Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474182
Ashna Kakkar, Rakshita Singh, Nirdosh Nirdosh, M. Tripathy
In the manuscript, a wideband 1×2 array antenna is designed and simulated. This array antenna is composed of rectangular patch in which parametric study of U-slot is carried out. It covers wideband frequency range from 1.46 GHz to 6.15 GHz with factional bandwidth of 122.85%. Rogers RT/ Duroid 5880 substrate is used with relative permittivity of 2.20 and dielectric loss tangent of 0.0009. The dimension of this array is 75×105×0.79mm3 with reduced ground plane. Different simulated antenna characteristics such as return loss (< −10 dB), peak gain (13.86 dB) and radiation patterns are obtained to analyze the array performance. This proposed array can be used for energy harvesting applications at GSM, LTE and Wimax bands.
{"title":"A Wideband U-Slotted 1×2 Array Antenna For Energy Harvesting","authors":"Ashna Kakkar, Rakshita Singh, Nirdosh Nirdosh, M. Tripathy","doi":"10.1109/SPIN.2018.8474182","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474182","url":null,"abstract":"In the manuscript, a wideband 1×2 array antenna is designed and simulated. This array antenna is composed of rectangular patch in which parametric study of U-slot is carried out. It covers wideband frequency range from 1.46 GHz to 6.15 GHz with factional bandwidth of 122.85%. Rogers RT/ Duroid 5880 substrate is used with relative permittivity of 2.20 and dielectric loss tangent of 0.0009. The dimension of this array is 75×105×0.79mm3 with reduced ground plane. Different simulated antenna characteristics such as return loss (< −10 dB), peak gain (13.86 dB) and radiation patterns are obtained to analyze the array performance. This proposed array can be used for energy harvesting applications at GSM, LTE and Wimax bands.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127282069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474247
Prateechi Singh, V. Saxena
In case of a disease, a burn or an allergy, it is very important to have a regular check and a correct diagnosis by the doctor during the healing process of that scar or the patch affected. This will also help the doctor in deciding the perfect medicine for the patient’s scars. Various Digital Image Processing techniques have been devised to solve this problem. Although use of soft computing based methods are very popular now in almost every area of work, lack of training data poses a big challenge. Thus, we have devised the method to solve the problem of identifying the scar, size of the scar, find the degree of burn or disease mapping the redness of the scar and finding the number of clusters of scars in an image purely by using basic image processing ways. This method is effective and computationally fast in the decision making process for the doctors.
{"title":"Assessing the Scar Images to Check Medical Treatment Effectiveness","authors":"Prateechi Singh, V. Saxena","doi":"10.1109/SPIN.2018.8474247","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474247","url":null,"abstract":"In case of a disease, a burn or an allergy, it is very important to have a regular check and a correct diagnosis by the doctor during the healing process of that scar or the patch affected. This will also help the doctor in deciding the perfect medicine for the patient’s scars. Various Digital Image Processing techniques have been devised to solve this problem. Although use of soft computing based methods are very popular now in almost every area of work, lack of training data poses a big challenge. Thus, we have devised the method to solve the problem of identifying the scar, size of the scar, find the degree of burn or disease mapping the redness of the scar and finding the number of clusters of scars in an image purely by using basic image processing ways. This method is effective and computationally fast in the decision making process for the doctors.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125111182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474234
V. Bhardwaj, Tanya Goel, Garima Mahendru
Spectrum Sensing is the quintessence of Cognitive Radio Network and helps in decongesting the RF band. A lot of research has already been done in detection of free space in the frequency spectrum and the need of the hour is exploitation of a novel characteristic of a signal from a newer perspective. Cognitive radio works in a multi-antenna based system with a number of secondary user sensors wherein the signals from primary user is received from different directions. Thus, the angle dimension of the received signal can also be exploited to propose new sensing schemes. In this paper, a novel technique based on direction of arrival estimation has been augmented with wavelet packet decomposition to enhance the performance characteristics in case of closely-spaced DOA and low SNR. The proposed algorithm provides high resolution as well as significantly reduced computation load. The better performance and reliability of the proposed WDOA estimation have been experimentally validated and presented in form of computer simulations.
{"title":"A NOVEL WAVELET PACKET BASED DIRECTION OF ARRIVAL ESTIMATION FOR SPECTRUM SENSING IN COGNITIVE RADIO NETWORKS","authors":"V. Bhardwaj, Tanya Goel, Garima Mahendru","doi":"10.1109/SPIN.2018.8474234","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474234","url":null,"abstract":"Spectrum Sensing is the quintessence of Cognitive Radio Network and helps in decongesting the RF band. A lot of research has already been done in detection of free space in the frequency spectrum and the need of the hour is exploitation of a novel characteristic of a signal from a newer perspective. Cognitive radio works in a multi-antenna based system with a number of secondary user sensors wherein the signals from primary user is received from different directions. Thus, the angle dimension of the received signal can also be exploited to propose new sensing schemes. In this paper, a novel technique based on direction of arrival estimation has been augmented with wavelet packet decomposition to enhance the performance characteristics in case of closely-spaced DOA and low SNR. The proposed algorithm provides high resolution as well as significantly reduced computation load. The better performance and reliability of the proposed WDOA estimation have been experimentally validated and presented in form of computer simulations.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123738058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474156
Varun Mishra, S. Gupta, Y. Verma, V. Ramola, Abhishek Bora
In this paper, the challenge of enhancing the gain and reducing the power requirements of latch comparators, preferably used in oversampled ADC is addressed. It is demonstrated that by designing the pre-amplifier stage using composite cascode differential structure, in which some transistors operate in subthreshold/ weak inversion region, high-gain (79 dB) at low-power (412nW) and low input noise (111.4nV/sqrt(Hz)) with 1.5V power supply, can be obtained through this stage. The succeeding latch circuitry is designed to enhance the comparator speed and to kickback noise effect. The proposed latch comparator operates at a low power consumption of 32μW and has a propagation delay of 0.78 ns only. The op-amp is designed using 180nm CMOS technology and simulations that demonstrate results are given.
{"title":"A High-Gain, Low-Power Latch Comparator Design for Oversampled ADCs","authors":"Varun Mishra, S. Gupta, Y. Verma, V. Ramola, Abhishek Bora","doi":"10.1109/SPIN.2018.8474156","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474156","url":null,"abstract":"In this paper, the challenge of enhancing the gain and reducing the power requirements of latch comparators, preferably used in oversampled ADC is addressed. It is demonstrated that by designing the pre-amplifier stage using composite cascode differential structure, in which some transistors operate in subthreshold/ weak inversion region, high-gain (79 dB) at low-power (412nW) and low input noise (111.4nV/sqrt(Hz)) with 1.5V power supply, can be obtained through this stage. The succeeding latch circuitry is designed to enhance the comparator speed and to kickback noise effect. The proposed latch comparator operates at a low power consumption of 32μW and has a propagation delay of 0.78 ns only. The op-amp is designed using 180nm CMOS technology and simulations that demonstrate results are given.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125594180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474054
S. K. Rajendra, Malvi Shrimali, Sachin Doshi, M. Sharma
Transformer plays very important role in power system utility. Its protection against various faults is necessary to avoid catastrophic failures. The terminal behaviour of the transformer utters about its health. Thus, analysing the terminal behaviour is helpful in predicting condition of the transformer. In this paper, frequency response analysis (FRA) is deployed to capture terminal behaviour of the winding corresponding to its healthy and faulty states. The acquired FRA signals are supplied to the Daubechies Orthogonal Wavelet Filter Bank and are decomposed into various subbands (SBs). Afterwards, Log Energy (LE) feature is extracted corresponding to each decomposed subband. The extracted features are then classified using decision tree method. The proposed methodology is implemented on the equivalent circuit model of the transformer winding to classify its FRA signals into normal and faulty states. Result shows that the FRA signals are classified properly and accuracy of 98.3% is achieved. The statistical parameters clearly indicate the difference between healthy and faulty signals.
变压器在电力系统公用事业中起着非常重要的作用。它对各种故障的保护是避免灾难性故障所必需的。变压器的终端行为反映了它的健康状况。因此，分析变压器接线端子的行为有助于预测变压器的工作状态。在本文中，频率响应分析(FRA)被用于捕捉绕组在其健康和故障状态下的终端行为。采集到的FRA信号被送入多贝西正交小波滤波器组，并被分解成不同的子带。然后，提取每个分解子带对应的Log Energy (LE)特征。然后使用决策树方法对提取的特征进行分类。将该方法应用于变压器绕组的等效电路模型，将其FRA信号分为正常状态和故障状态。结果表明，该方法分类准确，准确率达到98.3%。统计参数清楚地表明健康信号和故障信号之间的差异。
{"title":"Detection of Power Transformer Winding Faults using Orthogonal Wavelet Filter Bank","authors":"S. K. Rajendra, Malvi Shrimali, Sachin Doshi, M. Sharma","doi":"10.1109/SPIN.2018.8474054","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474054","url":null,"abstract":"Transformer plays very important role in power system utility. Its protection against various faults is necessary to avoid catastrophic failures. The terminal behaviour of the transformer utters about its health. Thus, analysing the terminal behaviour is helpful in predicting condition of the transformer. In this paper, frequency response analysis (FRA) is deployed to capture terminal behaviour of the winding corresponding to its healthy and faulty states. The acquired FRA signals are supplied to the Daubechies Orthogonal Wavelet Filter Bank and are decomposed into various subbands (SBs). Afterwards, Log Energy (LE) feature is extracted corresponding to each decomposed subband. The extracted features are then classified using decision tree method. The proposed methodology is implemented on the equivalent circuit model of the transformer winding to classify its FRA signals into normal and faulty states. Result shows that the FRA signals are classified properly and accuracy of 98.3% is achieved. The statistical parameters clearly indicate the difference between healthy and faulty signals.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"460 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116450803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474258
Tapashi Thakuria, T. Bezboruah
In this paper a more efficient Radio Frequency(RF) energy harvesting system is designed at 900 MHz of ISM band. A schottky diode based Dickson voltage multiplier is used for enhancing the output DC voltage. The output efficiency is tested at the input power range from −10dBm to 40dBm using 1st, 2nd and 3rd stages of the multiplier. The maximum efficiency of the system is achieved at 10dBm which is 84.18 %.
{"title":"Design of an Efficient RF Energy Harvesting System at 900 MHz","authors":"Tapashi Thakuria, T. Bezboruah","doi":"10.1109/SPIN.2018.8474258","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474258","url":null,"abstract":"In this paper a more efficient Radio Frequency(RF) energy harvesting system is designed at 900 MHz of ISM band. A schottky diode based Dickson voltage multiplier is used for enhancing the output DC voltage. The output efficiency is tested at the input power range from −10dBm to 40dBm using 1st, 2nd and 3rd stages of the multiplier. The maximum efficiency of the system is achieved at 10dBm which is 84.18 %.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117101786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474036
Sachin N. Kapgate, Saurav Gupta, A. Sahoo
Many practical systems tend to have some extent of nonlinearity involved in their behavior. System identification and control design for nonlinear dynamical systems is achieving extensive attention in many practical applications. To model nonlinear system behavior, many mathematical models have been developed and employed in practical applications. This paper mainly focuses on application of least mean square (LMS) variants for the adaptive implementation of one such model known as nonlinear Volterra model. The challenging problems involved with the stability and convergence rate of traditional least mean square based approach are shown individually. The supporting analysis and simulations are provided to justify the efficacy of presented work. Least mean square variants based Volterra modeling approaches can be effectively applied in system control design, acoustic echo cancellation and stability analysis of the nonlinear systems.
{"title":"Adaptive Volterra Modeling For Nonlinear Systems Based on LMS Variants","authors":"Sachin N. Kapgate, Saurav Gupta, A. Sahoo","doi":"10.1109/SPIN.2018.8474036","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474036","url":null,"abstract":"Many practical systems tend to have some extent of nonlinearity involved in their behavior. System identification and control design for nonlinear dynamical systems is achieving extensive attention in many practical applications. To model nonlinear system behavior, many mathematical models have been developed and employed in practical applications. This paper mainly focuses on application of least mean square (LMS) variants for the adaptive implementation of one such model known as nonlinear Volterra model. The challenging problems involved with the stability and convergence rate of traditional least mean square based approach are shown individually. The supporting analysis and simulations are provided to justify the efficacy of presented work. Least mean square variants based Volterra modeling approaches can be effectively applied in system control design, acoustic echo cancellation and stability analysis of the nonlinear systems.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"32 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120909779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474276
S. Deka, Prakash Chauhan, N. Sarma
Cooperative Spectrum Sensing (CSS) in Cognitive Radio Network (CRN) is proven to enhance the efficiency of spectrum sensing by using spatial diversity of secondary users (SUs). However, during designing of CSS schemes the incorporation of dynamic interaction among the SUs and the selection of appropriate sensing threshold play an important role. This paper contributes in the following way by - (i) proposing a coalitional game theory based model for CSS, (ii) proposing a distance based adaptive sensing threshold determination technique and (iii) considering cooperation overhead in CSS due to reporting error. The CSS model is evaluated via simulation studies and the results obtained show that proposed model improves performance of spectrum sensing in terms of detection probability compared to similar CSS techniques.
{"title":"Dynamic Threshold based Cooperative Spectrum Sensing using Coalitional Game for CRNs","authors":"S. Deka, Prakash Chauhan, N. Sarma","doi":"10.1109/SPIN.2018.8474276","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474276","url":null,"abstract":"Cooperative Spectrum Sensing (CSS) in Cognitive Radio Network (CRN) is proven to enhance the efficiency of spectrum sensing by using spatial diversity of secondary users (SUs). However, during designing of CSS schemes the incorporation of dynamic interaction among the SUs and the selection of appropriate sensing threshold play an important role. This paper contributes in the following way by - (i) proposing a coalitional game theory based model for CSS, (ii) proposing a distance based adaptive sensing threshold determination technique and (iii) considering cooperation overhead in CSS due to reporting error. The CSS model is evaluated via simulation studies and the results obtained show that proposed model improves performance of spectrum sensing in terms of detection probability compared to similar CSS techniques.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128084581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474111
Pranjal Gupta, M. Srivastava, D. Prasad, Ajay Roy, Manish Kumar Verma
This research paper proposes a new circuit configuration which can act like a grounded impedance simulator/grounded impedance scaling circuit. The presented configuration can simulate electronically tunable grounded resistance/capacitance/inductance/FDNR and also work as a grounded impedance multiplier circuit, which can scale-up/scale-down the value of arbitrary grounded impedance with an electronically controllable multiplication factor. The proposed circuit employed three voltage difference trans-conductance amplifiers along with three grounded passive elements. The use of grounded passive elements makes this realization suitable for monolithic integration. The presented circuit does not have any requirement of matched passive elements. Under non ideal conditions the behavior of proposed configuration is found un-deviated. To verify the mathematical analysis, the presented configuration is simulated under PSPICE TSMC 0.18μm simulation environment.
{"title":"A Generalized Grounded Impedance Simulator/Grounded Impedance Scaling Circuit with Electronic Tuning","authors":"Pranjal Gupta, M. Srivastava, D. Prasad, Ajay Roy, Manish Kumar Verma","doi":"10.1109/SPIN.2018.8474111","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474111","url":null,"abstract":"This research paper proposes a new circuit configuration which can act like a grounded impedance simulator/grounded impedance scaling circuit. The presented configuration can simulate electronically tunable grounded resistance/capacitance/inductance/FDNR and also work as a grounded impedance multiplier circuit, which can scale-up/scale-down the value of arbitrary grounded impedance with an electronically controllable multiplication factor. The proposed circuit employed three voltage difference trans-conductance amplifiers along with three grounded passive elements. The use of grounded passive elements makes this realization suitable for monolithic integration. The presented circuit does not have any requirement of matched passive elements. Under non ideal conditions the behavior of proposed configuration is found un-deviated. To verify the mathematical analysis, the presented configuration is simulated under PSPICE TSMC 0.18μm simulation environment.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130823916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-01DOI: 10.1109/SPIN.2018.8474266
C. Jayaprakash, B. Damodaran, S. V., K P Soman
Independent Component Analysis (ICA) is a commonly used technique for the dimensionality reduction of Hyperspectral images (HSI) to capture the linear relationship in the original input features of the image. Even though kernel methods were introduced to capture the nonlinear features, they possess high computational complexity, while dealing with a large number of pixels of HSI. Recent research has introduced Random Fourier feature maps (RFF) to project high dimensional data to low dimension. In this paper, we propose a nonlinear component analysis for the dimensionality reduction of HSI based on RFF maps. The proposed method has experimented on two dataset namely Pavia University and Salinas scene. It is verified that the feature extracted using RFF maps outperforms the conventional and kernel methods, in terms of classification accuracy.
{"title":"Dimensionality Reduction of Hyperspectral Images for Classification using Randomized Independent Component Analysis","authors":"C. Jayaprakash, B. Damodaran, S. V., K P Soman","doi":"10.1109/SPIN.2018.8474266","DOIUrl":"https://doi.org/10.1109/SPIN.2018.8474266","url":null,"abstract":"Independent Component Analysis (ICA) is a commonly used technique for the dimensionality reduction of Hyperspectral images (HSI) to capture the linear relationship in the original input features of the image. Even though kernel methods were introduced to capture the nonlinear features, they possess high computational complexity, while dealing with a large number of pixels of HSI. Recent research has introduced Random Fourier feature maps (RFF) to project high dimensional data to low dimension. In this paper, we propose a nonlinear component analysis for the dimensionality reduction of HSI based on RFF maps. The proposed method has experimented on two dataset namely Pavia University and Salinas scene. It is verified that the feature extracted using RFF maps outperforms the conventional and kernel methods, in terms of classification accuracy.","PeriodicalId":184596,"journal":{"name":"2018 5th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"269 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131249524","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：