Multilevel segmentation of histopathological images using cooccurrence of tissue objects

This paper presents a new approach for unsupervised segmentation of histopathological tissue images. This approach has two main contributions. First, it introduces a new set of high-level texture features to represent the prior knowledge of spatial organization of the tissue components. These texture features are defined on the tissue components, which are approximately represented by tissue objects, and quantify the frequency of two component types being cooccurred in a particular spatial relationship. As they are defined on components, rather than on image pixels, these object cooccurrence features are expected to be less vulnerable to noise and variations that are typically observed at the pixel level of tissue images. Second, it proposes to obtain multiple segmentations by multilevel partitioning of a graph constructed on the tissue objects and combine them by an ensemble function. This multilevel graph partitioning algorithm introduces randomization in graph construction and refinements in its multilevel scheme to increase diversity of individual segmentations, and thus, improve the final result. The experiments on 200 colon tissue images reveal that the proposed approach--the object cooccurrence features together with the multilevel segmentation algorithm--is effective to obtain high-quality results. The experiments also show that it improves the segmentation results compared to the previous approaches.     

A novel tool path/posture optimization concept to avoid chatter vibration in machining – Proposed concept and its verification in turning

This research presents novel strategies to optimize tool path/posture to avoid chatter vibration in various machining operations. It is well known that the chatter stability depends on tool geometry and cutting conditions; whereas it is less known that it also depends on tool path/posture relative to the dynamically most compliant direction. In order to realize an intelligent tool path/posture planning with consideration of the chatter stability, a simple index is proposed to represent the machining stability due to the tool path/posture. As an example, the stability in turning is considered, and the use of proposed stability index is verified experimentally.     

Motorcycle accidents,rider behaviour,and psychological models

The aims of the present study were to: (a) investigate the factor structure of the Motorcycle Rider Behaviour Questionnaire (MRBQ) [Elliott, M.A., Baughan, B.J., Sexton, B.F., 2007. Errors and violations in relation to motorcyclists’ crash risk. Accident Analysis and Prevention 39, 491–499] in among Turkish riders, and (b) study the relationships between different types of rider behaviour and motorcyclists’ active and passive accidents and offences, and (c) investigate the usefulness of the Theory of Planned Behaviour (TPB), Health Belief Model (HBM), and Locus of Control (T-LOC) in explaining rider behaviours. MRBQ was administered to a sample of motorcyclists (N = 451). Principal components analysis yielded a 5-factor solution including traffic errors, control errors, speed violations, performance of stunts, and use of safety equipment. Annual mileage was related to higher number of active and passive accidents and offences whereas age was related to lower number of active and passive accidents. Stunts were the main predictors of active accidents and offences. Speeding violations predicted offences. Stunts and speeding violations were associated with the fate factor of the T-LOC, and with attitudes, subjective norms, and intention components of TPB, and cues to action and perceived severity components of the HBM. Use of safety equipment was related to the high level of perceived behavioural control and intention components of the TPB, the low score of perceived barriers component of the HBM, and the low fate factor of the T-LOC. While traffic errors were associated with the high score of perceived barriers and cues to action component of the HBM, control errors were related to the high score of vehicle and environment factor of the T-LOC.