Adaptive Resonance Theory Research Papers (original) (raw)

In this paper, we propose a hybrid approach of Arabic scripts web page language identification based on decision tree and ARTMAP approaches. We use the decision tree approach to find the general identities of a web document, be it an Arabic script-based or a non-Arabic-based. Then, we use the selected representations of identified pages from the decision tree approach as

- by
- •
- Arabic, Pattern Recognition, Neural Network, Algorithm

A neural network model is developed to explain how visual thalamocortical interactions give rise to boundary percepts such as illusory contours and surface percepts such as filled-in brightnesses. Top-down feedback interactions are needed in addition to bottom-up feed-forward interactions to simulate these data. One feedback loop is modeled between lateral geniculate nucleus (LGN) and cortical area V1, and another within cortical areas V1 and V2. The first feedback loop realizes a matching process which enhances LGN cell activities that are consistent with those of active cortical cells, and suppresses LGN activities that are not. This corticogeniculate feedback, being endstopped and oriented, also enhances LGN ON cell activations at the ends of thin dark lines, thereby leading to enhanced cortical brightness percepts when the lines group into closed illusory contours. The second feedback loop generates boundary representations, including illusory contours, that coherently bind dist...

- by S. Grossberg
- •
- Perception, Visual Neuroscience, Modeling, Forecasting
- by Ibrahim Tansel
- •
- Engineering, Time Series, Neural Network, Wavelet Transform
- by Massimo Pacella
- •
- Engineering, Data Analysis, Monte Carlo Simulation, Process Control
- by sameer singh
- •
- Engineering, Technology, Art, System Identification

Radar memancarkan gelombang elektromagnetik mendapatkan data-data yang berkaitan dengan pesawat
terbang yang meliputi jarak, ketinggian, arah dan kecepatan. Untuk identifikasi, radar dilengkapi dengan peralatan
interogator Identification Friend or Foe (IFF) sebagai bagian dari Secondary Surveillance Radar (SSR). Interogator
IFF mengirimkan sinyal pertanyaan kepada pesawat terbang yang ingin diidentifikasi. Pesawat terbang yang
dilengkapi dengan transponder (transmitter responder) akan menjawab sinyal pertanyaan tersebut secara otomatis
berupa kode identifikasi pesawat. Bila pesawat tidak dapat merespon pertanyaan yang diberikan, maka pesawat akan
diidentifikasikan sebagai penerbangan gelap (black flight). Proses identifikasi pada kasus penerbangan gelap dapat
dilakukan dengan menganalisa data Radar Cross Section (RCS) dan kecepatan dari pesawat terbang.
Seringkali data yang tertangkap di radar berupa RCS dan kecepatan pesawat dari sebuah pesawat terbang
tidak selalu sama. Agar proses identifikasi pesawat terbang di udara dapat dilakukan dengan cepat dan memiliki
tingkat keakuratan yang tinggi diperlukan sebuah sistem identifikasi pesawat terbang adaptif yang mampu
mengidentifikasi data yang berubah-ubah namun tetap stabil. Untuk tujuan tersebut, pada makalah ini akan
disampaikan aplikasi Jaringan Saraf Tiruan model Adaptive Resonance Theory 1 (JST-ART1) pada Sistem
Identifikasi Pesawat Terbang (SIPT-ART1) dengan memanfaatkan RCS dan kecepatan pesawat terbang sebagai
parameter identifikasi. Untuk meyakinkan akurasi hasil identifikasi kedua parameter, dilakukan fusi informasi untuk
menyatakan hasil identifikasi.

Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the profusion of options causes confusion. We survey clustering algorithms for data sets appearing in statistics, computer science, and machine learning, and illustrate their applications in some benchmark data sets, the traveling salesman problem, and bioinformatics, a new field attracting intensive efforts. Several tightly related topics, proximity measure, and cluster validation, are also discussed.

- by Ibitoye Adeniyi Francis
- •
- Bioinformatics, Computer Science, Algorithms, Statistics
- by Jimmi Gonzalez
- •
- Artificial Intelligence, Machine Learning, Data Mining, Fuzzy Logic

This book provides an overview of the concepts behind the human attention control system from neuro-cognitive and computational points of view in three parts.
The first part contains four chapters. In the first chapter, different forms of attention are classified according to processing paths, clinical models, stimulus types, and appearance. This chapter provides a brief introduction and general overview of different kinds of attention and various terms related to the attention control system's characteristics. In the second chapter, the functional anatomy of attention is explained based on the most famous attentional networks and pathways. The neurotransmitters' role in the proper functioning of the attention control system is described following the electrophysiological observations reported in experimental studies on the attention system. The first and second chapters are useful for students and researchers who have just started studying this system. Students who are familiar with the cognitive neuroscience of attention can skip these two chapters. Memory and attention have a close relationship that is described in the third chapter. In this chapter, the strong dependency between memory and different types of attention is discussed. The fourth chapter shows how attention and motor control systems interact. In addition to researchers in neuroscience and engineering, this chapter can be attractive to researchers in sport sciences to design more efficient activities and tools.
The information provided in the first part is the basis of findings reported in the second part that includes four chapters. The fifth chapter is about potent factors, such as nutrition, that can affect the human attention control system's function. General information about these factors can be helpful for anyone who wants to increase attention span and concentration. In the sixth chapter, the most common diseases and disorders associated with attention deficit and specific features of each are described. One of the problems and challenges for students and researchers outside the fields of psychiatry and psychology is how they can evaluate and quantify the attention control system's performance. Several famous subjective and objective (behavioral or neurophysiological) assessment methods are introduced in the seventh chapter. In the eighth chapter, various medicinal, non-medicinal, alternative therapeutic and rehabilitation methods and technologies are explained. The explanations given for these diagnostic and therapeutic methods can also pave the way for developing new techniques.
The last part, which would be of most interest to people keen on modeling, emphasizes conceptual and computational models of attention. These models help scientists developing new diagnostic and therapeutic methods, and finding out more knowledge about the function of the attention control system. The last chapter of this part contains the description of a novel oscillatory computational model of the human attention control system proposed by the authors.

- by Golnaz Baghdadi
- •
- Visual attention, Computational Modelling, Attention, Attentional Control
- by Andrea Baraldi
- •
- Fuzzy Logic, Pattern Recognition, Fuzzy set theory, Fuzzy Sets
- by Magy Kandil
- •
- Face Recognition, Adaptive Resonance Theory, Sms Huffman Code
- by Ravi Pediredla
- •
- Neural Network, Feature Selection, Knowledge Based Systems, Cross Validation
- by Andrea Baraldi
- •
- Fuzzy Logic, Pattern Recognition, Fuzzy set theory, Fuzzy Sets
- by Luis Gil
- •
- Analytical Chemistry, Nitrogen, Adaptive Resonance Theory, Correlation coefficient

Diverse theories of animal navigation aim at explaining how to determine and maintain a course from one place to another in the environment, although each presents a particular perspective with its own terminologies. These vocabularies sometimes overlap, but unfortunately with different meanings. This paper attempts to define precisely the existing concepts and terminologies, so as to describe comprehensively the different theories and models within the same unifying framework. We present navigation strategies within a four-level hierarchical framework based upon levels of complexity of required processing (Guidance, Place recognition-triggered Response, Topological navigation, Metric navigation). This classification is based upon what information is perceived, represented and processed. It contrasts with common distinctions based upon the availability of certain sensors or cues and rather stresses the information structure and content of central processors. We then review computati...

- by Sidney Wiener and +1
- •
- Cognitive Science, Electrophysiology, Locomotion, Information Structure
- by Amine Chohra
- •
- Decision Making, Fuzzy Logic, Back Propagation, Soft Computing

Context-awareness is viewed as one of the most important aspects in the emerging pervasive computing paradigm. Mobile context-aware applications are required to sense and react to changing environment conditions. Such applications, usually, need to recognize, classify and predict context in order to act efficiently, beforehand, for the benefit of the user. In this paper, we propose a novel adaptive mobility prediction algorithm, which deals with location context representation and trajectory prediction of moving users. Machine Learning (ML) is used for trajectory classi- fication. Our algorithm adopts spatial and temporal on-line clustering, and relies on Adaptive Resonance Theory (ART) for trajectory prediction. The proposed algorithm applies a Hausdorff-like distance over the extracted trajectories han- dling location prediction. Since our approach is time-sensi- tive, the Hausdorff distance is considered more advantageous than a simple Euclidean norm. Two learning methods (non-reinforcement and reinforcement learning) are presented and evaluated. Finally, we compare our algo- rithm with Offline kMeans and Online kMeans algorithms. Our findings are very promising for the use of the proposed algorithm in mobile context aware applications.

Problem in object identification occurs when the system is not able to exactly identify an object that is being observed or detected because of the ambiguity resulted from the identification process. This matter happens when the identified object’s parameters are not accordance to the existing database. In this paper we propose a novel object identification method which is a combination of neural network and information fusion. There will be three steps of identification
process and two steps of object identification. At the first object identification step, we employ Adaptive Resonance Theory 1 Neural Network (ART1-NN) to recognize the observed object’s patterns by matching them with knowledge memorized by the
ART1 after a successful learning. Next, at the second step, information fusion is applied to fuse the outputs from ART1-NN to obtain single identified pattern. The method excellence comes from the ART1-NN capability as direct-access pattern matcher that enables to access object identity directly. By this mechanism, the identification process is conducted faster than the existing conventional system. In the other hand, fusing
the identified patterns eliminate the ambiguity of the
identified object

- by Adang Ahmad and +1
- •
- Artificial Neural Networks, Information Fusion, Adaptive Resonance Theory, Aerial Object Identification
- by Maryann Bruns
- •
- Analytical Chemistry, Fuzzy Logic, Back Propagation, Olive Oil
- by Shigekazu Ishihara and +1
- •
- Principal Component Analysis, Product Design, Neural Network, Industrial Ergonomics
- by Gülşen Akman
- •
- Mechanical Engineering, Applied Mathematics, Supply Chain Management, Fuzzy Logic
- by robert gjerdingen
- •
- Music Theory, Pattern Recognition, Syntax, Neural Networks
- by David Canca
- •
- Neural Network, Adaptive Resonance Theory, Soft Constraints, Competitive Learning

We present an ART-based neural network model (adapted from [2]) of the development of discrimination-shift learning that models the trial-by-trial learning process in great detail. In agreement with the results of human participants (4–20 years of age) in [1] the model revealed two distinct learning modes in the learning process: (1) a discontinuous rational learning process by means of hypothesis

The paper deals with the potential of the artificial neural networks in the field of tribology. Their properties of learning and nonlinear behavior make them useful to model complex nonlinear processes, better than the analytical methods. The neural structures, considered appropriate for such models, are presented. The applications found in the referenced papers mainly consist of prediction and classification. They present some common points, specific to the field: wear processes and particles, friction parameters, faults in mechanical structures. The results obtained by the authors, in their interdisciplinary research are described, proving that neural networks are an useful tool during the design stage as well as the running stage.

- by Minodora RIPA
- •
- Mechanical Engineering, Artificial Intelligence, Machine Learning, Prediction
- by Sachin Sharma
- •
- Bioinformatics, Computer Science, Algorithms, Statistics
- by Ethem Alpaydin
- •
- Reinforcement Learning, Clustering Algorithms, Fuzzy Systems, Multidisciplinary
- by Sameer Singh
- •
- Engineering, Technology, Art, System Identification

The estimate and the subsequent monitoring of the energy production of a photovoltaic system is a difficult issue because of the many variables involved, such as weather conditions and construction parameters. The mathematical models usually used do not describe, in an optimal way, the actual behavior of the photovoltaic module as they do not consider all the possible variables involved. This approach leads to an estimation error, from which arises the need to improve the mathematical model used. Given the extreme difficulty in identifying and measuring variables other than solar radiation and ambient temperature, we proposed to optimize the mathematical model using the theory of adaptive neural networks. We aim to create a better estimation method that pursues the real behavior of the PV module based on experimental data. We used a SART (Supervised Adaptive Resonance Theory) neural network to correct the power estimates of the one diode model (ODM). For this purpose, we presented an Estimation Model (EM) for estimating and monitoring the maximum power output of a photovoltaic panel that can take into account the non-linear characteristics of the system. We implemented this system via Matlab and evaluated the performance on a significant sample of actual data for a specific type of PV module. The experimental results show that we can improve the estimation and that this method can then be also used in the monitoring process of the PV system in order to identify specific faults. Finally we proposed a scheme of a possible system for estimating and monitoring the output power of a PV module.

NeuroFAST is an on-line fuzzy modeling learning algorithm, featuring high function approximation accuracy and fast convergence. It is based on a first-order Takagi-Sugeno-Kang (TSK) model, where the consequence part of each fuzzy rule is a linear equation. Structure identification is performed by a fuzzy adaptive resonance theory (ART)-like mechanism, assisted by fuzzy rule splitting and adding procedures. The well known δ rule continuously performs parameter identification on both premise and consequence parameters. Simulation results indicate the potential of the algorithm. It is worth noting that NeuroFAST achieves a remarkable performance in the Box and Jenkins gas furnace process, outperforming all previous approaches compared

- by Konstantinos Zikidis
- •
- Art Theory, Structure, Fuzzy set theory, Fuzzy Logic Control
- by Andrey Gavrilov
- •
- Data Analysis, Semi-supervised Learning, Neural Network, Unsupervised Learning
- by Mladen Kezunovic
- •
- Neural Networks, Fault Detection, Computer Hardware, Comparative Study
- by Palma Blonda
- •
- Fuzzy Logic, Fuzzy set theory, Fuzzy Sets, Clustering Algorithms
- by Gail Carpenter
- •
- Machine Learning, Pattern Recognition, Neural Networks, Neural Network
- by Gail Carpenter
- •
- Pattern Recognition, Fuzzy set theory, Fuzzy Sets, Neural Networks
- by Tom Kazmierski
- •
- Neurofeedback, Circuits and Systems, Neural Networks, Modeling and Simulation
- by Hiroshi Takahashi
- •
- Engineering, Technology, Fuzzy Logic, Gene expression
- by Klaus G Troitzsch
- •
- Artificial Neural Networks, Adaptive Resonance Theory
- by Ei Khin
- •
- Cognitive Science, Neural Network, Adaptive Resonance Theory

This paper concerns with the ART1 (Adaptive Resonance Theory 1) in Neural Network. Important features of ART1 are similarity measure (criterion), vigilance parameter (ρ), and their function to classify the input patterns. Experimental results show that the similarity measure as designed originally does not increase the number of categories with the increased value of ρ but decreases, too. This is against the claim of ‘stability-plasticity’ dilemma. A number of researchers have considered this and suggested alternative similarity measures. Here, we propose a new similarity criterion which eliminates this problem and also possesses the property of lowest list presentations needed for self stabilization of the network. We compare the results of different similarity criteria experimentally and present them in graphs. Analysis of the network under noisy environment is also carried out.

- by Ei Khin
- •
- Cognitive Science, Neural Network, Adaptive Resonance Theory