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.

Simulated annealing with adaptive neighborhood: A case study in off-line robot path planning

Simulated annealing (SA) is an optimization technique that can process cost functions with degrees of nonlinearities, discontinuities and stochasticity. It can process arbitrary boundary conditions and constraints imposed on these cost functions. The SA technique is applied to the problem of robot path planning. Three situations are considered here: the path is represented as a polyline; as a Bezier curve; and as a spline interpolated curve. In the proposed SA algorithm, the sensitivity of each continuous parameter is evaluated at each iteration increasing the number of accepted solutions. The sensitivity of each parameter is associated to its probability distribution in the definition of the next candidate. (C) 2010 Elsevier Ltd. All rights reserved.

Off-line simulation inspires insight: a neurodynamics approach to efficient robot task learning

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.

DFMA Aspects in the Design of a Transfer Line for Off-line Ion Sources

In this thesis, the DFMA is presented and used for the purpose of having a design for a vertical transfer line that can be easily manufactured and assembled. The design of the transfer line, the major components and drawings are presented. The ease of assembly, the costs of manufacturing and differences between the use of steel structure and aluminum are compared. The ALARA principle is followed to minimize the risk of radiation exposure by the means of locating the test ion sources outside the radioactive area.

Vibration analysis of a power take-off line

Gear rattle is a phenomenon that occurs when idling or lightly loaded gears collide due to engine’s torque fluctuations. This behaviour is related to vibration behaviour of the transmission system. Aim of this master’s thesis is to evaluate Adams and Adams/Machinery as a simulation tools for modelling the rattle e ect in a transmission system. A case study of tractor’s power take-o driveline, suspected to be prone to rattle, is performed in this work. Modelling methods used by Adams in this type of study are presented in the theory section while simulation model build with the software during this work is presented in the results. The Machinery toolbox is used to create gears and bearings while other model components are created with standard Adams tool set. Geometries and excitations are exported from other softwares. Results were obtained from multiple variations of a base model. These result sets and literature review suggest that Adams/Machinery may not be the most suitable tool for rattle analysis. While the system behaviour was partially captured, for accurate modelling user-written routines must be used which may be more easily performed with other tools. Further research about this topic is required.

ESL students' off-line and on-line texts : differences and similarities /

This study was undertaken to investigate any textual differences and similarities within essays written with a word processing program and an e-mail editor by non-native writers. It arose from many contradictions and a paucity of empirical research within the field of second language learning and electronic technology. To further explore these contradictory observations, 3 classes of intermediate level ESL (English as a Second Language) students v^ote 6 essays, alternating between a word processing program and an e-mail editor. Prior to the data collection, students read brief texts and responded to questions that focused upon three formal topics: immigration, economics, and multiculturalism. Data were examined for (a) the differences in the frequency counts of 12 cohesive devices, (b) sentence complexity, which focused upon the occurrences of simple and complex sentences, (c) the number of words within the writings, (d) the method of contextualization preferred by writers, and (e) any variations in the final grades of the students' texts that resulted from holistic rating. Results of analysis indicated that there were no statistically significant differences in the frequency counts of the linguistic features. Sentence complexity did not vary within the off-line and on-line essays. The average number of words found within the off-line essays was approximately 20% greater than within on-line essays. Contextualization methods were not different within word-processed or e-mailed essays. Finally, there was no difference in the quality of the texts when holistically rated.

Antecedentes de la lealtad en los entornos on line y off line: un análisis empírico aplicado al sector de la aviación civil

El objetivo de esta investigación es analizar la lealtad de los usuarios de líneas aéreas tanto en el entorno online como en el entorno offline. La revisión bibliográfica ha identificado tres antecedentes: la satisfacción, la confianza y el valor percibido. Se ha llevado a cabo un estudio empírico realizándose un total de 1710 entrevistas personales en el aeropuerto del Prat (Barcelona) a usuarios de dos compañías aéreas tradicionales, Iberia y British Airways, y a una compañía low cost, Easyjet. Se trata de las tres compañías que operan con vuelos directos Barcelona-Londres. En el análisis de los datos se han utilizado modelos de ecuaciones estructurales y en particular la técnica utilizada fue el análisis factorial confirmatorio. Los resultados revelan que tanto la satisfacción, como la confianza y el valor percibido explican las relaciones de lealtad entre los pasajeros y las compañías aéreas.

Dimensionalising on- and off-line brands' composite equity

This paper approaches the subject of brand equity measurement on and offline. The existing body of research knowledge on brand equity measurement has derived from classical contexts; however, the majority of today's brands prosper simultaneously online and offline. Since branding on the Web needs to address the unique characteristics of computer-mediated environments, it was posited that classical measures of brand equity were inadequate for this category of brands. Aaker's guidelines for building a brand equity measurement system were thus followed and his brand equity ten was employed as a point of departure. The main challenge was complementing traditional measures of brand equity with new measures pertinent to the Web. Following 16 semi-structured interviews with experts, ten additional measures were identified.

In vitro evaluation of Cu and Fe bioavailability in cashew nuts by off-line coupled SEC-UV and SIMAAS

In this work Cu and Fe bioavailability in cashew nuts was evaluated using in vitro method. Extractions with simulated gastric and intestinal fluids and dialysis procedures were applied for this purpose. The proteins separation and quantification were performed by size exclusion chromatography (SEC) coupled on-line to ultra-violet (UV) and off-line to simultaneous multielement atomic absorption spectrometry (SIMAAS). The SEC-UV and SIMAAS profiles of the protein fractions obtained by alkaline extraction (NaOH) and precipitation with HCl indicated the presence of high and low molecular weight species in the range between >75 kDa and 9.3 kDa. Almost 83% of Cu and 78% of Fe were extracted during cashew nut digestion and 90% of both elements were dialyzed. With these results it is possible to assume that 75% of Cu and 70% of Fe present in cashew nut could be bioavailable. The SEC-UV and SIMAAS chromatographic profiles obtained after in vitro gastrointestinal digestion reveal that Cu and Fe not dialyzed can be associated to a compound of 9.2 kDa. (C) 2010 Elsevier B.V. All rights reserved.