Automatic detection of gait events: a case study using inductive learning techniques

One of the problems which occurs in the development of a control system for functional electrical stimulation of the lower limbs is to detect accurately specific events within the gait cycle. We present a method for the classification of phases of the gait cycle using the artificial intelligence technique of inductive learning. Both the terminology of inductive learning and the algorithm used for the analyses are fully explained. Given a set of examples of sensor data from the gait events that are to be delected, the inductive learning algorithm is able to produce a decision tree (or set of rules) which classify the data using a minimum number of sensors. The nature of the redundancy of the sensor set is examined by progressively removing combinations of sensors and noting the effect on both the size of the decision trees produced and their classification accuracy on ‘unseen’ testing data. Since the algorithm is able to calculate which sensors are more important (informative), comparisons with the intuitive appreciation of sensor importance of five researchers in the fields were made, revealing that those sensors which appear intuitively most informative may, in fact, provide the least information. Comparison results with the standard statistical classification technique of linear discriminant analysis are also presented, showing the relative simplicity of the inductively derived rules together with their good classification accuracy. In addition to the control of FES, such techniques are also applicable to automatic gait analysis and the construction of expert systems for diagnosis of gait pathologies.     

Rule-based production planning in flexible manufacturing systems

Production planning in flexible manufacturing may require the solution of a large-scale discrete-event dynamic stochastic optimization problem, due to the complexity of the system to be optimized, and to the occurrence of discrete events (new orders and hard failures). The production planning problem is here approached for a multistage multipart-type manufacturing shop, where each work cell can share its processing time among the different types of parts. The solution of this problem is obtained by an open-loop-feedback control strategy, updated each time a new event occurs. At each event time, two coupled problems are solved: 1) a product-order scheduling problem, conditioned on estimated values of the production capacities of all component work cells; and 2) a production-capacity planning problem, conditioned on predefined sequences of the product orders to be processed. In particular, the article aims at defining a production planning procedure that integrates both analytical tools, derived from mathematical programming, and knowledge-based rules, coming from experience. The objective is to formulate a hybrid (knowledge-based/analytical) planning architecture, and to analyze its use for multicell multipart-type manufacturing systems.     

An online self-organizing scheme for Parsimonious and Accurate Fuzzy Neural Networks

In this paper, an online self-organizing scheme for Parsimonious and Accurate Fuzzy Neural Networks (PAFNN), and a novel structure learning algorithm incorporating a pruning strategy into novel growth criteria are presented. The proposed growing procedure without pruning not only simplifies the online learning process but also facilitates the formation of a more parsimonious fuzzy neural network. By virtue of optimal parameter identification, high performance and accuracy can be obtained. The learning phase of the PAFNN involves two stages, namely structure learning and parameter learning. In structure learning, the PAFNN starts with no hidden neurons and parsimoniously generates new hidden units according to the proposed growth criteria as learning proceeds. In parameter learning, parameters in premises and consequents of fuzzy rules, regardless of whether they are newly created or already in existence, are updated by the extended Kalman filter (EKF) method and the linear least squares (LLS) algorithm, respectively. This parameter adjustment paradigm enables optimization of parameters in each learning epoch so that high performance can be achieved. The effectiveness and superiority of the PAFNN paradigm are demonstrated by comparing the proposed method with state-of-the-art methods. Simulation results on various benchmark problems in the areas of function approximation, nonlinear dynamic system identification and chaotic time-series prediction demonstrate that the proposed PAFNN algorithm can achieve more parsimonious network structure, higher approximation accuracy and better generalization simultaneously.     

A distributed knowledge-based approach to flexible automation: The contract net framework

This article applied distributed artificial intelligence to the real-time planning and control of flexible manufacturing systems (FMS) consisting of asynchronous manufacturing cells. A knowledge-based approach is used to determine the course of action, resource sharing, and processor assignments. Within each cell there is an embedded automatic planning system that executes dynamic scheduling and supervises manufacturing operations. Because of the decentralized control, real-time task assignments are carried out by a negotiation process among cell hosts. The negotiation process is modeled by augmented Petri nets —the combination of production rules and Petri nets—and is excuted by a distributed, rule-based algorithm.     

Reconstructing muscle activation during normal walking: a comparison of symbolic and connectionist machine learning techniques

One symbolic (rule-based inductive learning) and one connectionist (neural network) machine learning technique were used to reconstruct muscle activation patterns from kinematic data measured during normal human walking at several speeds. The activation patterns (or desired outputs) consisted of surface electromyographic (EMG) signals from the semitendinosus and vastus medialis muscles. The inputs consisted of flexion and extension angles measured at the hip and knee of the ipsilateral leg, their first and second derivatives, and bilateral foot contact information. The training set consisted of data from six trials, at two different speeds. The testing set consisted of data from two additional trials (one at each speed), which were not in the training set. It was possible to reconstruct the muscular activation at both speeds using both techniques. Timing of the reconstructed signals was accurate. The integrated value of the activation bursts was less accurate. The neural network gave a continuous output, whereas the rule-based inductive learning rule tree gave a quantised activation level. The advantage of rule-based inductive learning was that the rules used were both explicit and comprehensible, whilst the rules used by the neural network were implicit within its structure and not easily comprehended. The neural network was able to reconstruct the activation patterns of both muscles from one network, whereas two separate rule sets were needed for the rule-based technique. It is concluded that machine learning techniques, in comparison to explicit inverse muscular skeletal models, show good promise in modelling nearly cyclic movements such as locomotion at varying walking speeds. However, they do not provide insight into the biomechanics of the system, because they are not based on the biomechanical structure of the system.     

A pattern-directed approach to flexible manufacturing: A framework for intelligent scheduling,learning, and control

The planning, scheduling, and control of manufacturing systems can all be viewed as problem-solving activities. In flexible manufacturing systems (FMSs), the computer program carrying out these problem-solving activities must additionally be able to handle the shorter lead time, the flexibility of job routing, the multiprocessing environment, the dynamic changing states, and the versatility of machines. This article presents an artificial intelligence (AI) method to perform manufacturing problem solving. Since the method is driven by manufacturing scenarios represented by symbolic patterns, it is referred to as pattern-directed. The method is based on three AI techniques. The first is the pattern-directed inference technique to capture the dynamic nature of FMSs. The second is the nonlinear planning technique to construct schedules and assign resources. The third is the inductive learning method to generate the pattern-directed heuristics. This article focuses on solving the FMS scheduling problem. In addition, this article reports the computation results to evaluate the utility of various heuristic functions, to identify important design parameters, and to analyze the resulting computational performance in using the pattern-directed approach for manufacturing problem-solving tasks such as scheduling.     

Experimental investigation of an FMS due-date scheduling problem: Evaluation of machine and AGV scheduling rules

Although extensive research has been conducted to solve design and operational problems of automated manufacturing systems, many of the problems still remain unsolved. This article investigates the scheduling problems of flexible manufacturing systems (FMSs). Specifically, the relative performances of machine and automated guided vehicle (AGV) scheduling rules are analyzed against various due-date criteria. First, the relevant literature is briefly reviewed, and then the rules are tested under different experimental conditions by using a simulation model of an FMS. The sensitivity to AGV workload, buffer capacity, and processing-time distribution is also investigated to assess the robustness of the scheduling rules.     

CORAL: Building up QSAR models for the chromosome aberration test

A high level of chromosomal aberrations in peripheral blood lymphocytes may be an early marker of cancer risk, but data on risk of specific cancers and types of chromosomal aberrations are limited. Consequently, the development of predictive models for chromosomal aberrations test is important task. Majority of models for chromosomal aberrations test are so-called knowledge-based rules system. The CORAL software (http://www.insilico.eu/coral, abbreviation of “CORrelation And Logic”) is an alternative for knowledge-based rules system. In contrast to knowledge-based rules system, the CORAL software gives possibility to estimate the influence upon the predictive potential of a model of different molecular alerts as well as different splits into the training set and validation set. This possibility is not available for the approaches based on the knowledge-based rules system. Quantitative Structure–Activity Relationships (QSAR) for chromosome aberration test are established for five random splits into the training, calibration, and validation sets. The QSAR approach is based on representation of the molecular structure by simplified molecular input-line entry system (SMILES) without data on physicochemical and/or biochemical parameters. In spite of this limitation, the statistical quality of these models is quite good.     

A DSS for job scheduling under process interruptions

The primary objective of this research is to solve the job-shop scheduling problems (JSSPs), by minimizing the makespan, with and without process interruptions. In this paper, we first developed a genetic algorithm for solving JSSPs, and then improved the algorithm by integrating it with two simple priority rules and a hybrid rule. The performance of the developed algorithm was tested by solving 40 benchmark problems and comparing their results with that of a number of well-known algorithms. In addition, we have studied the job-shop scheduling under process interruptions such as machine unavailability and breakdown. For convenience of implementation, we have developed a decision support system (DSS). In the DSS, we built a graphical user interface for user friendly data inputs, model choices, and output generation. An overview of the DSS and an analysis of the experimental results are provided. The incorporation of priority rules, and a hybrid rule, not only improves the solutions but also reduces the overall computational time. The experimental results show that when the machine unavailability information is known in advance, the effect on the schedule is very little compared to the sudden machine breakdown scenario.     

Neuro-fuzzy decision trees

Fuzzy decision trees are powerful, top-down, hierarchical search methodology to extract human interpretable classification rules. However, they are often criticized to result in poor learning accuracy. In this paper, we propose Neuro-Fuzzy Decision Trees (N-FDTs); a fuzzy decision tree structure with neural like parameter adaptation strategy. In the forward cycle, we construct fuzzy decision trees using any of the standard induction algorithms like fuzzy ID3. In the feedback cycle, parameters of fuzzy decision trees have been adapted using stochastic gradient descent algorithm by traversing back from leaf to root nodes. With this strategy, during the parameter adaptation stage, we keep the hierarchical structure of fuzzy decision trees intact. The proposed approach of applying backpropagation algorithm directly on the structure of fuzzy decision trees improves its learning accuracy without compromising the comprehensibility (interpretability). The proposed methodology has been validated using computational experiments on real-world datasets.     

A Mixture of Delta-Rules Approximation to Bayesian Inference in Change-Point Problems

Error-driven learning rules have received considerable attention because of their close relationships to both optimal theory and neurobiological mechanisms. However, basic forms of these rules are effective under only a restricted set of conditions in which the environment is stable. Recent studies have defined optimal solutions to learning problems in more general, potentially unstable, environments, but the relevance of these complex mathematical solutions to how the brain solves these problems remains unclear. Here, we show that one such Bayesian solution can be approximated by a computationally straightforward mixture of simple error-driven ‘Delta’ rules. This simpler model can make effective inferences in a dynamic environment and matches human performance on a predictive-inference task using a mixture of a small number of Delta rules. This model represents an important conceptual advance in our understanding of how the brain can use relatively simple computations to make nearly optimal inferences in a dynamic world.     

Sensorimotor Learning Biases Choice Behavior: A Learning Neural Field Model for Decision Making

According to a prominent view of sensorimotor processing in primates, selection and specification of possible actions are not sequential operations. Rather, a decision for an action emerges from competition between different movement plans, which are specified and selected in parallel. For action choices which are based on ambiguous sensory input, the frontoparietal sensorimotor areas are considered part of the common underlying neural substrate for selection and specification of action. These areas have been shown capable of encoding alternative spatial motor goals in parallel during movement planning, and show signatures of competitive value-based selection among these goals. Since the same network is also involved in learning sensorimotor associations, competitive action selection (decision making) should not only be driven by the sensory evidence and expected reward in favor of either action, but also by the subject''s learning history of different sensorimotor associations. Previous computational models of competitive neural decision making used predefined associations between sensory input and corresponding motor output. Such hard-wiring does not allow modeling of how decisions are influenced by sensorimotor learning or by changing reward contingencies. We present a dynamic neural field model which learns arbitrary sensorimotor associations with a reward-driven Hebbian learning algorithm. We show that the model accurately simulates the dynamics of action selection with different reward contingencies, as observed in monkey cortical recordings, and that it correctly predicted the pattern of choice errors in a control experiment. With our adaptive model we demonstrate how network plasticity, which is required for association learning and adaptation to new reward contingencies, can influence choice behavior. The field model provides an integrated and dynamic account for the operations of sensorimotor integration, working memory and action selection required for decision making in ambiguous choice situations.     

Controlling flexible manufacturing systems based on a dynamic selection of the appropriate operational criteria and scheduling policy

This study presents the development of a multi-criteria control methodology for flexible manufacturing systems (FMSs). The control methodology is based on a two-tier decision making mechanism. The first tier is designed to select a dominant decision criterion and a relevant scheduling rule set using a rule-based algorithm. In the second tier, using a look-ahead multi-pass simulation, a scheduling rule that best advances the selected criterion is determined. The decision making mechanism was integrated with the shop floor control module that comprises a real-time simulation model at the top control level and RapidCIM methodology at the low equipment control level. A factorial experiment was designed to analyze and evaluate the two-tier decision making mechanism and the effects that the main design parameters have on the system’s performance. Next, the proposed control methodology was compared to a selected group of scheduling rules/policies using DEA. The results demonstrated the superiority of the suggested control methodology as well as its capacity to cope with a fast changing environment.     

An integrated rule- and case-based approach to AIDS initial assessment

The traditional approach to the development of knowledge-based systems (KBS) has been rule-based, where heuristic knowledge is encoded in a set of production rules. A rule-based reasoning (RBR) system needs a well constructed domain theory as its reasoning basis, and it does not make substantial use of the knowledge embedded in previous cases. An RBR system performs relatively well in a knowledge-rich application environment. Although its capability may be limited when previous experiences are not a good representation of the whole population, a case-based reasoning (CBR) system is capable of using past experiences as problem solving tools, therefore, it is appropriate for an experience-rich domain. In recent years, both RBR and CBR have emerged as important and complementary reasoning methodologies in artificial intelligence. For problem solving in AIDS intervention and prevention, it is useful to integrate RBR and CBR. In this paper, a hybrid KBS which integrates a deductive RBR system and an inductive CRB system is proposed to assess AIDS-risky behaviors.     

Convergence analysis of cascade error projection--an efficient learning algorithm for hardware implementation

In this paper, we present a mathematical foundation, including a convergence analysis, for cascading architecture neural network. Our analysis also shows that the convergence of the cascade architecture neural network is assured because it satisfies Liapunov criteria, in an added hidden unit domain rather than in the time domain. From this analysis, a mathematical foundation for the cascade correlation learning algorithm can be found. Furthermore, it becomes apparent that the cascade correlation scheme is a special case from mathematical analysis in which an efficient hardware learning algorithm called Cascade Error Projection(CEP) is proposed. The CEP provides efficient learning in hardware and it is faster to train, because part of the weights are deterministically obtained, and the learning of the remaining weights from the inputs to the hidden unit is performed as a single-layer perceptron learning with previously determined weights kept frozen. In addition, one can start out with zero weight values (rather than random finite weight values) when the learning of each layer is commenced. Further, unlike cascade correlation algorithm (where a pool of candidate hidden units is added), only a single hidden unit is added at a time. Therefore, the simplicity in hardware implementation is also achieved. Finally, 5- to 8-bit parity and chaotic time series prediction problems are investigated; the simulation results demonstrate that 4-bit or more weight quantization is sufficient for learning neural network using CEP. In addition, it is demonstrated that this technique is able to compensate for less bit weight resolution by incorporating additional hidden units. However, generation result may suffer somewhat with lower bit weight quantization.     

Predicting species distributions for conservation decisions

Species distribution models (SDMs) are increasingly proposed to support conservation decision making. However, evidence of SDMs supporting solutions for on‐ground conservation problems is still scarce in the scientific literature. Here, we show that successful examples exist but are still largely hidden in the grey literature, and thus less accessible for analysis and learning. Furthermore, the decision framework within which SDMs are used is rarely made explicit. Using case studies from biological invasions, identification of critical habitats, reserve selection and translocation of endangered species, we propose that SDMs may be tailored to suit a range of decision‐making contexts when used within a structured and transparent decision‐making process. To construct appropriate SDMs to more effectively guide conservation actions, modellers need to better understand the decision process, and decision makers need to provide feedback to modellers regarding the actual use of SDMs to support conservation decisions. This could be facilitated by individuals or institutions playing the role of ‘translators’ between modellers and decision makers. We encourage species distribution modellers to get involved in real decision‐making processes that will benefit from their technical input; this strategy has the potential to better bridge theory and practice, and contribute to improve both scientific knowledge and conservation outcomes.     

Constructing a fuzzy rule-based system using the ILFN network and Genetic Algorithm.

In this paper, a method for automatic construction of a fuzzy rule-based system from numerical data using the Incremental Learning Fuzzy Neural (ILFN) network and the Genetic Algorithm is presented. The ILFN network was developed for pattern classification applications. The ILFN network, which employed fuzzy sets and neural network theory, equips with a fast, one-pass, on-line, and incremental learning algorithm. After trained, the ILFN network stored numerical knowledge in hidden units, which can then be directly interpreted into if then rule bases. However, the rules extracted from the ILFN network are not in an optimized fuzzy linguistic form. In this paper, a knowledge base for fuzzy expert system is extracted from the hidden units of the ILFN classifier. A genetic algorithm is then invoked, in an iterative manner, to reduce number of rules and select only discriminate features from input patterns needed to provide a fuzzy rule-based system. Three computer simulations using a simulated 2-D 3-class data, the well-known Fisher's Iris data set, and the Wisconsin breast cancer data set were performed. The fuzzy rule-based system derived from the proposed method achieved 100% and 97.33% correct classification on the 75 patterns for training set and 75 patterns for test set, respectively. For the Wisconsin breast cancer data set, using 400 patterns for training and 299 patterns for testing, the derived fuzzy rule-based system achieved 99.5% and 98.33% correct classification on the training set and the test set, respectively.     

Active inference and agency: optimal control without cost functions

This paper describes a variational free-energy formulation of (partially observable) Markov decision problems in decision making under uncertainty. We show that optimal control can be cast as active inference. In active inference, both action and posterior beliefs about hidden states minimise a free energy bound on the negative log-likelihood of observed states, under a generative model. In this setting, reward or cost functions are absorbed into prior beliefs about state transitions and terminal states. Effectively, this converts optimal control into a pure inference problem, enabling the application of standard Bayesian filtering techniques. We then consider optimal trajectories that rest on posterior beliefs about hidden states in the future. Crucially, this entails modelling control as a hidden state that endows the generative model with a representation of agency. This leads to a distinction between models with and without inference on hidden control states; namely, agency-free and agency-based models, respectively.     

Classifying Cinnamomums using rough sets classifier based on interval-discretization

Classification, which is the task of assigning objects to one of several predefined categories, is a pervasive problem that encompasses many diverse applications. Decision tree classifier, which is a simple yet widely used classification technique, employs training data to yield decision rules; moreover, it can create thresholds and then split the list of continuous attributes into descrete intervals for handling continuous attributes (Quinlan in Journal of Artificial Intelligence Research 4:77–90, 1996). Rough set theory (Pawlak in International Journal of Computer and Information Sciences 11:341–356, 1982; International Journal of Man-Machine Studies 20:469–483, 1984; Rough sets: theoretical aspects of reasoning about data. Kluwer, Dordrecht, 1991) has been applied to a wide variety of decision analysis problems for the extraction of rules from databases. This paper proposes a hybrid approach that takes advantage of combining decision tree and rough sets classifier and applies it to plant classification. The introduced approach starts with decision tree classifier (C4.5) as preprocessing technique to make interval-discretization, subsequently, and uses rough set method for extracting rules. The proposed approach aims at finding out classification rules via analyzing lamina attributes (leaf stalk, leaf width, leaf length, length/width ratio) of Cinnamomum, which are gathered and measured by plant specialists in the field of Taiwan. A comparison with the widely used algorithms (e.g., decision tree, multilayer perceptrons, naïve Bayes, and rough sets classifier) is carried out to show numerous advantages of the proposed approach. Finally, employing with test data in which species are unknown, results of classification are approved by consulting the relative plant specialists.     

Two-day radial-arm water maze learning and memory task; robust resolution of amyloid-related memory deficits in transgenic mice

The radial arm water maze (RAWM) contains six swim paths (arms) extending out of an open central area, with an escape platform located at the end of one arm (the goal arm). The goal arm location remains constant for a given mouse. On day 1, mice are trained for 15 trials (spaced over 3 h), with trials alternating between visible and hidden platform. On day 2, mice are trained for 15 trials with the hidden platform. Entry into an incorrect arm is scored as an error. The RAWM has the spatial complexity and performance measurement simplicity of the dry radial arm maze combined with the rapid learning and strong motivation observed in the Morris water maze without requiring foot shock or food deprivation as motivating factors. With two sessions each day, 16 mice can be tested over 2 days.