Pub Date : 2000-02-22DOI: 10.1109/NRSC.2000.838939
Oilv Abdel Alim, Neamal Elboughdadly, Chaimaa ElMorchedi, Safwat, Gehan Abouelseoud, Nadia El badry, Nevin Mohsen
A simple straightforward strategy to build a security system using audio-visual clues is proposed. A series of face and audio-visual verification is used to construct the system. The practical considerations that lead to specific data representation methods, design procedure, decision making criteria and subjective performance evaluation criteria involved in the research is illustrated. An account of the reasons behind choosing the used features and neural network architectures is included. Preliminary results of testing some of the nodes of the system on their members as well as intruders are shown.
{"title":"Identity verification using audio-visual features","authors":"Oilv Abdel Alim, Neamal Elboughdadly, Chaimaa ElMorchedi, Safwat, Gehan Abouelseoud, Nadia El badry, Nevin Mohsen","doi":"10.1109/NRSC.2000.838939","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838939","url":null,"abstract":"A simple straightforward strategy to build a security system using audio-visual clues is proposed. A series of face and audio-visual verification is used to construct the system. The practical considerations that lead to specific data representation methods, design procedure, decision making criteria and subjective performance evaluation criteria involved in the research is illustrated. An account of the reasons behind choosing the used features and neural network architectures is included. Preliminary results of testing some of the nodes of the system on their members as well as intruders are shown.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127045246","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838958
M. Tayel, Marwah Abd Elmonem
An interpretation of the new fuzzy reasoning model (NFRM) is developed. This interpretation makes the traditional fuzzy reasoning model (FRM) a special case under certain conditions. In addition, a neural network is constructed to represent the NFRM. The proposed neuro-new fuzzy reasoning model (NNFRM) optimizes the parameters of the NFRM by using the well-known backpropagation concept. The parameters to be optimized are those of the input membership functions, output membership function and relation matrix. The proposed NNFRM is used to predict future values of a chaotic time series, which is considered a benchmark problem. It is shown that the proposed NNFRM outperforms other modeling methods in prediction of this chaotic time series. The NNFRM used here has fewer adjustable parameters, than those used in other modeling techniques.
{"title":"NNFRM: neuro-new fuzzy reasoning model interpreted as general case of fuzzy reasoning model","authors":"M. Tayel, Marwah Abd Elmonem","doi":"10.1109/NRSC.2000.838958","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838958","url":null,"abstract":"An interpretation of the new fuzzy reasoning model (NFRM) is developed. This interpretation makes the traditional fuzzy reasoning model (FRM) a special case under certain conditions. In addition, a neural network is constructed to represent the NFRM. The proposed neuro-new fuzzy reasoning model (NNFRM) optimizes the parameters of the NFRM by using the well-known backpropagation concept. The parameters to be optimized are those of the input membership functions, output membership function and relation matrix. The proposed NNFRM is used to predict future values of a chaotic time series, which is considered a benchmark problem. It is shown that the proposed NNFRM outperforms other modeling methods in prediction of this chaotic time series. The NNFRM used here has fewer adjustable parameters, than those used in other modeling techniques.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125584224","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838917
H. Elkamchouchi, G.A. Saleh
A neural network algorithm used in a non-conventional way to solve the non-uniformly spaced array problem is demonstrated. Using this algorithm, the problem of uniformly spaced and non-uniformly excited arrays was solved. Comparison between this method and the Dolph-Chebyshev method demonstrated its capability of producing lower sidelobe levels for same beamwidth and number of elements. Moreover, using this algorithm to synthesize non-uniformly spaced and non-uniformly excited arrays improved its performance remarkably and enabled it to compete with other synthesis methods such as Redlich and the iterative optimization.
{"title":"Solution of the non-uniformly spaced array problem using neural networks","authors":"H. Elkamchouchi, G.A. Saleh","doi":"10.1109/NRSC.2000.838917","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838917","url":null,"abstract":"A neural network algorithm used in a non-conventional way to solve the non-uniformly spaced array problem is demonstrated. Using this algorithm, the problem of uniformly spaced and non-uniformly excited arrays was solved. Comparison between this method and the Dolph-Chebyshev method demonstrated its capability of producing lower sidelobe levels for same beamwidth and number of elements. Moreover, using this algorithm to synthesize non-uniformly spaced and non-uniformly excited arrays improved its performance remarkably and enabled it to compete with other synthesis methods such as Redlich and the iterative optimization.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120980806","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838956
A. A. Abdelaziz
The most common and simple structure to reduce the level of the reflected power from a metallic surface is the single layer structure known as Salisbury screen which is a sheet of porous material impregnated with graphite and spaced a quarter-wavelength off a metallic backing plate. The main disadvantage of this mechanism is the narrow frequency bandwidth. Many techniques have been reported to improve the working frequency bandwidth but with some degradation in the other technical properties of the overall structure. In this paper a novel technique has been introduced based on a spatial kind of material called the circuit analog screen. Theoretical analysis shows that the bandwidth of the reflected power will be improved if the graphite sheet of the Salisbury screen has been loaded by circuit analog screen with spatial geometry with spatial parameters.
{"title":"A novel technique for improving the performance of Salisbury screen","authors":"A. A. Abdelaziz","doi":"10.1109/NRSC.2000.838956","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838956","url":null,"abstract":"The most common and simple structure to reduce the level of the reflected power from a metallic surface is the single layer structure known as Salisbury screen which is a sheet of porous material impregnated with graphite and spaced a quarter-wavelength off a metallic backing plate. The main disadvantage of this mechanism is the narrow frequency bandwidth. Many techniques have been reported to improve the working frequency bandwidth but with some degradation in the other technical properties of the overall structure. In this paper a novel technique has been introduced based on a spatial kind of material called the circuit analog screen. Theoretical analysis shows that the bandwidth of the reflected power will be improved if the graphite sheet of the Salisbury screen has been loaded by circuit analog screen with spatial geometry with spatial parameters.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121581656","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838951
H. El-Bakry, M. Abo-Elsoud, M. Kamel
A new approach to the face recognition problem is presented through combining Fourier descriptors with principal component analysis (PCA) and neural networks. Here the faces are vertically oriented frontal view with scaling, orientation, expression, and illumination changes. There are many research activities on face recognition using the face space which is described by a set of eigenfaces. Each face is efficiently represented by its projection onto the space expanded by the eigenfaces and has a new descriptor. Previous work on eigenface has shown that it performs well only with changes in expression, but results are poor in the case of rotating, or scaling the input face. In order to enhance the performance of the eigenfaces technique to accommodate other variations of the input face, the Fourier vector of each face is projected in the eigenspace. Neural networks are used to recognize the face through learning the correct classification of these new descriptors. A real-time system has been created which combines the face detection and recognition techniques. A recognition rate of 91% has been achieved over real tests. It is also shown that our proposed system behaves accurately in the case of rotated or scaled faces as well as for changes in expression.
{"title":"Integrating Fourier descriptors and PCA with neural networks for face recognition","authors":"H. El-Bakry, M. Abo-Elsoud, M. Kamel","doi":"10.1109/NRSC.2000.838951","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838951","url":null,"abstract":"A new approach to the face recognition problem is presented through combining Fourier descriptors with principal component analysis (PCA) and neural networks. Here the faces are vertically oriented frontal view with scaling, orientation, expression, and illumination changes. There are many research activities on face recognition using the face space which is described by a set of eigenfaces. Each face is efficiently represented by its projection onto the space expanded by the eigenfaces and has a new descriptor. Previous work on eigenface has shown that it performs well only with changes in expression, but results are poor in the case of rotating, or scaling the input face. In order to enhance the performance of the eigenfaces technique to accommodate other variations of the input face, the Fourier vector of each face is projected in the eigenspace. Neural networks are used to recognize the face through learning the correct classification of these new descriptors. A real-time system has been created which combines the face detection and recognition techniques. A recognition rate of 91% has been achieved over real tests. It is also shown that our proposed system behaves accurately in the case of rotated or scaled faces as well as for changes in expression.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125271604","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838934
H. T. Bahbouh, A. Salama
As we build faster digital switching circuits, the ability to accomplish global synchronization with a high-speed clock becomes a limiting factor to system throughput. Self-timed circuit design is an active research area and synthesis of self-timed control circuits using signal transition graphs is a promising approach. Our goal is to construct a FIFO circuit that does not require the distribution of a clocking signal. We use the notation of signal transition graphs to describe circuit behavior. Since circuit behavior is presented by signal transitions rather than states, signal transition graphs simplify the algorithm and graph manipulation. The synthesized logic is hazard-free and guaranteed to have the fastest operation compared with similar designs.
{"title":"Synthesis of self-timed FIFO circuit from signal transition graphs (STGs)","authors":"H. T. Bahbouh, A. Salama","doi":"10.1109/NRSC.2000.838934","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838934","url":null,"abstract":"As we build faster digital switching circuits, the ability to accomplish global synchronization with a high-speed clock becomes a limiting factor to system throughput. Self-timed circuit design is an active research area and synthesis of self-timed control circuits using signal transition graphs is a promising approach. Our goal is to construct a FIFO circuit that does not require the distribution of a clocking signal. We use the notation of signal transition graphs to describe circuit behavior. Since circuit behavior is presented by signal transitions rather than states, signal transition graphs simplify the algorithm and graph manipulation. The synthesized logic is hazard-free and guaranteed to have the fastest operation compared with similar designs.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115993352","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838981
N. Ismail
Ultrasonic phased arrays are capable of producing both single or multiple focus field patterns in the patterns in the treatment volume. A circular phased array applicator used to produce the desired power deposition and temperature distributions in a multilayered concentric cylindrical model is discussed. The driving signals of the phased array are obtained by the pseudoinverse technique. The temperature distributions obtained show that this type of phased array is capable of generating heat levels suitable for cancer therapy.
{"title":"Heat generated by a circular ultrasound phased array for deep seated tumor treatments","authors":"N. Ismail","doi":"10.1109/NRSC.2000.838981","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838981","url":null,"abstract":"Ultrasonic phased arrays are capable of producing both single or multiple focus field patterns in the patterns in the treatment volume. A circular phased array applicator used to produce the desired power deposition and temperature distributions in a multilayered concentric cylindrical model is discussed. The driving signals of the phased array are obtained by the pseudoinverse technique. The temperature distributions obtained show that this type of phased array is capable of generating heat levels suitable for cancer therapy.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128986835","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838925
H. El-Bakry, M. Abo-Elsoud, M.S. Kanel
A new concept for detection of human faces is presented. An efficient approach to reduce the computation time taken by neural networks for the searching process is introduced. We combine both Fourier and wavelet transforms with cooperative modular neural networks (MNNs) to enhance the performance of the detection process. Such an approach is applied to identify human faces automatically in cluttered scenes. Here, neural networks are used to test whether a window of 20/spl times/20 pixels contains a face or not. The major difficulty in the learning process comes from the large database required for face/nonface images. A simple design for cooperative MNNs is presented to solve this problem by dividing these data into some groups. Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. In order to have a faster detection algorithm, a combination of the FFT and the wavelet transform is made in order to reduce the elapsed time during the test phase and enhance the detection performance. Feature measurements of the input faces are made through Fourier descriptors which are insensitive to rotation, translation and scaling. Such a feature is modified to reduce the number of neurons in the hidden layer. The second stage extracts wavelet coefficients that have been shown to provide advantages in terms of better representation for a given data to be compressed. Finally, the resulting vector is fed to one of five neural networks for face detection. Compared to previous work in face detection, the use of this combination reduces the number of neurons required for neural networks. Simulation results for the proposed algorithm show good performance on detecting faces with rotation, occlusion, noise, or change in illumination.
{"title":"Modular neural networks for face detection","authors":"H. El-Bakry, M. Abo-Elsoud, M.S. Kanel","doi":"10.1109/NRSC.2000.838925","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838925","url":null,"abstract":"A new concept for detection of human faces is presented. An efficient approach to reduce the computation time taken by neural networks for the searching process is introduced. We combine both Fourier and wavelet transforms with cooperative modular neural networks (MNNs) to enhance the performance of the detection process. Such an approach is applied to identify human faces automatically in cluttered scenes. Here, neural networks are used to test whether a window of 20/spl times/20 pixels contains a face or not. The major difficulty in the learning process comes from the large database required for face/nonface images. A simple design for cooperative MNNs is presented to solve this problem by dividing these data into some groups. Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. In order to have a faster detection algorithm, a combination of the FFT and the wavelet transform is made in order to reduce the elapsed time during the test phase and enhance the detection performance. Feature measurements of the input faces are made through Fourier descriptors which are insensitive to rotation, translation and scaling. Such a feature is modified to reduce the number of neurons in the hidden layer. The second stage extracts wavelet coefficients that have been shown to provide advantages in terms of better representation for a given data to be compressed. Finally, the resulting vector is fed to one of five neural networks for face detection. Compared to previous work in face detection, the use of this combination reduces the number of neurons required for neural networks. Simulation results for the proposed algorithm show good performance on detecting faces with rotation, occlusion, noise, or change in illumination.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132881995","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 : 2000-02-22DOI: 10.1109/NRSC.2000.838915
H. El-Kamchouchi, N. El-Araby
This paper is concerned with the symmetric excitation design of linear array antennas. Exact solutions for broadside array antenna synthesis are extended to cover evaluating the system of excitation coefficients producing general predetermined radiation patterns.
{"title":"Exact generalized polynomial array synthesis","authors":"H. El-Kamchouchi, N. El-Araby","doi":"10.1109/NRSC.2000.838915","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838915","url":null,"abstract":"This paper is concerned with the symmetric excitation design of linear array antennas. Exact solutions for broadside array antenna synthesis are extended to cover evaluating the system of excitation coefficients producing general predetermined radiation patterns.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128018561","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}
Most of classical methods for shape recognition depend on classification of the object's features. This paper, gets round these classical methods, and presents a technique to determine a signature for any given closed shape to recognize it. It is simple in calculations, efficient in time and space complexity. It is based on geometrical computations to represent the shape signature. It is found that the proposed technique is proper for the description and recognition process as well is illustrated by numerical examples.
{"title":"Shape signature for recognition process","authors":"I.H. Khalifa, M.S.H. Fahmi, A.-E. Hassanien, H.A.R.M. Elsalamony","doi":"10.1109/NRSC.2000.838946","DOIUrl":"https://doi.org/10.1109/NRSC.2000.838946","url":null,"abstract":"Most of classical methods for shape recognition depend on classification of the object's features. This paper, gets round these classical methods, and presents a technique to determine a signature for any given closed shape to recognize it. It is simple in calculations, efficient in time and space complexity. It is based on geometrical computations to represent the shape signature. It is found that the proposed technique is proper for the description and recognition process as well is illustrated by numerical examples.","PeriodicalId":211510,"journal":{"name":"Proceedings of the Seventeenth National Radio Science Conference. 17th NRSC'2000 (IEEE Cat. No.00EX396)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2000-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115294875","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：