Health State Classification of a Spherical Tank Using a Hybrid Bag of Features and K-Nearest Neighbor

Feature analysis puts a great impact in determining the various health conditions of mechanical vessels. To achieve balance between traditional feature extraction and the automated feature selection process, a hybrid bag of features (HBoF) is designed for multiclass health state classification of spherical tanks in this paper. The proposed HBoF is composed of (a) the acoustic emission (AE) features and (b) the time and frequency based statistical features. A wrapper-based feature chooser algorithm, Boruta, is utilized to extract the most intrinsic feature set from HBoF. The selective feature matrix is passed to the multi-class k-nearest neighbor (k-NN) algorithm to differentiate among normal condition (NC) and two faulty conditions (FC1 and FC2). Experimental results demonstrate that the proposed methodology generates an average 99.7% accuracy for all working conditions. Moreover, it outperforms the existing state-of-art works by achieving at least 19.4%.

International phase 1 study protocol to develop a health state classification system for a preference-based measure for women with breast cancer: the BREAST-Q Utility module

IntroductionConcerns unique to women with breast cancer can include impact of cancer on body image, sexual well-being and changes in breast appearance and sensation. These important issues are not captured by the existing generic preference-based measures (PBMs) and no breast cancer-specific PBM currently exists. This Phase 1 protocol describes a mixed-methods study to develop and validate the descriptive health state classification system for a breast cancer-specific PBM, called the BREAST-Q Utility module.Methods and analysisA heterogeneous sample of women aged 18 years and older diagnosed with breast cancer who are undergoing or have had treatment for breast cancer will be invited to participate in qualitative interviews. Participants will be asked to describe impact of their diagnosis and treatment(s) on their health-related quality of life (HRQOL). Interviews will be audio recorded, transcribed verbatim and coded using a line-by-line approach. At the end of each interview, based on each participant’s cancer treatment history, patients will complete the mastectomy, breast-conserving therapy or reconstruction module of BREAST-Q, with modified 5-point Likert scale to measure importance of the BREAST-Q concepts. Both sources of data will be analysed to identify the most important HRQOL concerns.A conceptual framework and item pool will be developed from the qualitative dataset. Preliminary version of the BREAST-Q Utility module will be created and refined at an in-person meeting of multidisciplinary experts. Content validity of the Utility module will be examined (cognitive debriefing, expert feedback). Psychometric properties of Utility module will be evaluated in a large sample of women with breast cancer.Ethics and disseminationThe study has been approved by Hamilton Integrated Research Ethics Board, Canada. Results of this study will be presented at international conferences and published in peer-reviewed journals.