Pub Date : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967042
Jae-Neung Lee, Keun-Chang Kwak
In this paper, we present auto-encoder (AE), stacked auto-encoder (SAE) and sparse auto-encoder (SPAE) to classify gaits of horse riding for real riding coaching. The parameters of each auto-encoder are adjusted to compare the performance. The data is collected from 16 inertial sensors attached to a motion capture suit to construct a motion database. We build the motion features as the method of gaits classification with the database. The experiment shows that the performance is 95% when applied AE. SPAE was the best in terms of time and AE was the best in performance. We can apply to coaching system by each horse gait for rider under real or horse simulator environments using the SPAE algorithm.
{"title":"A performance comparison of auto-encoder and its variants for classification","authors":"Jae-Neung Lee, Keun-Chang Kwak","doi":"10.1109/ICSIGSYS.2017.7967042","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967042","url":null,"abstract":"In this paper, we present auto-encoder (AE), stacked auto-encoder (SAE) and sparse auto-encoder (SPAE) to classify gaits of horse riding for real riding coaching. The parameters of each auto-encoder are adjusted to compare the performance. The data is collected from 16 inertial sensors attached to a motion capture suit to construct a motion database. We build the motion features as the method of gaits classification with the database. The experiment shows that the performance is 95% when applied AE. SPAE was the best in terms of time and AE was the best in performance. We can apply to coaching system by each horse gait for rider under real or horse simulator environments using the SPAE algorithm.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701116","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 : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967057
A. Harjoko, R. M. Hujja, Lukman Awaludin
3D data needs in various fields has increased along with the development of simulation and modeling technology. The current technology makes interaction with 3D data becomes easier and interesting. The existence of virtual reality and 3D printers provide ease to create and display 3D objects. The existence of a 3D scanner to reconstruct a real object into a 3D digital object is one of the practical solutions to facilitate the creation of 3D data. The methods to perform 3D object reconstruction process also began to be found, such as using a single camera, stereo camera, laser beam, structured light, and the combination of these methods with various algorithms. In this study, we create a prototype of low-cost 3D surface reconstruction system with a stereo camera. The Stereo camera using image processing to generate point cloud of the object with displacement and disparity mapping process. The point of cloud from the object then connected to produce 3D surface. Reconstruction is done by applying texture from object photograph to the surface of 3D point cloud that has been reconstructed. The system made by using a low-cost web camera to test the ability to reconstruct 3D objects surface with inexpensive equipment. Testing is done by giving structured light variable using the projector. The results of this study indicate that the calibration process camera position and light conditions will determine the outcome of reconstruction where the dual camera system is very dependent on the calibration process to produce a proper reconstruction.
{"title":"Low-cost 3D surface reconstruction using Stereo camera for small object","authors":"A. Harjoko, R. M. Hujja, Lukman Awaludin","doi":"10.1109/ICSIGSYS.2017.7967057","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967057","url":null,"abstract":"3D data needs in various fields has increased along with the development of simulation and modeling technology. The current technology makes interaction with 3D data becomes easier and interesting. The existence of virtual reality and 3D printers provide ease to create and display 3D objects. The existence of a 3D scanner to reconstruct a real object into a 3D digital object is one of the practical solutions to facilitate the creation of 3D data. The methods to perform 3D object reconstruction process also began to be found, such as using a single camera, stereo camera, laser beam, structured light, and the combination of these methods with various algorithms. In this study, we create a prototype of low-cost 3D surface reconstruction system with a stereo camera. The Stereo camera using image processing to generate point cloud of the object with displacement and disparity mapping process. The point of cloud from the object then connected to produce 3D surface. Reconstruction is done by applying texture from object photograph to the surface of 3D point cloud that has been reconstructed. The system made by using a low-cost web camera to test the ability to reconstruct 3D objects surface with inexpensive equipment. Testing is done by giving structured light variable using the projector. The results of this study indicate that the calibration process camera position and light conditions will determine the outcome of reconstruction where the dual camera system is very dependent on the calibration process to produce a proper reconstruction.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121103577","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 : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967049
F. Hidayah, K. Anwar
In this paper, we consider channel coding scheme for single carrier Internet of Things (SC-IoT). We propose new Raptor codes for SC-IoT devices with new degree distributions suitable for single carrier transmission to provide long term battery life services. In the proposed Raptor codes, Low Density Generator Matrix (LDGM) codes are used as the precode, called LDGM-Raptor codes. The codes are optimally designed using extrinsic information transfer (EXIT) chart in order to meet the requirement of SC-IoT providing low bit-error rate (BER). We found that although LDGM-Raptor codes is simple, the performances of codes are good enough with turbo-cliff closes to the Shannon capacity limit of channels.
{"title":"Low Density Generator Matrix (LDGM)-based Raptor codes for single carrier Internet of Things (SC-IoT)","authors":"F. Hidayah, K. Anwar","doi":"10.1109/ICSIGSYS.2017.7967049","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967049","url":null,"abstract":"In this paper, we consider channel coding scheme for single carrier Internet of Things (SC-IoT). We propose new Raptor codes for SC-IoT devices with new degree distributions suitable for single carrier transmission to provide long term battery life services. In the proposed Raptor codes, Low Density Generator Matrix (LDGM) codes are used as the precode, called LDGM-Raptor codes. The codes are optimally designed using extrinsic information transfer (EXIT) chart in order to meet the requirement of SC-IoT providing low bit-error rate (BER). We found that although LDGM-Raptor codes is simple, the performances of codes are good enough with turbo-cliff closes to the Shannon capacity limit of channels.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126496324","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 : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967021
Giashinta Larashati, R. P. Astuti, B. S. Nugroho
Massive MIMO technology can increase capacity, data rate, and link reliability significantly without additional bandwidth or transmission power. Most of the previous study on Massive MIMO systems are using low frequency (2.6 GHz). This frequency is not suitable for future broadband technology, because IoT devices will use high frequency and possible cell coverage would be smaller. This work proposes Massive MIMO transceiver antenna that can be implemented in high frequency (60 GHz). This system provides broadband wireless communication which gives high capacity, high data rate and wide bandwidth. In this works the number of antennas is 64×64. Antennas can be set adaptively to capacity. In this case all of the antennas as a receiver are functioned to get redundancies and 32 antennas as transmitter adjusted to the required capacity. Configuration of antenna has been set to eliminate the mutual coupling effect. The system utilizes full duplex single channel (FDSC) which use the same frequency and time to transmit and receive data. In FDSC, bandwidth can be minimized, but self interference effect appeared and disturbing the system performance of Massive MIMO. The effect of self interference for Massive MIMO transceiver antenna simulated from 10% to 100%. The proposed system provides the channel capacity ≈ 390 bits/s/Hz or ≈ 39× spectral efficiency of SISO system. The simulation result shows that mutual coupling effect ≈ 0. The Massive MIMO have a tolerance of 20% self interference effect, however it could decrease 20% channel capacity as well.
{"title":"Modeling of massive MIMO transceiver antenna for full-duplex single-channel system (in case of self interference effect)","authors":"Giashinta Larashati, R. P. Astuti, B. S. Nugroho","doi":"10.1109/ICSIGSYS.2017.7967021","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967021","url":null,"abstract":"Massive MIMO technology can increase capacity, data rate, and link reliability significantly without additional bandwidth or transmission power. Most of the previous study on Massive MIMO systems are using low frequency (2.6 GHz). This frequency is not suitable for future broadband technology, because IoT devices will use high frequency and possible cell coverage would be smaller. This work proposes Massive MIMO transceiver antenna that can be implemented in high frequency (60 GHz). This system provides broadband wireless communication which gives high capacity, high data rate and wide bandwidth. In this works the number of antennas is 64×64. Antennas can be set adaptively to capacity. In this case all of the antennas as a receiver are functioned to get redundancies and 32 antennas as transmitter adjusted to the required capacity. Configuration of antenna has been set to eliminate the mutual coupling effect. The system utilizes full duplex single channel (FDSC) which use the same frequency and time to transmit and receive data. In FDSC, bandwidth can be minimized, but self interference effect appeared and disturbing the system performance of Massive MIMO. The effect of self interference for Massive MIMO transceiver antenna simulated from 10% to 100%. The proposed system provides the channel capacity ≈ 390 bits/s/Hz or ≈ 39× spectral efficiency of SISO system. The simulation result shows that mutual coupling effect ≈ 0. The Massive MIMO have a tolerance of 20% self interference effect, however it could decrease 20% channel capacity as well.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"138 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113986098","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 : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967053
Vishal Deep, Tarek A. Elarabi
The increasing industrial demand for low data-rate and low power networking protocols for IoT communications from past several years led to the development of ZigBee technology. As a result of advancement in VLSI technologies, development of more power efficient, accurate, and small digital ZigBee transmitter design has become achievable but yet challenging. This paper presents digital design and FPGA PoC implementation for the 2.4 GHz-band digital ZigBee transmitter. The proposed hardware design of the transmitter described by utilizing Verilog Hardware Description Language and the prototype implementation is done by employing Xilinx Vivado 2016.2. The paper demonstrates the design of the four building blocks of an energy efficient digital ZigBee transmitter; i.e. cyclic redundancy check, bit-to-symbol block, symbol-to-chip block, and offset quadrature phase shift keying Modulator. Simulation waveform verifies functionality of the transmitter and its low power and low data-rate suitability for Internet of Things' applications.
{"title":"Efficient IEEE 802.15.4 ZigBee standard hardware design for IoT applications","authors":"Vishal Deep, Tarek A. Elarabi","doi":"10.1109/ICSIGSYS.2017.7967053","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967053","url":null,"abstract":"The increasing industrial demand for low data-rate and low power networking protocols for IoT communications from past several years led to the development of ZigBee technology. As a result of advancement in VLSI technologies, development of more power efficient, accurate, and small digital ZigBee transmitter design has become achievable but yet challenging. This paper presents digital design and FPGA PoC implementation for the 2.4 GHz-band digital ZigBee transmitter. The proposed hardware design of the transmitter described by utilizing Verilog Hardware Description Language and the prototype implementation is done by employing Xilinx Vivado 2016.2. The paper demonstrates the design of the four building blocks of an energy efficient digital ZigBee transmitter; i.e. cyclic redundancy check, bit-to-symbol block, symbol-to-chip block, and offset quadrature phase shift keying Modulator. Simulation waveform verifies functionality of the transmitter and its low power and low data-rate suitability for Internet of Things' applications.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127215944","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 : 2017-05-16DOI: 10.1109/ICSIGSYS.2017.7967043
Zhiyang Chen, Liya Huang, Yangyang Shen, Jun Wang, Ruijie Zhao, Jiafei Dai
Electrocorticogram (ECoG) is an effective way for Epilepsy research, as well as automatic seizure detection. This study proposes a method for feature extraction and classification of pre-ictal and ictal ECoGs, based upon mutual information (MI) and support vector machine (SVM) which has not only high accuracy but also fast speed. First, the mutual information among 76 channels is computed and converted into a 76×76 matrix, and then statistical significance of splicing mutual information between pre-ictal and ictal ECoGs is tested, and the coefficients of variation and fluctuation indexes of MI corresponding to the selected channels which exhibit the most significant differences are selected as features. SVM is then used as the classifier for identifying ictal ECoGs. In addition, two methods based on empirical mode decomposition (EMD) and wavelet, are applied on data as a control. The results of this study show that the MI of the selected channels from pre-ictal ECoGs is higher than that from ictal ECoGs, and the classification accuracy by combining coefficients of variation and fluctuation indexes as feature vectors is up to 100% and faster than the other methods.
{"title":"A new algorithm for classification of ictal and pre-ictal epilepsy ECoG using MI and SVM","authors":"Zhiyang Chen, Liya Huang, Yangyang Shen, Jun Wang, Ruijie Zhao, Jiafei Dai","doi":"10.1109/ICSIGSYS.2017.7967043","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967043","url":null,"abstract":"Electrocorticogram (ECoG) is an effective way for Epilepsy research, as well as automatic seizure detection. This study proposes a method for feature extraction and classification of pre-ictal and ictal ECoGs, based upon mutual information (MI) and support vector machine (SVM) which has not only high accuracy but also fast speed. First, the mutual information among 76 channels is computed and converted into a 76×76 matrix, and then statistical significance of splicing mutual information between pre-ictal and ictal ECoGs is tested, and the coefficients of variation and fluctuation indexes of MI corresponding to the selected channels which exhibit the most significant differences are selected as features. SVM is then used as the classifier for identifying ictal ECoGs. In addition, two methods based on empirical mode decomposition (EMD) and wavelet, are applied on data as a control. The results of this study show that the MI of the selected channels from pre-ictal ECoGs is higher than that from ictal ECoGs, and the classification accuracy by combining coefficients of variation and fluctuation indexes as feature vectors is up to 100% and faster than the other methods.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125645778","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 : 2017-05-01DOI: 10.1109/ICSIGSYS.2017.7967063
Fauzy Satrio Wibowo, Febrianto Alqodri, Nurani Lathifah, S. Sendari, D. Lestari, A. N. Handayani, Y. Rahmawati, Ardi Lestari, Choirul Ulfa Kusumahadi
This paper describes the proposed system, which is able to monitor, record and give indicator about air quality information especially the CO values in the environment. The system is designed to work real time using web-based and android applications. A portable gas detector was developed using micro controller. In order to detect the CO value, TGS2600 is used; here an additional function is added by using a thermal sensor to detect the temperature in the environment. Furthermore, a WiFi module is attached to the micro controller to send the data and communicate with the web-based server. The advantage of the proposed system is that, the users can monitor, record and get a warning about the CO value portably. Moreover, the user can also setup the threshold level of each parameter. The proposed system was to be tested using by Black-box method to test the functionality. The results showed that the system runs well with 0% error and can show the CO and temperature values in real time.
{"title":"Developing portable instrument based on Internet of Things for Air Quality Information System","authors":"Fauzy Satrio Wibowo, Febrianto Alqodri, Nurani Lathifah, S. Sendari, D. Lestari, A. N. Handayani, Y. Rahmawati, Ardi Lestari, Choirul Ulfa Kusumahadi","doi":"10.1109/ICSIGSYS.2017.7967063","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967063","url":null,"abstract":"This paper describes the proposed system, which is able to monitor, record and give indicator about air quality information especially the CO values in the environment. The system is designed to work real time using web-based and android applications. A portable gas detector was developed using micro controller. In order to detect the CO value, TGS2600 is used; here an additional function is added by using a thermal sensor to detect the temperature in the environment. Furthermore, a WiFi module is attached to the micro controller to send the data and communicate with the web-based server. The advantage of the proposed system is that, the users can monitor, record and get a warning about the CO value portably. Moreover, the user can also setup the threshold level of each parameter. The proposed system was to be tested using by Black-box method to test the functionality. The results showed that the system runs well with 0% error and can show the CO and temperature values in real time.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123419559","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 : 2017-05-01DOI: 10.1109/ICSIGSYS.2017.7967067
Huyuan ShangGuan, R. Mukundan
Several methods for capturing motion data from single video have been reported in computer vision literature, and most of them deal with stationary background. The problem becomes more complex and challenging in a moving scene where traditional background subtraction algorithms often fail. We require robust algorithms for marker-less tracking of human body's movements and for extracting motion information from them. This paper reviews recent research work done in the area of video based 3D motion capture through marker-less tracking, learning and detection algorithms, and identifies their usefulness and limitations. The paper then proposes a novel framework based on state-of-the-art methods for object detection and pose estimation for obtaining the 3D joint positions of a tracked human model in a single view video stream. Experimental results are presented to show the effectiveness of the proposed algorithm in capturing 3D motion information.
{"title":"Video based motion capture in environments with non-stationary background","authors":"Huyuan ShangGuan, R. Mukundan","doi":"10.1109/ICSIGSYS.2017.7967067","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967067","url":null,"abstract":"Several methods for capturing motion data from single video have been reported in computer vision literature, and most of them deal with stationary background. The problem becomes more complex and challenging in a moving scene where traditional background subtraction algorithms often fail. We require robust algorithms for marker-less tracking of human body's movements and for extracting motion information from them. This paper reviews recent research work done in the area of video based 3D motion capture through marker-less tracking, learning and detection algorithms, and identifies their usefulness and limitations. The paper then proposes a novel framework based on state-of-the-art methods for object detection and pose estimation for obtaining the 3D joint positions of a tracked human model in a single view video stream. Experimental results are presented to show the effectiveness of the proposed algorithm in capturing 3D motion information.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121190258","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 : 2017-05-01DOI: 10.1109/ICSIGSYS.2017.7967066
R. Choras
Forearm vein recognition is one of the methods used for identification. In this paper forearms vein features are used for recognition in biometric systems. Forearm vein can be considered more secured compared to other biometric traits because the veins are inside the human body. The forearm recognition has been developed using characteristic points based technique where forearm image is normalized, binarized and thinned, is then a crossing number is used to extract properties of the veins e.g. bifurcation.
{"title":"Biometric personal authentication using images of forearm vein patterns","authors":"R. Choras","doi":"10.1109/ICSIGSYS.2017.7967066","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967066","url":null,"abstract":"Forearm vein recognition is one of the methods used for identification. In this paper forearms vein features are used for recognition in biometric systems. Forearm vein can be considered more secured compared to other biometric traits because the veins are inside the human body. The forearm recognition has been developed using characteristic points based technique where forearm image is normalized, binarized and thinned, is then a crossing number is used to extract properties of the veins e.g. bifurcation.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125599026","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 : 2017-05-01DOI: 10.1109/ICSIGSYS.2017.7967075
B. Rohman, M. Nishimoto
Landmines are a humanitarian challenge because they do not discriminate between soldiers and civilians. One potential method for detecting unexploded landmines in post-conflict zones is the use of ground penetrating radar (GPR). However, detecting shallowly-buried landmines under a variety of soil and surface conditions is a challenging task in terms of signal processing. The present paper proposes a new approach based on multi-scale power spectrum features. The power spectrum of GPR response is processed using multi-scale triangular filter banks in order to produce a set of feature coefficients, which are then ranked by their significance with respect to the classification using the feature selection algorithm ReliefF. Using these ranked features, a support vector machine based classifier is used to evaluate the feasibility of landmine detection using this approach. The soil conditions considered are homogeneous (dry), homogeneous (moist) and heterogeneous, with different surface roughnesses. The results indicate that the proposed method can successfully detect landmines in a variety of environments using a relatively small number of spectral features. In addition, the GPR frequency bands that are most effective for landmine detection tasks are identified.
{"title":"Multi-scaled power spectrum based features for landmine detection using Ground Penetrating Radar","authors":"B. Rohman, M. Nishimoto","doi":"10.1109/ICSIGSYS.2017.7967075","DOIUrl":"https://doi.org/10.1109/ICSIGSYS.2017.7967075","url":null,"abstract":"Landmines are a humanitarian challenge because they do not discriminate between soldiers and civilians. One potential method for detecting unexploded landmines in post-conflict zones is the use of ground penetrating radar (GPR). However, detecting shallowly-buried landmines under a variety of soil and surface conditions is a challenging task in terms of signal processing. The present paper proposes a new approach based on multi-scale power spectrum features. The power spectrum of GPR response is processed using multi-scale triangular filter banks in order to produce a set of feature coefficients, which are then ranked by their significance with respect to the classification using the feature selection algorithm ReliefF. Using these ranked features, a support vector machine based classifier is used to evaluate the feasibility of landmine detection using this approach. The soil conditions considered are homogeneous (dry), homogeneous (moist) and heterogeneous, with different surface roughnesses. The results indicate that the proposed method can successfully detect landmines in a variety of environments using a relatively small number of spectral features. In addition, the GPR frequency bands that are most effective for landmine detection tasks are identified.","PeriodicalId":212068,"journal":{"name":"2017 International Conference on Signals and Systems (ICSigSys)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114441469","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：