Statistical segmentation and structural recognition for floor plan interpretation

A generic method for floor plan analysis and interpretation is presented in this article. The method, which is mainly inspired by the way engineers draw and interpret floor plans, applies two recognition steps in a bottom-up manner. First, basic building blocks, i.e., walls, doors, and windows are detected using a statistical patch-based segmentation approach. Second, a graph is generated, and structural pattern recognition techniques are applied to further locate the main entities, i.e., rooms of the building. The proposed approach is able to analyze any type of floor plan regardless of the notation used. We have evaluated our method on different publicly available datasets of real architectural floor plans with different notations. The overall detection and recognition accuracy is about 95 %, which is significantly better than any other state-of-the-art method. Our approach is generic enough such that it could be easily adopted to the recognition and interpretation of any other printed machine-generated structured documents.     

Cognitive-behavioral and pharmacologic interventions for childrens' distress during painful medical procedures.

This study evaluated the efficacy of a cognitive–behavioral intervention package and a low-risk pharmacologic intervention (oral Valium), as compared with a minimal treatment-attention control condition, in reducing children's distress during bone marrow aspirations. The subjects were 56 leukemia patients who ranged in age from 3 years to 13 years. The three intervention conditions were delivered in a randomized sequence within a repeated-measures counterbalanced design. Dependent outcome measures included observed behavioral distress scores, self-reported pain scores, pulse rate, and blood pressure scores. Repeated-measures analyses of variance indicated that children in the cognitive-behavior therapy condition had significantly lower behavioral distress, lower pain ratings, and lower pulse rates than when they were in the attention-control condition. When children were in the Valium condition, they exhibited no significant differences from the attention control condition except that they had lower diastolic blood pressure scores. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Context awareness in network selection for dynamic environments

Mobile devices of new generation are able to connect to multiple networks and to constitute new infrastructureless networks. These dynamic environments require new security paradigms and automatic mechanisms to minimize user intervention. Our goal is the definition of a new concept of distance that considers the current domain constraints and the user preferences. This paper addresses some of the problems of these complex environments by using Multidimensional Scaling (MDS) techniques. We also propose collaborative mechanisms for automatic environment marking. Based on these ideas we have developed Pervasive Interaction Manager (PervsIM), a decision mechanism that selects the most appropriate network or peer to interact with. Besides we have defined an embedded access control module which ensures that PervsIM decisions are followed by all applications. Furthermore, several simulation results and implementation details outline how these results can be incorporated in today’s mobile devices.     

Critical Success Factors for Managing Systems Integration

System integration is a complex technological task, and an infrastructure decision that seems right today might well be obsolete tomorrow. This article proposes a framework of critical success factors (CSFs) that can be used to manage IS integration projects, according to a firm's current stage of IT integration maturity and other IS infrastructure characteristics. To demonstrate the potential utility of this CSF framework, the authors analyze case studies at two firms using 86 metrics for 20 CSFs developed by the authors.     

Classification of Potato Chips Using Pattern Recognition

ABSTRACT: An approach to classify potato chips using pattern recognition from color digital images consists of 5 steps: (1) image acquisition, (2) preprocessing, (3) segmentation, (4) feature extraction, and (5) classification. Ten chips prepared for each of the following 6 conditions were examined: 2 pretreatments (blanched and unblanched) at 3 temperatures (120°C, 150°C, and 180°C). More than 1500 features were extracted from each of the 60 images. Finally, 11 features were selected according to their classification attributes. Seven different classification cases (for example, classification of the 6 classes or distinction between blanched and unblanched samples) were analyzed using the selected features. Although samples were highly heterogeneous, using a simple classifier and a small number of features, it was possible to obtain a good performance value in all cases: classification of the 6 classes was in the confidence interval between 78% and 89% with a probability of 95%.     

Cytologic diagnosis of Chlamydia in cervicovaginal secretions. Use of a Papanicolaou stain modification with buffered wright solution

OBJECTIVE: To carry out a prospective study on 1,569 females to evaluate the diagnostic utility of adding buffered Wright solution to Papanicolaou stain for observing cytoplasmic inclusions in cervicovaginal cytology. STUDY DESIGN: Group A had multivacuolated cells and group B, granules (not in a vacuole) in the cytoplasm of low-intermediate epithelial or parabasal cells. There were 7 patients in group A and 16 in group B. Two duplicate plates of cervicovaginal secretions were obtained from each patient before and after treatment; one was stained with Papanicolaou stain and the other with our variant. The trial of therapy consisted of doxycycline (effectiveness for statistical analysis = 0.9) in oral doses of 100 mg every 12 hours for 7 days; 7 days after the beginning of treatment, check samples were obtained. RESULTS: In group A, six patients had cytoplasmic inclusions with the variant stain, and two had cytoplasmic inclusions with Papanicolaou stain. The binomial test revealed that probably six of the seven patients had infections with Chlamydia (P = .372) and that in 100% of cases, the variant stain showed cytoplasmic inclusions, while Papanicolaou stain was observed in 33% of cases. These findings were morphologically and statistically proven (P = .124) on control slides with posttreatment absence of multivacuolated cells. CONCLUSION: In relation to the selection criteria for B group, the intracytoplasmic granules found in parabasal and low intermediate cells had no relation to Chlamydia. The study demonstrated the superiority of our variant of Papanicolaou stain for cervicovaginal Chlamydia diagnosis.