Off-line signature verification and forgery detection using fuzzy modeling

Automatic signature verification is a well-established and an active area of research with numerous applications such as bank check verification, ATM access, etc. This paper proposes a novel approach to the problem of automatic off-line signature verification and forgery detection. The proposed approach is based on fuzzy modeling that employs the Takagi-Sugeno (TS) model. Signature verification and forgery detection are carried out using angle features extracted from box approach. Each feature corresponds to a fuzzy set. The features are fuzzified by an exponential membership function involved in the TS model, which is modified to include structural parameters. The structural parameters are devised to take account of possible variations due to handwriting styles and to reflect moods. The membership functions constitute weights in the TS model. The optimization of the output of the TS model with respect to the structural parameters yields the solution for the parameters. We have also derived two TS models by considering a rule for each input feature in the first formulation (Multiple rules) and by considering a single rule for all input features in the second formulation. In this work, we have found that TS model with multiple rules is better than TS model with single rule for detecting three types of forgeries; random, skilled and unskilled from a large database of sample signatures in addition to verifying genuine signatures. We have also devised three approaches, viz., an innovative approach and two intuitive approaches using the TS model with multiple rules for improved performance. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Off-line signature verification and forgery detection system based on fuzzy modeling

This paper presents an innovative approach for signature verification and forgery detection based on fuzzy modeling. The signature image is binarized and resized to a fixed size window and is then thinned. The thinned image is then partitioned into a fixed number of eight sub-images called boxes. This partition is done using the horizontal density approximation approach. Each sub-image is then further resized and again partitioned into twelve further sub-images using the uniform partitioning approach. The features of consideration are normalized vector angle (α) from each box. Each feature extracted from sample signatures gives rise to a fuzzy set. Since the choice of a proper fuzzification function is crucial for verification, we have devised a new fuzzification function with structural parameters, which is able to adapt to the variations in fuzzy sets. This function is employed to develop a complete forgery detection and verification system.

Development of a novel titration and off-gas analysis (TOGA) sensor for study of biological processes in wastewater treatment systems

The development of the new TOGA (titration and off-gas analysis) sensor for the detailed study of biological processes in wastewater treatment systems is outlined. The main innovation of the sensor is the amalgamation of titrimetric and off-gas measurement techniques. The resulting measured signals are: hydrogen ion production rate (HPR), oxygen transfer rate (OTR), nitrogen transfer rate (NTR), and carbon dioxide transfer rate (CTR). While OTR and NTR are applicable to aerobic and anoxic conditions, respectively, HPR and CTR are useful signals under all of the conditions found in biological wastewater treatment systems, namely, aerobic, anoxic and anaerobic. The sensor is therefore a powerful tool for studying the key biological processes under all these conditions. A major benefit from the integration of the titrimetric and off-gas analysis methods is that the acid/base buffering systems, in particular the bicarbonate system, are properly accounted for. Experimental data resulting from the TOGA sensor in aerobic, anoxic, and anaerobic conditions demonstrates the strength of the new sensor. In the aerobic environment, carbon oxidation (using acetate as an example carbon source) and nitrification are studied. Both the carbon and ammonia removal rates measured by the sensor compare very well with those obtained from off-line chemical analysis. Further, the aerobic acetate removal process is examined at a fundamental level using the metabolic pathway and stoichiometry established in the literature, whereby the rate of formation of storage products is identified. Under anoxic conditions, the denitrification process is monitored and, again, the measured rate of nitrogen gas transfer (NTR) matches well with the removal of the oxidised nitrogen compounds (measured chemically). In the anaerobic environment, the enhanced biological phosphorus process was investigated. In this case, the measured sensor signals (HPR and CTR) resulting from acetate uptake were used to determine the ratio of the rates of carbon dioxide production by competing groups of microorganisms, which consequently is a measure of the activity of these organisms. The sensor involves the use of expensive equipment such as a mass spectrometer and requires special gases to operate, thus incurring significant capital and operational costs. This makes the sensor more an advanced laboratory tool than an on-line sensor. (C) 2003 Wiley Periodicals, Inc.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Assessment of regional long-axis function during dobutamine echocardiography

Echocardiographic analysis of regional left ventricular function is based upon the assessment of radial motion. Long-axis motion is an important contributor to overall function. but has been difficult to evaluate clinically until the recent development of tissue Doppler techniques. We sought to compare the standard visual assessment of radial motion with quantitative tissue Doppler measurement of peak systolic velocity. timing and strain rate (SRI) in 104 patients with known or suspected coronary artery disease undergoing dobutamine stress echocardiography (DbE). A standard DbE protocol was used with colour tissue Doppler images acquired in digital cine-loop format. peak systolic velocity (PSV), time to peak velocity (TPV) and SRI were assessed off-line by an independent operator. Wall motion was assessed by an experienced reader. Mean PSV, TPV and SRI values were compared with wall motion and the presence of coronary artery disease by angiography. A further analysis included assessing the extent of jeopardized myocardium by comparing average values of PSV, TPV and SRI against the previously validated angiographic score. Segments identified as having normal and abnormal radial wall motion showed significant differences in mean PSV (7.9 +/- 3.8 and 5.9 +/- 3.3 cm/s respectively; P < 0.001), TPV (84 40 and 95 +/- 48 ms respectively; P = 0.005) and SRI (- 1.45 +/- 0.5 and - 1.1 +/- 0.9 s(-1) respectively; P < 0.001). The presence of a stenosed subtending coronary artery was also associated with significant differences from normally perfused segments for mean PSV (8.1 3.4 compared with 5.7 +/- 3.7 cm/s; P < 0.001), TPV (78 50 compared with 92 +/- 45 ms; P < 0.001) and SRI (- 1.35 0.5 compared with - 1.20 +/- 0.4 s(-1); P = 0.05). PSV, TPV and SRI also varied significantly according to the extent of jeopardized myocardium within a vascular territory. These results suggest that peak systolic velocity, timing of contraction and SRI reflect the underlying physiological characteristics of the regional myocardium during DbE, and may potentially allow objective analysis of wall motion.

Effects of slurry rheology on industrial grinding performance

To determine the effect of slurry rheology on industrial grinding performance, 45 surveys were conducted on 16 full-scale grinding mills in five sites. Four operating variables - mill throughput, slurry density, slurry viscosity and feed fines content-were investigated. The rheology of the mill discharge slurries was measured either on-line or off-line, and the data were processed using a standard procedure to obtain a full range of flow curves. Multi-linear regression was employed as a statistical analysis tool to determine whether or not rheological effects exert an influence on industrial grinding, and to assess the influence of the four mill operating conditions on mill performance in terms of the Grinding Index, a criterion describing the overall breakage of particles across the mill. The results show that slurry rheology does influence industrial grinding. The trends of these effects on Grinding Index depend upon the rheological nature of the slurry-whether the slurries are dilatant or pseudoplastic, and whether they exhibit a high or low yield stress. The interpretation of the regression results is discussed, the observed effects are summarised, and the potential for incorporating rheological principles into process control is considered, Guidelines are established to improve industrial grinding operations based on knowledge of the rheological effects. This study confirms some trends in the effect of slurry rheology on grinding reported in the literature, and extends these to a broader understanding of the relationship between slurry properties and rheology, and their effects on industrial milling performance. (C) 2002 Elsevier Science B.V. All rights reserved.

Myocardial abnormalities in hypertensive patients with normal and abnormal left ventricular filling: a study of ultrasound tissue characterization and strain

Abnormal left ventricular (LV) filling is common, but not universal, in hypertensive LV hypertrophy (LVH). We sought to elucidate the relative contributions of myocardial structural changes, loading and hypertrophy to LV dysfunction in 113 patients: 85 with hypertensive LVH and 28 controls without LVH and with normal filling. Patients with normal dobutamine stress echocardiography and no history of coronary artery disease were selected, in order to exclude a contribution from ischaemia or scar. Abnormal LV filling was identified in 65 LVH patients, based on Doppler measurement of transmitral filling and annular velocities. All patients underwent grey-scale and colour tissue Doppler imaging from three apical views, which were stored and analysed off line. Integrated backscatter (113) and strain rate imaging were used to detect changes in structure and function; average cyclic variation of 113, strain rate and peak systolic strain were calculated by averaging each segment. Calibrated 113 intensity, corrected for pericardial 113 intensity, was measured in the septum and posterior wall from the parasternal long-axis view. Patients with LVH differed significantly from controls with respect to all backscatter and strain parameters, irrespective of the presence or absence of abnormal LV filling. LVH patients with and without abnormal LV filling differed with regard to age, LV mass and incidence of diabetes mellitus, but also showed significant differences in cyclic variation (P < 0.01), calibrated 113 in the posterior wall (P < 0.05) and strain rate (P < 0.01), although blood pressure, heart rate and LV systolic function were similar. Multivariate logistic regression analysis demonstrated that age, LV mass index and calibrated IB in the posterior wall were independent determinants of abnormal LV filling in patients with LVH. Thus structural and functional abnormalities can be detected in hypertensive patients with LVH with and without abnormal LV filling. In addition to age and LVH, structural (not functional) abnormalities are likely to contribute to abnormal LV filling, and may be an early sign of LV damage. 113 is useful for the detection of myocardial abnormalities in patients with hypertensive LVH.

Abnormal left ventricular filling with increasing age reflects abnormal myocardial characteristics independent of ischemia or hypertrophy

Abnormal left ventricular (IV) filling may occur with increasing age despite apparently normal IV size and function, and is usually attributed to IV hypertrophy and coronary artery disease. The purpose of this study was to determine whether myocardial abnormalities could be identified in 67 such patients (36 men, mean age 57 +/- 9 years) whose IV hypertrophy and coronary artery disease were excluded by dobutamine echocardiography. All patients underwent gray scale and color tissue Doppler imaging from 3 apical views, which were stored and analyzed off line. Disturbances in structure and function were assessed by averaging the cyclic variation of integrated backscatter, strain rate, and peak systolic strain from each myocardial segment. Calibrated integrated backscatter (corrected for pericardial backscatter intensity) was measured in the septum and posterior wall from the parasternal long-axis view. Abnormal IV filling was present in 36 subjects (54%). Subjects with and without abnormal IV filling had similar IV mass, but differed in age (p <0.01), cyclic variation (p = 0.001), strain rate (p <0.01), and peak systolic strain (p <0.001). Multivariate logistic regression analysis demonstrated that age (p = 0.016) and cyclic variation (p = 0.042) were the most important determinants of abnormal IV filling in these apparently normal subjects. (C) 2003 by Excerpta Medica, Inc.

Reproducibility and accuracy of echocardiographic measurements of left ventricular parameters using real-time three-dimensional echocardiography

OBJECTIVES We sought to determine whether assessment of left ventricular (LV) function with real-time (RT) three-dimensional echocardiography (3DE) could reduce the variation of sequential LV measurements and provide greater accuracy than two-dimensional echocardiography (2DE). BACKGROUND Real-time 3DE has become feasible as a standard clinical tool, but its accuracy for LV assessment has not been validated. METHODS Unselected patients (n = 50; 41 men; age, 64 +/- 8 years) presenting for evaluation of LV function were studied with 2DE and RT-3DE. Test-retest variation was performed by a complete restudy by a separate sonographer within 1 h without alteration of hemodynamics or therapy. Magnetic resonance imaging (MRI) images were obtained during a breath-hold, and measurements were made off-line. RESULTS The test-retest variation showed similar measurements for volumes but wider scatter of LV mass measurements with M-mode and 2DE than 3DE. The average MRI end-diastolic volume was 172 +/- 53 ml; LV volumes were underestimated by 2DE (mean difference, -54 +/- 33; p < 0.01) but only slightly by RT-3DE (-4 +/- 29; p = 0.31). Similarly, end-systolic volume by MRI (91 +/- 53 ml) was underestimated by 2DE (mean difference, -28 +/- 28; p < 0.01) and by RT-3DE (mean difference, -3 +/- 18; p = 0.23). Ejection fraction by MRI was similar by 2DE (p = 0.76) and RT-3DE (p = 0.74). Left ventricular mass (183 +/- 50 g) was overestimated by M-mode (mean difference, 68 +/- 86 g; p < 0.01) and 2DE (16 +/- 57; p = 0.04) but not RT-3DE (0 +/- 38 g; p = 0.94). There was good inter- and intra-observer correlation between RT-3DE by two sonographers for volumes, ejection fraction, and mass. CONCLUSIONS Real-time 3DE is a feasible approach to reduce test-retest variation of LV volume, ejection fraction, and mass measurements in follow-up LV assessment in daily practice. (C) 2004 by the American College of Cardiology Foundation.

Focused beam reflectance technique for in situ particle sizing in wastewater treatment settling tanks

Due to the complexities involved with measuring activated sludge floc size distributions, this parameter has largely been ignored by wastewater researchers and practitioners. One of the major reasons has been that instruments able to measure particle size distributions were complex, expensive and only provided off-line measurements. The Focused Beam Reflectance Method (FBRM) is one of the rare techniques able to measure the particle size distribution in situ. This paper introduces the technique for monitoring wastewater treatment systems and compares its performance with other sizing techniques. The issue of the optimal focal point is discussed, and similar conclusions as found in the literature for other particulate systems are drawn. The study also demonstrates the capabilities of the FBRM in evaluating the performance of settling tanks. Interestingly, the floc size distributions did not vary with position inside the settling tank flocculator. This was an unexpected finding, and seriously questioned the need for a flocculator in the settling tank. It is conjectured that the invariable size distributions were caused by the unique combination of high solids concentration, low shear and zeolite dosing. (C) 2004 Society of Chemical Industry.

Low-cost real-time gesture recognition

A major impediment to developing real-time computer vision systems has been the computational power and level of skill required to process video streams in real-time. This has meant that many researchers have either analysed video streams off-line or used expensive dedicated hardware acceleration techniques. Recent software and hardware developments have greatly eased the development burden of realtime image analysis leading to the development of portable systems using cheap PC hardware and software exploiting the Multimedia Extension (MMX) instruction set of the Intel Pentium chip. This paper describes the implementation of a computationally efficient computer vision system for recognizing hand gestures using efficient coding and MMX-acceleration to achieve real-time performance on low cost hardware.

Fuzzy modeling based recognition of multi-font numerals

In this paper, we present a new scheme for off-line recognition of multi-font numerals using the Takagi-Sugeno (TS) model. In this scheme, the binary image of a character is partitioned into a fixed number of sub-images called boxes. The features consist of normalized vector distances (gamma) from each box. Each feature extracted from different fonts gives rise to a fuzzy set. However, when we have a small number of fonts as in the case of multi-font numerals, the choice of a proper fuzzification function is crucial. Hence, we have devised a new fuzzification function involving parameters, which take account of the variations in the fuzzy sets. The new fuzzification function is employed in the TS model for the recognition of multi-font numerals.

Microarray expression profiling in melanoma reveals a BRAF mutation signature

We have used microarray gene expression pro. ling and machine learning to predict the presence of BRAF mutations in a panel of 61 melanoma cell lines. The BRAF gene was found to be mutated in 42 samples (69%) and intragenic mutations of the NRAS gene were detected in seven samples (11%). No cell line carried mutations of both genes. Using support vector machines, we have built a classifier that differentiates between melanoma cell lines based on BRAF mutation status. As few as 83 genes are able to discriminate between BRAF mutant and BRAF wild-type samples with clear separation observed using hierarchical clustering. Multidimensional scaling was used to visualize the relationship between a BRAF mutation signature and that of a generalized mitogen-activated protein kinase ( MAPK) activation ( either BRAF or NRAS mutation) in the context of the discriminating gene list. We observed that samples carrying NRAS mutations lie somewhere between those with or without BRAF mutations. These observations suggest that there are gene-specific mutation signals in addition to a common MAPK activation that result from the pleiotropic effects of either BRAF or NRAS on other signaling pathways, leading to measurably different transcriptional changes.