Computational Aspects of Cognition and Consciousness in Intelligent Devices

We review computational intelligence methods of sensory perception and cognitive functions in animals, humans, and artificial devices. Top-down symbolic methods and bottom-up sub-symbolic approaches are described. In recent years, computational intelligence, cognitive science and neuroscience have achieved a level of maturity that allows integration of top-down and bottom-up approaches in modeling the brain. Continuous adaptation and teaming is a key component of computationally intelligent devices, which is achieved using dynamic models of cognition and consciousness. Human cognition performs a granulation of the seemingly homogeneous temporal sequences of perceptual experiences into meaningful and comprehensible chunks of concepts and complex behavioral sehemas. They are accessed during action selection and conscious decision making as part of the intentional cognitive cycle. Implementations in computational and robotic environments are demonstrated.     

基于计算智能方法的动态系统故障诊断技术

简要地综述了基于计算智能方法的动态系统故障诊断技术的最新进展。将计算智能方法与基于模型的方法结合，用于不确定非线性动态系统的故障诊断是这一领域新的发展趋势。重点分析了用于非线性系统故障诊断的基于状态／参数估计的计算智能方法，主要包括神经网络、模糊逻辑、遗传算法。探讨了提高诊断算法鲁棒性的途径。同时也对无模型的基于计算智能的故障诊断方法中的一些研究热点问题进行了分析。最后探讨了该领域今后的发展方向。     

A microworld approach to the formalization of musical knowledge

This paper is about the importance of applying computational modeling and artificial intelligence techniques to music cognition and computer music research. The construction of microworlds as a methodology plays a key role in the different stages of this research. Several uses of microworlds are described. Microworlds have been criticized in the domains of artificial intelligence and the cognitive sciences, but this critique has to be seen in its proper context (i.e. in modeling of human intelligence, not as a methodology). It is shown that the microworld approach is still an important methodology in music cognition and computer music research, and a promising strategy in the design of a general representation formalism of musical knowledge.Henkjan Honing is research fellow at the University of Amsterdam, where he is doing research on the formalization of musical knowledge concentrating on time and temporal structure. With Peter Desain he wrote the bookMusic, Mind and Machine: Studies in Computer Music, Music Cognition and Artificial Intelligence.     

AI-SIMCOG: a simulator for spiking neurons and multiple animats’ behaviours

Designing a biologically inspired neural architecture as a controller for a complete animat or physical robot environment, to test the hypotheses on intelligence or cognition is non-trivial, particularly, if the controller is a network of spiking neurons. As a result, simulators that integrate spike coding and artificial or real-world platforms are scarce. In this paper, we present artificial intelligence simulator of cognition, a software simulator designed to explore the computational power of pulsed coding at the level of small cognitive systems. Our focus is on convivial graphical user interface, real-time operation and multilevel Hebbian synaptic adaptation, accomplished through a set of non-linear dynamic weights and on-line, life-long modulation. Inclusions of transducer and hormone components, intrinsic oscillator and several learning functions in a discrete spiking neural algorithm are distinctive features of the software. Additional features are the easy link between the production of specific neural architectures and an artificial 2D-world simulator, where one or more animats implement an input–output transfer function in real-time, as do robots in the real world. As a result, the simulator code is exportable to a robot’s microprocessor. This realistic neural model is thus amenable to investigate several time related cognitive problems.

Gaussian process approach for modelling of nonlinear systems

Parametric modelling principals such as neural networks, fuzzy models and multiple model techniques have been proposed for modelling of nonlinear systems. Research effort has focused on issues such as the selection of the structure, constructive learning techniques, computational issues, the curse of dimensionality, off-equilibrium behaviour, etc. To reduce these problems, the use of non-parametrical modelling approaches have been proposed. This paper introduces the Gaussian process (GP) prior approach for the modelling of nonlinear dynamic systems. The relationship between the GP model and the radial basis function neural network is explained. Issues such as selection of the dimension of the input space and the computation load are also discussed. The GP modelling technique is demonstrated on an example of the nonlinear hydraulic positioning system.     

Learning style Identifier: Improving the precision of learning style identification through computational intelligence algorithms

Identifying students’ learning styles has several benefits such as making students aware of their strengths and weaknesses when it comes to learning and the possibility to personalize their learning environment to their learning styles. While there exist learning style questionnaires for identifying a student's learning style, such questionnaires have several disadvantages and therefore, research has been conducted on automatically identifying learning styles from students’ behavior in a learning environment. Current approaches to automatically identify learning styles have an average precision between 66% and 77%, which shows the need for improvements in order to use such automatic approaches reliably in learning environments. In this paper, four computational intelligence algorithms (artificial neural network, genetic algorithm, ant colony system and particle swarm optimization) have been investigated with respect to their potential to improve the precision of automatic learning style identification. Each algorithm was evaluated with data from 75 students. The artificial neural network shows the most promising results with an average precision of 80.7%, followed by particle swarm optimization with an average precision of 79.1%. Improving the precision of automatic learning style identification allows more students to benefit from more accurate information about their learning styles as well as more accurate personalization towards accommodating their learning styles in a learning environment. Furthermore, teachers can have a better understanding of their students and be able to provide more appropriate interventions.     

从知识表示到表示:人工智能认识论上的进步

知识表示是对智能进行模拟的一个数学模型,然而它可以不是一个对智能本质的描述,特别是传统的符号主义知识表示离揭示人的智能行为发生的内在过程还有很大的差距,在神经科学和心理学的指导下,通过对智能行为的生理基础和心理过程的研究,遵循“解释智能”的思想,可以得到对知识的心智表示的新认识,这种表示观的不同,预示着人工智能方法论上的进步。     

基于生物脑网络连接特性的高效神经网络算法

人工神经网络发展至今,已经在计算机视觉、类脑智能等方面得到广泛应用.在过去几十年中,人们对神经网络的研究注重追求更高的准确率,从而忽略了对网络计算成本的控制.而人脑作为高效且节能的网络,其对人工智能的发展起到了重要启示作用.如何仿真生物脑网络的连接特性,建立超低能耗的人工神经网络模型实现基本相同的目标识别正确率成为当前研究的热点.为建立低能耗的人工神经网络模型,本文结合大脑网络的连接特性,通过改变人工神经网络的连接实现网络的高效性.实验结果表明,结合生物脑网络的连接特性,改变网络的连接,很大程度上减少了网络的计算成本,而网络的性能并没有受到明显影响.     

计算智能方法及应用研究

介绍了4种计算智能方法,即神经网络、模糊计算、遗传算法和免疫算法,通过总结和比较各智能算法的优缺点及其在各个领域的应用,给出了计算智能存在的主要问题及发展趋势。设计了脱机手写签名识别软件,提取签名图像的骨架特征和边角特征,并利用BP神经网络方法有效地识别真、假签名。     

Statistical and computational intelligence tools for the analyses of warp tension in different back-rest oscillations

In this paper, experimental, computational intelligence based and statistical investigations of warp tensions in different back-rest oscillations are presented. Firstly, in the experimental stage, springs having different stiffnesses are used to obtain different back-rest oscillations. For each spring, fabrics are woven in different weft densities and the warp tensions are measured and saved during weaving process. Secondly, in the statistical investigation, the experimental data are analyzed by using linear multiple and quadratic multiple-regression models. Later, in the computational intelligence based investigation, the data obtained from the experimental study are analyzed by using artificial neural networks that are universal approximators which provide a massively parallel processing and decentralized computing. Specially, radial basis function neural network structure is chosen. In this structure, cross-validation technique is used in order to determine the number of radial basis functions. Finally, the results of regression analysis, the computational intelligence based analysis and experimental measurements are compared by using the coefficient of determination. From the results, it is shown that the computational intelligence based analysis indicates a better agreement with the experimental measurement than the statistical analysis.     

Exploring aspects of cell intelligence with artificial reaction networks

The Artificial Reaction Network (ARN) is a Cell Signalling Network inspired connectionist representation belonging to the branch of A-Life known as Artificial Chemistry. Its purpose is to represent chemical circuitry and to explore computational properties responsible for generating emergent high-level behaviour associated with cells. In this paper, the computational mechanisms involved in pattern recognition and spatio-temporal pattern generation are examined in robotic control tasks. The results show that the ARN has application in limbed robotic control and computational functionality in common with Artificial Neural Networks. Like spiking neural models, the ARN can combine pattern recognition and complex temporal control functionality in a single network, however it offers increased flexibility. Furthermore, the results illustrate parallels between emergent neural and cell intelligence.     

基于小脑-基底神经节机理的行为认知计算模型

针对智能体的行为认知问题,提出一种小脑与基底神经节相互协调的行为认知计算模型。该模型核心为操作条件学习算法,包括评价机制、行为选择机制、取向机制及小脑与基底神经节的协调机制。初期的学习信号来自于下橄榄体和黑质两部分,在熵的意义上说明该算法是收敛的。采用该学习方法为自平衡两轮机器人建立运动神经认知系统,利用RBF网络逼近行为和评价网络。仿真实验表明该方法改善仅有基底神经节作用的行为-评价算法学习速度慢和失败次数多的问题,学习后期通过温度的不断降低,加快学习速度,震荡逐渐消失,改善学习效果。     

A new artificial neural network structure for solving high-order linear fractional differential equations

Artificial neural networks afford great potential in learning and stability against small perturbations of input data. Using artificial intelligence techniques and modelling tools offers an ever-greater number of practical applications. In the present study, an iterative algorithm, which was based on the combination of a power series method and a neural network approach, was used to approximate a solution for high-order linear and ordinary differential equations. First, a suitable truncated series of the solution functions were substituted into the algorithm's equation. The problem considered here had a solution as a series expansion of an unknown function, and the proper implementation of an appropriate neural architecture led to an estimate of the unknown series coefficients. To prove the applicability of the concept, some illustrative examples were provided to demonstrate the precision and effectiveness of this method. Comparing the proposed methodology with other available traditional techniques showed that the present approach was highly accurate.     

Application of an emotional neural network to facial recognition

In our attempts to model human intelligence by mimicking the brain structure and function, we overlook an important aspect in human cognition, which is the emotional factor. It may currently sound unthinkable to have emotional machines; however, it is possible to simulate certain artificial emotions with the aim of improving machine learning. This paper investigates the efficiency of an emotional neural network, which uses a modified back propagation learning algorithm. The modifed algorithm, namely the emotional BP learning algorithm, has two emotional parameters, anxiety and confidence, that are modeled during machine learning and decision making. The emotional neural network will be implemented to a facial recognition problem using images of faces with different orientations and contrast levels, and its performance will be compared to that of a conventional neural network. Experimental results suggest that artificial emotions can be successfully modeled and efficiciently implemented to improve neural networks learning and generaliztion.     

Using adaptive neuro-fuzzy inference system for hydrological time series prediction

Conventionally, the multiple linear regression procedure has been known as the most popular models in simulating hydrological time series. However, when the nonlinear phenomenon is significant, the multiple linear will fail to develop an appropriate predictive model. Recently, intelligence system approaches such as artificial neural network (ANN) and neuro-fuzzy methods have been used successfully for time series modelling. In most instances for neural networks, multi layer perceptrons (MLPs) that are trained with the back-propagation algorithm have been used. The major shortcoming of this approach is that the knowledge contained in the trained networks is difficult to interpret. Using neuro-fuzzy approaches, which enable the information that is stored in trained networks to be expressed in the form of a fuzzy rule base, would help to overcome this issue. In the present study, a time series neuro-fuzzy model is proposed that is capable of exploiting the strengths of traditional time series approaches. The aim of this article is to investigate the potential of a neuro-fuzzy system with a Sugeno inference engine, considering different numbers of membership functions. Three rivers have been selected and daily prediction for them was applied. For better judgment, outcomes of the network have been compared to an autoregressive model.     

Medical image fusion based on hybrid intelligence

Medical image fusion combines complementary images from different modalities for proper diagnosis and surgical planning. A new approach for medical image fusion based on the hybrid intelligence system is proposed. This paper has integrated the swarm intelligence and neural network to achieve a better fused output. The edges are an important feature of an image and they are detected and optimized by using ant colony optimization. The detected edges are enhanced and it is given as the feeding input to the simplified pulse coupled neural network. The firing maps are generated and the maximum fusion rule is applied to get the fused image. The performance of the proposed method is compared both subjectively and objectively, with the genetic algorithm method, neuro-fuzzy method and also with the modified pulse coupled neural network. The results show that the proposed hybrid intelligent method performs better when compared to the existing computational and hybrid intelligent methods.     

The implications for understanding high-level cognition of a grounding in elementary adaptive systems

There is a certain tendency to consider that, whereas approaches based on artificial life may be appropriate for lower-level cognition, the computational theory of mind based primarily on the manipulation of symbolic representations is the only possible approach to high-level cognition. This article contests that view, and argues that a constructivist approach to cognition rooted in elementary living organisms leads to a radically new understanding of phenomena such as communication, representation, intentional action and language. Whatever the level of cognition, the computational paradigm is necessarily objectivist, whereas the constructivist paradigm is non-objectivist. It is suggested that within the field of Artificial Life, objectivism is appropriate from an engineering perspective, but that constructivism is appropriate from a biological perspective aimed at modelling living organisms as autonomous systems.     

基于计算智能的基因表达数据聚类分析研究进展

基因表达数据聚类是发现基因功能和确立基因调控网络的重要方法,计算智能在该领域的应用为分析 大量基因数据提供了新途径．本文根据基因表达数据的特点,提出了基因表达数据聚类领域的关键问题,探讨了基 于计算智能的基因表达数据聚类基本框架,综述了计算智能在基因数据聚类领域的应用现状,最后指出了在基因数 据聚类领域计算智能方法未来的发展方向．     

The selection of an optimal segmentation region in physiological signals

Physiological signals are often corrupted by noisy sources. Usually, artificial intelligence algorithms analyze the whole signal, regardless of its varying quality. Instead, experienced cardiologists search for a high-quality signal segment, where more accurate conclusions can be draw. We propose a methodology that simultaneously selects the optimal processing region of a physiological signal and determines its decoding into a state sequence of physiologically meaningful events. Our approach comprises two phases. First, the training of a neural network that then enables the estimation of the state probability distribution of a signal sample. Second, the use of the neural network output within an integer program. The latter models the problem of finding a time window by maximizing a likelihood function defined by the user. Our method was tested and validated in two types of signals, the phonocardiogram and the electrocardiogram. In phonocardiogram and electrocardiogram segmentation tasks, the system's sensitivity increased on average from 95.1% to 97.5% and from 78.9% to 83.8%, respectively, when compared to standard approaches found in the literature.