A5024893012- Neural Networks and Applications
- Advanced Memory and Neural Computing
- Neural dynamics and brain function
- Fuzzy Logic and Control Systems
- Evolutionary Algorithms and Applications
- EEG and Brain-Computer Interfaces
- Neural Networks and Reservoir Computing
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Gene Regulatory Network Analysis
- Face and Expression Recognition
- Remote-Sensing Image Classification
- Image and Signal Denoising Methods
- Functional Brain Connectivity Studies
- Time Series Analysis and Forecasting
- Biomedical Text Mining and Ontologies
- Cognitive Science and Mapping
- Semantic Web and Ontologies
- Video Surveillance and Tracking Methods
- Advanced Image Processing Techniques
- Stock Market Forecasting Methods
- Speech Recognition and Synthesis
- Genetics, Bioinformatics, and Biomedical Research
Auckland University of Technology
2016-2025
University of Ulster
2020-2025
Bulgarian Academy of Sciences
2023-2025
Institute of Information and Communication Technologies
2023-2025
University of Auckland
2004-2024
Dalian University
2023-2024
Obuda University
2023
Teesside University
2023
Technical University of Sofia
1992-2023
Birla Institute of Technology and Science, Pilani - Goa Campus
2023
This paper introduces a new type of fuzzy inference systems, denoted as dynamic evolving neural-fuzzy system (DENFIS), for adaptive online and offline learning, their application time series prediction. DENFIS evolve through incremental, hybrid (supervised/unsupervised), accommodate input data, including features, classes, etc., local element tuning. New rules are created updated during the operation system. At each moment, output is calculated based on m-most activated which dynamically...
From the Publisher: Covering latest issues and achievements, this well documented, precisely presented text is timely suitable for graduate upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy related areas. The author's goal to explain principles of networks systems demonstrate how they can be applied building knowledge-based problem solving. Especially useful are comparisons between different techniques (AI rule-based methods,...
This paper introduces evolving fuzzy neural networks (EFuNNs) as a means for the implementation of connectionist systems (ECOS) paradigm that is aimed at building online, adaptive intelligent have both their structure and functionality in time. EFuNNs evolve parameter values through incremental, hybrid supervised/unsupervised, online learning. They can accommodate new input data, including features, classes, etc., local element tuning. New connections neurons are created during operation...
This paper presents a constructive method for deriving an updated discriminant eigenspace classification when bursts of data that contains new classes is being added to initial in the form random chunks. Basically, we propose incremental linear analysis (ILDA) its two forms: sequential ILDA and Chunk ILDA. In experiments, have tested using datasets with small number small-dimensional features, as well large large-dimensional features. We compared proposed against traditional batch LDA terms...
Spiking Neural Networks (SNN) were shown to be suitable tools for the processing of spatio-temporal information. However, due their inherent complexity, formulation efficient supervised learning algorithms SNN is difficult and remains an important problem in research area. This article presents SPAN - a spiking neuron that able learn associations arbitrary spike trains fashion allowing information encoded precise timing spikes. The idea proposed algorithm transform during phase into analog...
Prologue.- Part I: Evolving Connectionist Systems: Methods and Techniques.- Processes Systems.- Systems for Unsupervised Learning.- Supervised Recurrent Systems, Reinforcement Learning Automata.- Neuro-Fuzzy Inference Evolutionary Computation Machines: A Framework, Biological Motivation.- Implementation Issues.- II: connectionist systems: Applications in Bioinformatics, Brain Study Intelligent Data Analysis, Modelling Knowledge Discovery Bioinformatics.- Dynamic of Functions Cognitive...
The quantum-inspired evolutionary algorithm (QEA) applies several quantum computing principles to solve optimization problems. In QEA, a population of probabilistic models promising solutions is used guide further exploration the search space. This paper clearly establishes that QEA an original belongs class estimation distribution algorithms (EDAs), while common points and specifics compared other EDAs are highlighted. behavior versatile relatively three classical extensively studied...
This paper presents spiking neural networks (SNNs) for remote sensing spatiotemporal analysis of image time series, which make use the highly parallel and low-power-consuming neuromorphic hardware platforms possible. illustrates this concept with introduction first SNN computational model crop yield estimation from normalized difference vegetation index series. It development testing a methodological framework utilizes spatial accumulation series Moderate Resolution Imaging Spectroradiometer...
Spiking neural networks (SNNs) receive trains of spiking events as inputs. In order to design efficient SNN systems, real-valued signals must be optimally encoded into spike so that the task-relevant information is retained. This paper provides a systematic quantitative and qualitative analysis guidelines for optimal temporal encoding. It proposes methodology three-step encoding workflow: method selection by signal characteristics, parameter optimization error metrics between original...