Search results

Control chart pattern recognition is a critical issue in statistical process control, as unnatural patterns on control charts are often associated with specific assignable causes adversely affecting the process. Several researchers have recently applied neural networks to pattern recognition for control charts. However, nearly all studies in this area assume that the in‐control process data in the control charts follow a normal distribution. This assumption contradicts the facts of practical manufacturing situations. This paper investigates how non‐normality affects the performance of neural network based control chart pattern recognition models. Extensive performance evaluation was carried out using simulated data with various non‐normalities. The non‐normality was measured in skewness and kurtosis. Numerical results indicate that the neural network based control chart pattern recognition models still perform well in a non‐normal distribution environment in terms of recognition accuracy and speed.

The purpose of this paper is to analyze how pattern recognition can contribute to the behavioral options of a goal‐oriented system.

A functional approach is used to develop the necessary cybernetic structures of a pattern recognition unit that can store observations as new standards for pattern matching by itself and can later apply them to recognize patterns in incoming sensor data.

Combining such a structure for pattern recognition with a feedback system shows that the resulting system can only deal with known patterns. To deal with novel patterns this structure has to be added to an adaptive system that can develop system‐specific behavior. Such a system has to able to initiate a trial and error process to test new behavior towards new patterns and to evaluate its effect on the highest, existential goal‐values of the system.

A system with a pattern recognition unit that can set new standards for pattern matching by itself is identified as the point of departure where not‐programmable and unpredictable individual behavior starts. Dealing with newly‐recognized pattern requires individual behavioral solutions and a system‐specific evaluation of the achieved results in relation to the highest goal‐values of the system. Here internal “emotional” criteria to select behavior emerge as a cybernetic necessity.

The paper is the third in a series of three on a cybernetic theory distinguishing system capable of pre‐programmed adaptation, system‐specific adaptation and learning. It determines the cybernetic starting point of individual psychology.

The purpose of this paper is to analyze how sequence learning can build on pattern‐recognition systems and how it can contribute to the behavioral options of goal‐oriented systems.

A functional approach is used to develop the necessary cybernetic structures of a subsystem for sequence learning, that can recognize patterns, register patterns occurring repeatedly and connect these to sequences. Based on that it is analyzed how goal‐oriented systems can use information about reoccurring sequences.

A subsystem for sequence learning basically requires pattern recognition and it needs a structure for the directed connection of single standards for pattern matching to standards for sequences, given that it can learn both new patterns and new sequences. Such a subsystem for sequence learning may recognize a certain pattern and with that the end of a certain sequence. So it may deliver more than one output signal at a point in time, and therefore needs additionally a subsystem for directing attention.

The paper analyses the principles of an “associative” way of connecting standards for pattern matching to standards for sequences. Also it shows the cybernetic necessity of an attention directing system that has to decide how to deal with the multiple outputs of a subsystem for sequence learning, i.e. to decide to act either towards a pattern or a whole sequence.

The paper investigates basic mechanisms of sequence learning and its contribution to goal‐oriented behavior. Also, it lays the base for an analysis of attention directing systems and anticipatory systems.

The purpose of the paper is to analyze cybernetic necessities of output‐side attention directing systems, i.e. how systems can decide to act towards one of various inputs.

Complex pattern recognition and sequence learning systems may recognize more than one pattern and deliver more than one output at a point in time. Therefore, they require an output‐side attention directing system to decide to act towards just one pattern. The necessary cybernetic structures of such systems are analyzed using a functional approach.

An output‐side attention directing system has to evaluate the effect of current observations (patterns, sequences, etc.) on highest level goal‐values (in a living system these are existential goal‐values like a body temperature or energy supply). Measure of this effect is the degree of goal‐approximation towards these goal‐values. This measure can either be preprogrammed for some patterns or sequences, or has to be determined in trial and error processes for new patterns or sequences learned by the system.

The paper shows the cybernetic necessities of the development of the “know how” of sequence learning systems in time, starting with default behavior, via learning new patterns and sequences, and trial and error to develop goal‐orientated actions towards them, until finally the achieved results enable experience based directing of attention.

The paper shows basic cybernetic structures and functions for output‐side attention directing systems required for all complex pattern recognition and sequence learning systems.

As most existing computer‐aided design systems do not provide part feature information which is essential for process planning, automatic part feature recognition systems serve as an important link between Computer Aided Design (CAD) and Computer Aided Process Planning (CAPP). Attempts to provide a structural framework for understanding various issues related to part feature recognition. Reviews previous work in the field of part feature recognition and classifies known feature recognition systems for the sake of updating information and future research. Briefly introduces about 12 systems. Studies 31 systems and lists them in the Appendix based on 60 references. Comments on future research directions.

This paper aims to conceptualize two patterns of user recognition mechanisms and two kinds of user contribution behavior in enterprise-hosted online product innovation community and explain their relationships between user recognition mechanisms and user contribution behavior of online product innovation community.

A Chinese enterprise-hosted online innovation community and an American enterprise-hosted online innovation community are selected as research objects. Four Logit models are developed and some hypotheses are supposed from the perspective of prosocial behavior theory. Objective user data with three months from two online product innovation communities are collected to test with Logit regression analysis.

Findings show that there are obvious correlations between user recognition mechanisms and user contribution behavior, and there is also an obvious difference in community user activity level between the quantity-based user recognition mechanism community and the quality-based user recognition mechanism community. More specifically, in the online product innovation community with quantity-based recognition mechanism, both variables of peer recognition and community image motivation significantly affect user proactive contribution behavior. In the online product innovation community with quality-based recognition mechanism, the variable of peer recognition significantly affects both user proactive contribution behavior and user responsive contribution behavior; the variable of community image motivation significantly affects both user proactive contribution behavior and user responsive contribution behavior.

Although it is voluntary, online user voluntary contribution behavior still need to be presented, recognized and affirmed by community. For enterprise-hosted online community managers, they should pay more attention to design the reasonable online community user recognition mechanism with the coexistence of quantity and quality.

The theoretical contribution in this study is to enrich the existing research theme about enterprise-hosted online product innovation community. First, it conceptualizes two patterns of user recognition mechanisms. Second, it regards the variable of user contribution behavior as the co-existence of proactive contribution and responsive contribution. Third, from the perspective of prosocial behavior theory, it is an important supplement to explain the mechanism of user contribution behavior in enterprise-hosted online product innovation community. Fourth, it deepens the overall understanding of the relationship between user recognition mechanism and user contribution behavior. This study provides theoretical guidance for enterprises how to design reasonable and efficient online product innovation community platform. The theoretical contribution in this study is to enrich the existing research theme about enterprise-hosted online product innovation community. First, it conceptualizes two patterns of user recognition mechanisms. Second, it regards the variable of user contribution behavior as the co-existence of proactive contribution and responsive contribution. Third, from the perspective of prosocial behavior theory, it is an important supplement to explain the mechanism of user contribution behavior in enterprise-hosted online product innovation community. Fourth, it deepens the overall understanding of the relationship between user recognition mechanism and user contribution behavior. This study provides theoretical guidance for enterprises how to design reasonable and efficient online product innovation community platform.

The concept of a fuzzy language is applied to pattern recognition using geometric figures, chromosomes and leukocytes as illustrative examples. For chromosomes, an algorithm for classifying a chromosome image as an “approximate median chromosome,” “approximate sub‐median chromosome” or “approximate acrocentric chromosome” is presented. For leukocytes, an equal‐perimeter circular shape measure and an equal‐area circular shape measure are proposed, and various properties, results, and the relationship between these two measures are presented. Quantitative measures of other visual concepts such as elongated, spiculed, indented, slightly indented and deeply indented arc also presented and illustrated by examples. The results obtained in this paper may have useful applications in pattern recognition, cybernetics and fuzzy systems.

The purpose of this paper is to analyze the main differences in the cybernetic structures necessary for elementary anticipation, understood as anticipation of the repetition of one known pattern, and complex anticipation, understood as anticipation of the repetition of known sequences of patterns.

A functional cybernetic approach is used to develop the necessary additions to an elementary anticipatory system, so that it can provide standards for anticipated sequences containing seven single patterns or “chunks”.

A subsystem for the anticipation of sequences is developed that is able to: identify the beginning of known sequences; search for different known sequences containing that beginning; and decide to use later patterns of such a sequence as standards for anticipated patterns. Deciding to actually use such patterns for anticipation requires an additional subsystem to switch between the feedback pattern recognition and the feedforward anticipation mode.

The paper shows how complex anticipation can be developed from elementary forms by adding highly parallel structures that apply the same underlying principles; and it emphasizes epistemological demands for the structure and the data organization that have to be fulfilled, so that anticipation of the repetition of sequences becomes possible.

The paper illustrates the complexity of the anticipation of sequences and it provides the base to analyze more complex forms of specifically human thinking.

The purpose of this paper is to obtain evidence concerning the basic dimensions included in cognitive prototypes pertaining to opportunity recognition and decision to launch a new venture; identifying the underlying dimensions of both prototypes – the cognitive frameworks current or nascent entrepreneurs employ in performing these important tasks.

The bi-dimensional models were tested in a sample of 284 founder entrepreneurs, using a 48-item questionnaire. It was used as structural equation confirmatory factor analysis to compare fit indices of uni-dimensional second-order and third-order bi-dimensional models of business opportunity and decision to launch a venture.

Results support the bi-dimensional models and offer support that both prototypes include two basic dimensions. For the business opportunity prototype these are viability and distinctiveness while for the decision to launch a new venture, the basic dimensions are feasibility and motivational aspects.

These results help to further clarify the nature of the cognitive frameworks individuals use to identify potential opportunities and reach an initial decision about whether to pursue their development. Uncovering the cognitive functioning of opportunity recognition and decision to exploit it, allow individuals to recognize opportunities easier and successfully; and to make more accurate and effective decisions.

Knowing the basic dimensions of opportunity and decision-making prototypes contributes to develop effective skills with respect to business opportunity recognition among students enrolled in entrepreneurship programs. These surveys can be used for self-assessment and also for investors, tutors, and entrepreneurship agents in order to help evaluate features of business opportunities and decision to launch a venture.

This study embraces a conceptual contribution, proposing a different model of the business opportunity and decision to exploit prototypes, and it extends Baron and Ensley (2006) previous work, to another important step in the entrepreneurial process – the decision to develop an identified opportunity through the launch of a new venture.

The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.

Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. Object recognition is a type of pattern recognition. Object recognition is widely used in the manufacturing industry for the purpose of inspection. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. In this work, recognition of objects manufactured in mechanical industry is considered. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such mechanical part. Red, green and blue RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

One important finding is that there is not any considerable change in the network performances after 500 iterations. It has been found that for data smaller network structure, smaller learning rate and momentum are required. The relative sample size also has a considerable effect on the performance of the classifier. Further studies suggest that classification accuracy is achieved with the confusion matrix of the data used. Hence, with these results the proposed system can be used efficiently for more objects. Depending upon the manufacturing product and process used, the dimension verification and surface roughness may be integrated with proposed technique to develop a comprehensive vision system. The proposed technique is also highly suitable for web inspections, which do not require dimension and roughness measurement and where desired accuracy is to be achieved at a given speed. In general, most recognition problems provide identity of object with pose estimation. Therefore, the proposed recognition (pose estimation) approach may be integrated with inspection stage.

This paper considers the problem of recognizing and classifying the objects of such mechanical part. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. ANN is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.