- Full text PDF available (7)
- This year (0)
- Last 5 years (0)
- Last 10 years (5)
Artificial Neural Networks (ANNs) are a relatively new approach to computing inspired by the design and operation of the human brain. This paper introduces ANNs and describes some of their applications in the area of medicine, including cancer prognosis, segmentation of magnetic resonance images, and automated analysis of electrocardiograms.
Microarrays are a powerful tool for comparison and understanding of gene expression levels in healthy and diseased states. The method relies upon the assumption that signals from microarray features are a reflection of relative gene expression levels of the cell types under investigation. It has previously been reported that the classical fluorescent dyes… (More)
Microarray technology is readily available to scientists interested in gene expression. Commensurate with this availability is the growing market in accessory products offering convenience but potentially variable performance. Here we evaluate seven commercial kits for probe labeling against a human apoptosis oligonucleotide array. All kits were found to… (More)
A multi-HMM speaker-independent isolated word recognition system is described. In this system , three vector quantization methods, the LBG algorithm, the EM algorithm, and a new MGC algorithm, are used for the classiication of the speech space. These quantizations of the speech space are then used to produce three HMMs for each word in the vocabulary. In… (More)
Describes two artificial neural network architectures for constructing maximum entropy models using multinomial distributions. The architectures presented maximize entropy in two ways: by the use of the partition function (which involves the solution of simultaneous polynomial equations), and by constrained gradient ascent. Results comparing the convergence… (More)
This paper presents a scheme of speaker-independent isolated word recognition in which Hidden Markov Modelling is used with Vector Quantization codebooks constructed using the Expectation-Maximization (EM) algorithm for Gaussian mixture models. In comparison with conventional vector quantization, the EM algorithm results in greater recognition accuracy.
In this paper, we present a syntactic approach to classifying moving objects in a domestic environment such as human beings and curtains blown by the wind and external events such as moving tree branches. We use quadratic forms as our simple pattern primitives and the description of the objects (or patterns) is based on the relationships between the forms.… (More)
OBJECTIVES Mesotheliomas occur in occult serous cavities after chronic exposure of mesothelial cells to asbestos fibres. Molecular events that contribute to the development of this cancer are therefore not readily accessible for study. We have used in vitro culture systems to study and compare induced and spontaneous transformation events in primary mouse… (More)