Minghong Geng lists you as their PhD advisor. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeStudents and postdocs2
- Seng Khoon TheFrom a thesis record ↗
- From a thesis record ↗
Works290 from public data
- Hierarchical Reinforcement Learning461
A survey of the diverse HRL approaches concerning the challenges of learning hierarchical policies, subtask discovery, transfer learning, and multi-agent learning using HRL is presented according to a novel taxonomy of the approaches.
- A fast pruned-extreme learning machine for classification problem368
The proposed pruned- ELM (P-ELM) algorithm is described as a systematic and automated approach for designing ELM classifier network that leads to compact network classifiers that generate fast response and robust prediction accuracy on unseen data, comparing with traditional ELM and other popular machine learning approaches.
- Text Mining: The state of the art and the challenges358
A text mining framework consisting of two components: Text refining that transforms unstructured text documents into an intermediate form; and knowledge distillation that deduces patterns or knowledge from the intermediate form is presented.
- 209
- Rule Extraction: From Neural Architecture to Symbolic Representation170
This paper shows how knowledge, in the form of fuzzy rules, can be derived from a supervised learning neural network called fuzzy ARTMAP.
- 141
- CRRN: Multi-scale Guided Concurrent Reflection Removal Network137
This paper proposes the Concurrent Reflection Removal Network (CRRN), a network that integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes.
- CRCTOL: A semantic‐based domain ontology learning system137
This paper presents a system, known as Concept-Relation-Concept Tuple-based Ontology Learning (CRCTOL), for mining ontologies automatically from domain-specific documents and presents two case studies where CRCTOL is used to build a terrorism domain ontology and a sport event domain ontology.
- 135
- Learning and inferencing in user ontology for personalized Semantic Web search135
The proposed user ontology model with the spreading activation based inferencing procedure has been incorporated into a semantic search engine, called OntoSearch, to provide personalized document retrieval services.
- On Quantitative Evaluation of Clustering Systems133
Clustering refers to the task of partitioning unlabelled data into meaningful groups (clusters) and is a useful approach in data mining processes for identifying hidden patterns and revealing underlying knowledge from large data collections.
- Integrated cognitive architectures: a survey130
A review of six cognitive architectures, namely Soar, ACT-R, ICARUS, BDI, the subsumption architecture and CLARION, pointing to promising directions towards generic and scalable architectures with close analogy to human brains.
- Adaptive resonance associative map124
Associative recall experiments on two pattern sets show that, besides the advantages of fast learning, guaranteed perfect storage, and full memory capacity, ARAM produces a stronger noise immunity than Bidirectional Associative Memory (BAM).
- Memes as building blocks: a case study on evolutionary optimization + transfer learning for routing problems121
The proposed approach is composed of four culture-inspired operators, namely, Learning, Selection, Variation and Imitation, which serves to identify the high quality knowledge that shall replicate and transmit to future search, while the variation operator injects new innovations into the learned knowledge.
- 118
- 114
- Modelling situation awareness for Context-aware Decision Support113
This paper presents a Context-aware Decision Support (CaDS) system, which consists of a situation model for shared situation awareness modelling and a group of entity agents, one for each individual user, for focused and customized decision support.
- 109
- Intelligence Through Interaction: Towards a Unified Theory for Learning106
A learning architecture within which a universal adaptation mechanism unifies a rich set of traditionally distinct learning paradigms, including learning by matching,learning by association, learning by instruction, and learning by reinforcement is presented.
- 100
- 100
- 95
- 79
- 77
- 76
- McDPC: multi-center density peak clustering75
This work proposes a novel clustering algorithm based on a hierarchical approach, named multi-center density peak clustering (McDPC), which achieves promising performance on both synthetic and real-world datasets and is benchmarked against other state-of-the-art clustering algorithms.
- REDPC: A residual error-based density peak clustering algorithm75
This paper proposes a residual error-based density peak clustering algorithm named REDPC, which adopts the residual error computation to measure the local density within a neighbourhood region and shows that REDPC performs better than DPC and other algorithms.
- Topic Detection, Tracking, and Trend Analysis Using Self-Organizing Neural Networks72
This work addresses the problem of Topic Detection and Tracking and subsequently detecting trends from a stream of text documents and proposes an incremental clustering algorithm that enables discovering interesting trends that are deducible only from reading all relevant documents.
- A Comparative Study on Chinese Text Categorization Methods.68
Comparison of three machine learning methods on Chinese text categorization reveals that all three methods produce satisfactory performance on the test corpus while ARAM exhibits a marginally better generalization capability, especially from relatively small and noisy training sets.
- Creating Human-like Autonomous Players in Real-time First Person Shooter Computer Games61
This paper illustrates how to create a software agent by employing FALCON, a self-organizing neural network that performs reinforcement learning, to play a well-known first person shooter computer game known as Unreal Tournament 2004, where the agent bot participated in the 2K Bot Prize competition.
- 61
- 59
- Explaining inferences in Bayesian networks58
The proposed Explaining BN Inferences (EBI) procedure for explaining how variables interact to reach conclusions generates high quality, concise and comprehensible explanations for BN inferences, in particular the underlying compensation mechanism that enables BN to outperform alternative prediction systems, such as decision tree.
- 55
- 55
- 50
- Self-Organizing Neural Networks Integrating Domain Knowledge and Reinforcement Learning50
This paper shows how self-organizing neural networks designed for online and incremental adaptation can integrate domain knowledge and RL, and proposes a vigilance adaptation and greedy exploitation strategy to maximize exploitation of the inserted domain knowledge while retaining the plasticity of learning and using new knowledge.
- 50
- OntoSearch: a full-text search engine for the semantic web50
The experimental results support the efficacy of the OntoSearch system by using domain ontology and user ontology for enhanced search performance.
- 48
- 47
- 46
- Knowledge discovery from texts43
This work defines a novel representation called the Concept Frame Graph (CFG), and proposes a learning algorithm for constructing a CFG knowledge base from text documents and an interactive concept map visualization technique for user-guided knowledge discovery from the knowledge base.
- 42
- 41
- 41
- Self-organizing neural networks for universal learning and multimodal memory encoding40
This paper shows how a family of biologically-inspired self-organizing neural networks, known as fusion Adaptive Resonance Theory (fusion ART), may provide a viable approach to realizing the learning and memory functions.
- 37
- Active Video Summarization: Customized Summaries via On-line Interaction with the User36
This paper introduces Active Video Summarization (AVS), an interactive approach to gather the user's preferences while creating the summary, and introduces a new dataset for customized video summarization (CSumm).
- Direct Code Access in Self-Organizing Neural Networks for Reinforcement Learning.36
This paper presents a direct code access procedure whereby TD-FALCON conducts instantaneous searches for cognitive nodes that match with the current states and at the same time providemaximal reward values to produce comparable performance with the original TD- FALCON while improving significantly in computation efficiency and network complexity.
- 36
- A hybrid agent architecture integrating desire, intention and reinforcement learning35
This paper presents a hybrid agent architecture that integrates the behaviours of BDI agents, specifically desire and intention, with a neural network based reinforcement learner known as Temporal Difference-Fusion Architecture for Learning and COgNition (TD-FALCON).
- Mining globally distributed frequent subgraphs in a single labeled graph35
A new measure, termed G-Measure, to find globally distributed frequent subgraphs, called G-Patterns, in a single labeled graph is proposed and a G-Miner algorithm is developed for finding G-patterns.
- 34
- Motivated learning for the development of autonomous systems34
It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in dynamically-changing environments.
- A Simple Curious Agent to Help People be Curious (Extended Abstract)34
This paper proposes a simple model for curious agents (CAs) which can be used to stimulate learners' curiosity in VLEs and potential future research directions will be discussed.
- 34
- Dynamically-optimized context in recommender systems34
This paper presents a framework that separates the contextual concerns from the actual recommendation module, so that contexts can be readily shared across applications, and devise a learning algorithm to dynamically identify the optimal set of contexts for a specific recommendation task and user.
- Rule Extraction, Fuzzy ARTMAP, and Medical Databases34
This paper aims to demonstrate the efforts towards in-situ applicability of EMMARM, which aims to provide real-time information about concrete mechanical properties such as E-modulus and compressive strength.
- MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis33
This paper proposes a new explainable fine-grained multi- class sentiment analysis method, namely MiMuSA, which mimics the human language understanding processes and outperforms other existing multi-class sentiment analysis methods in terms of accuracy and F1-Score.
- 33
- Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-streams32
Contextual Event Segmentation (CES) is proposed, a novel segmentation paradigm that uses an LSTM-based generative network to model the photo-stream sequences, predict their visual context, and track their evolution.
- An adaptive computational model for personalized persuasion32
The experimental results show that the MAP-based agent is able to change the others' attitudes and behaviors intentionally, interpret individual differences between users, and adapt to user's behavior for effective persuasion.
- A Hybrid Architecture Combining Reactive Plan Execution and Reactive Learning32
This work seeks to create an agent that has the capability of learning as well as utilising knowledge represented at a higher level of abstraction, and describes an architecture it has developed that combines the BDI framework to the low-level reinforcement learner.
- A systematic density-based clustering method using anchor points31
This work proposes a novel clustering algorithm named Anchor Points based Clustering (APC), which takes anchor points as centers to obtain intermediate clusters, which can divide the whole dataset more appropriately so as to better facilitate further grouping.
- Extreme learning machine terrain-based navigation for unmanned aerial vehicles31
This paper presents extreme learning machine as a mechanism for learning the stored digital elevation information so as to aid UAVs to navigate through terrain without the need for GPS.
- 31
- Machine Learning for Refining Knowledge Graphs: A Survey30
A survey of machine learning approaches to KG refinement according to the kind of operations in KG refinement, the training datasets, mode of learning, and process multiplicity is presented.
- 30
- 29
- 29
- 29
- 28
- Neural modeling of sequential inferences and learning over episodic memory28
A neural model of sequential representation and inferences on episodic memory is presented and it is shown how episodi memory can be formed and learnt so that the memory performance becomes dependent on the order and the interchange of memory cues.
- 28
- EEG-Based Emotion Recognition via Fast and Robust Feature Smoothing27
This paper extracts six statistical features from raw EEG signals and applies a simple yet cost-effective feature smoothing method to improve the recognition accuracy, and achieves the shortest feature processing time and the highest classification accuracy on emotion recognition in the valence-arousal quadrant space.
- 27
- 26
- Towards personalised web intelligence25
The key challenges in personalised information management are outlined and a detailed account of FOCI’s underlying personalisation mechanism is given and a set of performance indices based on information entropy are proposed that measures the degree of matching between a system-generated cluster structure and a user-preferred category organisation.
- CONCEPT HIERARCHY MEMORY MODEL: A NEURAL ARCHITECTURE FOR CONCEPTUAL KNOWLEDGE REPRESENTATION, LEARNING, AND COMMONSENSE REASONING25
A neural network based cognitive architecture termed Concept Hierarchy Memory Model (CHMM), which provides a systematic treatment for concept formation and organization of a concept hierarchy, performs an important class of commonsense reasoning, including concept recognition and property inheritance.
- Aspect Sentiment Triplet Extraction Incorporating Syntactic Constituency Parsing Tree and Commonsense Knowledge Graph24
A novel end-to-end model, namely GCN-EGTS, which is an enhanced Grid Tagging Scheme for ASTE leveraging syntactic constituency parsing tree and a commonsense knowledge graph based on GCNs is proposed.
- Adaptive computer-generated forces for simulator-based training24
An adaptive CGF that performs well against rule-based CGF and human subjects can be designed with a better understanding of the existing constraints.
- 24
- 23
- 23
- Band selection for hyperspectral images using probabilistic memetic algorithm23
A formal probabilistic memetic algorithm for band selection is proposed, able to adaptively control the degree of global exploration against local exploitation as the search progresses, and empirical studies conducted on five well-known hyperspectral images against two recently proposed state-of-the-art MAs are presented.
- Maximizing winning trades using a novel RSPOP fuzzy neural network intelligent stock trading system23
The proposed RSPOP Intelligent Stock Trading System is designed based on the premise that it is possible to capitalize on the swings in a stock counter’s price, without a need for predicting target prices.
- 23
- Connectionist expert system with adaptive learning capability23
A neural network expert system called adaptive connectionist expert system (ACES) which will learn adaptively from past experience which is based on the neural logic network, which is capable of doing both pattern processing and logical inferencing is described.
- 22
- 22
- 21
- Towards autonomous behavior learning of non-player characters in games21
Two hybrid learning strategies are presented to realize the integration of the two distinct learning paradigms in one framework to provide an efficient method to building intelligent NPC agents in games and pave the way towards building autonomous expert and intelligent systems for other applications.
- 21
- Ontology enhanced web image retrieval: aided by wikipedia & spreading activation theory21
It is proved that it is a viable way to build ontology under various domains and a novel understanding of the ontology is provided, which considers it as a type of semantic network, which is similar to brain models in the cognitive research field.
- A Hybrid of Plot-Based and Character-Based Interactive Storytelling21
A hybrid system of the plot-based and character-based approaches is proposed, constructed as a multi-agent system (MAS), which involves a scriptwriter agent, a director agent, virtual actor agents and other support agents to achieve the balance between conveying story moral and enhancing the modeling of character behaviors.
- Fuzzy cognitive goal net for interactive storytelling plot design21
A model called Fuzzy Cognitive Goal Net is proposed as the story plot planning tool for interactive storytelling, which combines the planning capability of Goal net and reasoning ability of FBuzzy Cognitive Maps.
- 20
- 19
- Salience-aware adaptive resonance theory for large-scale sparse data clustering19
This paper presents a class of self-organizing neural networks, called the salience-aware adaptive resonance theory (SA-ART) model, which extends Fuzzy ART with measures for cluster-wise salient feature modeling to alleviate the side-effect of noisy features incurred by high dimensionality.
- An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings19
An integrated autonomous computational model termed genetic algorithm and rough set incorporated neural fuzzy inference system (GARSINFIS) is applied to predict underpricing in initial public offerings (IPOs) and encouraging experimental results show that it may yield higher initial returns of IPOs by following the advices provided by GARSinFIS than any other benchmarking model.
- 19
- 19
- 19
- 19
- 18
- Wikipedia2Onto— Building Concept Ontology Automatically, Experimenting with Web Image Retrieval18
Wikipedia2Onto— Building Concept Ontology Automatically, Experimenting with Web Image Retrieval experiments with web image retrieval.
- Self-Organizing Neural Architecture for Reinforcement Learning17
A self-organizing neural architecture, known as TD-FALCON, that learns cognitive codes across multi-modal pattern spaces, involving states, actions, and rewards, and is capable of adapting and functioning in a dynamic environment with external evaluative feedback signals is presented.
- Goods Consumed During Transit in Split Delivery Vehicle Routing Problems: Modeling and Solution16
This paper gives mathematical formulas to model SDVRP-GCT and provide solutions by extending three ant colony algorithms and discusses the pros and cons of the proposed solutions and subsequently suggest their preferable application scenarios.
- Community Discovery in Social Networks via Heterogeneous Link Association and Fusion16
The feasibility of a newly proposed heterogeneous data clustering algorithm, called Generalized Heterogeneous Fusion Adaptive Resonance Theory (GHF-ART), for discovering communities in heterogeneous social networks, and the promising results comparing with existing methods demonstrate the effectiveness and efficiency of GHF- ART.
- 16
- FOCI16
How text mining techniques including a novel user-configurable clustering, trend analysis and visualization techniques can be used synergistically to address the problem of managing information gathered from the web is shown.
- 16
- 15
- A novel density peak clustering algorithm based on squared residual error15
This paper analyzes the limitations of DPC and proposes a novel density peak clustering algorithm that provides a better decision graph comparing to DPC for the determination of cluster centroids and shows that it outperforms D PC and other clustering algorithms on the benchmarking datasets.
- Encoding and Recall of Spatio-Temporal Episodic Memory in Real Time15
This paper proposes a computational model called STEM for encoding and recall of episodic events together with the associated contextual information in real time, designed to learn memory chunks or cognitive nodes, each encoding a set of co-occurring multi-modal activity patterns across multiple pattern channels.
- 15
- Predictive Self-Organizing Networks for Text Categorization15
A class of predictive self-organizing neural networks known as Adaptive Resonance Associative Map (ARAM) for classification of free-text documents performs supervised learning and integrates user-defined classification knowledge in the form of IF-THEN rules.
- Inductive neural logic network and the SCM algorithm15
A procedure for NLN to learn multi-dimensional mapping of both binary and analog data, known as the Supervised Clustering and Matching (SCM) algorithm, provides a means of inferring inductive knowledge from databases.
- CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation14
Inspired by human cooperation schemes, CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution, which eliminates redundant actions, improving the overall cooperation efficiency of agents.
- 14
- Cooperative reinforcement learning in topology-based multi-agent systems14
This paper proposes a cooperative learning strategy, under which autonomous agents are assembled in a binary tree formation (BTF), and applies it to a class of reinforcement learning agents known as temporal difference-fusion architecture for learning and cognition (TD-FALCON).
- Discovering Image-Text Associations for Cross-Media Web Information Fusion14
A similarity-based multilingual retrieval model is employed and a vague transformation technique is adopted for measuring the information similarity between visual features and textual features in order to support cross-media web content summarization.
- Learning and inferencing in user ontology for personalized semantic web services14
This paper adopts a statistical approach to learning a semantic-based user ontology model from domain ontology and a spreading activation procedure for inferencing in the userOntology model and applies the methods of learning and exploitinguser ontology to a semantic search engine for finding academic publications.
- 13
- 13
- Brain Informatics and Health13
This paper provides a general method to neuronal morphology modeling (including the soma and its connections to surrounding dendrites, and axons, with a focus on how different components are connected) and handles the challenging task when there are not many detailed sample points for soma.
- 13
- iFALCON: A neural architecture for hierarchical planning13
A novel neural-based model of hierarchical planning that can seek and acquire new plans online if the necessary knowledge are lacking is presented that enables all propositions and descriptions of plans to be computed and learnt simultaneously as inherent features of the model rather than discretely processed like in most symbolic approaches.
- 13
- 13
- Adaptive Resonance Theory in Social Media Data Clustering12
This chapter will give a bird’s eye view of clustering in social media analytics, in terms of data characteristics, challenges and issues, and a class of novel approaches based on adaptive resonance theory (ART).
- 12
- Mining RDF metadata for generalized association rules12
A novel frequent generalized pattern mining algorithm, called GP-Close, for mining generalized associations from RDF metadata that employs the notion of generalization closure for systematic over-generalization reduction.
- 11
- Adaptive Resonance Theory in Social Media Data Clustering: Roles, Methodologies, and Applications11
This chapter will give a bird’s eye view of clustering in social media analytics, in terms of data characteristics, challenges and issues, and a class of novel approaches based on adaptive resonance theory (ART).
- A coordination framework for multi-agent persuasion and adviser systems11
Challenges and issues in multi-agent adviser systems are identified and defined in this paper supported by a survey study about perceived usefulness and user comprehensibility of advices delivered by multiple agents.
- 11
- 11
- 10
- 10
- Self-Regulating Action Exploration in Reinforcement Learning10
Experimental results from the K -Armed Bandit and Air Combat Maneuver scenario prove that optimal action policies can be discovered using the right amount of training iterations and the proposed method eliminates the guesswork on the amount of exploration needed during reinforcement learning.
- Investigating Intelligent Agents in a 3D Virtual World10
This research empirically assesses the efficacy of a specific form of Web 3.0 application in the form of intelligent agents that offer assistance to users in the virtual world and offers guidelines for creating intelligent agents in thevirtual world.
- A Latent Model for Visual Disambiguation of Keyword-based Image Search10
A latent model based approach that resolves user search ambiguity by allowing sense specific diversity in search results by learning the visual word sense models in a totally unsupervised manner, and is able to mine the long tail of image search.
- 10
- 10
- 10
- WEB STRUCTURE ANALYSIS FOR INFORMATION MINING10
The approach to extracting information from the web analyzes the structural content of web pages through exploiting the latent information given by HTML tags to derive extraction rules based on a library of HTML parsing functions.
- L2M2: A Hierarchical Framework Integrating Large Language Model and Multi-agent Reinforcement Learning9
L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models, demonstrating its potential for addressing complex multi-agent coordination tasks.
- 9
- 9
- 9
- 9
- 9
- FOCI: A Personalized Web Intelligence System9
This paper introduces a system known as Flexible Organizer for Competitive Intelligence (FOCI) that provides an integrated platform for gathering, organizing, tracking, and dissemination of competitive information on the web.
- Text categorization, supervised learning, and domain knowledge integration9
It is shown that ARAM performs reasonably well in mining categorization knowledge from sparse and high dimensional document feature space and can be improved by incorporating rules derived from the Reuters category description.
- 9
- 8
- 8
- 8
- Deep Reinforcement Learning With Explicit Context Representation7
A framework for discrete environments called Iota explicit context representation (IECR), which contains four new algorithms that learn using context and shows that all the algorithms, which use contextual information, converge in around 40000 training steps of the neural networks, significantly outperforming their state-of-the-art equivalents.
- Modelling Autobiographical Memory Loss across Life Span7
This paper is the first research work on quantitative evaluations of autobiographical memory loss using a neurocomputational model and results show high correlation with human memory recall performance across their life span, even with another population not being used for learning.
- 7
- 7
- 7
- 7
- 7
- A self-organizing neural architecture integrating desire, intention and reinforcement learning7
A self-organizing neural architecture that integrates the features of belief, desire, and intention (BDI) systems with reinforcement learning that is able to learn plans efficiently, achieve good plan utilization, and combine both intentional and reactive action execution to yield a robust performance is presented.
- 7
- Learning causal models for noisy biological data mining: an application to ovarian cancer detection7
An application to the problem of ovarian cancer detection shows that the approach effectively discovers causal interactions among cancer-specific proteins, and with the proposed error-handling procedure, the network perfectly distinguishes between the cancer and normal patients.
- 7
- 7
- Predictive Adaptive Resonance Theory and Knowledge Discovery in Databases7
Benchmark experiments on a large scale data set show that on-line pruning has been effective in reducing the number of the recognition categories and the time for convergence and Interestingly, the pruned networks also produce better predictive performance.
- 7
- Spatial-temporal episodic memory modeling for ADLs: encoding, retrieval, and prediction6
A cognitive model named Spatial-Temporal Episodic Memory for ADL, which extends STADLART to encode event sequences in the form of distributed episodic memory patterns, and which outperforms STADLART and other state-of-the-art models in ADL retrieval and subsequent event prediction tasks.
- 6
- Adaptive Resonance Theory (ART) for Social Media Analytics6
This chapter presents the ART-based clustering algorithms for social media analytics in detail, and introduces Fuzzy ART and its clustering mechanisms, which provides a deep understanding of the base model that is used and extended for handling the social media clustering challenges.
- Perception Coordination Network: A Neuro Framework for Multimodal Concept Acquisition and Binding6
The experimental results suggest that PCN is able to handle the multimodal concept acquisition and binding effectively and should be considered as a viable neural network for multisensory integration.
- 6
- Self-organizing Cognitive Models for Virtual Agents6
A brain inspired agent architecture that integrates goal-directed autonomy, natural language interaction and human-like personification is proposed that maintains explicit mental representation of desires, intention, personalities, self-awareness, situation awareness and user awareness.
- 6
- Modeling Believable Virtual Characters with Evolutionary Fuzzy Cognitive Maps in Interactive Storytelling.6
E-FCM is used, namely Evolutionary Fuzzy Cognitive Map, to model the attributes of characters (such as emotions and behaviors) as concepts with the dynamic causal relationships among them, so that the variables evolve in a dynamic manner with their respective evolving time schedules.
- 6
- Guest Editorial: Text and Web Mining6
Text mining can be envisaged as an immediate ex-tension of data mining or web content mining, which is primarily concerned with the materials on the web only.
- A Memory Model for Concept Hierarchy Representation and Commonsense Reasoning6
A memory model is proposed which forms concept hierarchy by learning sample relations between concepts by updating memory contents in the concept layer through code firing in the coding layer 1, which is able to perform an important class of commonsense reasoning, namely recognition and inheritance.
- FedART: A neural model integrating federated learning and adaptive resonance theory5
This work proposes a novel one-shot FL approach called Federated Adaptive Resonance Theory (FedART) which leverages self-organizing Adaptive Resonance Theory (ART) models to learn category codes, where each code represents a cluster of similar data samples.
- Who are the ‘silent spreaders’?: contact tracing in spatio-temporal memory models5
A neural network model called Spatio-Temporal Episodic Memory for COVID-19 (STEM-COVID) is presented to identify ACCs from contact tracing data and displays strong robustness against noisy data and different ACC proportions, which partially reflects the effect of breakthrough infections after vaccination on the virus transmission.
- 5
- Perception Coordination Network: A Framework for Online Multi-Modal Concept Acquisition and Binding5
Experimental results suggest that PCN can handle the multi-modal concept acquisition and binding problem effectively, and a biologically plausible neural network model named Perception Coordination Network (PCN) is proposed for online multi- modal concept Acquisition and binding.
- 5
- Towards a Brain Inspired Model of Self-Awareness for Sociable Agents5
A brain inspired model of self-awareness is presented that allows an agent to learn to attend to different aspects of self as an individual with identity, physical embodiment, mental states, experiences, and reflections on how others may think about oneself.
- 5
- A comparative study between motivated learning and reinforcement learning5
This paper analyzes advanced reinforcement learning techniques and compares some of them to motivated learning and results demonstrate that in the selected category of problems, motivated learning outperformed all reinforcement learning algorithms the authors compared with.
- 5
- 5
- FAME, Soft Flock Formation Control for Collective Behavior Studies and Rapid Games Development5
FAME provides an extensive range of advanced features that gives enhanced soft formation control over multiple flocks, which not only supports the research studies of collective intelligence and behaviors, but is useful for rapid development of digital games.
- Adding Personality to Information Clustering5
A sample session is illustrated to show how a user may create and personalize an information portfolio according to his/her preferences and how the system discovers novel information groupings while organizing familiar information according to user-defined themes.
- 5
- Real-Time Hierarchical Map Segmentation for Coordinating Multirobot Exploration4
A novel real-time hierarchical map segmentation method for supporting multi-agent exploration of indoor environments, wherein clusters of regions of segments are formed hierarchically from randomly sampled points in the environment.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Agent-Augmented Co-Space: Toward Merging of Real World and Cyberspace4
This paper proposes to develop cognitive agents, based on a family of self-organizing neural models, known as fusion Adaptive Resonance Theory (fusion ART), which aims to have such agents roaming freely in the landscape of Co-Space, developing an awareness of its surrounding and interacting with avatars of real human.
- S-MADE: Interactive Storytelling Architecture through Goal Execution and Decomposition.4
A new hybrid interactive storytelling architecture S-MADE is proposed, which combines the story plot generation and character performance through goal execution and decomposition mechanism and creates dynamic storylines as well as character behaviors simultaneously.
- Integrating Semantic Templates with Decision Tree for Image Semantic Learning4
This paper presents a decision tree based image semantic learning method, which avoids the difficult image feature discretization problem by making use of semantic template (ST) defined for each concept in the authors' database.
- 4
- Organizing and personalizing intelligence gathering from the web4
An integrated web-based application, code-named FOCI (Flexible Organizer for Competitive Intelligence), can help the knowledge worker in the gathering, organizing, tracking and dissemination of competitive intelligence (CI).
- 4
- Supervised Adaptive Resonance Theory and Rules4
This chapter highlights that the supervised ART architecture is compatible with IF-THEN rule-based symbolic representation, which means that the rules extracted from a supervised ART system can be compared directly with the originally inserted rules.
- 4
- 4
- MemoryART: Enhancing LLMs via Multi-Memory Models with Adaptive Resonance Theory for Healthcare Agents3
This work proposes a cognitively-inspired memory framework named MemoryART, which is grounded in Adaptive Resonance Theory (ART) and leverages multi-channel competitive learning and resonance matching to enable efficient and interpretable episodic memory encoding, alleviating issues of prototype collapse and noisy memory associations.
- Synthesis and Evaluation of Long-term History-aware Medical Dialogue3
A framework for synthesizing high-quality, long-term medical dialogues with LLMs, and defines automatic measures—Faithfulness, Coherence, and Diversity—together with two LLM-based evaluations: Correctness and Realism.
- Development and Validation of Machine Learning Models for Predicting Early Cognitive Decline Using Home Sensor–Derived Behavioral Data: Sensors in-Home for Elder Wellbeing (SINEW) Cohort Study3
This study aimed to use a continuous, home-based monitoring sensor system for older adults to distinguish those exhibiting normal aging from those with MCI, early dementia, prefrailty, or frailty, and to predict their transition from normal aging to one of these conditions.
- Predicting Mild Cognitive Impairment through Ambient Sensing and Artificial Intelligence3
Experiments show that machine learning-based predictive models are able to identify mild cognitive impairment (MCI) cases based on the extracted digital biomarkers with reasonably high F1 scores of more than 0.85, which shows that the sensor-based digital biomarkers are indicative of the users’ cognitive health status and could be further exploited for more general health assessment applications.
- FedSTEM-ADL: A Federated Spatial-Temporal Episodic Memory Model for ADL Prediction3
FedSTEM-ADL, a federated spatial-temporal episodic memory model, is introduced to address data privacy concerns in multi-user ADL analysis and consistently outperforms the baseline models in the task of next ADL event prediction.
- 3
- Hierarchical Reinforcement Learning with Integrated Discovery of Salient Subgoals3
In LIDOSS, the search space of a high level policy can be reduced by focusing only on the subgoal states that have high saliency, and the results show that LIDOSS outperforms Hierarchical Actor Critic, a state-of-the-art HRL method, in the fixed goal tasks.
- Online Multimodal Co-indexing and Retrieval of Social Media Data3
This chapter presents a study on using the Online Multimodal Co-indexing Adaptive Resonance Theory (OMC-ART) for an effective and efficient indexing and retrieval of social media data.
- 3
- 3
- Beyond Traits: Social Context Based Personality Model3
This paper proposes Social Context based Personality model - a continuation and specification of the Cognitive-Affective Personality System theory, showing model's potential in generation of contextual and multidimensional personalities both for individual and group simulations.
- 3
- 3
- 3
- 3
- 3
- 3
- ARTEM: Enhancing Large Language Model Agents with Spatial-Temporal Episodic Memory2
This work introduces Agentic Retrieval with Temporal-Episodic Memory (ARTEM), a hybrid LLM-based agent architecture integrating LLMs with a self-organizing neural network named Spatial-Temporal Episodic Memory (STEM), designed to handle episodic memory tasks.
- 299. SENSORS IN-HOME FOR ELDER WELLBEING (SINEW): DIGITAL PHENOTYPING AND ARTIFICIAL INTELLIGENCE FOR EARLY DETECTION OF DEMENTIA2
A reliable and effective sensor system for in-home use that will facilitate the early detection of cognitive and physical decline is developed and found that FusionART produces the highest level of performance across all three measures of precision, recall and F1 scores.
- DisambiguART: A Neural-based Inference Model for Knowledge Graph Disambiguation2
A new model called DisambiguART is proposed leveraging multi-channel matching and inference in a self-organizing neural network for sense disambiguation in KGs to conduct inferences directly over the graph representation through bi-directional interactions of bottom-up activations and top-down matching.
- 2
- Socially-Enriched Multimedia Data Co-clustering2
This chapter explains how to use the Generalized Heterogeneous Fusion Adaptive Resonance Theory (GHF-ART) for clustering large-scale web multimedia documents and reveals an adaptive method for effective fusion of the multimodal features.
- Analysis of Public Transportation Patterns in a Densely Populated City with Station-based Shared Bikes2
This paper analyses the public transportation patterns in a densely populated city, Chicago, USA, using comprehensive datasets covering the transportation records on shared bikes, buses, taxis and subways collected over one year's time and applies self-regulated clustering methods to reveal both the majority transportation patterns and the irregular ones.
- Dramaturgical and dissonance theories in explicit social context modeling for complex agents2
A new approach to social situation modeling based on the dramaturgical and dissonance theories is developed with implementation used to generate example behavior depicting new social modeling capabilities and a believable representation of the relevant psychological theories.
- 2
- 2
- Topic Based Query Suggestions for Video Search2
This paper proposes an alternative method of presenting query suggestions by their thematic topics that adopts a document-centric approach to mine topics in the corpus, and does not require the availability of a query log.
- 2
- 2
- A non-parametric visual-sense model of images—extending the cluster hypothesis beyond text2
A method to cluster the polysemous images into their semantic categories using the Hierarchical Dirichlet Process and a non-parametric Bayesian approach that exploits the complementary text and visual information of images for semantic clustering.
- Data Mining for Biomedical Applications: PAKDD 2006 Workshop, BioDM 2006, Singapore, April 9, 2006, Proceedings (Lecture Notes in Computer Science / Lecture Notes in Bioinformatics)2
Exploiting Indirect Neighbours and Topological Weight to Predict Protein Function from Protein-Protein Interactions and 3D Clustering Algorithm for Gene-Sample-Time Microarray Data is explored.
- Scaling Up Multi-Agent Reinforcement Learning for Large Agent Teams and Long-Horizon Tasks: A Survey1
A novel taxonomy of MARL studies is introduced, categorizing them based on the external organizational control structures over all agents and the internal policy structures of individual agents, highlighting a set of critical open problems that call for further investigation in the field of scalable MARL.
- Relation prediction in knowledge graphs: A self-organizing neural network approach1
This work presents KG2ART-a novel self-organizing neural network that employs a fundamentally different approach to relation prediction without representation learning, and consistently outperforms state-of-the-art baselines in prediction accuracy.
- 1
- Clustering and Its Extensions in the Social Media Domain1
This chapter summarizes existing clustering and related approaches for the identified challenges as described in Sect.
- Community Discovery in Heterogeneous Social Networks1
This chapter studies the commonly used social links of users and explores the feasibility of the proposed heterogeneous data co-clustering algorithm GHF-ART, as introduced in Sect.
- Learning Generalized Video Memory for Automatic Video Captioning1
Based on a class of self-organizing neural networks, GVM’s model is able to learn new video features incrementally and is shown to be competitive against other state-of-the-art methods.
- Modeling human-like non-rationality for social agents1
This paper proposes brief survey of work in computational disciplines related to human-like non-rationality modeling including: Social Signal Processing, Cognitive Architectures, Affective Computing, Human-Like Agents and Normative Multi-agent Systems.
- Social context cognition crowd‐sourcing and semi‐automatic parametrization1
A semi‐automatic method of parameterizing an existing social context cognition model and a new method of its crowd‐sourcing‐based parametrization is described, which contributes to the believable agent modeling and social simulations by making much needed applications of socialcontext cognition models easier.
- 1
- An Autonomous Agent for Learning Spatiotemporal Models of Human Daily Activities1
An autonomous agent is proposed, named Agent for Spatia-Temporal Activity Pattern Modeling (ASTAPM), being able to learn spatial and temporal patterns of human ADLs, using a self-organizing neural network model named Spatiotemporal - Adaptive Resonance Theory.
- 1
- MAP: A Computational Model for Adaptive Persuasion (Extended Abstract)1
This paper presents a computational model called Model for Adaptive Persuasion (MAP), a semi-connected network model which enables an agent to adapt its persuasion strategies through feedback, and implemented and evaluated a MAP-based virtual nurse agent who takes care and recommends healthy lifestyle habits to the elderly.
- Brain Informatics and Health: International Conference, BIH 2014, Warsaw, Poland, August 11-14, 2014.Proceedings1
This book constitutes the proceedings of the International Conference on Brain Informatics and Health, BIH 2014, held in Warsaw, Poland, in August 2014, as part of 2014 Web Intelligence Congress, WIC 2014.
- 1
- 1
- 1
- Learning Feature Dependencies for Noise Correction in Biomedical Prediction1
A Bayesian Network-based Noise Correction framework named BN-NC is introduced, which accurately detects the errors in biomedical feature values, automatically corrects for the errors to maintain higher prediction accuracy over competing methods including Decision Trees, Naive Bayes and Support Vector Machines.
- 1
- 1
- Ontology-Assisted Mining of RDF Documents1
An Apriori-based algorithm for mining association rules (AR) from RDF documents makes use of a domain ontology to provide generalization of relations and presents a generalized pruning method for removing uninteresting rules.
- 1
- Active IP Network Node Developments1
This paper presents the on-going active node development effort in the IST project called Future Active IP Networks (FAIN), introducing the active networking paradigm, and underlines the motivation behind the project.
- 1
- Interpretable Machine Learning for In-Home Mild Cognitive Impairment Detection–
It is demonstrated that passively collected, sensor-derived digital biomarkers can be leveraged to indicate cognitive status and potentially providing clinically meaningful insights on the impairment conditions, achieving high predictive accuracy regardless the noisy and sparse availability of data.
- –
- Multimodal Contrastive Spatiotemporal Self-Organizing Neural Networks for In-Home Activity Learning of Mild Cognitive Impairment–
A multimodal spatiotemporal machine learning model based on a class of self-organizing neural networks that can integrate different spatiotemporal data types for MCI detection is reported, outperforming state-of-the-art models including Support Vector Machines (SVM) and Long Short-Term Memory (LSTM) based on cyclomatic complexity features in terms of specificity and accuracy.
- Interpretable Machine Learning for Personalized Profiling of Mild Cognitive Impairment from Daily Activities–
A study on a personalized MCI prediction and profiling from an in-home and mobile cognitive health monitoring integrating data on Activities of Daily Living (ADLs), digital biomarkers, and spatial-temporal features is presented.
- MEASE: Multi-agent Episodic Action Sequence Explanation–
This work presents MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors, coupled with abstraction algorithms that identify significant cooperative agent behaviors.
- –
- –
- –
- –
- –
- Personalized Web Image Organization–
This chapter presents using the Probabilistic ART with user preference architecture, which groups images of similar semantics together and simultaneously mines the key tags/topics of individual clusters to give users direct control of the generated clusters.
- Using a Neurocomputational Autobiographical Memory Model to Study Memory Loss–
This chapter introduces the neurocomputational AM model, which is consistent with Conway and Pleydell-Pearce’s model in terms of both the network structure and dynamics, and proposes how to apply the parameterized computational model to quantitatively study memory loss in people of different age groups.
- –
- –
- An Autonomous Agent for Learning Spatiotemporal Models of Human Daily Activities: (Extended Abstract)–
An autonomous agent is proposed, named Agent for Spatia-Temporal Activity Pattern Modeling (ASTAPM), being able to learn spatial and temporal patterns of human ADLs, using a self-organizing neural network model named Spatiotemporal - Adaptive Resonance Theory.
- –
- Preface: Trends in Natural and Machine Intelligence–
The third International Neural Network Society Winter Conference was held in Bangkok, Thailand, on October 3-5, 2012, with an aim to bring together scientists, practitioners, and students worldwide to discuss the past, present, and future challenges and trends in the area of natural and machine intelligence.
- –
- –
- –
- An application of hierarchical knowledge integration in hand-written form processing–
A Hierarchical Interactive Reasoning approach for handwritten form processing and an application of this approach to a prototype form processing system has significantly improved recognition performance in the prototype system.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.