Pub Date : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848177
Suman Pokhrel, Laxmi Kanta Dahal, N. Gupta, Rijesh Shrestha, Anshul Srivastava, Akash Bhasney
A brain tumor is a collection, or mass, of abnormal cells in your brain. Your skull, which encloses your brain, is very rigid. Any growth inside such a restricted space can cause problems. Magnetic resonance imaging (MRI) is a non-invasive method for producing three-dimensional (3D) tomographic images of the human body. MRI is most often used for the detection of tumors, lesions, and other abnormalities in soft tissues, such as the brain. Clinically, radiologists qualitatively analyze films produced by MRI scanners. Brain Tumor segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual classification can result in inaccurate prediction and diagnosis. Moreover, it is an aggravating task when there is a large amount of data present to be assisted. Brain tumors have high diversity in appearance and there is a similarity between tumor and normal tissues and thus the extraction of tumor regions from images becomes unyielding. We implemented various state of the art Neural Networks like MobileN etV2, MobileNetV3 small, MobileNetV3 large, VGG16, VGG19 and our Custom CNN model. Among these models CNN was able to get the Highest amount of accuracy. Our proposed method consists of a Convolutional Neural Network (CNN) (which is implemented using Keras and Tensor flow) that is integrated to a full featured cross-platform desktop application(which is implemented using PyQt5 and MariaDB) that can be easily used in hospitals as well as local clinics. The main aim of this project is to distinguish between normal and abnormal pixels, and classify a tumor affected brain using real-world datasets.
{"title":"Brain Tumor Detection Application Based On Convolutional Neural Network","authors":"Suman Pokhrel, Laxmi Kanta Dahal, N. Gupta, Rijesh Shrestha, Anshul Srivastava, Akash Bhasney","doi":"10.1109/CONIT55038.2022.9848177","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848177","url":null,"abstract":"A brain tumor is a collection, or mass, of abnormal cells in your brain. Your skull, which encloses your brain, is very rigid. Any growth inside such a restricted space can cause problems. Magnetic resonance imaging (MRI) is a non-invasive method for producing three-dimensional (3D) tomographic images of the human body. MRI is most often used for the detection of tumors, lesions, and other abnormalities in soft tissues, such as the brain. Clinically, radiologists qualitatively analyze films produced by MRI scanners. Brain Tumor segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual classification can result in inaccurate prediction and diagnosis. Moreover, it is an aggravating task when there is a large amount of data present to be assisted. Brain tumors have high diversity in appearance and there is a similarity between tumor and normal tissues and thus the extraction of tumor regions from images becomes unyielding. We implemented various state of the art Neural Networks like MobileN etV2, MobileNetV3 small, MobileNetV3 large, VGG16, VGG19 and our Custom CNN model. Among these models CNN was able to get the Highest amount of accuracy. Our proposed method consists of a Convolutional Neural Network (CNN) (which is implemented using Keras and Tensor flow) that is integrated to a full featured cross-platform desktop application(which is implemented using PyQt5 and MariaDB) that can be easily used in hospitals as well as local clinics. The main aim of this project is to distinguish between normal and abnormal pixels, and classify a tumor affected brain using real-world datasets.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"242 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":"114145394","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/CONIT55038.2022.9847738
P. B. Niranjane, S. Amdani
In directed and weighted graph, with n nodes and m edges, the K-shortest paths problem involve finding a set of k shortest paths between a defined source and destination pair where the first path is shortest, and the remaining k-1 paths are in increasing lengths. In K-shortest path problem there are two classes, k shortest simple path problem and k shortest non-simple path problem. The first algorithm to solve K shortest simple path problems is Yen's algorithm based on deviation path concept. Later many variants of Yen's algorithm are proposed with improved computational performance. In this paper some of the variants of Yen's algorithm for finding top k simple shortest path are studied and compared.
{"title":"Comparison of Variants of Yen's Algorithm for Finding K-Simple Shortest Paths","authors":"P. B. Niranjane, S. Amdani","doi":"10.1109/CONIT55038.2022.9847738","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847738","url":null,"abstract":"In directed and weighted graph, with n nodes and m edges, the K-shortest paths problem involve finding a set of k shortest paths between a defined source and destination pair where the first path is shortest, and the remaining k-1 paths are in increasing lengths. In K-shortest path problem there are two classes, k shortest simple path problem and k shortest non-simple path problem. The first algorithm to solve K shortest simple path problems is Yen's algorithm based on deviation path concept. Later many variants of Yen's algorithm are proposed with improved computational performance. In this paper some of the variants of Yen's algorithm for finding top k simple shortest path are studied and compared.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"71 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":"114165066","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/CONIT55038.2022.9847725
S. Bhatlawande, S. Shilaskar, Mohit Agrawal, Varad Ashtekar, Mahesh Badade, Shwetambari Belote, Jyoti Madake
Numerous studies in the field of object detection have been conducted over the past few decades. Several effective methods have been developed. Among various object detection algorithms, Faster RCNN offers excellent results in both detection speed and accuracy. It is a combination of Fast RCNN and RPN layers. This paper conducts a comparative study of object detection using Faster RCNN. The study shows that use of smaller convolutional network called Region Proposal Network improves performance of the system. It shows that object detection using Faster RCNN can give high accuracy and faster performance as compared to other methods and algorithms. It takes only 0.2 seconds to predict a single image. Also, it gives 70% Mean Accuracy Precision (mAP) on the PASCAL VOC 2007 and PASCAL VOC 2012 datasets.
{"title":"Study of Object Detection with Faster RCNN","authors":"S. Bhatlawande, S. Shilaskar, Mohit Agrawal, Varad Ashtekar, Mahesh Badade, Shwetambari Belote, Jyoti Madake","doi":"10.1109/CONIT55038.2022.9847725","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847725","url":null,"abstract":"Numerous studies in the field of object detection have been conducted over the past few decades. Several effective methods have been developed. Among various object detection algorithms, Faster RCNN offers excellent results in both detection speed and accuracy. It is a combination of Fast RCNN and RPN layers. This paper conducts a comparative study of object detection using Faster RCNN. The study shows that use of smaller convolutional network called Region Proposal Network improves performance of the system. It shows that object detection using Faster RCNN can give high accuracy and faster performance as compared to other methods and algorithms. It takes only 0.2 seconds to predict a single image. Also, it gives 70% Mean Accuracy Precision (mAP) on the PASCAL VOC 2007 and PASCAL VOC 2012 datasets.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"7 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":"114348066","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/CONIT55038.2022.9847816
Nirzari Vora, Siddharth Joshi, Darshan Patel
In today's time, fuel price and shortage of conventional sources like coal are the biggest concern worldwide. Henceforth, world is moving towards adapting green energy i.e. renewable energy for the production of the electricity. Renewable sources are available in nature. One can harness in the forms of the solar energy, the wind energy, the tidal energy, the biomass energy, the geothermal energy etc. These sources are environment friendly and clean to use to produce electricity. One issue which has to be addressed while using these sources is that they are weather and location dependent. So reliability on these sources alone is less which leads to combining other source, be it conventional or other renewable sources. This combination of two or more sources to generate power is called hybrid system and in this paper, we are considering PVES (Photo-Voltaic Energy System) as main source and BESS (Battery Energy Storage System) for storage purpose. The simulations studies and analysis for the parallel & standalone Operation of PVES and BESS is performed and proposed in this paper. The system is used for the DC microgrid applications. The MATLAB simulation analysis is done by varying climatic conditions i.e. change in insolation and change in temperature.
{"title":"Analysis of the Parallel & Standalone Operation of PVES and BESS for Microgrid Applications with Varying Climatic Condition","authors":"Nirzari Vora, Siddharth Joshi, Darshan Patel","doi":"10.1109/CONIT55038.2022.9847816","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847816","url":null,"abstract":"In today's time, fuel price and shortage of conventional sources like coal are the biggest concern worldwide. Henceforth, world is moving towards adapting green energy i.e. renewable energy for the production of the electricity. Renewable sources are available in nature. One can harness in the forms of the solar energy, the wind energy, the tidal energy, the biomass energy, the geothermal energy etc. These sources are environment friendly and clean to use to produce electricity. One issue which has to be addressed while using these sources is that they are weather and location dependent. So reliability on these sources alone is less which leads to combining other source, be it conventional or other renewable sources. This combination of two or more sources to generate power is called hybrid system and in this paper, we are considering PVES (Photo-Voltaic Energy System) as main source and BESS (Battery Energy Storage System) for storage purpose. The simulations studies and analysis for the parallel & standalone Operation of PVES and BESS is performed and proposed in this paper. The system is used for the DC microgrid applications. The MATLAB simulation analysis is done by varying climatic conditions i.e. change in insolation and change in temperature.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"49 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":"117054203","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}
In-vehicle Human-Machine Interface (HMI) plays a significant role for conditionally automated vehicles in realizing effective communications from driving automation systems to drivers during either automated driving period or control transitions. The present study aimed to investigate the effects of in-vehicle HMI on drivers' eye-tracking characteristics pre and post takeover request (TOR). A driving simulator-based experiment was conducted comparing the differences of drivers' visual behaviors with or without HMI under two TB (time budget) conditions (TB = 4 s; TB = 10 s). The visual HMI adopted in the experiments consisted of vehicle status display and a bird-view depiction of the traffic situation. Experiment results showed fixations prior to the TOR were more frequently shifted from real traffic situation to HMI which was effective in indirectly maintaining drivers' mode and situation awareness. Pre TOR entropy measures indicated a more dispersed but still ordered scanning pattern in spatial sampling. Saccadic behaviors were shown to be encouraged for a less cognitively demanded but a more visually loaded acquisition of surrounding information with the assistance of HMI. Post TOR fixation measure showed a prolonged Eyes-on-Traffic-Time (EoTT) when HMI was provided. And as a physiological indicator for mental workload, blink rate and blink latency did not show an additional increase after the issue of TOR under “with HMI” condition. We conclude that the introduction of in-vehicle visual HMI can be a valid option to support drivers in both automated driving and takeover time.
{"title":"Research on the Effects of in-Vehicle Human-Machine Interface on Drivers' Pre and Post Takeover Request Eye-tracking Characteristics","authors":"Weimin Liu, Qingkun Li, Zhenyuan Wang, Wenjun Wang, Chao Zeng, Bo Cheng","doi":"10.1109/CONIT55038.2022.9848040","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848040","url":null,"abstract":"In-vehicle Human-Machine Interface (HMI) plays a significant role for conditionally automated vehicles in realizing effective communications from driving automation systems to drivers during either automated driving period or control transitions. The present study aimed to investigate the effects of in-vehicle HMI on drivers' eye-tracking characteristics pre and post takeover request (TOR). A driving simulator-based experiment was conducted comparing the differences of drivers' visual behaviors with or without HMI under two TB (time budget) conditions (TB = 4 s; TB = 10 s). The visual HMI adopted in the experiments consisted of vehicle status display and a bird-view depiction of the traffic situation. Experiment results showed fixations prior to the TOR were more frequently shifted from real traffic situation to HMI which was effective in indirectly maintaining drivers' mode and situation awareness. Pre TOR entropy measures indicated a more dispersed but still ordered scanning pattern in spatial sampling. Saccadic behaviors were shown to be encouraged for a less cognitively demanded but a more visually loaded acquisition of surrounding information with the assistance of HMI. Post TOR fixation measure showed a prolonged Eyes-on-Traffic-Time (EoTT) when HMI was provided. And as a physiological indicator for mental workload, blink rate and blink latency did not show an additional increase after the issue of TOR under “with HMI” condition. We conclude that the introduction of in-vehicle visual HMI can be a valid option to support drivers in both automated driving and takeover time.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"421 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":"116169778","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/CONIT55038.2022.9848131
Rituparna Sinha, Rajat K. Pal, R. K. De
Massively parallel sequencers have enabled genome sequences to be available at a very low cost and price, which opened huge scope on analyzing human genome sequences from different perspectives, thereby the association of diseases with genetic alterations gets further enlightened. However, the sequencing process and alignment of NGS technology based short reads suffer from various sequencing biases which needs to be addressed. In this work, the mappability bias occurring with respect to repeat rich regions of the DNA have been addressed in a novel approach. A model has been designed which considers all non-uniquely mapped reads and performs a pipeline of computations to allocate the reads to an optimal location, due to which the precise detection of breakpoints in the region of duplications and deletions are obtained. In addition, the application of this model for mappability bias correction, prior to the detection of structurally altered regions of the genome, leads to a better sensitivity value.
{"title":"A Model for Optimal Assignment of Non-Uniquely Mapped NGS Reads in DNA Regions of Duplications or Deletions","authors":"Rituparna Sinha, Rajat K. Pal, R. K. De","doi":"10.1109/CONIT55038.2022.9848131","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848131","url":null,"abstract":"Massively parallel sequencers have enabled genome sequences to be available at a very low cost and price, which opened huge scope on analyzing human genome sequences from different perspectives, thereby the association of diseases with genetic alterations gets further enlightened. However, the sequencing process and alignment of NGS technology based short reads suffer from various sequencing biases which needs to be addressed. In this work, the mappability bias occurring with respect to repeat rich regions of the DNA have been addressed in a novel approach. A model has been designed which considers all non-uniquely mapped reads and performs a pipeline of computations to allocate the reads to an optimal location, due to which the precise detection of breakpoints in the region of duplications and deletions are obtained. In addition, the application of this model for mappability bias correction, prior to the detection of structurally altered regions of the genome, leads to a better sensitivity value.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"136 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":"124607571","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/CONIT55038.2022.9847791
Ashish Kumar, Sudhanshu K. Mishra, Ayush Kejriwal
In this paper, the relationship between COVID-19 Maximum Infection Rate (MIR) and the happiness indicators has been investigated for the prediction of Happiness Score of Countries using Random Forest (RF) algorithm. The per-formance of the proposed algorithm is also compared against five other algorithms such as Linear Regression (LR), Ada Boost Classifier (ABC), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (NB) and Logistic Regression. The comparison of performance includes parameters like training accuracy, testing accuracy and computation time. It is clear from the observation that the proposed approach is superior to others. Then the parameters like MAE, MSE, RMSE, R2 Score, Adjusted R2 Score is calculated. This proposed algorithm can be used for other classification and regression work involving large amount of data with missing values like COVID- 19 datasets.
{"title":"Prediction of Happiness Score of Countries by Considering Maximum Infection Rate of People by COVID-19 using Random Forest Algorithm","authors":"Ashish Kumar, Sudhanshu K. Mishra, Ayush Kejriwal","doi":"10.1109/CONIT55038.2022.9847791","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847791","url":null,"abstract":"In this paper, the relationship between COVID-19 Maximum Infection Rate (MIR) and the happiness indicators has been investigated for the prediction of Happiness Score of Countries using Random Forest (RF) algorithm. The per-formance of the proposed algorithm is also compared against five other algorithms such as Linear Regression (LR), Ada Boost Classifier (ABC), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (NB) and Logistic Regression. The comparison of performance includes parameters like training accuracy, testing accuracy and computation time. It is clear from the observation that the proposed approach is superior to others. Then the parameters like MAE, MSE, RMSE, R2 Score, Adjusted R2 Score is calculated. This proposed algorithm can be used for other classification and regression work involving large amount of data with missing values like COVID- 19 datasets.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"4 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":"124929079","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/CONIT55038.2022.9848014
Mukul Soni, Mayank Singhal, Jatin, R. Katarya
Owing to ongoing rapid developments in network related technologies combined with the great surge in their usage, the methodologies for cyber-attacks like intrusions are also constantly modernizing leading to a greater rate of accuracy, effect and frequency of such network-related issues. In this research exercise, we establish an innovative and efficient methodology for Deep Learning-based solutions for Intrusion detection. To establish this, we propose a Deep Neural Network (DNN) trained by an Enhanced Artificial Bee Colony Algorithm for efficient and accurate intrusion detection over wireless and interconnected environments. This research effort constitutes a holistic and comparative analysis of the complete functionality and technicality of the proposed system. The proposed model performed much better than many other state-of-the-art models. Furthermore, the comprehensive explanation provided by this research can be leveraged into the development of more precocious and modern Intrusion Detection System.
{"title":"Optimizing Deep Neural Network using Enhanced Artificial Bee Colony Algorithm for an Efficient Intrusion Detection System","authors":"Mukul Soni, Mayank Singhal, Jatin, R. Katarya","doi":"10.1109/CONIT55038.2022.9848014","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848014","url":null,"abstract":"Owing to ongoing rapid developments in network related technologies combined with the great surge in their usage, the methodologies for cyber-attacks like intrusions are also constantly modernizing leading to a greater rate of accuracy, effect and frequency of such network-related issues. In this research exercise, we establish an innovative and efficient methodology for Deep Learning-based solutions for Intrusion detection. To establish this, we propose a Deep Neural Network (DNN) trained by an Enhanced Artificial Bee Colony Algorithm for efficient and accurate intrusion detection over wireless and interconnected environments. This research effort constitutes a holistic and comparative analysis of the complete functionality and technicality of the proposed system. The proposed model performed much better than many other state-of-the-art models. Furthermore, the comprehensive explanation provided by this research can be leveraged into the development of more precocious and modern Intrusion Detection System.","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":"125043863","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/CONIT55038.2022.9848137
Disha D N, S. S., Sharada U. Shenoy, Sudesh Rao
bipolar disorder may be an advanced disorder that affects variant individuals across the world. We assume that with the utilization of huge information with machine learning we will facilitate every patient as well as doctors to perform a much better designation of this sickness. Paper aims to use different Machine learning algorithms to predict the variants of bipolar disorder. The prediction model would help the psychiatrists fordiagnosing whether the patients are having a depression or mania episode, or staying in an exceedingly euthymic state. It also aims at developing a prophetic model with an appropriate level of confidence, it's essential to own each associate understanding of the information that's getting used and also thetheory relating to every algorithmic rule that's applied, similarly as having enough information for the algorithms to figure with.
{"title":"Prediction of Bipolar Disorder Using Machine Learning Techniques","authors":"Disha D N, S. S., Sharada U. Shenoy, Sudesh Rao","doi":"10.1109/CONIT55038.2022.9848137","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848137","url":null,"abstract":"bipolar disorder may be an advanced disorder that affects variant individuals across the world. We assume that with the utilization of huge information with machine learning we will facilitate every patient as well as doctors to perform a much better designation of this sickness. Paper aims to use different Machine learning algorithms to predict the variants of bipolar disorder. The prediction model would help the psychiatrists fordiagnosing whether the patients are having a depression or mania episode, or staying in an exceedingly euthymic state. It also aims at developing a prophetic model with an appropriate level of confidence, it's essential to own each associate understanding of the information that's getting used and also thetheory relating to every algorithmic rule that's applied, similarly as having enough information for the algorithms to figure with.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"52 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":"123651346","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/CONIT55038.2022.9847880
S. Selvi, Nikhil Agarwal, Paarth Barkur, Yash Mishra, Abhsihek Kumar
The prediction of future development of a natural phenomenon is one of the main objectives of recent technology, but this is a great challenge when dealing with an epidemic or pandemic. This proved to be particularly true in the case of Covid-19 global pandemic that the world is suffering and facing since January 2020. The response to the virus infection are partially known, however the immune system is mostly affected especially in patients with pre-existing respiratory or systemic diseases. Most infections by coronavirus are mild and self-treated. Therefore, in early stages of the disease, it will be misleading to estimate the real spread of the virus based on the reports of hospital. Moreover, such reports vary according to how measurements are performed, and the number of tests related only to the number of symptomatic patients. Despite all this, the large amount of official data published in last months, and updated daily has motivated various mathematical models, which are required to predict the evolution of an epidemic and plan effective control strategies. Due to the incompleteness of the data and intrinsic complexity, predicting the evolution, the peak or the end of the pandemic is a challenge. In this paper, a deep learning based approach is proposed aiming to evaluate a-priori risk of an epidemic caused by Covid-19. The proposed algorithm leverages image processing and deep learning algorithms to detect Covid and differentiate between normal, Covid affected, lung opacity and viral pneumonia affected chest x-rays. This results in setting strategies to prevent or decrease the impact of future epidemic waves. The accuracy for the proposed algorithm is 95.01% and Recall is 98.5% on validation data. The inference is that combining image processing with deep learning can improve performance of Covid detection.
{"title":"A Novel Deep Learning Algorithm for Covid Detection and Classification","authors":"S. Selvi, Nikhil Agarwal, Paarth Barkur, Yash Mishra, Abhsihek Kumar","doi":"10.1109/CONIT55038.2022.9847880","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847880","url":null,"abstract":"The prediction of future development of a natural phenomenon is one of the main objectives of recent technology, but this is a great challenge when dealing with an epidemic or pandemic. This proved to be particularly true in the case of Covid-19 global pandemic that the world is suffering and facing since January 2020. The response to the virus infection are partially known, however the immune system is mostly affected especially in patients with pre-existing respiratory or systemic diseases. Most infections by coronavirus are mild and self-treated. Therefore, in early stages of the disease, it will be misleading to estimate the real spread of the virus based on the reports of hospital. Moreover, such reports vary according to how measurements are performed, and the number of tests related only to the number of symptomatic patients. Despite all this, the large amount of official data published in last months, and updated daily has motivated various mathematical models, which are required to predict the evolution of an epidemic and plan effective control strategies. Due to the incompleteness of the data and intrinsic complexity, predicting the evolution, the peak or the end of the pandemic is a challenge. In this paper, a deep learning based approach is proposed aiming to evaluate a-priori risk of an epidemic caused by Covid-19. The proposed algorithm leverages image processing and deep learning algorithms to detect Covid and differentiate between normal, Covid affected, lung opacity and viral pneumonia affected chest x-rays. This results in setting strategies to prevent or decrease the impact of future epidemic waves. The accuracy for the proposed algorithm is 95.01% and Recall is 98.5% on validation data. The inference is that combining image processing with deep learning can improve performance of Covid detection.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"24 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":"122147999","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：