Search

In this paper the ability of two common statistical discriminant analysis procedures are compared with two commercial neural network software packages. The major objective of this study was to determine which of the procedures could best discriminate between normal and abnormal ultrasonic liver textures. The same set of features were input into both statistical discriminant analysis procedures and both neural network models. Preliminary results have found the restricted Coulomb Energy (RCE) neural network model to have a testing accuracy of 90.6% which is approximately 10% better than any of the other techniques investigated. © 1991.

Backpropagation neural networks have been developed for detection of geological lineaments in the Landsat Thematic Mapper (TM) imagery of the Canadian Shield using edge images as input and digitized lineament maps as the desired output. Lineament detection is a challenging problem for traditional image processing and pattern recognition techniques. Many linear features observable in geological image data do not represent lineaments, and the presence and extent of lineaments must be inferred from contextual information. In order to compare the ability of neural networks and conventional classifiers to recognize lineaments prior to performing edge/line element grouping operations, various gradient and curvature features are extracted from the image data set. Selected features from this group formed the inputs to backpropagation neural networks, linear discriminant classifiers, and nearest-neighbor classifiers. The neural network results were compared with the results obtained using conventional classifiers for sample training and test sets. The trained neural network was then applied to the edge image to mask out those edge points which had been classified as non- lineament points.

The primary objective of this research is the development and testing of neural network models for two fundamental computer vision tasks: edge/line detection and texture analysis. In order to test the ability of the neural network models to detect patterns in images we used both remote sensing data and medical imagery. Neural network models for edge and line detection were used to detect geological lineaments in Landsat data. Neural network models for the analysis of image texture variations were used on ultrasonic images to distinguish patients with normal liver scans from patients with diffuse liver disease. 1.

This article discusses the integration of various aspects of the child's development, particularly the development of language and communication and the way in which these developments interact to enable the child to construct a coherent sense of self. Multiplex developmental disorder is presented as an example of a disorder that affects several of these crucial strands of development. Recent research and controversies regarding the diagnostic descriptions of multiplex and other pervasive developmental disorders are presented. This discussion is used to illustrate the ways in which such disorders affect not only the individual aspects of development, but the child's ability to form a cohesive sense of self. The implications of these difficulties in self-definition for treating children with disorders that affect a variety of aspects of development are also discussed.

This article examines the communication styles of children with mental retardation, emphasizing the assessment and intervention protocols used by health and education professionals. This article highlights the following approaches: a developmental psycholinguistic orientation, a pragmatics approach, and a supportive interdependent format consistent with the 1992 revision of how mental retardation is classified. This article discusses children with mental retardation who show challenging and disruptive behavior.

This article presents issues related to the communication assessment of children with psychiatric and communication disorders. Challenges inherent in assessing this population are discussed. Frequently used assessment instruments and procedures are described. Consideration is given to the assessment of very young or low-functioning children and older or high-functioning children.

This article discusses the assessment of communication skills in children from birth to 5 years of age. The different methods appropriate for different developmental levels and the relationship of collateral areas, such as hearing, cognition, and speech motor control to the communication process, are addressed. The need for standardized and informal measures is emphasized Case studies are presented to illustrate the principles outlined.

This article defines communication and describes its various disorders. Some of these disorders are associated with other DSM-IV conditions, such as mental retardation or pervasive developmental disorder. Others are specific to the language-learning process. The interactions between communication and psychiatric disorders are discussed. Suggestions for integrating treating approaches among communication disorders and mental health professionals are presented.

This study examines the temperamental characteristics of children who were identified at age two as being slow in expressive language development, and those of peers with normal language history. When the children were in first grade (approximately age six), parents and clinicians rated subjects' temperamental characteristics, using a standardized temperament assessment instrument. Subjects with a history of slow expressive language development were rated significantly lower on Approach/Withdrawal-indicating shyness, aloofness, or reduced outgoingness-than peers with normal language history. Approach/Withdrawal scores were significantly correlated with average sentence length in spontaneous speech, and this measure also predicted Approach/Withdrawal scores in regression analyses. The clinical and theoretical implications of these findings for early language delay are discussed.

Traumatic brain injuries (TBI) may result in a broad array of cognitive-communicative impairments. Cognitive-communicative impairments are the result of deficits in linguistic and nonlinguistic cognitive functions. The speech-language pathologist functions as a member of the multidisciplinary team of professionals that collaboratively assess and treat individuals with TBI. The role of the speech-language pathologist includes assessment of all aspects of communication, as well as the communicative implications of cognitive deficits, and swallowing; treatment planning and programming, as determined by the individual's stage of recovery; client and family training/counseling; and interdisciplinary consultation. The effectiveness of speech and language intervention for specific cognitive deficits (e.g., attention, memory, executive functions) as well as general issues of social-skills training and early intervention are illustrated by scientific and clinical evidence from group-treatment and single-subject studies as well as case studies.

A simplified, 3-category method for scoring the Kaufman Hand Movements test was devised to replace a previously used, more complex 21-category scoring method. The concurrent validity and diagnostic sensitivity of the rescored test as a measure of limb apraxia were investigated in a reanalysis of the test protocols of 23 aphasic adults. Using the Limb Apraxia Test as the criterion measure, a Pearson r of .71 and predictive validity of 100% were obtained. These results encourage further investigation of the Kaufman Hand Movements lest as an efficient measure of limb apraxia.