Pub Date : 2019-12-05DOI: 10.1109/ICIICT1.2019.8741499
Aravindaraman B A, P. Ranjana
Garbage disposal is one of the main problems faced in India regardless of the growth of the states and the area of development. It is a major problem in the under developed places It is found that most cases the trashes are spread across the road side because it is not collected on time. This trash leads to spread of disease and cause illness. There is a possibility of having some deadly disease. So, the proposed systems find the solution for the garbage disposal by designing a smart dust bin by managing the garbage. The garbage is collected, and the garbage collector sent from the control room. The smart dustbin sends the message to the control room through the sensors attached to it. The dustbin is attached with the ultrasonic sensor, infrared sensor for detecting the level of the waste and anonymous gases which is connected to a Raspberry Pi microcontroller where it is programmed to send message to the control room if the garbage is full and also if the garbage is not disposed for a long time.
{"title":"Design Of A Monitoring System For Waste Management Using IoT","authors":"Aravindaraman B A, P. Ranjana","doi":"10.1109/ICIICT1.2019.8741499","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741499","url":null,"abstract":"Garbage disposal is one of the main problems faced in India regardless of the growth of the states and the area of development. It is a major problem in the under developed places It is found that most cases the trashes are spread across the road side because it is not collected on time. This trash leads to spread of disease and cause illness. There is a possibility of having some deadly disease. So, the proposed systems find the solution for the garbage disposal by designing a smart dust bin by managing the garbage. The garbage is collected, and the garbage collector sent from the control room. The smart dustbin sends the message to the control room through the sensors attached to it. The dustbin is attached with the ultrasonic sensor, infrared sensor for detecting the level of the waste and anonymous gases which is connected to a Raspberry Pi microcontroller where it is programmed to send message to the control room if the garbage is full and also if the garbage is not disposed for a long time.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133604902","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741450
D. Selvathi, K. Suganya
Diabetic eye disease is one of the major problems worldwide. That can cause major impairment to the eyes, including a permanent loss of vision. Early detection of eye diseases increase the survival rate by successful treatment. The proposed methodology is to explore machine learning technique to detect diabetic diseased using thermography images of an eye and to introduce the effect of thermal variation of abnormality in the eye structure as a diagnosis imaging modality which are useful for ophthalmologists to do the clinical diagnosis. Thermal images are pre-processed, and then Gray Level Co-occurrence Matrix (GLCM) based texture features from gray images, statistical features from RGB and HSI images are extracted and classified using classifier with various combination of features. To detect diabetic diseased eye, here Support Vector Machine classifier is used for classification and their performance are compared. A 5-fold cross validation scheme is used to enhance the generalization capability of the proposed method. Experimental results obtained for various feature combinations gives maximum accuracy of 86. 22%, sensitivity of 94. 07% and specificity of 79. 17% using SVM classifier with five-fold validation.
{"title":"Support Vector Machine Based Method for Automatic Detection of Diabetic Eye Disease using Thermal Images","authors":"D. Selvathi, K. Suganya","doi":"10.1109/ICIICT1.2019.8741450","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741450","url":null,"abstract":"Diabetic eye disease is one of the major problems worldwide. That can cause major impairment to the eyes, including a permanent loss of vision. Early detection of eye diseases increase the survival rate by successful treatment. The proposed methodology is to explore machine learning technique to detect diabetic diseased using thermography images of an eye and to introduce the effect of thermal variation of abnormality in the eye structure as a diagnosis imaging modality which are useful for ophthalmologists to do the clinical diagnosis. Thermal images are pre-processed, and then Gray Level Co-occurrence Matrix (GLCM) based texture features from gray images, statistical features from RGB and HSI images are extracted and classified using classifier with various combination of features. To detect diabetic diseased eye, here Support Vector Machine classifier is used for classification and their performance are compared. A 5-fold cross validation scheme is used to enhance the generalization capability of the proposed method. Experimental results obtained for various feature combinations gives maximum accuracy of 86. 22%, sensitivity of 94. 07% and specificity of 79. 17% using SVM classifier with five-fold validation.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131203644","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741465
Santhana Krishnan. J, G. S
Health care field has a vast amount of data, for processing those data certain techniques are used. Data mining is one of the techniques often used. Heart disease is the Leading cause of death worldwide. This System predicts the arising possibilities of Heart Disease. The outcomes of this system provide the chances of occurring heart disease in terms of percentage. The datasets used are classified in terms of medical parameters. This system evaluates those parameters using data mining classification technique. The datasets are processed in python programming using two main Machine Learning Algorithm namely Decision Tree Algorithm and Naive Bayes Algorithm which shows the best algorithm among these two in terms of accuracy level of heart disease.
{"title":"Prediction of Heart Disease Using Machine Learning Algorithms.","authors":"Santhana Krishnan. J, G. S","doi":"10.1109/ICIICT1.2019.8741465","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741465","url":null,"abstract":"Health care field has a vast amount of data, for processing those data certain techniques are used. Data mining is one of the techniques often used. Heart disease is the Leading cause of death worldwide. This System predicts the arising possibilities of Heart Disease. The outcomes of this system provide the chances of occurring heart disease in terms of percentage. The datasets used are classified in terms of medical parameters. This system evaluates those parameters using data mining classification technique. The datasets are processed in python programming using two main Machine Learning Algorithm namely Decision Tree Algorithm and Naive Bayes Algorithm which shows the best algorithm among these two in terms of accuracy level of heart disease.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123977631","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741495
R. Rajeshwari, T. Pasupathi, J. A. Vijaya Selvi
Free Space Optical Communication (FSOC) refers to an optical communication where unguided visible, infrared or ultraviolet light is used to carry the signal. In Wireless Optical Communication systems, optical signal is modulated and transmitted over the free space atmospheric channel. When the laser beam is propagating through the turbulent atmospheric channel it is heavily affected by various parameters. Generally, the intensity of the laser beam is greatly degraded by the phenomenon such as absorption and scattering effect due to natural atmospheric components namely gases, dust, smoke, precipitation, fog, rain etc. In other hand, the performance of FSOC is heavily affected by the fluctuation in the atmosphere. This fluctuation results in atmospheric turbulence effect such as beam wandering beam scintillation and wavefront aberration. Therefore, the performance of the FSOC is degraded by the atmospheric turbulence tremendously. Hence it is necessary to develop a suitable optoelectronic arrangements and algorithms to compensate the atmospheric turbulences. This paper shows the viability to improve the performance of FSOC by compensating the atmospheric turbulence effect. In this paper, a wavefront aberration compensation technique to mitigate the wavefront aberrations due to the channel is developed using the necessary opto electronic assembly. This paper mainly elaborates experimental implementation for calculation of wavefront aberration and also demonstrates the correction achieved experimentally.
{"title":"Wavefront Compensation Technique for Terrestrial Line of Sight Free Space Optical Communication","authors":"R. Rajeshwari, T. Pasupathi, J. A. Vijaya Selvi","doi":"10.1109/ICIICT1.2019.8741495","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741495","url":null,"abstract":"Free Space Optical Communication (FSOC) refers to an optical communication where unguided visible, infrared or ultraviolet light is used to carry the signal. In Wireless Optical Communication systems, optical signal is modulated and transmitted over the free space atmospheric channel. When the laser beam is propagating through the turbulent atmospheric channel it is heavily affected by various parameters. Generally, the intensity of the laser beam is greatly degraded by the phenomenon such as absorption and scattering effect due to natural atmospheric components namely gases, dust, smoke, precipitation, fog, rain etc. In other hand, the performance of FSOC is heavily affected by the fluctuation in the atmosphere. This fluctuation results in atmospheric turbulence effect such as beam wandering beam scintillation and wavefront aberration. Therefore, the performance of the FSOC is degraded by the atmospheric turbulence tremendously. Hence it is necessary to develop a suitable optoelectronic arrangements and algorithms to compensate the atmospheric turbulences. This paper shows the viability to improve the performance of FSOC by compensating the atmospheric turbulence effect. In this paper, a wavefront aberration compensation technique to mitigate the wavefront aberrations due to the channel is developed using the necessary opto electronic assembly. This paper mainly elaborates experimental implementation for calculation of wavefront aberration and also demonstrates the correction achieved experimentally.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125854282","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741353
Sunny Pahlajani, Avinash A. Kshirsagar, V. Pachghare
A blockchain is a distributed ledger of records called as blocks. These blocks are linked using cryptographic hash. Each block contains a hash of the previous block, a timestamp, and transaction data. Consensus layer is the main layer in Blockchain Architecture, in which consensus protocol is configured to decide how new block is added in blockchain. Consensus algorithm solves the problem of trust in blockchain. Consensus algorithms can be classified into two classes. The first class is voting-based consensus, which requires nodes in the blockchain network to broadcast their results of mining a new block or transaction, before appending the block to blockchain. The second class is proof-based consensus, which requires the nodes joining the blockchain network to solve and mathematical puzzle to show that they are more eligible than the others to do the appending or mining work. Performance of blockchain can be increased with the use of suitable consensus algorithm. However, theory and data support for the selecting suitable consensus in private blockchain is very limited. This paper contributes theory and data used for selecting suitable consensus algorithm and would help researchers for further exploring of consensus in private blockchain environment.
{"title":"Survey on Private Blockchain Consensus Algorithms","authors":"Sunny Pahlajani, Avinash A. Kshirsagar, V. Pachghare","doi":"10.1109/ICIICT1.2019.8741353","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741353","url":null,"abstract":"A blockchain is a distributed ledger of records called as blocks. These blocks are linked using cryptographic hash. Each block contains a hash of the previous block, a timestamp, and transaction data. Consensus layer is the main layer in Blockchain Architecture, in which consensus protocol is configured to decide how new block is added in blockchain. Consensus algorithm solves the problem of trust in blockchain. Consensus algorithms can be classified into two classes. The first class is voting-based consensus, which requires nodes in the blockchain network to broadcast their results of mining a new block or transaction, before appending the block to blockchain. The second class is proof-based consensus, which requires the nodes joining the blockchain network to solve and mathematical puzzle to show that they are more eligible than the others to do the appending or mining work. Performance of blockchain can be increased with the use of suitable consensus algorithm. However, theory and data support for the selecting suitable consensus in private blockchain is very limited. This paper contributes theory and data used for selecting suitable consensus algorithm and would help researchers for further exploring of consensus in private blockchain environment.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116272829","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741488
Alan Koshy, N. Mj, Prof. Shyna A, Prof. Ansamma John
In this age of digitization, there is a growing need to preserve physical copies of documents such as historical text. It is important in digitization to capture every aspect of the document which is infeasible due to challenges such as fading, creases, and shadows. Various approaches have been put forth to improve upon text extraction by means of preprocessing. This paper analyses the effect of applying some general preprocessing methods such as Thresholding, Morphology, and Blurring and enhancements of quality in the output obtained. Experimental results show that preprocessing improves the visual and structural quality of the document to a certain extent.
{"title":"Preprocessing Techniques for High Quality Text Extraction from Text Images","authors":"Alan Koshy, N. Mj, Prof. Shyna A, Prof. Ansamma John","doi":"10.1109/ICIICT1.2019.8741488","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741488","url":null,"abstract":"In this age of digitization, there is a growing need to preserve physical copies of documents such as historical text. It is important in digitization to capture every aspect of the document which is infeasible due to challenges such as fading, creases, and shadows. Various approaches have been put forth to improve upon text extraction by means of preprocessing. This paper analyses the effect of applying some general preprocessing methods such as Thresholding, Morphology, and Blurring and enhancements of quality in the output obtained. Experimental results show that preprocessing improves the visual and structural quality of the document to a certain extent.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132766066","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741434
R. P, A. James
Object recognition and classification is a challenging task in computer vision because of the large variation in shape, size and other attributes within the same object class. Also we need to consider other challenges such as the presence of noise and haze, occlusion, low illumination conditions, blur and the cluttered backgrounds. Due to these facts, object recognition and classification gained attention in recent years. Many researchers have proposed different methods to address the problem of recognition. This paper proposes a method for object recognition and classification based improved bag of features using SURF(Speeded Up Robust Features) and MSER(Maximally Stable External Regions) local feature extraction. Combination of SURF and MSER feature extraction algorithm can improve the recognition efficiency and the classification accuracy can be improved by spatial pyramid matching. SURF and MSER extracts the local features of an image and generate a image histogram codebook. Spatial pyramid matching is applied to this histogram, which improves the accuracy of classification. The experiment is conducted on Caltech 101 and Caltech 256 dataset.
{"title":"Object Recognition and Classification Based on Improved Bag of Features using SURF AND MSER Local Feature Extraction","authors":"R. P, A. James","doi":"10.1109/ICIICT1.2019.8741434","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741434","url":null,"abstract":"Object recognition and classification is a challenging task in computer vision because of the large variation in shape, size and other attributes within the same object class. Also we need to consider other challenges such as the presence of noise and haze, occlusion, low illumination conditions, blur and the cluttered backgrounds. Due to these facts, object recognition and classification gained attention in recent years. Many researchers have proposed different methods to address the problem of recognition. This paper proposes a method for object recognition and classification based improved bag of features using SURF(Speeded Up Robust Features) and MSER(Maximally Stable External Regions) local feature extraction. Combination of SURF and MSER feature extraction algorithm can improve the recognition efficiency and the classification accuracy can be improved by spatial pyramid matching. SURF and MSER extracts the local features of an image and generate a image histogram codebook. Spatial pyramid matching is applied to this histogram, which improves the accuracy of classification. The experiment is conducted on Caltech 101 and Caltech 256 dataset.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121524400","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741459
N. Meenakshi, M. Monish, K. Dikshit, S. Bharath
Security is the serious issue looked by everybody when we are far from our family unit. In the present situation acceptable answer for the above issue isn’t yet found. Introduced here is an electronic securing framework which Arduino assumes the job of the preparing unit. Arduino which is a microcontroller board has a place with at uber family. It is an open source straight forward instrument. It can detect, screen, store and control application. Access control for the entryway is accomplished utilizing Arduino Mega 2560 board. This task displays a keyless framework for locking and opening purposes utilizing a predefined PICTURE secret key and OTP. Unauthorized person access is ensured by sending OTP and PICTURE password to ADMIN to get OTP and PICTURE password where the person needs to contact the ADMIN to get OTP and PICTURE password. It is entered through the 2.8″ TFT touch display, which display all the UI messages and takes inputs from user. In case of authorized user, the system allows fingerprint sensor to validate the person followed by sending either PICTURE password or OTP via SIM using GSM module to the user registered mobile number saved in database (local SD card) in order to access the door. If the entered password matches, door will be opened automatically otherwise a message showing incorrect password will be displayed on TFT display and a notification will be sent to the owner that the security was tried to be breached. This hardware project achieves 3 levels of security with commonly available component and also consumes less power. This system also has an option to unlock the door through SMS in case of emergency by the ADMIN.
当我们远离我们的家庭单位时，安全是每个人都关注的严重问题。在目前的情况下，还没有找到上述问题的可接受的答案。这里介绍一个电子安全框架，由Arduino承担准备单元的工作。Arduino是一个微控制器板，在优步家族中占有一席之地。它是一个开源的直接工具。它可以检测、筛选、存储和控制应用程序。入口通道的访问控制使用Arduino Mega 2560板完成。此任务显示一个无密钥框架，用于使用预定义的PICTURE秘密密钥和OTP进行锁定和打开。通过将OTP和PICTURE密码发送给ADMIN以获取OTP和PICTURE密码，确保未经授权的人员访问，其中人员需要联系ADMIN以获取OTP和PICTURE密码。它通过2.8″TFT触摸显示器输入，该显示器显示所有UI消息并接受用户的输入。在授权用户的情况下，系统允许指纹传感器验证人，然后通过使用GSM模块的SIM发送图片密码或OTP到数据库中保存的用户注册手机号码(本地SD卡)，以便进入门。如果输入的密码匹配，门将自动打开，否则将在TFT显示器上显示密码不正确的消息，并向业主发送安全试图突破的通知。该硬件项目采用通用组件实现三级安全，功耗更低。该系统还具有管理员在紧急情况下通过短信开门的选项。
{"title":"Arduino Based Smart Fingerprint Authentication System","authors":"N. Meenakshi, M. Monish, K. Dikshit, S. Bharath","doi":"10.1109/ICIICT1.2019.8741459","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741459","url":null,"abstract":"Security is the serious issue looked by everybody when we are far from our family unit. In the present situation acceptable answer for the above issue isn’t yet found. Introduced here is an electronic securing framework which Arduino assumes the job of the preparing unit. Arduino which is a microcontroller board has a place with at uber family. It is an open source straight forward instrument. It can detect, screen, store and control application. Access control for the entryway is accomplished utilizing Arduino Mega 2560 board. This task displays a keyless framework for locking and opening purposes utilizing a predefined PICTURE secret key and OTP. Unauthorized person access is ensured by sending OTP and PICTURE password to ADMIN to get OTP and PICTURE password where the person needs to contact the ADMIN to get OTP and PICTURE password. It is entered through the 2.8″ TFT touch display, which display all the UI messages and takes inputs from user. In case of authorized user, the system allows fingerprint sensor to validate the person followed by sending either PICTURE password or OTP via SIM using GSM module to the user registered mobile number saved in database (local SD card) in order to access the door. If the entered password matches, door will be opened automatically otherwise a message showing incorrect password will be displayed on TFT display and a notification will be sent to the owner that the security was tried to be breached. This hardware project achieves 3 levels of security with commonly available component and also consumes less power. This system also has an option to unlock the door through SMS in case of emergency by the ADMIN.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128427685","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741426
P. Ranjana, S. Sridevi, T. Sudalai Muthu, V. V. Gnanaraj
In the present digitized world fleet management is done on the two wheelers by fixing the fuel with fixed laboratory condition. But in the real world, the mileage prediction will change based on various factors like the driving style of the driver, driving speed, road condition, traffic condition etc. So to have an effective fleet management a Machine learning multi feature regression is modeled to predict the distance to be travelled by the two wheelers with the available fuel. It is designed using the sensors placed on the two wheelers and the petrol tank, through which the values obtained through the sensors are applied on regression model to predict the mileage in real time with more accuracy.
{"title":"Machine Learning Algorithm in Two wheelers fuel Prediction","authors":"P. Ranjana, S. Sridevi, T. Sudalai Muthu, V. V. Gnanaraj","doi":"10.1109/ICIICT1.2019.8741426","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741426","url":null,"abstract":"In the present digitized world fleet management is done on the two wheelers by fixing the fuel with fixed laboratory condition. But in the real world, the mileage prediction will change based on various factors like the driving style of the driver, driving speed, road condition, traffic condition etc. So to have an effective fleet management a Machine learning multi feature regression is modeled to predict the distance to be travelled by the two wheelers with the available fuel. It is designed using the sensors placed on the two wheelers and the petrol tank, through which the values obtained through the sensors are applied on regression model to predict the mileage in real time with more accuracy.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133740181","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 : 2019-04-25DOI: 10.1109/ICIICT1.2019.8741438
Indhraom Prabha M, G. Umarani Srikanth
This paper presents a detailed review of deep learning techniques used in Sentiment Analysis. Sentiment analysis is one of the most researched areas in natural language processing. Natural language processing has a wide range of applications like voice recognition, machine translation, product review, aspect oriented product analysis, sentiment analysis and text classification like email categorization and spam filtering. The conventional methods used for sentiment analysis is lexicon based processing. However, with the advancements in the field of artificial intelligence, the machine learning algorithms started to play a major role in sentiment analysis applications. Currently deep learning technique is the latest hotspot being used for predicting the sentiments. Several research works have been carried out in the Natural Language Processing (NLP) using the deep learning methods. The most popular deep learning methods employed includes Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) particularly the Long Short Term Memory (LSTM). These techniques are used in combination or as stand-alone based on the domain area of application. The focus of this survey is on the various flavors of the deep learning methods used in different applications of sentiment analysis at sentence level and aspect/target level. Furthermore, the advantages and drawbacks of the methods are discussed along with their performance parameters.
{"title":"Survey of Sentiment Analysis Using Deep Learning Techniques","authors":"Indhraom Prabha M, G. Umarani Srikanth","doi":"10.1109/ICIICT1.2019.8741438","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741438","url":null,"abstract":"This paper presents a detailed review of deep learning techniques used in Sentiment Analysis. Sentiment analysis is one of the most researched areas in natural language processing. Natural language processing has a wide range of applications like voice recognition, machine translation, product review, aspect oriented product analysis, sentiment analysis and text classification like email categorization and spam filtering. The conventional methods used for sentiment analysis is lexicon based processing. However, with the advancements in the field of artificial intelligence, the machine learning algorithms started to play a major role in sentiment analysis applications. Currently deep learning technique is the latest hotspot being used for predicting the sentiments. Several research works have been carried out in the Natural Language Processing (NLP) using the deep learning methods. The most popular deep learning methods employed includes Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) particularly the Long Short Term Memory (LSTM). These techniques are used in combination or as stand-alone based on the domain area of application. The focus of this survey is on the various flavors of the deep learning methods used in different applications of sentiment analysis at sentence level and aspect/target level. Furthermore, the advantages and drawbacks of the methods are discussed along with their performance parameters.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"198200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132605392","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：