Your 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.

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.

Preliminary findings from an ongoing investigation of the potential relationship between narrative discourse performance and executive functions in adults with traumatic brain injuries (TBI) are reported. Narrative stories were elicited from 32 adults with TBI. Stories were analysed at three levels: sentence production, intersentential cohesive adequacy, and story episode structure. These measures were then correlated with scores from the Wisconsin Card Sorting Test (WCST), the primary measure of executive function. A significant correlation was noted between a factor score from the WCST and the measure of story structure, but not sentence production or cohesive adequacy. These results suggest that executive functions may be a promising avenue to pursue in the search for underlying causal factors of narrative discourse dysfunction and, therefore to better delineate the nature of communicative deficits secondary to TBI.

This review analyses several recent studies of discourse deficits subsequent to traumatic brain injury. The review describes methodological problems related to incomplete subject descriptions, use of different discourse elicitation tasks and analyses, and examines the findings from each study by level of analysis. The limitations of these findings are discussed and general conclusions regarding discourse abilities following traumatic brain injury are offered. Implications for future research are also presented.

The tracking technique involves a sender reading consecutive segments from a story and a receiver attempting to repeat each segment verbatim. The reliability and validity of the tracking procedure have been criticized based upon uncontrolled variables such as sender, receiver, and text characteristics. To address these problems, a computer-assisted interactive tracking simulation (CATS) system has been developed in which story segments are presented to the receiver via a video laser disc system and repair strategies are implemented through a computer program.

Potential environmental impacts on wildlife result from siting and construction (short-term impacts) and habitat removal and fragmentation (long-term impacts) as a consequence of transportation corridor construction. Especially in rural districts, wildlife migration corridors and dispersal orientation are altered or destroyed and wildlife populations and their gene pools are isolated. This significantly weakens the wildlife community. Prudent selection of construction corridors reduces fragmentation impacts by maximizing preserved fragment sizes, and by running parallel to, not through, natural areas. Corridor width determines the degree to which wildlife movement is restricted except that culverts, underpasses, overpasses, and one-way gates, can aid wildlife in cross movements. Minimum underpass dimensions for large wildlife should be no smaller than 14 ft×14 ft and should include natural substratum inverts. Rail corridors have four characteristics that minimize adverse environmental impacts. The railbed is dry, ballast fillters runoff, there is little runoff beyond the toe of slope, and drainage ditches serve to control sheet flow and erosion, sediment movement, and uncontrolled channel flow. Rail corridors usually occupy smaller land areas because they are narrower and are more feasible to elevate so as to allow free movement of wildlife across the corridor. © 1993 Springer-Verlag New York Inc.

The food and habitat niches of two nesting species of hawks Accipiter spp were studied in an extensively forested area of the Eastern Deciduous Forest Biome Nesting habitat was quantitated at 19 Cooper s hawk A cooperu nests and 16 northern goshawk A gentilis nests There was no significant trend for Cooper's hawks to nest in less mature forests than northern goshawks as reported previously for western North America Forest habitats did not differ markedly except that shrub cover was greater at Cooper's hawk nest sites, which were also on flatter terrain and closer to roads, forest openings, and human habitation However, these few differences resulted m reducing habitat‐niche overlap considerably (0 538), as was calculated using principal components analysis Mean prey weight was significantly larger for the northern goshawk which follows its 2 2‐fold body weight advantage over Cooper's hawk Although bird prey was of primary importance to both Accipiter, goshawks took twice the proportion of mammals compared to their smaller congener Food‐niche overlap was lowest by prey species overlap (0 470), followed by prey size class overlap (0 529), and highest by vertical foraging zone overlap (0 816) The Cooper's hawk showed the greatest niche breadth for both food and habitat niches indicating it as more of a generalist Overall, niche complementarity of food and habitat dimensions resulted in niche overdispersion along food and habitat dimensions with a total niche overlap (0 504) that was below the competition threshold These results suggested that competition (past and current) was responsible for segregating niches Copyright © 1992, Wiley Blackwell. All rights reserved