A comparison of adaptive control strategies for hot steel strip rolling mills

Many modeling situations occur in which the plant has uncertain dynamics, nonlinearities, time varying characteristics and noise corrupted input and output measurements. These processes generally require a human operator whose function is to provide intelligent modeling and control. This exact situation occurs in the modeling and control of roll force in a hot steel rolling mill. It is the purpose of this paper to investigate and compare various adaptive control strategies for this problem.The first strategy uses a parameter identification technique to track the parameters in the roll force setup model from one steel run to the next. The next algorithm provides feedback control from run to run by an adaptive controller which uses a linear reinforcement learning scheme to adjust its parameters. The third method accounts for the above complexities by approaching the problem from a behavioral and structural point of view. The behavior of the model is assessed through a performance evaluator and the model is modified structurally and parametrically to improve the performance of the system as the process evolves. The derivation is based on correlation techniques and linear reinforcement learning theory, the latter of which provides memory and intelligence to the algorithm to model the decision process of the human operator. The results of this work serve to reinforce the opinion that the nonlinear mathematical structure of the model should be able to change from one steel run to the next in order to compensate for changes in mill characteristics and in the mill environment. Modeling results are presented from actual mill data and comparisons are made with time invariant models. In addition, the algorithms are general enough so that they may be easily applied to other processes that seem to defy traditional modeling techniques. They are not case dependent.     

The s-ethos system: A methodology for systematic flight analysis centered on human factors

The aeronautics community needs several alternative methods and tools to describe and analyze interactions between human operators and systems, according to some constraints (e.g., human factors, air safety, etc.). Hence, it needs to build models from the observation of real interactions, especially piloting, and to use extant theories from several fields: cognitive ergonomics and artificial intelligence, mainly. S-ETHOS sketches out a knowledge-based system that analyzes human pilot activities and provides feedback to improve air safety by giving measured appraisal of pilot error. The core of S-ETHOS is the ETHOS model that depicts the standard behavior based on the human pilot. S-ETHOS helps any air safety expert to simulate the pilot behavior during his mission and then will compare behavior between the simulation and real situations. It allows the air safety expert to know how the pilot assesses each situation. We implemented the ETHOS model according to an object-oriented approach, relying on a knowledge modeling language called OBJLOG II+. This model provides a first keystone to understanding how the human pilot captures and builds his environment through complex states. We will discuss the identified behaviors and potential deviations and associated situations.     

Mathematical modeling of decision making: a soft and fuzzy approach to capturing hard decisions

This research focuses on a modeling approach and set of mathematical tools that were derived from research on intelligence systems, namely fuzzy system modeling. This study systematically evaluates these tools as an approach for modeling human decision making, contrasting the approach with more traditional methods based on regression. The research was conducted using experts and a simulated task environment related to allocating rewards in the form of merit pay. The results indicate that fuzzy system models generally perform as well as or better than both linear and nonlinear regression methods in terms of model fit. These results are discussed in terms of issues regarding modeling precision versus parsimony, the value of adaptive modeling techniques, empirical versus subjective approaches to model building, and individual differences in judgment strategies. Potential applications of this research include using the modeling approach studied to build higher-fidelity models that yield new insights and a better understanding of decision-making strategies and environments.     

面向TD-LTE通信系统的功放新模型

鉴于参数辨识过程简单的优点,记忆多项式模型已被广泛用于模拟功率放大器的行为。在记忆多项式功放模型的基础上,提出了一种面向TD-LTE通信系统的有理函数功放新模型。该模型通过基于两个记忆多项式模型的比率,在保证模拟小信号输入功放特性的同时还能够对大信号驱动下的功放行为进行准确预测,应用最小二乘法技术提取模型参数。利用NXP功放管设计Doherty功放电路,在ADS环境下导出强非线性输入输出信号数据实现模型性能验证。结果表明,提出的新模型性能优于传统的记忆多项式模型,具有更高精度,能够精确模拟功率放大器特性,对射频功放行为建模的研究与发展具有重要参考价值。     

基于人工智能的自然长寿人群生命信息系统建模

以中国新疆和田地区维吾尔自然长寿人群为例，探索一种基于人工智能(artificial intelligence，AI)的生命信息系统新的建模方法．在建模过程中，由于引入人工智能和数据融合技术，能够高效地提取隐藏于复杂数据中对生命起关键作用的因素，因此成功地建立了一个既非语言表达也非数学公式描述的隐式的自然长寿人群的人工智能模型．此人工智能模型不但更接近实际，而且具有判别、预见等超前功能．该模型可修改、可移植．     

时空数据库中数据建模的研究

研究了时空数据库中的时空建模技术。早期表示时空信息的数据模型通常用基于几何学的空间对象来表示实体，重要的特性都用空间对象的属性来表示。时态信息可以与基于时间戳的独立层次相关联，也可以与独立的空间对象相关联。随着时空建模的进一步发展，出现了面向对象的数据模型和基于事件的数据模型。综合研究了这些典型的时空数据模型，讨论了它们的应用及时空分析建模的作用。此外介绍了针对移动对象的数据类型的建模方法，以及在时空分析数据库管理系统STADBS中，基于Realms的二级平衡二叉树的时空数据模型。     

On learning discontinuous human control strategies*

Models of human control strategy (HCS), which accurately emulate dynamic human behavior, have far reaching potential in areas ranging from robotics to virtual reality to the intelligent vehicle highway project. A number of learning algorithms, including fuzzy logic, neural networks, and locally weighted regression exist for modeling continuous human control strategies. These algorithms, however, may not be well suited for modeling discontinuous human control strategies. Therefore, we propose a new stochastic, discontinuous modeling framework, for abstracting human control strategies, based on hidden Markov models (HMM). In this paper, we first describe the real-time driving simulator which we developed for investigating human control strategies. Next, we demonstrate the shortcomings of a typical continuous modeling approach in modeling discontinuous human control strategies. We then propose an HMM-based method for modeling discontinuous human control strategies. The proposed controller overcomes these shortcomings and demonstrates greater fidelity to the human training data. We conclude the paper with further comparisons between the two competing modeling approaches and we propose avenues for future research. © 2001 John Wiley & Sons, Inc.     

深度学习在多核缓存预取中的应用研究综述

当前人工智能技术应用于系统结构领域的研究前景广阔,特别是将深度学习应用于多核架构的数据预取研究已经成为国内外的研究热点。针对基于深度学习的缓存预取任务进行了研究,形式化地定义了深度学习缓存预取模型。在介绍当前常见的多核缓存架构和预取技术的基础上,全面分析了现有基于深度学习的典型缓存预取器的设计思路。深度学习神经网络在多核缓存预取领域的应用主要采用了深度神经网络、循环神经网络、长短期记忆网络和注意力机制等机器学习方法,综合对比分析现有基于深度学习的数据预取神经网络模型后发现,基于深度学习的多核缓存预取技术在计算成本、模型优化和实用性等方面还存在着局限性,未来在自适应预取模型以及神经网络预取模型的实用性方面还有很大的研究探索空间和发展前景。     

Acquisition of internal representation in robots - toward human-robot communication using primitive language

This research aims to clarify behavior intelligence and human cooperation intelligence of robots by emotion models which are based on the robot's hardware structure. In this paper, a human's mental image (internal expression) is given consideration as a method for emotional expression of robots. The hypothesis model for the acquisition of the internal expression of robots and experimental results using a real autonomous robot are described.     

A temporal graph framework for intelligence extraction in social media networks

Social media networks (SMNs) are increasingly used in professional management of knowledge workers and related assets. However, the factors affecting behavioral trends and activity levels in these networks are not well understood. Although social and cognitive theories can help to explain human behavior in traditional social networks, their application to SMNs has not been validated. Traditional social network modeling techniques may not accurately predict real-world SMN activities. This research developed a temporal graph framework for intelligence extraction in SMNs. Theory-based, data-driven models (Conformity Model (COM), Recency-Primacy Model (REM), Trend Interaction Model (TIM), Periodic Interaction Model (PIM)) were developed based on the framework to capture various aspects of user behavior: conformity effect, recency, primacy, periodicity, and dynamic trend. The models capture the activity history and dynamically combine pricing information to enhance predictive accuracy. Using data of 83,536 GitHub software repositories on cryptocurrency, this article reports the results of experiments that compare the models’ performance in predicting SMN activities over time. Experimental results show that the model (REM) that captures recency/primacy effects of human cognitive processing outperformed other models in 9 (out of 18) measures pertaining to engagement, contribution, influence, and popularity. Primacy plays a dominant role in predicting engagement, contribution, and popularity, whereas recency plays a key role in predicting influence. Short-term trend (modeled with TIM) was found to yield significantly better performance on predicting user contribution. The models also outperformed an integrated machine learning (IML) model by most measures. Overall, the effects modeled by REM and TIM were found to be more significant than the effects modeled by COM, PIM, and IML. The research contributes to enhancing understanding of SMN behavior, developing new models to simulate and predict SMN activities, and designing new artifacts for information systems practitioners to manage knowledge assets and to extract SMN intelligence.     

计算机动画中人体建模与皮肤变形技术的研究现状与展望

人体动画制作技术是计算机动画领域内的研究热点和难点。在制作真实感人体动画时,除了有真实的人体运动和灵活的运动控制方法外,还需要有逼真的人体造型和皮肤变形效果。为了使计算机动画研究领域的研究人员对当前各种人体建模与皮肤变形技术有较全面的了解,对计算机动画中的真实感人体建模与皮肤变形技术进行了较为全面的阐述,将现有的方法分为三大类:基于面模型的方法、基于体模型的方法和基于层次式模型的方法,并分析和比较了这些方法的优缺点。在回顾了现有的人体建模与变形技术的基础上指出,3维扫描技术的发展使人体建模和皮肤变形的研究面临新的契机。如何充分利用基于扫描技术建模的优点,并结合层次式建模与变形方法的灵活性的特点,创作出高度真实感的人体皮肤模型及其变形效果,是未来研究的重要方向。     

Computer graphics aided geometric modeling and mesh generation schemes for preprocessing and finite element analysis

The paper describes automated generation and editing schemes together with the development of computer-aided geometric models for general applications. For the construction of general finite element models of complex shapes, conventional approaches typical of wireframe, surface, or solid modeling cannot be effectively utilized for generating continuum solid models as well as discrete models simultaneously. In view of these facts, features to generate and model two-dimensional as well as threedimensional continuum and discrete models by isoparametric mapping/solid geometrical modeling techniques via a common interactive processor are described. The proposed scheme is demonstrated for modeling structural, thermal, or flow networks that are commonly encountered in engineering applications. In a research environment, the techniques addressed in this paper should prove to be very useful in providing flexibility and thereby significantly reducing the work load of frequent CAD users.     

A survey on computational intelligence approaches for predictive modeling in prostate cancer

Predictive modeling in medicine involves the development of computational models which are capable of analysing large amounts of data in order to predict healthcare outcomes for individual patients. Computational intelligence approaches are suitable when the data to be modelled are too complex for conventional statistical techniques to process quickly and efficiently. These advanced approaches are based on mathematical models that have been especially developed for dealing with the uncertainty and imprecision which is typically found in clinical and biological datasets. This paper provides a survey of recent work on computational intelligence approaches that have been applied to prostate cancer predictive modeling, and considers the challenges which need to be addressed. In particular, the paper considers a broad definition of computational intelligence which includes metaheuristic optimisation algorithms (also known as nature inspired algorithms), Artificial Neural Networks, Deep Learning, Fuzzy based approaches, and hybrids of these, as well as Bayesian based approaches, and Markov models. Metaheuristic optimisation approaches, such as the Ant Colony Optimisation, Particle Swarm Optimisation, and Artificial Immune Network have been utilised for optimising the performance of prostate cancer predictive models, and the suitability of these approaches are discussed.     

智能需求获取与建模研究综述

需求获取和建模是指从需求文本或记录中获取显式和隐式的需求,并通过表格化、图形化、形式化等方法构建相应模型的过程,是软件开发过程中极为关键的一步,为后续系统设计与实现铺平道路,提高软件开发效率和质量,提升软件系统稳定性和可行性.研究者们在需求获取与建模方面获得了一系列研究成果,根据其关注阶段不同,可以将它们分为需求知识提...     

大尺度大脑模型：相关理论，建模策略与典型模型

利用计算神经科学原理或图论对大脑进行建模得到的大尺度大脑模型,在脑科学研究和人工智能等方面有着极大的研究意义和应用价值。合理的大尺度大脑模型将对探索和理解大脑工作的内在机制以及大脑神经系统相关疾病的成因有很大帮助,也将大大推动人工智能领域由当前的弱人工智能向强人工智能迈进。因此,大尺度大脑模型的相关研究在过去十年间受到国内外学者的广泛关注。通过查阅大量关于大尺度大脑模型的研究文献,并对其相关研究进行回顾、归纳、分析和总结,报告了大尺度大脑模型的研究现状。给出了大尺度大脑模型的明确定义,归纳总结了大尺度大脑模型的多个范畴,同时介绍了研究大尺度大脑模型所需了解的相关基础理论;归纳了大尺度大脑模型的有效构建策略,回顾了迄今为止国内外具有代表性的几个大尺度大脑模型的详细建模方法及应用;总结了大尺度大脑模拟领域目前存在的不足和遇到的困难,展望了大尺度大脑模型将来可能的发展趋势和应用方向。     

Soft computing for greenhouse climate control

The methodology proposed in the paper applies artificial intelligence (AI) techniques to the modeling and control of some climate variables within a greenhouse. The nonlinear physical phenomena governing the dynamics of temperature and humidity in such systems are, in fact, difficult to model and control using traditional techniques. The paper proposes a framework for the development of soft computing-based controllers in modern greenhouses     

A fuzzy cognitive map model to calculate a user's desirability based on personality in e-learning environments

The recent research in artificial intelligence shows an increasing interest in the modeling of human behavior factors such as personality, mood, and emotion for developing human-friendly systems. That is why there is an interest in developing models and algorithms to determine a human's emotions while interacting with a system to improve the quality of the interaction. In this paper, we propose a computational model to calculate a user's desirability based on personality in e-learning environments. The desirability is one of the most important variables in determining a user's emotions. The model receives several e-learning environmental events and predicts the desirability of the events based on the user's personality and his/her goals. The proposed model has been evaluated in a simulated and real e-learning environment. The results show that the model formulates the relationship between personality and emotions with high accuracy.     

机器人操作技能模型综述

机器人技能学习是人工智能与机器人学的交叉领域,目的是使机器人通过与环境和用户的交互得到经验数据,基于示教学习或强化学习,从经验数据中自主获取和优化技能,并应用于以后的相关任务中.技能学习使机器人的任务部署更加灵活快捷和用户友好,而且可以让机器人具有自我优化的能力.技能模型是技能学习的基础和前提,决定了技能效果的上限.日益复杂和多样的机器人操作任务,对技能操作模型的设计实现带来了很多挑战.本文给出了技能操作模型的概念与性质,阐述了流程、运动、策略和效果预测四种技能表达模式,并对其典型应用和未来趋势做出了概括.     

面向小样本数据的机器学习方法研究综述

小样本学习是面向小样本数据的机器学习,旨在利用较少的有监督样本数据去构建能够解决实际问题的机器学习模型。小样本学习能够解决传统机器学习方法在样本数据不充分时性能严重下降的问题,可以为新型小样本任务实现低成本和快速的模型部署,缩小人类智能与人工智能之间的距离,对推动发展通用型人工智能具有重要意义。从小样本学习的概念、基础模型和实际应用入手,系统梳理当前小样本学习的相关工作,将小样本学习方法分类为基于模型微调、基于数据增强、基于度量学习和基于元学习,并具体阐述这4大类方法的核心思想、基本模型、细分领域和最新研究进展,以及每一类方法在科学研究或实际应用中存在的问题,总结目前小样本学习研究的常用数据集和评价指标,整理基于部分典型小样本学习方法在Omniglot和Mini-ImageNet数据集上的实验结果。最后对各种小样本学习方法及其优缺点进行总结,分别从数据层面、理论研究和应用研究3个方面对小样本学习的未来研究方向进行展望。     

布局及布置设计问题求解自动化的理论与方法综述

布局及布置设计问题是设计领域的一个重要部分，在工程实践中有着广泛的应用，它的求解自动化理论及方法对于设计自动化领域具有典型意义。由于其本身具有建模复杂性和NP完全的性质，求解具有很大的难度，文中介绍了布局问题的概念和目前存在的多种建模方法及求解方法，并指出求解布局问题的发展方向－建立复杂布局问题的复合知识模型并以虚拟现实技术为手段进行人机智能合作（协作）的求解，该发展方向对于设计过程许多阶段的自动化求解也具有参考价值。