Pub Date : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332165
Sudeep D. Thepade, Mrunal E. Idhate
The image took in the dark light has low contrast, which affects the clarity of details in it. This results in the loss of information and details in poorly illuminated images. Such images are not suitable for computer vision analysis and observations. In many places, images taken in the dark light like CCTV images at night, military, satellite images, medical images, etc. Several methods proposed for contrast enhancement of low light (darker) images like histogram equalization, bright channel prior, camera response model, and robust retinex model. The contrast enhancement gone using existing methods have some limitations like getting blurring effect, getting over the brightening of details. To overcome these disadvantages, the paper proposes the contrast enhancement of darker images with the weighted blending of bright channel prior (BCR) and robust retinex model (RRM) with different assigned weights. For the performance evaluation of the variations of the proposed method, the image entropy value is computed. From the experimentation done on images from the ExDark dataset, it observed that the proposed weighted blending based contrast enhancement method gives better performance over existing BCR and RRM.
{"title":"Contrast Enhancement of Dark Images using Weighted Blending of Bright Channel Prior and Robust Retinex Method","authors":"Sudeep D. Thepade, Mrunal E. Idhate","doi":"10.1109/IBSSC51096.2020.9332165","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332165","url":null,"abstract":"The image took in the dark light has low contrast, which affects the clarity of details in it. This results in the loss of information and details in poorly illuminated images. Such images are not suitable for computer vision analysis and observations. In many places, images taken in the dark light like CCTV images at night, military, satellite images, medical images, etc. Several methods proposed for contrast enhancement of low light (darker) images like histogram equalization, bright channel prior, camera response model, and robust retinex model. The contrast enhancement gone using existing methods have some limitations like getting blurring effect, getting over the brightening of details. To overcome these disadvantages, the paper proposes the contrast enhancement of darker images with the weighted blending of bright channel prior (BCR) and robust retinex model (RRM) with different assigned weights. For the performance evaluation of the variations of the proposed method, the image entropy value is computed. From the experimentation done on images from the ExDark dataset, it observed that the proposed weighted blending based contrast enhancement method gives better performance over existing BCR and RRM.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115185133","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332174
L. S. B. Pereira, R. Rodrigues, E. A. C. Neto
The volume of data collected in the industry has grown rapidly in recent years, transforming into a challenge the task of analyzing this data. To identify patterns and improve industrial processes, several Artificial Intelligence techniques can be used, especially clustering methods. This work applies the technique of clustering and dimensionality reduction in the mining industry, performing a case study in a public database about an iron mining flotation process. The K-means algorithm was used and it was able to identify a statistically significant difference between the clusters in the silica concentration value, an important impurity in the flotation process.
{"title":"Unsupervised machine learning in industrial applications: a case study in iron mining","authors":"L. S. B. Pereira, R. Rodrigues, E. A. C. Neto","doi":"10.1109/IBSSC51096.2020.9332174","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332174","url":null,"abstract":"The volume of data collected in the industry has grown rapidly in recent years, transforming into a challenge the task of analyzing this data. To identify patterns and improve industrial processes, several Artificial Intelligence techniques can be used, especially clustering methods. This work applies the technique of clustering and dimensionality reduction in the mining industry, performing a case study in a public database about an iron mining flotation process. The K-means algorithm was used and it was able to identify a statistically significant difference between the clusters in the silica concentration value, an important impurity in the flotation process.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114704105","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332185
Jaineel Shah, Prafful Javare, Divya Khetan
These days, crypto-currency is getting popular in society. Many people around the globe are using these coins for transactions. This world of crypto-currency works on the principle of exchange between different cryptocurrencies. It is observed that while exchanging currencies, we often get less amount of money compared to what we hope for, as exchange rates are volatile, and they increase if a considerable amount is exchanged. This phenomenon of the exchange rate dropping, when the exchange amount increases is called slippage. To solve this problem, we propose a novel application/API - Slipswap. In this work, we propose a web application “SlipSwap” that takes the input value of one currency and gives an optimal way to exchange so that the user loses the least amount of money. There is no such tool available, which helps users save a significant amount of money. Further, the proposed tool can be used as an API and can be integrated with different platforms.
{"title":"SlipSwap: Reduce the slippage that is incurred during the swap of tokens using Algorithmic analysis","authors":"Jaineel Shah, Prafful Javare, Divya Khetan","doi":"10.1109/IBSSC51096.2020.9332185","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332185","url":null,"abstract":"These days, crypto-currency is getting popular in society. Many people around the globe are using these coins for transactions. This world of crypto-currency works on the principle of exchange between different cryptocurrencies. It is observed that while exchanging currencies, we often get less amount of money compared to what we hope for, as exchange rates are volatile, and they increase if a considerable amount is exchanged. This phenomenon of the exchange rate dropping, when the exchange amount increases is called slippage. To solve this problem, we propose a novel application/API - Slipswap. In this work, we propose a web application “SlipSwap” that takes the input value of one currency and gives an optimal way to exchange so that the user loses the least amount of money. There is no such tool available, which helps users save a significant amount of money. Further, the proposed tool can be used as an API and can be integrated with different platforms.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131688566","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332157
Prashanth Kannadaguli
This work is related to building a Human Detection system based on Fully Connected One Shot (FCOS). It is one of the most recent Deep Learning approaches primitively built using single shot detection proposal. Unlike the double stage region-based object detection schemes this technique do not follow semantic segmentation, it does not undergo loss of the object information such as disappearance of the gradients and it does not require pre-defined anchors. This technique comprises strong feature extractors and reinforce multi scale object detection and it is very quick in the multithreaded GPU environments. Since our fundamental research is concentrated on object classification related to Unmanned Aerial Vehicle (UAV) applications, as a first step we choose to detect the humans from thermal dataset. Therefore, we used thermal images and videos possessed from thermal cameras of UAV lm to 50m above ground level as our dataset in building the model and testing. The FCOS extracts the features of an object using its efficient per-pixel fashion. Finally, the performance analysis of these model in terms of mean Average Precision (mAP) indicates that the modelling using FCOS performs in a promising way and it can be used in automatic human detection systems.
{"title":"FCOS Based Human Detection System Using Thermal Imaging for UAV Based Surveillance Applications","authors":"Prashanth Kannadaguli","doi":"10.1109/IBSSC51096.2020.9332157","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332157","url":null,"abstract":"This work is related to building a Human Detection system based on Fully Connected One Shot (FCOS). It is one of the most recent Deep Learning approaches primitively built using single shot detection proposal. Unlike the double stage region-based object detection schemes this technique do not follow semantic segmentation, it does not undergo loss of the object information such as disappearance of the gradients and it does not require pre-defined anchors. This technique comprises strong feature extractors and reinforce multi scale object detection and it is very quick in the multithreaded GPU environments. Since our fundamental research is concentrated on object classification related to Unmanned Aerial Vehicle (UAV) applications, as a first step we choose to detect the humans from thermal dataset. Therefore, we used thermal images and videos possessed from thermal cameras of UAV lm to 50m above ground level as our dataset in building the model and testing. The FCOS extracts the features of an object using its efficient per-pixel fashion. Finally, the performance analysis of these model in terms of mean Average Precision (mAP) indicates that the modelling using FCOS performs in a promising way and it can be used in automatic human detection systems.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131135396","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332164
Jai Mangal
This paper contemplates potential outcomes to develop an adaptable, lightweight and precisely vigorous RFID reader for the applications over the microwave frequency range of 5.8 GHz. The dimensions of the proposed antenna are 20mm$times$ 18mm$times$ 1.6mm. Two annular slots were inserted in the patch to reduce the dimensions of the antenna which results in the formation of horn structure along with the circular patch. The patch antenna is fabricated over the surface called FR-4 epoxy. The ground plane of the antenna is made partial like open cone structure. This help antenna to achieve high gain along with the annular slots and reduced dimensions. The antenna attains the reflection coefficient of -21.97 dB at 5.8 GHz. The proposed antenna achieves the peak gain of 2.97 dBi at 6.2 GHz. The efficiency of the antenna comes out to be 63.97% at 5.8 GHz and it increases with increase in the frequency. The innovated antenna arrangements permit coordination with portable RFID application devices.
{"title":"RFID Reader with Miniaturized Horn Patch for Microwave Frequency Applications at 5.8 GHz","authors":"Jai Mangal","doi":"10.1109/IBSSC51096.2020.9332164","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332164","url":null,"abstract":"This paper contemplates potential outcomes to develop an adaptable, lightweight and precisely vigorous RFID reader for the applications over the microwave frequency range of 5.8 GHz. The dimensions of the proposed antenna are 20mm$times$ 18mm$times$ 1.6mm. Two annular slots were inserted in the patch to reduce the dimensions of the antenna which results in the formation of horn structure along with the circular patch. The patch antenna is fabricated over the surface called FR-4 epoxy. The ground plane of the antenna is made partial like open cone structure. This help antenna to achieve high gain along with the annular slots and reduced dimensions. The antenna attains the reflection coefficient of -21.97 dB at 5.8 GHz. The proposed antenna achieves the peak gain of 2.97 dBi at 6.2 GHz. The efficiency of the antenna comes out to be 63.97% at 5.8 GHz and it increases with increase in the frequency. The innovated antenna arrangements permit coordination with portable RFID application devices.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129590768","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332160
Sudeep D. Thepade, P. Chaudhari, M. Dindorkar, S. Bang
The outbreak of the novel Coronavirus has caused catastrophic consequences on the entire global economy leading to a huge loss of health and wealth. Mankind has suffered a lot due to this pandemic. Large number of screening tests are performed on the suspected individuals by using Covid-19 test kits. As the rate of spread of this disease is increasing exponentially, medical organizations are finding it difficult to screen the suspected cases due to limited availability of test kits. Early diagnosis of coronavirus infection can be made from chest X-ray images of an individual. Current paper proposes a color space based global texture feature extraction method to identify covid19 infected cases. Luminance Chroma features of chest X-ray images are extracted from YCrCb, Kekre-LUV, and CIE-LUV color spaces. These extracted features are used for training different machine learning classifiers and ensembles to perform 3-class classification as covid19, pneumonia, and normal. Results computed at 10-fold cross-validation show that ensembles perform better than the individual machine learning (ML) classifiers. Performance of the proposed method is calibrated on an open-source dataset: Covid19 by considering Accuracy, Positive predicted value (PPV), Sensitivity (Recall), F Measure, and Matthew’s correlation coefficient (MCC) performance measures.
{"title":"Covid19 Identification using Machine Learning Classifiers with Histogram of Luminance Chroma Features of Chest X-ray images","authors":"Sudeep D. Thepade, P. Chaudhari, M. Dindorkar, S. Bang","doi":"10.1109/IBSSC51096.2020.9332160","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332160","url":null,"abstract":"The outbreak of the novel Coronavirus has caused catastrophic consequences on the entire global economy leading to a huge loss of health and wealth. Mankind has suffered a lot due to this pandemic. Large number of screening tests are performed on the suspected individuals by using Covid-19 test kits. As the rate of spread of this disease is increasing exponentially, medical organizations are finding it difficult to screen the suspected cases due to limited availability of test kits. Early diagnosis of coronavirus infection can be made from chest X-ray images of an individual. Current paper proposes a color space based global texture feature extraction method to identify covid19 infected cases. Luminance Chroma features of chest X-ray images are extracted from YCrCb, Kekre-LUV, and CIE-LUV color spaces. These extracted features are used for training different machine learning classifiers and ensembles to perform 3-class classification as covid19, pneumonia, and normal. Results computed at 10-fold cross-validation show that ensembles perform better than the individual machine learning (ML) classifiers. Performance of the proposed method is calibrated on an open-source dataset: Covid19 by considering Accuracy, Positive predicted value (PPV), Sensitivity (Recall), F Measure, and Matthew’s correlation coefficient (MCC) performance measures.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125651035","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332208
O. Vaidya, S. Gandhe, Abhishek Sharma, Asit Bhate, Vishal Bhosale, Rushabh Mahale
According to World Health Organization (WHO), the 5% of world’s population is disabled of speaking and hearing. That makes a large number of people who are deaf and mute in whole world and communications between deaf-mute and a normal person has always been a challenging task. We have developed a cheap, reliable and efficient device that would help deaf-mute people to work with other normal people efficiently towards the development of humanity. In this paper, 3-D accelerometer is used to detect the gesture of disable person and based on it customized database is generated which is processed through nodeMCU and Raspberry Pi and displayed the message on LCD screen. The Support Vector Classifier algorithm is used in proposed system. The experimental analysis gives comparison of proposed system with existing machine learning algorithm and shows that our system outperforms well in terms of translating complete sentence instead of single alphabet which resulted into increased accuracy of device.
{"title":"Design and Development of Hand Gesture based Communication Device for Deaf and Mute People","authors":"O. Vaidya, S. Gandhe, Abhishek Sharma, Asit Bhate, Vishal Bhosale, Rushabh Mahale","doi":"10.1109/IBSSC51096.2020.9332208","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332208","url":null,"abstract":"According to World Health Organization (WHO), the 5% of world’s population is disabled of speaking and hearing. That makes a large number of people who are deaf and mute in whole world and communications between deaf-mute and a normal person has always been a challenging task. We have developed a cheap, reliable and efficient device that would help deaf-mute people to work with other normal people efficiently towards the development of humanity. In this paper, 3-D accelerometer is used to detect the gesture of disable person and based on it customized database is generated which is processed through nodeMCU and Raspberry Pi and displayed the message on LCD screen. The Support Vector Classifier algorithm is used in proposed system. The experimental analysis gives comparison of proposed system with existing machine learning algorithm and shows that our system outperforms well in terms of translating complete sentence instead of single alphabet which resulted into increased accuracy of device.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122277395","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332217
Sudeep D. Thepade, Akshay Shirbhate
Images captured under poor illumination or at night time doesn’t have significant details as compared to images captured under proper lighting conditions. These images, when used for computer vision applications might be the reason for undesirable output. So, these kinds of images are not suitable for observation and analysis is case of any computer vision application. To solve this problem, visibility enhancement in low light images with weighted fusion of robust retinex model and dark channel prior based enhancement method have been proposed in the literature. The paper proposes visibility enhancement in low light images with weighted fusion of robust retinex model and dark channel prior based enhancement. The validation of proposed method is judged based on entropy. The performance based on the entropy as measure, is evaluated for proposed system and compared with the other existing popular low light image enhancement techniques. For rigorous validation, different weights combinations are explored in the proposed fusion based image enhancement method.
{"title":"Visibility Enhancement in Low Light Images with Weighted Fusion of Robust Retinex Model and Dark Channel Prior","authors":"Sudeep D. Thepade, Akshay Shirbhate","doi":"10.1109/IBSSC51096.2020.9332217","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332217","url":null,"abstract":"Images captured under poor illumination or at night time doesn’t have significant details as compared to images captured under proper lighting conditions. These images, when used for computer vision applications might be the reason for undesirable output. So, these kinds of images are not suitable for observation and analysis is case of any computer vision application. To solve this problem, visibility enhancement in low light images with weighted fusion of robust retinex model and dark channel prior based enhancement method have been proposed in the literature. The paper proposes visibility enhancement in low light images with weighted fusion of robust retinex model and dark channel prior based enhancement. The validation of proposed method is judged based on entropy. The performance based on the entropy as measure, is evaluated for proposed system and compared with the other existing popular low light image enhancement techniques. For rigorous validation, different weights combinations are explored in the proposed fusion based image enhancement method.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"73 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120897908","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332158
Sudeep D. Thepade, Ketan Jadhav
The novel corona virus caused by the SARS-CoV2 virus originated in Wuhan, China and spread globally. The massive outbreak of the virus resulted in millions of people being infected. Early detection of the virus is crucial in the complete recovery of the patient but can be fatal if detected in the later stages. The symptoms of the virus being similar to flu make it difficult to detect. This paper attempts an automated system for identification of the Covid19 virus infected images of chest X-Ray. The proposed method uses a dataset which has human chest X-Rays of non infected people as well as patients suffering from pneumonia and Covid19 virus infection. Local binary patterns with variations in its input parameters are used for feature extraction. The resulting feature sets are classified using several machine learning algorithms and ensembles of these individual models. Results of experimentation are obtained across 10 fold cross validation testing. Evaluation metrics accuracy, positive predictive value (PPV), sensitivity and f-measure are used to compare performance. Observations of the results show that the ensemble of RTree-RForest-KNN gives the best classification performance while ensemble models perform better than most individual classifiers. Comparing the input parameters of the LBP, the best performance is given by parameters R=6 (P=48) and R=7 (P=56) gives the best performance for the average of metrics for 10 fold cross validation in the proposed Covid19 identification method from chest X-Ray images.
{"title":"Covid19 Identification from Chest X-Ray Images using Local Binary Patterns with assorted Machine Learning Classifiers","authors":"Sudeep D. Thepade, Ketan Jadhav","doi":"10.1109/IBSSC51096.2020.9332158","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332158","url":null,"abstract":"The novel corona virus caused by the SARS-CoV2 virus originated in Wuhan, China and spread globally. The massive outbreak of the virus resulted in millions of people being infected. Early detection of the virus is crucial in the complete recovery of the patient but can be fatal if detected in the later stages. The symptoms of the virus being similar to flu make it difficult to detect. This paper attempts an automated system for identification of the Covid19 virus infected images of chest X-Ray. The proposed method uses a dataset which has human chest X-Rays of non infected people as well as patients suffering from pneumonia and Covid19 virus infection. Local binary patterns with variations in its input parameters are used for feature extraction. The resulting feature sets are classified using several machine learning algorithms and ensembles of these individual models. Results of experimentation are obtained across 10 fold cross validation testing. Evaluation metrics accuracy, positive predictive value (PPV), sensitivity and f-measure are used to compare performance. Observations of the results show that the ensemble of RTree-RForest-KNN gives the best classification performance while ensemble models perform better than most individual classifiers. Comparing the input parameters of the LBP, the best performance is given by parameters R=6 (P=48) and R=7 (P=56) gives the best performance for the average of metrics for 10 fold cross validation in the proposed Covid19 identification method from chest X-Ray images.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121694431","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}
Industrial pollution is one of the most serious problems faced today. Long-term exposure to air pollution causes severe health issues including respiratory and lung disorders. Presently laws regarding industrial pollution monitoring and control are not stringent enough. The working dataset includes parameters of air in terms of ambient air as well as of the stack emission. On this data, various Machine Learning (ML) algorithms were applied for prediction of emission rate, and comparative analysis is done. These algorithms were implemented using python and the mean square error of each of these was measured to check for accuracy. It was observed that among all classifiers, the Multi-layer perceptron model was seen to have the least error. The air dispersion models are then applied to the predicted emission rate to calculate the dispersion of pollutants from the source that is at the stack level.
{"title":"Air Pollution Prediction using Machine Learning","authors":"Shreyas Simu, V. Turkar, Rohit Martires, Vranda Asolkar, Swizel Monteiro, Vaylon Fernandes, Vassant Salgaoncary","doi":"10.1109/IBSSC51096.2020.9332184","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332184","url":null,"abstract":"Industrial pollution is one of the most serious problems faced today. Long-term exposure to air pollution causes severe health issues including respiratory and lung disorders. Presently laws regarding industrial pollution monitoring and control are not stringent enough. The working dataset includes parameters of air in terms of ambient air as well as of the stack emission. On this data, various Machine Learning (ML) algorithms were applied for prediction of emission rate, and comparative analysis is done. These algorithms were implemented using python and the mean square error of each of these was measured to check for accuracy. It was observed that among all classifiers, the Multi-layer perceptron model was seen to have the least error. The air dispersion models are then applied to the predicted emission rate to calculate the dispersion of pollutants from the source that is at the stack level.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"2 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133578584","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：