Pub Date : 1900-01-01DOI: 10.1109/ICSYSE.1991.161118
P. A. Ramamoorthy, S. Huang
It is pointed out that by merging the advantages of fuzzy expert systems and neural networks one can arrive at a more powerful yet more flexible system for inferencing and learning. The advantages of fuzzy expert systems are their ability to provide nonlinear mapping through the membership functions and fuzzy rules, and the ability to deal with fuzzy information and incomplete and/or imprecise data. The merger of these two concepts is explained using the truck backer-upper control problem. Novel network architectures obtained by merging these two concepts and simulation results for the truck backer-upper problem using the architecture are shown.<>
{"title":"Fuzzy expert systems vs. neural networks-truck backer-upper control revisited","authors":"P. A. Ramamoorthy, S. Huang","doi":"10.1109/ICSYSE.1991.161118","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161118","url":null,"abstract":"It is pointed out that by merging the advantages of fuzzy expert systems and neural networks one can arrive at a more powerful yet more flexible system for inferencing and learning. The advantages of fuzzy expert systems are their ability to provide nonlinear mapping through the membership functions and fuzzy rules, and the ability to deal with fuzzy information and incomplete and/or imprecise data. The merger of these two concepts is explained using the truck backer-upper control problem. Novel network architectures obtained by merging these two concepts and simulation results for the truck backer-upper problem using the architecture are shown.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127555850","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161133
E. Kolesar, R. Reston, D. G. Ford, R. Fitch
A two-dimensional, electrically multiplexed robotic tactile sensor fabricated by coupling a piezoelectric polyvinylidene fluoride (PVDF) polymeric film to a monolithic silicon integrated circuit (IC) is discussed. The integrated circuit incorporates 25 sensor electrodes arranged in a symmetrical 5*5 matrix. Each electrode occupies a 600- mu m by 600- mu m square area. A 25- mu m-thick PVDF film was attached to the electrode array with a nonconductive adhesive. The response of the tactile sensor is essentially linear for loads spanning 0.8 to 60 grams of force (GMF). The response bandwidth is 33 Hz, the hysteresis level is very small, and taxel crosstalk is not a significant problem. A precharge bias scheme has been implemented to stabilize the pre- and post-load sensor response. A simple tactile object image measurement process was evaluated to recognize the shapes of circular, rectangular, toroidal, and hexagonal loads.<>
{"title":"Object imaging with a multiplexed piezoelectric polymer tactile sensor","authors":"E. Kolesar, R. Reston, D. G. Ford, R. Fitch","doi":"10.1109/ICSYSE.1991.161133","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161133","url":null,"abstract":"A two-dimensional, electrically multiplexed robotic tactile sensor fabricated by coupling a piezoelectric polyvinylidene fluoride (PVDF) polymeric film to a monolithic silicon integrated circuit (IC) is discussed. The integrated circuit incorporates 25 sensor electrodes arranged in a symmetrical 5*5 matrix. Each electrode occupies a 600- mu m by 600- mu m square area. A 25- mu m-thick PVDF film was attached to the electrode array with a nonconductive adhesive. The response of the tactile sensor is essentially linear for loads spanning 0.8 to 60 grams of force (GMF). The response bandwidth is 33 Hz, the hysteresis level is very small, and taxel crosstalk is not a significant problem. A precharge bias scheme has been implemented to stabilize the pre- and post-load sensor response. A simple tactile object image measurement process was evaluated to recognize the shapes of circular, rectangular, toroidal, and hexagonal loads.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128259633","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161089
M. A. Unseren
The dynamic coupling effects in the modeling and control of a multiple-joint serial-link manipulator turning a crank mechanism are considered. By dynamically distributing the load, i.e., the crank, the generalized contact forces are decomposed into internal stress and motion components. A rigid body model for the entire closed-chain system is developed. It is shown that a subset of the internal stress contact forces may be explicitly controlled while simultaneously and independently controlling the position of the system.<>
{"title":"Dynamic coupling effects in modeling and control of hard contact motion of a manipulator","authors":"M. A. Unseren","doi":"10.1109/ICSYSE.1991.161089","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161089","url":null,"abstract":"The dynamic coupling effects in the modeling and control of a multiple-joint serial-link manipulator turning a crank mechanism are considered. By dynamically distributing the load, i.e., the crank, the generalized contact forces are decomposed into internal stress and motion components. A rigid body model for the entire closed-chain system is developed. It is shown that a subset of the internal stress contact forces may be explicitly controlled while simultaneously and independently controlling the position of the system.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124962010","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161102
E. Mahmoud, Y. Elcherif, S. Mashali, E. Talkhan
A distributed arithmetic implementation for two-dimensional FIR digital filters for real-time image processing is presented. Parallelism and pipelining are two features of the proposed filter structure that contribute to its high-speed performance. Speed performance and hardware complexity are evaluated, and the effects of finite-precision arithmetic are considered.<>
{"title":"A new distributed arithmetic implementation of 2D digital filters","authors":"E. Mahmoud, Y. Elcherif, S. Mashali, E. Talkhan","doi":"10.1109/ICSYSE.1991.161102","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161102","url":null,"abstract":"A distributed arithmetic implementation for two-dimensional FIR digital filters for real-time image processing is presented. Parallelism and pipelining are two features of the proposed filter structure that contribute to its high-speed performance. Speed performance and hardware complexity are evaluated, and the effects of finite-precision arithmetic are considered.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128889648","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161116
R. Kaul, K. Adkins, S. Bibyk
The hardware and algorithms used to vector quantize predicted pixel intensity differences for real-time video compression are described. The hardware is designed for rapid vector quantization (VQ) performance, which entails the development of application-specific associative memory circuits. A modified DPCM algorithm is originally examined to determine how neural circuitry could enhance its operation. It was determined that quantization and encoding could be improved by consolidating these two functions into one, and by increasing the amount of information (i.e. number of pixels) quantized at a time. The result is a predictive scheme that vector quantizes differential values. Some of the disadvantages of VQ algorithms are solved using associative memories. The video compression algorithm and the associative memory design are described.<>
{"title":"An all digital implementation of a modified Hamming net for video compression with prediction and quantization circuits","authors":"R. Kaul, K. Adkins, S. Bibyk","doi":"10.1109/ICSYSE.1991.161116","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161116","url":null,"abstract":"The hardware and algorithms used to vector quantize predicted pixel intensity differences for real-time video compression are described. The hardware is designed for rapid vector quantization (VQ) performance, which entails the development of application-specific associative memory circuits. A modified DPCM algorithm is originally examined to determine how neural circuitry could enhance its operation. It was determined that quantization and encoding could be improved by consolidating these two functions into one, and by increasing the amount of information (i.e. number of pixels) quantized at a time. The result is a predictive scheme that vector quantizes differential values. Some of the disadvantages of VQ algorithms are solved using associative memories. The video compression algorithm and the associative memory design are described.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"372 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122437908","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161127
R. Acharya
A symmetrical axis transform (SAT) using geodesic morphology for 3-D object representation is proposed. The SAT has been previously defined using Euclidean morphological operations. An extension of the SAT to represent arbitrary non-Euclidean surfaces using geodesic operators is described. The concept of a surface skeleton is defined. Initial experimental results are also provided.<>
{"title":"Surface representation using geodesic morphology","authors":"R. Acharya","doi":"10.1109/ICSYSE.1991.161127","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161127","url":null,"abstract":"A symmetrical axis transform (SAT) using geodesic morphology for 3-D object representation is proposed. The SAT has been previously defined using Euclidean morphological operations. An extension of the SAT to represent arbitrary non-Euclidean surfaces using geodesic operators is described. The concept of a surface skeleton is defined. Initial experimental results are also provided.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121352304","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161121
S. Seyed
A model of fuzzy-firing neuron, called fuzzioid is proposed. It is a generalization (the fuzzification) of the binary (on or off) model of a neuron. The model is based on a concept that the firing action in a neuron is fuzzy-there is an intensity (or a degree) of firing. A fuzzy connectionist system as a network of fuzzily interconnected neurons, where each connecting link (axon/dendrite synapse) is modeled by an elastic device called a fuzzistor, is also developed. The system's knowledge of its external world is stored as fuzzistances (connection strengths) among the neurons.<>
{"title":"The brain as a fuzzy engineering problem","authors":"S. Seyed","doi":"10.1109/ICSYSE.1991.161121","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161121","url":null,"abstract":"A model of fuzzy-firing neuron, called fuzzioid is proposed. It is a generalization (the fuzzification) of the binary (on or off) model of a neuron. The model is based on a concept that the firing action in a neuron is fuzzy-there is an intensity (or a degree) of firing. A fuzzy connectionist system as a network of fuzzily interconnected neurons, where each connecting link (axon/dendrite synapse) is modeled by an elastic device called a fuzzistor, is also developed. The system's knowledge of its external world is stored as fuzzistances (connection strengths) among the neurons.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116782780","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161068
J. McCorkle
The synthetic aperture radar (SAR) focusing problem is considered, with special attention given to focusing an area in the near-field of the synthetic aperture over a decade or more of bandwidth in a manner that preserves target resonance characteristics. An approximation that reduces the computational load is shown. An error analysis of the approximation shows quantitatively what conditions are required to guarantee that the depth of focus is adequate to preserve long-duration target resonance effects.<>
{"title":"Focusing of synthetic aperture ultra wideband data","authors":"J. McCorkle","doi":"10.1109/ICSYSE.1991.161068","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161068","url":null,"abstract":"The synthetic aperture radar (SAR) focusing problem is considered, with special attention given to focusing an area in the near-field of the synthetic aperture over a decade or more of bandwidth in a manner that preserves target resonance characteristics. An approximation that reduces the computational load is shown. An error analysis of the approximation shows quantitatively what conditions are required to guarantee that the depth of focus is adequate to preserve long-duration target resonance effects.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117085295","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161113
R. Nordgren, P. Meckl
A two-mode coupled compound pendulum is used to compare a computed-torque-type model reference adaptive controller and a feedforward neural network controller. A derived globally asymptotically stable adaptation law for the neural net controller shows that the back error propagation scheme used is, in some cases, also asymptotically stable. Computer simulations of the two controllers demonstrate their relative performance. This comparison shows that the derived adaptation law compares favorably with the performance of the model reference adaptive controller. It also lends insight into the required input signal frequency content in order to guarantee proper convergence of the neural network. The convergence and stability properties of the neural network when it is used as a feedforward computed-torque controller are analyzed.<>
{"title":"A comparison of a neural network and a model reference adaptive controller","authors":"R. Nordgren, P. Meckl","doi":"10.1109/ICSYSE.1991.161113","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161113","url":null,"abstract":"A two-mode coupled compound pendulum is used to compare a computed-torque-type model reference adaptive controller and a feedforward neural network controller. A derived globally asymptotically stable adaptation law for the neural net controller shows that the back error propagation scheme used is, in some cases, also asymptotically stable. Computer simulations of the two controllers demonstrate their relative performance. This comparison shows that the derived adaptation law compares favorably with the performance of the model reference adaptive controller. It also lends insight into the required input signal frequency content in order to guarantee proper convergence of the neural network. The convergence and stability properties of the neural network when it is used as a feedforward computed-torque controller are analyzed.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121815895","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 : 1900-01-01DOI: 10.1109/ICSYSE.1991.161175
D. Zhu, R. Conners, P. Araman
The problem of three-dimensional image filtering in a computer vision system that would locate and identify internal structural failure is discussed. In particular, a two-dimensional adaptive filter has been extended to three-dimensions. In conjunction with segmentation and labeling, the filter has been used in the computer vision system to successfully detect potential internal defects in hardwood logs. The issue of efficient computerized tomography (CT) image filtering for suppressing unwanted detail, such as the annual rings, in the CT images of hardwood logs is addressed. By incorporating the three-dimensional correlation information among image pixels, an improved three-dimensional adaptive algorithm for image filtering is presented. Analysis and experiments demonstrate its filtering performance.<>
{"title":"3-D signal processing in a computer vision system (hardwood logs inspection)","authors":"D. Zhu, R. Conners, P. Araman","doi":"10.1109/ICSYSE.1991.161175","DOIUrl":"https://doi.org/10.1109/ICSYSE.1991.161175","url":null,"abstract":"The problem of three-dimensional image filtering in a computer vision system that would locate and identify internal structural failure is discussed. In particular, a two-dimensional adaptive filter has been extended to three-dimensions. In conjunction with segmentation and labeling, the filter has been used in the computer vision system to successfully detect potential internal defects in hardwood logs. The issue of efficient computerized tomography (CT) image filtering for suppressing unwanted detail, such as the annual rings, in the CT images of hardwood logs is addressed. By incorporating the three-dimensional correlation information among image pixels, an improved three-dimensional adaptive algorithm for image filtering is presented. Analysis and experiments demonstrate its filtering performance.<<ETX>>","PeriodicalId":250037,"journal":{"name":"IEEE 1991 International Conference on Systems Engineering","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116207850","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：