Matching case history patterns in case-based reasoning

This paper introduces a mechanism for representing and recognizing case history patterns with rich internal temporal aspects. A case history is characterized as a collection of elemental cases as in conventional case-based reasoning systems, together with the corresponding temporal constraints that can be relative and/or with absolute values. A graphical representation for case histories is proposed as a directed, partially weighted and labeled simple graph. In terms of such a graphical representation, an eigen-decomposition graph matching algorithm is proposed for recognizing case history patterns.

Temporal pattern recognition in video clips detection

Temporal representation and reasoning plays an important role in Data Mining and Knowledge Discovery, particularly, in mining and recognizing patterns with rich temporal information. Based on a formal characterization of time-series and state-sequences, this paper presents the computational technique and algorithm for matching state-based temporal patterns. As a case study of real-life applications, zone-defense pattern recognition in basketball games is specially examined as an illustrating example. Experimental results demonstrate that it provides a formal and comprehensive temporal ontology for research and applications in video events detection.

Dense pixel matching between unrectified and distorted images using dynamic programming

In this paper, a novel framework for dense pixel matching based on dynamic programming is introduced. Unlike most techniques proposed in the literature, our approach assumes neither known camera geometry nor the availability of rectified images. Under such conditions, the matching task cannot be reduced to finding correspondences between a pair of scanlines. We propose to extend existing dynamic programming methodologies to a larger dimensional space by using a 3D scoring matrix so that correspondences between a line and a whole image can be calculated. After assessing our framework on a standard evaluation dataset of rectified stereo images, experiments are conducted on unrectified and non-linearly distorted images. Results validate our new approach and reveal the versatility of our algorithm.

An ultra-short-term wind power prediction method using “offline classification and optimization, online model matching” based on time series features

The applicability of ultra-short-term wind power prediction (USTWPP) models is reviewed. The USTWPP method proposed extracts featrues from historical data of wind power time series (WPTS), and classifies every short WPTS into one of several different subsets well defined by stationary patterns. All the WPTS that cannot match any one of the stationary patterns are sorted into the subset of nonstationary pattern. Every above WPTS subset needs a USTWPP model specially optimized for it offline. For on-line application, the pattern of the last short WPTS is recognized, then the corresponding prediction model is called for USTWPP. The validity of the proposed method is verified by simulations.

Between-taxon matching of common and rare species richness patterns

Aim: Our primary aim is to understand how assemblages of rare (restricted range) and common (widespread) species are correlated with each other among different taxa. We tested the proposition that marine species richness patterns of rare and common species differ, both within a taxon in their contribution to the richness pattern of the full assemblage and among taxa in the strength of their correlations with each other. Location The UK intertidal zone. Methods: We used high-resolution marine datasets for UK intertidal macroalgae, molluscs and crustaceans each with more than 400 species. We estimated the relative contribution of rare and common species, treating rarity and commonness as a continuous spectrum, to spatial patterns in richness using spatial crosscorrelations. Correlation strength and significance was estimated both within and between taxa. Results: Common species drove richness patterns within taxa, but rare species contributed more when species were placed on an equal footing via scaling by binomial variance. Between taxa, relatively small sub-assemblages (fewer than 60 species) of common species produced the maximum correlation with each other, regardless of taxon pairing. Cross-correlations between rare species were generally weak, with maximum correlation occurring between small sub-assemblages in only one case. Cross-correlations between common and rare species of different taxa were consistently weak or absent. Main conclusions: Common species in the three marine assemblages were congruent in their richness patterns, but rare species were generally not. The contrast between the stronger correlations among common species and the weak or absent correlations among rare species indicates a decoupling of the processes driving common and rare species richness patterns. The internal structure of richness patterns of these marine taxa is similar to that observed for terrestrial taxa.

Derivation of an Efficient Rule System Pattern Matcher

Formalizing algorithm derivations is a necessary prerequisite for developing automated algorithm design systems. This report describes a derivation of an algorithm for incrementally matching conjunctive patterns against a growing database. This algorithm, which is modeled on the Rete matcher used in the OPS5 production system, forms a basis for efficiently implementing a rule system. The highlights of this derivation are: (1) a formal specification for the rule system matching problem, (2) derivation of an algorithm for this task using a lattice-theoretic model of conjunctive and disjunctive variable substitutions, and (3) optimization of this algorithm, using finite differencing, for incrementally processing new data.

Structural matching of 2D electrophoresis gels using deformed graphs

2D electrophoresis is a well-known method for protein separation which is extremely useful in the field of proteomics. Each spot in the image represents a protein accumulation and the goal is to perform a differential analysis between pairs of images to study changes in protein content. It is thus necessary to register two images by finding spot correspondences. Although it may seem a simple task, generally, the manual processing of this kind of images is very cumbersome, especially when strong variations between corresponding sets of spots are expected (e.g. strong non-linear deformations and outliers). In order to solve this problem, this paper proposes a new quadratic assignment formulation together with a correspondence estimation algorithm based on graph matching which takes into account the structural information between the detected spots. Each image is represented by a graph and the task is to find a maximum common subgraph. Successful experimental results using real data are presented, including an extensive comparative performance evaluation with ground-truth data. (C) 2010 Elsevier B.V. All rights reserved.

CENSUS HISTOGRAMS: A SIMPLE FEATURE EXTRACTION and MATCHING APPROACH FOR FACE RECOGNITION

Most face recognition approaches require a prior training where a given distribution of faces is assumed to further predict the identity of test faces. Such an approach may experience difficulty in identifying faces belonging to distributions different from the one provided during the training. A face recognition technique that performs well regardless of training is, therefore, interesting to consider as a basis of more sophisticated methods. In this work, the Census Transform is applied to describe the faces. Based on a scanning window which extracts local histograms of Census Features, we present a method that directly matches face samples. With this simple technique, 97.2% of the faces in the FERET fa/fb test were correctly recognized. Despite being an easy test set, we have found no other approaches in literature regarding straight comparisons of faces with such a performance. Also, a window for further improvement is presented. Among other techniques, we demonstrate how the use of SVMs over the Census Histogram representation can increase the recognition performance.

Effect of airborne particle abrasion protocols on surface topography of Y-TZP ceramic

This study aimed to evaluate Y-TZP surface after different airborne particle abrasion protocols. Seventy-six Y-TZP ceramic blocks (5×4×4) mm3 were sintered and polished. Specimens were randomly divided into 19 groups (n=4) according to control group and 3 factors: a) protocol duration (2 and 4 s); b) particle size (30 μm, alumina coated silica particle; 45 μm, alumina particle; and 145 μm, alumina particle) and; c) pressure (1.5, 2.5 and 4.5 bar). Airborne particle abrasion was performed following a strict protocol. For qualitative and quantitative results, topography surfaces were analyzed in a digital optical profilometer (Interference Microscopic), using different roughness parameters (Ra, Rq, Rz, X-crossing, Mr1, Mr2 and Sdr) and 3D images. Surface roughness also was analyzed following the primer and silane applications on Y-TZP surfaces. One-way ANOVA revealed that treatments (application period, particle size and pressure of particle blasting) provided significant difference for all roughness parameters. The Tukey test determined that the significant differences between groups were different among roughness parameters. In qualitative analysis, the bonding agent application reduced roughness, filing the valleys in the surface. The protocols performed in this study verified that application period, particle size and pressure influenced the topographic pattern and amplitude of roughness.

Comparison of the reliability of multifocal visual evoked cortical potentials generated by pattern reversal and pattern pulse stimulation

This study compared the effectiveness of the multifocal visual evoked cortical potentials (mfVEP) elicited by pattern pulse stimulation with that of pattern reversal in producing reliable responses (signal-to-noise ratio >1.359). Participants were 14 healthy subjects. Visual stimulation was obtained using a 60-sector dartboard display consisting of 6 concentric rings presented in either pulse or reversal mode. Each sector, consisting of 16 checks at 99% Michelson contrast and 80 cd/m2 mean luminance, was controlled by a binary m-sequence in the time domain. The signal-to-noise ratio was generally larger in the pattern reversal than in the pattern pulse mode. The number of reliable responses was similar in the central sectors for the two stimulation modes. At the periphery, pattern reversal showed a larger number of reliable responses. Pattern pulse stimuli performed similarly to pattern reversal stimuli to generate reliable waveforms in R1 and R2. The advantage of using both protocols to study mfVEP responses is their complementarity: in some patients, reliable waveforms in specific sectors may be obtained with only one of the two methods. The joint analysis of pattern reversal and pattern pulse stimuli increased the rate of reliability for central sectors by 7.14% in R1, 5.35% in R2, 4.76% in R3, 3.57% in R4, 2.97% in R5, and 1.78% in R6. From R1 to R4 the reliability to generate mfVEPs was above 70% when using both protocols. Thus, for a very high reliability and thorough examination of visual performance, it is recommended to use both stimulation protocols.

Comparison of pattern VEP results acquired using CRT and TFT stimulators in the clinical practice

There are several electrophysiological systems available commercially. Usually, control groups are required to compare their results, due to the differences between display types. Our aim was to examine the differences between CRT and LCD/TFT stimulators used in pattern VEP responses performed according to the ISCEV standards. We also aimed to check different contrast values toward thresholds. In order to obtain more precise results, we intended to measure the intensity and temporal response characteristics of the monitors with photometric methods. To record VEP signals, a Roland RetiPort electrophysiological system was used. The pattern VEP tests were carried out according to ISCEV protocols on a CRT and a TFT monitor consecutively. Achromatic checkerboard pattern was used at three different contrast levels (maximal, 75, 25%) using 1A degrees and 15` check sizes. Both CRT and TFT displays were luminance and contrast matched, according to the gamma functions based on measurements at several DAC values. Monitor-specific luminance parameters were measured by means of spectroradiometric instruments. Temporal differences between the displays` electronic and radiometric signals were measured with a device specifically built for the purpose. We tested six healthy control subjects with visual acuity of at least 20/20. The tests were performed on each subject three times on different days. We found significant temporal differences between the CRT and the LCD monitors at all contrast levels and spatial frequencies. In average, the latency times were 9.0 ms (+/- 3.3 ms) longer with the TFT stimulator. This value is in accordance with the average of the measured TFT input-output temporal difference values (10.1 +/- A 2.2 ms). According to our findings, measuring the temporal parameters of the TFT monitor with an adequately calibrated measurement setup and correcting the VEP data with the resulting values, the VEP signals obtained with different display types can be transformed to be comparable.

Comparison of the reliability of multifocal visual evoked cortical potentials generated by pattern reversal and pattern pulse stimulation

This study compared the effectiveness of the multifocal visual evoked cortical potentials (mfVEP) elicited by pattern pulse stimulation with that of pattern reversal in producing reliable responses (signal-to-noise ratio >1.359). Participants were 14 healthy subjects. Visual stimulation was obtained using a 60-sector dartboard display consisting of 6 concentric rings presented in either pulse or reversal mode. Each sector, consisting of 16 checks at 99% Michelson contrast and 80 cd/m² mean luminance, was controlled by a binary m-sequence in the time domain. The signal-to-noise ratio was generally larger in the pattern reversal than in the pattern pulse mode. The number of reliable responses was similar in the central sectors for the two stimulation modes. At the periphery, pattern reversal showed a larger number of reliable responses. Pattern pulse stimuli performed similarly to pattern reversal stimuli to generate reliable waveforms in R1 and R2. The advantage of using both protocols to study mfVEP responses is their complementarity: in some patients, reliable waveforms in specific sectors may be obtained with only one of the two methods. The joint analysis of pattern reversal and pattern pulse stimuli increased the rate of reliability for central sectors by 7.14% in R1, 5.35% in R2, 4.76% in R3, 3.57% in R4, 2.97% in R5, and 1.78% in R6. From R1 to R4 the reliability to generate mfVEPs was above 70% when using both protocols. Thus, for a very high reliability and thorough examination of visual performance, it is recommended to use both stimulation protocols.

Influence of treatment with and without extractions on the growth pattern of dolichofacial patients

OBJECTIVE: The objective of this retrospective study was to compare, by means of lateral cephalograms, the facial growth pattern changes due to the treatment with and without extractions of four first premolars in dolichofacial individuals. METHODS: Groups 1 and 2 were constituted of 23 dolichofacial patients each, with Class II malocclusion, division 1 and initial age average of 12.36 and 12.29 years, respectively. Patients from Group 1 were treated without extractions and Group 2 was treated with extraction of the four first premolars, given that both used occipital headgear. Groups were compatibilized according to age, treatment period, gender and malocclusion severity. The t test was applied for intergroups comparison. RESULTS: Most variables (SN.PP, SN.Ocl and FMA) did not present statistically significant difference between groups. CONCLUSION: Although the treatment with extractions tend to reduce the mandibular plane angle (SN.GoGn) and the facial axis (NS.Gn), the analyzed treatment protocols did not affect in a clinically relevant way the facial growth pattern.

Impact of long-term corticosteroid therapy on the distribution pattern of lower limb atherosclerosis

OBJECTIVE: Ectopic calcification and mediacalcinosis can be promoted by corticosteroid use. Aim of the present investigation is to describe macrovascular disease features in patients with long-term corticosteroid therapy and symptomatic lower limb peripheral arterial occlusive disease (PAD). METHODS: A consecutive series of 2783 patients undergoing clinical and angiographic work-up of PAD were screened for long-term (>5 years) corticosteroid use (group A). Comparison was performed to a randomly selected age-, sex- and risk factor-matched PAD control cohort from the same series without corticosteroid use (group B). Patients with diabetes mellitus or severe renal failure were excluded. Arterial calcification was evaluated by qualitative assessment on radiographic images. Severity of atherosclerotic lesions was analysed from angiographic images using a semi-quantitative score (Bollinger score). RESULTS: In general, 12 patients (5 males, mean age 78.5 +/- 9.0 years) with 15 ischaemic limbs qualified to be enrolled in group A and were compared to 23 matching control patients (6 2 males, mean age 79.5 +/- 6 years) with 32 ischaemic limbs. Incompressibility of ankle arteries determined by measurement of the ankle-brachial index was seen in 12 limbs (80%) in group A compared to 3 limbs (9%) in group B (p = 0.0009). No significant difference was found comparing group A and B for segmental calcification, whereas comparison of the atherosclerotic burden using the angiographic severity score showed a significantly higher score at the infragenicular arterial level in group A (p = 0.001). CONCLUSION: Findings suggest that the long-term corticosteroid therapy is associated with a distally accentuated, calcifying peripheral atherosclerosis inducing arterial incompressibility. This occlusion pattern is comparable to patients with renal failure or diabetes. Further research is required to support our observations.