Pub Date : 2017-08-01DOI: 10.1109/ICECOS.2017.8167147
Visa Musa Ibrahim, Z. Abdul-Malek, N. Muhamad, M. I. Mousa, Z. Nawawi, M. Sidik, M. Jambak
A reliable diagnostic technique of Gas insulated switchgear condition monitoring is used in this research for the detection of Sulphur hexafluoride gas (SF6) decomposition products due to its high sensitivity and anti-electromagnetic interference; it is known as decomposition by-product method. A simulated coaxial decomposition chamber was designed and used to simulate the decomposition of SF6 under the effect of fixed metallic artificial defect on the surface of the spacer at the pressure of 0.2MPa when the chamber is energized at a 45KV experimental voltage over the period of 30 hours due to the presence of partial discharge caused by the artificial defect. The decomposition products (HF, SOF2, SOF4, SO2F2, SO2F10, SiF4, SO2, CO, C2F6 and CF4) were detected offline by FTIR spectrometer. These decomposed products and its concentration can be used detect and identify the type and the level of fault in switchgear (contamination fault) before failure for purpose of preventive maintenance.
{"title":"Sulphur hexafluoride gas decomposition products of fixed metallic defect in coaxial gas insulated switchgear","authors":"Visa Musa Ibrahim, Z. Abdul-Malek, N. Muhamad, M. I. Mousa, Z. Nawawi, M. Sidik, M. Jambak","doi":"10.1109/ICECOS.2017.8167147","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167147","url":null,"abstract":"A reliable diagnostic technique of Gas insulated switchgear condition monitoring is used in this research for the detection of Sulphur hexafluoride gas (SF6) decomposition products due to its high sensitivity and anti-electromagnetic interference; it is known as decomposition by-product method. A simulated coaxial decomposition chamber was designed and used to simulate the decomposition of SF6 under the effect of fixed metallic artificial defect on the surface of the spacer at the pressure of 0.2MPa when the chamber is energized at a 45KV experimental voltage over the period of 30 hours due to the presence of partial discharge caused by the artificial defect. The decomposition products (HF, SOF<inf>2</inf>, SOF<inf>4</inf>, SO<inf>2</inf>F<inf>2</inf>, SO<inf>2</inf>F<inf>10</inf>, SiF<inf>4</inf>, SO<inf>2</inf>, CO, C<inf>2</inf>F<inf>6</inf> and CF<inf>4</inf>) were detected offline by FTIR spectrometer. These decomposed products and its concentration can be used detect and identify the type and the level of fault in switchgear (contamination fault) before failure for purpose of preventive maintenance.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"23 1","pages":"270-274"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73988163","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167150
Z. Zakaria, N. Ahmad, Mona Riza Mohd Esa, Z. Adzis, M. Sidik, N. Zainuddin, I. Jambak
In this paper, we reported the wavelet analysis of lightning electric field of Narrow Bipolar Pulses (NBP) measured during two different monsoon season in Johor, Malaysia. The lightning electric field of NBP were divided into Narrow positive Bipolar Pulses (NPBP) and Narrow Negative Bipolar Pulses (NNBP). Analysis on the wavelet and frequency spectrum reveals that the energy spectrum for both NBPs concentrates at higher frequency (200 kHz to 600 kHz) in comparison to return strokes. Further, NBPs radiated higher energy power spectrum during northeast monsoon with average peak power spectrum of the initial stage NNBP and NPBP are 76,650 (V/m)2 and 76309 (V/m)2, respectively.
{"title":"Wavelet analysis of narrow bipolar pulses in tropical region","authors":"Z. Zakaria, N. Ahmad, Mona Riza Mohd Esa, Z. Adzis, M. Sidik, N. Zainuddin, I. Jambak","doi":"10.1109/ICECOS.2017.8167150","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167150","url":null,"abstract":"In this paper, we reported the wavelet analysis of lightning electric field of Narrow Bipolar Pulses (NBP) measured during two different monsoon season in Johor, Malaysia. The lightning electric field of NBP were divided into Narrow positive Bipolar Pulses (NPBP) and Narrow Negative Bipolar Pulses (NNBP). Analysis on the wavelet and frequency spectrum reveals that the energy spectrum for both NBPs concentrates at higher frequency (200 kHz to 600 kHz) in comparison to return strokes. Further, NBPs radiated higher energy power spectrum during northeast monsoon with average peak power spectrum of the initial stage NNBP and NPBP are 76,650 (V/m)2 and 76309 (V/m)2, respectively.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"11 1","pages":"280-284"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78564540","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167174
N. Husni, A. Handayani, S. Nurmaini, I. Yani
This paper represents a cooperative searching strategy of swarm robot in finding and localizing odor source. 3 robots, namely: Cyborg G11, Cyborg G12, and Cyborg G13 were used as agents that form the swarm in this research. The cooperation among the robots trough communication has shown the success of the swarm in odor searching. When one of the agents in swarm robot detected a high concentration of odor in its place, it will use the data of this concentration as its own information in order to decide what position it should go. Moreover, this data was also shared to the other robot trough wireless communication such that they can compare their own data with the data shared to them. By having the information, each agent can decide what solution they should take. The experimental work in this research shows that using communication among the robot can support the robots in searching and finding the odor source.
{"title":"Cooperative searching strategy for swarm robot","authors":"N. Husni, A. Handayani, S. Nurmaini, I. Yani","doi":"10.1109/ICECOS.2017.8167174","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167174","url":null,"abstract":"This paper represents a cooperative searching strategy of swarm robot in finding and localizing odor source. 3 robots, namely: Cyborg G11, Cyborg G12, and Cyborg G13 were used as agents that form the swarm in this research. The cooperation among the robots trough communication has shown the success of the swarm in odor searching. When one of the agents in swarm robot detected a high concentration of odor in its place, it will use the data of this concentration as its own information in order to decide what position it should go. Moreover, this data was also shared to the other robot trough wireless communication such that they can compare their own data with the data shared to them. By having the information, each agent can decide what solution they should take. The experimental work in this research shows that using communication among the robot can support the robots in searching and finding the odor source.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"31 1","pages":"92-97"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81620520","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167138
Mohammad Tariq Meeran, P. Annus, Yannick Le Moullec
This paper focuses on proposing approaches for the improvement of Voice over Internet Protocol (VoIP) service quality in Wireless Mesh Network (WMN). While WMNs have self-healing, self-forming and dynamic topology features, they still pose challenges for the implementation of multimedia applications, such as voice, in various scenarios. The research has been conducted using a network simulator and experiments conducted on three main scenarios with mesh nodes in no-mobility, partial mobility and full mobility deployments. The experiments consider the IEEE 802.11n/g/e/s standards; G.711, G.726 and G.729 voice codecs; and AODV-reactive, OLSR-proactive and HWMP hybrid routing protocols. The measurement and evaluation is based on the Mean Opinion Score (MOS) rating-scale defined by ITU-T standard and supported by the delay, jitter and packet loss metrics. The proposed approaches identify the integration choices and inclusion of supportive mesh nodes in order to improve VoIP quality. The analysis of the results show that our proposed approaches improve the VoIP quality in terms of 5 point MOS rating-scale by 0.2 in no mobility, 2.2 in partial mobility and 0.9 in full mobility scenarios. The results show that whereas minor gains are achieved in the no-mobility scenarios, significant and considerable gains are achieved for the full mobility and partial mobility scenarios, respectively. The results for the two latter cases thus illustrate the merit of the proposed approach.
{"title":"Approaches for improving VoIP QoS in WMNs","authors":"Mohammad Tariq Meeran, P. Annus, Yannick Le Moullec","doi":"10.1109/ICECOS.2017.8167138","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167138","url":null,"abstract":"This paper focuses on proposing approaches for the improvement of Voice over Internet Protocol (VoIP) service quality in Wireless Mesh Network (WMN). While WMNs have self-healing, self-forming and dynamic topology features, they still pose challenges for the implementation of multimedia applications, such as voice, in various scenarios. The research has been conducted using a network simulator and experiments conducted on three main scenarios with mesh nodes in no-mobility, partial mobility and full mobility deployments. The experiments consider the IEEE 802.11n/g/e/s standards; G.711, G.726 and G.729 voice codecs; and AODV-reactive, OLSR-proactive and HWMP hybrid routing protocols. The measurement and evaluation is based on the Mean Opinion Score (MOS) rating-scale defined by ITU-T standard and supported by the delay, jitter and packet loss metrics. The proposed approaches identify the integration choices and inclusion of supportive mesh nodes in order to improve VoIP quality. The analysis of the results show that our proposed approaches improve the VoIP quality in terms of 5 point MOS rating-scale by 0.2 in no mobility, 2.2 in partial mobility and 0.9 in full mobility scenarios. The results show that whereas minor gains are achieved in the no-mobility scenarios, significant and considerable gains are achieved for the full mobility and partial mobility scenarios, respectively. The results for the two latter cases thus illustrate the merit of the proposed approach.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"13 1","pages":"22-27"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73916103","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167153
A. A. Kusuma, B. S. Munir, P. Pramana
This paper discuss about effect of traction substation for high speed railway in Indonesia. The purpose of this paper is to obtain magnitude of voltage and current unbalance due to traction substation that perceived by system and generator adjacent to traction substation. Analysis is performed by doing simulation of 5 scenarios in simple system model that created in power system simulation program. These 5 scenarios are being performed to represent the actual condition of Indonesia power system. Based on the analysis of simulation result, it can be stated that the magnitude of voltage and current unbalance on system and generator are influenced by magnitude of system short circuit level (SCL), position of supply substation to traction location, amount number of power plant near to traction location, percentage impedance of generator transformer, and the magnitude of generator load.
{"title":"Effect of traction substation for high speed railway in Indonesia","authors":"A. A. Kusuma, B. S. Munir, P. Pramana","doi":"10.1109/ICECOS.2017.8167153","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167153","url":null,"abstract":"This paper discuss about effect of traction substation for high speed railway in Indonesia. The purpose of this paper is to obtain magnitude of voltage and current unbalance due to traction substation that perceived by system and generator adjacent to traction substation. Analysis is performed by doing simulation of 5 scenarios in simple system model that created in power system simulation program. These 5 scenarios are being performed to represent the actual condition of Indonesia power system. Based on the analysis of simulation result, it can be stated that the magnitude of voltage and current unbalance on system and generator are influenced by magnitude of system short circuit level (SCL), position of supply substation to traction location, amount number of power plant near to traction location, percentage impedance of generator transformer, and the magnitude of generator load.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"30 1","pages":"295-299"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88922314","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167143
M. Yunus, F. Fatoni, U. Khayam
This paper discusses the measurement and detection of partial discharge (PD) on the metal enclosed power apparatus, mainly on the effect of the presence of metal box on PD induced electromagnetic wave detected by internal loop antenna. The loop antenna was designed, manufactured, and tested using vector network analyzer. The loop antenna shows low return loss and high voltage standing wave ratio. The loop antenna is used for PD measurement. The experimental results show that the presence of metal box gives significant change on the PD signal detected by using loop antenna. Without metal box, the measurement sensitivity decreases because of the high level of background noise. The Metal box acts as electromagnetic wave shielding and reduce the external noise. When the loop antenna placed inside metal box, the measurement sensitivity increases because of the low level of background noise inside metal box.
{"title":"Effect of the presence of metal box on partial discharge detected by internal loop antenna","authors":"M. Yunus, F. Fatoni, U. Khayam","doi":"10.1109/ICECOS.2017.8167143","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167143","url":null,"abstract":"This paper discusses the measurement and detection of partial discharge (PD) on the metal enclosed power apparatus, mainly on the effect of the presence of metal box on PD induced electromagnetic wave detected by internal loop antenna. The loop antenna was designed, manufactured, and tested using vector network analyzer. The loop antenna shows low return loss and high voltage standing wave ratio. The loop antenna is used for PD measurement. The experimental results show that the presence of metal box gives significant change on the PD signal detected by using loop antenna. Without metal box, the measurement sensitivity decreases because of the high level of background noise. The Metal box acts as electromagnetic wave shielding and reduce the external noise. When the loop antenna placed inside metal box, the measurement sensitivity increases because of the low level of background noise inside metal box.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"58 1","pages":"248-253"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87018627","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 : 2017-08-01DOI: 10.1109/ICECOS.2017.8167119
Md Abdullah Al Imran, Sai Peck Lee, M. A. Manazir Ahsan
Architecture patterns and tactics are established architectural solutions widely used as design decisions during software architecture design phase. Architecture pattern provides the skeleton of a system by defining the components and connector required to establish the requirements of the system. It also encourages reusing the architecture to many similar systems or family of systems. Moreover, architecture pattern addresses the non-functional requirements of the system by reasoning the quality attributes aimed to achieve. Selection of appropriate architecture pattern has a direct impact on the success of the system and also to the quality factors of the system. Tactics, on the other hand, are fine-grained design decisions which complement architecture pattern in achieving a certain quality of the software system. However, selection of architectural solutions for the target software system can be a complex task because of the varying impact factors of architecture solutions for different quality requirements. Because of the notable impact factor on the overall system, architectural solutions should not be chosen without proven facts. The main aim of this research is to find the best possible way to achieve an appropriate set of architectural solutions. Therefore, we propose an approach to achieve a suitable set of architectural solutions based on the target quality goals. The proposed approach uses quality goals to retrieve a candidate set of architecture solutions and finally achieve an appropriate set of final architectural solutions by omitting conflicting solutions through mapping relationship impact among architectural solutions. Through a comprehensive case study, the effectiveness of the proposed approach is found in achieving an appropriate set of architectural solutions with no negative confliction among the final solutions.
{"title":"Quality driven architectural solutions selection approach through measuring impact factors","authors":"Md Abdullah Al Imran, Sai Peck Lee, M. A. Manazir Ahsan","doi":"10.1109/ICECOS.2017.8167119","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167119","url":null,"abstract":"Architecture patterns and tactics are established architectural solutions widely used as design decisions during software architecture design phase. Architecture pattern provides the skeleton of a system by defining the components and connector required to establish the requirements of the system. It also encourages reusing the architecture to many similar systems or family of systems. Moreover, architecture pattern addresses the non-functional requirements of the system by reasoning the quality attributes aimed to achieve. Selection of appropriate architecture pattern has a direct impact on the success of the system and also to the quality factors of the system. Tactics, on the other hand, are fine-grained design decisions which complement architecture pattern in achieving a certain quality of the software system. However, selection of architectural solutions for the target software system can be a complex task because of the varying impact factors of architecture solutions for different quality requirements. Because of the notable impact factor on the overall system, architectural solutions should not be chosen without proven facts. The main aim of this research is to find the best possible way to achieve an appropriate set of architectural solutions. Therefore, we propose an approach to achieve a suitable set of architectural solutions based on the target quality goals. The proposed approach uses quality goals to retrieve a candidate set of architecture solutions and finally achieve an appropriate set of final architectural solutions by omitting conflicting solutions through mapping relationship impact among architectural solutions. Through a comprehensive case study, the effectiveness of the proposed approach is found in achieving an appropriate set of architectural solutions with no negative confliction among the final solutions.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"15 1","pages":"131-136"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88100728","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 : 2017-01-01DOI: 10.1109/ICECOS.2017.8167169
E. Dutkiewicz, B. Jayawickrama, Ying He
The high demand for wireless Internet including emerging Internet of Things (IoT) applications is putting extreme pressure on better utilisation of the available radio spectrum. The expected spectrum “crunch” requires highly efficient radio resource management schemes with low complexity and high responsiveness to the changing network conditions. Spectrum sharing is regarded as an essential approach to regaining access to otherwise unused spectrum and it is considered an essential component in the development of IoT and 5G networks. Spectrum sharing can be conducted at different time scales. As the time scale of the operation of spectrum sharing decreases, the possibility for utilising more available spectrum holes increases. However, the shorter time scale brings with it challenges. Efficient decisions regarding the use of spectrum sharing require accurate knowledge of the spatial and temporal spectrum use in a geographical area of interest. This knowledge can be represented in Radio Spectrum Maps which need to be generated efficiently and accurately. In this paper we give an overview of the spectrum sharing concept for IoT and 5G networks. We also present our research on spectrum sharing to enable Smart Building IoT applications.
{"title":"Radio spectrum maps for emerging IoT and 5G networks: Applications to smart buildings","authors":"E. Dutkiewicz, B. Jayawickrama, Ying He","doi":"10.1109/ICECOS.2017.8167169","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167169","url":null,"abstract":"The high demand for wireless Internet including emerging Internet of Things (IoT) applications is putting extreme pressure on better utilisation of the available radio spectrum. The expected spectrum “crunch” requires highly efficient radio resource management schemes with low complexity and high responsiveness to the changing network conditions. Spectrum sharing is regarded as an essential approach to regaining access to otherwise unused spectrum and it is considered an essential component in the development of IoT and 5G networks. Spectrum sharing can be conducted at different time scales. As the time scale of the operation of spectrum sharing decreases, the possibility for utilising more available spectrum holes increases. However, the shorter time scale brings with it challenges. Efficient decisions regarding the use of spectrum sharing require accurate knowledge of the spatial and temporal spectrum use in a geographical area of interest. This knowledge can be represented in Radio Spectrum Maps which need to be generated efficiently and accurately. In this paper we give an overview of the spectrum sharing concept for IoT and 5G networks. We also present our research on spectrum sharing to enable Smart Building IoT applications.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"21 1","pages":"7-9"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84541016","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 : 2017-01-01DOI: 10.1109/ICECOS.2017.8167121
D. Liliana, Chan Basaruddin
In this paper we present a comprehensive review of a well-known sequential classifier in machine learning Conditional Random Fields (CRFs). CRFs is proposed to cope the limitation of both generative Hidden Markov Models (HMMs) and discriminative Maximum Entropy Markov Models (MEMMs) for solving the sequential classification problems. CRFs is widely used to accomplish the sequential classification which has a temporal dimension. On its way, CRFs has been improved both on the structural learning model as well as on the area of implementation. Those areas are varying from information extraction, image understanding, computer vision, behavioral analysis, natural language processing, bioinformatics, etc. This review provides a compact and informative summary of the major research on CRFs. We present a brief description about CRFs fundamental, CRFs roadmap, and CRFs related area of implementation from several literature papers on CRFs. The contribution of this paper is to explore the roadmap of CRFs research and potential prospect in developing CRFs to solve machine learning problems, particularly problems with sequential structures.
{"title":"A review on conditional random fields as a sequential classifier in machine learning","authors":"D. Liliana, Chan Basaruddin","doi":"10.1109/ICECOS.2017.8167121","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167121","url":null,"abstract":"In this paper we present a comprehensive review of a well-known sequential classifier in machine learning Conditional Random Fields (CRFs). CRFs is proposed to cope the limitation of both generative Hidden Markov Models (HMMs) and discriminative Maximum Entropy Markov Models (MEMMs) for solving the sequential classification problems. CRFs is widely used to accomplish the sequential classification which has a temporal dimension. On its way, CRFs has been improved both on the structural learning model as well as on the area of implementation. Those areas are varying from information extraction, image understanding, computer vision, behavioral analysis, natural language processing, bioinformatics, etc. This review provides a compact and informative summary of the major research on CRFs. We present a brief description about CRFs fundamental, CRFs roadmap, and CRFs related area of implementation from several literature papers on CRFs. The contribution of this paper is to explore the roadmap of CRFs research and potential prospect in developing CRFs to solve machine learning problems, particularly problems with sequential structures.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"36 1","pages":"143-148"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74842051","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 : 2017-01-01DOI: 10.1109/ICECOS.2017.8167123
D. Komalasari, M. R. Widyanto, T. Basaruddin, D. Liliana
Facial expression recognition is an active research area in the field of signal social processing. The goal is to distinguish human emotion. The problem is similar emotion, variation of emotion, and independent object through face image. The existing research using various method for modeling human facial to entirely describe facial expression through face image. We consider to variation analysis of the face image using Generalized Procrustes Analysis (GPA) method. GPA is implied for modeling variation of facial expression. We fit our GPA model exact the position of facial skeleton using Active Appearance Model (AAM). AAM is needed for extract shape feature of face image. Also, we use Gabor to get texture information of face image. The facial expression recognition method is based on Support Vector Machine (SVM). We tested our model with CK+ and Jaffe dataset on six basic emotion: anger, disgust, fear, happy, sad, and surprise. Our method gained accuracy 93.58% for CK+ dataset and 94.7% for Jaffe dataset.
{"title":"Shape analysis using generalized procrustes analysis on Active Appearance Model for facial expression recognition","authors":"D. Komalasari, M. R. Widyanto, T. Basaruddin, D. Liliana","doi":"10.1109/ICECOS.2017.8167123","DOIUrl":"https://doi.org/10.1109/ICECOS.2017.8167123","url":null,"abstract":"Facial expression recognition is an active research area in the field of signal social processing. The goal is to distinguish human emotion. The problem is similar emotion, variation of emotion, and independent object through face image. The existing research using various method for modeling human facial to entirely describe facial expression through face image. We consider to variation analysis of the face image using Generalized Procrustes Analysis (GPA) method. GPA is implied for modeling variation of facial expression. We fit our GPA model exact the position of facial skeleton using Active Appearance Model (AAM). AAM is needed for extract shape feature of face image. Also, we use Gabor to get texture information of face image. The facial expression recognition method is based on Support Vector Machine (SVM). We tested our model with CK+ and Jaffe dataset on six basic emotion: anger, disgust, fear, happy, sad, and surprise. Our method gained accuracy 93.58% for CK+ dataset and 94.7% for Jaffe dataset.","PeriodicalId":6528,"journal":{"name":"2017 International Conference on Electrical Engineering and Computer Science (ICECOS)","volume":"24 1","pages":"154-159"},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78596396","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：