkumar, Kalla Narotham, S. Pungati, Ankit A. Bhurane, A. Kothari
This paper investigates the use of Support Vector Machines (SVMs) in sleep stage classification and their sensitivity to adversarial assaults. It illustrates the power of machine learning (ML) for precise sleep stage classification, while also emphasizing the security risks posed by adversarial attacks on ML models. Using the secML module in Python, the study investigates defense mechanisms and the robustness of SVMs against adversarial attacks. The findings highlight the significance of taking security into account when designing and deploying ML models for safety-critical applications, such as autonomous driving, cyber-security systems, healthcare, etc.
{"title":"Analysis of Adversarial Attacks on Support Vector Machine","authors":"Bharti Dakhale, K. Vipinkumar, Kalla Narotham, S. Pungati, Ankit A. Bhurane, A. Kothari","doi":"10.1109/PCEMS58491.2023.10136124","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136124","url":null,"abstract":"This paper investigates the use of Support Vector Machines (SVMs) in sleep stage classification and their sensitivity to adversarial assaults. It illustrates the power of machine learning (ML) for precise sleep stage classification, while also emphasizing the security risks posed by adversarial attacks on ML models. Using the secML module in Python, the study investigates defense mechanisms and the robustness of SVMs against adversarial attacks. The findings highlight the significance of taking security into account when designing and deploying ML models for safety-critical applications, such as autonomous driving, cyber-security systems, healthcare, etc.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542167","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136070
Mukesh Yadav, Dhirendra S. Mishra
The field of information security has covered various sectors in order to secure data which is stored online, offline, and during transmission over the network. The standard process of system log analysis is to first parse unstructured logs into structured data, and then apply data mining and machine learning techniques to analyze the data and build a threat detection model. This paper proposes a novel idea for identifying the network threat in an organisation. We take live network device logs in different log formats as input and send them for analysis. Whether a live log contains an anomaly, any vulnerability, or any insider threat will be identified. To find suspicious activity in the network, the logs will be processed, and find any activity at the same time.
{"title":"Identification of network threats using live log stream analysis","authors":"Mukesh Yadav, Dhirendra S. Mishra","doi":"10.1109/PCEMS58491.2023.10136070","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136070","url":null,"abstract":"The field of information security has covered various sectors in order to secure data which is stored online, offline, and during transmission over the network. The standard process of system log analysis is to first parse unstructured logs into structured data, and then apply data mining and machine learning techniques to analyze the data and build a threat detection model. This paper proposes a novel idea for identifying the network threat in an organisation. We take live network device logs in different log formats as input and send them for analysis. Whether a live log contains an anomaly, any vulnerability, or any insider threat will be identified. To find suspicious activity in the network, the logs will be processed, and find any activity at the same time.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122777740","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136067
Vedant Titarmare, P. Chandankhede, Minakshi M. Wanjari
Since we know that python is a developing language so it is easy to write a voice assistant script in python. Day by day life became smarter and more connected to technology. We already know some voice services like google, Siri etc. Now in our Zira voice assistance system, it can act as a daily schedule reminder, send email, calculator, play music and a search tool. Our project works on voice input and provides voice output and displays text on screen. Our main voice help agenda makes people smarter and delivers faster results with a computer. Voice Help captures voice input with our microphone and transforms our voice into understandable computer language providing the necessary solutions and answers that the user asks. By doing this project, I realized that the concept of AI in all fields reduced human effort and time saving.
{"title":"Interactive Zira Voice Assistant- A Personalized Desktop Application","authors":"Vedant Titarmare, P. Chandankhede, Minakshi M. Wanjari","doi":"10.1109/PCEMS58491.2023.10136067","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136067","url":null,"abstract":"Since we know that python is a developing language so it is easy to write a voice assistant script in python. Day by day life became smarter and more connected to technology. We already know some voice services like google, Siri etc. Now in our Zira voice assistance system, it can act as a daily schedule reminder, send email, calculator, play music and a search tool. Our project works on voice input and provides voice output and displays text on screen. Our main voice help agenda makes people smarter and delivers faster results with a computer. Voice Help captures voice input with our microphone and transforms our voice into understandable computer language providing the necessary solutions and answers that the user asks. By doing this project, I realized that the concept of AI in all fields reduced human effort and time saving.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114034163","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136035
Vasundhara, A. Mandloi, Mehul Patel
One of the most promising and soon-to-be-used network for increasing spectrum flexibility is Elastic Optical Networks (EON). Routing and wavelength allocation are two of the greatest issues in conventional WDM networks. The functionality of EON network is impacted by routing and spectrum allocation (RSA) issues. RSA has become a trickier operation as traffic from mobile backhaul and the data center keeps increasing. To keep up with the vast amount of information that is to be delivered, space division multiplexing (SDM) technologies like MultiCore Fiber (MCF) and MultiMode Fiber (MMF) are being thoroughly investigated. Using multicore fiber and multimode fiber, SDM technology can scale the network bandwidth. With the addition of spatial dimension, the spectrum status in SDM-EONs becomes more complicated and as a result problem of spectrum fragmentation will be more severe in SDM-EONs than in basic EONs. So the key motivation behind this study is the effective routing, spectrum, and core assignment for a potential SDMEON by controlling the fragmentation coefficient (FC) parameter. Due to the dynamic allocation of the requests and of routing constraints spectrum resource is not efficiently utilized and it gets fragmented in SDM-EON. Fragmentation which is determined on how many slots are lined up next to one another is then compared to the crosstalk (XT) threshold value. Due to the addition of fiber core and mode dimensions in the network, MCF and MMF are also challenging to address. Till now according to our knowledge, no work has been done on SDM using Fragmentation Coefficient (FC) based upon CASR and later on compared it with XT threshold. The proposed technique performs better in terms of bandwidth blocking probability (BBP) as compared to the benchmark technique [1].
{"title":"Fragmentation Coefficient (FC) conscious Routing, Core and Spectrum Allocation in SDM-EON based on MultiCore Fiber","authors":"Vasundhara, A. Mandloi, Mehul Patel","doi":"10.1109/PCEMS58491.2023.10136035","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136035","url":null,"abstract":"One of the most promising and soon-to-be-used network for increasing spectrum flexibility is Elastic Optical Networks (EON). Routing and wavelength allocation are two of the greatest issues in conventional WDM networks. The functionality of EON network is impacted by routing and spectrum allocation (RSA) issues. RSA has become a trickier operation as traffic from mobile backhaul and the data center keeps increasing. To keep up with the vast amount of information that is to be delivered, space division multiplexing (SDM) technologies like MultiCore Fiber (MCF) and MultiMode Fiber (MMF) are being thoroughly investigated. Using multicore fiber and multimode fiber, SDM technology can scale the network bandwidth. With the addition of spatial dimension, the spectrum status in SDM-EONs becomes more complicated and as a result problem of spectrum fragmentation will be more severe in SDM-EONs than in basic EONs. So the key motivation behind this study is the effective routing, spectrum, and core assignment for a potential SDMEON by controlling the fragmentation coefficient (FC) parameter. Due to the dynamic allocation of the requests and of routing constraints spectrum resource is not efficiently utilized and it gets fragmented in SDM-EON. Fragmentation which is determined on how many slots are lined up next to one another is then compared to the crosstalk (XT) threshold value. Due to the addition of fiber core and mode dimensions in the network, MCF and MMF are also challenging to address. Till now according to our knowledge, no work has been done on SDM using Fragmentation Coefficient (FC) based upon CASR and later on compared it with XT threshold. The proposed technique performs better in terms of bandwidth blocking probability (BBP) as compared to the benchmark technique [1].","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128533216","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136029
Ravikumar Puppala, K. Prakash, R. R. Kumar, Md. Farukh Hashmi, K. Kumar
The use of Artificial Intelligence (AI) algorithms for analyzing practical data has increased with the advent of AI models. Combining physics and engineering has garnered a lot of interest so much, so that the triboelectric Nano-generators (TENG) industry may also use AI technologies. In this work, the classifiers suitable for predicting the system accuracy for TENG are analyzed. The experimental data used for training and testing, and two of the Machine Learning (ML) classifiers provided promising results: K Nearest Neighbor (KNN) and Neural Network (NN). Different ML parameters are generated such as precision, recall and F1 score with the help of Confusion matrix for KNN and NN of the practical TENG energy data. Additionally, we assess the TENG’s output quality in CS mode under various load factors using ML models.
{"title":"Performance Prediction of Contact Separation Mode Triboelectric nanogenerators using Machine Learning Models","authors":"Ravikumar Puppala, K. Prakash, R. R. Kumar, Md. Farukh Hashmi, K. Kumar","doi":"10.1109/PCEMS58491.2023.10136029","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136029","url":null,"abstract":"The use of Artificial Intelligence (AI) algorithms for analyzing practical data has increased with the advent of AI models. Combining physics and engineering has garnered a lot of interest so much, so that the triboelectric Nano-generators (TENG) industry may also use AI technologies. In this work, the classifiers suitable for predicting the system accuracy for TENG are analyzed. The experimental data used for training and testing, and two of the Machine Learning (ML) classifiers provided promising results: K Nearest Neighbor (KNN) and Neural Network (NN). Different ML parameters are generated such as precision, recall and F1 score with the help of Confusion matrix for KNN and NN of the practical TENG energy data. Additionally, we assess the TENG’s output quality in CS mode under various load factors using ML models.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129258019","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136074
Venkatesh Kandukuri, Srujal Reddy Gundedi, V. Kamble, V. Satpute
Sign language is the language used by deaf and dumb people to communicate with others. Deaf and mute people express their thoughts and ideas through hand movements or facial expressions or gestures. However, interpreting sign language can be challenging for individuals who are not fluent in it. The current sign language recognition methods often rely on expensive hardware such as depth cameras or specialized gloves, which can be a barrier to widespread adoption. In this paper, we propose a low-cost solution for sign language recognition using MobileNet, a lightweight convolutional neural network architecture. This Paper deals with the static American Sign alphabet (j and z dynamic). The proposed model extracts the features and classifies them. The Model is able to predict the alphabet successfully corresponding to the sign. A finger Spelling dataset is used to train and test the model. The proposed model was successfully recognized with an accuracy of 99.93%. The obtained results and graphs show that the system is able to predict the sign correctly.
{"title":"Deaf and Mute Sign Language Translator on Static Alphabets Gestures using MobileNet","authors":"Venkatesh Kandukuri, Srujal Reddy Gundedi, V. Kamble, V. Satpute","doi":"10.1109/PCEMS58491.2023.10136074","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136074","url":null,"abstract":"Sign language is the language used by deaf and dumb people to communicate with others. Deaf and mute people express their thoughts and ideas through hand movements or facial expressions or gestures. However, interpreting sign language can be challenging for individuals who are not fluent in it. The current sign language recognition methods often rely on expensive hardware such as depth cameras or specialized gloves, which can be a barrier to widespread adoption. In this paper, we propose a low-cost solution for sign language recognition using MobileNet, a lightweight convolutional neural network architecture. This Paper deals with the static American Sign alphabet (j and z dynamic). The proposed model extracts the features and classifies them. The Model is able to predict the alphabet successfully corresponding to the sign. A finger Spelling dataset is used to train and test the model. The proposed model was successfully recognized with an accuracy of 99.93%. The obtained results and graphs show that the system is able to predict the sign correctly.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130410543","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136096
Maneesh Kumar Singh, D. Jhariya, Raghvendra Singh, Abhishek Upadhyay
Machine learning algorithms are the turf of artificial intelligence which handle the learning aspect of computers/machines due to advancement in technologies that permitted these binary machines to build a better understanding of patterns and logic; also help in finding solutions for real-world problems. As a machine learning tool, support vector machines (SVMs) are a prominent supervised algorithm that deals with the classification and regression of the observed datasets. In this paper, support Vector Machine algorithm has been implemented over Field Programmable Gate Array (FPGA) for classification in linear mode to accelerate the computations by the aid of the parallel nature of FPGAs to acquire high prediction accuracy at a cost of its high computational complexity.
{"title":"Performance Comparison of FPGA based Linear SVMS Classifier and Computer Simulation","authors":"Maneesh Kumar Singh, D. Jhariya, Raghvendra Singh, Abhishek Upadhyay","doi":"10.1109/PCEMS58491.2023.10136096","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136096","url":null,"abstract":"Machine learning algorithms are the turf of artificial intelligence which handle the learning aspect of computers/machines due to advancement in technologies that permitted these binary machines to build a better understanding of patterns and logic; also help in finding solutions for real-world problems. As a machine learning tool, support vector machines (SVMs) are a prominent supervised algorithm that deals with the classification and regression of the observed datasets. In this paper, support Vector Machine algorithm has been implemented over Field Programmable Gate Array (FPGA) for classification in linear mode to accelerate the computations by the aid of the parallel nature of FPGAs to acquire high prediction accuracy at a cost of its high computational complexity.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123369995","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：