Employing optimized combinations of one-class classifiers for automated currency validation

Automated currency validation requires a decision to be made regarding the authenticity of a banknote presented to the validation system. This decision often has to be made with little or no information regarding the characteristics of possible counterfeits as is the case for issues of new currency. A method for automated currency validation is presented which segments the whole banknote into different regions, builds individual classifiers on each region and then combines a small subset of the region specific classifiers to provide an overall decision. The segmentation and combination of region specific classifiers to provide optimized false positive and false negative rates is achieved by employing a genetic algorithm. Experiments based on high value notes of Sterling currency were carried out to assess the effectiveness of the proposed solution.     

A comparison of backpropagation and general regression neural networks in quantative trace metal analysis using anodic stripping voltammetry and cybernetic instrumentation

A comparison is made between backpropagation and general regression neural networks for the prediction of parts per billion lead concentration when used to process data obtained from digested curry powder by the electrochemical analysis method of differential pulse, anodic stripping at a thin film mercury electrode (TFME). Two data sets are used, one requiring the net to classify an unknown analytical data vector into one of a number of previously learnt concentrations, and one requiring the net to predict the probable concentration of an unknown sample by interpolation of the already learnt concentrations. For both of these data sets the general regression neural network is shown to train faster and to provide results superior to those obtained by backpropagation.     

The problem of definition expansion and contraction

This article is the fourth of a series of articles discussing various open research problems in automated reasoning. The problem proposed for research focuses on finding criteria that would enable an automated reasoning program to expand or contract definitions wisely. For evaluating a proposed solution to this research problem, we include suggestions concerning possible test problems.This work was supported by the Applied Mathematical Sciences subprogram of the Office of Energy Research, U.S. Department of Energy, under contract W-31-109-Eng-38.     

A novel fuzzy clustering algorithm for the analysis of axillary lymph node tissue sections

Recently Fourier Transform Infrared (FTIR) spectroscopic imaging has been used as a tool to detect the changes in cellular composition that may reflect the onset of a disease. This approach has been investigated as a mean of monitoring the change of the biochemical composition of cells and providing a diagnostic tool for various human cancers and other diseases. The discrimination between different types of tissue based upon spectroscopic data is often achieved using various multivariate clustering techniques. However, the number of clusters is a common unknown feature for the clustering methods, such as hierarchical cluster analysis, k-means and fuzzy c-means. In this study, we apply a FCM based clustering algorithm to obtain the best number of clusters as given by the minimum validity index value. This often results in an excessive number of clusters being created due to the complexity of this biochemical system. A novel method to automatically merge clusters was developed to try to address this problem. Three lymph node tissue sections were examined to evaluate our new method. These results showed that this approach can merge the clusters which have similar biochemistry. Consequently, the overall algorithm automatically identifies clusters that accurately match the main tissue types that are independently determined by the clinician.     

A novel automated image analysis method for maceral analysis

A new image analysis technique has been developed which allows maceral analysis of coal to be carried out. The technique is able to separate the liptinite component from the background resin by using two separate images of the surface captured with different camera exposure times. At normal exposure, the liptinite has a similar grey scale value to the surrounding resin, but at a higher exposure time, the resin remains black whilst the liptinite grey scale increases significantly enough to distinguish it from the resin. The method has been tested for repeatability and reproducibility and found to be within the ISO Standard requirements.     

An integral theorem prover and the role of proof planning

An investigation is made into the ways proof planning can enhance the capability of a rule based prover for the theory of integration. The integrals are of the Riemann type and are defined in a way to maximize the theorem proving methods of predicate calculus. Approximately fifty theorems have been proved and several examples are discussed. A major shortcoming was found to be the inability of the system to work with or produce a proof plan. As a result, a planning scheme based on the idea of subgoals or milestones was considered. With user defined plans, there was a substantial increase in performance and capability of the system and, in some cases, proofs which were previously unsuccessful were completed.     

High accuracy path tracking for vehicles in presence of sliding: Application to farm vehicle automatic guidance for agricultural tasks

When designing an accurate automated guidance system for vehicles, a major problem is sliding and pseudo-sliding effects. This is especially the case in agricultural applications, where five-centimetre accuracy with respect to the desired trajectory is required, although the vehicles are moving on slippery ground. It has been established that RTK GPS was a very suitable sensor to achieve automated guidance with such high precision: several control laws have been designed for vehicles equipped with this sensor, and provide the expected guidance accuracy as long as the vehicles do not slide. In previous work, further control developments have been proposed to take sliding into account: guidance accuracy in slippery environments has been shown to be preserved, except transiently at the beginning/end of curves. In this paper, the design of this control law is first recalled and discussed. A Model Predictive Control method is then applied in order to preserve accuracy of guidance even during these curvature transitions. Finally, the overall control scheme is implemented, and improvements with respect to previous guidance laws are demonstrated through full-scale experiments.     

Investigation of the Correlation between Texture and Microstructure on a Submicrometer Scale in the TEM

In recent years the investigation of local texture and microstructure by analysis of electron backscatter diffraction patterns (EBSP) in the SEM has become a very powerful and popular method. With the introduction of SEM with field emission guns (FEG) the spatial resolution of EBSP measurements could be enhanced from 500 nm with a tungsten emitter to better than 50 nm. This evolution of SEM techniques raises the question whether transmission electron microscopy (TEM) still has fields of application in texture research. The present article answers this question with a clear “yes” and presents three examples of investigations where TEM is indispensable. The three examples comprise the investigation of the correlation between dislocation structure and deformation texture, a study on nucleation mechanisms of recrystallization in highly deformed metals and the investigation of microtexture and microstructure in nanocrystalline materials. Together with the presentation of these cases some of the necessary measurement techniques are described briefly. It is shown that TEM has to be applied when highest spatial resolution of orientation determination and imaging and high accuracy of orientation determination are to be reached, when the three‐dimensional and quantitative characterization of lattice defects is required or when materials with a high density of lattice defects are to be investigated.     

Using Automated Negotiation for Grid Services

The popularity of grid services has widened their application to numerous domains and increased the utilization of computational resources. In order to create more incentives for the resources owners to lease their resources and prevent users from wasting the resources, the introduction of a market-oriented grid is inevitable. However, the issues for the negotiation between service provider and consumer over the supply and demand of resources can be complex, with highly interdependent issues. In this research, a simulated automated negotiation mechanism including a co-evolutionary mechanism and a modified game theory approach is proposed, to assist them in reaching an agreement over the conflicting issues. In the proposed architecture, the co-evolution process is able to reduce the multiple dimensional search space into a two-dimension search space and identify the appropriate negotiation strategies for the negotiating agents to form a payoff matrix which can be used for the game theory related stage of their interaction. The multiple stage negotiation process is introduced to improve the negotiation result. In this paper, an application which requires a large amount of computational resources to process the data generated from mobile devises is used to demonstrate that the proposed system is able to resolve the conflicts and obtain a valid solution.     

Transit smart card data mining for passenger origin information extraction

The automated fare collection(AFC) system,also known as the transit smart card(SC) system,has gained more and more popularity among transit agencies worldwide.Compared with the conventional manual fare collection system,an AFC system has its inherent advantages in low labor cost and high efficiency for fare collection and transaction data archival.Although it is possible to collect highly valuable data from transit SC transactions,substantial efforts and methodologies are needed for extracting such data because most AFC systems are not initially designed for data collection.This is true especially for the Beijing AFC system,where a passenger’s boarding stop(origin) on a flat-rate bus is not recorded on the check-in scan.To extract passengers’ origin data from recorded SC transaction information,a Markov chain based Bayesian decision tree algorithm is developed in this study.Using the time invariance property of the Markov chain,the algorithm is further optimized and simplified to have a linear computational complexity.This algorithm is verified with transit vehicles equipped with global positioning system(GPS) data loggers.Our verification results demonstrated that the proposed algorithm is effective in extracting transit passengers’ origin information from SC transactions with a relatively high accuracy.Such transit origin data are highly valuable for transit system planning and route optimization.