Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application

A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR)(1). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.

NMR and pattern recognition studies on the acute biochemical effects of Lu(NO3)(3)

Pattern recognition methods were applied to the analysis of 600 MHz H-1 NMR spectra of urine from rats dosed with compounds that induced organ-specific damage in the liver and kidney. Male Wistar rats were separated into groups (n=4) and each was treated with one of following compounds: HgCl2, CCl4, Lu(NO3)(3) and Changle (a kind of rare earth complex mixed with La, Ce, Pr and Nd). Urine samples from the rats dosed with HgCl2, CCl4 and Lu(NO3)(3) were collected over a 24 h time course and the samples from the rats administrated with Changle were gained after 3 months. These samples were measured by 600 MHz NMR spectroscopy. Each spectrum was data-processed to provide 223 intensity-related descriptors of spectra. Urine spectral data corresponding to the time intervals, 0-8 h (HgCl2 and CCl4), 4-8 (Lu(NO3)(3)) h and 90 d (Changle) were analyzed using principal component analysis (PCA). Successful classification of the toxicity and biochemical effects of Lu(NO3)(3) was achieved.

Discrimination of herbal medicines by molecular spectroscopy and chemical pattern recognition

The molecular spectroscopy (including near infrared diffuse reflection spectroscopy, Raman spectroscopy and infrared spectroscopy) with OPUS/Ident software was applied to clustering ginsengs according to species and processing methods. The results demonstrate that molecular spectroscopic analysis could provide a rapid, nondestructive and reliable method for identification of Chinese traditional medicine. It's found that the result of Raman spectroscopic analysis was the best one among these three methods. Comparing with traditional methods, which are laborious and time consuming, the molecular spectroscopic analysis is more effective.

SEARCH FOR THE BASIC REGULARITIES OF THE TRANSITION EMISSION OF EUROPIUM(II) ION IN COMPLEX FLUORIDES USING PATTERN-RECOGNITION

The relationship between structures of complex fluorides and spectral structure of Eu(II) ion in complex fluorides (AB(m)F(n)) is investigated by means of pattern recognition methods, such as KNN, ALKNN, BAYES, LLM, SIMCA and PCA. A learning set consisting of 32 f-f transition emission host compounds and 31 d-f transition emission host compounds and a test set consisting of 27 host compounds were characterized by 12 crystal structural parameters. These parameters, i.e. features, were reduced from 12 to 6 by multiple criteria for the classification of these host compounds as f-f transition emission or d-f transition emission. A recognition rate from 79.4 to 96.8% and prediction capabilities from 85.2 to 92.6% were obtained. According to the above results, the spectral structures of Eu(II) ion in seven unknown host lattices were predicted.

Molecular cloning and characterisation of a pattern recognition protein, lipopolysaccharide and beta-1,3-glucan binding protein (LGBP) from Chinese shrimp Fenneropenaeus chinensis

A pattern recognition protein (PRP), lipopolysaccharide and beta-1,3-glucan binding protein (LGBP) cDNA was cloned from the haemocyte of Chinese shrimp Fenneropenaeus chinensis by the techniques of homology cloning and RACE. Analysis of nucleotide sequence revealed that the full-length cDNA of 1,275 bp has an open reading frame of 1,098 bp encoding a protein of 366 amino acids including a 17 amino acid signal peptide. Sequence comparison of the deduced amino acid sequence of F. chinensis LGBP showed a high identity of 94%, 90%, 87%, 72% and 63% with Penaeus monodon BGBP, Litopenaeus stylirostris LGBP, Marsupenaeu japonicus BGBP, Homarus gammarus BGBP and Pacifastacus leniusculus LGBP, respectively. The calculated molecular mass of the mature protein is 39,857 Da with a deduced pI of 4.39. Two putative integrin binding motifs, RGD (Arg-Gly-Asp) and a potential recognition motif for beta-1,3-linkage of polysaccharides were observed in LGBP sequence. RT-PCR analysis showed that LGBP gene expresses in haemocyte and hepatopancreas only, but not in other tissues. Capillary electrophoresis RT-PCR method was used to quantify the variation of mRNA transcription level during artificial infection with heat-killed Vibrio anguillarum and Staphylococcus aureusin. A significant enhancement of LGBP transcription was appeared at 6 h post-injection in response to bacterial infection. These results have provided useful information to understand the function of LGBP in shrimp.

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.

A Neural Network Model of Spatio-Temporal Pattern Recognition, Recall and Timing

This paper describes the design of a self~organizing, hierarchical neural network model of unsupervised serial learning. The model learns to recognize, store, and recall sequences of unitized patterns, using either short-term memory (STM) or both STM and long-term memory (LTM) mechanisms. Timing information is learned and recall {both from STM and from LTM) is performed with a learned rhythmical structure. The network, bearing similarities with ART (Carpenter & Grossberg 1987a), learns to map temporal sequences to unitized patterns, which makes it suitable for hierarchical operation. It is therefore capable of self-organizing codes for sequences of sequences. The capacity is only limited by the number of nodes provided. Selected simulation results are reported to illustrate system properties.

Experimental investigation of a wavelet based drive-by bridge inspection system incorporating pattern recognition

This paper presents the results of an experimental investigation, carried out in order to verify the feasibility of a ‘drive-by’ approach which uses a vehicle instrumented with accelerometers to detect and locate damage in a bridge. In theoretical simulations, a simplified vehicle-bridge interaction model is used to investigate the effectiveness of the approach in detecting damage in a bridge from vehicle accelerations. For this purpose, the accelerations are processed using a continuous wavelet transform and damage indicators are evaluated and compared. Alternative statistical pattern recognition techniques are incorporated to allow for repeated vehicle passes. Parameters such as vehicle speed, damage level, location and road roughness are varied in simulations to investigate the effect. A scaled laboratory experiment is carried out to assess the effectiveness of the approach in a more realistic environment, considering a number of bridge damage scenarios.

Pattern Recognition Approach for Road Collision Hotspots Analysis: Case Study of Northern Ireland

In order to address road safety effectively, it is essential to understand all the factors, which
attribute to the occurrence of a road collision. This is achieved through road safety
assessment measures, which are primarily based on historical crash data. Recent advances
in uncertain reasoning technology have led to the development of robust machine learning
techniques, which are suitable for investigating road traffic collision data. These techniques
include supervised learning (e.g. SVM) and unsupervised learning (e.g. Cluster Analysis).
This study extends upon previous research work, carried out in Coll et al. [3], which
proposed a non-linear aggregation framework for identifying temporal and spatial hotspots.
The results from Coll et al. [3] identified Lisburn area as the hotspot, in terms of road safety,
in Northern Ireland. This study aims to use Cluster Analysis, to investigate and highlight any
hidden patterns associated with collisions that occurred in Lisburn area, which in turn, will
provide more clarity in the causation factors so that appropriate countermeasures can be put
in place.

Where and how to find data on safety: what do systematic reviews of complementary therapies tell us?

Background: Successfully identifying relevant data for systematic reviews with a focus on safety may require retrieving information from a wider range of sources than for ‘effectiveness’ systematic reviews. Searching for safety data continues to prove a major challenge. Objectives: To examine search methods used in systematic reviews of safety and to investigate indexing. Methods: Systematic reviews focusing on safety of complementary therapies and related interventions were retrieved from comprehensive searches of major databases. Data was extracted on search strategies, sources used and indexing in major databases. Safety related search terms were compared against index terms available on major databases. Data extraction by one researcher using a pre-prepared template was checked for accuracy by a second researcher. Results: Screening of 2563 records resulted in 88 systematic reviews being identified. Information sources used varied with the type of intervention being addressed. Comparison of search terms with available index terms revealed additional potentially relevant terms that could be used in constructing search strategies. Seventy-nine reviews were indexed on PubMed, 84 on EMBASE, 21 on CINAHL, 15 on AMED, 6 on PsycINFO, 2 on BNI and HMIC. The mean number of generic safety-related indexing terms on PubMed records was 2.6. For EMBASE the mean number was 4.8 with at least 61 unique terms being employed. Most frequently used indexing terms and subheadings were adverse effects, side effects, drug interactions and herb-drug interactions. Use of terms specifically referring to safety varied across databases. Conclusions: Investigation of search methods revealed the range of information sources used, a list of which may prove a valuable resource for those planning to conduct systematic reviews of safety. The findings also indicated that there is potential to improve safety-related search strategies. Finally, an insight is provided into indexing of and most effective terms for finding safety studies on major databases.

Using what we know: consequences of intentionally retrieving gist versus item-specific information

The effect of a prior gist-based versus item-specific retrieval orientation on recognition of objects and words was examined. Prior item-specific retrieval increased item-specific recognition of episodically related but not previously tested objects relative to both conceptual- and perceptual-gist retrieval. An item-specific retrieval advantage also was found when the stimuli were words (synonyms) rather than objects but not when participants overtly named objects during gist-based recognition testing, which suggests that they did not always label objects under general gist-retrieval instructions. Unlike verbal overshadowing, labeling objects during recognition attenuated (but did not eliminate) test- and interference-related forgetting. A full understanding of how retrieval affects subsequent memory, even for events or facts that are not themselves retrieved, must take into account the specificity with which that retrieval occurs.