Unsupervised learning about 4D features of microparticle motion.

Material clusters of different sizes are known to exist in high-temperature plasmas due to plasma-wall interactions. The facts that these clusters, ranging from sub-microns to above mm in size, can move from one location to another quickly and that there are a lot of them make high-speed imaging and tracking one of the best, effective, and sometimes only diagnostic. An unsupervised machine learning technique based on deconvolutional neural networks is developed to analyze two-camera videos of high-temperature microparticles generated from exploding wires. The neural network utilizes a locally competitive algorithm to infer representations and optimize a dictionary composed of kernels, or basis vectors, for image analysis. Our primary goal is to use this method for feature recognition and prediction of the time-dependent three-dimensional (or "4D") microparticle motion. Features equivalent to local velocity vectors have been identified as the dictionary kernels or "building blocks" of the scene. The dictionary elements from the left and right camera views are found to be strongly correlated and satisfy the projection geometrical constraints. The results show that unsupervised machine learning techniques are promising approaches to process large sets of images for high-temperature plasmas and other scientific experiments. Machine learning techniques can be useful to handle the large amount of data and therefore aid the understanding of plasma-wall interaction.

Orthodontic treatment priority: a comparison of two indices.

Approval for state sponsored funding of orthodontic treatment is often decided using an index of malocclusion. The purpose of this study was to determine whether two indices used for prioritizing patients would identify different groups of individuals qualifying for orthodontic treatment funding approval. In addition, the characteristics of patients approved using different indices were compared. The records of 40 patients previously submitted for state medicaid funding approval were evaluated by three study examiners using two orthodontic treatment priority indices, the Salzmann Handicapping Malocclusion Assessment (Salzmann) and the Index of Orthodontic Treatment Need (IOTN). Comparisons were made between state medicaid and study examiner Salzmann scores, rankings, and funding decisions, and between study examiner Salzmann rankings, IOTN rankings, and funding decisions. Correlation and rank correlation coefficients between the state and study examiners' Salzman scores were high (r = 0.74; p < 0.001, and R = 0.77; p < 0.001). Rank correlation analysis of the study examiners' Salzmann and IOTN values demonstrated a weaker relationship (R = 0.40; p < 0.02). Agreement on funding decisions, evaluated by the Kappa statistic, was greater between the two Salzmann evaluations (K = 0.57) than between the study examiners' Salzmann and IOTN evaluations (K = 0.14). As expected, depending on the method used to determine orthodontic treatment funding priority, different patients were likely to be identified for treatment approval. The characteristics of patients whose treatment was approved was closely related to the criteria defined by the method employed.