Pub Date : 2019-01-01DOI: 10.1109/ICGHIT.2019.00035
Aftab Saad Sohail, Maria Sameen, Qazi Ahmed
This study proposes mathematical tools derived from topology and category theory along with computational linguistics which can be used to analyze the linguistics of the monetary policy statements and quantify its tone.
{"title":"Formal Notations of Linguistic Analysis for Monetary Policy","authors":"Aftab Saad Sohail, Maria Sameen, Qazi Ahmed","doi":"10.1109/ICGHIT.2019.00035","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00035","url":null,"abstract":"This study proposes mathematical tools derived from topology and category theory along with computational linguistics which can be used to analyze the linguistics of the monetary policy statements and quantify its tone.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128996551","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 : 2019-01-01DOI: 10.1109/ICGHIT.2019.00029
Young-Sun Yun, Jinmang Jung, Seongbae Eun, Shin Cha, S. So
Voice conversion is the transform technique of the individuality between source and target speakers. In the previous studies, we proposed the voice conversion using synthesized speeches based on formant or line spectral information. The suggested method used the piecewise linear transform function of formant or LSP(line spectral pairs) features on formant intervals. In this paper, we propose the conversion of the individuality between speakers using a deep neural network. Along with improvements in deep neural network research, end-to-end speech conversion methods have been proposed and the results are suitable for generating more natural utterances compared to the past. Among them, we explore the representative speech generation methods and propose the voice conversion system to use formant features as additional information for local and global conditioned deep neural networks.
{"title":"Voice Conversion of Synthesized Speeches Using Deep Neural Networks","authors":"Young-Sun Yun, Jinmang Jung, Seongbae Eun, Shin Cha, S. So","doi":"10.1109/ICGHIT.2019.00029","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00029","url":null,"abstract":"Voice conversion is the transform technique of the individuality between source and target speakers. In the previous studies, we proposed the voice conversion using synthesized speeches based on formant or line spectral information. The suggested method used the piecewise linear transform function of formant or LSP(line spectral pairs) features on formant intervals. In this paper, we propose the conversion of the individuality between speakers using a deep neural network. Along with improvements in deep neural network research, end-to-end speech conversion methods have been proposed and the results are suitable for generating more natural utterances compared to the past. Among them, we explore the representative speech generation methods and propose the voice conversion system to use formant features as additional information for local and global conditioned deep neural networks.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128586186","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00025
Ittided Poonkasem, N. Theera-Umpon, S. Auephanwiriyakul, D. Patikulsila
The patients with diabetes have a chance to have blindness. An impairment of metabolism can cause a high glucose level in blood vessel leading to an abnormality called hard exudates. Hard exudates are often arranged in clumps or circinate rings and located in the outer layer of the retina. The aim of this research is to detect hard exudates by applying image processing techniques and classify them by using convolutional neuron network (CNN). DIARETDB1 dataset is used in the experiments. The proposed method achieves the area under the curve (AUC) of 0.97 and 0.95 on the training and validation sets, respectively, of 10-fold cross validation experiment. These show that the combination of image processing techniques, three channels of fundus images, and CNN can perform as a promising classification tool in hard exudates detection system.
{"title":"Detection of Hard Exudates in Fundus Images Using Convolutional Neural Networks","authors":"Ittided Poonkasem, N. Theera-Umpon, S. Auephanwiriyakul, D. Patikulsila","doi":"10.1109/ICGHIT.2019.00025","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00025","url":null,"abstract":"The patients with diabetes have a chance to have blindness. An impairment of metabolism can cause a high glucose level in blood vessel leading to an abnormality called hard exudates. Hard exudates are often arranged in clumps or circinate rings and located in the outer layer of the retina. The aim of this research is to detect hard exudates by applying image processing techniques and classify them by using convolutional neuron network (CNN). DIARETDB1 dataset is used in the experiments. The proposed method achieves the area under the curve (AUC) of 0.97 and 0.95 on the training and validation sets, respectively, of 10-fold cross validation experiment. These show that the combination of image processing techniques, three channels of fundus images, and CNN can perform as a promising classification tool in hard exudates detection system.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131701802","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00034
Aftab Saad Sohail, Maria Sameen, Qazi Ahmed
This study proposes an index which can be used to measure the sensitivity of monetary policy communication, based on the value of index positivity or negativity of a sentence is identified. The Latent Dirichlet Allocation algorithm has been applied on extracted monetary policy data and identified words. The clouds of identified words are the quantified which resulted in a single variable; index.
{"title":"Latent Dirichlet Allocation Algorithm using Linguistic Analysis","authors":"Aftab Saad Sohail, Maria Sameen, Qazi Ahmed","doi":"10.1109/ICGHIT.2019.00034","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00034","url":null,"abstract":"This study proposes an index which can be used to measure the sensitivity of monetary policy communication, based on the value of index positivity or negativity of a sentence is identified. The Latent Dirichlet Allocation algorithm has been applied on extracted monetary policy data and identified words. The clouds of identified words are the quantified which resulted in a single variable; index.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114600252","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00013
Wai-Khuen Cheng, A. A. Ileladewa, T. Tan
Recommendation is inevitably crucial in human life, as almost every human daily activity involves decision and choice making from amongst various alternatives at our disposal. The use of computers has made automated decision making interesting, and beneficial in many areas of real-life activities, targeted at meeting different yet specific users' needs, such as in Social Internet of Things (SIoT). SIoT is defined as an emerging paradigm of IoT where intelligent devices are able to create social relationships among them in achieving a goal. Providing particular recommendation by using Social Network Services (SNS) with geographical location-aware feature is one of the interesting SIoT problems. This is mainly because the recommendation is usually constrained by several factors, which pose challenges to us on the available options, and hence having the right information that leads us in taking right decision at the right time is essential. The main contribution of this paper is providing a personalized recommendation framework which is suitable to be adopted in SIoT systems. We also analyzed the performances of the proposed framework with different datasets. Promising results are shown from the analysis.
{"title":"A Personalized Recommendation Framework for Social Internet of Things (SIoT)","authors":"Wai-Khuen Cheng, A. A. Ileladewa, T. Tan","doi":"10.1109/ICGHIT.2019.00013","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00013","url":null,"abstract":"Recommendation is inevitably crucial in human life, as almost every human daily activity involves decision and choice making from amongst various alternatives at our disposal. The use of computers has made automated decision making interesting, and beneficial in many areas of real-life activities, targeted at meeting different yet specific users' needs, such as in Social Internet of Things (SIoT). SIoT is defined as an emerging paradigm of IoT where intelligent devices are able to create social relationships among them in achieving a goal. Providing particular recommendation by using Social Network Services (SNS) with geographical location-aware feature is one of the interesting SIoT problems. This is mainly because the recommendation is usually constrained by several factors, which pose challenges to us on the available options, and hence having the right information that leads us in taking right decision at the right time is essential. The main contribution of this paper is providing a personalized recommendation framework which is suitable to be adopted in SIoT systems. We also analyzed the performances of the proposed framework with different datasets. Promising results are shown from the analysis.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122735604","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00032
Ren-Jun Chong, W. Lee
Industrial Internet of Things (IIoT) is a paradigm shifting technology used for enhancing the manufacturing process. Under this technology, cloud server is widely used to store sensor data collected through various sensor nodes. The stored data is being used for various analysis and computation, including machine learning and statistics, in hope of finding useful inferences for industrial purpose. However, some of these sensor data and analysis results are sensitive, which should be handled properly to protect the user privacy. In addition, the cloud server environment may not be fully trusted, due to potential cyber security attack by adversaries. Encryption is one of the most straightforward way to protect user privacy, but encrypted sensor data prohibits the cloud server to perform any further analysis. Homomorphic encryption is useful to provide encryption to sensor data, yet allow the third party (cloud server) to perform computation on the encrypted data. However, homomorphic encryption algorithm is usually complex and require a lot of computational effort. In this paper, we propose implementation technique to accelerate the ElGamal partial homomorphic encryption in GPU platform. This implementation allows homomorphic multiplication to be performed on cloud server for IIoT applications at high performance, yet able to protect the user privacy.
{"title":"Accelerating ElGamal Partial Homomorphic Encryption with GPU Platform for Industrial Internet of Things","authors":"Ren-Jun Chong, W. Lee","doi":"10.1109/ICGHIT.2019.00032","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00032","url":null,"abstract":"Industrial Internet of Things (IIoT) is a paradigm shifting technology used for enhancing the manufacturing process. Under this technology, cloud server is widely used to store sensor data collected through various sensor nodes. The stored data is being used for various analysis and computation, including machine learning and statistics, in hope of finding useful inferences for industrial purpose. However, some of these sensor data and analysis results are sensitive, which should be handled properly to protect the user privacy. In addition, the cloud server environment may not be fully trusted, due to potential cyber security attack by adversaries. Encryption is one of the most straightforward way to protect user privacy, but encrypted sensor data prohibits the cloud server to perform any further analysis. Homomorphic encryption is useful to provide encryption to sensor data, yet allow the third party (cloud server) to perform computation on the encrypted data. However, homomorphic encryption algorithm is usually complex and require a lot of computational effort. In this paper, we propose implementation technique to accelerate the ElGamal partial homomorphic encryption in GPU platform. This implementation allows homomorphic multiplication to be performed on cloud server for IIoT applications at high performance, yet able to protect the user privacy.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128611291","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00026
A. Choudhary, D. C. Meena, Animesh Kumar Patra
Fault diagnosis is a crucial part of electrical engineering. Faults are bound to happen, so we need some diagnosis techniques for fault detection and mitigation. Asynchronous motor are widely used in industries today and occurrence of fault is a common problem. This paper discusses simulink modeling of asynchronous motor in_healthy_and faulty_conditions. Both rotor and stator faults_are discussed. Modeling is done in MATLAB/Simulink environment.
{"title":"Asynchronous Motor Modeling in Simulink for Stator and Rotor Fault Analysis","authors":"A. Choudhary, D. C. Meena, Animesh Kumar Patra","doi":"10.1109/ICGHIT.2019.00026","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00026","url":null,"abstract":"Fault diagnosis is a crucial part of electrical engineering. Faults are bound to happen, so we need some diagnosis techniques for fault detection and mitigation. Asynchronous motor are widely used in industries today and occurrence of fault is a common problem. This paper discusses simulink modeling of asynchronous motor in_healthy_and faulty_conditions. Both rotor and stator faults_are discussed. Modeling is done in MATLAB/Simulink environment.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133448673","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00015
Maythem K. Abbas, Tan Jung Low, Raed M. T. Abdulla
Fatal road accidents are increasing because of fast driving. Nowadays, Road traffic departments are provided with different types of speed traps and cameras to place at some roads segments for the sake of detecting the speed offenders, which might help in reducing the problem. Many drivers know where those cameras and speed traps are, so they tend to reduce their speeds when approaching those cameras then, increase it back when leaving the cameras' visibility area. This research proposes a concept of an unavoidable speed offence detection system for smart cities and highways in a try of controlling the problem. The system proposes placing a set of Vehicular Ad-Hoc Network (VANET) devices on the roadside and within the vehicles to achieve side to side communication. The provided communication would be responsible for delivering real time information about the cars' instant status, including its speed, which would help in detecting the speeding offenders. By conducting this research, it is expected to produce a prototype of the system which would warn the speeding drivers at any time about their offence and to ensure a fine will be issued for every offender. In addition, the proposed system is expected to help traffic policemen in doing their job of identifying and proving that a driver has broken the road driving rules.
{"title":"Automated Fining System for High Speed Driving Offences via VANET","authors":"Maythem K. Abbas, Tan Jung Low, Raed M. T. Abdulla","doi":"10.1109/ICGHIT.2019.00015","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00015","url":null,"abstract":"Fatal road accidents are increasing because of fast driving. Nowadays, Road traffic departments are provided with different types of speed traps and cameras to place at some roads segments for the sake of detecting the speed offenders, which might help in reducing the problem. Many drivers know where those cameras and speed traps are, so they tend to reduce their speeds when approaching those cameras then, increase it back when leaving the cameras' visibility area. This research proposes a concept of an unavoidable speed offence detection system for smart cities and highways in a try of controlling the problem. The system proposes placing a set of Vehicular Ad-Hoc Network (VANET) devices on the roadside and within the vehicles to achieve side to side communication. The provided communication would be responsible for delivering real time information about the cars' instant status, including its speed, which would help in detecting the speeding offenders. By conducting this research, it is expected to produce a prototype of the system which would warn the speeding drivers at any time about their offence and to ensure a fine will be issued for every offender. In addition, the proposed system is expected to help traffic policemen in doing their job of identifying and proving that a driver has broken the road driving rules.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133400519","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00010
Hyunjung Kim, Jong Wook Kim, Beakcheol Jang
The indoor positioning technology has been attracting the attention of researchers due to the increasing pervasiveness of smartphones and the development of sensor technology along with the increase of time that modern people spend indoor. Sensor technology, which is the most commonly used data source for indoor positioning, has an advantage that sensors can receive data from smartphone without installing the device separately. However, indoor positioning technology which depends only on sensor data, has the disadvantage of cumulatively accumulating errors. To solve this problem, techniques using landmarks which make a singular point of indoor localization are studied. In this paper, we provide a system that combines crowd sourcing technique and landmarks to receive data from many unspecified users. Our proposed system updates the indoor landmark map by automatically removing the unused landmarks for a long time and adding more landmarks through crowd sourcing. The system calculates the location of the user through the SLAM algorithm using the improved landmark map.
{"title":"Indoor Positioning System using Sensor and Crowdsourcing Landmark Map Update","authors":"Hyunjung Kim, Jong Wook Kim, Beakcheol Jang","doi":"10.1109/ICGHIT.2019.00010","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00010","url":null,"abstract":"The indoor positioning technology has been attracting the attention of researchers due to the increasing pervasiveness of smartphones and the development of sensor technology along with the increase of time that modern people spend indoor. Sensor technology, which is the most commonly used data source for indoor positioning, has an advantage that sensors can receive data from smartphone without installing the device separately. However, indoor positioning technology which depends only on sensor data, has the disadvantage of cumulatively accumulating errors. To solve this problem, techniques using landmarks which make a singular point of indoor localization are studied. In this paper, we provide a system that combines crowd sourcing technique and landmarks to receive data from many unspecified users. Our proposed system updates the indoor landmark map by automatically removing the unused landmarks for a long time and adding more landmarks through crowd sourcing. The system calculates the location of the user through the SLAM algorithm using the improved landmark map.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129943166","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 : 1900-01-01DOI: 10.1109/ICGHIT.2019.00033
Aneeqa Mumrez, Hira Tariq, Ushna Ajmal, M. Abrar
Technology has always tried to help mankind. In this age of science and technology, man is trying to move towards ease and comfort using technology. Technology is being implemented to save money and time both. IoT has changed the way a human thinks. Advancements in ICT and IOT has opened many new research avenues for mankind. Before man thought about how he can become expert in something and provide his services but now man has changed his view and is trying to use technology to do every task without human interference. This research paper provides all the details to implement one of IOT's application and serve humanity. This is all about remote patient monitoring system which is capable enough to measure human body temperature, pulse rate, and blood pressure and send it to the doctor who can access it from anywhere in the world.
{"title":"IOT- Based Framework for E-Health Monitoring System","authors":"Aneeqa Mumrez, Hira Tariq, Ushna Ajmal, M. Abrar","doi":"10.1109/ICGHIT.2019.00033","DOIUrl":"https://doi.org/10.1109/ICGHIT.2019.00033","url":null,"abstract":"Technology has always tried to help mankind. In this age of science and technology, man is trying to move towards ease and comfort using technology. Technology is being implemented to save money and time both. IoT has changed the way a human thinks. Advancements in ICT and IOT has opened many new research avenues for mankind. Before man thought about how he can become expert in something and provide his services but now man has changed his view and is trying to use technology to do every task without human interference. This research paper provides all the details to implement one of IOT's application and serve humanity. This is all about remote patient monitoring system which is capable enough to measure human body temperature, pulse rate, and blood pressure and send it to the doctor who can access it from anywhere in the world.","PeriodicalId":160708,"journal":{"name":"2019 International Conference on Green and Human Information Technology (ICGHIT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116911254","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：