Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154079
P. J. Beryl Princess, S. Silas, E. Rajsingh
Rapid growth in automobiles has caused an upsurge of accidents per day, which leads to the loss of lives and incurable disabilities to the victims. Therefore, the severity of the accident must be analyzed in real-time to save the injured and enhance emergency services. Accordingly, the accident image is considered as significant data in this work. From the accident image, essential features such as shape, texture and intensity gradient features are extracted using Hu moments, Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HoG) respectively. The extracted image features are combined to form a hybrid feature vector. With an objective to recognize the severity of the accident, the hybrid feature is employed to train the machine learning classifier models such as Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), AdaBoost (AB) and Gradient Boosting (GB). The performance of the classifiers is evaluated in terms of Area under the curve (AUC), precision, recall and F1-score. The results show the Random Forest performs better with AUC 0.75 compared to other models. Moreover, the result also reveals that hybrid features improve the recognition rate compared to the single feature.
{"title":"Machine Learning Approach for Identification of Accident Severity from Accident Images Using Hybrid Features","authors":"P. J. Beryl Princess, S. Silas, E. Rajsingh","doi":"10.1109/incet49848.2020.9154079","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154079","url":null,"abstract":"Rapid growth in automobiles has caused an upsurge of accidents per day, which leads to the loss of lives and incurable disabilities to the victims. Therefore, the severity of the accident must be analyzed in real-time to save the injured and enhance emergency services. Accordingly, the accident image is considered as significant data in this work. From the accident image, essential features such as shape, texture and intensity gradient features are extracted using Hu moments, Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HoG) respectively. The extracted image features are combined to form a hybrid feature vector. With an objective to recognize the severity of the accident, the hybrid feature is employed to train the machine learning classifier models such as Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), AdaBoost (AB) and Gradient Boosting (GB). The performance of the classifiers is evaluated in terms of Area under the curve (AUC), precision, recall and F1-score. The results show the Random Forest performs better with AUC 0.75 compared to other models. Moreover, the result also reveals that hybrid features improve the recognition rate compared to the single feature.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115424518","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9153982
R. R. Pillai, R. Lohani
Wireless body area networks (WBANs) is a recently developing technology which will be playing a vital role in resolving some challenges faced in the healthcare sector. Energy-efficient solutions help to foster the acceptance of this technology by the patients. To solve the issues related to conservation of energy during temporary disconnection of sensor node from the sink, a solution based on hidden Markov Model (HMM) has been developed. Here a novel approach of predicting hypertension from heart rate data using Hidden Markov Models has been implemented. The model is using the concept that since the heart rate is a major correlate of blood pressure, it can predict the development of hypertension in patients with elevated blood pressure values. The simultaneous happening of tachycardia and hypertension may lead to cardiovascular problems. Here using Hidden Markov Model decoding the change of state happening over tachycardia is detected and emergency data loss is prevented considering the temporary disconnection for a small interval of time.
{"title":"Emergency data detection using Hidden Markov Model during temporary disconnection of Wireless Body Area Networks","authors":"R. R. Pillai, R. Lohani","doi":"10.1109/incet49848.2020.9153982","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9153982","url":null,"abstract":"Wireless body area networks (WBANs) is a recently developing technology which will be playing a vital role in resolving some challenges faced in the healthcare sector. Energy-efficient solutions help to foster the acceptance of this technology by the patients. To solve the issues related to conservation of energy during temporary disconnection of sensor node from the sink, a solution based on hidden Markov Model (HMM) has been developed. Here a novel approach of predicting hypertension from heart rate data using Hidden Markov Models has been implemented. The model is using the concept that since the heart rate is a major correlate of blood pressure, it can predict the development of hypertension in patients with elevated blood pressure values. The simultaneous happening of tachycardia and hypertension may lead to cardiovascular problems. Here using Hidden Markov Model decoding the change of state happening over tachycardia is detected and emergency data loss is prevented considering the temporary disconnection for a small interval of time.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117180942","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154090
Darkunde Mayur Ashok, Agrawal Nidhi Ghanshyam, S. Salim, Dungarpur Burhanuddin Mazahir, B. Thakare
The challenging problem of 21st Century is to detect sarcasm in vivid data available on a large scale. Over 20 years of study in this field, the past 10 years have shown a significant progress not only in semantic features, but also an upward trend has also been observed in the various machine-learning approaches to analyze and process the data. To enlist a few, theories of sarcasm, it's syntactical and semantic properties; lexical features have been an area of interest for almost all of them. In this paper, we propose a unique deep neural network model whose Bidirectional LSTM undergo Hyper parameters optimization using genetic algorithm followed by a Convolution Neural Network for sarcasm detection. We put forward the results in a robust way, which may result in a better future work in this field.
{"title":"Sarcasm Detection using Genetic Optimization on LSTM with CNN","authors":"Darkunde Mayur Ashok, Agrawal Nidhi Ghanshyam, S. Salim, Dungarpur Burhanuddin Mazahir, B. Thakare","doi":"10.1109/incet49848.2020.9154090","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154090","url":null,"abstract":"The challenging problem of 21st Century is to detect sarcasm in vivid data available on a large scale. Over 20 years of study in this field, the past 10 years have shown a significant progress not only in semantic features, but also an upward trend has also been observed in the various machine-learning approaches to analyze and process the data. To enlist a few, theories of sarcasm, it's syntactical and semantic properties; lexical features have been an area of interest for almost all of them. In this paper, we propose a unique deep neural network model whose Bidirectional LSTM undergo Hyper parameters optimization using genetic algorithm followed by a Convolution Neural Network for sarcasm detection. We put forward the results in a robust way, which may result in a better future work in this field.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127187293","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154142
R. P, Shamjiith, R. K
Text recognition is a vast field of research and experimentation under image processing domain. It is a process by which the system locates the area whichever any kind of text is present and to extract them. The extracted text must be converted to human readable form after several processing and to classify them into meaningful classes based on the content. The platform used here is MATLAB R2018a. Firstly, Pre-processing is done on the ICDAR 2017 dataset in order to remove noise content. Then Segmentation is done to get a rough idea of the textual content present. Needful features are extracted using MSER (Maximally stable extremal regions). The obtained result is then processed with Stroke width transform. Geometrical features of text are matched with the regions. Finally, all of the processed regions are merged to obtain the exact text and extract them with OCR (Optical Character Recognition). Classifying these into meaningful attributes makes more sense to the extracted text.
{"title":"Multi-Oriented Text Recognition and Classification in Natural Images using MSER","authors":"R. P, Shamjiith, R. K","doi":"10.1109/incet49848.2020.9154142","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154142","url":null,"abstract":"Text recognition is a vast field of research and experimentation under image processing domain. It is a process by which the system locates the area whichever any kind of text is present and to extract them. The extracted text must be converted to human readable form after several processing and to classify them into meaningful classes based on the content. The platform used here is MATLAB R2018a. Firstly, Pre-processing is done on the ICDAR 2017 dataset in order to remove noise content. Then Segmentation is done to get a rough idea of the textual content present. Needful features are extracted using MSER (Maximally stable extremal regions). The obtained result is then processed with Stroke width transform. Geometrical features of text are matched with the regions. Finally, all of the processed regions are merged to obtain the exact text and extract them with OCR (Optical Character Recognition). Classifying these into meaningful attributes makes more sense to the extracted text.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125174788","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9154102
Caleb Meriga, Ravi Teja Ponnuri, B. Vamsi Krishna, Shaik Saidulu, M. Durga Prakesh
In this work, the concept of hybrid structured channel is proposed to reduce the short channel effect (SCE), while still permitting high current through the channel. 5nm Dual gate junctionless gate-all-around (JL-GAA) FET using two different hybrid structured channels (i.e. concentric cylindrical and zigzag structures) were compared. The performance characteristics of the two hybrid structures were attained and analyzed. The zigzag structured channel showed to have higher conductivity, constant Dirac point, high output conductance of ~220% more than concentric cylindrical structured channel.
{"title":"Dual Gate Junctionless Gate-All-Around (JL-GAA) FETs using Hybrid Structured Channels","authors":"Caleb Meriga, Ravi Teja Ponnuri, B. Vamsi Krishna, Shaik Saidulu, M. Durga Prakesh","doi":"10.1109/incet49848.2020.9154102","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154102","url":null,"abstract":"In this work, the concept of hybrid structured channel is proposed to reduce the short channel effect (SCE), while still permitting high current through the channel. 5nm Dual gate junctionless gate-all-around (JL-GAA) FET using two different hybrid structured channels (i.e. concentric cylindrical and zigzag structures) were compared. The performance characteristics of the two hybrid structures were attained and analyzed. The zigzag structured channel showed to have higher conductivity, constant Dirac point, high output conductance of ~220% more than concentric cylindrical structured channel.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115254422","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 : 2020-06-01DOI: 10.1109/INCET49848.2020.9154160
Aravinda Babu Tummala, Deergha Rao Korrai
Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (MIMO OFDM) wireless communication is well known in the literature. However, the problems occur in classical MIMO system can be overcome with large number of array antennas such systems, termed as Massive MIMO. But, the latency may be more for these systems using traditional equalizers such as Zero Forcing (ZF) and Minimum Mean Square Error (MMSE). Hence, this paper proposes LDPC coded Massive MIMO OFDM system using Approximate Message Passing (AMP) equalizer. The performance of the proposed system is analysed through simulations. In this simulation, different transmit and receive antennas (64,128), (64,256), (64,512) and (64, 1024) and 16QAM are used. Finally, the performance of LDPC coded and uncoded massive MIMO OFDM using AMP equalizer is analyzed in comparison with ZF and MMSE equalizers using BER and latency as performance measures.
{"title":"Performance Analysis of LDPC Coded Massive MIMO-OFDM System","authors":"Aravinda Babu Tummala, Deergha Rao Korrai","doi":"10.1109/INCET49848.2020.9154160","DOIUrl":"https://doi.org/10.1109/INCET49848.2020.9154160","url":null,"abstract":"Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (MIMO OFDM) wireless communication is well known in the literature. However, the problems occur in classical MIMO system can be overcome with large number of array antennas such systems, termed as Massive MIMO. But, the latency may be more for these systems using traditional equalizers such as Zero Forcing (ZF) and Minimum Mean Square Error (MMSE). Hence, this paper proposes LDPC coded Massive MIMO OFDM system using Approximate Message Passing (AMP) equalizer. The performance of the proposed system is analysed through simulations. In this simulation, different transmit and receive antennas (64,128), (64,256), (64,512) and (64, 1024) and 16QAM are used. Finally, the performance of LDPC coded and uncoded massive MIMO OFDM using AMP equalizer is analyzed in comparison with ZF and MMSE equalizers using BER and latency as performance measures.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116812876","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 : 2020-06-01DOI: 10.1109/INCET49848.2020.9154070
Arushi Gupta, Sandeep Suri, K. Sharma
The growth of each and every country in the world leads to World Development which can be in terms of imports, exports, GDP, production, population, etc. The various factors play a very important role in analyzing a country’s growth globally. There are tools to rank multiple countries based on a single indicator but there is no tool available for comparing and predicting the future trends on the basis of various indicators. Also, it is difficult for common people to find the data and then to compare on these indicators. So, we deduce a tool using data mining techniques to find the ranking of each country based on given parameters. This tool will be a boon for the companies, the officials and the common people.
{"title":"Ranking of Countries using R","authors":"Arushi Gupta, Sandeep Suri, K. Sharma","doi":"10.1109/INCET49848.2020.9154070","DOIUrl":"https://doi.org/10.1109/INCET49848.2020.9154070","url":null,"abstract":"The growth of each and every country in the world leads to World Development which can be in terms of imports, exports, GDP, production, population, etc. The various factors play a very important role in analyzing a country’s growth globally. There are tools to rank multiple countries based on a single indicator but there is no tool available for comparing and predicting the future trends on the basis of various indicators. Also, it is difficult for common people to find the data and then to compare on these indicators. So, we deduce a tool using data mining techniques to find the ranking of each country based on given parameters. This tool will be a boon for the companies, the officials and the common people.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117069324","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 : 2020-06-01DOI: 10.1109/INCET49848.2020.9154169
U. Kr, Rajani Katiyar, C. Manjunatha, Nivedita P Birajadar, Likhita Likhita, P. K
In this paper, a low-cost electrochemical system is designed for the detection of Heavy metals (HM’s) in soil solution. The system consists of screen-printed electrode, a potentiostat and microcontroller. The three terminal of Screen printed electrode is working electrode (WE), reference electrode(RE) and a counter electrode(CE). A potentiostat is electronic circuit that has been designed which applies suitable voltage for operation and analyze the signal coming from screen printed electrode. Based on peak current obtained at different reduction potential presence of these heavy metal ions is determined. The proposed circuit is simulated and also implemented using hardware components. The output from potentiostat are processed using microcontroller and results are displayed. The result is found to be effective and reliable.
{"title":"Heavy Metal-Ion Detection in Soil Using Anodic Stripping Voltammetry","authors":"U. Kr, Rajani Katiyar, C. Manjunatha, Nivedita P Birajadar, Likhita Likhita, P. K","doi":"10.1109/INCET49848.2020.9154169","DOIUrl":"https://doi.org/10.1109/INCET49848.2020.9154169","url":null,"abstract":"In this paper, a low-cost electrochemical system is designed for the detection of Heavy metals (HM’s) in soil solution. The system consists of screen-printed electrode, a potentiostat and microcontroller. The three terminal of Screen printed electrode is working electrode (WE), reference electrode(RE) and a counter electrode(CE). A potentiostat is electronic circuit that has been designed which applies suitable voltage for operation and analyze the signal coming from screen printed electrode. Based on peak current obtained at different reduction potential presence of these heavy metal ions is determined. The proposed circuit is simulated and also implemented using hardware components. The output from potentiostat are processed using microcontroller and results are displayed. The result is found to be effective and reliable.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128432036","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 : 2020-06-01DOI: 10.1109/incet49848.2020.9153993
R. K. Megalingam, Gowtham Kishore Indukuri, D. K. Krishna Reddy, Esarapu Dilip Vignesh, Vedha Krishna Yarasuri
This research work intends to help farmers’ effective crop harvests by technology-aided irrigation. For that purpose, we propose an easily accessible IoT based monitoring, wireless controlled rover irrigation system. Through this IoT system data, farmers can irrigate their crops according to moisture and temperature values and see that every plant is getting sufficient water and sunlight. This wireless rover system uses a microcontroller unit as the master controller. Joysticks are used to control the rover using wireless interface. The sensor unit which is part of the rover system consists of moisture sensor and a temperature sensor, for detection of the moisture and temperature respectively in close proximity of plants. We have used Google-assistant bolt IoT, Integromat, telegram bot and mail gun, for data analysis. We also used a bolt WiFi module for connecting it to the internet. We have used the bolt cloud platform for data transferring and storing and predictions.
{"title":"Irrigation Monitoring and Prediction System Using Machine Learning","authors":"R. K. Megalingam, Gowtham Kishore Indukuri, D. K. Krishna Reddy, Esarapu Dilip Vignesh, Vedha Krishna Yarasuri","doi":"10.1109/incet49848.2020.9153993","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9153993","url":null,"abstract":"This research work intends to help farmers’ effective crop harvests by technology-aided irrigation. For that purpose, we propose an easily accessible IoT based monitoring, wireless controlled rover irrigation system. Through this IoT system data, farmers can irrigate their crops according to moisture and temperature values and see that every plant is getting sufficient water and sunlight. This wireless rover system uses a microcontroller unit as the master controller. Joysticks are used to control the rover using wireless interface. The sensor unit which is part of the rover system consists of moisture sensor and a temperature sensor, for detection of the moisture and temperature respectively in close proximity of plants. We have used Google-assistant bolt IoT, Integromat, telegram bot and mail gun, for data analysis. We also used a bolt WiFi module for connecting it to the internet. We have used the bolt cloud platform for data transferring and storing and predictions.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128527077","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：