Pub Date : 2014-12-01DOI: 10.1109/ICCIC.2014.7238424
Surendra Gupta, Hema Saini
Brain-Computer Interfaces (BCIs) are communication systems, in which users use their brain activity instead of original motor movements, to produce signals related to specific intention, which in turn are used to control computers or communication devices attached to it. These activities are generally measured by Electroencephalography (EEG). BCI uses pattern recognition approach in which features are extracted from EEG signals which are used to identify the user's mental state. BCI commonly used feature extraction method is Common Spatial Pattern (CSP). Despite of its effective usefulness, it suffers from intrinsic variations and nonstationarity of EEG data as CSP ignores the within class dissimilarities. Also, the formulation of CSP criteria is based on variance using L2-norm, which makes it sensitive to outliers too. A new PCA plus LDA method based on L1-norm has been proposed alternative to CSP which efficiently considers between the classes and within the class dissimilarities. Also the objective function is reformulated using L1-norm to suppress the effect of outliers. The optimal spatial pattern of given method are obtained by introducing an iterative algorithm. The proposed method was evaluated against Dataset IIa of BCI Competition IV. The result showed that the proposed method outperformed in almost all the cases with low mis-classification rate and results in average kappa value 0.3482.
{"title":"EEG features extraction using PCA plus LDA approach based on L1-norm for motor imaginary classification","authors":"Surendra Gupta, Hema Saini","doi":"10.1109/ICCIC.2014.7238424","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238424","url":null,"abstract":"Brain-Computer Interfaces (BCIs) are communication systems, in which users use their brain activity instead of original motor movements, to produce signals related to specific intention, which in turn are used to control computers or communication devices attached to it. These activities are generally measured by Electroencephalography (EEG). BCI uses pattern recognition approach in which features are extracted from EEG signals which are used to identify the user's mental state. BCI commonly used feature extraction method is Common Spatial Pattern (CSP). Despite of its effective usefulness, it suffers from intrinsic variations and nonstationarity of EEG data as CSP ignores the within class dissimilarities. Also, the formulation of CSP criteria is based on variance using L2-norm, which makes it sensitive to outliers too. A new PCA plus LDA method based on L1-norm has been proposed alternative to CSP which efficiently considers between the classes and within the class dissimilarities. Also the objective function is reformulated using L1-norm to suppress the effect of outliers. The optimal spatial pattern of given method are obtained by introducing an iterative algorithm. The proposed method was evaluated against Dataset IIa of BCI Competition IV. The result showed that the proposed method outperformed in almost all the cases with low mis-classification rate and results in average kappa value 0.3482.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"13 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127017288","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238456
V. Palanisamy, A. Kumarkombaiya
The proposed methodology involved to finding the chain details of pharmaceutical compound by retrieving the data in numeric format which is taken from functional group. The data mining technique of Enhanced Knuth-Morris-Pratt algorithm used to readily implement to identify the pattern of chemical compounds as in string data based on functional groups connected to one another which is similar from the numeric data.
{"title":"Efficient analysis of pharmaceutical compound structure based on pattern matching algorithm in data mining techniques","authors":"V. Palanisamy, A. Kumarkombaiya","doi":"10.1109/ICCIC.2014.7238456","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238456","url":null,"abstract":"The proposed methodology involved to finding the chain details of pharmaceutical compound by retrieving the data in numeric format which is taken from functional group. The data mining technique of Enhanced Knuth-Morris-Pratt algorithm used to readily implement to identify the pattern of chemical compounds as in string data based on functional groups connected to one another which is similar from the numeric data.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129301212","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238410
Upasana Trivedi, N. Dutta
The Transmission Control Protocol (TCP) is most important transport layer protocol for the internet access over TCP/IP. The TCP protocol was mainly designed for wired network and it assumes that the packet loss in the network occurs mainly due to congestion only. However, in wireless environment the scenario is somewhat different. As compared to wired link, wireless links are slower and less reliable. Furthermore, characteristic of the wireless network, such as user mobility plays another significant role in packet loss. The loss of packets due to link failure or user movement in wireless part is much more higher compared to loss due to congestion. In this research, we aimed at designing a strategy by extending regular TCP in order to minimize the packet loss and increase throughput to end users. We are specifically targeting a LAN connected users in a moving train and trying to provide reliable connection over TCP session. Few modifications to regular TCP and some new functional components like Mobile TCP Agent (MTA) is proposed to handle TCP session on the train.
{"title":"A novel approach to handle TCP connections for LAN in mobile vehicle","authors":"Upasana Trivedi, N. Dutta","doi":"10.1109/ICCIC.2014.7238410","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238410","url":null,"abstract":"The Transmission Control Protocol (TCP) is most important transport layer protocol for the internet access over TCP/IP. The TCP protocol was mainly designed for wired network and it assumes that the packet loss in the network occurs mainly due to congestion only. However, in wireless environment the scenario is somewhat different. As compared to wired link, wireless links are slower and less reliable. Furthermore, characteristic of the wireless network, such as user mobility plays another significant role in packet loss. The loss of packets due to link failure or user movement in wireless part is much more higher compared to loss due to congestion. In this research, we aimed at designing a strategy by extending regular TCP in order to minimize the packet loss and increase throughput to end users. We are specifically targeting a LAN connected users in a moving train and trying to provide reliable connection over TCP session. Few modifications to regular TCP and some new functional components like Mobile TCP Agent (MTA) is proposed to handle TCP session on the train.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585924","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238526
T. Mohanapriya, T. Manikandan
In a deregulated power industry, estimation of power price and management of congestion is a major issues handled by market members. Modeling of sensible pricing structure of power systems is important to provide financial signals for electrical utilities. Locational Marginal Pricing technique is used to determine the energy price for transacted power and to manage the system congestion. In this paper Lossless Direct Current Optimal Power Flow is used to find the LMP value at each bus. Resulting optimization problem is solved by Linear Programming. Variation of LMP values with transmission constraint is studied in this paper. Simulation is carried out on IEEE 14 bus test system and obtained result gives the electricity value at each location.
{"title":"Congestion management of deregulated electricity market using locational marginal pricing","authors":"T. Mohanapriya, T. Manikandan","doi":"10.1109/ICCIC.2014.7238526","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238526","url":null,"abstract":"In a deregulated power industry, estimation of power price and management of congestion is a major issues handled by market members. Modeling of sensible pricing structure of power systems is important to provide financial signals for electrical utilities. Locational Marginal Pricing technique is used to determine the energy price for transacted power and to manage the system congestion. In this paper Lossless Direct Current Optimal Power Flow is used to find the LMP value at each bus. Resulting optimization problem is solved by Linear Programming. Variation of LMP values with transmission constraint is studied in this paper. Simulation is carried out on IEEE 14 bus test system and obtained result gives the electricity value at each location.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"34 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123366246","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238348
M. Mayilvaganan, K. Rajeswari
The proposed methodology involved in this paper, is to diagnosis and analysis the health risk factor which is related to Blood Pressure, Pulse rate and Kidney function by Glomerular Filtration Rate (GFR). The computing techniques can handle two most predominant values such as `True' or `False', `1' or `0', `Black' or `White', but Fuzzy Logic, also handle grey values which occur in between `Black' and `White'. The system consists of 234 combination input fields and one output field. This work focus about Adaptive Neuro Fuzzy Interface System (ANFIS) depends on fuzzy logic controller to diagnose the various level of health risk factor value which is aggregated with Blood Pressure, Pulse Rate and Kidney function based on various Input Parameters. In this paper, Fuzzy Logic circuit was developed with 2's Complement in full adder using the input such as Blood Pressure value taken from Systolic and Diastolic value, Pulse Rate and GFR value. Using the OR gate value, Pulse rate and Blood pressure value are compared with Kidney function and getting the output as risk factor value in efficient manner. The input rule based classifier membership functions are X0, X1, X2. Xn for blood pressure values such as Low, Normal, Very Low, Extreme Low Meds, Very Danger Low, Danger too Low BP, Border Line, Very Danger High Blood pressure etc and the output classifier membership function are Y0, Y1, Y2. Yn for risk factor values such as Low, High and Normal. The proposed ANFIS system is validated with blood pressure data set values using Mat Lab Fuzzy Tool Box, and simulated output analyse the risk factor value of a human being.
{"title":"Risk factor analysis of patient based on adaptive neuro fuzzy interface system","authors":"M. Mayilvaganan, K. Rajeswari","doi":"10.1109/ICCIC.2014.7238348","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238348","url":null,"abstract":"The proposed methodology involved in this paper, is to diagnosis and analysis the health risk factor which is related to Blood Pressure, Pulse rate and Kidney function by Glomerular Filtration Rate (GFR). The computing techniques can handle two most predominant values such as `True' or `False', `1' or `0', `Black' or `White', but Fuzzy Logic, also handle grey values which occur in between `Black' and `White'. The system consists of 234 combination input fields and one output field. This work focus about Adaptive Neuro Fuzzy Interface System (ANFIS) depends on fuzzy logic controller to diagnose the various level of health risk factor value which is aggregated with Blood Pressure, Pulse Rate and Kidney function based on various Input Parameters. In this paper, Fuzzy Logic circuit was developed with 2's Complement in full adder using the input such as Blood Pressure value taken from Systolic and Diastolic value, Pulse Rate and GFR value. Using the OR gate value, Pulse rate and Blood pressure value are compared with Kidney function and getting the output as risk factor value in efficient manner. The input rule based classifier membership functions are X0, X1, X2. Xn for blood pressure values such as Low, Normal, Very Low, Extreme Low Meds, Very Danger Low, Danger too Low BP, Border Line, Very Danger High Blood pressure etc and the output classifier membership function are Y0, Y1, Y2. Yn for risk factor values such as Low, High and Normal. The proposed ANFIS system is validated with blood pressure data set values using Mat Lab Fuzzy Tool Box, and simulated output analyse the risk factor value of a human being.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121179849","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238544
S. Vijayalakshmi, D. Manimegalai
Selection of attributes plays a vital role to improve the quality of clustering. We present a comparative study on three attribute selection techniques and it reveals unattempt combinations, and provides guidelines in selecting attributes. It is occasionally studied in unsupervised learning; however it has been extensively explored in supervised learning. The suggested framework is primarily concerned with the problem of determining and selecting key distributional noun attributes, which are nominated by ranking the attributes according to the importance measure scores from the original noun attributes without class information. Experimental results on Reuter, 20 Newsgroup, WebKB and SCJC (Specific Crime Judgment Corpus) datasets indicate that algorithm with different scores in the context are able to identify the important attributes.
{"title":"Distributed noun attribute based on its first appearance for text document clustering","authors":"S. Vijayalakshmi, D. Manimegalai","doi":"10.1109/ICCIC.2014.7238544","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238544","url":null,"abstract":"Selection of attributes plays a vital role to improve the quality of clustering. We present a comparative study on three attribute selection techniques and it reveals unattempt combinations, and provides guidelines in selecting attributes. It is occasionally studied in unsupervised learning; however it has been extensively explored in supervised learning. The suggested framework is primarily concerned with the problem of determining and selecting key distributional noun attributes, which are nominated by ranking the attributes according to the importance measure scores from the original noun attributes without class information. Experimental results on Reuter, 20 Newsgroup, WebKB and SCJC (Specific Crime Judgment Corpus) datasets indicate that algorithm with different scores in the context are able to identify the important attributes.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121585547","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238511
Jitendra Singh, S. Goyal
In present days, power crisis increasing due to increase the consumer's load. To overcome this problem some optimization techniques have been used to solve the economic load dispatch problem. This paper presents an efficient and reliable Biogeography Based Optimization (BBO) algorithm, which is used to solve the Economic Load Dispatch problem of thermal power station even as generator and transmission constraints are considered and satisfying it. Biogeography basically is the study of the geographical distribution of the biological organism. Biogeography based optimization is a comparatively new approach. Mathematical models of biogeography explain how an organism arises and how to migrate from one habitat to another habitat, or get died out. In BBO algorithm, solutions are sharing the good features between solutions that are immigration and emigration process. This algorithm looks for the overall optimum solution mostly through two steps - Migration and Mutation. The Results of the proposed method have been compared with results of IEEE 30-bus, 6 generator system and got the better quality of the obtained solution. This method is one of the prominent approaches for solving the Economic Load Dispatch problems under practical conditions.
{"title":"Transmission constrained economic load dispatch using biogeography based optimization","authors":"Jitendra Singh, S. Goyal","doi":"10.1109/ICCIC.2014.7238511","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238511","url":null,"abstract":"In present days, power crisis increasing due to increase the consumer's load. To overcome this problem some optimization techniques have been used to solve the economic load dispatch problem. This paper presents an efficient and reliable Biogeography Based Optimization (BBO) algorithm, which is used to solve the Economic Load Dispatch problem of thermal power station even as generator and transmission constraints are considered and satisfying it. Biogeography basically is the study of the geographical distribution of the biological organism. Biogeography based optimization is a comparatively new approach. Mathematical models of biogeography explain how an organism arises and how to migrate from one habitat to another habitat, or get died out. In BBO algorithm, solutions are sharing the good features between solutions that are immigration and emigration process. This algorithm looks for the overall optimum solution mostly through two steps - Migration and Mutation. The Results of the proposed method have been compared with results of IEEE 30-bus, 6 generator system and got the better quality of the obtained solution. This method is one of the prominent approaches for solving the Economic Load Dispatch problems under practical conditions.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114877371","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238370
S. V. Viraktamath, Satish Rachayya Hiremath, G. V. Attimarad
Present day modern hand held communicating devices rely on forward error correction techniques for their proper functioning. Most digital communication systems nowadays convolutionally encode the transmitted data to compensate for Additive White Gaussian Noise (AWGN), fading of the channel, quantization distortions and other data degradation effects. For its efficient performance the Viterbi algorithm has proven to be a very practical algorithm for forward error correction of convolutionally encoded messages. Convolutional coding and Viterbi decoding is one of the forward error correction technique used in most of the communication applications. This paper investigates the impact of code rates on the performance of hard decision Viterbi decoder for image transmission applications. In this paper different code rates such as 1/2, 2/3 and 3/5 have been simulated using different constraint lengths as well as different generator polynomials for the image input. For the lesser BER reconstructed image can be processed to get lesser MSE. All the simulations are conducted in MATLAB over AWGN channel.
{"title":"Impact of code rate and improvisation of the reconstructed image for CODEC","authors":"S. V. Viraktamath, Satish Rachayya Hiremath, G. V. Attimarad","doi":"10.1109/ICCIC.2014.7238370","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238370","url":null,"abstract":"Present day modern hand held communicating devices rely on forward error correction techniques for their proper functioning. Most digital communication systems nowadays convolutionally encode the transmitted data to compensate for Additive White Gaussian Noise (AWGN), fading of the channel, quantization distortions and other data degradation effects. For its efficient performance the Viterbi algorithm has proven to be a very practical algorithm for forward error correction of convolutionally encoded messages. Convolutional coding and Viterbi decoding is one of the forward error correction technique used in most of the communication applications. This paper investigates the impact of code rates on the performance of hard decision Viterbi decoder for image transmission applications. In this paper different code rates such as 1/2, 2/3 and 3/5 have been simulated using different constraint lengths as well as different generator polynomials for the image input. For the lesser BER reconstructed image can be processed to get lesser MSE. All the simulations are conducted in MATLAB over AWGN channel.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115918196","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238376
A. Murugan, T. Sridevi
Feature selection or variable reduction is a fundamental problem in data mining, refers to the process of identifying the few most important features for application of a learning algorithm. The best subset contains the minimum number of dimensions retaining a suitably high accuracy on classifier in representing the original features. The objective of the proposed approach is to reduce the number of input features thus to identify the key features and eliminating irrelevant features with no predictive information using clustering technique, K-nearest neighbors (KNN) and rough set. This paper deals with two partition based clustering algorithm in data mining namely K-Means and Fuzzy C Means (FCM). These two algorithms are implemented for original data set without considering the class labels and further rough set theory implemented on the partitioned data set to generate feature subset after removing the outlier by using KNN. Wisconsin Breast Cancer datasets derived from UCI machine learning database are used for the purpose of testing the proposed hybrid method. The results show that the hybrid method is able to produce more accurate diagnosis and prognosis results than the full input model with respect to the classification accuracy.
{"title":"An enhanced feature selection method comprising rough set and clustering techniques","authors":"A. Murugan, T. Sridevi","doi":"10.1109/ICCIC.2014.7238376","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238376","url":null,"abstract":"Feature selection or variable reduction is a fundamental problem in data mining, refers to the process of identifying the few most important features for application of a learning algorithm. The best subset contains the minimum number of dimensions retaining a suitably high accuracy on classifier in representing the original features. The objective of the proposed approach is to reduce the number of input features thus to identify the key features and eliminating irrelevant features with no predictive information using clustering technique, K-nearest neighbors (KNN) and rough set. This paper deals with two partition based clustering algorithm in data mining namely K-Means and Fuzzy C Means (FCM). These two algorithms are implemented for original data set without considering the class labels and further rough set theory implemented on the partitioned data set to generate feature subset after removing the outlier by using KNN. Wisconsin Breast Cancer datasets derived from UCI machine learning database are used for the purpose of testing the proposed hybrid method. The results show that the hybrid method is able to produce more accurate diagnosis and prognosis results than the full input model with respect to the classification accuracy.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132404576","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238315
R. Palaniappan, K. Sundaraj, Sebastian Sundaraj, N. Huliraj, S. S. Revadi, B. Archana
Pulmonary acoustic signal analysis provides essential information on the present state of the Lungs. In this paper, we intend to distinguish between normal, airway obstruction pathology and interstitial lung disease using pulmonary acoustic signal recordings. The proposed method extracts Mel frequency cepstral coefficients (MFCC) and AR Coefficients as features from pulmonary acoustic signals. The extracted features are then classified using Artificial Neural Network (ANN) classifier. The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 92.59% and 91.69% was reported for the MFCC features and AR coefficients features respectively. The performance analysis of the ANN classifier using confusion matrix revealed that normal, airway obstruction and interstitial lung disease are classified at 92.75%, 91.30% and 92.75% classification accuracy respectively for the MFCC features. Similarly, normal, airway obstruction and interstitial lung disease are classified at 92.75%, 91.30% and 89.85% classification accuracy respectively for the AR coefficient features. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and interstitial lung disease.
{"title":"Classification of respiratory pathology in pulmonary acoustic signals using parametric features and artificial neural network","authors":"R. Palaniappan, K. Sundaraj, Sebastian Sundaraj, N. Huliraj, S. S. Revadi, B. Archana","doi":"10.1109/ICCIC.2014.7238315","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238315","url":null,"abstract":"Pulmonary acoustic signal analysis provides essential information on the present state of the Lungs. In this paper, we intend to distinguish between normal, airway obstruction pathology and interstitial lung disease using pulmonary acoustic signal recordings. The proposed method extracts Mel frequency cepstral coefficients (MFCC) and AR Coefficients as features from pulmonary acoustic signals. The extracted features are then classified using Artificial Neural Network (ANN) classifier. The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 92.59% and 91.69% was reported for the MFCC features and AR coefficients features respectively. The performance analysis of the ANN classifier using confusion matrix revealed that normal, airway obstruction and interstitial lung disease are classified at 92.75%, 91.30% and 92.75% classification accuracy respectively for the MFCC features. Similarly, normal, airway obstruction and interstitial lung disease are classified at 92.75%, 91.30% and 89.85% classification accuracy respectively for the AR coefficient features. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and interstitial lung disease.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130139548","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：