Pub Date : 2018-02-01DOI: 10.23919/ICACT.2018.8323921
Muhammad Hanif, Choonhwa Lee
Big data and cloud computing became the centre of interest for the past decade. With the increase of data size and different cloud application, the idea of big data analytics become very popular both in industry and academia. The research communities in industry and academia never stopped trying to come up with the fast, robust, and fault tolerant analytic engines. MapReduce becomes one of the popular big data analytic engine over the past few years. Hadoop is a standard implementation of MapReduce framework for running data-intensive applications on the clusters of commodity servers. By thoroughly studying the framework we find out that the shuffle phase, all-to-all input data fetching phase in reduce task significantly affect the application performance. There is a problem of variance in both the intermediate key's frequencies and their distribution among data nodes throughout the cluster in Hadoop's MapReduce system. This variance in system causes network overhead which leads to unfairness on the reduce input among different data nodes in the cluster. Because of the above problems, applications experience performance degradation due to shuffle phase of MapReduce applications. We develop a new novel algorithm; unlike previous systems our algorithm considers each node's capabilities as heuristics to decide a better available trade-off for the locality and fairness in the system. By comparing with the default Hadoop's partitioning algorithm and Leen partitioning algorithm: a). In case of 2 million key-value pairs to process, on the average our approach achieve better resource utilization by about 19%, and 9%, in that order; b). In case of 3 million key-value pairs to process, our approach achieve near optimal resource utilization by about 15%, and 7%, respectively.
{"title":"Capacity-aware key partitioning scheme for heterogeneous big data analytic engines","authors":"Muhammad Hanif, Choonhwa Lee","doi":"10.23919/ICACT.2018.8323921","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323921","url":null,"abstract":"Big data and cloud computing became the centre of interest for the past decade. With the increase of data size and different cloud application, the idea of big data analytics become very popular both in industry and academia. The research communities in industry and academia never stopped trying to come up with the fast, robust, and fault tolerant analytic engines. MapReduce becomes one of the popular big data analytic engine over the past few years. Hadoop is a standard implementation of MapReduce framework for running data-intensive applications on the clusters of commodity servers. By thoroughly studying the framework we find out that the shuffle phase, all-to-all input data fetching phase in reduce task significantly affect the application performance. There is a problem of variance in both the intermediate key's frequencies and their distribution among data nodes throughout the cluster in Hadoop's MapReduce system. This variance in system causes network overhead which leads to unfairness on the reduce input among different data nodes in the cluster. Because of the above problems, applications experience performance degradation due to shuffle phase of MapReduce applications. We develop a new novel algorithm; unlike previous systems our algorithm considers each node's capabilities as heuristics to decide a better available trade-off for the locality and fairness in the system. By comparing with the default Hadoop's partitioning algorithm and Leen partitioning algorithm: a). In case of 2 million key-value pairs to process, on the average our approach achieve better resource utilization by about 19%, and 9%, in that order; b). In case of 3 million key-value pairs to process, our approach achieve near optimal resource utilization by about 15%, and 7%, respectively.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116483556","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323863
S. Aich, K. Younga, Kueh Lee Hui, A. Al-Absi, M. Sain
In the past few years, lot of researchers are working to get some breakthrough for early detection of Parkinson's disease. As the old age population is increasing at a higher rate as well as it is predicted that the old age population will increase to a much higher total by 2050, it's a become a rising concern to the developed countries because the cost due to the healthcare service of these disease is really high. Parkinson's disease (PD) belongs to the group of neurological disorder, which directly affect the bra in cells and the effect is shown in terms of movement, voice and other cognitive disabilities. Researchers are keep working on different fields such as gait analysis as well as on speech analysis to find the predictors of the Parkinson's disease. Recently machine learning based approach has been used by many researchers across the field because of its accuracy on the complex data. Machine learning based approach has been used in many cases of Parkinson's disease using gait data as well as voice data. However, so far no body ha s compared the performance metrics using different feature sets by applying non-linear based classification approach based on the voice data. So in this paper we have proposed a new approach by comparing the performance metrics with different feature sets such as original feature sets as well as Principal component Analysis based feature reduction technique for selecting the feature sets. We have used non-linear based classification approach to compare the performance metrics. We have found an accuracy of 96.83% using random forest classifiers using PCA based feature sets. This analysis will help the clinicians to differentiate the PD group from healthy group based on the voice data.
{"title":"A nonlinear decision tree based classification approach to predict the Parkinson's disease using different feature sets of voice data","authors":"S. Aich, K. Younga, Kueh Lee Hui, A. Al-Absi, M. Sain","doi":"10.23919/ICACT.2018.8323863","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323863","url":null,"abstract":"In the past few years, lot of researchers are working to get some breakthrough for early detection of Parkinson's disease. As the old age population is increasing at a higher rate as well as it is predicted that the old age population will increase to a much higher total by 2050, it's a become a rising concern to the developed countries because the cost due to the healthcare service of these disease is really high. Parkinson's disease (PD) belongs to the group of neurological disorder, which directly affect the bra in cells and the effect is shown in terms of movement, voice and other cognitive disabilities. Researchers are keep working on different fields such as gait analysis as well as on speech analysis to find the predictors of the Parkinson's disease. Recently machine learning based approach has been used by many researchers across the field because of its accuracy on the complex data. Machine learning based approach has been used in many cases of Parkinson's disease using gait data as well as voice data. However, so far no body ha s compared the performance metrics using different feature sets by applying non-linear based classification approach based on the voice data. So in this paper we have proposed a new approach by comparing the performance metrics with different feature sets such as original feature sets as well as Principal component Analysis based feature reduction technique for selecting the feature sets. We have used non-linear based classification approach to compare the performance metrics. We have found an accuracy of 96.83% using random forest classifiers using PCA based feature sets. This analysis will help the clinicians to differentiate the PD group from healthy group based on the voice data.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131881014","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323769
Sabeen Javaid, Ali Sufian, Saima Pervaiz, Mehak Tanveer
Traffic management system is a cornerstone of a Smart city. In the current problems of the world, urban mobility is one of the major problems, especially in metropolitan cities. Previous traffic management systems are not capable enough to tackle this growth of traffic on the road networks. The purpose of this paper is to propose a smart traffic management system using the Internet of Things and a decentralized approach to optimize traffic on the roads and intelligent algorithms to manage all traffic situations more accurately. This proposed system is overcoming the flaws of previous traffic management systems. The system takes traffic density as input from cameras which is abstracted from Digital Image Processing technique and sensors data, resultantly giving output as signals management. An algorithm is used to predicts the traffic density for future to minimize the traffic congestion. Besides this, RFIDs are also used to prioritize the emergency vehicles like ambulance, fire brigade etc. by implementing RFID tags in such vehicles. In the case of emergency situations, such as fire explosion or burning of something, fire and smoke sensors are also deployed on the road to detect such situations. Moreover, a mobile application is connected to a centralized server which intimates to nearby rescue department about fire explosion with the location to take further action. In addition, the native user can ask about future traffic condition at a particular node. The proposed system is validated by constructing a prototype and deploying it in a city of Pakistan. A web application is also there to provide useful information in graphical formats to the higher authorities of the smart city which is fruitful in future road planning.
{"title":"Smart traffic management system using Internet of Things","authors":"Sabeen Javaid, Ali Sufian, Saima Pervaiz, Mehak Tanveer","doi":"10.23919/ICACT.2018.8323769","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323769","url":null,"abstract":"Traffic management system is a cornerstone of a Smart city. In the current problems of the world, urban mobility is one of the major problems, especially in metropolitan cities. Previous traffic management systems are not capable enough to tackle this growth of traffic on the road networks. The purpose of this paper is to propose a smart traffic management system using the Internet of Things and a decentralized approach to optimize traffic on the roads and intelligent algorithms to manage all traffic situations more accurately. This proposed system is overcoming the flaws of previous traffic management systems. The system takes traffic density as input from cameras which is abstracted from Digital Image Processing technique and sensors data, resultantly giving output as signals management. An algorithm is used to predicts the traffic density for future to minimize the traffic congestion. Besides this, RFIDs are also used to prioritize the emergency vehicles like ambulance, fire brigade etc. by implementing RFID tags in such vehicles. In the case of emergency situations, such as fire explosion or burning of something, fire and smoke sensors are also deployed on the road to detect such situations. Moreover, a mobile application is connected to a centralized server which intimates to nearby rescue department about fire explosion with the location to take further action. In addition, the native user can ask about future traffic condition at a particular node. The proposed system is validated by constructing a prototype and deploying it in a city of Pakistan. A web application is also there to provide useful information in graphical formats to the higher authorities of the smart city which is fruitful in future road planning.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128634088","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323747
Jorge Quinteros, N. Baloian, J. Pino, Alvaro Riquelme, Sergio Peñafiel, Horacio Sanson, Douglas Teoh
The Japanese public health system relies upon a mandatory insurance scheme that subsidizes every medical procedure. This causes some practitioners in doubt to order unnecessary exams, especially in departments like the emergency room (ER) (where time and personnel constraints apply), generating additional costs for the public health system. In this context arises the need and challenge of developing a computer application based on Artificial Intelligence that, given a patient's symptoms upon entering the ER, recommends the most appropriate exams to increase the accuracy of the diagnosis. This paper presents the preliminary results on the development of such a tool using a Bayesian Network (BN). Although there is a lot of literature on BN for medical diagnosis, this work is innovative as it is focused on suggesting useful exams based on pre-test probabilities, and that it was built using only medical data and other freely available information sources. A fundamental disease list was established using a Human Symptom-Disease Network (HSDN) containing symptom-disease relationships. The co-occurrence between disease and symptom terms on the HSDN was translated into rough sensitivity and specificity estimates and used to set the conditional probabilities of the BN. Prior probabilities of diseases were estimated using hospital data of regular and emergency visits. Information about findings (exams) and their sensitivity-specificity data was scraped from web databases and mapped into the network. Preliminary tests for inspecting the accuracy of the developed tool were made with the help of a medical expert, based on relevant literature. Obtained results show that the tool is able to find differential diagnoses for most cases. This work opens the door for future improvements of the system.
{"title":"Diagnostic test suggestion via Bayesian network of non-expert assisted knowledge base","authors":"Jorge Quinteros, N. Baloian, J. Pino, Alvaro Riquelme, Sergio Peñafiel, Horacio Sanson, Douglas Teoh","doi":"10.23919/ICACT.2018.8323747","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323747","url":null,"abstract":"The Japanese public health system relies upon a mandatory insurance scheme that subsidizes every medical procedure. This causes some practitioners in doubt to order unnecessary exams, especially in departments like the emergency room (ER) (where time and personnel constraints apply), generating additional costs for the public health system. In this context arises the need and challenge of developing a computer application based on Artificial Intelligence that, given a patient's symptoms upon entering the ER, recommends the most appropriate exams to increase the accuracy of the diagnosis. This paper presents the preliminary results on the development of such a tool using a Bayesian Network (BN). Although there is a lot of literature on BN for medical diagnosis, this work is innovative as it is focused on suggesting useful exams based on pre-test probabilities, and that it was built using only medical data and other freely available information sources. A fundamental disease list was established using a Human Symptom-Disease Network (HSDN) containing symptom-disease relationships. The co-occurrence between disease and symptom terms on the HSDN was translated into rough sensitivity and specificity estimates and used to set the conditional probabilities of the BN. Prior probabilities of diseases were estimated using hospital data of regular and emergency visits. Information about findings (exams) and their sensitivity-specificity data was scraped from web databases and mapped into the network. Preliminary tests for inspecting the accuracy of the developed tool were made with the help of a medical expert, based on relevant literature. Obtained results show that the tool is able to find differential diagnoses for most cases. This work opens the door for future improvements of the system.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134468554","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323935
Jinhyung Oh, Youngjun Chong
The 3.5GHz band was determined as the mobile communication frequency in IMT-2020. Basically, TD-LTE in small cell environment and supplementary downlink in hotspot area will be used in 3.5GHz band. In addition, the frequency resources are becoming insufficient over time due to the explosive increase in the radio equipment. If we use frequency resources in a time and space based sharing manner, it is expected that we will be able to efficiently use the scarce frequency resources. According to recent trends, the channel sounder for the 3.5GHz band consists of a universal device such as NI equipment for baseband and transceiver and its own modules which are high power amplifier, RF switch, timing module and antenna. In this paper, we introduce the channel sounder and have verified various measurement parameters such as path loss, delay spread, K-factor and channel capacity for actual radio measurements through this channel sounder in urban and suburban areas in the 3.5GHz band. Additionally, we show the result of the path loss modelling with time and space rate using this system.
{"title":"A detailed large-scale radio propagation characteristics: Approaches with time and spatial ratio","authors":"Jinhyung Oh, Youngjun Chong","doi":"10.23919/ICACT.2018.8323935","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323935","url":null,"abstract":"The 3.5GHz band was determined as the mobile communication frequency in IMT-2020. Basically, TD-LTE in small cell environment and supplementary downlink in hotspot area will be used in 3.5GHz band. In addition, the frequency resources are becoming insufficient over time due to the explosive increase in the radio equipment. If we use frequency resources in a time and space based sharing manner, it is expected that we will be able to efficiently use the scarce frequency resources. According to recent trends, the channel sounder for the 3.5GHz band consists of a universal device such as NI equipment for baseband and transceiver and its own modules which are high power amplifier, RF switch, timing module and antenna. In this paper, we introduce the channel sounder and have verified various measurement parameters such as path loss, delay spread, K-factor and channel capacity for actual radio measurements through this channel sounder in urban and suburban areas in the 3.5GHz band. Additionally, we show the result of the path loss modelling with time and space rate using this system.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126996690","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323907
Chi-Yurl Yoon, Miyoung Huh, Shin-Gak Kang, Juyoung Park, Changkyu Lee
With the advent of Internet of Things (IoT) and industrialization, the development of Information Technology (IT) has led to various studies not only in industry but also in agriculture. Especially, IoT technology can overcome distance and place constraints of wired communication systems used in existing farms, and can expect agricultural IT development from automation of agricultural data collection. In this paper, smart farm system using low power Bluetooth and Low Power Wide Area Networks (LPWAN) communication modules including the wired communication network used in the existing farm was constructed. In addition, the system implements the monitoring and control functions using the MQ Telemetry Transport (MQTT) communication method, which is an IoT dedicated protocol, thereby enhancing the possibility of development of agricultural IoT.
{"title":"Implement smart farm with IoT technology","authors":"Chi-Yurl Yoon, Miyoung Huh, Shin-Gak Kang, Juyoung Park, Changkyu Lee","doi":"10.23919/ICACT.2018.8323907","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323907","url":null,"abstract":"With the advent of Internet of Things (IoT) and industrialization, the development of Information Technology (IT) has led to various studies not only in industry but also in agriculture. Especially, IoT technology can overcome distance and place constraints of wired communication systems used in existing farms, and can expect agricultural IT development from automation of agricultural data collection. In this paper, smart farm system using low power Bluetooth and Low Power Wide Area Networks (LPWAN) communication modules including the wired communication network used in the existing farm was constructed. In addition, the system implements the monitoring and control functions using the MQ Telemetry Transport (MQTT) communication method, which is an IoT dedicated protocol, thereby enhancing the possibility of development of agricultural IoT.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125803092","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323675
S. Velankar, Sakshi Valecha, Shreya Maji
In this paper, we attempt to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value. For the first phase of our investigation, we aim to understand and identify daily trends in the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price. Our data set consists of various features relating to the Bitcoin price and payment network over the course of five years, recorded daily. For the second phase of our investigation, using the available information, we will predict the sign of the daily price change with highest possible accuracy.
{"title":"Bitcoin price prediction using machine learning","authors":"S. Velankar, Sakshi Valecha, Shreya Maji","doi":"10.23919/ICACT.2018.8323675","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323675","url":null,"abstract":"In this paper, we attempt to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value. For the first phase of our investigation, we aim to understand and identify daily trends in the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price. Our data set consists of various features relating to the Bitcoin price and payment network over the course of five years, recorded daily. For the second phase of our investigation, using the available information, we will predict the sign of the daily price change with highest possible accuracy.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127957508","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323699
En-Chun Kuo, M. Chang, Da-Yu Kao
Open wireless network services are now freely shared in the most of the public areas but have barely protection about communication data between the web server and the client-side. Evil Twin Attack (ETA) appears to be a legitimate Wi-Fi Access Point (AP) and becomes a common attack in smart home environments where attackers can compromise the security of the connected devices. By setting up a rogue access point, deceiving users into establishing the network connection with the same SSID as the legitimate one, the attacker can launch the man-in-the-middle attack and steal some private information. To identify the fake APs, this paper presents an improved and practical client-side detection method to mathematically detect the ETA by observing the time-delay of TCP connection termination between the client and the server. This proposed time-delay model is further experimented and measured from the following three date-time intervals: Initial Ending, Ending Response, and Confirmed Ending. The utility of this model is illustrated by applying it to the client side which makes it more convenient for users to deploy and ensure their security with high detection rate.
{"title":"User-side evil twin attack detection using time-delay statistics of TCP connection termination","authors":"En-Chun Kuo, M. Chang, Da-Yu Kao","doi":"10.23919/ICACT.2018.8323699","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323699","url":null,"abstract":"Open wireless network services are now freely shared in the most of the public areas but have barely protection about communication data between the web server and the client-side. Evil Twin Attack (ETA) appears to be a legitimate Wi-Fi Access Point (AP) and becomes a common attack in smart home environments where attackers can compromise the security of the connected devices. By setting up a rogue access point, deceiving users into establishing the network connection with the same SSID as the legitimate one, the attacker can launch the man-in-the-middle attack and steal some private information. To identify the fake APs, this paper presents an improved and practical client-side detection method to mathematically detect the ETA by observing the time-delay of TCP connection termination between the client and the server. This proposed time-delay model is further experimented and measured from the following three date-time intervals: Initial Ending, Ending Response, and Confirmed Ending. The utility of this model is illustrated by applying it to the client side which makes it more convenient for users to deploy and ensure their security with high detection rate.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126326918","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323873
Wonjoo Park, Jeong-Woo Son, Sang-Yun Lee, Sun-Joong Kim
We propose a clip recommendation technology based on topic similarity. Topics of a clip can represent semantics of each contents. When the topic distributions for clips are similar, it means they are alike. In this paper, we propose a system to learn topic distributions for broadcast contents and link clips based on topics similarity of each clip. The higher the similarity is among the clips, the higher the semantic is among them. This system can be adopted clip recommendation with audiences viewing history and their interest.
{"title":"Clip recommendation based on topic similarity","authors":"Wonjoo Park, Jeong-Woo Son, Sang-Yun Lee, Sun-Joong Kim","doi":"10.23919/ICACT.2018.8323873","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323873","url":null,"abstract":"We propose a clip recommendation technology based on topic similarity. Topics of a clip can represent semantics of each contents. When the topic distributions for clips are similar, it means they are alike. In this paper, we propose a system to learn topic distributions for broadcast contents and link clips based on topics similarity of each clip. The higher the similarity is among the clips, the higher the semantic is among them. This system can be adopted clip recommendation with audiences viewing history and their interest.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117204242","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323739
N. Zhang, Zhiquan Bai, Qi Zhang, Anyang Liu, Shangqian Sun, K. Kwak
In spatial modulation (SM) system, the information bits can be transmitted through two ways, the selection of both the transmit antenna and the constellation symbol. However, conventional bit-to-symbol mapping scheme in SM system only selects the transmit antenna or the constellation symbol independently. With the consideration of the similarity among the transmit antennas and the joint selection of the transmit antenna and the constellation symbol, cosine similarity based bit to symbol-and-antenna mapping scheme is proposed in this paper to reduce the hamming distance between adjacent symbols and achieve better system performance. Simulation results and performance analysis show that the proposed scheme can improve the system average bit error rate (BER) effectively compared with the conventional bit-to-symbol mapping scheme.
{"title":"Cosine similarity based bit to symbol-and-antenna mapping in spatial modulation system","authors":"N. Zhang, Zhiquan Bai, Qi Zhang, Anyang Liu, Shangqian Sun, K. Kwak","doi":"10.23919/ICACT.2018.8323739","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323739","url":null,"abstract":"In spatial modulation (SM) system, the information bits can be transmitted through two ways, the selection of both the transmit antenna and the constellation symbol. However, conventional bit-to-symbol mapping scheme in SM system only selects the transmit antenna or the constellation symbol independently. With the consideration of the similarity among the transmit antennas and the joint selection of the transmit antenna and the constellation symbol, cosine similarity based bit to symbol-and-antenna mapping scheme is proposed in this paper to reduce the hamming distance between adjacent symbols and achieve better system performance. Simulation results and performance analysis show that the proposed scheme can improve the system average bit error rate (BER) effectively compared with the conventional bit-to-symbol mapping scheme.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131905629","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：