With recent technological and scientific advancements in the power systems, there has been a tandem need for load forecasting. This paper mainly discusses short-term load forecasting, which refers to the prediction of the system load demand over an interval ranging between minutes ahead to one week ahead. With advent of Machine Learning, the process of demand prediction has become easier and cost effective. The challenge of predicting the future demand can be characterized as a regression problem, hence the method of Support Vector Regression is used, as it has proved to be a robust method in the recent research. Different Neural Networks are also being used in several domains; hence Deep Neural Network has also been used to test the accuracy, The paper discusses the results obtained by two different methods. The comparison between the outcomes of the different algorithms has been discussed, in order to get a thorough understanding. The methods are explained vastly. The paper also discusses the factors affecting load forecasting directly.
{"title":"Short Term Load Forecasting using Machine Learning Techniques","authors":"Sonakshi Dua, Shaurya Gautam, Mahi Garg, Rajendra Mahla, Mrityunjay Chaudhary, S. Vadhera","doi":"10.1109/CONIT55038.2022.9848160","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848160","url":null,"abstract":"With recent technological and scientific advancements in the power systems, there has been a tandem need for load forecasting. This paper mainly discusses short-term load forecasting, which refers to the prediction of the system load demand over an interval ranging between minutes ahead to one week ahead. With advent of Machine Learning, the process of demand prediction has become easier and cost effective. The challenge of predicting the future demand can be characterized as a regression problem, hence the method of Support Vector Regression is used, as it has proved to be a robust method in the recent research. Different Neural Networks are also being used in several domains; hence Deep Neural Network has also been used to test the accuracy, The paper discusses the results obtained by two different methods. The comparison between the outcomes of the different algorithms has been discussed, in order to get a thorough understanding. The methods are explained vastly. The paper also discusses the factors affecting load forecasting directly.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127107408","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848356
Gadde Satya Sai Naga Himabindu, Rajat Rao, Divyashikha Sethia
Emojis enjoy an important place in digital communication. They can express feelings and emotions in contexts when words cannot. In other words, they add emotions to a piece of text. Emojis are rising concurrently with the increased use of social media platforms for communication and have become a language in itself. Single emoji prediction systems are no longer adequate because multiple emojis are being grouped to convey emotions these days. The multi-label emoji prediction system for code-mixed language has not yet been explored to the best of our knowledge. It explores multi-label emoji prediction in Hinglish, one of the most commonly used code-mixed languages. This paper presents a framework for Hinglish multi-label emoji prediction. The proposed Encoder-decoder based Emoji Prediction model for Hinglish (EDEPHi) model outperforms other baseline models and is far more diverse in terms of predicted emojis.
{"title":"Encoder-decoder based multi-label emoji prediction for Code-Mixed Language (Hindi+English)","authors":"Gadde Satya Sai Naga Himabindu, Rajat Rao, Divyashikha Sethia","doi":"10.1109/CONIT55038.2022.9848356","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848356","url":null,"abstract":"Emojis enjoy an important place in digital communication. They can express feelings and emotions in contexts when words cannot. In other words, they add emotions to a piece of text. Emojis are rising concurrently with the increased use of social media platforms for communication and have become a language in itself. Single emoji prediction systems are no longer adequate because multiple emojis are being grouped to convey emotions these days. The multi-label emoji prediction system for code-mixed language has not yet been explored to the best of our knowledge. It explores multi-label emoji prediction in Hinglish, one of the most commonly used code-mixed languages. This paper presents a framework for Hinglish multi-label emoji prediction. The proposed Encoder-decoder based Emoji Prediction model for Hinglish (EDEPHi) model outperforms other baseline models and is far more diverse in terms of predicted emojis.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124365605","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847947
G. Snehalatha, J. Selvakumar, Esther Rani Thuraka
Data converters implemented using CMOS technology play crucial role in electronics which is ever increasing. ADCs find their applications in signal processing and communication applications. Because of small area, low power and low/medium input signals Successive Approximation ADCs are preferred in most of the applications. Machine Learning algorithms are used to fine-tune the Successive Stochastic Approximation Analog to Digital Converter (SSA ADC), which is used in Biomedical applications. Compared to SAR ADC, SSA ADC offers low power and errors caused by DAC can be corrected to maximum possible extent using stochastic process. Various ADCs, SAR ADC and SSA ADC architectures for Biomedical applications have been compared with respect to parameters, methods and tools.
{"title":"Comparative Study and Review on Successive Approximation/Stochastic Approximation Analog to Digital Converters for Biomedical Applications","authors":"G. Snehalatha, J. Selvakumar, Esther Rani Thuraka","doi":"10.1109/CONIT55038.2022.9847947","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847947","url":null,"abstract":"Data converters implemented using CMOS technology play crucial role in electronics which is ever increasing. ADCs find their applications in signal processing and communication applications. Because of small area, low power and low/medium input signals Successive Approximation ADCs are preferred in most of the applications. Machine Learning algorithms are used to fine-tune the Successive Stochastic Approximation Analog to Digital Converter (SSA ADC), which is used in Biomedical applications. Compared to SAR ADC, SSA ADC offers low power and errors caused by DAC can be corrected to maximum possible extent using stochastic process. Various ADCs, SAR ADC and SSA ADC architectures for Biomedical applications have been compared with respect to parameters, methods and tools.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127363021","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848267
Harini V, Sairam M V S, Madhu R
A dual-band hexagonal-shaped planar quad element millimeter-wave Multi-Input Multi-Output (MIMO) antenna is proposed for 5G femtocells applications. Initially, a hexagonal-shaped single element is designed and analysis is performed on Rogers R04003 ™ substrate with Er of 3.55 and & = 0.0027 with a thickness of substrate as 0.8mm. Later the single element is repeatedly placed on four sides of the substrate making a quad element MIMO antenna with four different ports. The Proposed antenna is radiating at 27.5GHz with a gain of 4.7 dBi at port1 and port3 and at port2 and port4, the antenna is radiating at dual bands like 28.5GHz and 38.5GHz with average gains of 4.69dBi and 5.5dBi. The antenna has a total efficiency of 95% with MIMO key performance metrics like envelope correlation coefficient and diversity gains as 0.045 and 9.995 at 10dB. Due to the lower perceptivity of tapping by unauthorized persons, MIMO antennas can be easily incorporated in 5G Femtocells.
{"title":"Dual-Band Hexagonal Millimeter Wave MIMO Antenna for 5G Femtocell Implementations","authors":"Harini V, Sairam M V S, Madhu R","doi":"10.1109/CONIT55038.2022.9848267","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848267","url":null,"abstract":"A dual-band hexagonal-shaped planar quad element millimeter-wave Multi-Input Multi-Output (MIMO) antenna is proposed for 5G femtocells applications. Initially, a hexagonal-shaped single element is designed and analysis is performed on Rogers R04003 ™ substrate with Er of 3.55 and & = 0.0027 with a thickness of substrate as 0.8mm. Later the single element is repeatedly placed on four sides of the substrate making a quad element MIMO antenna with four different ports. The Proposed antenna is radiating at 27.5GHz with a gain of 4.7 dBi at port1 and port3 and at port2 and port4, the antenna is radiating at dual bands like 28.5GHz and 38.5GHz with average gains of 4.69dBi and 5.5dBi. The antenna has a total efficiency of 95% with MIMO key performance metrics like envelope correlation coefficient and diversity gains as 0.045 and 9.995 at 10dB. Due to the lower perceptivity of tapping by unauthorized persons, MIMO antennas can be easily incorporated in 5G Femtocells.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129043307","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}
The Time-series data is a sequence of data points at regular time intervals indexed in time order. It is also known as time-stamped data. These sequential data characteristics might change during the process. Change points in time series data are substantial statistical property changes in the data. Many applications rely on the detection of these changes for appropriate modeling and prediction. Many vital activities can be monitored with the help of Change-Point Detection (CPD) algorithms, and appropriate actions can be made as a response. There are a variety of methods for detecting CPD in time series, which are divided into supervised and unsupervised categories. This comparative study compares all of the algorithms that have been published in the literature. Many novel algorithms based on the results of deep learning are also evaluated. Finally, we give the community some challenges to ponder.
{"title":"A Comparative Study on Change-Point Detection Methods in Time Series Data","authors":"Aditya Pushkar, Muktesh Gupta, Rajesh Wadhvani, Manasi Gyanchandani","doi":"10.1109/CONIT55038.2022.9848051","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848051","url":null,"abstract":"The Time-series data is a sequence of data points at regular time intervals indexed in time order. It is also known as time-stamped data. These sequential data characteristics might change during the process. Change points in time series data are substantial statistical property changes in the data. Many applications rely on the detection of these changes for appropriate modeling and prediction. Many vital activities can be monitored with the help of Change-Point Detection (CPD) algorithms, and appropriate actions can be made as a response. There are a variety of methods for detecting CPD in time series, which are divided into supervised and unsupervised categories. This comparative study compares all of the algorithms that have been published in the literature. Many novel algorithms based on the results of deep learning are also evaluated. Finally, we give the community some challenges to ponder.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127310709","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848116
Chidananda C, V. N, M. Vishwanath
This paper proposes a multi-level inverter (MLI) which has two or more unequal DC voltage source with lesser number of components. The proposed MLI composed of many basic DC source units, where each basic DC source unit are stacked in series to get higher voltage levels. The proposed topology of MLI is derived from a basic MLI cascaded H-bridge inverter. The designed AMLI is capable of handling negative current and hence capable of operating in all 4 quadrants due to absence of components like diode which is seen in the proposed topology, the phase opposition disposition PWM technique is used to trigger the switches. By utilizing three different DC voltage source as input to AMLI, we get an output waveform in staircase form of 15 level. The THD of output staircase waveform is 8.25% in which it has majority of higher harmonics distortion, by using LCL filter the THD of 0.1% can be achieved. The work is carried out on MATLAB / SIMULINK 2020Ra.
{"title":"Asymmetric Multi-Level Inverter","authors":"Chidananda C, V. N, M. Vishwanath","doi":"10.1109/CONIT55038.2022.9848116","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848116","url":null,"abstract":"This paper proposes a multi-level inverter (MLI) which has two or more unequal DC voltage source with lesser number of components. The proposed MLI composed of many basic DC source units, where each basic DC source unit are stacked in series to get higher voltage levels. The proposed topology of MLI is derived from a basic MLI cascaded H-bridge inverter. The designed AMLI is capable of handling negative current and hence capable of operating in all 4 quadrants due to absence of components like diode which is seen in the proposed topology, the phase opposition disposition PWM technique is used to trigger the switches. By utilizing three different DC voltage source as input to AMLI, we get an output waveform in staircase form of 15 level. The THD of output staircase waveform is 8.25% in which it has majority of higher harmonics distortion, by using LCL filter the THD of 0.1% can be achieved. The work is carried out on MATLAB / SIMULINK 2020Ra.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133988448","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847754
Jai Garg, Jatin Papreja, Kumar Apurva, Goonjan Jain
Effective and efficient grading has been recognized as an important issue in any educational institution. In this study, a grading system involving BERT for Automatic Short Answer Grading (ASAG) is proposed. A BERT Regressor model is fine-tuned using a domain-specific ASAG dataset to achieve a baseline performance. In order to improve the final grading performance, an effective strategy is proposed involving careful integration of BERT Regressor model with Semantic Text Similarity. A set of experiments is conducted to test the performance of the proposed method. Two performance metrics namely: Pearson's Correlation Coefficient and Root Mean Squared Error are used for evaluation purposes. The results obtained highlights the usefulness of proposed system for domain specific ASAG tasks in real life.
{"title":"Domain-Specific Hybrid BERT based System for Automatic Short Answer Grading","authors":"Jai Garg, Jatin Papreja, Kumar Apurva, Goonjan Jain","doi":"10.1109/CONIT55038.2022.9847754","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847754","url":null,"abstract":"Effective and efficient grading has been recognized as an important issue in any educational institution. In this study, a grading system involving BERT for Automatic Short Answer Grading (ASAG) is proposed. A BERT Regressor model is fine-tuned using a domain-specific ASAG dataset to achieve a baseline performance. In order to improve the final grading performance, an effective strategy is proposed involving careful integration of BERT Regressor model with Semantic Text Similarity. A set of experiments is conducted to test the performance of the proposed method. Two performance metrics namely: Pearson's Correlation Coefficient and Root Mean Squared Error are used for evaluation purposes. The results obtained highlights the usefulness of proposed system for domain specific ASAG tasks in real life.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133659298","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848285
Yatharth Saxena, Nirdesh Mishra, M. Sameer, Pankaj Dahiya
Edge detection is substantial in helping us to pre-process any image for various applications from helping us to detect objects to detecting various medical conditions. The paper tackled one major shortcoming with the currently present system which is edge thickness. To improve there is an implementation of multiple thresholds instead of two thresholds generally used by techniques like that in Canny. The selected method solves multiple problems perfecting the handling of errors and more real to truth results. Our aim of refining the method helps us in better edge detection in images with low contrast as well as medical images like MRIs and X-rays.
{"title":"Improved Edge Detection Approach to Tackle Edge Thickness and Better Edge Connectivity","authors":"Yatharth Saxena, Nirdesh Mishra, M. Sameer, Pankaj Dahiya","doi":"10.1109/CONIT55038.2022.9848285","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848285","url":null,"abstract":"Edge detection is substantial in helping us to pre-process any image for various applications from helping us to detect objects to detecting various medical conditions. The paper tackled one major shortcoming with the currently present system which is edge thickness. To improve there is an implementation of multiple thresholds instead of two thresholds generally used by techniques like that in Canny. The selected method solves multiple problems perfecting the handling of errors and more real to truth results. Our aim of refining the method helps us in better edge detection in images with low contrast as well as medical images like MRIs and X-rays.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122242648","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848020
A. Chavan, Alok Sahu, Apparna A. Junnarkar
In like manner, the objective of this exploration study is to foster a proficient trust-based security answer for dynamic range detecting in CR-MANETs. Our proposed answer for working on the exhibition of CR-MANETs within the sight of attacks, for example, SSDF and ISSDF is depicted exhaustively in the accompanying area. The primary component of the interaction includes the improvement of SSDF and ISSDF assaults for use in CR-MANETs. Second, the writing survey and recognizable proof of worries connected with the security of CR-MANETs against different sorts of attacks. In the accompanying area, we propose a one of a kind trust-based worldview that can improve the inadequacies of existing methodologies while likewise safeguarding CR-MANETs from SSDF and ISSDF attacks. Leading a presentation examination to demonstrate the adequacy of the proposed model was the last advance in characterizing the review results. We are endeavoring to assemble a trust-based framework in which the trust of PU and SU will be estimated in light of their development designs and different measurements like energy utilization and creation. Alongside a setting mindful circulated trust procedure, the structure is based on a versatility mindful answer for energy proficient SSDF and ISSDF assault location, as well as a setting mindful disseminated trust technique. With the assistance of PU missing and present settings, the SU hubs analyze the dependability of their associations with each other. They will then, at that point, mention objective facts from each other while considering the versatility and energy upsides of SUs.
{"title":"Context-aware Secure Spectrum Sensing for Cognitive Radio Networks","authors":"A. Chavan, Alok Sahu, Apparna A. Junnarkar","doi":"10.1109/CONIT55038.2022.9848020","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848020","url":null,"abstract":"In like manner, the objective of this exploration study is to foster a proficient trust-based security answer for dynamic range detecting in CR-MANETs. Our proposed answer for working on the exhibition of CR-MANETs within the sight of attacks, for example, SSDF and ISSDF is depicted exhaustively in the accompanying area. The primary component of the interaction includes the improvement of SSDF and ISSDF assaults for use in CR-MANETs. Second, the writing survey and recognizable proof of worries connected with the security of CR-MANETs against different sorts of attacks. In the accompanying area, we propose a one of a kind trust-based worldview that can improve the inadequacies of existing methodologies while likewise safeguarding CR-MANETs from SSDF and ISSDF attacks. Leading a presentation examination to demonstrate the adequacy of the proposed model was the last advance in characterizing the review results. We are endeavoring to assemble a trust-based framework in which the trust of PU and SU will be estimated in light of their development designs and different measurements like energy utilization and creation. Alongside a setting mindful circulated trust procedure, the structure is based on a versatility mindful answer for energy proficient SSDF and ISSDF assault location, as well as a setting mindful disseminated trust technique. With the assistance of PU missing and present settings, the SU hubs analyze the dependability of their associations with each other. They will then, at that point, mention objective facts from each other while considering the versatility and energy upsides of SUs.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128413482","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848119
S.Rakesh Kumar, Shashank Swaroop
Brain tumor is one of life threatening diseases for humans and the treatment is challenging. Recently the disease diagnosis industry is seeing enormous developments. Brain tumors can be identified from Magnetic Resonance Imaging (MRI) images. There are existing techniques available for brain tumor detection using image processing techniques. Some recent studies used machine learning approaches for brain tumor detection. However, an effective model and application is required for this life threatening disease. Availability of dataset is an added advantage for these studies. Nowadays, large amounts of data can be preserved for research and these can be used effectively by deep learning models. Disease diagnosis through deep learning techniques are emerging these days. In this paper, brain tumor detection is proposed through a deep learning model, Convolutional Neural Network (CNN). Deep learning models are achieving good results on brain tumor detection. In this work, an application is proposed, in which users can upload the MRI image and detect whether it is a tumor or normal MRI. CNN based classification for brain tumor detection has achieved highest classification accuracy around 99.5%. Experimental results showed that high precision value 99.3% for optimized training epochs.
{"title":"An Effective Application to Identify Brain Tumor using Deep Learning Model","authors":"S.Rakesh Kumar, Shashank Swaroop","doi":"10.1109/CONIT55038.2022.9848119","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848119","url":null,"abstract":"Brain tumor is one of life threatening diseases for humans and the treatment is challenging. Recently the disease diagnosis industry is seeing enormous developments. Brain tumors can be identified from Magnetic Resonance Imaging (MRI) images. There are existing techniques available for brain tumor detection using image processing techniques. Some recent studies used machine learning approaches for brain tumor detection. However, an effective model and application is required for this life threatening disease. Availability of dataset is an added advantage for these studies. Nowadays, large amounts of data can be preserved for research and these can be used effectively by deep learning models. Disease diagnosis through deep learning techniques are emerging these days. In this paper, brain tumor detection is proposed through a deep learning model, Convolutional Neural Network (CNN). Deep learning models are achieving good results on brain tumor detection. In this work, an application is proposed, in which users can upload the MRI image and detect whether it is a tumor or normal MRI. CNN based classification for brain tumor detection has achieved highest classification accuracy around 99.5%. Experimental results showed that high precision value 99.3% for optimized training epochs.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132986501","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：