Pub Date : 2018-10-01DOI: 10.1109/TENCON.2018.8650367
Basabadatta Mohanty, H. K. Sahoo, B. Patnaik
In the proposed work presented in the paper, adaptive equalizer for MIMO-OFDM system is designed using neural network with functional expansions and neural weights are adjusted using sparse adaptive filter with block processing of input samples. By introducing l0-norm sparsity in the cost function of the block RLS (BRLS), equalization can be achieved for MIMO wireless channels with a comparatively less computational load. Nakagami-m fading channel model is used to represent the dispersive nature of fading wireless channel. 16-QAM constellation format is used to modulate the incoming data. The most important contribution of the paper lies in the inclusion of norm based sparsity in equalizer design which yields a low bit error rate (BER) and mean square error (MSE) even in low SNR conditins.
{"title":"Neural Network and Sparse Block Processing Based Nonlinear Adaptive Equalizer for MIMO OFDM Communication Systems","authors":"Basabadatta Mohanty, H. K. Sahoo, B. Patnaik","doi":"10.1109/TENCON.2018.8650367","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650367","url":null,"abstract":"In the proposed work presented in the paper, adaptive equalizer for MIMO-OFDM system is designed using neural network with functional expansions and neural weights are adjusted using sparse adaptive filter with block processing of input samples. By introducing l0-norm sparsity in the cost function of the block RLS (BRLS), equalization can be achieved for MIMO wireless channels with a comparatively less computational load. Nakagami-m fading channel model is used to represent the dispersive nature of fading wireless channel. 16-QAM constellation format is used to modulate the incoming data. The most important contribution of the paper lies in the inclusion of norm based sparsity in equalizer design which yields a low bit error rate (BER) and mean square error (MSE) even in low SNR conditins.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123898920","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650453
T. Adiono, K. Prakoso, Christoporus Deo Putratama, Bramantio Yuwono, S. Fuada
We reported the practical implementation of a real-time image-based human detection in FPGA. The Histogram of Oriented Gradients (HOG) features and the AdaBoost classifiers are used as an approach. The systolic array architecture based Support Vectoring Machine (SVM) processing is also implemented in our system. According to the results, it can be shown that the humans are successfully detected from a 1280 x 1024 of image resolution with 129 fps of frame rate, it is not only from the front and back views (horizontal axis) but also robust in human detection from different angles (vertical axis). We also compared our architecture with other works.
{"title":"Practical Implementation of A Real-time Human Detection with HOG-AdaBoost in FPGA","authors":"T. Adiono, K. Prakoso, Christoporus Deo Putratama, Bramantio Yuwono, S. Fuada","doi":"10.1109/TENCON.2018.8650453","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650453","url":null,"abstract":"We reported the practical implementation of a real-time image-based human detection in FPGA. The Histogram of Oriented Gradients (HOG) features and the AdaBoost classifiers are used as an approach. The systolic array architecture based Support Vectoring Machine (SVM) processing is also implemented in our system. According to the results, it can be shown that the humans are successfully detected from a 1280 x 1024 of image resolution with 129 fps of frame rate, it is not only from the front and back views (horizontal axis) but also robust in human detection from different angles (vertical axis). We also compared our architecture with other works.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"795 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123906126","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650530
Minsoo Jeong, I. Orikumhi, Sunwoo Kim
In this paper, we propose an optimal power allocation scheme for multiple unmanned aerial vehicles (UAVs) communications that maximizes the sum rates at the UAVs. The proposed scheme exploits the location information of multiple UAVs and adapts the transmit power based on the UAV distance from the transmitting base station (BS). The location information enables the BS to dynamically adapt the transmit power over the UAVs entire flight time to maximize the average sum rate. The average sum rate and power allocated to the UAVs during the flight time are used as the performance metrics. In addition, the proposed scheme is compared with the fixed power allocation scheme, and the results give useful insight into UAV location-aware communication. The simulation results show that at low transmit power, a sum rate improvement can be achieved when the adaptive power transmission scheme is applied as compared to a fixed transmit power schemes.
{"title":"Location-aware Power Adaptation Scheme for UAV Communications","authors":"Minsoo Jeong, I. Orikumhi, Sunwoo Kim","doi":"10.1109/TENCON.2018.8650530","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650530","url":null,"abstract":"In this paper, we propose an optimal power allocation scheme for multiple unmanned aerial vehicles (UAVs) communications that maximizes the sum rates at the UAVs. The proposed scheme exploits the location information of multiple UAVs and adapts the transmit power based on the UAV distance from the transmitting base station (BS). The location information enables the BS to dynamically adapt the transmit power over the UAVs entire flight time to maximize the average sum rate. The average sum rate and power allocated to the UAVs during the flight time are used as the performance metrics. In addition, the proposed scheme is compared with the fixed power allocation scheme, and the results give useful insight into UAV location-aware communication. The simulation results show that at low transmit power, a sum rate improvement can be achieved when the adaptive power transmission scheme is applied as compared to a fixed transmit power schemes.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116411151","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650074
Ashley Riz A. Advincula, Joana Mae B. Masilang, Jann Marc F. Villablanca, L. G. Sison
Cardiac rehabilitation is a program where the patient is supervised by a physical therapist while doing the exercise routine designed by their doctor. In the Philippines, a stand-alone equipment that can automate the doctor’s prescribed exercise routine while actively monitoring the patient’s vital sign is needed. The equipment could enable a safe and effective recovery with minimal supervision from the medical practitioners. This project aims to provide an automated aerobic exercise for cardiovascular rehabilitation patients through an adaptive cardiovascular training device. The automated exercise is based on the patient's heart rate which would be effectuated through the automatic adjustment of the load resistance of the cycling equipment. The equipment also includes blood pressure and oxygen saturation monitors to actively monitor the patient’s condition during the exercise.
{"title":"Cardiovascular Rehabilitation Equipment (CaRE)","authors":"Ashley Riz A. Advincula, Joana Mae B. Masilang, Jann Marc F. Villablanca, L. G. Sison","doi":"10.1109/TENCON.2018.8650074","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650074","url":null,"abstract":"Cardiac rehabilitation is a program where the patient is supervised by a physical therapist while doing the exercise routine designed by their doctor. In the Philippines, a stand-alone equipment that can automate the doctor’s prescribed exercise routine while actively monitoring the patient’s vital sign is needed. The equipment could enable a safe and effective recovery with minimal supervision from the medical practitioners. This project aims to provide an automated aerobic exercise for cardiovascular rehabilitation patients through an adaptive cardiovascular training device. The automated exercise is based on the patient's heart rate which would be effectuated through the automatic adjustment of the load resistance of the cycling equipment. The equipment also includes blood pressure and oxygen saturation monitors to actively monitor the patient’s condition during the exercise.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123674526","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650526
F. Cruz, E. Chua, Charity L. Monteclaro, Ma. Lhealynn N. Daquioag, Rigel Kent L. Zabate, M. G. Binag, Marlou Ryan G. Ga
Nowadays, the Philippines encounters unpredictable weather and the awareness of the circumstance is important. The traditional use of measuring instruments is implemented to perceive the state of the atmosphere. Rain gauge remote sensor node is a device that is utilized for effective monitoring of rainfall. It is known that rain gauge remote sensor nodes need energy to fully operate. Since most of remote areas lack on providing electric power, batteries are common substitute for the sensor nodes to operate at a span of time. Repetitive changing of batteries is time-wasting and costly for remote areas. Solar panel power source is a remedy for this situation which is used to continuously supply energy to the rain gauge remote sensor node. This paper gives information to the readers on a device that is possible to be placed on remote areas like mountains which have limited source of electricity or zero accessibility at all. The design of the power supply has been accumulated from voltage and current measurements that are evaluated through distinctive trials during various operating modes.
{"title":"Power Model of Rain Gauge Sensor Node with Solar Panel Power Source","authors":"F. Cruz, E. Chua, Charity L. Monteclaro, Ma. Lhealynn N. Daquioag, Rigel Kent L. Zabate, M. G. Binag, Marlou Ryan G. Ga","doi":"10.1109/TENCON.2018.8650526","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650526","url":null,"abstract":"Nowadays, the Philippines encounters unpredictable weather and the awareness of the circumstance is important. The traditional use of measuring instruments is implemented to perceive the state of the atmosphere. Rain gauge remote sensor node is a device that is utilized for effective monitoring of rainfall. It is known that rain gauge remote sensor nodes need energy to fully operate. Since most of remote areas lack on providing electric power, batteries are common substitute for the sensor nodes to operate at a span of time. Repetitive changing of batteries is time-wasting and costly for remote areas. Solar panel power source is a remedy for this situation which is used to continuously supply energy to the rain gauge remote sensor node. This paper gives information to the readers on a device that is possible to be placed on remote areas like mountains which have limited source of electricity or zero accessibility at all. The design of the power supply has been accumulated from voltage and current measurements that are evaluated through distinctive trials during various operating modes.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123923919","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650129
Sang-Yun Yun, Jaesung Jung, N. Cho
Increasing fault current contribution from Distributed Generation (DG) has become a major concern in power system protection coordination. This paper analyzes the single-line to ground fault (SLGF) current contribution from DG to fault location based on the type of transformer and DG. First of all, sequence network model for different type of transformer and DG is presented to calculate the SLGF current. Then, the fault current calculation method according to DG type is introduced because the system including inverter-based DG is not able to calculate the fault current by the conventional model. Using this model, actual distribution system is used to analyze the SLGF current contribution from DG to fault location when the different combination of transformer and DG is interconnected.
{"title":"Analyzing the Single-Line to Ground Fault Current Contribution by the Type of Transformer and Distributed Generator","authors":"Sang-Yun Yun, Jaesung Jung, N. Cho","doi":"10.1109/TENCON.2018.8650129","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650129","url":null,"abstract":"Increasing fault current contribution from Distributed Generation (DG) has become a major concern in power system protection coordination. This paper analyzes the single-line to ground fault (SLGF) current contribution from DG to fault location based on the type of transformer and DG. First of all, sequence network model for different type of transformer and DG is presented to calculate the SLGF current. Then, the fault current calculation method according to DG type is introduced because the system including inverter-based DG is not able to calculate the fault current by the conventional model. Using this model, actual distribution system is used to analyze the SLGF current contribution from DG to fault location when the different combination of transformer and DG is interconnected.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123953304","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650419
Abigail Alejandro Antenor, Kristine Delica Campang, Khristen Anne Mendoza Rafols, A. Ballesil-Alvarez, M. T. D. Leon, C. V. Densing, R. J. Maestro, M. Rosales
This paper highlights the design and implementation of a thermoelectric energy harvesting interface circuit that generates a regulated 1 V voltage level at the output and delivers the maximum possible energy to a wireless sensor node. The system is able to self-start from a 270 mV input produced by a thermoelectric module that utilizes the varying temperature conditions from the environment. A maximum power point tracking mechanism is included so that the system would always operate at the maximum power point. The whole system is implemented in 65 nm CMOS Process Technology covering an area of 475 um by 360 um.
{"title":"Design and Implementation of a Thermoelectric Energy Harvesting Interface Circuit with Maximum Power Point Tracking and Self-Startup Capability for Wireless Sensor Nodes","authors":"Abigail Alejandro Antenor, Kristine Delica Campang, Khristen Anne Mendoza Rafols, A. Ballesil-Alvarez, M. T. D. Leon, C. V. Densing, R. J. Maestro, M. Rosales","doi":"10.1109/TENCON.2018.8650419","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650419","url":null,"abstract":"This paper highlights the design and implementation of a thermoelectric energy harvesting interface circuit that generates a regulated 1 V voltage level at the output and delivers the maximum possible energy to a wireless sensor node. The system is able to self-start from a 270 mV input produced by a thermoelectric module that utilizes the varying temperature conditions from the environment. A maximum power point tracking mechanism is included so that the system would always operate at the maximum power point. The whole system is implemented in 65 nm CMOS Process Technology covering an area of 475 um by 360 um.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123961120","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650446
J. C. Bastidas, K. Mehmood, M. S. Zaman, C. Noh, Chul-Hwan Kim
This paper proposes an energy management system (EMS) power dispatch algorithm for a set of various distributed energy resources such as distributed generators and energy storage system in hybrid configuration (HESS) connected to a 1-MW power grid system. The HESS is composed of a stationary centralized Vanadium Redox Battery and decentralized energy storage system represented by Li-ion electric vehicle (EV) charging parking lot at a commercial workplace. The proposed EMS incorporates vehicle-to-grid and grid-to-vehicle charging capabilities and detailed model of both incorporated battery technologies. Robustness, load levelling, peak shaving, ancillary service features and simulation results of the proposed EMS dispatch model were confirmed under the presence of different levels of power mismatch, the high intermittence of PV power output and the EV penetration. The simulation study is carried out with Matlab/Simulink considering the load profile curves of residential and commercial loads connected to the system with a 5 minutes dispatch interval.
{"title":"EMS Strategy for Accommodation of High Solar Intermittency in PV Plants with EV Parking Lot and VRB in Hybrid Storage Configuration","authors":"J. C. Bastidas, K. Mehmood, M. S. Zaman, C. Noh, Chul-Hwan Kim","doi":"10.1109/TENCON.2018.8650446","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650446","url":null,"abstract":"This paper proposes an energy management system (EMS) power dispatch algorithm for a set of various distributed energy resources such as distributed generators and energy storage system in hybrid configuration (HESS) connected to a 1-MW power grid system. The HESS is composed of a stationary centralized Vanadium Redox Battery and decentralized energy storage system represented by Li-ion electric vehicle (EV) charging parking lot at a commercial workplace. The proposed EMS incorporates vehicle-to-grid and grid-to-vehicle charging capabilities and detailed model of both incorporated battery technologies. Robustness, load levelling, peak shaving, ancillary service features and simulation results of the proposed EMS dispatch model were confirmed under the presence of different levels of power mismatch, the high intermittence of PV power output and the EV penetration. The simulation study is carried out with Matlab/Simulink considering the load profile curves of residential and commercial loads connected to the system with a 5 minutes dispatch interval.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124017900","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650310
Siva Mouni Nemalidinne, A. P. Sindhu, Deep Gupta
The recurring forest fires have prolonged catastrophic effects on the environment as well as human individuals. The detection of such fire is a very prominent issue using visible and infrared (IR) images. This paper presents a fusion approach for IR and visible images using several features of the nonsubsampled contourlet transform (NSCT). Firstly, NSCT is applied to decompose the reference IR and visible image into the different low and high-frequency components. Low-frequency coefficient is fused by a pulse coupled neural network (PCNN) motivated by the sum-modified Laplacian (SML) to retain the more amount of information available in both the source images and log Gabor energy based fusion rule is applied to fuse the high-frequency coefficients to preserve the more edge details. At last, inverse NSCT is applied to reconstruct the fused image. Furthermore, several experiments are performed to evaluate the performance of the proposed approach in terms of visual appearance as well as several performance measures. Experimental results show the superiority of the presented fusion method in the NSCT domain over the other existing fusion approaches in terms of the improvement in all the performance measures.
{"title":"Nonsubsampled Contourlet Domain Fusion Approach for Infrared and Visible Fire Images","authors":"Siva Mouni Nemalidinne, A. P. Sindhu, Deep Gupta","doi":"10.1109/TENCON.2018.8650310","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650310","url":null,"abstract":"The recurring forest fires have prolonged catastrophic effects on the environment as well as human individuals. The detection of such fire is a very prominent issue using visible and infrared (IR) images. This paper presents a fusion approach for IR and visible images using several features of the nonsubsampled contourlet transform (NSCT). Firstly, NSCT is applied to decompose the reference IR and visible image into the different low and high-frequency components. Low-frequency coefficient is fused by a pulse coupled neural network (PCNN) motivated by the sum-modified Laplacian (SML) to retain the more amount of information available in both the source images and log Gabor energy based fusion rule is applied to fuse the high-frequency coefficients to preserve the more edge details. At last, inverse NSCT is applied to reconstruct the fused image. Furthermore, several experiments are performed to evaluate the performance of the proposed approach in terms of visual appearance as well as several performance measures. Experimental results show the superiority of the presented fusion method in the NSCT domain over the other existing fusion approaches in terms of the improvement in all the performance measures.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126136517","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 : 2018-10-01DOI: 10.1109/TENCON.2018.8650411
R. Yusof, U. Khairuddin, N. R. Rosli, Hafizza Abdul Ghafar, Nik Mohamad Aizuddin Nik Azmi, Azlin Ahmad, A. S. M. Khairuddin
Tropical wood recognition is a very challenging task due to the lack of discriminative features among some species of the wood, and also some very discriminative features among inter class species. Moreover, noises due to illuminations, or the uncontrolled environment as well as the wood features such as the size of pores, the density of pores, etc., which depend very much on the age, weather and other factors, contributing to the irregularities of the features. In this paper, we explore the use of feature extraction techniques, classification techniques for better accuracy of the system. In particular, we explore the use of one of the deep learning method residual network based CNN (Res-Net), noting the capability of the network to learn the features of images and its ability of generalization. Results have shown that good feature extraction methods can give a much better accuracy for all the datasets tested, and Res-Net performed badly due to lack of data, which cause the problem of overfitting.
{"title":"A Study of Feature Extraction and Classifier Methods for Tropical Wood Recognition System","authors":"R. Yusof, U. Khairuddin, N. R. Rosli, Hafizza Abdul Ghafar, Nik Mohamad Aizuddin Nik Azmi, Azlin Ahmad, A. S. M. Khairuddin","doi":"10.1109/TENCON.2018.8650411","DOIUrl":"https://doi.org/10.1109/TENCON.2018.8650411","url":null,"abstract":"Tropical wood recognition is a very challenging task due to the lack of discriminative features among some species of the wood, and also some very discriminative features among inter class species. Moreover, noises due to illuminations, or the uncontrolled environment as well as the wood features such as the size of pores, the density of pores, etc., which depend very much on the age, weather and other factors, contributing to the irregularities of the features. In this paper, we explore the use of feature extraction techniques, classification techniques for better accuracy of the system. In particular, we explore the use of one of the deep learning method residual network based CNN (Res-Net), noting the capability of the network to learn the features of images and its ability of generalization. Results have shown that good feature extraction methods can give a much better accuracy for all the datasets tested, and Res-Net performed badly due to lack of data, which cause the problem of overfitting.","PeriodicalId":132900,"journal":{"name":"TENCON 2018 - 2018 IEEE Region 10 Conference","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126191057","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：