Pub Date : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452973
L.A. Rakhsith, B. Karthik, A. D, K. V, K. Anusha
There is a huge panic among the people in recent times due to the spread of communicable diseases. People are in close vicinity to one another when in closed spaces like shops, restaurants, classrooms, etc. There is also a cause for worry in workplaces regarding the safety of the workplace. This paper discusses about two models which can be used to detect the distance between people to ensure social distancing and to detect if people are wearing a mask which can be implemented to follow safety measures. To implement these models deep learning techniques are used. For the social distancing model object detection is done to detect humans and this is done through the YOLOv3. For the mask detection model, the MobileNetV2 is the algorithm which is used for classification. This is used to detect if the people are wearing a mask. These two models can be used for the purpose of prevention against widely spreading diseases. For example, if the people of an organization have to request their customers to stay 6 feet apart or wear a mask in cases where the customers are not following the standard safety protocols, the people of the organization should go directly up to them and request for it. This increases the contact between people and at the same time increases the risk factor for the people working in that organization. When these models are implemented, it reduces unnecessary human contact while also ensuring to alert the customers if they break these protocols.
{"title":"Face Mask and Social Distancing Detection for Surveillance Systems","authors":"L.A. Rakhsith, B. Karthik, A. D, K. V, K. Anusha","doi":"10.1109/ICOEI51242.2021.9452973","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452973","url":null,"abstract":"There is a huge panic among the people in recent times due to the spread of communicable diseases. People are in close vicinity to one another when in closed spaces like shops, restaurants, classrooms, etc. There is also a cause for worry in workplaces regarding the safety of the workplace. This paper discusses about two models which can be used to detect the distance between people to ensure social distancing and to detect if people are wearing a mask which can be implemented to follow safety measures. To implement these models deep learning techniques are used. For the social distancing model object detection is done to detect humans and this is done through the YOLOv3. For the mask detection model, the MobileNetV2 is the algorithm which is used for classification. This is used to detect if the people are wearing a mask. These two models can be used for the purpose of prevention against widely spreading diseases. For example, if the people of an organization have to request their customers to stay 6 feet apart or wear a mask in cases where the customers are not following the standard safety protocols, the people of the organization should go directly up to them and request for it. This increases the contact between people and at the same time increases the risk factor for the people working in that organization. When these models are implemented, it reduces unnecessary human contact while also ensuring to alert the customers if they break these protocols.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127128867","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9453085
Ramandeep Kaur, Ankita Guleria
Usage of digital devices especially smartphones significantly increased in the previous decade. Moreover, COVID pandemic has further shifted much of the work towards digital device assisted applications. In today's era, people across all ages are spending a lot of time in front of these devices. This also implies a surge in Digital Eye Strain cases, which is one of the emerging health issues. Researchers have linked this problem with symptoms such as dry eyes, altered blinking pattern, visual fatigue etc. Although the previous studies on facial features have already focused on blinking patterns, yawn detection and head movement, the proposed research work has concluded that other facial gestures comprising droopy eyes and decrease in glabellar length are also relevant features for this study to increase the accuracy. This paper tries to effectively detect when a user is under strain so that he or she can take timely precautions. A supervised method based on statistical features linked to suggested symptoms is proposed for classifying videos recorded in real time as user under strain using SVM. The main finding is an explicit feature set comprising of two newly proposed features along with four other apposite features derived from previous theoretical studies. The proposed system shows considerable increase in accuracy when tested on YawDD, the best possible dataset available for our use case.
{"title":"Digital Eye Strain Detection System Based on SVM","authors":"Ramandeep Kaur, Ankita Guleria","doi":"10.1109/ICOEI51242.2021.9453085","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9453085","url":null,"abstract":"Usage of digital devices especially smartphones significantly increased in the previous decade. Moreover, COVID pandemic has further shifted much of the work towards digital device assisted applications. In today's era, people across all ages are spending a lot of time in front of these devices. This also implies a surge in Digital Eye Strain cases, which is one of the emerging health issues. Researchers have linked this problem with symptoms such as dry eyes, altered blinking pattern, visual fatigue etc. Although the previous studies on facial features have already focused on blinking patterns, yawn detection and head movement, the proposed research work has concluded that other facial gestures comprising droopy eyes and decrease in glabellar length are also relevant features for this study to increase the accuracy. This paper tries to effectively detect when a user is under strain so that he or she can take timely precautions. A supervised method based on statistical features linked to suggested symptoms is proposed for classifying videos recorded in real time as user under strain using SVM. The main finding is an explicit feature set comprising of two newly proposed features along with four other apposite features derived from previous theoretical studies. The proposed system shows considerable increase in accuracy when tested on YawDD, the best possible dataset available for our use case.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128944218","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452910
S. Varun, R. Nagaraj
The outburst of corona virus called SARS-COV-2 saw a sudden surge in active cases all over the world. Kalman filter with its tremendous prediction capability achieves the actual value within limited iteration so that any locality can be aware of the increase in the status of the infected patients. This paper proposes the estimation algorithm for tracking covid19 patients in locality using kalman filter. The vitals acquired from these patients through sensors can be transmitted to the doctor through internet for further monitoring thereby decreasing the fatality rate including post covid19 patients. Kalman filtering along with monitoring system can bring wonders in medical field thus decreasing the risk of sudden heart attack, variation in blood pressure, blood sugar fluctuations in patients located in remote locations.
{"title":"Covid19 tracking algorithm and conceptualization of an associated patient monitoring system","authors":"S. Varun, R. Nagaraj","doi":"10.1109/ICOEI51242.2021.9452910","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452910","url":null,"abstract":"The outburst of corona virus called SARS-COV-2 saw a sudden surge in active cases all over the world. Kalman filter with its tremendous prediction capability achieves the actual value within limited iteration so that any locality can be aware of the increase in the status of the infected patients. This paper proposes the estimation algorithm for tracking covid19 patients in locality using kalman filter. The vitals acquired from these patients through sensors can be transmitted to the doctor through internet for further monitoring thereby decreasing the fatality rate including post covid19 patients. Kalman filtering along with monitoring system can bring wonders in medical field thus decreasing the risk of sudden heart attack, variation in blood pressure, blood sugar fluctuations in patients located in remote locations.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"51 Suppl 53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126899763","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9453048
Fang Ji, Yulong Xue
Network information inheritance of traditional and migrant craftsmanship based on the background of big data is studied. The data structure has not yet achieved uniformity in scope, and it is still difficult to achieve data integration on one platform; in addition, the increasing business volume makes the development direction of data present a trend of fragmentation, and the user's business model Is also gradually changing. To face with this challenge, this paper studies the novel data structure for the efficient analysis. We apply the model on the scenario of the traditional and migrant craftsmanship, the test results reflect that the model is efficient.
{"title":"Network information inheritance of traditional and migrant craftsmanship based on the background of big data","authors":"Fang Ji, Yulong Xue","doi":"10.1109/ICOEI51242.2021.9453048","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9453048","url":null,"abstract":"Network information inheritance of traditional and migrant craftsmanship based on the background of big data is studied. The data structure has not yet achieved uniformity in scope, and it is still difficult to achieve data integration on one platform; in addition, the increasing business volume makes the development direction of data present a trend of fragmentation, and the user's business model Is also gradually changing. To face with this challenge, this paper studies the novel data structure for the efficient analysis. We apply the model on the scenario of the traditional and migrant craftsmanship, the test results reflect that the model is efficient.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130743619","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452921
A. Mary, Emmaneni Venkata Naga Sai Prem, Sri Hari Jujjavarapu, P. Asha
The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for everybody. Any disturbance or inaccessibility of this asset may prompt genuine effects at different levels of our public. As the reliance on the Internet continues developing at an exponential rate, the dangers to the accessibility of network assets have likewise been expanding quickly. In this research, we focus on the detection deep learning procedures against DoS attacks and recommend a learning centric detect scheme for the discovery, proof of identity, categorization of network attack. mitigation of IoT DDoS attacks.
{"title":"Securing Data by Detecting Multi Channel Attacks Using Deep Learning","authors":"A. Mary, Emmaneni Venkata Naga Sai Prem, Sri Hari Jujjavarapu, P. Asha","doi":"10.1109/ICOEI51242.2021.9452921","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452921","url":null,"abstract":"The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for everybody. Any disturbance or inaccessibility of this asset may prompt genuine effects at different levels of our public. As the reliance on the Internet continues developing at an exponential rate, the dangers to the accessibility of network assets have likewise been expanding quickly. In this research, we focus on the detection deep learning procedures against DoS attacks and recommend a learning centric detect scheme for the discovery, proof of identity, categorization of network attack. mitigation of IoT DDoS attacks.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"2007 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130604086","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452817
Y. V. Sai, Salman, T. Sasikala
An In-Depth look at images for finding information using deep learning and reverse image search explains that current technology necessitates a modern approach for extracting information from images. Generating a caption from an image may require computer vision and natural language processing concepts for generating the caption in a natural language like English etc. This paper attempts to show how more information can be generated from an image for further analysis of making some predictions. This project is able to detect the person's identity if a person's face is visible in the image as well as all about the image as to where it has taken resolution, and all other factors. The entire project will describe as much information as possible and utilize it for further analysis. For example, given a white lion image then the image may tell the output as “The white lion is a rare color mutation of the lion, specifically the Southern African lion.” or if an image contains a person as an anonymous then the output will be like “Name, Address and lot more”. It can give you complete information about an image, apart from the basic information and the EXIF data, it also shows other useful and in-depth data. There are some reasons that why you need to get information from a photo if a photo you saw that selling a product at a cheap price then we definitely may be interested to buy but wait that may be a scam or what if someone send you the friend request that is the real or fake person that also we have to be aware and what if you are going to meet with a wrong people if he used a fake photo last time with you and you are going to meet with the wrong guy.
{"title":"An In-Depth Look at the Images for Finding Information using Deep learning and Reverse Image Search","authors":"Y. V. Sai, Salman, T. Sasikala","doi":"10.1109/ICOEI51242.2021.9452817","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452817","url":null,"abstract":"An In-Depth look at images for finding information using deep learning and reverse image search explains that current technology necessitates a modern approach for extracting information from images. Generating a caption from an image may require computer vision and natural language processing concepts for generating the caption in a natural language like English etc. This paper attempts to show how more information can be generated from an image for further analysis of making some predictions. This project is able to detect the person's identity if a person's face is visible in the image as well as all about the image as to where it has taken resolution, and all other factors. The entire project will describe as much information as possible and utilize it for further analysis. For example, given a white lion image then the image may tell the output as “The white lion is a rare color mutation of the lion, specifically the Southern African lion.” or if an image contains a person as an anonymous then the output will be like “Name, Address and lot more”. It can give you complete information about an image, apart from the basic information and the EXIF data, it also shows other useful and in-depth data. There are some reasons that why you need to get information from a photo if a photo you saw that selling a product at a cheap price then we definitely may be interested to buy but wait that may be a scam or what if someone send you the friend request that is the real or fake person that also we have to be aware and what if you are going to meet with a wrong people if he used a fake photo last time with you and you are going to meet with the wrong guy.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130916419","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452851
Shaoyun Yin, Hao Cheng, Tao Sun
The building information model runs through the entire life cycle of a building. Simulating the construction through BIM can optimize the management of the whole life cycle of the building, so as to achieve the improvement of project quality and production efficiency. With the significant acceleration of my country's urbanization progress and the rapid development of the domestic construction industry, the rapid penetration and wide application of BIM technology in my country's construction industry has become an inevitable trend. As a major for training talents in the construction industry, engineering management is in urgent need of teaching reform. Therefore, only by integrating BIM technology into the teaching system can it adapt to social development and the needs of enterprises.
{"title":"Integration of BIM and Data Optimization Technology Into the Online Guiding of Engineering Management in Colleges","authors":"Shaoyun Yin, Hao Cheng, Tao Sun","doi":"10.1109/ICOEI51242.2021.9452851","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452851","url":null,"abstract":"The building information model runs through the entire life cycle of a building. Simulating the construction through BIM can optimize the management of the whole life cycle of the building, so as to achieve the improvement of project quality and production efficiency. With the significant acceleration of my country's urbanization progress and the rapid development of the domestic construction industry, the rapid penetration and wide application of BIM technology in my country's construction industry has become an inevitable trend. As a major for training talents in the construction industry, engineering management is in urgent need of teaching reform. Therefore, only by integrating BIM technology into the teaching system can it adapt to social development and the needs of enterprises.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130989386","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9452867
Rahul Agrawal, K. Jajulwar, Urvashi Agrawal
The common challenge observed in the early stages of pregnancy is the birth defect of infants. The key factors for this challenge are genetics and infection during pregnancy. According to GHO information, in 2015 about 4.5 million deaths occurred due to the sudden death syndrome and lack of nourishment of the fetus during pregnancy. One of the most important causes for abnormalities in infants is the bulge in their legs and abdomen. Bulge leads to many other problems and affect body functions such as brain, hand, and legs mostly in abdomen. In this paper, 117 images obtained from Beth Israel Deaconess Medical are taken for research purpose i.e., to identify the abnormalities in the fetal brain by using unsupervised learning algorithm. Proposed system is equipped to detect or classify the abnormalities of the fetus having gestational age from 14-38 weeks. Head region and abdomen region of the fetus is used for futher research analysis. Convex hull method is applied to the acquired images for performing image segmentation. The parameters like head diameter and abdomen circumference are used to incorporate feature extraction and followed by that k-means clustering algorithm is used to classify abnormalities in infants. The proposed system gives promising results for detecting the abnormalitiesof fetus and the accuracy is coming out to be 83.76% by using K-means clustering algorithm.
在怀孕早期观察到的常见挑战是婴儿的出生缺陷。这一挑战的关键因素是遗传和怀孕期间的感染。根据全球健康组织的信息，2015年约有450万人死于猝死综合症和怀孕期间胎儿营养不足。婴儿畸形最重要的原因之一是腿部和腹部的隆起。肥胖会导致许多其他问题，影响大脑、手、腿等身体功能，主要是在腹部。本文选取Beth Israel Deaconess Medical获得的117张图像作为研究目的，即利用无监督学习算法识别胎儿大脑的异常。该系统可检测或分类胎龄在14-38周的胎儿的异常。胎儿的头部区域和腹部区域用于进一步的研究分析。对采集的图像采用凸包法进行图像分割。采用头径、腹围等参数进行特征提取，然后采用k-means聚类算法对婴儿异常进行分类。该系统在胎儿异常检测方面取得了良好的效果，采用k均值聚类算法，准确率达到83.76%。
{"title":"A Design Approach for Performance Analysis of Infants Abnormality Using K Means Clustering","authors":"Rahul Agrawal, K. Jajulwar, Urvashi Agrawal","doi":"10.1109/ICOEI51242.2021.9452867","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9452867","url":null,"abstract":"The common challenge observed in the early stages of pregnancy is the birth defect of infants. The key factors for this challenge are genetics and infection during pregnancy. According to GHO information, in 2015 about 4.5 million deaths occurred due to the sudden death syndrome and lack of nourishment of the fetus during pregnancy. One of the most important causes for abnormalities in infants is the bulge in their legs and abdomen. Bulge leads to many other problems and affect body functions such as brain, hand, and legs mostly in abdomen. In this paper, 117 images obtained from Beth Israel Deaconess Medical are taken for research purpose i.e., to identify the abnormalities in the fetal brain by using unsupervised learning algorithm. Proposed system is equipped to detect or classify the abnormalities of the fetus having gestational age from 14-38 weeks. Head region and abdomen region of the fetus is used for futher research analysis. Convex hull method is applied to the acquired images for performing image segmentation. The parameters like head diameter and abdomen circumference are used to incorporate feature extraction and followed by that k-means clustering algorithm is used to classify abnormalities in infants. The proposed system gives promising results for detecting the abnormalitiesof fetus and the accuracy is coming out to be 83.76% by using K-means clustering algorithm.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547691","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}
Nowadays, many Telugu Language documents have become available in digital form in this information era. These documents should be grouped into a class based on their content for easy retrieval of these electronic data records. Text categorization is perhaps the crucial issue in information systems concerned with text records, owing to the increasing volume of information contained in digital form. Text categorization methods have been applied to Telugu text in order to derive valuable information and insights from unstructured Telugu text. Text categorization is the method of identifying a category or several categories from a set of predefined choices for a document. Indian languages are difficult to categories because they have a lot of morphology, a lot of different word forms, and a lot of different feature spaces. Since Telugu is morphologically rich and requires special algorithms to perform morphological analysis, there hasn't been much research done on it. To construct an organized and reduced-feature lexicon, the preprocessing methods which are designed specifically for Telugu language are applied to raw data. Significant pre-processing is required to construct accurate classification model Telugu text documents. In this paper, we compare the different machine learning and deep learning classifiers performance on the Telugu text such as Naïve Bayes, Support Vector Machine (SVM), and neural network classifier.
{"title":"Comparative Study on Telugu text Classification using Machine Learning and Deep Learning models","authors":"Veerraju Gampala, Jaideep Vallapuneni, Pavan Kumar Ande, Ravindra Kumar Indurthi, N. Rajesh","doi":"10.1109/ICOEI51242.2021.9453040","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9453040","url":null,"abstract":"Nowadays, many Telugu Language documents have become available in digital form in this information era. These documents should be grouped into a class based on their content for easy retrieval of these electronic data records. Text categorization is perhaps the crucial issue in information systems concerned with text records, owing to the increasing volume of information contained in digital form. Text categorization methods have been applied to Telugu text in order to derive valuable information and insights from unstructured Telugu text. Text categorization is the method of identifying a category or several categories from a set of predefined choices for a document. Indian languages are difficult to categories because they have a lot of morphology, a lot of different word forms, and a lot of different feature spaces. Since Telugu is morphologically rich and requires special algorithms to perform morphological analysis, there hasn't been much research done on it. To construct an organized and reduced-feature lexicon, the preprocessing methods which are designed specifically for Telugu language are applied to raw data. Significant pre-processing is required to construct accurate classification model Telugu text documents. In this paper, we compare the different machine learning and deep learning classifiers performance on the Telugu text such as Naïve Bayes, Support Vector Machine (SVM), and neural network classifier.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116214566","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 : 2021-06-03DOI: 10.1109/ICOEI51242.2021.9453044
P. A, G. S, Archith K, P. K
Cervical cancer is the second most common form of gynecologic cancer in less developed countries, after breast cancer. The Pap-Smear examination is now becoming as one of the most important screening methodologies in the speedy identification of this form of carcinoma, and among all strategies, the diagnostic test is the one that is most widely used in cervical cancer diagnosis. Machine Learning has the ability to provide accurate prognosis by using machine algorithm to perform classification, prediction, and estimation to achieve a high prediction rate. The Ensemble approach incorporates three machine learning techniques: K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Random Forest. With the precision percentage of 97.83 percent, the last technique provides more accurate results. To summarize, machine learning has the potential to achieve high diagnosis accuracy, while still being effective.
{"title":"Projection of Malignant Tumor of the Cervix using Machine Learning","authors":"P. A, G. S, Archith K, P. K","doi":"10.1109/ICOEI51242.2021.9453044","DOIUrl":"https://doi.org/10.1109/ICOEI51242.2021.9453044","url":null,"abstract":"Cervical cancer is the second most common form of gynecologic cancer in less developed countries, after breast cancer. The Pap-Smear examination is now becoming as one of the most important screening methodologies in the speedy identification of this form of carcinoma, and among all strategies, the diagnostic test is the one that is most widely used in cervical cancer diagnosis. Machine Learning has the ability to provide accurate prognosis by using machine algorithm to perform classification, prediction, and estimation to achieve a high prediction rate. The Ensemble approach incorporates three machine learning techniques: K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Random Forest. With the precision percentage of 97.83 percent, the last technique provides more accurate results. To summarize, machine learning has the potential to achieve high diagnosis accuracy, while still being effective.","PeriodicalId":420826,"journal":{"name":"2021 5th International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125211450","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：