Pub Date : 2015-10-15DOI: 10.1109/CSUDET.2015.7446217
A. Mas’ud, Mohammed E. Eltayeb, F. Muhammad-Sukki, N. Bani
This paper compares the statistical error tolerances of the single neural network (SNN) and the ensemble neural network (ENN) recognition efficiencies, when both the SNN and ENN are applied to recognize partial discharge (PD) patterns. Statistical fingerprints from the phased and amplitude resolved patterns of PDs, have been applied for training and testing the SNN and the ENN. Statistical mean and variances of the SNN and ENN recognition rates were compared and evaluated over several iterations in order to obtain an acceptable value. The results show that the ENN is generally more robust and often provides an improved recognition rate with higher mean value and lower variance when compared with the SNN. The result implies that it is possible to determine the accurate statistical error tolerances for the SNN and ENN recognition probability for correct diagnosis of PD fault.
{"title":"Statistical error tolerances of partial discharge recognition rates","authors":"A. Mas’ud, Mohammed E. Eltayeb, F. Muhammad-Sukki, N. Bani","doi":"10.1109/CSUDET.2015.7446217","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446217","url":null,"abstract":"This paper compares the statistical error tolerances of the single neural network (SNN) and the ensemble neural network (ENN) recognition efficiencies, when both the SNN and ENN are applied to recognize partial discharge (PD) patterns. Statistical fingerprints from the phased and amplitude resolved patterns of PDs, have been applied for training and testing the SNN and the ENN. Statistical mean and variances of the SNN and ENN recognition rates were compared and evaluated over several iterations in order to obtain an acceptable value. The results show that the ENN is generally more robust and often provides an improved recognition rate with higher mean value and lower variance when compared with the SNN. The result implies that it is possible to determine the accurate statistical error tolerances for the SNN and ENN recognition probability for correct diagnosis of PD fault.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124131556","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446225
S. Teh, Y. Sin, Kah-Yoong Chan, N. Devaraj, M. Saw, F. Yam
Doped zinc oxide (ZnO) colloids have attracted significant attention recently due to its wide range of applications owing to the effective tunable properties and remarkable solution processability. In this work, low cost sol-gel spin coating technique was employed to synthesize the aluminum doped ZnO colloids (AZO). The influences of the Al doping concentration on the structural and optical properties of the AZO colloids were investigated using field-emission scanning electron microscopy (FESEM), ultraviolet-visible (UV-Vis) spectrophotometer and photoluminescence (PL) spectroscopy. Elemental composition was confirmed using energy dispersive X-Ray spectrophotometer (EDX). The size of colloid particles decrease from approximately 400 nm to 100 nm as the Al doping concentration is increased. As the size of the colloids decrease, the position of absorption peak was blue shifted, whilst the tunable optical band gap (Eg) of the AZO colloids is profound.
{"title":"Influence of aluminum dopant on the structural and optical properties of zinc oxide colloids prepared by sol-gel spin coating method","authors":"S. Teh, Y. Sin, Kah-Yoong Chan, N. Devaraj, M. Saw, F. Yam","doi":"10.1109/CSUDET.2015.7446225","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446225","url":null,"abstract":"Doped zinc oxide (ZnO) colloids have attracted significant attention recently due to its wide range of applications owing to the effective tunable properties and remarkable solution processability. In this work, low cost sol-gel spin coating technique was employed to synthesize the aluminum doped ZnO colloids (AZO). The influences of the Al doping concentration on the structural and optical properties of the AZO colloids were investigated using field-emission scanning electron microscopy (FESEM), ultraviolet-visible (UV-Vis) spectrophotometer and photoluminescence (PL) spectroscopy. Elemental composition was confirmed using energy dispersive X-Ray spectrophotometer (EDX). The size of colloid particles decrease from approximately 400 nm to 100 nm as the Al doping concentration is increased. As the size of the colloids decrease, the position of absorption peak was blue shifted, whilst the tunable optical band gap (Eg) of the AZO colloids is profound.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130276672","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446224
A. U. Lawan, H. Abbas
This paper presents the multicarrier PWM techniques studies based on the three Level shifted based modulation techniques; Phase Disposition PWM (PDPWM), Phase opposition disposition PWM (PODPWM), Alternate phase opposition disposition PWM (APODPWM) of a MMC based inverter and a comparative study is done based on total harmonics, voltage profile quality and load current waveforms. The Simulation has been carried out for the five-level MMC inverter specific modulation types, similarities and performance using MATLAB/Simulink. The results were verified.
{"title":"Level shifted PWMs comparison for a 5-level modular multilevel converter (MMC) topology inverter","authors":"A. U. Lawan, H. Abbas","doi":"10.1109/CSUDET.2015.7446224","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446224","url":null,"abstract":"This paper presents the multicarrier PWM techniques studies based on the three Level shifted based modulation techniques; Phase Disposition PWM (PDPWM), Phase opposition disposition PWM (PODPWM), Alternate phase opposition disposition PWM (APODPWM) of a MMC based inverter and a comparative study is done based on total harmonics, voltage profile quality and load current waveforms. The Simulation has been carried out for the five-level MMC inverter specific modulation types, similarities and performance using MATLAB/Simulink. The results were verified.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116541971","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446220
K. Siow, T. Chen, Y. W. Chan, A. Jalar, R. Vemal, S. T. Chua, F. Husna
Silicone gels provide the dielectric insulation in insulated gate bipolar transistor (IGBT) power modules to prevent partial discharge, inhibit moisture ingress and keep out contaminants from the internal circuitry. The junction temperatures of these power modules are located between 150oC and 175oC and these temperatures will increase to 200oC in the near future. In addition, power modules are expected to operate for 15 to 20 years. The development time of these power modules is getting shorter to meet the market expectations. Similar demanding conditions are expected for micro-electromechanical systems (MEMS) applications. Hence, there is a need to use characterization tools to short-list silicone gels for further analysis or building of qualification units. Amongst the three silicone gels analysed here, sample C shows the most promise because of its lack of thermal events during the DSC analysis. Sample C also maintains the softness and inertness during the thermal ageing at 150oC for up to 1000 hours. These studies show that judicious use of DSC-TGA, FTIR and gel penetrometer can provide valuable information for the said purpose.
{"title":"Characterization of silicone gel properties for high power IGBT modules and MEMS","authors":"K. Siow, T. Chen, Y. W. Chan, A. Jalar, R. Vemal, S. T. Chua, F. Husna","doi":"10.1109/CSUDET.2015.7446220","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446220","url":null,"abstract":"Silicone gels provide the dielectric insulation in insulated gate bipolar transistor (IGBT) power modules to prevent partial discharge, inhibit moisture ingress and keep out contaminants from the internal circuitry. The junction temperatures of these power modules are located between 150oC and 175oC and these temperatures will increase to 200oC in the near future. In addition, power modules are expected to operate for 15 to 20 years. The development time of these power modules is getting shorter to meet the market expectations. Similar demanding conditions are expected for micro-electromechanical systems (MEMS) applications. Hence, there is a need to use characterization tools to short-list silicone gels for further analysis or building of qualification units. Amongst the three silicone gels analysed here, sample C shows the most promise because of its lack of thermal events during the DSC analysis. Sample C also maintains the softness and inertness during the thermal ageing at 150oC for up to 1000 hours. These studies show that judicious use of DSC-TGA, FTIR and gel penetrometer can provide valuable information for the said purpose.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"50 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123149768","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446221
J. Hai, Ooi Chee Pun, T. Haw
Video and Image Processing solution requiring high throughput rate are often implemented in a dedicated hardware such as FPGA. The design process traditionally uses Verilog and VHDL for synthesizing and validating the hardware. These design process are technically complex and time consuming. In this paper, we present an alternative approach using a model based design framework based on HDL Coder, Vision HDL Toolbox and Simulink to accelerate the design of video and image solution. Several important issues in this framework are discussed namely, Pixel Streaming Design, Co-simulation and FPGA in the Loop (FIL). Based on this framework, a video of human walking are processed to extract out two features which are the human height and edge. The design is implemented in an Altera DE2-115 FPGA board. The goal of this paper is to tackle the technical complexity and reduce development time of traditional FPGA design.
{"title":"Accelerating video and image processing design for FPGA using HDL coder and simulink","authors":"J. Hai, Ooi Chee Pun, T. Haw","doi":"10.1109/CSUDET.2015.7446221","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446221","url":null,"abstract":"Video and Image Processing solution requiring high throughput rate are often implemented in a dedicated hardware such as FPGA. The design process traditionally uses Verilog and VHDL for synthesizing and validating the hardware. These design process are technically complex and time consuming. In this paper, we present an alternative approach using a model based design framework based on HDL Coder, Vision HDL Toolbox and Simulink to accelerate the design of video and image solution. Several important issues in this framework are discussed namely, Pixel Streaming Design, Co-simulation and FPGA in the Loop (FIL). Based on this framework, a video of human walking are processed to extract out two features which are the human height and edge. The design is implemented in an Altera DE2-115 FPGA board. The goal of this paper is to tackle the technical complexity and reduce development time of traditional FPGA design.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121851950","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446219
Mohammed Aliyu Gadam, A. A. Maryam, N. K. Nordin, A. Sali, F. Hisyam
User equipments (UEs) offloaded from the MeNBs to the PeNBs via cell range extension (CRE) bias in a co-channel deployment suffered severe interference. The severity of the downlink interference varies significantly with the change in the CRE bias. The baseline approach for Interference mitigation technique based on time domain muting (TDM) of resources by MeNBs used trial and error technique which is causing resource wastage and is practically not feasible. Proposed here is a Model for TDM based on estimated cell load conditions and symbol efficiency (SE) as metrics to determine the muting ratio of resources. System level simulation was conducted to validate the throughput performances and the MeNBs- PeNBs resource trade-offs of the proposed method. Compared to the baseline (centralized) approach, the proposed decentralized TDM algorithm exhibited optimal throughput performance and adapted to the change in CRE bias with better trade-offs.
{"title":"Decentralized time domain muting for interference mitigation in LTE-advanced heterogeneous networks","authors":"Mohammed Aliyu Gadam, A. A. Maryam, N. K. Nordin, A. Sali, F. Hisyam","doi":"10.1109/CSUDET.2015.7446219","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446219","url":null,"abstract":"User equipments (UEs) offloaded from the MeNBs to the PeNBs via cell range extension (CRE) bias in a co-channel deployment suffered severe interference. The severity of the downlink interference varies significantly with the change in the CRE bias. The baseline approach for Interference mitigation technique based on time domain muting (TDM) of resources by MeNBs used trial and error technique which is causing resource wastage and is practically not feasible. Proposed here is a Model for TDM based on estimated cell load conditions and symbol efficiency (SE) as metrics to determine the muting ratio of resources. System level simulation was conducted to validate the throughput performances and the MeNBs- PeNBs resource trade-offs of the proposed method. Compared to the baseline (centralized) approach, the proposed decentralized TDM algorithm exhibited optimal throughput performance and adapted to the change in CRE bias with better trade-offs.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116889901","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446223
Zamani Md Sani, Loi Wei Sen, Hadhrami Abd Ghani, R. Besar
Road markers provide vital information to ensure traffic safety. Different sets of markers are normally used between the highways and the normal road. At the normal road for example, the double lane markers are used to indicate the hazardous area, where overtaking is prohibited while broken marker lane indicate otherwise. To avoid traffic accidents and provide safety, these markers should be accurately detected and classified, which is best solved via vision detection approach. Marker type classification is however affected by the changing sun illumination throughout the day. In this paper, real-time recognition of these markers is developed using the artificial neural network (ANN) to alert the users while driving. The accuracy of the scheme is observed when different input features (geometrical and texture) and image pixels are fed for recognizing broken and double lane markers. A very high accuracy result with low error rate is obtained at 98.83% (10-fold cross validation) accuracy detection using additional features, compared with ~95% by using only the image pixels as the input vector and average processing time is at ~30ms per frame.
{"title":"Real-time daytime road marker recognition using features vectors and neural network","authors":"Zamani Md Sani, Loi Wei Sen, Hadhrami Abd Ghani, R. Besar","doi":"10.1109/CSUDET.2015.7446223","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446223","url":null,"abstract":"Road markers provide vital information to ensure traffic safety. Different sets of markers are normally used between the highways and the normal road. At the normal road for example, the double lane markers are used to indicate the hazardous area, where overtaking is prohibited while broken marker lane indicate otherwise. To avoid traffic accidents and provide safety, these markers should be accurately detected and classified, which is best solved via vision detection approach. Marker type classification is however affected by the changing sun illumination throughout the day. In this paper, real-time recognition of these markers is developed using the artificial neural network (ANN) to alert the users while driving. The accuracy of the scheme is observed when different input features (geometrical and texture) and image pixels are fed for recognizing broken and double lane markers. A very high accuracy result with low error rate is obtained at 98.83% (10-fold cross validation) accuracy detection using additional features, compared with ~95% by using only the image pixels as the input vector and average processing time is at ~30ms per frame.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131126520","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446218
Y. W. Chan, T. Chen, K. Siow, B. Y. Majlis, T. S. Yeoh
Plasma modification is used to alter surface chemical and physical properties of substrates to improve specific characteristics including adhesion and biocompatibility. Such stable and highly cross-linked coatings produced via high discharge power, however, results in a low concentration of reactive chemical functionalities on the surface. Here, we carried out the Theory of Inventive Problem Solving (TRIZ) process consist of functional analysis, cause and effect chain analysis and physical contradiction to arrive at the relevant inventive principles to solve this issue. Then, we selected relevant examples from the literature to demonstrate the application of these proposed inventive steps in solving this issue. This paper is expected to be useful to engineers/scientists who are interested to use the TRIZ technique to generate novel ideas in solving chemical or materials science related engineering problems.
{"title":"TRIZ technique to produce stable plasma modified surfaces with high density of reactive chemical functionalities","authors":"Y. W. Chan, T. Chen, K. Siow, B. Y. Majlis, T. S. Yeoh","doi":"10.1109/CSUDET.2015.7446218","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446218","url":null,"abstract":"Plasma modification is used to alter surface chemical and physical properties of substrates to improve specific characteristics including adhesion and biocompatibility. Such stable and highly cross-linked coatings produced via high discharge power, however, results in a low concentration of reactive chemical functionalities on the surface. Here, we carried out the Theory of Inventive Problem Solving (TRIZ) process consist of functional analysis, cause and effect chain analysis and physical contradiction to arrive at the relevant inventive principles to solve this issue. Then, we selected relevant examples from the literature to demonstrate the application of these proposed inventive steps in solving this issue. This paper is expected to be useful to engineers/scientists who are interested to use the TRIZ technique to generate novel ideas in solving chemical or materials science related engineering problems.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116587828","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 : 2015-10-01DOI: 10.1109/CSUDET.2015.7446222
Shun Ying Kwang, Ee Fu Kwang, Davis Tee, C. S. Tan
In order to reduce CO2 emission and develop best management practices for deforested agricultural activities (Cameron Highland Malaysia), the formation and emission rates of CO2 in the current land management and the factors affecting the process must be understood. The Total Organic Carbon (TOC), land moistures and temperature of the land use are evaluated. This has to be correlated to the agricultural activities. We propose to use peat treatment that will enable the carbon increased over time during the agricultural activities. The land quality is evaluated and the carbon content using peat treatment is investigated during the land use changes. Generally, the land quality could enhance the carbon reduction in the atmosphere as well as improving the land quality by using peat treatment.
{"title":"Evaluation of peat treatment in Cameron Highland Malaysia","authors":"Shun Ying Kwang, Ee Fu Kwang, Davis Tee, C. S. Tan","doi":"10.1109/CSUDET.2015.7446222","DOIUrl":"https://doi.org/10.1109/CSUDET.2015.7446222","url":null,"abstract":"In order to reduce CO2 emission and develop best management practices for deforested agricultural activities (Cameron Highland Malaysia), the formation and emission rates of CO2 in the current land management and the factors affecting the process must be understood. The Total Organic Carbon (TOC), land moistures and temperature of the land use are evaluated. This has to be correlated to the agricultural activities. We propose to use peat treatment that will enable the carbon increased over time during the agricultural activities. The land quality is evaluated and the carbon content using peat treatment is investigated during the land use changes. Generally, the land quality could enhance the carbon reduction in the atmosphere as well as improving the land quality by using peat treatment.","PeriodicalId":330138,"journal":{"name":"2015 IEEE Conference on Sustainable Utilization And Development In Engineering and Technology (CSUDET)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133423356","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：