Biomimetic pattern recognition for speaker-independent speech recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology ( Hidden Markov Models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic Pattern Recognition (BPR) in recognizing some Mandarin Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.

A more complex neuron in biomimetic pattern recognition

Biomimetic pattern recognition has been proposed for several years, but the discussion of its neuron was not very wide and deep. In this paper, we propose a new more complex neuron named M-neuron and give the application in the last part of the paper.

An improved BP algorithm for pattern recognition

An improved BP algorithm for pattern recognition is proposed in this paper. By a function substitution for error measure, it resolves the inconsistency of BP algorithm for pattern recognition problems, i.e. the quadratic error is not sensitive to whether the training pattern is recognized correctly or not. Trained by this new method, the computer simulation result shows that the convergence speed is increased to treble and performance of the network is better than conventional BP algorithm with momentum and adaptive step size.

A fibrinogen-related protein from bay scallop Argopecten irradians involved in innate immunity as pattern recognition receptor

The family of fibrinogen-related proteins (FREPs) is a group of proteins with fibrinogen-like domains. Many members of this family play important roles as pattern recognition receptors in innate immune responses. The cDNA of bay scallop Argopecten irradians FREP (designated as AiFREP) was cloned by rapid amplification of cDNA ends (RACE) method based on the expressed sequence tag (EST). The full-length cDNA of AiFREP was of 990 bp. The open reading frame encoded a polypeptide of 251 amino acids, including a signal sequence and a 213 amino acids fibrinogen-like domain. The fibrinogen-like domain of AiFREP was highly similar to those of mammalian ficolins and other FREPs. The temporal expression of AiFREP mRNA in hemolymph was examined by fluorescent quantitative real-time PCR. The mRNA level of scallops challenged by Listonella anguillarum was significantly up-regulated, peaked to 9.39-fold at 9 h after stimulation, then dropped back to 4.37-fold at 12 h, while there was no significant change in the Micrococcus luteus challenged group in all periods of treatment. The function of AiFREP was investigated by recombination and expression of the cDNA fragment encoding its mature peptide in Escherichia coli Rosetta gami (DE3). The recombinant AiFREP (rAiFREP) agglutinated chicken erythrocytes and human A, B, O-type erythrocytes. The agglutinating activities were calcium-dependent and could be inhibited by acetyl group-containing carbohydrates. rAiFREP also agglutinated Gram-negative bacteria E. coli JM109, L anguillarum and Gram-positive bacteria M. luteus in the presence of calcium ions. These results collectively suggested that AiFREP functions as a pattern recognition receptor in the immune response of bay scallop and contributed to nonself recognition in invertebrates, which would also provide clues for elucidating the evolution of the lectin pathway of the complement system. (C) 2008 Elsevier Ltd. All rights reserved.

An ancient C-type lectin in Chlamys farreri (CfLec-2) that mediate pathogen recognition and cellular adhesion

C-type lectins are a superfamily of Ca2+ dependent carbohydrate-recognition proteins which play significant diverse roles in nonself-recognition and clearance of invaders. In the present study, a C-type lectin (CfLec-2) from Zhikong scallop Chlamys farreri was selected to investigate its functions in innate immunity. The mRNA expression of CfLec-2 in hemocytes was significantly up-regulated (P < 0.01) after scallops were stimulated by LPS. PGN or beta-glucan, and reached the highest expression level at 12h post-stimulation, which was 72.5-, 23.6- or 43.8-fold compared with blank group, respectively. The recombinant Cflec-2 (designated as rCfLec-2) could bind LPS, PGN, mannan and zymosan in vitro, but it could not bind beta-glucan. Immunofluorescence assay with polyclonal antibody specific for Cflec-2 revealed that CfLec-2 was mainly located in the mantle, kidney and gonad. Furthermore, rCfLec-2 could bind to the surface of scallop hemocytes, and then initiated cellular adhesion and recruited hemocytes to enhance their encapsulation in vitro, and this process could be specifically blocked by anti-rCfLec-2 serum. These results collectively suggested that CfLec-2 from the primitive deuterostome C. farreri could perform two distinct immune functions, pathogen recognition and cellular adhesion synchronously, while these functions were performed by collectins and selectins in vertebrates, respectively. The synchronous functions of pathogen recognition and cellular adhesion performed by CfLec-2 tempted us to suspect that CfLec-2 was an ancient form of C-type lectin, and apparently the differentiation of these two functions mediated by C-type lectins occurred after mollusk in phylogeny. (C) 2010 Elsevier Ltd. All rights reserved.

CfLGBP, a pattern recognition receptor in Chlamys farreri involved in the immune response against various bacteria

Lipopolysaccharide and beta-1, 3-glucan binding protein (LGBP) is a kind of pattern recognition receptor, which can recognize and bind LPS and beta-1, 3-glucan, and plays curial roles in the innate immune defense against Gram-negative bacteria and fungi. In this study, the functions of LGBP from Zhikong scallop Chlamys farreri performed in innate immunity were analyzed. Firstly, the mRNA expression of CfLGBP in hemocytes toward three typical PAMPS stimulation was examined by realtime PCR. It was up-regulated extremely (P < 0.01) post stimulation of LPS and beta-glucan, and also exhibited a moderate up-regulation (P < 0.01) after PGN injection. Further PAMPs binding assay with the polyclonal antibody specific for CfLGBP proved that the recombinant CfLGBP (designated as rCfLGBP) could bind not only LPS and beta-glucan, but also PGN in vitro. More importantly, rCfLGBP exhibited obvious agglutination activity towards Gram-negative bacteria Escherichia coil, Gram-positive bacteria Bacillus subtilis and fungi Pichia pastoris. Taking the results of immunofluorescence assay into account, which displayed CfLGBP was expressed specifically in the immune cells (hemocytes) and vulnerable organ (gill and mantle), we believed that LGBP in C farreri, serving as a multi-functional PRR, not only involved in the immune response against Gram-negative and fungi as LGBP in other invertebrates, but also played significant role in the event of anti-Gram-positive bacteria infection. As the first functional research of LGBP in mollusks, our study provided new implication into the innate immune defense mechanisms of C. farreri and mollusks. (C) 2010 Elsevier Ltd. All rights reserved.

Cflec-5, a pattern recognition receptor in scallop Chlamys farreri agglutinating yeast Pichia pastoris

C-type lectins are a superfamily of carbohydrate-recognition proteins which play crucial roles as pattern recognition receptors (PRRs) in the innate immunity. In this study, the full-length cDNA of a C-type lectin was cloned from scallop Chlamys farreri (designated as Cflec-5) by expression sequence tag (EST) analysis and rapid amplification of cDNA ends (RACE) approach The full-length cDNA of Cflec-5 was of 1412 bp. The open reading frame encoded a polypeptide of 153 amino acids, including a signal sequence and a conserved carbohydrate-recognition domain with the EPN motif determining the mannose-binding specificity The deduced amino acid sequence of Cflec-5 showed high similarity to members of C-type lectin superfamily. The quantitative real-time PCR was performed to investigate the tissue distribution of Cflec-5 mRNA and its temporal expression profiles in hemocytes post pathogen-associated molecular patterns (PAMPs) stimulation. In healthy scallops, the Cflec-5 mRNA was mainly detected in gill and mantle, and marginally in other tissues The mRNA expression of Cflec-5 could be significantly induced by lipopolysaccharide (LPS) and glucan stimulation and reached the maximum level at 6 h and 12 h, respectively But its expression level did not change significantly during peptidoglycan (PGN) stimulation The function of Cflec-5 was investigated by recombination and expression of the cDNA fragment encoding its mature peptide in Escherichia coli Rosetta Gami (DE3) The recombinant Cflec-5 agglutinated Pichia pastoris in a calcium-independent way The agglutinating activity could be inhibited by D-mannose. LPS and glucan, but not by D-galactose or PGN. These results collectively suggested that Cflec-5 was involved in the innate Immune response of scallops and might contribute to nonself-recognition through its interaction with various PAMPs (C) 2010 Elsevier Ltd All rights reserved

Some Aspects of Pattern Recognition by Computer

A computer may gather a lot of information from its environment in an optical or graphical manner. A scene, as seen for instance from a TV camera or a picture, can be transformed into a symbolic description of points and lines or surfaces. This thesis describes several programs, written in the language CONVERT, for the analysis of such descriptions in order to recognize, differentiate and identify desired objects or classes of objects in the scene. Examples are given in each case. Although the recognition might be in terms of projections of 2-dim and 3-dim objects, we do not deal with stereoscopic information. One of our programs (Polybrick) identifies parallelepipeds in a scene which may contain partially hidden bodies and non-parallelepipedic objects. The program TD works mainly with 2-dimensional figures, although under certain conditions successfully identifies 3-dim objects. Overlapping objects are identified when they are transparent. A third program, DT, works with 3-dim and 2-dim objects, and does not identify objects which are not completely seen. Important restrictions and suppositions are: (a) the input is assumed perfect (noiseless), and in a symbolic format; (b) no perspective deformation is considered. A portion of this thesis is devoted to the study of models (symbolic representations) of the objects we want to identify; different schemes, some of them already in use, are discussed. Focusing our attention on the more general problem of identification of general objects when they substantially overlap, we propose some schemes for their recognition, and also analyze some problems that are met.

Semantics-Preserving Dimensionality Reduction: Rough and Fuzzy-Rough-Based Approaches

R. Jensen and Q. Shen. Semantics-Preserving Dimensionality Reduction: Rough and Fuzzy-Rough Based Approaches. IEEE Transactions on Knowledge and Data Engineering, 16(12): 1457-1471. 2004.

Large-Scale Neural Systems for Vision and Cognition

— Consideration of how people respond to the question What is this? has suggested new problem frontiers for pattern recognition and information fusion, as well as neural systems that embody the cognitive transformation of declarative information into relational knowledge. In contrast to traditional classification methods, which aim to find the single correct label for each exemplar (This is a car), the new approach discovers rules that embody coherent relationships among labels which would otherwise appear contradictory to a learning system (This is a car, that is a vehicle, over there is a sedan). This talk will describe how an individual who experiences exemplars in real time, with each exemplar trained on at most one category label, can autonomously discover a hierarchy of cognitive rules, thereby converting local information into global knowledge. Computational examples are based on the observation that sensors working at different times, locations, and spatial scales, and experts with different goals, languages, and situations, may produce apparently inconsistent image labels, which are reconciled by implicit underlying relationships that the network’s learning process discovers. The ARTMAP information fusion system can, moreover, integrate multiple separate knowledge hierarchies, by fusing independent domains into a unified structure. In the process, the system discovers cross-domain rules, inferring multilevel relationships among groups of output classes, without any supervised labeling of these relationships. In order to self-organize its expert system, the ARTMAP information fusion network features distributed code representations which exploit the model’s intrinsic capacity for one-to-many learning (This is a car and a vehicle and a sedan) as well as many-to-one learning (Each of those vehicles is a car). Fusion system software, testbed datasets, and articles are available from http://cns.bu.edu/techlab.

An Active Pattern Recognition Architecture for Mobile Robots

An active, attentionally-modulated recognition architecture is proposed for object recognition and scene analysis. The proposed architecture forms part of navigation and trajectory planning modules for mobile robots. Key characteristics of the system include movement planning and execution based on environmental factors and internal goal definitions. Real-time implementation of the system is based on space-variant representation of the visual field, as well as an optimal visual processing scheme utilizing separate and parallel channels for the extraction of boundaries and stimulus qualities. A spatial and temporal grouping module (VWM) allows for scene scanning, multi-object segmentation, and featural/object priming. VWM is used to modulate a tn~ectory formation module capable of redirecting the focus of spatial attention. Finally, an object recognition module based on adaptive resonance theory is interfaced through VWM to the visual processing module. The system is capable of using information from different modalities to disambiguate sensory input.

Fusion Artmap: A Neural Network Architecture for Multi-Channel Data Fusion and Classification

Fusion ARTMAP is a self-organizing neural network architecture for multi-channel, or multi-sensor, data fusion. Single-channel Fusion ARTMAP is functionally equivalent to Fuzzy ART during unsupervised learning and to Fuzzy ARTMAP during supervised learning. The network has a symmetric organization such that each channel can be dynamically configured to serve as either a data input or a teaching input to the system. An ART module forms a compressed recognition code within each channel. These codes, in turn, become inputs to a single ART system that organizes the global recognition code. When a predictive error occurs, a process called paraellel match tracking simultaneously raises vigilances in multiple ART modules until reset is triggered in one of them. Parallel match tracking hereby resets only that portion of the recognition code with the poorest match, or minimum predictive confidence. This internally controlled selective reset process is a type of credit assignment that creates a parsimoniously connected learned network. Fusion ARTMAP's multi-channel coding is illustrated by simulations of the Quadruped Mammal database.

Neural Pattern Recognition on Multichannel Input Representation

This article presents a new neural pattern recognition architecture on multichannel data representation. The architecture emploies generalized ART modules as building blocks to construct a supervised learning system generating recognition codes on channels dynamically selected in context using serial and parallel match trackings led by inter-ART vigilance signals.

ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network

This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This supervised learning system is built up from a pair of Adaptive Resonance Theory modules (ARTa and ARTb) that are capable of self-organizing stable recognition categories in response to arbitrary sequences of input patterns. During training trials, the ARTa module receives a stream {a^(p)} of input patterns, and ARTb receives a stream {b^(p)} of input patterns, where b^(p) is the correct prediction given a^(p). These ART modules are linked by an associative learning network and an internal controller that ensures autonomous system operation in real time. During test trials, the remaining patterns a^(p) are presented without b^(p), and their predictions at ARTb are compared with b^(p). Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms, and achieves 100% accuracy after training on less than half the input patterns in the database. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. This computation increases the vigilance parameter ρa of ARTa by the minimal amount needed to correct a predictive error at ARTb· Parameter ρa calibrates the minimum confidence that ARTa must have in a category, or hypothesis, activated by an input a^(p) in order for ARTa to accept that category, rather than search for a better one through an automatically controlled process of hypothesis testing. Parameter ρa is compared with the degree of match between a^(p) and the top-down learned expectation, or prototype, that is read-out subsequent to activation of an ARTa category. Search occurs if the degree of match is less than ρa. ARTMAP is hereby a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success. As a result, rare but important events can be quickly and sharply distinguished even if they are similar to frequent events with different consequences. Between input trials ρa relaxes to a baseline vigilance pa When ρa is large, the system runs in a conservative mode, wherein predictions are made only if the system is confident of the outcome. Very few false-alarm errors then occur at any stage of learning, yet the system reaches asymptote with no loss of speed. Because ARTMAP learning is self stabilizing, it can continue learning one or more databases, without degrading its corpus of memories, until its full memory capacity is utilized.