Internet time-delay prediction plays a key role in improving dynamic performance for many applications, especially for Internet-based tele-operation systems. Therefore, ideal prediction approach for Internet time-delay must be investigated emphatically. In this paper, after analayzing Internet time-delay, a new approach based on neural network is developed to predict the uncertain time-delay in the Internet. By using measured data between four Internet nodes and MATLAB environment, the feed-forward multi-layer perceptron (FMLP) neural network has been trained with single-step-ahead Prediction algorithm. Then, using validation data, the performance of the neural network was evaluated. It is shown that this neural network can predict time-delay based on their proper inputs.
{"title":"Modelling and Prediction of Internet Time-Delay by Feed-Forward Multi-layer Perceptron Neural Network","authors":"Seyed Reza Seyed Tabib, A. Jalali","doi":"10.1109/UKSIM.2008.93","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.93","url":null,"abstract":"Internet time-delay prediction plays a key role in improving dynamic performance for many applications, especially for Internet-based tele-operation systems. Therefore, ideal prediction approach for Internet time-delay must be investigated emphatically. In this paper, after analayzing Internet time-delay, a new approach based on neural network is developed to predict the uncertain time-delay in the Internet. By using measured data between four Internet nodes and MATLAB environment, the feed-forward multi-layer perceptron (FMLP) neural network has been trained with single-step-ahead Prediction algorithm. Then, using validation data, the performance of the neural network was evaluated. It is shown that this neural network can predict time-delay based on their proper inputs.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"10 1","pages":"611-616"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86857270","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 paper develops a model for the biologically inspired process of identifying faces from relative distances between blemishes using pre-stored knowledge in a database. A facial picture is loaded into the program and the operator selects facial blemishes by clicking on them and uses an extra list to select the size and color of the facial blemish. The 2-D location, size and colour are recorded to uniquely identify the individual. For scars and other facial blemishes that are not of standard size and shape, such as skin dots or freckles, the operator marks the area as other points are marked. Results show the success of the method.
{"title":"Personal Identification Using Facial Blemishes","authors":"Andreas Psyllos, D. Al-Dabass","doi":"10.1109/UKSIM.2008.137","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.137","url":null,"abstract":"The paper develops a model for the biologically inspired process of identifying faces from relative distances between blemishes using pre-stored knowledge in a database. A facial picture is loaded into the program and the operator selects facial blemishes by clicking on them and uses an extra list to select the size and color of the facial blemish. The 2-D location, size and colour are recorded to uniquely identify the individual. For scars and other facial blemishes that are not of standard size and shape, such as skin dots or freckles, the operator marks the area as other points are marked. Results show the success of the method.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"32 1","pages":"531-536"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86915289","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 is inspired from specific situations for the early phases of drugs testing. The particularity of the problem consists in the small dimension of the analyzed samples. For this reason, there is a presumption that the small dimension of samples affects the result of ANOVA statistical tests, when multiples groups have to be compared. Six dermatological treatments are tested on groups of ten patients each to test their effect on particular affections. In order to observe a difference between treatments an ANOVA technique is applied. The result suggests that no statistically significant difference can be observed between the six drugs. For objective reasons, despite the result of ANOVA, a hierarchy between drug’s variants must be established taking into account the general effect on the observed affections. The statistical inferential problem is converted into a decisional problem with weighted criteria of evaluation. The general decisional situation in which a set of alternatives are evaluated from the point of view of a set of criteria of evaluation is modeled and simulated. Then, the model is applied for the pharmaceutical problem. The robustness of the method of weighting the criteria of evaluation is studied using the empirical influence curve. Applying this method of ranking, one of the six creams is recommended as optimal with respect to all criteria of evaluation. The advantage of such an approach is that an inferential deadlock, due to the small number of data, can be surpassed. Computer implementations are made using Matlab.
{"title":"Robust Simulation for Decisional Problems Applied for Drug Testing","authors":"R. Câmpean","doi":"10.1109/UKSIM.2008.51","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.51","url":null,"abstract":"This paper is inspired from specific situations for the early phases of drugs testing. The particularity of the problem consists in the small dimension of the analyzed samples. For this reason, there is a presumption that the small dimension of samples affects the result of ANOVA statistical tests, when multiples groups have to be compared. Six dermatological treatments are tested on groups of ten patients each to test their effect on particular affections. In order to observe a difference between treatments an ANOVA technique is applied. The result suggests that no statistically significant difference can be observed between the six drugs. For objective reasons, despite the result of ANOVA, a hierarchy between drug’s variants must be established taking into account the general effect on the observed affections. The statistical inferential problem is converted into a decisional problem with weighted criteria of evaluation. The general decisional situation in which a set of alternatives are evaluated from the point of view of a set of criteria of evaluation is modeled and simulated. Then, the model is applied for the pharmaceutical problem. The robustness of the method of weighting the criteria of evaluation is studied using the empirical influence curve. Applying this method of ranking, one of the six creams is recommended as optimal with respect to all criteria of evaluation. The advantage of such an approach is that an inferential deadlock, due to the small number of data, can be surpassed. Computer implementations are made using Matlab.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"2016 1","pages":"117-121"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86453355","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 contribution includes characterizations of basic properties of two physically realized devices – simulators. It is the simulator of random kinematics excitation (the RKE Simulator) and the simulator of direction channel (the DCh Simulator). These simulators serve to probe for properties of the operator as an element of special man-machine system, which is the subsystem of the sensory system on the base of a passive optoelectronic rangefinder.
{"title":"Simulators of the Direction Channel of the Passive Optoelectronic Rangefinder","authors":"V. Čech, J. Jevicky","doi":"10.1109/UKSIM.2008.99","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.99","url":null,"abstract":"The contribution includes characterizations of basic properties of two physically realized devices – simulators. It is the simulator of random kinematics excitation (the RKE Simulator) and the simulator of direction channel (the DCh Simulator). These simulators serve to probe for properties of the operator as an element of special man-machine system, which is the subsystem of the sensory system on the base of a passive optoelectronic rangefinder.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"16 1","pages":"132-137"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90162643","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 amount of data produced by medicine diagnosis and other means constantly increases -- in both number of measurements and in number of dimensions. For many modeling or data mining methods this increase causes problems. First main problem is well known curse of dimensionality. The second is the amount of training data items which lengthens the training process. Both these problems reduces usability of modeling methods.The aim of this article is to study several data reduction techniques and test their influence on one particular inductive modeling method -- GAME -- developed in our department. Application of each method affecting the performance (accuracy) and learning time of the GAME modeling method has been studied.To obtain representative results several datasets has been tested -- for example well known Iris dataset or real-world application for medical data (e.g. EEG classification).
{"title":"Basic Data Reduction Techniques and Their Influence on GAME Modeling Method","authors":"Miroslav Cepek, M. Snorek","doi":"10.1109/UKSIM.2008.91","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.91","url":null,"abstract":"The amount of data produced by medicine diagnosis and other means constantly increases -- in both number of measurements and in number of dimensions. For many modeling or data mining methods this increase causes problems. First main problem is well known curse of dimensionality. The second is the amount of training data items which lengthens the training process. Both these problems reduces usability of modeling methods.The aim of this article is to study several data reduction techniques and test their influence on one particular inductive modeling method -- GAME -- developed in our department. Application of each method affecting the performance (accuracy) and learning time of the GAME modeling method has been studied.To obtain representative results several datasets has been tested -- for example well known Iris dataset or real-world application for medical data (e.g. EEG classification).","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"1 1","pages":"138-143"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80566319","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}
In this paper we propose an automatic target recognitionalgorithm to recognize and distinguish of three classes oftargets: personnel, wheeled vehicles and animals, based on thedoppler signatures they produce when moving, using a low-resolutionground surveillance pulse doppler RADAR. Using signal processingtechniques such as the short-time Fourier transform (STFT)and the chirplet transform, various parameters of the targets canbe extracted from the signal. This paper proposed classification ofmoving targets with use of the chirplet transform. The algorithmwas trained and tested on real radar signatures of multiple examplesof moving targets from each class and the performance wasshown to be invariant to target speed and orientation.
{"title":"Recognition of Moving Terrestrial Targets in the Presence of Terrestrial Clutters with a Pulse Doppler RADAR","authors":"M. Alaee, H. Amindavar, A. Reza","doi":"10.1109/UKSIM.2008.118","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.118","url":null,"abstract":"In this paper we propose an automatic target recognitionalgorithm to recognize and distinguish of three classes oftargets: personnel, wheeled vehicles and animals, based on thedoppler signatures they produce when moving, using a low-resolutionground surveillance pulse doppler RADAR. Using signal processingtechniques such as the short-time Fourier transform (STFT)and the chirplet transform, various parameters of the targets canbe extracted from the signal. This paper proposed classification ofmoving targets with use of the chirplet transform. The algorithmwas trained and tested on real radar signatures of multiple examplesof moving targets from each class and the performance wasshown to be invariant to target speed and orientation.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"69 1","pages":"23-27"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81202258","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}
Aminu Mohammed, M. Ould-Khaoua, L. Mackenzie, J. Abdulai
Broadcasting is a fundamental and frequently usedoperation in mobile ad hoc networks (MANETs) wherea source node diffuses a message to all other nodes inthe networks. Flooding, the process in which eachnode retransmits every uniquely received packetexactly once is the simplest and most commonly usedmechanism for broadcasting in MANETs. Despite itssimplicity, it can result in high redundantretransmission, contention and collision, aphenomenon collectively referred to as the broadcaststorm problem, which can greatly increase thenetwork communication overhead. This paperproposes an adjusted counter-based scheme whichcombines the advantages of probability and counterbasedapproaches to mitigate this inherent problem.The scheme is simple, efficient and uses tworebroadcast probabilities to differentiate betweenmobile nodes in sparse and dense area as againstdropping the rebroadcast packet when a node is indense area. We evaluate the performance of ourscheme by comparing it against flooding, fixedprobability and counter-based schemes. Simulationresults reveal that our scheme achieves betterperformance in terms of saved rebroadcast, end-toenddelay and without sacrificing reachability.
{"title":"An Adjusted Counter-Based Broadcast Scheme for Mobile Ad Hoc Networks","authors":"Aminu Mohammed, M. Ould-Khaoua, L. Mackenzie, J. Abdulai","doi":"10.1109/UKSIM.2008.16","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.16","url":null,"abstract":"Broadcasting is a fundamental and frequently usedoperation in mobile ad hoc networks (MANETs) wherea source node diffuses a message to all other nodes inthe networks. Flooding, the process in which eachnode retransmits every uniquely received packetexactly once is the simplest and most commonly usedmechanism for broadcasting in MANETs. Despite itssimplicity, it can result in high redundantretransmission, contention and collision, aphenomenon collectively referred to as the broadcaststorm problem, which can greatly increase thenetwork communication overhead. This paperproposes an adjusted counter-based scheme whichcombines the advantages of probability and counterbasedapproaches to mitigate this inherent problem.The scheme is simple, efficient and uses tworebroadcast probabilities to differentiate betweenmobile nodes in sparse and dense area as againstdropping the rebroadcast packet when a node is indense area. We evaluate the performance of ourscheme by comparing it against flooding, fixedprobability and counter-based schemes. Simulationresults reveal that our scheme achieves betterperformance in terms of saved rebroadcast, end-toenddelay and without sacrificing reachability.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"54 1","pages":"441-446"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84755777","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}
For the evaluation of wireless network protocols, simulation has established itself as a good compromise between cost and complexity, on the one hand, and accuracy of results, on the other hand. Most established network simulators, however, were originally developed for wired networks and only later extended to the wireless domain. Some simulators like Opnet are not even restricted to communication networks at all, but can be used to simulate all kinds of networked systems. In this paper, we present ShoX, a network simulator explicitly designed for the simulation of wireless networks. Together with its strong GUI support, this allows a very efficient development and evaluation of network protocols without any considerable learning curve. All relevant concepts known from the domain of wireless networks like nodes, links, OSI layers, packets, mobility, signal propagation and traffic models are directly available. Defining new layers, packets or models is as easy as subclassing the existing abstract classes which ensures at compile time that all required methods are provided by the user. ShoX is completely based on Java and XML, thus superseding to learn unfamiliar languages like Tcl or NED. It features an integrated GUI for configuration, visualization and statistics.
{"title":"ShoX: An Easy to Use Simulation Platform for Wireless Networks","authors":"J. Lessmann, T. Heimfarth, P. Janacik","doi":"10.1109/UKSIM.2008.32","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.32","url":null,"abstract":"For the evaluation of wireless network protocols, simulation has established itself as a good compromise between cost and complexity, on the one hand, and accuracy of results, on the other hand. Most established network simulators, however, were originally developed for wired networks and only later extended to the wireless domain. Some simulators like Opnet are not even restricted to communication networks at all, but can be used to simulate all kinds of networked systems. In this paper, we present ShoX, a network simulator explicitly designed for the simulation of wireless networks. Together with its strong GUI support, this allows a very efficient development and evaluation of network protocols without any considerable learning curve. All relevant concepts known from the domain of wireless networks like nodes, links, OSI layers, packets, mobility, signal propagation and traffic models are directly available. Defining new layers, packets or models is as easy as subclassing the existing abstract classes which ensures at compile time that all required methods are provided by the user. ShoX is completely based on Java and XML, thus superseding to learn unfamiliar languages like Tcl or NED. It features an integrated GUI for configuration, visualization and statistics.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"10 1","pages":"410-415"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87236914","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}
Crucial component of the successful performance of an economic system (ECSYS) is maintenance of an optimality of functioning of all industrial and economic criteria of the given system. The purpose of the given work is stochastic modelling of the stability of ECSYS. The process of deterministic and stochastic modelling of ECSYS stability is considered in the conditions of uncertainty using benchmarking and dynamic programming method by Bellman.
{"title":"Modelling of Stability of Economic Systems Using Benchmarking and Dynamic Programming","authors":"Vitalijs Jurenoks, V. Jansons, K. Didenko","doi":"10.1109/UKSIM.2008.96","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.96","url":null,"abstract":"Crucial component of the successful performance of an economic system (ECSYS) is maintenance of an optimality of functioning of all industrial and economic criteria of the given system. The purpose of the given work is stochastic modelling of the stability of ECSYS. The process of deterministic and stochastic modelling of ECSYS stability is considered in the conditions of uncertainty using benchmarking and dynamic programming method by Bellman.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"98 1","pages":"295-300"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76074610","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}
An experiment was conducted to determine how feedback training affects distance estimation, in simulation. Eighteen subjects participated in this experiment and training was conducted using a night vision simulation of an original scene. Testing was performed on a PC desktop computer running VegaPrime to simulate light source halos in an open field. Subjects were exposed to three flash types; five flashes, single flash, and a prolonged flash. Flashes were presented to the subjects both above and below the horizon. There were significant improvements for the group that received feedback training; their accuracy in distance estimation persisted for two weeks, but with some deterioration in scores. Immediate feedback is an effective training technique, but simulation software must be realistic in reproducing the gamut of depth cues for naturalistic environments for effective training.
{"title":"Distance Estimation and Simulation Training","authors":"Garrett Morawiec, K. Niall, K. Scullion","doi":"10.1109/UKSIM.2008.66","DOIUrl":"https://doi.org/10.1109/UKSIM.2008.66","url":null,"abstract":"An experiment was conducted to determine how feedback training affects distance estimation, in simulation. Eighteen subjects participated in this experiment and training was conducted using a night vision simulation of an original scene. Testing was performed on a PC desktop computer running VegaPrime to simulate light source halos in an open field. Subjects were exposed to three flash types; five flashes, single flash, and a prolonged flash. Flashes were presented to the subjects both above and below the horizon. There were significant improvements for the group that received feedback training; their accuracy in distance estimation persisted for two weeks, but with some deterioration in scores. Immediate feedback is an effective training technique, but simulation software must be realistic in reproducing the gamut of depth cues for naturalistic environments for effective training.","PeriodicalId":22356,"journal":{"name":"Tenth International Conference on Computer Modeling and Simulation (uksim 2008)","volume":"55 1","pages":"447-448"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76279477","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：