Pub Date : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741496
S. Sheeba, T. Jeyaseelan
Tonsillitis is the major problem for children and aged people. There exists a lack of doctors for frequently monitoring and detecting the Tonsillitis. Therefore, it is very important to develop an automated tonsillitis monitoring and detection system. In this project the design and implementation of automated tonsillitis monitoring and detection system using FPGA is proposed. An automated tonsillitis monitoring and detection system aims for separate use also provides portability, a compact size with reliable functionality. In this system a tonsillitis image of a person is acquired through camera and the image is processed for noise reduction. The preprocessed image is further processed to extract tonsil color and size by using boundary detection and feature extraction algorithm. At last, the three stages are determined using classifier. The execution of the proposed method is assessed by comparing the results of proposed experimental system with results of the doctors. The simulation results that shows the red color level of tonsillitis image for normal stage, early stage and final stage lies in the range of (224-243), (185-123) and (39-109) respectively.
{"title":"Design and Implementation of Reconfigurable Architecture for Automatic Monitoring and Detection System for Tonsillitis","authors":"S. Sheeba, T. Jeyaseelan","doi":"10.1109/ICIICT1.2019.8741496","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741496","url":null,"abstract":"Tonsillitis is the major problem for children and aged people. There exists a lack of doctors for frequently monitoring and detecting the Tonsillitis. Therefore, it is very important to develop an automated tonsillitis monitoring and detection system. In this project the design and implementation of automated tonsillitis monitoring and detection system using FPGA is proposed. An automated tonsillitis monitoring and detection system aims for separate use also provides portability, a compact size with reliable functionality. In this system a tonsillitis image of a person is acquired through camera and the image is processed for noise reduction. The preprocessed image is further processed to extract tonsil color and size by using boundary detection and feature extraction algorithm. At last, the three stages are determined using classifier. The execution of the proposed method is assessed by comparing the results of proposed experimental system with results of the doctors. The simulation results that shows the red color level of tonsillitis image for normal stage, early stage and final stage lies in the range of (224-243), (185-123) and (39-109) respectively.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133278350","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741412
P. Bhagyasree, A. James, C. Saravanan
Handwritten Character Recognition (HCR) plays an important role in Optical character Recognition (OCR) and Pattern Recognition (PR), as it has a good number of applications in various fields. HCR contributes extremely to the growth of automation and are applicable in the areas of bank cheque, medical prescriptions, tax returns etc. But handwritten characters are much more difficult to recognize than the printed characters due to difference in writing styles for different people. Both conventional approaches and deep learning techniques have been used for handwritten character recognition. Deep learning techniques such as Convolutional Neural Networks always shows better accuracy than the conventional techniques. In this paper a new deep learning techniques, namely Directed Acyclic Graph - Convolutional Neural Network (DAG-CNN) is used for handwritten character recognition.
{"title":"A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN","authors":"P. Bhagyasree, A. James, C. Saravanan","doi":"10.1109/ICIICT1.2019.8741412","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741412","url":null,"abstract":"Handwritten Character Recognition (HCR) plays an important role in Optical character Recognition (OCR) and Pattern Recognition (PR), as it has a good number of applications in various fields. HCR contributes extremely to the growth of automation and are applicable in the areas of bank cheque, medical prescriptions, tax returns etc. But handwritten characters are much more difficult to recognize than the printed characters due to difference in writing styles for different people. Both conventional approaches and deep learning techniques have been used for handwritten character recognition. Deep learning techniques such as Convolutional Neural Networks always shows better accuracy than the conventional techniques. In this paper a new deep learning techniques, namely Directed Acyclic Graph - Convolutional Neural Network (DAG-CNN) is used for handwritten character recognition.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"12 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132433553","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741432
Pandimurugan V, Jayaprakash R, R. V, Yogeshwar Singh K
The main aim of this paper, to introduce the online based app for applying and renewals of bus pass in the government bus. Those who wish to take a bus pass in the government bus and also renewal of their bus pass within the specific period of time which is easy by using this app
{"title":"Smart Buspass System Using Android","authors":"Pandimurugan V, Jayaprakash R, R. V, Yogeshwar Singh K","doi":"10.1109/ICIICT1.2019.8741432","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741432","url":null,"abstract":"The main aim of this paper, to introduce the online based app for applying and renewals of bus pass in the government bus. Those who wish to take a bus pass in the government bus and also renewal of their bus pass within the specific period of time which is easy by using this app","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132313669","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741445
Jipsha Mariam Dolly, Nisa A K
Multimodal fusion of medical image, as a powerful tool for the application of clinical images has grown with the emergence of various image modalities in medical imaging. The main objective of the image fusion is to merge features from several different input images into one image which becomes more reliable and easy to understand by patients. Fusion of medical image can apply in different areas, like image processing, computer vision, pattern recognition, machine learning and artificial intelligence etc. The fusion of multimodal medical images also helps the doctors for their easy diagnosis and treatments. In this review paper a survey is taken into account on different earlier methods used in fusion of multimodal medical images.
{"title":"A Survey on Different Multimodal Medical Image Fusion Techniques and Methods","authors":"Jipsha Mariam Dolly, Nisa A K","doi":"10.1109/ICIICT1.2019.8741445","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741445","url":null,"abstract":"Multimodal fusion of medical image, as a powerful tool for the application of clinical images has grown with the emergence of various image modalities in medical imaging. The main objective of the image fusion is to merge features from several different input images into one image which becomes more reliable and easy to understand by patients. Fusion of medical image can apply in different areas, like image processing, computer vision, pattern recognition, machine learning and artificial intelligence etc. The fusion of multimodal medical images also helps the doctors for their easy diagnosis and treatments. In this review paper a survey is taken into account on different earlier methods used in fusion of multimodal medical images.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126510975","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741443
Shamin N, P. Fathimal, R. R., K. Prakash
The expansion in populace has prompted gigantic increment in the contamination also. It may peeve numerous relentless diseases for the people. For eliminating or alleviating the garbages and to keep up the cleanness, it requires a smart garbage managing architecture. But there is another severe problem, that to segregate the wastes that has been collected. This paper proposes IoT stationed smart waste segregation and management device which detects the wastes in the dustbins with the aid of using Sensor devices and as soon as it is detected the waste substances in it will be segregated with the help of sensors and right away information is transferred to cloud database via IoT. Microcontroller is utilized as an association between the sensors and IoT module. Ultra-sonic sensor is utilized to distinguish the nearness of the waste material. The moisture sensor is used to analyze and report the moisture content in the waste, and if there is moisture content available then the waste cannot be put in the dustbin. Metal sensor is used to separate the metal items and is separated to a section. Image processing algorithm is used to identify the plastics and degradable items and is separated to another separate sections. The dustbin data are uploaded to the cloud using IoT in real time. This helps in clearing the wastage from dustbin in an efficient and smartest way.
{"title":"Smart Garbage Segregation & Management System Using Internet of Things(IoT) & Machine Learning(ML)","authors":"Shamin N, P. Fathimal, R. R., K. Prakash","doi":"10.1109/ICIICT1.2019.8741443","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741443","url":null,"abstract":"The expansion in populace has prompted gigantic increment in the contamination also. It may peeve numerous relentless diseases for the people. For eliminating or alleviating the garbages and to keep up the cleanness, it requires a smart garbage managing architecture. But there is another severe problem, that to segregate the wastes that has been collected. This paper proposes IoT stationed smart waste segregation and management device which detects the wastes in the dustbins with the aid of using Sensor devices and as soon as it is detected the waste substances in it will be segregated with the help of sensors and right away information is transferred to cloud database via IoT. Microcontroller is utilized as an association between the sensors and IoT module. Ultra-sonic sensor is utilized to distinguish the nearness of the waste material. The moisture sensor is used to analyze and report the moisture content in the waste, and if there is moisture content available then the waste cannot be put in the dustbin. Metal sensor is used to separate the metal items and is separated to a section. Image processing algorithm is used to identify the plastics and degradable items and is separated to another separate sections. The dustbin data are uploaded to the cloud using IoT in real time. This helps in clearing the wastage from dustbin in an efficient and smartest way.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130924337","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741359
Bhagya C, Shyna A
Recent years have witnessed a boundless growth in the field of deep learning. With the preferment in the field of deep learning, the task of object detection has become more exciting and challenging. Object detection focuses on detecting the presence of entire objects within a given image. Deep learning based object detection techniques have shown an efficacy to learn the object features directly from the data. The paper mainly focuses on providing a survey on various state-of-the-art deep learning based object detection techniques. The work also concentrates on providing an extensive comparison regarding the opportunities and obstacles faced by different object detection techniques. The paper concludes by identifying the future golden scopes for research in these fields.
{"title":"An Overview of Deep Learning Based Object Detection Techniques","authors":"Bhagya C, Shyna A","doi":"10.1109/ICIICT1.2019.8741359","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741359","url":null,"abstract":"Recent years have witnessed a boundless growth in the field of deep learning. With the preferment in the field of deep learning, the task of object detection has become more exciting and challenging. Object detection focuses on detecting the presence of entire objects within a given image. Deep learning based object detection techniques have shown an efficacy to learn the object features directly from the data. The paper mainly focuses on providing a survey on various state-of-the-art deep learning based object detection techniques. The work also concentrates on providing an extensive comparison regarding the opportunities and obstacles faced by different object detection techniques. The paper concludes by identifying the future golden scopes for research in these fields.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"48 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114155910","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741469
Shanmuga Sai R, Uma Priyadarsini, M. Nalini
The proposed system is going to deal with a very challenging task of automatically generating presentation slides for academic papers. The wide accessibility of web archives in electronic structures requires a programmed method to mark the records with a predefined set of subjects, what is known as customized Text Categorization (TC). Over the previous decades, it has been seen a substantial number of cutting edge machine learning calculations to address this testing errand. The produced introduction slides can be used as drafts to enable the moderators to set up their formal slides quickly. Documents are usually represented by the "bag-of-words": namely, each word or phrase occurs in documents once or more times is considered as a feature. It initially utilizes the relapse strategy to take in the significance scores of the sentences in a scholastic paper, and afterward a compelling calculation is created for multi-name grouping with using those information that are important to the objectives.The key is the development of a coefficient-based mapping among preparing and test cases, where the mapping relationship abuses the connections among the examples, instead of the unequivocal connection between the factors and the class marks of information and fabricates the staggered classifier on the adjusted low-dimensional data depictions in the meantime. It at first uses the backslide system to take in the importance scores of the sentences in an educational paper, and after that experiences the Latent Dirichlet Allocation (LDA) methodology to make especially sorted out slides by picking and modifying key articulations and sentences to a point for the slide. We set up a sentence scoring model in light of gullible Bayes classifier and use the LDA strategy to modify and expel key articulations and sentences for delivering the slides. Exploratory results exhibit that our technique can deliver very much wanted slides over regular procedures.
{"title":"Cooperative Quality Choice and Categorization for Multilabel Soak Up Process","authors":"Shanmuga Sai R, Uma Priyadarsini, M. Nalini","doi":"10.1109/ICIICT1.2019.8741469","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741469","url":null,"abstract":"The proposed system is going to deal with a very challenging task of automatically generating presentation slides for academic papers. The wide accessibility of web archives in electronic structures requires a programmed method to mark the records with a predefined set of subjects, what is known as customized Text Categorization (TC). Over the previous decades, it has been seen a substantial number of cutting edge machine learning calculations to address this testing errand. The produced introduction slides can be used as drafts to enable the moderators to set up their formal slides quickly. Documents are usually represented by the \"bag-of-words\": namely, each word or phrase occurs in documents once or more times is considered as a feature. It initially utilizes the relapse strategy to take in the significance scores of the sentences in a scholastic paper, and afterward a compelling calculation is created for multi-name grouping with using those information that are important to the objectives.The key is the development of a coefficient-based mapping among preparing and test cases, where the mapping relationship abuses the connections among the examples, instead of the unequivocal connection between the factors and the class marks of information and fabricates the staggered classifier on the adjusted low-dimensional data depictions in the meantime. It at first uses the backslide system to take in the importance scores of the sentences in an educational paper, and after that experiences the Latent Dirichlet Allocation (LDA) methodology to make especially sorted out slides by picking and modifying key articulations and sentences to a point for the slide. We set up a sentence scoring model in light of gullible Bayes classifier and use the LDA strategy to modify and expel key articulations and sentences for delivering the slides. Exploratory results exhibit that our technique can deliver very much wanted slides over regular procedures.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114354909","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741487
V. R, Parthasarathi Rv, Navaneethraj A, S. P, M. Ka, Karan S
Hypaponics is a monitoring system which takes care of integrated vertical farming. Hypaponics contains fields like Aquaponics, Agriculture and poultry. It is monitored using various sensors and the predictions are taken based on the data using Machine Learning Algorithms. These are the advantages for the farmers to decrease their water, fertilizer usage in farm and to increase their profit hence it gives multiple ways for the income. It also gives pure organic food to eat. We can also use Solar power panels for energy. This also helps the environment to lead a healthy life free from pollution. The sensors will be kept inside the hypaponics system. The detailed information about it will be noted under the hardware topic and the data from the IoT will be stored on the cloud (AWS, Microsoft Azure, Google cloud, IBM Cloud, etc) for machine learning. The organic store will be hosted where the organic products are uploaded with their cost. The consumer can check whether its organic or not by the QR code that the consumer found on their pack, where each field, product will have unique QR code in it. The farmers will also get all kind of supports from the help desk they find on the portal. The whole system is monitored 24/7 and the input to farmers are given at a regular intervals of time. The latest technologies like Internet of Things and Machine Learning are used in this project to predict the plants growth and the maintenance charges are also less. The 10% of the water is only consumed by this method while comparing with the ancient irrigation methodologies. This also saves the environment from pollution, food poisoning, diseases.
Hypaponics是一种监控系统，负责综合垂直农业。水培法包括水培、农业和家禽等领域。它使用各种传感器进行监测，并使用机器学习算法根据数据进行预测。这些都是农民在农场中减少水和肥料使用并增加利润的优势，因此它为收入提供了多种途径。它还提供了纯有机食品。我们也可以使用太阳能电池板作为能源。这也有助于让环境远离污染，过上健康的生活。传感器将被保存在低耕系统中。有关它的详细信息将在硬件主题下注明，来自物联网的数据将存储在云(AWS, Microsoft Azure, Google cloud, IBM cloud等)上用于机器学习。有机商店将托管在有机产品上传与他们的成本。消费者可以通过包装上的QR码来检查其是否有机，每个领域，产品都会有唯一的QR码。农民也将从他们在门户网站上找到的帮助台获得各种支持。整个系统全天候监控，每隔一段时间向农民提供投入。该项目采用了物联网和机器学习等最新技术，预测植物生长，维护费用也更低。与古代的灌溉方法相比，这种方法只消耗了10%的水。这也使环境免受污染，食物中毒，疾病。
{"title":"Hypaponics - Monitoring and Controlling using Internet of Things and Machine Learning","authors":"V. R, Parthasarathi Rv, Navaneethraj A, S. P, M. Ka, Karan S","doi":"10.1109/ICIICT1.2019.8741487","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741487","url":null,"abstract":"Hypaponics is a monitoring system which takes care of integrated vertical farming. Hypaponics contains fields like Aquaponics, Agriculture and poultry. It is monitored using various sensors and the predictions are taken based on the data using Machine Learning Algorithms. These are the advantages for the farmers to decrease their water, fertilizer usage in farm and to increase their profit hence it gives multiple ways for the income. It also gives pure organic food to eat. We can also use Solar power panels for energy. This also helps the environment to lead a healthy life free from pollution. The sensors will be kept inside the hypaponics system. The detailed information about it will be noted under the hardware topic and the data from the IoT will be stored on the cloud (AWS, Microsoft Azure, Google cloud, IBM Cloud, etc) for machine learning. The organic store will be hosted where the organic products are uploaded with their cost. The consumer can check whether its organic or not by the QR code that the consumer found on their pack, where each field, product will have unique QR code in it. The farmers will also get all kind of supports from the help desk they find on the portal. The whole system is monitored 24/7 and the input to farmers are given at a regular intervals of time. The latest technologies like Internet of Things and Machine Learning are used in this project to predict the plants growth and the maintenance charges are also less. The 10% of the water is only consumed by this method while comparing with the ancient irrigation methodologies. This also saves the environment from pollution, food poisoning, diseases.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114819662","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741492
Archa Gopan, Abid Hussain Muhammed
Image captured by satellite will be degraded due to scattering of the light by the atmospheric particles under challenging environmental conditions like fog, haze, smoke, etc. Hence this will seriously affect the performance of computer vision system. In this paper an image dehazing based on Quad tree subdivision and convolution neural network(CNN) transmission map is developed to provide end to end dehazing. This algorithm will help to recover the image clearly and accurately. Road extraction plays a significant role in traffic management, city planning road monitoring map updating, GPS navigation, etc. After analyzing various road models and features, this paper also presents an effective method for road extraction based on morphological operation and canny edge detection from the dehazed image. Hence provide a fast, simple and accurate method of dehazing and road extraction.
{"title":"Dehazing and Road Feature Extraction from Satellite Images","authors":"Archa Gopan, Abid Hussain Muhammed","doi":"10.1109/ICIICT1.2019.8741492","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741492","url":null,"abstract":"Image captured by satellite will be degraded due to scattering of the light by the atmospheric particles under challenging environmental conditions like fog, haze, smoke, etc. Hence this will seriously affect the performance of computer vision system. In this paper an image dehazing based on Quad tree subdivision and convolution neural network(CNN) transmission map is developed to provide end to end dehazing. This algorithm will help to recover the image clearly and accurately. Road extraction plays a significant role in traffic management, city planning road monitoring map updating, GPS navigation, etc. After analyzing various road models and features, this paper also presents an effective method for road extraction based on morphological operation and canny edge detection from the dehazed image. Hence provide a fast, simple and accurate method of dehazing and road extraction.","PeriodicalId":118897,"journal":{"name":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124550119","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 : 2019-04-01DOI: 10.1109/ICIICT1.2019.8741449
S. Ramachandran, V. Sasireka
Nowadays wearable devices and smartphones have been embedded with sensors, like microphones, global positioning systems (GPS), thermometers, cameras, and accelerometers, which use a sensing paradigm, called mobile crowd sensing. Several individuals employ their mobile devices for extracting and sharing data corresponding to their wish. Mobile crowd sensing is advantaged over traditional sensor networks because of its extensive coverage, high sensing accuracy, and low cost,. Accordingly, this survey presents a distinct mobile crowd sensing techniques. Thus, this review article provides a detailed review of 25 research papers showing the mobile crowd sensing techniques, like task assignment-based methods, group-based recruitment system, green mobile crowd sensing-based techniques and so on. Moreover, an elaborative analysis and discussion are made concerning the evaluation metrics, employed methods, utilized datasets, a tool for implementation, publication year, and energy consumption. Eventually, the research gaps and issues of various mobile crowd sensing techniques are presented for extending the researchers towards a better future scope.
{"title":"Descriptive Study and Analysis Of Crowd Sourcing Techniques in Mobile Social Media Networks","authors":"S. Ramachandran, V. Sasireka","doi":"10.1109/ICIICT1.2019.8741449","DOIUrl":"https://doi.org/10.1109/ICIICT1.2019.8741449","url":null,"abstract":"Nowadays wearable devices and smartphones have been embedded with sensors, like microphones, global positioning systems (GPS), thermometers, cameras, and accelerometers, which use a sensing paradigm, called mobile crowd sensing. Several individuals employ their mobile devices for extracting and sharing data corresponding to their wish. Mobile crowd sensing is advantaged over traditional sensor networks because of its extensive coverage, high sensing accuracy, and low cost,. Accordingly, this survey presents a distinct mobile crowd sensing techniques. Thus, this review article provides a detailed review of 25 research papers showing the mobile crowd sensing techniques, like task assignment-based methods, group-based recruitment system, green mobile crowd sensing-based techniques and so on. Moreover, an elaborative analysis and discussion are made concerning the evaluation metrics, employed methods, utilized datasets, a tool for implementation, publication year, and energy consumption. Eventually, the research gaps and issues of various mobile crowd sensing techniques are presented for extending the researchers towards a better future scope.","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":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130448374","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：