Tony Allen

Applications and innovations in intelligent systems XII

The paper presents a consultative rule-based expert system for fInite element mesh design. The aim of the expert system presented is to propose the appropriate type of the fInite elements and determine the resolution values for the fmite element mesh to be used for the analysis. The extensive knowledge base, comprising about 1900 rules, was built mainly by the use of machine learning techniques. Several examples will confIrm that an expert system shell written in Prolog enables efficient use of the knowledge base and adequate communication between the system and the user. The system has the ability to explain the inference process. Thus, it can also be used as a teaching tool for inexperienced users students. The results of the experimental use of the system are encouraging and can be used as guidelines for further developments and improvements of the system.

DACH1: its role as a classifier of long term good prognosis in luminal breast cancer.

Background Oestrogen receptor (ER) positive (luminal) tumours account for the largest proportion of females with breast cancer. Theirs is a heterogeneous disease presenting clinical challenges in managing their treatment. Three main biological luminal groups have been identified but clinically these can be distilled into two prognostic groups in which Luminal A are accorded good prognosis and Luminal B correlate with poor prognosis. Further biomarkers are needed to attain classification consensus. Machine learning approaches like Artificial Neural Networks (ANNs) have been used for classification and identification of biomarkers in breast cancer using high throughput data. In this study, we have used an artificial neural network (ANN) approach to identify DACH1 as a candidate luminal marker and its role in predicting clinical outcome in breast cancer is assessed. Materials and methods A reiterative ANN approach incorporating a network inferencing algorithm was used to identify ER-associated biomarkers in a publically available cDNA microarray dataset. DACH1 was identified in having a strong influence on ER associated markers and a positive association with ER. Its clinical relevance in predicting breast cancer specific survival was investigated by statistically assessing protein expression levels after immunohistochemistry in a series of unselected breast cancers, formatted as a tissue microarray. Results Strong nuclear DACH1 staining is more prevalent in tubular and lobular breast cancer. Its expression correlated with ER-alpha positive tumours expressing PgR, epithelial cytokeratins (CK)18/19 and ‘luminal-like’ markers of good prognosis including FOXA1 and RERG (p<0.05). DACH1 is increased in patients showing longer cancer specific survival and disease free interval and reduced metastasis formation (p<0.001). Nuclear DACH1 showed a negative association with markers of aggressive growth and poor prognosis. Conclusion Nuclear DACH1 expression appears to be a Luminal A biomarker predictive of good prognosis, but is not independent of clinical stage, tumour size, NPI status or systemic therapy.

Use of colour for hand-filled form analysis and recognition

Colour information in form analysis is currently under utilized. As technology has advanced and computing costs have reduced, the processing of forms in colour has now become practicable. This paper describes a novel colour-based approach to the extraction of filled data from colour form images. Images are first quantized to reduce the colour complexity and data is extracted by examining the colour characteristics of the images. The improved performance of the proposed method has been verified by comparing the processing time, recognition rate, extraction precision and recall rate to that of an equivalent black and white system.

Error recovery in a blended style eye gaze and speech interface

In the work carried out earlier [1][2], it was found that an eye gaze and speech enabled interface was the most preferred form of data entry method when compared to other methods such as mouse and keyboard, handwriting and speech only. It was also found that several non-native United Kingdom (UK) English speaking speakers did not prefer the eye gaze and speech system due to the low success rate caused by the inaccuracy of the speech recognition component. Hence in order to increase the usability of the eye gaze and speech data entry system for these users, error recovery methods are required. In this paper we present three different multimodal interfaces that employ the use of speech recognition and eye gaze tracking within a virtual keypad style interface to allow for the use of error recovery (re-speak with keypad, spelling with keypad and re-speak and spelling with keypad). Experiments show that through the use of this virtual keypad interface, an accuracy gain of 10.92% during first attempt and 6.20% during re-speak by non-native speakers in ambiguous fields (initials, surnames, city and alphabets) can be achieved [3]. The aim of this work is to investigate whether the usability of the eye gaze and speech system can be improved through one of these three multimodal blended multimodal error recovery methods.

Handwriting style classification

Abstract.This paper describes an independent handwriting style classifier that has been designed to select the best recognizer for a given style of writing. For this purpose a definition of handwriting legibility has been defined and a method implemented that can predict this legibility. The technique consists of two phases. In the feature-extraction phase, a set of 36 features is extracted from the image contour. In the classification phase, two nonparametric classification techniques are applied to the extracted features in order to compare their effectiveness in classifying words into legible, illegible, and middle classes. In the first method, a multiple discriminant analysis (MDA) is used to transform the space of extracted features (36 dimensions) into an optimal discriminant space for a nearest mean based classifier. In the second method, a probabilistic neural network (PNN) based on the Bayes strategy and nonparametric estimation of probability density function is used. The experimental results show that the PNN method gives superior classification results when compared with the MDA method. For the legible, illegible, and middle handwriting the method provides 86.5% (legible/illegible), 65.5% (legible/middle), and 90.5% (middle/illegible) correct classification for two classes. For the three-class legibility classification the rate of correct classification is 67.33% using a PNN classifier.

Extracting finite structure from infinite language

This paper presents a novel connectionist memory-rule based model capable of learning the finite-state properties of an input language from a set of positive examples. The model is based upon an unsupervised recurrent self-organizing map with laterally interconnected neurons. A derivation of functional-equivalence theory is used that allows the model to exploit similarities between the future context of previously memorized sequences and the future context of the current input sequence. This bottom-up learning algorithm binds functionally related neurons together to form states. Results show that the model is able to learn the Reber grammar perfectly from a randomly generated training set and to generalize to sequences beyond the length of those found in the training set. ed sequences and the future context of the current input sequence. This bottom-up learning algorithm binds functionally related neurons together to form states. Results show that the model is able to learn the Reber grammar [A. Cleeremans, D. Schreiber, J. McClelland, Finite state automata and simple recurrent networks, Neural Computation, 1 (1989) 372-381] perfectly from a randomly generated training set and to generalize to sequences beyond the length of those found in the training set.

A recurrent self-organizing map for temporal sequence processing

We present a novel approach to unsupervised temporal sequence proc- essing in the form of an unsupervised, recurrent neural network based on a self- organizing map (SOM). A standard SOM clusters each input vector irrespective of context, whereas the recurrent SOM presented here clusters each input based on an input vector and a context vector. The latter acts as a recurrent conduit feeding back a 2-D representation of the previous winning neuron. This recurrency allows the network to operate on temporal sequence processing tasks. The network has been applied to the difficult natural language processing problem of position vari- ant recognition, e.g. recognising a noun phrase regardless of its position within a sentence.

Whole word recognition in facsimile images

This paper presents the research carried out in producing a whole recognizor for cursive handwritten words in facsimile images. Two sets of handwritten data samples are collected and converted into facsimile images. The first set comprises approximately 1600 word images from 8 writers and is used for development purposes. The second set consists of approximately 2000 word images from 10 writers. This set is used for testing only. The algorithms for extraction of holistic features namely, vertical bars, holes and cups used in the recognizor are described. A series of test are carried out and the results are presented using a 200 word lexicon. The holistic recognizor produced 62% top rank and 82% in top 5 alternatives. When a lexicon of 1000 words was used these values reduced to 49% and 70% respectively. The future directions of the research for improvement of recognition rate are proposed. It is envisaged that definition of further features would improve the overall accuracy.

Eye gaze and speech for data entry: a comparison of different data entry methods

In this paper we present a multimodal interface that employs speech recognition and eye gaze tracking technology for use in data entry tasks. The aim of this work is to compare the usability of this multimodal system against other data entry methods (handwriting, mouse and keyboard and speech only) when carrying out the data entry task of filling a form. Discussions regarding the relationships between efficiency, effectiveness, ergonomic quality, hedonic quality, naturalness, familiarity and users preference are presented. The experimental results show that the majority of the users prefer using the proposed eye and speech system compared to the other form-filling methods even though such a method is neither the fastest nor the most accurate.

Automated assessment: it's assessment Jim but not as we know it

An extensive literature survey on automated assessment and handwriting recognition has shown that no work has been done in addressing the area of assessment of handwritten exam scripts. We therefore introduce the novel concept of applying image extraction and cursive script recognition (CSR) techniques to the area of automated assessment. We demonstrate the potential for using a holistic CSR engine as the input process for a system capable of automatically scoring handwritten responses to multi-choice questions. This innovative system utilises the constrained nature of simple multiple choice questions to enhance the recognition rate of the handwritten response. Fifty writers were chosen to answer eight multiple choice questions and results show that the system yields an average 83% CSR word accuracy, which enables the system to score over 54% of all response with 99% confidence.