Search results

Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association.

This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations.

This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends.

This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources.

The purpose of this paper is to outline an integrative, high-level, neurocomputational theory of brain function based on temporal codes, neural timing nets, and active regeneration of temporal patterns of spikes within recurrent neural circuits that provides a time-domain alternative to connectionist approaches.

This conceptual-theoretical paper draws from cybernetics, theoretical biology, neurophysiology, integrative and computational neuroscience, psychology, and consciousness studies.

The high-level functional organization of the brain involves adaptive cybernetic, goal-seeking, switching, and steering mechanisms embedded in percept-action-environment loops. The cerebral cortex is conceived as a network of reciprocally connected, re-entrant loops within which circulate neuronal signals that build up, decay, and/or actively regenerate. The basic signals themselves are temporal patterns of spikes (temporal codes), held in the spike correlation mass-statistics of both local and global neuronal ensembles. Complex temporal codes afford multidimensional vectorial representations, multiplexing of multiple signals in spike trains, broadcast strategies of neural coordination, and mutually reinforcing, autopoiesis-like dynamics. Our working hypothesis is that complex temporal codes form multidimensional vectorial representations that interact with each other such that a few basic processes and operations may account for the vast majority of both low- and high-level neural informational functions. These operational primitives include mutual amplification/inhibition of temporal pattern vectors, extraction of common signal dimensions, formation of neural assemblies that generate new temporal pattern primitive “tags” from meaningful, recurring combinations of features (perceptual symbols), active regeneration of temporal patterns, content-addressable temporal pattern memory, and long-term storage and retrieval of temporal patterns via a common synaptic and/or molecular mechanism. The result is a relatively simplified, signal-centric view of the brain that utilizes universal coding schemes and pattern-resonance processing operations. In neurophenomenal terms, waking consciousness requires regeneration and build up of temporal pattern signals in global loops, whose form determines the contents of conscious experience at any moment.

Understanding how brains work as informational engines has manifold long-reaching practical implications for design of autonomous, adaptive robotic systems. By proposing how new concepts might arise in brains, the theory bears potential implications for constructivist theories of mind, i.e. how observer-actors interacting with one another can self-organize and complexify.

The theory is highly original and heterodox in its neural coding and neurocomputational assumptions. By providing a possible alternative to standard connectionist theory of brain function, it expands the scope of thinking about how brains might work as informational systems.

We know a good deal today about how our brains construct emotions. The new fields of interpersonal neurobiology and affective neuroscience are challenging many of our conventional understandings, particularly the notion that thinking and feeling are separate operations and that it is the teacher's primary task to engage students in the former. This chapter addresses some of the findings of recent research on basic emotion command systems, emotional style, neural resonance and neuroplasticity, arguing that we can no longer ignore the evidence that our students’ cognition, emotion and bodily health are fundamentally connected. The arguments for a holistic approach to education are exceedingly robust and have neuropsychological research findings to support them.

The purpose of this research is to illustrate the use of artificial neural network (ANN) and data‐mining (DM) technologies as a good approach for satisfying the requirements of library users.

This research presents the Intelligent Library Materials Recommendations System (ILMRS) which uses the adaptive resonance theory (ART) network to distribute readers into different clusters according to their personal background. When clusters of related personal background have been established, the Apriori algorithm is used to discover the suitable materials in which readers are interested and which they may need.

The investigation results indicate that the ART and Apriori mining techniques can be used to improve the accuracy of the recommendations for reading materials in the library. Moreover, readers can be divided by means of demographic variables into three segments. Finally, the questionnaire survey proved that the proposed recommender system will be a suitable approach for stimulating the readers' motivation and interest. Research limitations/implications – This research is limited by its datasets from a digital library of a university in Taiwan, and it is applied by ART and Apriori mining techniques to recommend materials of readers.

Today, digital information is becoming ever more popular. The huge quantity and the diversity of digital information are its main features. Therefore, readers are interested in obtaining useful information in an efficient manner. In this research, a digital library can use this approach to anticipate a reader's needs in advance based on the mining results.

In treating both sewage and storm runoff, wastewater treatment plants are important to maintaining a healthy environment. If the plant operations managers do not respond correctly to plant conditions, environmental damage resulting in the deterioration of human health may be the result. Unfortunately, there are no formal models to help these managers; they rely upon their own intuition to manage the plants. The purpose of this paper is to investigate the effectiveness of various models, originally used for manufacturing, to detect process conditions in wastewater treatment facilities. We compare and contrast the performance of five statistical models and three neural network architectures. The data used in the research is 527 daily measurements of 38 sensor readings of the process state variables of an urban wastewater treatment plant.

We describe an intelligent video categorization engine (IVCE) that uses the learning capability of artificial neural networks (ANNs) to classify suitably preprocessed video segments into a predefined number of semantically meaningful events (categories).

We provide a survey of existing techniques that have been proposed, either directly or indirectly, towards achieving intelligent video categorization. We also compare the performance of two popular ANNs: Kohonen's self‐organizing map (SOM) and fuzzy adaptive resonance theory (Fuzzy ART). In particular, the ANNs are trained offline to form the necessary knowledge base prior to online categorization.

Experimental results show that accurate categorization can be achieved near instantaneously.

The main limitation of this research is the need for a finite set of predefined categories. Further research should focus on generalization of such techniques.

Machine understanding of video footage has tremendous potential for three reasons. First, it enables interactive broadcast of video. Second, it allows unequal error protection for different video shots/segments during transmission to make better use of limited channel resources. Third, it provides intuitive indexing and retrieval for video‐on‐demand applications.

The purpose of this paper is to identify the efficiency of vibration signals for fault diagnosis system of induction motors.

A fault diagnosis system for induction motors using vibration signals is designed based on pattern recognition. Genetic algorithm is used for feature reduction and neural network tuning.

The usage of genetic algorithm improves the system performance through selecting significant features and optimizing network structure. The efficiency of vibration signals is demonstrated.

Condition monitoring and fault diagnosis for induction motors is one of the main industry maintenance parts. Motors faults usually result in whole production line breakdown. In this paper, one fault diagnosis system is proposed for induction motors based on feature recognition through combination of feature extraction, genetic algorithm and neural network techniques. From the paper, one can learn practically the whole procedure of feature‐based fault diagnosis system and the efficiency of GA and vibration signals for motor fault diagnosis. One real test has been done to validate the system performance. The results indicate that this system is promising for the real application in industry.

The use of genetic algorithm for feature selection and neural network tuning; the choice of vibration analysis for fault diagnosis of induction motor.

To advance marketing research and practice, this study aims to examine the application of the innovative, mobile-applicable neuroimaging method – mobile functional near-infrared spectroscopy (mfNIRS) – in the field of marketing research, providing comprehensive guidelines and practical recommendations.

A general review and investigation of when and how to use mfNIRS in business-to-consumer and business-to-business marketing settings is used to illustrate the utility of mfNIRS.

The research findings help prospective marketing and consumer neuroscience researchers to structure mfNIRS experiments, perform the analysis and interpret the obtained mfNIRS data.

The application of mfNIRS offers opportunities for marketing research that allow the exploration of neural processes and associated behaviour of customers in naturalistic settings.

The application of mfNIRS as a neuroimaging method enables the investigation of unconscious neural processes that control customer behaviour and can act as process variables for companies.

This is one of the first studies to provide comprehensive guidelines and applied practical recommendations concerning when and how to apply mfNIRS in marketing research.

Fuzziology explores the fuzziness inherent in what we know about ourselves and our experience, about our thoughts and feelings, drives for understanding and urges to create. By studying the fuzziness – its nature, sources, causes and factors affecting its dynamics, we are able to transcend the limitations, which it constantly puts on the processes of our understanding and knowing. The basic postulate and paradox of fuzziology are formulated together with its main principles, logical tools and theorems. The link between Socrates' maieutic inquiry, the ancient Vedic wisdom and fuzziology has helped us to reveal the significance of its central maxim: “Do not reject anything, but do not remain with anything either; go beyond!”