Supervised and unsupervised learning to classify scoliosis and healthy subjects based on non-invasive rasterstereography analysis

The aim of our study was to classify scoliosis compared to to healthy patients using non-invasive surface acquisition via Video-raster-stereography, without prior knowledge of radiographic data. Data acquisitions were made using Rasterstereography; unsupervised learning was adopted for clustering and supervised learning was used for prediction model Support Vector Machine and Deep Network architectures were compared. A M-fold cross validation procedure was performed to evaluate the results. The accuracy and balanced accuracy of the best supervised model were close to 85%. Classification rates by class were measured using the confusion matrix, giving a low percentage of unclassified patients. Rasterstereography has turned out to be a good tool to distinguish subject with scoliosis from healthy patients limiting the exposure to unnecessary radiations.

Cefepime precision dosing tool: From Standard to Precise Dose Using Nonparametric Population Pharmacokinetics

Cefepime is the second most common cephalosporin used in U.S. hospitals. We aim to develop and validate cefepime population pharmacokinetic (PK) model and integrate into precision dosing tool for implementation. Two datasets (680 patients) were used to build cefepime PK model in Pmetrics, and three datasets (34 patients) were used for the validation. A separate application dataset (115 patients) was used for the implementation and validation of a precision dosing tool. The model support points and covariates were used to generate the optimal initial dose (OID). Cefepime PK was described by a two-compartment model including weight and creatinine clearance (CrCl) as covariates. The median rate of elimination was 0.30 hr −1 (adults) and 0.96 hr −1 (pediatrics), central volume of distribution 13.85 L, and rate of transfer from the central to the peripheral compartments 1.22 hr −1 and from the peripheral to the central compartments 1.38 hr −1 . After integration in BestDose, the observed vs. predicted cefepime concentration fit using the application dataset was excellent (R 2 >0.98) and the median difference between observed and what BestDose predicted in a second occasion was 4%. For OID, cefepime 0.5-1g 4-hour infusion q8-24hr with CrCl<70 mL/min was needed to achieve a target range of free trough:MIC 1-4 at MIC 8 mg/L, while continuous infusion was needed for higher CrCl and weight values. In conclusion, we developed and validated a cefepime model for clinical application. The model was integrated in a precision dosing tool for implementation and the median concentration prediction bias was 4%. OID algorithm was provided.

Conceptual and model support for the development of an innovative-active university

The monograph is devoted to the development of theoretical-methodical and model- information basis for the construction of innovative- active HEI on the basis of autonomy of its activities, quality of education, anti-corruption. Trends in the modernization of the world system of higher education have been identified, a study of the phenomenon of "autonomous, innovative- active university" has been conducted, and a list of factors influencing the increase in the competitiveness of individual HEIs has been formed. Based on the analysis of the legislative basis and state initiatives, the opportunities for the development of an innovative-active university (IAU) have been identified. The stratification of HEI of Ukraine according to the level of their educational, scientific and technical, innovative and international activities was carried out. Conceptual and methodological bases of IAU construction are developed, the mechanism of its functioning is formed and conceptual bases of formation of system of corporate management of rendering of HEI educational services on the principles of counteraction of corruption are offered. Recommended for researchers, professionals in education, economics, information management and protection, teachers, graduate students and students of higher education institutions.

Classification of Spam Text using SVM

The necessity for spam detection is particularly pertinent nowadays, as there is no quality control over social media, and users have the ability to distribute unverified material, therefore facilitating fraud and deceit. Spam detection can aid in the prevention of such fraud. This scenario has developed mostly as a result of the distribution of disparate, unconfirmed information via shopping websites, emails, and text messages (SMS). There are several ways of categorising and identifying spam. Each of them has certain advantages and disadvantages. The machine learning model “Support Vector Machine” is employed to detect spam in this case. SVM is a basic concept: the method proposes a line or hyperplane to classify the data. The model can categorise any type of text into a given category after being fed a set of labelled training data for each category.

Motives for Substance Use in Daily Life: A Systematic Review of Studies Using Ecological Momentary Assessment

The motivational model of substance use posits that four motive subtypes (coping, enhancement, social, conformity) dynamically interact with contextual factors to affect decisions about substance use. Yet prior studies assessing the motivational model have relied on between-persons, cross-sectional evaluations of trait motives. We systematically reviewed studies using ecological momentary assessment (EMA; N = 64) on motives for substance use to examine methodological features of EMA studies examining the motivational model, support for the motivational model between and within individuals, and associations between trait motives and daily processes. Results of the reviewed studies provide equivocal support for the motivational model and suggest that EMA measures and trait measures of motives might not reflect the same construct. The reviewed body of research indicates that most studies have not examined the momentary and dynamic nature of the motivational model, and more research is needed to inform interventions that address heterogeneous reasons for substance use in daily life.

Peramalan Harga Saham Menggunakan Metode Support Vector Machine (SVM)

Penelitian ini bertujuan untuk menganalisis ketepatan model Support Verctor Machine (SVM) dalam memprediksi harga saham. Kombinasi dari 28 periode perkiraan dan 30 periode input indikator teknis digunakan. Data transaksi saham dari 31 perusahaan yang terdaftar di Bursa Efek Indonesia dan aktif diperdagangkan antara Maret 2006 dan Februari 2018 digunakan. Hasil menunjukkan bahwa kinerja sistem tertinggi tidak terjadi ketika indikator teknis periode input kira-kira sama dengan periode perkiraan. Meskipun demikian, hasil kinerja saham perusahaan berbeda-beda. Namun model prediksi dengan SVM memberikan keuntungan yang lebih besar dibandingkan dengan strategi buy and hold.