Pub Date : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9545023
Karthi S P, A. A, D. S, Guru K, Hariram S
Traditional notice board, is widely used in many places, where there are abundant amount of people either working at the particular places or people who visit those public places like universities, institutions, bus stand, railway station, hospitals etc. Here, the existing ordinary notice board is enhanced into a multi-featured board as well as a smart notice board which alerts the people whenever a place catches fire i.e it acts as a fire alarming system and a special feature is that it transmits the audio message spontaneously, spoken by the user, more precisely an authorized user which requires an authentication to use the particular smart notice board i.e it requires the authentication in a form of password in text form. Here microcontroller and GSM models have been used for transferring the message to the audiences.
{"title":"Smart Information Display System","authors":"Karthi S P, A. A, D. S, Guru K, Hariram S","doi":"10.1109/ICIRCA51532.2021.9545023","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9545023","url":null,"abstract":"Traditional notice board, is widely used in many places, where there are abundant amount of people either working at the particular places or people who visit those public places like universities, institutions, bus stand, railway station, hospitals etc. Here, the existing ordinary notice board is enhanced into a multi-featured board as well as a smart notice board which alerts the people whenever a place catches fire i.e it acts as a fire alarming system and a special feature is that it transmits the audio message spontaneously, spoken by the user, more precisely an authorized user which requires an authentication to use the particular smart notice board i.e it requires the authentication in a form of password in text form. Here microcontroller and GSM models have been used for transferring the message to the audiences.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123950242","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}
Over the years with the advent of social media and messaging apps, people have been using jargon, abbreviated words, and casual language while chatting with other people. This leads to a lack of conversational skills during interviews, job meetings, or even daily conversations. Poorly spoken English has been a prime factor due to which students are unsuccessful in clearing the interviews for a job. There are many studies that indicate that an overwhelming percentage of engineers in the country cannot speak English fluently which is required for high-end consulting jobs. Present-day institutions provide solutions for improving English speaking but are expensive. Hence, there is a need for an instantly available conversing partner to hone communication skills. We propose a virtual assistant that can communicate with the user in an attempt to improve English speaking skills. The system consists of SynQG model for question generation, RoBERTa Grammar Error Correction model and praat-parselmouth for speech analysis. The user practices English speaking by answering the questions generated by the system. A thorough speech analysis report is provided to the user based on these answers highlighting mistakes as well as strengths in areas like grammar and pronunciation.
{"title":"Virtual Assistant for Enhancing English Speaking Skills","authors":"Ayushi Desai, Yash Gandhi, Jaynil Gaglani, Nikahat Mulla","doi":"10.1109/ICIRCA51532.2021.9544877","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544877","url":null,"abstract":"Over the years with the advent of social media and messaging apps, people have been using jargon, abbreviated words, and casual language while chatting with other people. This leads to a lack of conversational skills during interviews, job meetings, or even daily conversations. Poorly spoken English has been a prime factor due to which students are unsuccessful in clearing the interviews for a job. There are many studies that indicate that an overwhelming percentage of engineers in the country cannot speak English fluently which is required for high-end consulting jobs. Present-day institutions provide solutions for improving English speaking but are expensive. Hence, there is a need for an instantly available conversing partner to hone communication skills. We propose a virtual assistant that can communicate with the user in an attempt to improve English speaking skills. The system consists of SynQG model for question generation, RoBERTa Grammar Error Correction model and praat-parselmouth for speech analysis. The user practices English speaking by answering the questions generated by the system. A thorough speech analysis report is provided to the user based on these answers highlighting mistakes as well as strengths in areas like grammar and pronunciation.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130257144","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544669
Malathy. S, C. Vanitha, Nirdhum Narayan, Rajesh Kumar, Gokul. R
Handwritten digit recognition have great impact in the applications of deep learning. Convolutional Neural Network in the deep learning has become one of the major methods and one of the important factors in the various success in recent times and deep learning is used majorly in the area of object recognition. In the paper work, the speech output feature is integrated along with the text output. Convolutional Neural Network model is applied in the image classification. The dataset used to train and test is the MNIST dataset. There are various applications of handwritten digit recognition in the real time. It is applied in detection of vehicle number, reading of bank cheques, the arrangement of letters in the post office.
{"title":"An Enhanced Handwritten Digit Recognition Using Convolutional Neural Network","authors":"Malathy. S, C. Vanitha, Nirdhum Narayan, Rajesh Kumar, Gokul. R","doi":"10.1109/ICIRCA51532.2021.9544669","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544669","url":null,"abstract":"Handwritten digit recognition have great impact in the applications of deep learning. Convolutional Neural Network in the deep learning has become one of the major methods and one of the important factors in the various success in recent times and deep learning is used majorly in the area of object recognition. In the paper work, the speech output feature is integrated along with the text output. Convolutional Neural Network model is applied in the image classification. The dataset used to train and test is the MNIST dataset. There are various applications of handwritten digit recognition in the real time. It is applied in detection of vehicle number, reading of bank cheques, the arrangement of letters in the post office.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129500391","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9545042
V. G, S. Thangam
Internet of things (IOT) is a technology trend in modern innovation which provides answers for issues in our standard of living. IOT is being applied in modernization of many spaces of life. IOT can also be utilized to solve issues in traditional agriculture methods and agribusiness area to naturally keep up and screen rural homesteads with insignificant human association. The paper highlights numerous parts of innovations associated with the space of IOT in farming and role of IOT in agribusiness. The impact of inclusion of IOT in organization advancements in IOT based agribusiness has been introduced, that includes sensors, actuators, network engineering, wireless technologies and architectural layers, network geographies utilized, and conventions.
{"title":"Smart agriculture and role of IOT","authors":"V. G, S. Thangam","doi":"10.1109/ICIRCA51532.2021.9545042","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9545042","url":null,"abstract":"Internet of things (IOT) is a technology trend in modern innovation which provides answers for issues in our standard of living. IOT is being applied in modernization of many spaces of life. IOT can also be utilized to solve issues in traditional agriculture methods and agribusiness area to naturally keep up and screen rural homesteads with insignificant human association. The paper highlights numerous parts of innovations associated with the space of IOT in farming and role of IOT in agribusiness. The impact of inclusion of IOT in organization advancements in IOT based agribusiness has been introduced, that includes sensors, actuators, network engineering, wireless technologies and architectural layers, network geographies utilized, and conventions.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128253681","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544996
Thangam Palaniswamy
Skeletal bone age assessment (BAA) is a commonly employed clinical practice used for the diagnosis of endocrine and metabolic illness in child growth. BAA approach generally starts with the acquisition of the X ray image of the left hand from the wrist to fingertip. The bones in the X ray image undergo comparison with the radiological images that exist in the standard atlas of bone development. Since manual methods are time consuming and erroneous, the recently developed deep learning (DL) models find useful in the design of automated BAA using X ray images. In this view, this paper presents a new DL empowered automated BAA (DL-ABAA) model using X ray images. The proposed DL-ABAA model performs initial preprocessing to improve the image quality. Followed by Fast region convolutional neural network (Fast-RCNN) with VGG-19 model-based feature extractor is involved for deriving the features from the input X ray images. At the same time, shuffled frog leaf optimization (SFLO) algorithm is utilized as a hyperparameter optimizer of the VGG-19 model. In addition, softmax (SM) based age prediction and extreme gradient boosting (XGBoost) based stage classification processes are applied to predict the age and determine the class labels. A detailed experimental results analysis stated the improved performance of the BAA technique over the recent approaches with the higher accuracy of 96.53%.
{"title":"Deep Learning Empowered Automatic Bone Age Assessment","authors":"Thangam Palaniswamy","doi":"10.1109/ICIRCA51532.2021.9544996","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544996","url":null,"abstract":"Skeletal bone age assessment (BAA) is a commonly employed clinical practice used for the diagnosis of endocrine and metabolic illness in child growth. BAA approach generally starts with the acquisition of the X ray image of the left hand from the wrist to fingertip. The bones in the X ray image undergo comparison with the radiological images that exist in the standard atlas of bone development. Since manual methods are time consuming and erroneous, the recently developed deep learning (DL) models find useful in the design of automated BAA using X ray images. In this view, this paper presents a new DL empowered automated BAA (DL-ABAA) model using X ray images. The proposed DL-ABAA model performs initial preprocessing to improve the image quality. Followed by Fast region convolutional neural network (Fast-RCNN) with VGG-19 model-based feature extractor is involved for deriving the features from the input X ray images. At the same time, shuffled frog leaf optimization (SFLO) algorithm is utilized as a hyperparameter optimizer of the VGG-19 model. In addition, softmax (SM) based age prediction and extreme gradient boosting (XGBoost) based stage classification processes are applied to predict the age and determine the class labels. A detailed experimental results analysis stated the improved performance of the BAA technique over the recent approaches with the higher accuracy of 96.53%.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"17 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126963562","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544606
L. Ding, Wei-Hau Du
This research study begins with deep learning and progresses to cluster computing to complete the image depth analysis pipeline. The deep neural model is taken into account in designing the proposed model. The convolutional layer is composed of several convolutional units in morphology, and the feature value of the related image is obtained through the convolution and operation. The parallel structure is utilized to optimize this layer. Further, the original data is taken as input, and complete the construction of the proposed model through a series of operations such as convolution, pooling, and nonlinear activation function mapping. The depth image analysis is selected as the verification target. Through the simulation, the analysis accuracy has been much higher than the traditional methods.
{"title":"Image Depth Analysis: From Deep Learning to Parallel Cluster Computing","authors":"L. Ding, Wei-Hau Du","doi":"10.1109/ICIRCA51532.2021.9544606","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544606","url":null,"abstract":"This research study begins with deep learning and progresses to cluster computing to complete the image depth analysis pipeline. The deep neural model is taken into account in designing the proposed model. The convolutional layer is composed of several convolutional units in morphology, and the feature value of the related image is obtained through the convolution and operation. The parallel structure is utilized to optimize this layer. Further, the original data is taken as input, and complete the construction of the proposed model through a series of operations such as convolution, pooling, and nonlinear activation function mapping. The depth image analysis is selected as the verification target. Through the simulation, the analysis accuracy has been much higher than the traditional methods.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127613431","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544508
P. Nikhate, A. Deshmukh, Swapnali Choudhari
The proposed research study analyzes several methods to achieve a higher data rate by using past wireless technologies and also enhancing the past technology by working on them and modifying them for achieving a better data flowing rate. This research work is focusing more on the multiple-inputs multiple-outputs(MIMO) system, and by using this system this research study aims to produce a higher data rate, higher data flowing channels by using multiplexing and diversity. Nowadays, wireless technology is on growing so for the future point of view, it is highly required to improve the current data flowing rate properties on the transceiver side. Here, by using both ends of the nodes, a higher data flowing capacity of the wireless system can be achieved with very negligible losses along with consistent quality performance while transporting the data packets from one door to another and getting a quick response through the channel that is modified by using spatial multiplexing and increasing it higher-level up. This spatial multiplexing help undamaged data packets to arrive at the link target as quickly as possible while transmission and due to this the higher data flowing rate can be achieved with a higher data gaining rate by only using the MIMO system. Based on past communication technologies, this study has have determined that Alamouti STBC and ZF equalizer is the best remedy for the analysis of MIMO system to calculate communication diversity including the helping hands of BPSK modulation technique for achieving a better quality result. The Alamouti STBC and ZF equalization technique is used to calculate the BER result and this would be the linear equalization technique that is used to find the receiver nodes on the transceivers. The most important key point is that, all the operations are performing on MATLAB.
{"title":"Study and Analysis in MIMO Wireless Channel for STBC and Equalization Techniques by Using Matlab","authors":"P. Nikhate, A. Deshmukh, Swapnali Choudhari","doi":"10.1109/ICIRCA51532.2021.9544508","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544508","url":null,"abstract":"The proposed research study analyzes several methods to achieve a higher data rate by using past wireless technologies and also enhancing the past technology by working on them and modifying them for achieving a better data flowing rate. This research work is focusing more on the multiple-inputs multiple-outputs(MIMO) system, and by using this system this research study aims to produce a higher data rate, higher data flowing channels by using multiplexing and diversity. Nowadays, wireless technology is on growing so for the future point of view, it is highly required to improve the current data flowing rate properties on the transceiver side. Here, by using both ends of the nodes, a higher data flowing capacity of the wireless system can be achieved with very negligible losses along with consistent quality performance while transporting the data packets from one door to another and getting a quick response through the channel that is modified by using spatial multiplexing and increasing it higher-level up. This spatial multiplexing help undamaged data packets to arrive at the link target as quickly as possible while transmission and due to this the higher data flowing rate can be achieved with a higher data gaining rate by only using the MIMO system. Based on past communication technologies, this study has have determined that Alamouti STBC and ZF equalizer is the best remedy for the analysis of MIMO system to calculate communication diversity including the helping hands of BPSK modulation technique for achieving a better quality result. The Alamouti STBC and ZF equalization technique is used to calculate the BER result and this would be the linear equalization technique that is used to find the receiver nodes on the transceivers. The most important key point is that, all the operations are performing on MATLAB.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126699669","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544862
A. Bharambe, Akshaya Arun Chandorkar, Dhanajay Kalbande
Dengue is one amongst the foremost widespread vector borne diseases best-known these days. According to National Institute of Allergy and Infectious Disease (NIAID), Dengue fever has been identified as a threat to public health [1]. More than 33% of the total world population is under risk, together with several cities of Asian nation. In recent years, the utilization of social media (from tweets to Facebook posts) in healthcare has risen tremendously because social media is the platform to point out growing want of patients who are suffering, to attach with one another. Tweets are too short to supply sufficient word occurrences for traditional classification methods to give results reliably. Also, natural language is extremely complicated creating classification of health connected problems difficult. The performance of most conventional classification systems depends on acceptable information illustration and tremendous effort in feature engineering. Deep Learning is new space of machine learning that do automatic feature extraction. In this study, Convolutional Neural Network (CNN) has been used to classify dengue related tweets extracted from twitter into seven multiple classes such as ‘Infected’, ‘Informative’, ‘Vaccination’, ‘News', ‘Awareness', ‘Concern’ and ‘Others'. From Experimental results, Deep Learning algorithm shows increased accuracy when put next to Machine Learning algorithms such as Support Vector Machine (SVM), Naïve Bayes(NB) and Decision Tree Classifier(DT).
{"title":"A Deep Learning Approach for Dengue Tweet Classification","authors":"A. Bharambe, Akshaya Arun Chandorkar, Dhanajay Kalbande","doi":"10.1109/ICIRCA51532.2021.9544862","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544862","url":null,"abstract":"Dengue is one amongst the foremost widespread vector borne diseases best-known these days. According to National Institute of Allergy and Infectious Disease (NIAID), Dengue fever has been identified as a threat to public health [1]. More than 33% of the total world population is under risk, together with several cities of Asian nation. In recent years, the utilization of social media (from tweets to Facebook posts) in healthcare has risen tremendously because social media is the platform to point out growing want of patients who are suffering, to attach with one another. Tweets are too short to supply sufficient word occurrences for traditional classification methods to give results reliably. Also, natural language is extremely complicated creating classification of health connected problems difficult. The performance of most conventional classification systems depends on acceptable information illustration and tremendous effort in feature engineering. Deep Learning is new space of machine learning that do automatic feature extraction. In this study, Convolutional Neural Network (CNN) has been used to classify dengue related tweets extracted from twitter into seven multiple classes such as ‘Infected’, ‘Informative’, ‘Vaccination’, ‘News', ‘Awareness', ‘Concern’ and ‘Others'. From Experimental results, Deep Learning algorithm shows increased accuracy when put next to Machine Learning algorithms such as Support Vector Machine (SVM), Naïve Bayes(NB) and Decision Tree Classifier(DT).","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125692931","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544796
A. Sasi, Sathish Kumar Ravichandran
Spatial Computation is the next step in the continuing convergence between the digital and physical realms. It is a set of inventions and developments that can better our lives through learning the real world, acknowledging and connecting our connection to, and traveling through various locations in the world. The lack of modern, precise, and effective diagnosis limits the rehabilitation of patients, despite technical advancements in medicines. The capabilities of spatial computing are expanded in a healthcare framework during the care and treatment of the patient. In this article, our purpose is to clarify the function of ProjectDR in the field of healthcare, which enables the display of medical images, such as CT scans and MRI results, directly on the patient's body in a manner that moves as patients do.
{"title":"Future Innovation in Healthcare by Spatial Computing using ProjectDR","authors":"A. Sasi, Sathish Kumar Ravichandran","doi":"10.1109/ICIRCA51532.2021.9544796","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544796","url":null,"abstract":"Spatial Computation is the next step in the continuing convergence between the digital and physical realms. It is a set of inventions and developments that can better our lives through learning the real world, acknowledging and connecting our connection to, and traveling through various locations in the world. The lack of modern, precise, and effective diagnosis limits the rehabilitation of patients, despite technical advancements in medicines. The capabilities of spatial computing are expanded in a healthcare framework during the care and treatment of the patient. In this article, our purpose is to clarify the function of ProjectDR in the field of healthcare, which enables the display of medical images, such as CT scans and MRI results, directly on the patient's body in a manner that moves as patients do.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125916686","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 : 2021-09-02DOI: 10.1109/ICIRCA51532.2021.9544621
Yadeeswaran K S, N.Mithun Mithra, Varsha Ks, K. R
Diabetic retinopathy is a condition caused due to diabetes affecting the blood vessels in the retina. This paper presents a two-phase approach for diagnosing various conditions of the eye and also classify the fundus image as diabetic retinopathy positive or normal. The ODIR dataset containing fundus images of various conditions is used for training and testing purposes. The proposed method consists of an ensemble model. The first phase is a convolutional neural network that takes fundus images for its input and outputs the diagnostic keywords for each eye. The second phase is a machine learning classifier that determines if a person has diabetic retinopathy or not based on the keywords generated from the previous model. The results of the two phases are satisfactory. The diagnosing phase has an accuracy up to 95% and the classifier has an accuracy up to 99%.
{"title":"Classification of diabetic retinopathy through identification of diagnostic keywords","authors":"Yadeeswaran K S, N.Mithun Mithra, Varsha Ks, K. R","doi":"10.1109/ICIRCA51532.2021.9544621","DOIUrl":"https://doi.org/10.1109/ICIRCA51532.2021.9544621","url":null,"abstract":"Diabetic retinopathy is a condition caused due to diabetes affecting the blood vessels in the retina. This paper presents a two-phase approach for diagnosing various conditions of the eye and also classify the fundus image as diabetic retinopathy positive or normal. The ODIR dataset containing fundus images of various conditions is used for training and testing purposes. The proposed method consists of an ensemble model. The first phase is a convolutional neural network that takes fundus images for its input and outputs the diagnostic keywords for each eye. The second phase is a machine learning classifier that determines if a person has diabetic retinopathy or not based on the keywords generated from the previous model. The results of the two phases are satisfactory. The diagnosing phase has an accuracy up to 95% and the classifier has an accuracy up to 99%.","PeriodicalId":245244,"journal":{"name":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129124606","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：