Advanced Feature Extraction Methods from Images of Drillings in Melamine Faced Chipboard for Automatic Diagnosis of Drill Wear.

In this paper, a novel approach to evaluation of feature extraction methodologies is presented. In the case of machine learning algorithms, extracting and using the most efficient features is one of the key problems that can significantly influence overall performance. It is especially the case with parameter-heavy problems, such as tool condition monitoring. In the presented case, images of drilled holes are considered, where state of the edge and the overall size of imperfections have high influence on product quality. Finding and using a set of features that accurately describes the differences between the edge that is acceptable or too damaged is not always straightforward. The presented approach focuses on detailed evaluation of various feature extraction approaches. Each chosen method produced a set of features, which was then used to train a selected set of classifiers. Five initial feature sets were obtained, and additional ones were derived from them. Different voting methods were used for ensemble approaches. In total, 38 versions of the classifiers were created and evaluated. Best accuracy was obtained by the ensemble approach based on Weighted Voting methodology. A significant difference was shown between different feature extraction methods, with a total difference of 11.14% between the worst and best feature set, as well as a further 0.2% improvement achieved by using the best voting approach.

Improved Drill State Recognition during Milling Process Using Artificial Intelligence.

In this article, an automated method for tool condition monitoring is presented. When producing items in large quantities, pointing out the exact time when the element needs to be exchanged is crucial. If performed too early, the operator gets rid of a good drill, also resulting in production downtime increase if this operation is repeated too often. On the other hand, continuing production with a worn tool might result in a poor-quality product and financial loss for the manufacturer. In the presented approach, drill wear is classified using three states representing decreasing quality: green, yellow and red. A series of signals were collected as training data for the classification algorithms. Measurements were saved in separate data sets with corresponding time windows. A total of ten methods were evaluated in terms of overall accuracy and the number of misclassification errors. Three solutions obtained an acceptable accuracy rate above 85%. Algorithms were able to assign states without the most undesirable red-green and green-red errors. The best results were achieved by the Extreme Gradient Boosting algorithm. This approach achieved an overall accuracy of 93.33%, and the only misclassification was the yellow sample assigned as green. The presented solution achieves good results and can be applied in industry applications related to tool condition monitoring.

A video to improve patient and surrogate understanding of cardiopulmonary resuscitation choices in the ICU: a randomized controlled trial.

OBJECTIVE: To determine if a video depicting cardiopulmonary resuscitation and resuscitation preference options would improve knowledge and decision making among patients and surrogates in the ICU. DESIGN: Randomized, unblinded trial. SETTING: Single medical ICU. PATIENTS: Patients and surrogate decision makers in the ICU. INTERVENTIONS: The usual care group received a standard pamphlet about cardiopulmonary resuscitation and cardiopulmonary resuscitation preference options plus routine code status discussions with clinicians. The video group received usual care plus an 8-minute video that depicted cardiopulmonary resuscitation, showed a simulated hospital code, and explained resuscitation preference options. MEASUREMENTS AND MAIN RESULTS: One hundred three patients and surrogates were randomized to usual care. One hundred five patients and surrogates were randomized to video plus usual care. Median total knowledge scores (0-15 points possible for correct answers) in the video group were 13 compared with 10 in the usual care group, p value of less than 0.0001. Video group participants had higher rates of understanding the purpose of cardiopulmonary resuscitation and resuscitation options and terminology and could correctly name components of cardiopulmonary resuscitation. No statistically significant differences in documented resuscitation preferences following the interventions were found between the two groups, although the trial was underpowered to detect such differences. A majority of participants felt that the video was helpful in cardiopulmonary resuscitation decision making (98%) and would recommend the video to others (99%). CONCLUSIONS: A video depicting cardiopulmonary resuscitation and explaining resuscitation preference options was associated with improved knowledge of in-hospital cardiopulmonary resuscitation options and cardiopulmonary resuscitation terminology among patients and surrogate decision makers in the ICU, compared with receiving a pamphlet on cardiopulmonary resuscitation. Patients and surrogates found the video helpful in decision making and would recommend the video to others.

Development, validation, and results of a survey to measure understanding of cardiopulmonary resuscitation choices among ICU patients and their surrogate decision makers.

BACKGROUND: Shared-decision-making about resuscitation goals of care for intensive care unit (ICU) patients depends on a basic understanding of cardiopulmonary resuscitation (CPR). Our objective was to develop and validate a survey to assess comprehension of CPR among ICU patients and surrogate decision-makers. METHODS: We developed a 12-item verbally-administered survey incorporating input from patients, clinicians, and expert focus groups. RESULTS: We administered the survey to 32 ICU patients and 37 surrogates, as well as to 20 resident physicians to test discriminative validity. Median (interquartile range) total knowledge scores were 7 (5-10) for patients, 9 (7-12) for surrogates, and 14.5 (14-15) for physicians (p <.001). Forty-four percent of patients and 24% of surrogates could not explain the purpose of CPR. Eighty-eight percent of patients and 73% of surrogates could not name chest compressions and breathing assistance as two components of CPR in the hospital. Forty-one percent of patients and 24% of surrogates could not name a single possible complication of CPR. Forty-three percent of participants could not specify that CPR would be performed with a full code order and 25% of participants could not specify that CPR would not be performed with a do-not-resuscitate order. Internal consistency (Cronbach's alpha = 0.97) and test-retest reliability (Pearson correlation = 0.96, p < .001) were high. CONCLUSIONS: This easily administered survey, developed to measure knowledge of CPR and resuscitation preference options among ICU patients and surrogates, showed strong face validity, content validity, internal consistency, test-retest reliability, and discriminative validity. A substantial proportion of ICU patients and surrogates decision-makers have poor knowledge of CPR and basic resuscitation options.