Auto-associative memory using n-tuple techniques

The use of n-tuple or weightless neural networks as pattern recognition devices has been well documented. They have a significant advantages over more common networks paradigms, such as the multilayer perceptron in that they can be easily implemented in digital hardware using standard random access memories. To date, n-tuple networks have predominantly been used as fast pattern classification devices. The paper describes how n-tuple techniques can be used in the hardware implementation of a general auto-associative network.

A comparative study of multilayered and single layered neural network based predictive controllers

The authors compare the performance of two types of controllers one based on the multilayered network and the other based on the single layered CMAC network (cerebellar model articulator controller). The neurons (information processing units) in the multi-layered network use Gaussian activation functions. The control scheme which is considered is a predictive control algorithm, along the lines used by Willis et al. (1991), Kambhampati and Warwick (1991). The process selected as a test bed is a continuous stirred tank reactor. The reaction taking place is an irreversible exothermic reaction in a constant volume reactor cooled by a single coolant stream. This reactor is a simplified version of the first tank in the two tank system given by Henson and Seborg (1989).

Trajectory planning of a robot using learning algorithms

The authors consider the problem of a robot manipulator operating in a noisy workspace. The manipulator is required to move from an initial position P(i) to a final position P(f). P(i) is assumed to be completely defined. However, P(f) is obtained by a sensing operation and is assumed to be fixed but unknown. The authors approach to this problem involves the use of three learning algorithms, the discretized linear reward-penalty (DLR-P) automaton, the linear reward-penalty (LR-P) automaton and a nonlinear reinforcement scheme. An automaton is placed at each joint of the robot and by acting as a decision maker, plans the trajectory based on noisy measurements of P(f).

RedGloo: Experiences of developing and using an emerging technology in higher education

Student life has change a lot since 2005 when the idea to create a Social Network Service (SNS) for students in the School of Systems Engineering at the University of Reading was conceived and went live in 2006, called RedGloo.

The cyber challenge: a robotics project to enthuse

Robotics is a key theme in many of the degrees offered in Systems Engineering. The topic has proved useful in attracting students to the University, and it also provides the basis of much practical and project work throughout the degrees. This paper focuses on one aspect, a Part 2 project in which students doing various degrees work together to develop a mobile robot which is controlled remotely to navigate an environment and perform specific tasks. In addition to providing practical experience of relevant academic topics, this project helps to contribute to key teaching and learning priorities including problem based learning, motivation and important employability skills.

Knowledge intensive processes characteristics and improvement: a banking best practice example

This paper identifies characteristics of knowledge intensive processes and a method to improve their performance based on analysis of investment banking front office processes. The inability to improve these processes using standard process improvement techniques confirmed that much of the process was not codified and depended on tacit knowledge and skills. This led to the use of a semi-structured analysis of the characteristics of the processes via a questionnaire to identify knowledge intensive processes characteristics that adds to existing theory. Further work identified innovative process analysis and change techniques that could generate improvements based on an analysis of their properties and the issue drivers. An improvement methodology was developed to harness a number of techniques that were found to effective in resolving the issue drivers and improving these knowledge intensive processes.

Managing change in complex projects: configuration management, asset information and big data

As we enter an era of ‘big data’, asset information is becoming a deliverable of complex projects. Prior research suggests digital technologies enable rapid, flexible forms of project organizing. This research analyses practices of managing change in Airbus, CERN and Crossrail, through desk-based review, interviews, visits and a cross-case workshop. These organizations deliver complex projects, rely on digital technologies to manage large data-sets; and use configuration management, a systems engineering approach with mid-20th century origins, to establish and maintain integrity. In them, configuration management has become more, rather than less, important. Asset information is structured, with change managed through digital systems, using relatively hierarchical, asynchronous and sequential processes. The paper contributes by uncovering limits to flexibility in complex projects where integrity is important. Challenges of managing change are discussed, considering the evolving nature of configuration management; potential use of analytics on complex projects; and implications for research and practice.

DC traction load flow including AC distribution network

In the first part some information and characterisation about an AC distribution network that feeds traction substations and their possible influences on the DC traction load flow are presented. Those influences are investigated and mathematically modelled. To corroborate the mathematical model, an example is presented and their results are confronted with real measurements.

Effect of solvent hydration and temperature in the deacidification process of sunflower oil using ethanol

This work presents liquid-liquid experimental data for systems composed of sunflower seed oil, ethanol and water from 10 to 60 degrees C. The influence of process variables (temperature (T) and water concentration in the solvent (W)) on both the solvent content present in the raffinate (S(RP)) and extract (S(EP)) phases and the partition of free fatty acids (k(2)) was evaluated using the response surface methodology, where flash calculations were performed for each trial using the UNIQUAC equation. Water content in the solvent was the most important factor on the responses of S(EP) and k(2). Additionally, statistical analysis showed that the S(RP) was predominantly affected by temperature factor for low water content in the solvent. (c) 2009 Elsevier Ltd. All rights reserved.

A Survey on Graphical Methods for Classification Predictive Performance Evaluation

Predictive performance evaluation is a fundamental issue in design, development, and deployment of classification systems. As predictive performance evaluation is a multidimensional problem, single scalar summaries such as error rate, although quite convenient due to its simplicity, can seldom evaluate all the aspects that a complete and reliable evaluation must consider. Due to this, various graphical performance evaluation methods are increasingly drawing the attention of machine learning, data mining, and pattern recognition communities. The main advantage of these types of methods resides in their ability to depict the trade-offs between evaluation aspects in a multidimensional space rather than reducing these aspects to an arbitrarily chosen (and often biased) single scalar measure. Furthermore, to appropriately select a suitable graphical method for a given task, it is crucial to identify its strengths and weaknesses. This paper surveys various graphical methods often used for predictive performance evaluation. By presenting these methods in the same framework, we hope this paper may shed some light on deciding which methods are more suitable to use in different situations.