Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160174
Gurmeet Singh, S. Anand, Brejesh Lall, Anurag Srivastava, Vaneet Singh
Electrical Impedance Tomography (EIT) is one of the growing and optimistic imaging modality for clinical imaging with such advantages as: non-invasive, low cost, ease of use and practicality, this method has been used in many areas of science and research. This paper consists of designing and development of hardware for EIT system using microcontroller MSP430G2 and AVR ATMEGA 16. A 16-electrode phantom is developed and studied with an instrumentation for EIT. Using serial communication data applies to PC for image reconstruction using EIDORS.
{"title":"Development of a microcontroller based electrical impedance tomography system","authors":"Gurmeet Singh, S. Anand, Brejesh Lall, Anurag Srivastava, Vaneet Singh","doi":"10.1109/LISAT.2015.7160174","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160174","url":null,"abstract":"Electrical Impedance Tomography (EIT) is one of the growing and optimistic imaging modality for clinical imaging with such advantages as: non-invasive, low cost, ease of use and practicality, this method has been used in many areas of science and research. This paper consists of designing and development of hardware for EIT system using microcontroller MSP430G2 and AVR ATMEGA 16. A 16-electrode phantom is developed and studied with an instrumentation for EIT. Using serial communication data applies to PC for image reconstruction using EIDORS.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116644665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160194
Zyad Nossire, J. Dichter, Navarun Gupta, J. Fathi
Mobile phone base station (tower) provides coverage for one or more geographical areas, known as cells. A mobile phone network is made up of a base station operating in conjunction with adjacent base stations. Base stations must be carefully located in relation to each other, so each cell in the network functions efficiently to ensure minimum interference between cells and good signal quality. One of the major problems for cellular wireless devices is calls being dropped and failure in downloading data. Our research uses a new recommendation in determining tower positions. Thus, providing an easy interface to replace traditional control methods and maintain signal levels. The weak WiFi wave propagation outside tower's coverage areas is investigated at the University of Bridgeport (UB) campus. The campus serves as good experimental settings because it exemplifies typical signal dead spots, locations where little to no WiFi signal is available. In this paper, we investigate path loss propagation between the base stations and we identify and categorize these problems. We then apply our path loss propagation algorithmic models to show that signal strength is significantly improved when applying the proposed model. Finally, we show the efficiency of the proposed positions.
移动电话基站(塔)提供覆盖一个或多个地理区域，称为小区。移动电话网络是由一个基站与相邻的基站一起操作组成的。基站之间必须仔细定位，这样网络中的每个小区才能有效地工作，以确保小区之间的干扰最小和良好的信号质量。蜂窝无线设备的主要问题之一是掉线和下载数据失败。我们的研究采用了一种新的建议来确定塔的位置。因此，提供了一个简单的接口，以取代传统的控制方法和维持信号电平。在布里奇波特大学(University of Bridgeport, UB)校园内，对塔架覆盖区域外的弱WiFi波传播进行了研究。校园是一个很好的实验场所，因为它是典型的信号盲区，在那里几乎没有WiFi信号可用。本文研究了基站间的路径损耗传播问题，并对这些问题进行了识别和分类。然后，我们应用我们的路径损耗传播算法模型来表明，当应用所提出的模型时，信号强度显着提高。最后，我们展示了所提出的位置的效率。
{"title":"A new selected points to enhance radio wave propagation strength outside the coverage area of the mobile towers in the dead spots of cellular mobile WiFi downloads","authors":"Zyad Nossire, J. Dichter, Navarun Gupta, J. Fathi","doi":"10.1109/LISAT.2015.7160194","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160194","url":null,"abstract":"Mobile phone base station (tower) provides coverage for one or more geographical areas, known as cells. A mobile phone network is made up of a base station operating in conjunction with adjacent base stations. Base stations must be carefully located in relation to each other, so each cell in the network functions efficiently to ensure minimum interference between cells and good signal quality. One of the major problems for cellular wireless devices is calls being dropped and failure in downloading data. Our research uses a new recommendation in determining tower positions. Thus, providing an easy interface to replace traditional control methods and maintain signal levels. The weak WiFi wave propagation outside tower's coverage areas is investigated at the University of Bridgeport (UB) campus. The campus serves as good experimental settings because it exemplifies typical signal dead spots, locations where little to no WiFi signal is available. In this paper, we investigate path loss propagation between the base stations and we identify and categorize these problems. We then apply our path loss propagation algorithmic models to show that signal strength is significantly improved when applying the proposed model. Finally, we show the efficiency of the proposed positions.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117214180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160191
M. Almi'ani, B. Barkana
The progress of medical imaging instrumentation has stirred the development of new computer-aided methods of image processing and analysis for better understanding and interpretation of medical images for differential diagnosis, intervention, and treatment monitoring. Image processing and analysis methods have been used to help physicians to make important medical decisions through physician-computer interaction. A modified region growing algorithm is proposed to extract cerebral vessels using a magnetic resonance angiography (MRA) database. To improve the performance of the image segmentation method, as a pre-processing step, image enhancement methods are applied by the gamma correction technique and spatial operations. This step improves the detection of gray-level discontinuities in MRA images. The traditional region growing method is modified by extending the neighborhood as 24 pixels and by defining a filling protocol to label vascular structure. The performance of the proposed algorithm is compared with that of the traditional region growing method and four other segmentation methods. Our proposed method outperformed the other methods. The minimum and maximum errors of the modified region growing method is calculated as zero and 0.82, respectively while the traditional region growing method has 1.85 and 21.91.
{"title":"A modified region growing based algorithm to vessel segmentation in magnetic resonance angiography","authors":"M. Almi'ani, B. Barkana","doi":"10.1109/LISAT.2015.7160191","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160191","url":null,"abstract":"The progress of medical imaging instrumentation has stirred the development of new computer-aided methods of image processing and analysis for better understanding and interpretation of medical images for differential diagnosis, intervention, and treatment monitoring. Image processing and analysis methods have been used to help physicians to make important medical decisions through physician-computer interaction. A modified region growing algorithm is proposed to extract cerebral vessels using a magnetic resonance angiography (MRA) database. To improve the performance of the image segmentation method, as a pre-processing step, image enhancement methods are applied by the gamma correction technique and spatial operations. This step improves the detection of gray-level discontinuities in MRA images. The traditional region growing method is modified by extending the neighborhood as 24 pixels and by defining a filling protocol to label vascular structure. The performance of the proposed algorithm is compared with that of the traditional region growing method and four other segmentation methods. Our proposed method outperformed the other methods. The minimum and maximum errors of the modified region growing method is calculated as zero and 0.82, respectively while the traditional region growing method has 1.85 and 21.91.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132474813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160217
R. Desimone, Betsy Mendieta Brito, J. Baston
Indoor signal propagation characteristics can be difficult to predict accurately. Factors such as building layout and building materials can have a major effect on signal propagation. In this paper we will model indoor signal propagation using lognormal shadowing characteristics. The benefit of this model over others is its simplicity. The accuracy of this model at predicting the relationship between received signal strength (RSS) and the distance from transmitter to receiver will be determined. The link that was tested and modeled uses the IEEE 802.11n standard. Both 2.4 GHz and 5 GHz Industrial Scientific and Medical (ISM) bands were tested and modeled.
{"title":"Model of indoor signal propagation using log-normal shadowing","authors":"R. Desimone, Betsy Mendieta Brito, J. Baston","doi":"10.1109/LISAT.2015.7160217","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160217","url":null,"abstract":"Indoor signal propagation characteristics can be difficult to predict accurately. Factors such as building layout and building materials can have a major effect on signal propagation. In this paper we will model indoor signal propagation using lognormal shadowing characteristics. The benefit of this model over others is its simplicity. The accuracy of this model at predicting the relationship between received signal strength (RSS) and the distance from transmitter to receiver will be determined. The link that was tested and modeled uses the IEEE 802.11n standard. Both 2.4 GHz and 5 GHz Industrial Scientific and Medical (ISM) bands were tested and modeled.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134217111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160192
Ramadhan J. Mstafa, K. Elleithy
Recently, video steganography has become a popular option for a secret data communication. The performance of any steganography algorithm is based on the embedding efficiency, embedding payload, and robustness against attackers. In this paper, we propose a novel video steganography algorithm in the wavelet domain based on the KLT tracking algorithm and BCH codes. The proposed algorithm includes four different phases. First, the secret message is preprocessed, and BCH codes (n, k, t) are applied in order to produce an encoded message. Second, face detection and face tracking algorithms are applied on the cover videos in order to identify the facial regions of interest. Third, the process of embedding the encoded message into the high and middle frequency wavelet coefficients of all facial regions is performed. Forth, the process of extracting the secret message from the high and middle frequency wavelet coefficients for each RGB components of all facial regions is accomplished. Experimental results of the proposed video steganography algorithm have demonstrated a high embedding efficiency and a high embedding payload.
{"title":"A novel video steganography algorithm in the wavelet domain based on the KLT tracking algorithm and BCH codes","authors":"Ramadhan J. Mstafa, K. Elleithy","doi":"10.1109/LISAT.2015.7160192","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160192","url":null,"abstract":"Recently, video steganography has become a popular option for a secret data communication. The performance of any steganography algorithm is based on the embedding efficiency, embedding payload, and robustness against attackers. In this paper, we propose a novel video steganography algorithm in the wavelet domain based on the KLT tracking algorithm and BCH codes. The proposed algorithm includes four different phases. First, the secret message is preprocessed, and BCH codes (n, k, t) are applied in order to produce an encoded message. Second, face detection and face tracking algorithms are applied on the cover videos in order to identify the facial regions of interest. Third, the process of embedding the encoded message into the high and middle frequency wavelet coefficients of all facial regions is performed. Forth, the process of extracting the secret message from the high and middle frequency wavelet coefficients for each RGB components of all facial regions is accomplished. Experimental results of the proposed video steganography algorithm have demonstrated a high embedding efficiency and a high embedding payload.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128546392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160213
Andre Santos, Edson Pinheiro, R. Mateus, A. Odeh, Eman Abdel Fattah
Long-Term Evolution (LTE) is a radio access technology. It is a standard cellular network that enables mobile transmission of streaming high definition video in real time. This paper analyzes the development and LTE performance in streaming multimedia through an analysis of the video transmission package performance. Furthermore, we examined the influence of LTE in streaming multimedia through the adoption of a simulator.
{"title":"Analysis of video streaming using LTE technology","authors":"Andre Santos, Edson Pinheiro, R. Mateus, A. Odeh, Eman Abdel Fattah","doi":"10.1109/LISAT.2015.7160213","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160213","url":null,"abstract":"Long-Term Evolution (LTE) is a radio access technology. It is a standard cellular network that enables mobile transmission of streaming high definition video in real time. This paper analyzes the development and LTE performance in streaming multimedia through an analysis of the video transmission package performance. Furthermore, we examined the influence of LTE in streaming multimedia through the adoption of a simulator.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114918353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160220
Remah Alshinina, K. Elleithy
Wireless Sensor Networks have been widely used by researchers in different personal and organizational applications. Recently, WSN has become the major focus of researchers to establish a secure network against malicious node. The security of WSN can be subjected to threats by attackers. In order to limit these threats on WSNs, Elliptic Curve Cryptography (ECC) introduces great features such as smaller key size, less parameters, and higher intensity compared with RSA and public key algorithms. In this paper, we proposed an ECC based approach using a unique authentication message and source privacy through a hidden generator point. This scheme contains the initialization phase, registration phase, and authentication phase. These phases were introduced to develop an efficient algorithm, decrease the overhead, and increase the authentication between nodes. The scheme allows many nodes to transfer unlimited messages without any imposed threshold and guarantee the message source privacy.
{"title":"An efficient message authentication and source privacy with a hidden generator point based on ECC","authors":"Remah Alshinina, K. Elleithy","doi":"10.1109/LISAT.2015.7160220","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160220","url":null,"abstract":"Wireless Sensor Networks have been widely used by researchers in different personal and organizational applications. Recently, WSN has become the major focus of researchers to establish a secure network against malicious node. The security of WSN can be subjected to threats by attackers. In order to limit these threats on WSNs, Elliptic Curve Cryptography (ECC) introduces great features such as smaller key size, less parameters, and higher intensity compared with RSA and public key algorithms. In this paper, we proposed an ECC based approach using a unique authentication message and source privacy through a hidden generator point. This scheme contains the initialization phase, registration phase, and authentication phase. These phases were introduced to develop an efficient algorithm, decrease the overhead, and increase the authentication between nodes. The scheme allows many nodes to transfer unlimited messages without any imposed threshold and guarantee the message source privacy.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125398311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160175
B. Beheshti
Date collection in wireless networks is performed by sampling the phenomenon to be measured at recurring intervals in time. In situations where the sensors must operate over a very long time without the possibility of battery replacement, the sleep cycle for these sensors must be as long as possible (and the longest the design allows). Longer sleep cycles, while extending battery life may be too long for the sampling rate required to collect data - i.e. more frequent wake ups would be needed from the sensor. On the other hand, the sensors can collect samples at a lower than required rate, but interpolate data-points in between the actual measured sampled data. Interpolation implemented in floating point can be demanding in terms of energy cost to the sensors. Therefore as it is generally the case, fixed point implementations have to be introduced to reduce the energy demands due to excessive computations/instruction count due to floating point arithmetic. In this paper we present a fixed point implementation of the Neville's interpolation scheme, and present performance results as compared to the floating point (ideal) results.
{"title":"Fixed point performance of interpolation/extrapolation algorithms for resource constrained wireless sensors","authors":"B. Beheshti","doi":"10.1109/LISAT.2015.7160175","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160175","url":null,"abstract":"Date collection in wireless networks is performed by sampling the phenomenon to be measured at recurring intervals in time. In situations where the sensors must operate over a very long time without the possibility of battery replacement, the sleep cycle for these sensors must be as long as possible (and the longest the design allows). Longer sleep cycles, while extending battery life may be too long for the sampling rate required to collect data - i.e. more frequent wake ups would be needed from the sensor. On the other hand, the sensors can collect samples at a lower than required rate, but interpolate data-points in between the actual measured sampled data. Interpolation implemented in floating point can be demanding in terms of energy cost to the sensors. Therefore as it is generally the case, fixed point implementations have to be introduced to reduce the energy demands due to excessive computations/instruction count due to floating point arithmetic. In this paper we present a fixed point implementation of the Neville's interpolation scheme, and present performance results as compared to the floating point (ideal) results.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126776957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160209
A. Odeh, K. Elleithy, M. Faezipour, Eman Abdelfattah
This paper investigates eight novel Steganography algorithms employing text file as a carrier file. The proposed model hides secret data in the text file by manipulating the font format or inserting special symbols in the text file. Furthermore, the suggested algorithms can be applied to both Unicode and ASCII code languages, regardless of the text file format. In addition, a merging capability among the techniques is introduced, which allows alternatives for users based on the system requirements. The proposed algorithms achieve a high degree of optimized Steganography attributes such as hidden ratio, robustness, and transparency.
{"title":"Highly efficient novel text steganography algorithms","authors":"A. Odeh, K. Elleithy, M. Faezipour, Eman Abdelfattah","doi":"10.1109/LISAT.2015.7160209","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160209","url":null,"abstract":"This paper investigates eight novel Steganography algorithms employing text file as a carrier file. The proposed model hides secret data in the text file by manipulating the font format or inserting special symbols in the text file. Furthermore, the suggested algorithms can be applied to both Unicode and ASCII code languages, regardless of the text file format. In addition, a merging capability among the techniques is introduced, which allows alternatives for users based on the system requirements. The proposed algorithms achieve a high degree of optimized Steganography attributes such as hidden ratio, robustness, and transparency.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134392130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-01DOI: 10.1109/LISAT.2015.7160185
K. Aboalayon, Wafaa S. Almuhammadi, M. Faezipour
In recent years, the estimation of human sleep disorders from Electroencephalogram (EEG) signals have played an important role in developing automatic detection of sleep stages. A few methods exist in the market presently towards this aim. However, sleep physicians may not have full assurance and consideration in such methods due to concerns associated with systems accuracy, sensitivity and specificity. This paper presents a novel and efficient technique that can be implemented in a microcontroller device to identify sleep stages in an effort to assist physicians in the diagnosis and treatment of related sleep disorders by enhancing the accuracy of the developed algorithm using a single channel of EEG signals. First, the dataset of EEG signal is filtered and decomposed into delta, theta, alpha, beta and gamma subbands using Butterworth band-pass filters. Second, a set of sample statistical discriminating features are derived from each frequency band. Finally, sleep stages consisting of Wakefulness, Rapid Eye Movement (REM) and Non-Rapid Eye Movement (NREM) are classified using several supervised machine learning classifiers including multi-class Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), K-Nearest Neighbors (KNN) and Naive Bayes (NB). This paper combines REM with Stage 1 NREM due to data similarities. Performance is then compared based on single channel EEG signals that were obtained from 20 healthy subjects. The results show that the proposed technique using DT classifier efficiently achieves high accuracy of 97.30% in differentiating sleeps stages. Also, a comparison of our method with some recent available works in the literature reiterates the high classification accuracy performance.
{"title":"A comparison of different machine learning algorithms using single channel EEG signal for classifying human sleep stages","authors":"K. Aboalayon, Wafaa S. Almuhammadi, M. Faezipour","doi":"10.1109/LISAT.2015.7160185","DOIUrl":"https://doi.org/10.1109/LISAT.2015.7160185","url":null,"abstract":"In recent years, the estimation of human sleep disorders from Electroencephalogram (EEG) signals have played an important role in developing automatic detection of sleep stages. A few methods exist in the market presently towards this aim. However, sleep physicians may not have full assurance and consideration in such methods due to concerns associated with systems accuracy, sensitivity and specificity. This paper presents a novel and efficient technique that can be implemented in a microcontroller device to identify sleep stages in an effort to assist physicians in the diagnosis and treatment of related sleep disorders by enhancing the accuracy of the developed algorithm using a single channel of EEG signals. First, the dataset of EEG signal is filtered and decomposed into delta, theta, alpha, beta and gamma subbands using Butterworth band-pass filters. Second, a set of sample statistical discriminating features are derived from each frequency band. Finally, sleep stages consisting of Wakefulness, Rapid Eye Movement (REM) and Non-Rapid Eye Movement (NREM) are classified using several supervised machine learning classifiers including multi-class Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), K-Nearest Neighbors (KNN) and Naive Bayes (NB). This paper combines REM with Stage 1 NREM due to data similarities. Performance is then compared based on single channel EEG signals that were obtained from 20 healthy subjects. The results show that the proposed technique using DT classifier efficiently achieves high accuracy of 97.30% in differentiating sleeps stages. Also, a comparison of our method with some recent available works in the literature reiterates the high classification accuracy performance.","PeriodicalId":235333,"journal":{"name":"2015 Long Island Systems, Applications and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134641059","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：