Wyniki wyszukiwania - BazTech

1

Development of Ensemble Tree Models for Generalized Blood Glucose Level Prediction

Annals of Computer Science and Information Systems

|

2022

|

Vol. 33

55--61

EN

Type-1 diabetes (T1D) patients must carefully monitor their insulin doses to avoid serious health complications. An effective regimen can be designed by predicting accurate blood glucose levels (BGLs). Several physiological and data-driven models for BGL prediction have been designed. However, less is known on the combination of different traditional machine learning (ML) algorithms for BGL prediction. Furthermore, most of the available models are patient-specific. This research aims to evaluate several traditional ML algorithms and their novel combinations for generalized BGL prediction. The data of forty T1D patients were generated using the Automated Insulin Dosage Advisor (AIDA) simulator. The twenty-four hour time-series contained samples at fifteen-minute intervals. The training data was obtained by joining eighty percent of each patient's time-series, and the remaining twenty percent time-series was joined to obtain the testing data. The models were trained using multiple patients' data so that they could make predictions for multiple patients. The traditional non-ensemble algorithms: linear regression (LR), support vector regression (SVR), k-nearest neighbors (KNN), multi-layer perceptron (MLP), decision tree (DCT), and extra tree (EXT) were evaluated for forecasting BGLs of multiple patients. A new ensemble, called the Tree-SVR model, was developed. The BGL predictions from the DCT and the EXT models were fed as features into the SVR model to obtain the final outcome. The ensemble approach used in this research was based on the stacking technique. The Tree-SVR model outperformed the non-ensemble models (LR, SVR, KNN, MLP, DCT, and EXT) and other novel Tree variants (Tree-LR, Tree-MLP, and Tree-KNN). This research highlights the utility of designing ensembles using traditional ML algorithms for generalized BGL prediction.

2

Stacking-based multi-objective evolutionary ensemble framework for prediction of diabetes mellitus

Singh Namrata, Singh Pradeep

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

1--22

EN

Diabetes mellitus (DM) is a combination of metabolic disorders characterized by elevated blood glucose levels over a prolonged duration. Undiagnosed DM can give rise to a host of associated complications like retinopathy, nephropathy and neuropathy and other vascular abnormalities. In this background, machine learning (ML) approaches can play an essential role in the early detection, diagnosis and therapeutic monitoring of the disease. Recently, several research works have been proposed to predict the onset of DM. To this end, we develop a stacking-based evolutionary ensemble learning system ‘‘NSGA-II-Stacking’’ for predicting the onset of Type-2 diabetes mellitus (T2DM) within five years. For this purpose, publicly accessible Pima Indian diabetes (PID) dataset is utilized. As a data pre-processing step, the missing values and outliers are identified and imputed with the median values. For base learner selection, a multi-objective optimization algorithm is utilized which simultaneously maximizes the classification accuracy and minimizes the ensemble complexity. As for model combination, k-nearest neighbor (K-NN) is employed as a meta-classifier that combines the predictions of the base learners. The comparative results demonstrate that the proposed NSGA-II-Stacking method significantly outperforms several individual ML approaches and conventional ensemble approaches. In terms of performance metrics, the proposed system achieves the highest accuracy of 83.8 %, sensitivity of 96.1 %, specificity of 79.9 %, f-measure of 88.5 % and area under ROC curve of 85.9 %.

3

Ocena wpływu wybranych parametrów profilowań georadarowych w badaniach podłoża gruntowego na potrzeby budownictwa na przykładzie zrębu Zakrzówka

Karczewski J., Ortyl Ł., Mazurkiewicz E.

Przegląd Geologiczny

|

2017

|

Vol. 65, nr 10/2

796--802

EN

The identification of bedrock for construction purposes in areas threatened by discontinuous deformations can be accomplished using various geophysical methods. The paper presents the results of studies conducted using the GPR method in the Zakrzówek horst area in Cracow as a site rich in karst structures (caves, cavities, sinkholes). A number of tests were carried out on the field using GPR equipment: ProEx System and RAMAC/GPR CU II of the Swedish company Mala Geoscience. During measurements 250 MHz shielded antennas were used. The following measurement parameters were changed during tests: sampling frequency, number ofstacks and distance between traces. The influence of the above parameters on the quality ofrecorded GPR images was analyzed.

4

Fifty years of stacking

Rashed M.

Acta Geophysica

|

2014

|

Vol. 62, no. 3

505--528

EN

Common-Mid-Point (CMP) stacking is a major process to enhance signal-to-noise ratio in seismic data. Since its appearance fifty years ago, CMP stacking has gone through different phases of prosperity and negligence within the geophysical community. During those times, CMP stacking developed from a simple process of averaging into a sophisticated process that involves complicated mathematics and state-of-the-art computation. This article summarizes the basic principles, assumptions, and violations related to the CMP stacking technique, presents a historical overview on the development stages of CMP stacking, and discusses its future potentiality.

5

Wzbogacanie analitu w kapilarze w wysokosprawnych technikach elektromigracyjnych - spiętrzanie

Dziomba S., Kowalski P., Olędzka I, Bączek T.

Analityka : nauka i praktyka

|

2013

|

nr 4

18--25

PL

Wykorzystując w precyzyjny sposób możliwości systemów elektroforetycznych, możemy uzyskać efekt wzbogacenia analitów w kapilarze, a tym samym wzmocnienie sygnału nawet do kilkuset tysięcy razy, co umożliwia znaczące obniżenie granicy wykywalności analitów w opracowanych metodach.

6

An Ergonomics Approach Model to Prevention of Occupational Musculoskeletal Injuries

Koltan A.

International Journal of Occupational Safety and Ergonomics

|

2009

|

Vol. 15, No. 1

113--124

EN

The objective of this study was to prevent occupational musculoskeletal injuries. Our workers stacked boxes of ceramics weighing 10–27 kg, making low back pain common in our enterprise. In all the stacking stations, recommended weight limits (RWL) were separately calculated using the revised National Institute for Occupational Health lifting equation. Since the boxes weighed significantly more than the RWL, we developed a new ergonomic design that completely changed the stacking process. The load put on the workers’ waist vertebrae in the new and the old stacking methods was compared to evaluate the success of the new ergonomic design, using Newton’s third law of motion. Thanks to the new ergonomic design, the load on the workers’ vertebrae decreased by 80%. Due to its simple technology and its very low cost compared to robots, the new ergonomic design can be commonly used in enterprises with repeated and constraining stacking.

7

Quantum Chemical Study of the Nature of Stacking Interactions of 2-Oxo-adenine with Native B-DNA Purines

Czyżnikowska Ż., Zaleśny R., Cysewski P.

Polish Journal of Chemistry

|

2008

|

Vol. 82, nr 12

2269-2279

EN

The scan of intermolecular interaction energy surfaces for stacked complexes of 2-oxoadenine (AA) with purine bases was performed using the density-fitting approach at the MP2 level of theory with correlation-consistent Dunning's basis sets. Moreover, the convergence of stabilization energy to the basis-set limit was analyzed using two-point extrapolation formula proposed by Halkier et al. Four different complexes in two different context alignments appearing in B-DNA were considered, namely 5c-A/A-3', 5'-A/AA-3', 5c-AA/A-3', 5c-G/A-3', 5'-G/AA-3', 5'-A/G-3' and 5'-AA/G-3'. The results of ab initio calculation allow to arrive at conclusion that oxidation of adenine at C2 position does not lead to significant changes in the structural parameters of stacked complexes. However, the modification of adenine by hydroxyl radical affects noticeably the stabilization energy only for 5'-G/AA-3' complex. In order to explain the source of this large stabilization effect, the intermolecular interaction energy decomposition was performed at the MP2/aug-cc-pVDZ level of theory for the minima on the interaction energy surfaces of adenine (2-oxo-ad e nine) with guanine. It was found that the observed larger stabilization energy for 5'-G/AA-3' compared to 5'-G/A-3' arises from the electrostatic interactions.

8

An ab initio Post SCF Study on Stacking Interactions of 8-Oxo-9-methylguanine with Four Canonical DNA Bases

Cysewski P., Czyżnikowska-Balcerak Z., Szefler B.

Polish Journal of Chemistry

|

2003

|

Vol. 77 / nr 10

1287-1300

EN

Stacking properties of 8-oxo-9-methylguanine interacting with all four canonical nucleic acid bases were studied and compared to dimers formed by unmodified guanine. The impact of twist angle and base-base separation distance on the stacked dimers energies were analyzed based on MP2/6-31G*(d=0.25) quantum chemistry and Amber molecular mechanics single point calculations. Besides, solvent affects were taken into account within PCM formalism. Presented data lead to the conclusion that 8-oxo-9-methylguanine has significantly different stacking properties compared to standard guanine. Although the dimers stabilization energies are similar for standard and modified 9-methylguanine structural properties are significantly diverse. The most stable dimers formed by 8-oxo- 9-methyl-G are characterized by different conformations compared to canonical 9- methylguanine. This may lead to complete alteration of stacking abilities. For example, 8-oxo-9-methyl-G if paired with 9-methyl-G exhibits strong stacking repulsion in the twist region, for which 9-methylguanine/9-methylguanine dimer has major attraction. The most stable stacking pair is formed by 8-oxo-9-methylguanine with 9-methylguanine, while the least stable one corresponds to 8-oxo-9-methylguanine/1-methylcytosine and 9-methylguanine/1-methylcytosine pairs. Besides, significant changes of stacked complexes polarities are observed, especially in case of pairs containing methylated pyrimidines. Polarities of dimer formed by two 9-methylated purines are much less sensitive to the environment but dipole moments of 9-methylpurine/1-methylpyrimidine stacking pairs are significantly altered by taking into account solvent effects. The observed differences in stacking properties between standard and modified guanine are related mainly to charge redistribution rather than direct interactions of O8 oxygen. The correlation energies of stacking dimers are very high and are main source of pairs stabilization. Both 9-methylguanine and 8-oxo-9-methylguanine are characterized by similar values of correlation energy.

9

Crystal and molecular structure of 7-chloropropyl-8-aminotheophylline semibenzene solvate

Karczmarzyk Z., Pawłowski M.

Polish Journal of Chemistry

|

1998

|

Vol. 72, nr 4

793-798

EN

The title compound, 8-amino-7-chloropropyl-1,3-dimethyl-3,7-dihydro-1H-purine-2,6-dione semibenzene solvate, C10H14N5O2Clx1/2C6H6, crystallizes in the triclinic system, space group P1, with cell contants a=8.291(7), b=9.224(6), c=11.098(3)A, alpha=72.31(4), beta=78.39(4) and gamma-63.95(7) degree. Asymmetric unit of the unit cell contains a molecule of 7-chloropropyl-8-aminotheophylline and a half of the benzene molecule; the centre of the benzene ring lies in the center of symmetry. The fused rings of the purine system are planar and are inclined with respect to each other at an angle 0.8(1) degree. The chloroalkyl group in the 7 position of the theophylline has a gauche- gauche-trans conformation. The crystal structure is stabilized by a network of intermolecular hydrogen bonds. Moreover, theophylline skeletons and benzene rings show significant stacking.