The performance of sparsely-connected associative memories built from sets of perceptrons configured in a ring structure is investigated using different patterns of connectivity. Architectures based on uniform and linear distributions of restricted maximum connection length are compared to those based on Gaussian distributions and to networks created by progressively rewiring a locally-connected network. It is found that while all four architectures are capable of good pattern-completion performance in sparse networks, the Gaussian, restricted-linear and restricted-uniform architectures require lower mean wiring lengths to achieve the same results. It is shown that in order to achieve good pattern-completion at low wiring costs, connectivity should be localized, though not completely local, and that distal connections are not necessary
{"title":"High Performance Associative Memory Models with Low Wiring Costs","authors":"L. Calcraft, R. Adams, N. Davey","doi":"10.1109/IS.2006.348489","DOIUrl":"https://doi.org/10.1109/IS.2006.348489","url":null,"abstract":"The performance of sparsely-connected associative memories built from sets of perceptrons configured in a ring structure is investigated using different patterns of connectivity. Architectures based on uniform and linear distributions of restricted maximum connection length are compared to those based on Gaussian distributions and to networks created by progressively rewiring a locally-connected network. It is found that while all four architectures are capable of good pattern-completion performance in sparse networks, the Gaussian, restricted-linear and restricted-uniform architectures require lower mean wiring lengths to achieve the same results. It is shown that in order to achieve good pattern-completion at low wiring costs, connectivity should be localized, though not completely local, and that distal connections are not necessary","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121749123","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}
We have previously used Markov models to describe movements of patients between hospital states; these may be actual or virtual and described by a phase-type distribution. Here we extend this approach to a Markov reward model for a healthcare system with constant size. This corresponds to a situation where there is a waiting list of patients so that the total number of in-patients remains at a constant level and all admissions are from the waiting list. The distribution of costs is evaluated for any time and expressions derived for the mean cost The approach is then illustrated by determining average cost at any time for a hospital system with two states: acute/rehabilitative and long-stay. In addition, we develop a Markov model to determine patient numbers and costs at any time where, again, there is a waiting list, so admissions are taken from this list, but we now allow a fixed growth which declines to zero as time tends to infinity. As before, the length of stay is described by a phase-type distribution, thus enabling the representation of durations and costs in each phase within a Markov framework. As an illustration, the model is used to determine costs over time for a four phase model, previously fitted to data for geriatric patients. Such an approach can be used to determine the number of patients and costs in each phase of hospital care thus facilitating an intelligent and systematic approach to the planning of healthcare and optimal use of scarce resources
{"title":"Using Markov Models to Manage High Occupancy Hospital Care","authors":"S. McClean, P. Millard","doi":"10.1109/IS.2006.348427","DOIUrl":"https://doi.org/10.1109/IS.2006.348427","url":null,"abstract":"We have previously used Markov models to describe movements of patients between hospital states; these may be actual or virtual and described by a phase-type distribution. Here we extend this approach to a Markov reward model for a healthcare system with constant size. This corresponds to a situation where there is a waiting list of patients so that the total number of in-patients remains at a constant level and all admissions are from the waiting list. The distribution of costs is evaluated for any time and expressions derived for the mean cost The approach is then illustrated by determining average cost at any time for a hospital system with two states: acute/rehabilitative and long-stay. In addition, we develop a Markov model to determine patient numbers and costs at any time where, again, there is a waiting list, so admissions are taken from this list, but we now allow a fixed growth which declines to zero as time tends to infinity. As before, the length of stay is described by a phase-type distribution, thus enabling the representation of durations and costs in each phase within a Markov framework. As an illustration, the model is used to determine costs over time for a four phase model, previously fitted to data for geriatric patients. Such an approach can be used to determine the number of patients and costs in each phase of hospital care thus facilitating an intelligent and systematic approach to the planning of healthcare and optimal use of scarce resources","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126473575","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}
Random keys are a common approach to the representation of permutations in evolutionary algorithms. This paper makes use of forma analysis, a powerful tool for the study of representations and operators used in evolutionary algorithms. Using forma analysis, it shall be argued that this approach, by abstracting away problem structure, can be improved by approaches where the structures they manipulate map more directly onto the problem domain. The arguments presented here are supported by an empirical study of the flowshop sequencing problem
{"title":"Forma Analysis of Permutation Random Keys","authors":"A. Tuson","doi":"10.1109/IS.2006.348412","DOIUrl":"https://doi.org/10.1109/IS.2006.348412","url":null,"abstract":"Random keys are a common approach to the representation of permutations in evolutionary algorithms. This paper makes use of forma analysis, a powerful tool for the study of representations and operators used in evolutionary algorithms. Using forma analysis, it shall be argued that this approach, by abstracting away problem structure, can be improved by approaches where the structures they manipulate map more directly onto the problem domain. The arguments presented here are supported by an empirical study of the flowshop sequencing problem","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"68 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123117183","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}
Radio frequency identification (RFID) sensor networks are increasingly being applied to the hospital environment. Capture of fine grained operational data in this environment can promote meaningful process reengineering with the objective of improving efficiencies in operational aspects. The RFID sensor nodes generate large amounts of fine grained real time data, related to resources and processes within the hospital environment. Understanding and managing these data in the context of the enterprise applications pose challenges for the middleware which has to connect sensor networks with enterprise applications. In this paper, we propose an architectural solution based on the notion of an event. The primary characteristics of an event are discussed and a three layered event representation model is developed to map raw sensory information to semantic events. A generalized event ontology language is proposed
{"title":"Architecting an Event-based Pervasive Sensing Environment in the Hospital","authors":"Bin Wu, R. George, K. Shujaee","doi":"10.1109/IS.2006.348430","DOIUrl":"https://doi.org/10.1109/IS.2006.348430","url":null,"abstract":"Radio frequency identification (RFID) sensor networks are increasingly being applied to the hospital environment. Capture of fine grained operational data in this environment can promote meaningful process reengineering with the objective of improving efficiencies in operational aspects. The RFID sensor nodes generate large amounts of fine grained real time data, related to resources and processes within the hospital environment. Understanding and managing these data in the context of the enterprise applications pose challenges for the middleware which has to connect sensor networks with enterprise applications. In this paper, we propose an architectural solution based on the notion of an event. The primary characteristics of an event are discussed and a three layered event representation model is developed to map raw sensory information to semantic events. A generalized event ontology language is proposed","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129917931","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}
This paper describes a framework for mobile robot path planning in dynamic environments where the environments are represented by grid maps. The planning heuristics considered in the paper is to generate the minimal set of paths so that all the possible path fragments of two edges are covered. We show that the number of required paths is linear in the dimensions of the grid (thus making application of the approach realistic and scalable). The main contribution of the paper is the description of all the minimal covers by means of an efficient algorithm. We prove its correctness and conclude that there are 2(m-1)(n-2)+(m-2)(n-1) minimal path fragment covers in an mtimesn grid
{"title":"Algorithrnic Generation of Path Fragrnent Covers for Mobile Robot Path Planning","authors":"J. Willemson, M. Kruusmaa","doi":"10.1109/IS.2006.348500","DOIUrl":"https://doi.org/10.1109/IS.2006.348500","url":null,"abstract":"This paper describes a framework for mobile robot path planning in dynamic environments where the environments are represented by grid maps. The planning heuristics considered in the paper is to generate the minimal set of paths so that all the possible path fragments of two edges are covered. We show that the number of required paths is linear in the dimensions of the grid (thus making application of the approach realistic and scalable). The main contribution of the paper is the description of all the minimal covers by means of an efficient algorithm. We prove its correctness and conclude that there are 2(m-1)(n-2)+(m-2)(n-1) minimal path fragment covers in an mtimesn grid","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130011263","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}
The approximation of general continuous functions by nonlinear network is very useful for system modeling and identification. Therefore, different type of networks and their combinations have developed. In present paper a wavelet neural network is used and a linear regression of inputs is used as a wavelet weight, also this model is applied in wavelet neuro-fuzzy model
{"title":"A New Artificial Neural Network and its Application in Wavelet Neural Network and Wavelet Neuro-Fuzzy Case study: Time Series Prediction","authors":"A. Banakar, M. Azeem","doi":"10.1109/IS.2006.348491","DOIUrl":"https://doi.org/10.1109/IS.2006.348491","url":null,"abstract":"The approximation of general continuous functions by nonlinear network is very useful for system modeling and identification. Therefore, different type of networks and their combinations have developed. In present paper a wavelet neural network is used and a linear regression of inputs is used as a wavelet weight, also this model is applied in wavelet neuro-fuzzy model","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"59 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127608471","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}
We show and justify how to calculate distances for intuitionistic fuzzy sets. We show a proper way of calculations not only from a mathematical point of view but also of an intuitive appeal making use of all the relevant information
{"title":"Distances Between Intuitionistic Fuzzy Sets: Straightforward Approaches may not work","authors":"E. Szmidt, J. Kacprzyk","doi":"10.1109/IS.2006.348507","DOIUrl":"https://doi.org/10.1109/IS.2006.348507","url":null,"abstract":"We show and justify how to calculate distances for intuitionistic fuzzy sets. We show a proper way of calculations not only from a mathematical point of view but also of an intuitive appeal making use of all the relevant information","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132751384","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}
A new algorithm for Arabic Soundex Function is proposed. The proposed algorithm is an improvement of the corresponding to the English Soundex Function which was developed in 1918. The algorithm can be used in searching and retrieving names written in Arabic language, which can be stored in a database of digital library. The algorithm is designed using intuitionistic fuzzy logic (fuzzy logic as a special case) to determine the 'degree of closeness' between the compared Arabic names
{"title":"An Intelligent Algorithm For Arabic Soundex Function Using Intuitionistic Fuzzy Logic","authors":"M. Yahia, Mohamad E. Saeed, Ashwag M. Salih","doi":"10.1109/IS.2006.348506","DOIUrl":"https://doi.org/10.1109/IS.2006.348506","url":null,"abstract":"A new algorithm for Arabic Soundex Function is proposed. The proposed algorithm is an improvement of the corresponding to the English Soundex Function which was developed in 1918. The algorithm can be used in searching and retrieving names written in Arabic language, which can be stored in a database of digital library. The algorithm is designed using intuitionistic fuzzy logic (fuzzy logic as a special case) to determine the 'degree of closeness' between the compared Arabic names","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134332977","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}
J. Kuppannan, P. Rangasamy, D. Thirupathi, N. Palaniappan
This paper proposes an algorithm to enhance text documents using intuitionistic fuzzy approach. The text document to be enhanced is obtained through scanner. In real life situations, this type of document occurs as handwritten/printed text and historical documents. Contrast intensification (CI) operator on intuitionistic fuzzy sets (IFSs) can be used to improve the quality of such degraded images. This enhancement supports the human perception in image processing applications. The aim of contrast enhancement is to process a given image so that the result is more suitable than the original for pattern recognition
{"title":"Intuitionistic Fuzzy Approach to Enhance Text Documents","authors":"J. Kuppannan, P. Rangasamy, D. Thirupathi, N. Palaniappan","doi":"10.1109/IS.2006.348511","DOIUrl":"https://doi.org/10.1109/IS.2006.348511","url":null,"abstract":"This paper proposes an algorithm to enhance text documents using intuitionistic fuzzy approach. The text document to be enhanced is obtained through scanner. In real life situations, this type of document occurs as handwritten/printed text and historical documents. Contrast intensification (CI) operator on intuitionistic fuzzy sets (IFSs) can be used to improve the quality of such degraded images. This enhancement supports the human perception in image processing applications. The aim of contrast enhancement is to process a given image so that the result is more suitable than the original for pattern recognition","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"10 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133293450","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}
This paper presents a hybrid learning algorithm for spiking neural networks (SNNs), referred to as an evolvable spiking neural network (ESNN) paradigm. The algorithm integrates a supervised and unsupervised learning approach. The unsupervised approach exploits a spike timing dependent plasticity (STDP) mechanism with explicit delay learning for multiple connections between neurons. Supervision of the synaptic delays and the excitatory/inhibitory connections is governed by a genetic algorithm (GA), while the STDP rule is free to operate in its normal unsupervised manner. A spike train encoding/decoding scheme is developed for the algorithm. The approach is validated by application to the Iris classification problem
{"title":"A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons","authors":"S. Johnston, G. Prasad, L. Maguire, T. McGinnity","doi":"10.1109/IS.2006.348493","DOIUrl":"https://doi.org/10.1109/IS.2006.348493","url":null,"abstract":"This paper presents a hybrid learning algorithm for spiking neural networks (SNNs), referred to as an evolvable spiking neural network (ESNN) paradigm. The algorithm integrates a supervised and unsupervised learning approach. The unsupervised approach exploits a spike timing dependent plasticity (STDP) mechanism with explicit delay learning for multiple connections between neurons. Supervision of the synaptic delays and the excitatory/inhibitory connections is governed by a genetic algorithm (GA), while the STDP rule is free to operate in its normal unsupervised manner. A spike train encoding/decoding scheme is developed for the algorithm. The approach is validated by application to the Iris classification problem","PeriodicalId":116809,"journal":{"name":"2006 3rd International IEEE Conference Intelligent Systems","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129419015","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：