scholarly journals ML4Chem: A Machine Learning Package for Chemistry and Materials Science

2020 ◽  
Author(s):  
Muammar El Khatib ◽  
Wibe de Jong
Keyword(s):  
Machine Learning ◽  
Materials Science ◽  
Building Blocks ◽  
Ease Of Use ◽  
Model Optimization ◽  
Data Preparation ◽  
Experience Design ◽  
User Experience Design ◽  
Regression Algorithms ◽  
Machine Learning Models

ML4Chem is an open-source machine learning library for chemistry and materials science. It provides an extendable platform to develop and deploy machine learning models and pipelines and is targeted to the non-expert and expert users. ML4Chem follows user-experience design and offers the needed tools to go from data preparation to inference. Here we introduce its atomistic module for the implementation, deployment, and reproducibility of atom-centered models. This module is composed of six core building blocks: data, featurization, models, model optimization, inference, and visualization. We present their functionality and ease of use with demonstrations utilizing neural networks and kernel ridge regression algorithms.

scholarly journals ML4Chem: A Machine Learning Package for Chemistry and Materials Science

2020 ◽  
Author(s):  
Muammar El Khatib ◽  
Wibe de Jong
Keyword(s):  
Machine Learning ◽  
Materials Science ◽  
Building Blocks ◽  
Ease Of Use ◽  
Model Optimization ◽  
Data Preparation ◽  
Experience Design ◽  
User Experience Design ◽  
Regression Algorithms ◽  
Machine Learning Models

ML4Chem is an open-source machine learning library for chemistry and materials science. It provides an extendable platform to develop and deploy machine learning models and pipelines and is targeted to the non-expert and expert users. ML4Chem follows user-experience design and offers the needed tools to go from data preparation to inference. Here we introduce its atomistic module for the implementation, deployment, and reproducibility of atom-centered models. This module is composed of six core building blocks: data, featurization, models, model optimization, inference, and visualization. We present their functionality and ease of use with demonstrations utilizing neural networks and kernel ridge regression algorithms.

scholarly journals Participatory Prototyping to Inform the Development of a Remote UX Design System in the Automotive Domain

2018 ◽  
Vol 2 (4) ◽  
pp. 74
Author(s):  
Stavros Tasoudis ◽  
Mark Perry
Keyword(s):  
User Experience ◽  
Participatory Design ◽  
Ease Of Use ◽  
Design System ◽  
User Needs ◽  
Experience Design ◽  
User Experience Design ◽  
Self Image ◽  
Traditional Research ◽  
Ux Design

This study reports on the empirical findings of participatory design workshops for the development of a supportive automotive user experience design system. Identifying and addressing this area with traditional research methods is problematic due to the different user experience (UX) design perspectives that might conflict and the related limitations of the automotive domain. To help resolve this problem, we conducted research with 12 user experience (UX) designers through individual participatory prototyping activities to gain insights into their explicit, observable, tacit and latent needs. These activities allowed us to explore their motivation to use different technologies; the system’s architecture; detailed features of interactivity; and to describe user needs including efficiency, effectiveness, engagement, naturalness, ease of use, information retrieval, self-image awareness, politeness, and flexibility. Our analysis led us to design implications that translate participants’ needs into UX design goals, informing practitioners on how to develop relevant systems further.

scholarly journals Participatory Prototyping to Inform the Development of a Remote UX Design System in Automotive

2018 ◽  
Author(s):  
Stavros Tasoudis ◽  
Mark Perry
Keyword(s):  
User Experience ◽  
Participatory Design ◽  
Ease Of Use ◽  
Design System ◽  
User Needs ◽  
Experience Design ◽  
User Experience Design ◽  
Self Image ◽  
Traditional Research ◽  
Ux Design

This study reports on empirical findings of participatory design workshops for the development of a supportive user experience design system in the automotive. Identifying and addressing this area with traditional research methods is problematic due to the different UX design perspectives that might be conflicting and the related automotive domain limitations. To help resolve this problem, we conducted research with 12 User Experience (UX) designers through individual participatory prototyping activities to gain insights on their explicit, observable, tacit and latent needs. These activities allowed us to explore their motivation to use different technologies; the system's architecture; detailed features of interactivity and describe user needs including Efficiency, Effectiveness, Engagement, Naturalness, Ease of Use, Information retrieval, Self-Image awareness, Politeness, and Flexibility. Our analysis led us to design implications that translate participants' needs into UX design goals, informing practitioners on how to develop relevant systems further.

scholarly journals Predicting the intention to use google glass: A comparative approach using machine learning models and PLS-SEM

2021 ◽  
pp. 311-320 ◽  
Author(s):  
MAhmad Qasim Mohammad AlHamad ◽  
Iman Akour ◽  
Muhammad Alshurideh ◽  
Asma Qassem Al-Hamad ◽  
Barween Al Kurdi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ease Of Use ◽  
Perceived Usefulness ◽  
Equation Modeling ◽  
Comparative Approach ◽  
Perceived Ease Of Use ◽  
Learning Models ◽  
Google Glass ◽  
Exchange Information ◽  
Machine Learning Models

Technology-based education is the modern-day medium that is widely being used by teachers and their students to exchange information over applications based on Information and Communication Technology (ICT) such as Google Glass. There is still resistance shown by a few universities around the globe when it comes to shifting to the online mode of education. While few have shifted to Google Glass, others are yet to do so. We base this study to explore Google Glass Adoption in the Gulf area. We thought that introducing the teachers and students to all the pros that Google Glass presents on the table might get their attention in considering using it as the medium to exchange information in their respective institutes. This paper presents the structure of a framework depicting the association between TAM and other Influential factors. All in all, this investigation analyzes the incorporation of the Technology Acceptance Model (TAM) with the major features associated with the method such as instructing and learning facilitator, functionality, and trust and information privacy to improve correspondence among facilitators and students during the learning process. A total of 420 questionnaires were collected from various universities. The data that was gathered through the surveys was employed for the analysis of the research model using the Partial least squares-structural equation modeling (PLS-SEM) and machine learning models. The outcome showed that the factor of functionality and trust and privacy goes hand in hand with perceived usefulness and perceived ease of use associated with Google Glass. Both the Factors, Perceived usefulness and perceived ease of use have a significant impact on Google Glass adoption. This implies the significant impact of Perceived ease of use and Trust and privacy on the adoption of Google Glass The study also offers practical implications of outcomes for future research.

scholarly journals Opportunities and Challenges for Machine Learning in Materials Science

2020 ◽  
Vol 50 (1) ◽  
pp. 71-103
Author(s):  
Dane Morgan ◽  
Ryan Jacobs
Keyword(s):  
Machine Learning ◽  
Best Practices ◽  
Materials Science ◽  
Molecular Simulations ◽  
Learning Models ◽  
Novel Materials ◽  
Domain Of Applicability ◽  
Rapid Changes ◽  
To Come ◽  
Machine Learning Models

Advances in machine learning have impacted myriad areas of materials science, such as the discovery of novel materials and the improvement of molecular simulations, with likely many more important developments to come. Given the rapid changes in this field, it is challenging to understand both the breadth of opportunities and the best practices for their use. In this review, we address aspects of both problems by providing an overview of the areas in which machine learning has recently had significant impact in materials science, and then we provide a more detailed discussion on determining the accuracy and domain of applicability of some common types of machine learning models. Finally, we discuss some opportunities and challenges for the materials community to fully utilize the capabilities of machine learning.

scholarly journals Predicting Reliability of Storage Systems

2020 ◽  
Vol 9 (8) ◽  
pp. 386-388
Keyword(s):  
Machine Learning ◽  
Storage Systems ◽  
Building Blocks ◽  
Self Monitoring ◽  
Storage Devices ◽  
Technology System ◽  
Large Numbers ◽  
Machine Learning Model ◽  
Near Future ◽  
Machine Learning Models

Large Organizations have to make use of various storage devices like HDD and SDD to provide storage of information of their clients as well as themselves. These Storage devices are present in large numbers and are the basic building blocks that are used to store information and in case of failure occurs then replacing these devices can halt some services which can cause loss to the Organization in terms of money and time as well. To remediate this we can monitor each of the storage devices, as these storage devices come with a SMART (Self Monitoring and Reporting Technology) system that monitors and reports the stats back to the user. Thus with the help of these SMART Parameters we can train a machine learning model to predict if the hard disk will experience failure in the near future or not. In this study we did a survey of various techniques are based on various machine learning models and provide a brief overview of each of the techniques. Among these techniques we find that random forest and deep learning methods provide better results than the other methods discussed in various studies.

scholarly journals Identifying Domains of Applicability of Machine Learning Models for Materials Science

2019 ◽  
Author(s):  
Christopher Sutton ◽  
Mario Boley ◽  
Luca M. Ghiringhelli ◽  
Matthias Rupp ◽  
Jilles Vreeken ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ground State ◽  
Materials Science ◽  
Many Body ◽  
Simple Set ◽  
Domain Of Applicability ◽  
N Gram ◽  
The Many ◽  
Error Statistic ◽  
Machine Learning Models

We present an extension to the usual machine learning process that allows for the identification of the domain of applicability of a fitted model, i.e., the region in its domain where it performs most accurately. This approach is applied to several vastly different but commonly used materials representations (namely the n-gram approach, SOAP, and the many body tenor representation), which are practically indistinguishable based on performance using a single error statistic. Moreover, these models appear unsatisfactory for screening applications as they fail to reliably identify the ground state polymorphs. When applying our newly developed analysis for each of the models, we can identify the domain of applicability for each model according to a simple set of interpretable conditions. We show that identification of the domain of applicability in the prediction of the formation energy enables a more accurate ground-state search - a crucial step for the discovery of novel materials.

scholarly journals Toward Food Sovereignty for Coastal Communities of Eastern Quebec: Co-Designing A Website to Support Consumption of Edible Resources from the St. Lawrence

2020 ◽  
Author(s):  
Catherine Fallon ◽  
Mélanie Lemire ◽  
Dany Dumont ◽  
Élizabeth Parent ◽  
Esteban Figueroa ◽  
...  
Keyword(s):  
Food Safety ◽  
Food Sovereignty ◽  
Ease Of Use ◽  
Coastal Communities ◽  
Marine Resources ◽  
Experience Design ◽  
Community Members ◽  
Preparation Methods ◽  
Web Based ◽  
User Experience Design

Background: Despite the abundance and proximity of edible marine resources, coastal communities along the St. Lawrence in Eastern Quebec rarely consume these resources. Within a community-based food sovereignty project, Manger notre Saint-Laurent (Sustenance from our St. Lawrence), members of participating communities (three non-Indigenous, one Indigenous) identified a need for a web-based decision tool to help make informed consumption choices.Objective: To co-design a prototype website that facilitates informed choices about consuming local edible marine resources based on seasonal and regional availability, food safety, nutrition, and sustainability.Method: We co-designed a prototype with community members, regional stakeholders, and experts in user experience design and web development. We conducted 48 interviews with a variety of people over three iterative cycles, assessing the prototype’s ease of use with a validated measure, the System Usability Scale.Results: Community members, regional stakeholders, and other experts identified problematic elements in initial versions of the website; for example, confusing symbols. We resolved issues and added features people identified as useful. The final prototype’s usability was rated at “best imaginable” with scores similar across socio- demographic groups.Conclusion: By co-designing with community members, regional stakeholders, and other experts from the beginning, we were able to integrate communities’ priorities and perspectives about edible marine resources into a prototype website adapted to community members' needs. The final prototype includes a tool to explore species, and index cards to regroup accurate evidence about food safety, nutrition, sustainability, regional and seasonal availability, taste properties, and responsible fishing, hunting, picking, and preparation methods.

scholarly journals COMPARATIVE ANALYSIS OF INFORMATIVE FEATURES QUANTITY AND COMPOSITION SELECTION METHODS FOR THE COMPUTER ATTACKS CLASSIFICATION USING THE UNSW-NB15 DATASET

T-Comm ◽  
2020 ◽  
Vol 14 (10) ◽  
pp. 53-60
Author(s):  
Oleg I. Sheluhin ◽  
◽  
Valentina P. Ivannikova ◽  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Comparative Analysis ◽  
Attack Detection ◽  
Features Selection ◽  
Data Preparation ◽  
Learning Models ◽  
Data Set ◽  
Machine Learning Models

A comparative analysis of statistical and model-based methods for selecting the quantity and the composition of informative features was performed using the UNSW-NB15 database for machine learning models training for attack detection. Feature selection is one of the most important steps in data preparation for machine learning tasks. It allows to increase a quality of machine learning models: it reduces sizes of the fitted models, training time and probability of overfitting. The research was conducted using Python programming language libraries: scikit-learn, which includes various machine learning models and functions for data preparation and models estimation, and FeatureSelector, which contains functions for statistical data analysis. Numerical results of experimental research of application of both statistical methods of features selection and machine learning models-based methods are provided. As the result, the reduced set of features is obtained, which allows improving the quality of classification by removing noise features that have little effect on the final result and reducing the quantity of informative features of the data set from 41 to 17. It is shown that the most effective among the analyzed methods for feature selection is the statistical method SelectKBest with the function chi2, which allows to obtain a reduced set of features providing an accuracy of classification as high as 90% in comparation with 74% provided with the full set.

Sign in / Sign up

Export Citation Format

Share Document