Machine learning for optimal selection of sparse triangular system solvers on GPUs

Background: Deep learning (DL) is an Artificial neural network-driven framework with multiple levels of representation for which non-linear modules combined in such a way that the levels of representation can be enhanced from lower to a much abstract level. Though DL is used widely in almost every field, it has largely brought a breakthrough in biological sciences as it is used in disease diagnosis and clinical trials. DL can be clubbed with machine learning, but at times both are used individually as well. DL seems to be a better platform than machine learning as the former does not require an intermediate feature extraction and works well with larger datasets. DL is one of the most discussed fields among the scientists and researchers these days for diagnosing and solving various biological problems. However, deep learning models need some improvisation and experimental validations to be more productive. Objective: To review the available DL models and datasets that are used in disease diagnosis. Methods: Available DL models and their applications in disease diagnosis were reviewed discussed and tabulated. Types of datasets and some of the popular disease related data sources for DL were highlighted. Results: We have analyzed the frequently used DL methods, data types and discussed some of the recent deep learning models used for solving different biological problems. Conclusion: The review presents useful insights about DL methods, data types, selection of DL models for the disease diagnosis.

Download Full-text

Application of L6 Orthogonal Array for Optimal Selection of Some Process Parameters in GMAW Process

Indian Welding Journal ◽

10.22486/iwj.v45i4.141203 ◽

2012 ◽

Vol 45 (4) ◽

pp. 41 ◽

Cited By ~ 1

Author(s):

M. K. Saha ◽

Santanu Das ◽

A. Bandyopadhyay ◽

S. Bandyopadhyay

Keyword(s):

Process Parameters ◽

Orthogonal Array ◽

Optimal Selection ◽

Selection Of

Download Full-text

Application of L6 Orthogonal Array for Optimal Selection of Some Process Parameters in GMAW Process

Indian Welding Journal ◽

10.22486/iwj/2012/v45/i4/141203 ◽

2012 ◽

Vol 45 (4) ◽

pp. 41

Author(s):

M. K. Saha ◽

Santanu Das ◽

A. Bandyopadhyay ◽

S. Bandyopadhyay

Keyword(s):

Process Parameters ◽

Orthogonal Array ◽

Optimal Selection ◽

Selection Of

Download Full-text

Design and implementation of an ADC-based real-time simulator along with an optimal selection of the switch model parameters

Electrical Engineering ◽

10.1007/s00202-021-01237-1 ◽

2021 ◽

Author(s):

Morteza Rezaei Larijani ◽

Mohammad Reza Zolghadri

Keyword(s):

Real Time ◽

Model Parameters ◽

Optimal Selection ◽

Design And Implementation ◽

Selection Of

Download Full-text

Methodology for Determining the Location of River Ports on a Modernized Waterway Based on Non-Cost Criteria: A Case Study of the Odra River Waterway

Sustainability ◽

10.3390/su13063571 ◽

2021 ◽

Vol 13 (6) ◽

pp. 3571

Author(s):

Bogusz Wiśnicki ◽

Dorota Dybkowska-Stefek ◽

Justyna Relisko-Rybak ◽

Łukasz Kolanda

Keyword(s):

Large Scale ◽

Multicriteria Decision Making ◽

Research Process ◽

Optimal Selection ◽

Investment Projects ◽

Odra River ◽

Research Problems ◽

Selection Of ◽

Construction Works

The paper responds to research problems related to the implementation of large-scale investment projects in waterways in Europe. As part of design and construction works, it is necessary to indicate river ports that play a major role within the European transport network as intermodal nodes. This entails a number of challenges, the cardinal one being the optimal selection of port locations, taking into account the new transport, economic, and geopolitical situation that will be brought about by modernized waterways. The aim of the paper was to present an original methodology for determining port locations for modernized waterways based on non-cost criteria, as an extended multicriteria decision-making method (MCDM) and employing GIS (Geographic Information System)-based tools for spatial analysis. The methodology was designed to be applicable to the varying conditions of a river’s hydroengineering structures (free-flowing river, canalized river, and canals) and adjustable to the requirements posed by intermodal supply chains. The method was applied to study the Odra River Waterway, which allowed the formulation of recommendations regarding the application of the method in the case of different river sections at every stage of the research process.

Download Full-text

Color Trend Analysis using Machine Learning with Fashion Collection Images

Clothing and Textiles Research Journal ◽

10.1177/0887302x21995948 ◽

2021 ◽

pp. 0887302X2199594

Author(s):

Ahyoung Han ◽

Jihoon Kim ◽

Jaehong Ahn

Keyword(s):

Machine Learning ◽

Trend Analysis ◽

Image Data ◽

Fashion Industry ◽

Color Palette ◽

Web Scraping ◽

Design Variables ◽

Sales Organizations ◽

Fashion Designers ◽

Selection Of

Fashion color trends are an essential marketing element that directly affect brand sales. Organizations such as Pantone have global authority over professional color standards by annually forecasting color palettes. However, the question remains whether fashion designers apply these colors in fashion shows that guide seasonal fashion trends. This study analyzed image data from fashion collections through machine learning to obtain measurable results by web-scraping catwalk images, separating body and clothing elements via machine learning, defining a selection of color chips using k-means algorithms, and analyzing the similarity between the Pantone color palette (16 colors) and the analysis color chips. The gap between the Pantone trends and the colors used in fashion collections were quantitatively analyzed and found to be significant. This study indicates the potential of machine learning within the fashion industry to guide production and suggests further research expand on other design variables.

Download Full-text

Machine learning approaches to understand and predict rate constants for organic processes in mixtures containing ionic liquids

Physical Chemistry Chemical Physics ◽

10.1039/d0cp04227g ◽

2021 ◽

Vol 23 (4) ◽

pp. 2742-2752

Author(s):

Tamar L. Greaves ◽

Karin S. Schaffarczyk McHale ◽

Raphael F. Burkart-Radke ◽

Jason B. Harper ◽

Tu C. Le

Keyword(s):

Machine Learning ◽

Ionic Liquids ◽

Rate Constants ◽

Learning Approaches ◽

Learning Models ◽

Organic Reaction ◽

Machine Learning Models ◽

Selection Of

Machine learning models were developed for an organic reaction in ionic liquids and validated on a selection of ionic liquids.

Download Full-text

Optimal Selection of Conductors in Three-Phase Distribution Networks Using a Discrete Version of the Vortex Search Algorithm

Computation ◽

10.3390/computation9070080 ◽

2021 ◽

Vol 9 (7) ◽

pp. 80

Author(s):

John Fernando Martínez-Gil ◽

Nicolas Alejandro Moyano-García ◽

Oscar Danilo Montoya ◽

Jorge Alexander Alarcon-Villamil

Keyword(s):

Objective Function ◽

Power Flow ◽

Phase Distribution ◽

Search Algorithm ◽

Distribution Networks ◽

Discrete Version ◽

Optimal Selection ◽

Flow Method ◽

Three Phase ◽

Selection Of

In this study, a new methodology is proposed to perform optimal selection of conductors in three-phase distribution networks through a discrete version of the metaheuristic method of vortex search. To represent the problem, a single-objective mathematical model with a mixed-integer nonlinear programming (MINLP) structure is used. As an objective function, minimization of the investment costs in conductors together with the technical losses of the network for a study period of one year is considered. Additionally, the model will be implemented in balanced and unbalanced test systems and with variations in the connection of their loads, i.e., Δ− and Y−connections. To evaluate the costs of the energy losses, a classical backward/forward three-phase power-flow method is implemented. Two test systems used in the specialized literature were employed, which comprise 8 and 27 nodes with radial structures in medium voltage levels. All computational implementations were developed in the MATLAB programming environment, and all results were evaluated in DigSILENT software to verify the effectiveness and the proposed three-phase unbalanced power-flow method. Comparative analyses with classical and Chu & Beasley genetic algorithms, tabu search algorithm, and exact MINLP approaches demonstrate the efficiency of the proposed optimization approach regarding the final value of the objective function.

Download Full-text