发布求助
文献互助 智能选刊 最新文献

Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems最新文献

筛选
英文 中文
Neural-network-based model predictive control: a case study 基于神经网络的模型预测控制:一个案例研究
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499507
V. Karla, H. Bakker
{"title":"Neural-network-based model predictive control: a case study","authors":"V. Karla, H. Bakker","doi":"10.1109/ANNES.1995.499507","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499507","url":null,"abstract":"This paper presents a specific example of model predictive control (MPG) of an Ultra-High Temperature (UHT) milk treatment plan using a Artificial Neural Network (ANN) as the model. Single-network and composite-network models were trained on plant data with the composite-network model performing better. Simulations of a MPC scheme using the composite network model as a prediction model show that the scheme does not perform as well as a PI controller. Some pitfalls and possible improvements are noted.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121748918","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}
引用次数: 6
Three-dimensional self-organizing maps for classification of image properties 用于图像属性分类的三维自组织映射
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499496
U. Seiffert, B. Michaelis
{"title":"Three-dimensional self-organizing maps for classification of image properties","authors":"U. Seiffert, B. Michaelis","doi":"10.1109/ANNES.1995.499496","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499496","url":null,"abstract":"The importance of analysing moving scenes within the wide area of digital image processing is increasingly high. Although a simple detection of object velocity by biological models has been considered in previously published papers (A. Tsukamoto et al., 1993; S. Wimbauer et al., 1994; J. Hogden et al., 1993), an implementation of artificial neural networks using a priori information for motion analysis is still quite rare. The paper shows the benefits from artificial neural networks and from using a priori information about the contents of the history in the image sequence to improve accuracy and speed of estimating motion parameters in the cases of distorted or overlapped objects. Firstly, it introduces 3 dimensional self organizing maps (SOM) with 2 dimensional input layers.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920049","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}
引用次数: 8
An emotion processing system based on fuzzy inference and subjective observations 基于模糊推理和主观观察的情感处理系统
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499429
T. Yanaru
{"title":"An emotion processing system based on fuzzy inference and subjective observations","authors":"T. Yanaru","doi":"10.1109/ANNES.1995.499429","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499429","url":null,"abstract":"The two theories concerning mixed emotions, adopted in this research is briefly explained. Also discussed are the image codes linked to the mixed emotional words and the way to realize a mechanism using fuzzy inference, in which the internal emotion of a simulated person reacts on a sequence of inputted terms and evokes some emotional change. The relevant part of the theory for subjective observation model to the application of emotion processing system is briefly explained. The construction methodology of the system, which has two functions, is described; one function is that the evoked emotion is transitive depending on the observation, and the other is that the aggregated emotion by the several subjective observations settles to the objective emotion. Some attractive results obtained from the simulated emotion processing system are shown: what kinds of emotions are evoked, and how the emotional transition is done by subjective observations, when a poem is used for the input signal. Lastly, the more expanded emotional Dialog System is introduced.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"12 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120873529","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}
引用次数: 8
A wool specification expert system in LEVEL5 Object or experiences of a procedural programmer with a hybrid system LEVEL5对象中的羊毛规格专家系统或过程程序员使用混合系统的经验
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499516
D. Maddever
{"title":"A wool specification expert system in LEVEL5 Object or experiences of a procedural programmer with a hybrid system","authors":"D. Maddever","doi":"10.1109/ANNES.1995.499516","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499516","url":null,"abstract":"Some experiences of a self-trained programmer developing an expert system (ES), initially in VP Expert and then ported to LEVEL5 Object, are discussed. Moving from an incremental approach of developing code in FORTRAN to the disciplined approach required for an ES which is object oriented (OO), proved frustrating but also rewarding. A need for careful analysis and design not only provided a structure for the OO system development but subsequently proved useful for more conventional systems developments. The ES assists with the determination of a specification for parcels of New Zealand wool to be processed into carpet yarn. The extension to an intelligent system which learns by way of an evolutionary algorithm is being customised for commercial use in a yarn manufacturing plant.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132084309","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}
引用次数: 0
Fuzzy hardware synthesis with generic LR fuzzy cells 通用LR模糊单元模糊硬件综合
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499456
Chao-Lieh Chen, Y. Kuo
{"title":"Fuzzy hardware synthesis with generic LR fuzzy cells","authors":"Chao-Lieh Chen, Y. Kuo","doi":"10.1109/ANNES.1995.499456","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499456","url":null,"abstract":"A novel primitive cell structure, called the LR fuzzy cell for hardware realization of fuzzy reasoning or other fuzzy computations is proposed. An LR fuzzy cell is an integral unit encapsulating an LR fuzzy set and a basic fuzzy operation like implication or an arithmetic operation. Using the LR fuzzy cells, we can synthesize high-performance fuzzy systems including fuzzy ASICs and general-purposed fuzzy processors in a fast and systematic way. The synthesized fuzzy systems inherently possess parallel inference ability. The system expandability and modifiability are also warrantable. The proposed generic LR fuzzy cells are implemented with current mode analog technology. By this technology, a fuzzy processor design based on this cell structure possesses the characteristics including small circuit area, high performance, low power dissipation, etc.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130526642","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}
引用次数: 2
On description of dynamical behavior of fuzzy control systems and a linguistic design method of fuzzy controllers 模糊控制系统动态行为的描述及模糊控制器的语言设计方法
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499463
T. Furuhashi, G. Adachi, Y. Uchikawa
{"title":"On description of dynamical behavior of fuzzy control systems and a linguistic design method of fuzzy controllers","authors":"T. Furuhashi, G. Adachi, Y. Uchikawa","doi":"10.1109/ANNES.1995.499463","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499463","url":null,"abstract":"This paper describes a method for the description of the dynamical behavior of fuzzy control systems and a linguistic design method for fuzzy controllers. The required response of the control systems can be given by linguistic expressions. The feasibility of the new method is examined by experiments with an inverted pendulum. The results show that the method is effective for satisfying the linguistic requirements.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125213897","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}
引用次数: 0
Cluster validation with generalized Dunn's indices 广义Dunn指数的聚类验证
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499469
J. Bezdek, N. Pal
{"title":"Cluster validation with generalized Dunn's indices","authors":"J. Bezdek, N. Pal","doi":"10.1109/ANNES.1995.499469","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499469","url":null,"abstract":"Some generalizations of Dunn's (1973) index for validation of crisp clusters are discussed. Numerical examples suggest that this index, which uses the standard measures for inter-set distance and set diameter can be improved by using different functions for either or both of these operators.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123458576","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}
引用次数: 104
An expert project management assistant 专业的项目管理助理
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499471
D. Russell
{"title":"An expert project management assistant","authors":"D. Russell","doi":"10.1109/ANNES.1995.499471","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499471","url":null,"abstract":"The paper discusses the management of large multi-layer projects and the need for computer assistance in the development of cohesive planning. Any system that purports to assist an experienced project manager, must itself contain embedded intelligence to be of any use. As projects are fragmented and subsequently abstracted back into the parent-project, limited recursive procedures must indicate the potential effect of the lower order plan and offer the responsible manager options and remediations before accepting changes. A sub-goal of the system is the preclusion of redundant task dependencies and the avoidance of inadvertent logic-loops. The system uses a consistent GUI (graphical user interface) and context-sensitive help and explanation procedures.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121392558","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}
引用次数: 0
Training error, generalization error and learning curves in neural learning 神经学习中的训练误差、泛化误差和学习曲线
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499426
S. Amari
{"title":"Training error, generalization error and learning curves in neural learning","authors":"S. Amari","doi":"10.1109/ANNES.1995.499426","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499426","url":null,"abstract":"A neural network is trained by using a set of available examples to minimize the training error such that the network parameters fit the examples well. However, it is desired to minimize the generalization error to which no direct access is possible. There are discrepancies between the training error and the generalization error due to the statistical fluctuation of examples. The article focuses on this problem from the statistical point of view. When the number of training examples is large, we have a universal asymptotic evaluation on the discrepancies of the two errors. This can be used for model selection based on the information criterion. When the number of training examples is small, their discrepancies are big, causing a serious overfitting or overtraining problem. We analyze this phenomenon by using a simple model. It is surprising that the generalization error even increases as the number of examples increases in a certain range. This shows the adequacy of the minimum training error learning method. We evaluate various means of overcoming the overtraining such as cross validated early stopping of training, introduction of the regularization terms, model selection and others.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129948616","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}
引用次数: 6
The QUEST questionnaire system QUEST问卷调查系统
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499474
K. Morton, C. Carey-Smith, K. Carey-Smith
{"title":"The QUEST questionnaire system","authors":"K. Morton, C. Carey-Smith, K. Carey-Smith","doi":"10.1109/ANNES.1995.499474","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499474","url":null,"abstract":"This paper describes the design and implementation of an expert system based questionnaire system. The concept of a questionnaire is examined from a process model and an information model point of view. From the questionnaire models two expert system implementations have been designed and implemented. Finally the shortcomings and advantages are presented and discussed.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233628","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}
引用次数: 7
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信