Pub Date : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036606
K. Huda, S. Shuvo, Kazi Abu Zilani, M. R. T. Hossain
For regulation of DC output voltage with unity power factor of AC-DC converter, a controlling procedure has been introduced in this paper which accounts for the effects of harmonics in non-linear loads. The scheme incorporates a single phase full bridge rectifier in conjunction with a PFC boost converter controlled by the fuzzy logic controller. The non-linear effects of bridge rectifier is compensated by hysteresis current control technique directed by the boost converter. The results show that the proposed controller can regulate the DC output voltage over a wide range of load and input voltage variation while making the input current sinusoidal with improved power factor.
{"title":"Power Quality Improvement with Single Phase Boost Rectifier using Fuzzy Logic Control","authors":"K. Huda, S. Shuvo, Kazi Abu Zilani, M. R. T. Hossain","doi":"10.1109/IC4ME247184.2019.9036606","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036606","url":null,"abstract":"For regulation of DC output voltage with unity power factor of AC-DC converter, a controlling procedure has been introduced in this paper which accounts for the effects of harmonics in non-linear loads. The scheme incorporates a single phase full bridge rectifier in conjunction with a PFC boost converter controlled by the fuzzy logic controller. The non-linear effects of bridge rectifier is compensated by hysteresis current control technique directed by the boost converter. The results show that the proposed controller can regulate the DC output voltage over a wide range of load and input voltage variation while making the input current sinusoidal with improved power factor.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"307 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116365273","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036614
M. Chowdhury, Faozia Rashid Taimy, Niloy Sikder, A. Nahid
The number of diabetic patients is increasing rapidly every year all around the world, and the worst fact is that these patients suffer from a wide range of physical conditions directly associated with long-term diabetes. Diabetic Retinopathy (DR) is a perfect example which affects the eyes of more than 50% of all diabetes patients to some degree. Starting from blurred vision, the effects of DR can extend to permanent blindness; and in most of the cases, victims fail to report any early symptoms. The traditional detection process of DR involves a trained clinician who takes enhanced pictures of the retina and looks for the presence of lesions and vascular abnormalities within them, which by description is a time-consuming and error-prone procedure. Alternatively, we can employ machine learning techniques that will automate the detection process as well as provide fast and more importantly, reliable results. Using a deep learning technique this paper determines the presence and severity of DR in diabetic individuals by analyzing the pictures of their retina. The CNN-based models are potent enough to carry out their tasks with accuracy up to 89.07%, even when the images are captured or provided in very low resolutions.
{"title":"Diabetic Retinopathy Classification with a Light Convolutional Neural Network","authors":"M. Chowdhury, Faozia Rashid Taimy, Niloy Sikder, A. Nahid","doi":"10.1109/IC4ME247184.2019.9036614","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036614","url":null,"abstract":"The number of diabetic patients is increasing rapidly every year all around the world, and the worst fact is that these patients suffer from a wide range of physical conditions directly associated with long-term diabetes. Diabetic Retinopathy (DR) is a perfect example which affects the eyes of more than 50% of all diabetes patients to some degree. Starting from blurred vision, the effects of DR can extend to permanent blindness; and in most of the cases, victims fail to report any early symptoms. The traditional detection process of DR involves a trained clinician who takes enhanced pictures of the retina and looks for the presence of lesions and vascular abnormalities within them, which by description is a time-consuming and error-prone procedure. Alternatively, we can employ machine learning techniques that will automate the detection process as well as provide fast and more importantly, reliable results. Using a deep learning technique this paper determines the presence and severity of DR in diabetic individuals by analyzing the pictures of their retina. The CNN-based models are potent enough to carry out their tasks with accuracy up to 89.07%, even when the images are captured or provided in very low resolutions.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126310661","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036515
Sultana Umme Habiba, Md. Khairul Islam, S. M. M. Ahsan
At present deep learning-based object recognition approaches have placed a tremendous effect for classifying different objects. Leaves recognition using supervised learning has shown satisfying performance which may help in various research purposes also. In our work, we have used a deep convolutional neural network as a classifier. We have used a transfer learning approach. We have prepared our work dataset based on Bangladeshi plants which contains eight different classes of leaves. We have experimented with VGG16, VGG19, Resnet50, InceptionV3, Inception-Resnetv2 and Xception deep convolutional neural network models where we have found the highest value in VGG 16 which shows almost 96% classification accuracy. Recognition of useful plants using leaf image will be greatly helpful in the research of ayurvedic and endangered plants.
{"title":"Bangladeshi Plant Recognition using Deep Learning based Leaf Classification","authors":"Sultana Umme Habiba, Md. Khairul Islam, S. M. M. Ahsan","doi":"10.1109/IC4ME247184.2019.9036515","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036515","url":null,"abstract":"At present deep learning-based object recognition approaches have placed a tremendous effect for classifying different objects. Leaves recognition using supervised learning has shown satisfying performance which may help in various research purposes also. In our work, we have used a deep convolutional neural network as a classifier. We have used a transfer learning approach. We have prepared our work dataset based on Bangladeshi plants which contains eight different classes of leaves. We have experimented with VGG16, VGG19, Resnet50, InceptionV3, Inception-Resnetv2 and Xception deep convolutional neural network models where we have found the highest value in VGG 16 which shows almost 96% classification accuracy. Recognition of useful plants using leaf image will be greatly helpful in the research of ayurvedic and endangered plants.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129330476","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036670
Md Rakibul Hasan, M. Maliha, M. Arifuzzaman
Every social networking sites like facebook, twitter, instagram etc become one of the key sources of information. It is found that by extracting and analyzing data from social networking sites, a business entity can be benefited in their product marketing. Twitter is one of the most popular sites where people used to express their feelings and reviews for a particular product. In our work, we use twitter data to analyze public views towards a product. Firstly, we have developed a natural language processing (NLP) based pre-processed data framework to filter tweets. Secondly, we incorporate Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) model concept to analyze sentiment. This is an initiative to use BoW and TFIDF are used together to precisely classify positive and negative tweets. We have found that by exploiting TF-IDF vectorizer, the accuracy of sentiment analysis can be substantially improved and simulation results show the efficiency of our proposed system. We achieved 85.25% accuracy in sentiment analysis using NLP technique.
{"title":"Sentiment Analysis with NLP on Twitter Data","authors":"Md Rakibul Hasan, M. Maliha, M. Arifuzzaman","doi":"10.1109/IC4ME247184.2019.9036670","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036670","url":null,"abstract":"Every social networking sites like facebook, twitter, instagram etc become one of the key sources of information. It is found that by extracting and analyzing data from social networking sites, a business entity can be benefited in their product marketing. Twitter is one of the most popular sites where people used to express their feelings and reviews for a particular product. In our work, we use twitter data to analyze public views towards a product. Firstly, we have developed a natural language processing (NLP) based pre-processed data framework to filter tweets. Secondly, we incorporate Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) model concept to analyze sentiment. This is an initiative to use BoW and TFIDF are used together to precisely classify positive and negative tweets. We have found that by exploiting TF-IDF vectorizer, the accuracy of sentiment analysis can be substantially improved and simulation results show the efficiency of our proposed system. We achieved 85.25% accuracy in sentiment analysis using NLP technique.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130531926","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036602
Azmain Yakin Srizon, Md. Al Mehedi Hasan
Having the five-year survival rate of approximately 5%, currently, the fourth leading reason for cancer-related deaths is pancreatic cancer. Previously, various works have concluded that early diagnosis plays a significant role in improving the survival rate and different online tools have been used to identify prognostic biomarker which is a long process. We think that the statistical feature selection method can provide a better and faster result here. To establish our statement, we selected three different mRNA microarray (GSE15471, GSE28735 and GSE16515) and a microRNA (GSE41372) dataset for identification of differentially expressed genes (DEGs) and differentially expressed microRNAs (DEMs). By using a parametric test (Student’s t-test), 178 DEGs and 16 DEMs were selected. After identifying target genes of DEMs, we selected two DEGs (ECT2 and NRP2) which were also identified among DEMs target genes. Furthermore, overall survival analysis confirmed that ECT2 and NRP2 were correlated with inadequate overall survival. Hence, we concluded that for pancreatic cancer, a parametric test like Student’s t-test can perform better for biomarker identification, and here, ECT2 and NRP2 can act as possible biomarkers. All the resources, programs and snippets of our literature can be discovered at https://github.com/Srizon143005/PancreaticCancerBiomarkers.
{"title":"Prognostic Biomarker Identification for Pancreatic Cancer by Analyzing Multiple mRNA Microarray and microRNA Expression Datasets","authors":"Azmain Yakin Srizon, Md. Al Mehedi Hasan","doi":"10.1109/IC4ME247184.2019.9036602","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036602","url":null,"abstract":"Having the five-year survival rate of approximately 5%, currently, the fourth leading reason for cancer-related deaths is pancreatic cancer. Previously, various works have concluded that early diagnosis plays a significant role in improving the survival rate and different online tools have been used to identify prognostic biomarker which is a long process. We think that the statistical feature selection method can provide a better and faster result here. To establish our statement, we selected three different mRNA microarray (GSE15471, GSE28735 and GSE16515) and a microRNA (GSE41372) dataset for identification of differentially expressed genes (DEGs) and differentially expressed microRNAs (DEMs). By using a parametric test (Student’s t-test), 178 DEGs and 16 DEMs were selected. After identifying target genes of DEMs, we selected two DEGs (ECT2 and NRP2) which were also identified among DEMs target genes. Furthermore, overall survival analysis confirmed that ECT2 and NRP2 were correlated with inadequate overall survival. Hence, we concluded that for pancreatic cancer, a parametric test like Student’s t-test can perform better for biomarker identification, and here, ECT2 and NRP2 can act as possible biomarkers. All the resources, programs and snippets of our literature can be discovered at https://github.com/Srizon143005/PancreaticCancerBiomarkers.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124679181","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036603
N. H. M. Bhuyan, Mamun Ahmed
Research in allocated radio spectrum for millimeter wave communication is one of the growing interest and recent development this concepts foster evolution of the new frontier for wireless communication system. The millimeter wave band (30 GHz to 300 GHz and wavelength range from 10 to 1 mm) falls in over 90% of the allocated radio spectrum. The focus of this work is using different enbNodes (eNodeB) in millimeter wave (mmWave) implementation of signal-to-interference-plus-noise ratio (SINR) for different enbNodes in network simulator ns-3. Finally, the result of our simple millimeter wave communication simulation is: if enbNodes increase then the SINR will decrease.
{"title":"Effect of different enbNodes on Millimeter Wave Communication","authors":"N. H. M. Bhuyan, Mamun Ahmed","doi":"10.1109/IC4ME247184.2019.9036603","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036603","url":null,"abstract":"Research in allocated radio spectrum for millimeter wave communication is one of the growing interest and recent development this concepts foster evolution of the new frontier for wireless communication system. The millimeter wave band (30 GHz to 300 GHz and wavelength range from 10 to 1 mm) falls in over 90% of the allocated radio spectrum. The focus of this work is using different enbNodes (eNodeB) in millimeter wave (mmWave) implementation of signal-to-interference-plus-noise ratio (SINR) for different enbNodes in network simulator ns-3. Finally, the result of our simple millimeter wave communication simulation is: if enbNodes increase then the SINR will decrease.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123818024","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036597
A. M. Jahirul Islam, J. Saha, K. Roy, A. Barua
At present, most of the people in rural areas use biomass such as wood, cow dung, jute sticks or other agricultural wastes for cooking in the clay stoves. Those traditional clay stoves not only inefficient but also poorly ventilated. As a result, they produce fine particles, aromatic hydrocarbons, carbon monoxide, and dioxins that cause air pollution. However, traditional biogas system accomplished in developing countries and some least developed countries (e.g. Bangladesh) are not automated. In this paper, an automated bidirectional business concept is introduced where both buyers and sellers are benefited at the same time in rural areas. In this community business model, people sell biogas from their micro biogas plant through the automated grid. This research is a master-slave wireless system based on Arduino that incorporates with payment system via a mobile application. RF pair along with transmitter and receiver is used in order to get transmitting and receiving biogas quantity and other signals for every user. In addition, an analytic calculation is done for the performance test of the proposed system.
{"title":"Automated Biogas Grid for Sustainable Development in Rural Area","authors":"A. M. Jahirul Islam, J. Saha, K. Roy, A. Barua","doi":"10.1109/IC4ME247184.2019.9036597","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036597","url":null,"abstract":"At present, most of the people in rural areas use biomass such as wood, cow dung, jute sticks or other agricultural wastes for cooking in the clay stoves. Those traditional clay stoves not only inefficient but also poorly ventilated. As a result, they produce fine particles, aromatic hydrocarbons, carbon monoxide, and dioxins that cause air pollution. However, traditional biogas system accomplished in developing countries and some least developed countries (e.g. Bangladesh) are not automated. In this paper, an automated bidirectional business concept is introduced where both buyers and sellers are benefited at the same time in rural areas. In this community business model, people sell biogas from their micro biogas plant through the automated grid. This research is a master-slave wireless system based on Arduino that incorporates with payment system via a mobile application. RF pair along with transmitter and receiver is used in order to get transmitting and receiving biogas quantity and other signals for every user. In addition, an analytic calculation is done for the performance test of the proposed system.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122186962","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036493
Ananna Rahman, Niloy Sikder, A. Nahid
Observing the condition of the cardiovascular system is a vital task in the medical sector. The electrocardiogram (ECG) is such a tool that can be used to detect cardiovascular abnormalities. The advanced techniques of Machine Learning can help us to detect such abnormalities with the help of computers. But to effectively train the machine, we need to extract meaningful features from the ECG signals instead of using the raw signal as input. In this study, a set of handcrafted features have been extracted after signal preprocessing and used to train a classifier properly. The aim of this paper is to propose an effective technique to classify 17 different classes of ECG signals based on an ensemble learning algorithm named Random Forest (RF) classifier. The method provides 88% classification accuracy.
{"title":"Heart Condition Monitoring Using Ensemble Technique Based on ECG Signals’ Power Spectrum","authors":"Ananna Rahman, Niloy Sikder, A. Nahid","doi":"10.1109/IC4ME247184.2019.9036493","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036493","url":null,"abstract":"Observing the condition of the cardiovascular system is a vital task in the medical sector. The electrocardiogram (ECG) is such a tool that can be used to detect cardiovascular abnormalities. The advanced techniques of Machine Learning can help us to detect such abnormalities with the help of computers. But to effectively train the machine, we need to extract meaningful features from the ECG signals instead of using the raw signal as input. In this study, a set of handcrafted features have been extracted after signal preprocessing and used to train a classifier properly. The aim of this paper is to propose an effective technique to classify 17 different classes of ECG signals based on an ensemble learning algorithm named Random Forest (RF) classifier. The method provides 88% classification accuracy.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"53 16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115966008","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036587
Md. Rifaet Ullah, Md. Al Mehedi Hasan, Julia Rahman, Md. Khaled Ben Islam
Finding an optimal subspace of bands that has the most expressive power for classifying hyperspectral image has been very challenging task due to its insufficient number of training pixels with respect to large number of bands. Feature reduction is considered a promising solution in this type of task. However, it is very hard to select an optimal feature reduction technique which is effective as well as computationally efficient in case of hyperspectral image classification. Moreover, it becomes challenging when the number of training pixels of a class is not sufficient. In this paper, we have rigorously studied some feature selection techniques for reducing spectral dimension by considering all the classes in hyperspectral image on a benchmark data set. We have projected that this study will be very supportive for further study on band selection and hyperspectral image classification.
{"title":"A comparative analysis of band selection techniques for hyperspectral image classification","authors":"Md. Rifaet Ullah, Md. Al Mehedi Hasan, Julia Rahman, Md. Khaled Ben Islam","doi":"10.1109/IC4ME247184.2019.9036587","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036587","url":null,"abstract":"Finding an optimal subspace of bands that has the most expressive power for classifying hyperspectral image has been very challenging task due to its insufficient number of training pixels with respect to large number of bands. Feature reduction is considered a promising solution in this type of task. However, it is very hard to select an optimal feature reduction technique which is effective as well as computationally efficient in case of hyperspectral image classification. Moreover, it becomes challenging when the number of training pixels of a class is not sufficient. In this paper, we have rigorously studied some feature selection techniques for reducing spectral dimension by considering all the classes in hyperspectral image on a benchmark data set. We have projected that this study will be very supportive for further study on band selection and hyperspectral image classification.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116211914","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036476
Tahsin Masrur, Md. Al Mehedi Hasan
Mortality rate of diseases like lung cancer can be decreased significantly by increasing the chance of early diagnosis. Identifying differentially expressed (DE) metabolites may contribute remarkably in this concern, and also in drug design. In the past, several kinds of approaches were attempted to discover biomarkers for diseases. Nonetheless, discovering compact-sized biomarkers while maintaining satisfactory classification performance is still a challenge. Therefore, for further contribution in this sector, we have declared biomarkers from our identified DE metabolites in plasma and serum blood sample of lung cancer. Student’s t-test, Kruskal-Wallis and Mann-Whitney-Wilcoxon test were applied to distinguish the DE metabolites. Cluster heatmap plot and fold change values were used to differentiate between up and down-regulated metabolites. Finally, RFE method was used to order the metabolites and select biomarkers from them. To assess the performance with our DE metabolites or biomarkers, SVM classifier was utilized. We found 28 DE metabolites from plasma dataset and 13 from serum (p-value $lt 0.05)$. In the end, 8 metabolites were selected from plasma sample and 5 were selected from serum sample as the metabolomic biomarkers. The relevant files and codes of our work can be found at https://github.com/Zeronfinity/LungCancerBiomarkerRFE.
{"title":"Identification of Metabolomic Biomarker using Multiple Statistical Techniques and Recursive Feature Elimination","authors":"Tahsin Masrur, Md. Al Mehedi Hasan","doi":"10.1109/IC4ME247184.2019.9036476","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036476","url":null,"abstract":"Mortality rate of diseases like lung cancer can be decreased significantly by increasing the chance of early diagnosis. Identifying differentially expressed (DE) metabolites may contribute remarkably in this concern, and also in drug design. In the past, several kinds of approaches were attempted to discover biomarkers for diseases. Nonetheless, discovering compact-sized biomarkers while maintaining satisfactory classification performance is still a challenge. Therefore, for further contribution in this sector, we have declared biomarkers from our identified DE metabolites in plasma and serum blood sample of lung cancer. Student’s t-test, Kruskal-Wallis and Mann-Whitney-Wilcoxon test were applied to distinguish the DE metabolites. Cluster heatmap plot and fold change values were used to differentiate between up and down-regulated metabolites. Finally, RFE method was used to order the metabolites and select biomarkers from them. To assess the performance with our DE metabolites or biomarkers, SVM classifier was utilized. We found 28 DE metabolites from plasma dataset and 13 from serum (p-value $lt 0.05)$. In the end, 8 metabolites were selected from plasma sample and 5 were selected from serum sample as the metabolomic biomarkers. The relevant files and codes of our work can be found at https://github.com/Zeronfinity/LungCancerBiomarkerRFE.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115527945","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：