Neural Network Logic Research Articles

Doubly Periodic Traveling Waves in a Cellular Neural Network with Linear Reaction

Szekeley observed that the dynamic pattern of the locomotion of salamanders can be explained by periodic vector sequences generated by logical neural networks. Such sequences can mathematically be described by periodic traveling and therefore it is of interest to propose dynamic models that may produce such waves. One such dynamic network model is built here based on reaction-diffusion principles and a complete discussion is given for the existence of doubly periodic waves as outputs. Since there are 2 parameters in our model and 4 a priori unknown parameters involved in our search of solutions, our results are nontrivial. The reaction term in our model is a linear function and hence our results can also be interpreted as existence criteria for solutions of a nontrivial linear problem depending on 6 parameters.

Solving Complex Logistics Problems with Multi-Artificial Intelligent System

The economy, which has become more information intensive, more global and more technologically dependent, is undergoing dramatic changes. The role of logistics is also becoming more and more important. In logistics, the objective of service providers is to fulfill all customers' demands while adapting to the dynamic changes of logistics networks so as to achieve a higher degree of customer satisfaction and therefore a higher return on investment. In order to provide high quality service, knowledge and information sharing among departments becomes a must in this fast changing market environment. In particular, artificial intelligence (AI) technologies have achieved significant attention for enhancing the agility of supply chain management, as well as logistics operations. In this research, a multi-artificial intelligence system, named Integrated Intelligent Logistics System (IILS) is proposed. The objective of IILS is to provide quality logistics solutions to achieve high levels of service performance in the logistics industry. The new feature of this agile intelligence system is characterized by the incorporation of intelligence modules through the capabilities of the case-based reasoning, multi-agent, fuzzy logic and artificial neural networks, achieving the optimization of the performance of organizations.

Adaptive Automata Applied on Automation and Robotics (A4R)

This paper presents the researches conducted using Adaptive Automata (AA) theory in robotics equipments, process and systems. The generalization and behavior adaptation features of AA allow their application for process modeling, identification, classification and decision making in the same way as traditional computational logic such as Fuzzy Logic and Artificial Neural Networks. As sample of AA applications, the paper presents the research on pattern recognition and the research on hybrid mapping for robot navigation.

Pre-earthquake fuzzy logic and neural network based rapid visual screening of buildings

When assessing buildings that may collapse during a large earthquake, conventional rapid visual screening procedures generally provide good results when identifying buildings for further investigation. Unfortunately, their accuracy at identify buildings at risk is not so good. In addition, there appears to be little room for improvement. This paper investigates an alternative screening procedure based on fuzzy logic and artificial neural networks. Two databases of buildings damaged during the Athens earthquake of 1999 are used for training purposes. Extremely good results are obtained from one database and not so good results are obtained from the second database. This finding illustrates the importance of specifically collecting data tailored to the requirements of the fuzzy logic based rapid visual screening procedure. In general, results demonstrate that the trained fuzzy logic based rapid visual screening procedure represents a marked improvement when identifying buildings at risk. In particular, when smaller percentages of the buildings with high damage scores are extracted for further investigation, the proposed fuzzy screening procedure becomes more efficient. This paper shows that the proposed procedure has a significant optimisation potential, is worth pursuing and, to this end, a strategy that outlines the future development of the fuzzy logic based rapid visual screening procedure is proposed.

EVOLVING NEURAL-SYMBOLIC SYSTEMS GUIDED BY ADAPTIVE TRAINING SCHEMES: APPLICATIONS IN FINANCE

The article presents a hybrid and adaptive intelligent methodology, based on neural logic networks and grammar-guided genetic programming. The aim of the study is to demonstrate how to generate efficient neural logic networks with the aid of genetic programming methods trained adaptively through an innovative scheme. The proposed adaptive training scheme of the genetic programming mechanism leads to the generation of high-diversity solutions and small-sized individuals. The overall methodology is advantageous due to the adaptive training scheme proposed for offering both accurate and interpretable results in the form of expert rules. Moreover, a sensitivity analysis study is provided within the article, comparing the performance of the proposed evolutionary neural logic networks methodology with well-known competitive inductive machine learning approaches. Two financial domains of application have been selected to demonstrate the capabilities of the proposed methodology: (a) classification of credit applicants for consumer loans of a German bank and (b) the credit-scoring decision-making process in an Australian bank. Results seem encouraging since the proposed methodology outperforms a number of competitive existing statistical and intelligent methodologies, while it also produces handy decision rules, short in length and transparent in meaning and use.

Model of land suitability evaluation based on computational intelligence

A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.

Enhancing knowledge discovery via association-based evolution of neural logic networks

The comprehensibility aspect of rule discovery is of emerging interest in the realm of knowledge discovery in databases. Of the many cognitive and psychological factors relating the comprehensibility of knowledge, we focus on the use of human amenable concepts as a representation language in expressing classification rules. Existing work in neural logic networks (or neulonets) provides impetus for our research; its strength lies in its ability to learn and represent complex human logic in decision-making using symbolic-interpretable net rules. A novel technique is developed for neulonet learning by composing net rules using genetic programming. Coupled with a sequential covering approach for generating a list of neulonets, the straightforward extraction of human-like logic rules from each neulonet provides an alternate perspective to the greater extent of knowledge that can potentially be expressed and discovered, while the entire list of neulonets together constitute an effective classifier. We show how the sequential covering approach is analogous to association-based classification, leading to the development of an association-based neulonet classifier. Empirical study shows that associative classification integrated with the genetic construction of neulonets performs better than general association-based classifiers in terms of higher accuracies and smaller rule sets. This is due to the richness in logic expression inherent in the neulonet learning paradigm.

GA-based synthesis approach for machining scheme selection and operation sequencing optimization for prismatic parts

To obtain global and near-global optimal process plans based on the combinations of different machining schemes selected from each feature, a genetic algorithm-based synthesis approach for machining scheme selection and operation sequencing optimization is proposed. The memberships derived from the fuzzy logic neural network (FL-NN), which contains the membership function of each machining operation to batch size, are presented to determine the priorities of alternative machining operations for each feature. After all alternative machining schemes for each feature are generated, their memberships are obtained by calculation. The proposed approach contains the outer iteration and nested genetic algorithm (GA). In an outer iteration, one machining scheme for each feature is selected by using the roulette wheel approach or highest membership approach in terms of its membership first, and then the corresponding operation precedence constraints are generated automatically. These constraints, which can be modified freely in different outer iterations, are then used in a constraints adjustment algorithm to ensure the feasibility of process plan candidates generated in GA. After that, GA obtains an optimal process plan candidate. At last, the global and near-global optimal process plans are obtained by comparing the optimal process plan candidates in the whole outer iteration. The proposed approach is experimentally validated through a case study.

EVOLUTIONARY NEURAL LOGIC NETWORKS IN SPLICE-JUNCTION GENE SEQUENCES CLASSIFICATION

The paper demonstrates the efficient use of hybrid intelligent systems for solving the classification problem of splice-junction gene sequences. The aim of the study is to obtain classification schemes able to recognize, given a sequence of DNA, the boundaries between exons and introns. Previous attempts to form efficient classifiers for the same problem using intelligent or standard statistical techniques are discussed throughout the paper. The authors propose the use of evolutionary neural logic networks, an advantageous approach for their ability to interpret their structure into expert rules, a desirable feature for field experts. Evolutionary neural logic networks in fact consist an innovative hybrid intelligent methodology, by which evolutionary programming techniques are used for obtaining the best possible topology of a neural logic network. The genetic programming process is guided using a context-free grammar and indirect encoding of the neural logic networks into the genetic programming individuals. Indicative classification results are presented and discussed in detail in terms of both, classification accuracy and solution interpretability.

Special issue: Recent developments in hybrid intelligent systems

The human-centric facet of intelligent systems, which are inherently based upon the principle of hybridization of the individual information technologies, is definitely an interesting and highly promising avenue to follow. The diversity of communication channels between information systems and the environment is immense, and their effective realization does call for a truly heterogeneous nature of the underlying technologies and algorithmic frameworks. Consider, for instance, processing visual information, which became omnipresent in many applications including a broad range of inspection and manufacturing systems. Computer vision offered remarkable opportunities of processing therein. Fuzzy sets support a granular view at images and form a setting for their interpretation at the higher, more abstract level. Neural networks and evolutionary optimization provide badly needed learning abilities. The technologies mentioned so far, when combined into an inherently hybrid system, help address the needs of intelligent vision systems and build a coherent and versatile implementation. Managing knowledge at various levels, starting from the detailed pixel-level and moving to the far more general abstract level, becomes crucial to the success of such systems. This special issue is a testimony to the ongoing innovation and recent developments in hybrid information systems. The study by Shahram Jafari and Ray Jarvis focuses on implementing perception in the context of robotic eye-to-hand coordination. The authors show an integration of different novel concepts to perform scene analysis, hand-eye coordination and object manipulation for robotic tasks. The underlying architectural considerations rely on the usage of the neuro-fuzzy systems in the formation of scene analysis and object recognition. Next, Ghosh and Petkov, in their study, deal with the cognitive evaluation of contour based shape descriptors in image processing. In the sequel, first-order logical networks discussed by Kijsirikul and Lerdlamnaochai offer an interesting insight into the problems of logic-based neurocomputing. The proposed method, called First-Order Logical Neural Network (FOLNN), leads to hybrid structures that combine standard feed-forward neural networks and mechanisms of inductive learning. The study by Sehgal, Gondal, and Dooley is focused on an important and timely issue of handling multiple missing values of genetic expression in problems of analysis and classification of microarray data. The authors offer a mechanism of a k-ranked covariance-based missing value imputation and demonstrate its superiority over the k-nearest neighbor method.

Bankruptcy prediction with neural logic networks by means of grammar-guided genetic programming

The paper demonstrates the efficient use of hybrid intelligent systems for solving the classification problem of bankruptcy. The aim of the study is to obtain classification schemes able to predict business failure. Previous attempts to form efficient classifiers for the same problem using intelligent or statistical techniques are discussed throughout the paper. The application of neural logic networks by means of genetic programming is proposed. This is an advantageous approach enabling the interpretation of the network structure through set of expert rules, which is a desirable feature for field experts. These evolutionary neural logic networks are consisted of an innovative hybrid intelligent methodology, by which evolutionary programming techniques are used for obtaining the best possible topology of a neural logic network. The genetic programming process is guided using a context-free grammar and indirect encoding of the neural logic networks into the genetic programming individuals. Indicative classification results are presented and discussed in detail in terms of both, classification accuracy and solution interpretability.

The construction of a fuzzy inference network by extension of the rule inference network

Fuzzy logic can bring about inappropriate inferences as a result of ignoring some information in the reasoning process. Neural networks are powerful tools for pattern processing, but are not appropriate for the logical reasoning needed to model human knowledge. The use of a neural logic network derived from a modified neural network, however, makes logical reasoning possible. In this paper, we construct a fuzzy inference network by extending the rule–inference network based on an existing neural logic network. The propagation rule used in the existing rule–inference network is modified and applied. In order to determine the belief value of a proposition pertaining to the execution part of the fuzzy rules in a fuzzy inference network, the nodes connected to the proposition to be inferenced should be searched for. The search costs are compared and evaluated through application of sequential and priority searches for all the connected nodes.

An intelligent forward quality enhancement system to achieve product customization

PurposeThis paper proposes an infrastructural framework, involving various emerging technologies, for the development of an agent‐based quality enhancement system with the distinct feature of the ability to cope with the potential quality problems from various customers' requirements.Design/methodology/approachThe proposed system is equipped with the “distributed problem solving” feature which automatically identifies and divides the potential quality problems into sub‐problems and directs straight to the associated agents that are capable of interacting and negotiating with each other to support customer needs. The new feature of this agile quality enhancement system is characterized with the incorporation of the quality mining engine through the capabilities of the online analytical processing, case‐based reasoning, fuzzy logic and artificial neural networks, achieving the optimization of the performance of organizations.FindingsIn this paper, the detailed architecture and the components included in the proposed system are described with a case study to validate its feasibility of application in actual environment.Originality/valueThe proposed system is to enhance customer satisfaction by automating problem solving procedures in all business processes.

An Adaptive Type-2 Fuzzy Neural Controller for Nonlinear Uncertain Systems

This article proposes a new control scheme using type-2 fuzzy neural network (type-2 FNN) and adaptive filter for controlling nonlinear uncertain systems. This type-2 FNN model combines the advantages of type-2 fuzzy logic systems and neural networks. The type-2 FNN system has the ability of universal approximation, that is, identification of nonlinear dynamic systems. We herein adopt it to develop a novel control scheme for nonlinear uncertain systems. The proposed control scheme consists of a PD-type adaptive FNN controller and a pre-filter. The adaptive filter is used to provide better performance under transient response and to treat the problem of disturbance attenuation. The tuning parameters for the filter and the type-2 FNN controller will change according to the learning algorithm. By the Lyapunov stability theorem, the convergence of parameters is given in order to guarantee the stability of nonlinear uncertain systems. The effectiveness of the proposed controller is demonstrated by simulated results.

The Application of Fuzzy Logic and Artificial Neural Networks To Parametric Cost Estimating of Floating offshore Structures

The Application of Fuzzy Logic and Artificial Neural Networks To Parametric Cost Estimating of Floating offshore Structures

An evolutionary system for neural logic networks using genetic programming and indirect encoding

Nowadays, intelligent connectionist systems such as artificial neural networks have been proved very powerful in a wide area of applications. Consequently, the ability to interpret their structure was always a desirable feature for experts. In this field, the neural logic networks (NLN) by their definition are able to represent complex human logic and provide knowledge discovery. However, under contemporary methodologies, the training of these networks may often result in non-comprehensible or poorly designed structures. In this work, we propose an evolutionary system that uses current advances in genetic programming that overcome these drawbacks and produces neural logic networks that can be arbitrarily connected and are easily interpretable into expert rules. To accomplish this task, we guide the genetic programming process using a context-free grammar and we encode indirectly the neural logic networks into the genetic programming individuals. We test the proposed system in two problems of medical diagnosis. Our results are examined both in terms of the solution interpretability that can lead in knowledge discovery, and in terms of the achieved accuracy. We draw conclusions about the effectiveness of the system and we propose further research directions.

Clustering with artificial neural networks and traditional techniques

In this article, two clustering techniques based on neural networks are introduced. The two neural network models are the Harmony theory network (HTN) and the self-organizing logic neural network (SOLNN), both of which are characterized by parallel processing, a distributed architecture, and a large number of nodes. After describing their clustering characteristics and potential, a comparison to classical statistical techniques is performed. This comparison allows the creation of a correspondence between each neural network clustering technique and particular metrics as used by the corresponding statistical methods, which reflect the affinity of the clustered patterns. In particular, the HTN is found to perform the clustering task with an accuracy similar to the best statistical methods, while it is further capable of proposing an optimal number of groups into which the patterns may be clustered. On the other hand, the SOLNN combines a high clustering accuracy with the ability to cluster higher-dimensional patterns without a considerable increase in the processing time. © 2003 Wiley Periodicals, Inc.

A Fuzzy Inference Network Model for Search Strategy Using Neural Logic Network

In this paper, a fuzzy inference network model for search strategy using neural logic network is presented. The model describes search strategy, and neural logic network is used to search. Fuzzy logic can bring about appropriate inference results by ignoring some information in the reasoning process. Neural logic networks are powerful tools for the reasoning process but not appropriate for the logical reasoning. To model human knowledge, besides the reasoning process capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy inference is a fuzzy logical reasoning, we construct a fuzzy inference network model based on the neural logic network, extending the existing rule inference network. And the traditional propagation rule is modified.

Image Recognition by Learning Multi-Valued Logic Neural Network

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.

Neural network identification of high-risk suicide patients.

A history of medically serious suicide attempts (MSSA) has been considered a major risk factor for suicide. Backpropagation (BP) neural networks (NN) successfully detected patient files of patients who had committed MSSA but failed to identify MSSA patients when trained with data collected during face-to-face interviews. To develop an expert support system for the detection of suicide risk in patients with major psychiatric disorders using fuzzy adaptive learning control networks (FALCON) and BP enhanced with fuzzy logic neural networks. We used four types of input sets: (a) the most significant variables as defined by Garson's calculation of trained BP; (b) variables identified by logistic regression; (c) variables considered significant by experienced clinicians; or (d) the variables considered definitive by the computer programmer. In addition, the complete set of 59 input variables was used. The target variable was the existence of prior MSSA. Four training trials were performed with each input set (75% of the data was used for training and 25% for testing). Data was collected from 197 (50 MSSA, 147 non-MSSA) patients hospitalized at Sha'ar Menashe Mental Health Centre. BP enhanced with fuzzy logic achieved the most accurate results with the three variables chosen by the programmer (mean +/- SD; sensitivity=97% +/- 3.4%, specificity=69.2% +/- 6.9%), and FALCON trained with 15 variables chosen by an expert clinician obtained the highest sensitivity and specificity (mean +/- SD; sensitivity=94% +/- 6.9%, specificity=69% +/- 6.9%). A combined system of BP enhanced with fuzzy logic and FALCON may improve the detection rate of MSSA patients during patient interviews. A prospective validation study testing a combined system across 1, 2 and 5-year spans may provide a reliable instrument to aid in the detection of suicide prone psychiatric patients.