Suchergebnisse

Classical molecular dynamics (MD) simulations will be able to reach sampling in the second timescale within five years, producing petabytes of simulation data at current force field accuracy. Notwithstanding this, MD will still be in the regime of low-throughput, high-latency predictions with average accuracy. We envisage that machine learning (ML) will be able to solve both the accuracy and time-to-prediction problem by learning predictive models using expensive simulation data. The synergies between classical, quantum simulations and ML methods, such as artificial neural networks, have the potential to drastically reshape the way we make predictions in computational structural biology and drug discovery. ; The authors thank Acellera Ltd. for funding. G.D.F. acknowledges support from MINECO (BIO2017-82628-P) and FEDER, as well as 'Unidad de Excelencia María de Maeztu', funded by MINECO (MDM-2014-0370). The authors thank the European Union's Horizon 2020 research and innovation programme under grant agreement No 675451 (CompBioMed project).

The field of education is constantly seeking more innovative and effective methods of teaching foundational knowledge to students. Organizations in both secondary and post-secondary education groups offer Physics Education Groups that try to better teach fundamental physics concepts to students in both university and high school. There are also government agencies such as the Educational Quality and Accountability Office (EQAO) in Ontario, which provides standardized tests to students. Although these standardized tests do not test the full capabilities and thought processes of students, they still provide insights into how students learn. Data from standardized EQAO tests can be analyzed to obtain crucial information about how to improve education standards by showing where resources can be allocated more effectively. One of the most powerful tools that can be used to analyze data is machine learning, which can find patterns and correlations in data that the human eye cannot see. This experiment used the linear regression algorithm to find correlations in data obtained from grade 9 EQAO mathematics tests from 50 schools in Ontario. The algorithm analyzed how students with varying scores answered a multiple-choice questionnaire at the end of the exam, which included statements such as "I am able to answer difficult mathematics questions." Based on the variables output from the machine learning algorithm, the importance of each statement was then ranked; this ranking can then lead to insights into how students learn, and how to better utilize resources. This experiment has shown that an elementary application of machine learning can lead to valuable insights into student learning and that more should be done to better analyze the abundant data in the education field. Le domaine de l'éducation recherche continuellement des méthodes innovatrices et efficaces pour l'enseignement de connaissances fondamentales aux étudiants. Les organisations de niveau secondaire et post-secondaire offrent des groupes d'éducation en physique qui essaient d'améliorer l'enseignement des concepts fondamentaux en physique aux étudiants à l'université ainsi qu'au secondaire. Il y a également des agences gouvernementales telles que l'Office de la qualité et de la responsabilité en éducation (OQRE) en Ontario, qui offre des tests standardisés aux étudiants. Bien que ces tests standardisés n'évaluent pas la pleine capacité et le processus de réflexion des élèves, ils offrent tout de même un aperçu des méthodes d'apprentissage. Les données des tests standardisés de l'OQRE peuvent être analysés afin d'obtenir des renseignements essentiels quant à la façon d'améliorer les normes d'éducation en démontrant où les ressources peuvent être attribuées plus efficacement. Un des outils les plus puissants qui peut être utilisé pour analyser les données est le l'apprentissage automatique, ce qui peut trouver des tendances et des corrélations à travers les données que l'œil humain ne peut percevoir. Cette expérience a utilisé l'algorithme à régression linéaire afin de trouver des corrélations dans les données obtenues des tests de mathématique de l'OQRE pour la mième année dans 50 écoles en Ontario. L'algorithme a analysé comment les étudiants possédant un résultat différent ont répondu à un questionnaire de questions à choix multiples à la fin de l'examen incluant des énoncés tels que « Je suis en mesure de répondre à des questions mathématiques dif ciles. » Selon les variables produits par l'algorithme d'apprentissage automatique, l'importance de chaque énoncé fut classée; ce classement peut ainsi mener à une compréhension envers l'apprentissage de l'étudiant, et comment maximiser les ressources. Cette expérience a démontré qu'une application élémentaire de l'apprentissage automatique peut mener à de précieux renseignements sur l'apprentissage des étudiants et que plus d'efforts doivent être accomplis afin de faciliter l'analyse des nombreuses données retrouvées dans le domaine de l'éducation.

Front Cover -- Machine Learning Applications in Industrial Solid Ash -- Copyright Page -- Dedication -- Contents -- Preface -- Acknowledgments -- 1 Industrial solid ashes generation -- 1.1 Introduction -- 1.2 Making and types of industrial solid ashes -- 1.2.1 Coal ashes -- 1.2.2 Municipal solid waste -- 1.2.3 Biomass -- 1.3 Production amounts of industrial solid ashes -- 1.3.1 Coal ashes -- 1.3.2 Municipal solid waste -- 1.3.3 Biomass -- References -- 2 Properties of industrial solid ashes -- 2.1 Introduction -- 2.2 Characteristics of coal ashes -- 2.2.1 Coal fly ash -- 2.2.1.1 Physical features -- 2.2.1.2 Mineral features -- 2.2.1.3 Chemical features -- 2.2.1.4 Classification -- 2.2.2 Coal bottom ash -- 2.2.2.1 Physical features -- 2.2.2.2 Chemical/mineralogical features -- 2.3 Characteristics of MSW bottom/fly ash -- 2.3.1 MSW bottom ash -- 2.3.1.1 Physical properties -- 2.3.1.2 Chemical features -- 2.3.1.3 Mineralogical features -- 2.3.2 MSW fly ash -- 2.3.2.1 Physical properties -- 2.3.2.2 Chemical features -- 2.3.2.3 Mineralogical features -- 2.4 Characteristics of biomass bottom/fly ash -- References -- 3 Ash management, recycling, and sustainability -- 3.1 Introduction -- 3.2 Management of CFA and CBA -- 3.2.1 Hazards of CFA and CBA -- 3.2.2 Application and utilization of CFA and CBA -- 3.2.2.1 Cement and concrete -- 3.2.2.2 Ceramic industry -- 3.2.2.3 Brick production -- 3.2.2.4 Road construction -- 3.2.2.5 Soil amelioration -- 3.2.2.6 Zeolites -- 3.2.2.7 Environmental protection (absorbent) -- 3.3 MSW bottom ash and fly ash -- 3.3.1 Cement production -- 3.3.2 Concrete -- 3.3.3 Road pavement -- 3.3.4 Embankment -- 3.3.5 Soil stabilization -- 3.3.6 Ceramic and glass -- 3.4 Biomass bottom/fly ashes -- References -- 4 Emerging innovative techniques for ash management -- 4.1 Introduction -- 4.2 Geopolymer -- 4.3 Recovery of REEs.

Analisis sentimen merupakan interpretasi dan klasifikasi emosi (positif, negatif, netral) pengguna tentang suatu subjek dalam data teks dengan menggunakan analisis teks. Dengan bantuan analisis sentimen, informasi yang tidak terstruktur yang dapat diubah menjadi data yang lebih terstruktur yang kemudian dapat digunakan menjelaskan opini masyarakat mengenai produk, merek, layanan, politik, atau topik lainnya. Terdapat beberapa metode yang dapat digunakan untuk melakukan analisis sentimen, salah satunya adalah machine learning. Machine learning digunakan sebagai tools untuk menghasilkan robot yang mampu mengklasifikasikan jenis sentimen dalam data tekstual. Merdeka Belajar Kampus Merdeka (MBKM), merupakan kebijakan Menteri Pendidikan dan Kebudayaan, yang bertujuan mendorong mahasiswa untuk menguasai berbagai keilmuan yang berguna untuk memasuki dunia kerja. Kampus Merdeka memberikan kesempatan bagi mahasiswa untuk memilih mata kuliah yang akan mereka ambil. Penelitian ini dilakukan untuk menghasilkan model machine learning dengan menggunakan metode Support Vector Machine (SVM) yang dapat digunakan untuk mengukur tingkat popularitas program kampus merdeka yang telah diluncurkan oleh Kementrian Pendidikan, Kebudayaan, Riset dan Teknologi Informasi Republik Indonesia berdasarkan data komentar atau opini masyarakat di media sosial.Berdasarkan penelitan yang dilakukan, ditemukan bahwa jumlah true positive rate adalah 270 record dikategorikan sebagai label positif dan false positive rate adalah 0 record dikategorikan sebagai label negatif. Kemudian jumlah true negative rate adalah 11 record dikategorikan sebagai label negatif dan false negative rate adalah 67 record dikategorikan sebagai label positif. Hasil pengujian data ditemukan bahwa tingkat akurasi algoritma SVM adalah sebesar 80,75%.

Data envelopment analysis (DEA) has been widely applied to evaluate the performance of banks, enterprises, governments, research institutions, hospitals, and other fields as a non-parametric estimation method for evaluating the relative effectiveness of research objects. However, the composition of its effective frontier surface is based on the input-output data of existing decision units, which makes it challenging to apply the method to predict the future performance level of other decision units. In this paper, the Slack Based Measure (SBM) model in DEA method is used to measure the relative efficiency values of decision units, and then, eleven machine learning models are used to train the absolute efficient frontier to be applied to the performance prediction of new decisions units. To further improve the prediction effect of the models, this paper proposes a training set under the DEA classification method, starting from the training-set sample selection and input feature indicators. In this paper, regression prediction of test set performance based on the training set under different classification combinations is performed, and the prediction effects of proportional relative indicators and absolute number indicators as machine-learning input features are explored. The robustness of the effective frontier surface under the integrated model is verified. An integrated models of DEA and machine learning with better prediction effects is proposed, taking China's regional carbon-dioxide emission (carbon emission) performance prediction as an example. The novelty of this work is mainly as follows: firstly, the integrated model can achieve performance prediction by constructing an effective frontier surface, and the empirical results show that this is a feasible methodological technique. Secondly, two schemes to improve the prediction effectiveness of integrated models are discussed in terms of training set partitioning and feature selection, and the effectiveness of the schemes is demonstrated by using ...

International audience ; In this short editorial we present some thoughts on present and future trends in Artificial Intelligence (AI) generally, and Machine Learning (ML) specifically. Due to the huge ongoing success in machine learning, particularly in statistical learning from big data, there is rising interest of academia, industry and the public in this field. Industry is investing heavily in AI, and spin-offs and start-ups are emerging on an unprecedented rate. The European Union is allocating a lot of additional funding into AI research grants, and various institutions are calling for a joint European AI research institute. Even universities are taking AI/ML into their curricula and strategic plans. Finally, even the people on the street talk about it, and if grandma knows what her grandson is doing in his new start-up, then the time is ripe: We are reaching a new AI spring. However, as fantastic current approaches seem to be, there are still huge problems to be solved: the best performing models lack transparency, hence are considered to be black boxes. The general and worldwide trends in privacy, data protection, safety and security make such black box solutions difficult to use in practice. Specifically in Europe, where the new General Data Protection Regulation (GDPR) came into effect on May, 28, 2018 which affects everybody (right of explanation). Consequently, a previous niche field for many years, explainable AI, explodes in importance. For the future, we envision a fruitful marriage between classic logical approaches (ontologies) with statistical approaches which may lead to context-adaptive systems (stochastic ontologies) that might work similar as the human brain.

Supervised machine learning is widely used in biology and deserves more scrutiny. We present a set of community-wide recommendations (DOME) aiming to help establish standards of supervised machine learning validation in biology. Formulated as questions, the DOME recommendations improve the assessment and reproducibility of papers when included as supplementary material. ; The work of the Machine Learning Focus Group was funded by ELIXIR, the research infrastructure for life-science data. IW was funded by the A*STAR Career Development Award (project no. C210112057) from the Agency for Science, Technology and Research (A*STAR), Singapore. D.F. was supported by Estonian Research Council grants (PRG1095, PSG59 and ERA-NET TRANSCAN-2 (BioEndoCar)); Project No 2014-2020.4.01.16-0271, ELIXIR and the European Regional Development Fund through EXCITE Center of Excellence. S.C.E.T. has received funding from the European Union's Horizon 2020 research and innovation programme under Marie Skłodowska-Curie Grant agreements No. 778247 and No. 823886, and Italian Ministry of University and Research PRIN 2017 grant 2017483NH8. ; Peer Reviewed ; "Article signat per 8 autors més 28 autors/es de l' ELIXIR Machine Learning Focus Group: Emidio Capriotti, Rita Casadio, Salvador Capella-Gutierrez, Davide Cirillo, Alessio Del Conte, Alexandros C. Dimopoulos, Victoria Dominguez Del Angel, Joaquin Dopazo, Piero Fariselli, José Maria Fernández, Florian Huber, Anna Kreshuk, Tom Lenaerts, Pier Luigi Martelli, Arcadi Navarro, Pilib Ó Broin, Janet Piñero, Damiano Piovesan, Martin Reczko, Francesco Ronzano, Venkata Satagopam, Castrense Savojardo, Vojtech Spiwok, Marco Antonio Tangaro, Giacomo Tartari, David Salgado, Alfonso Valencia & Federico Zambelli" ; Postprint (author's final draft)

"Text data is important for many domains, from healthcare to marketing to the digital humanities, but specialized approaches are necessary to create features for machine learning from language. Supervised Machine Learning for Text Analysis in R explains how to preprocess text data for modeling, train models, and evaluate model performance using tools from the tidyverse and tidymodels ecosystem. Models like these can be used to make predictions for new observations, to understand what natural language features or characteristics contribute to differences in the output, and more. If you are already familiar with the basics of predictive modeling, use the comprehensive, detailed examples in this book to extend your skills to the domain of natural language processing"--

"Over the past 20 years, there has been an incredible change in the size, structure, and types of data collected in the social and behavioral sciences. Thus, social and behavioral researchers have increasingly been asking the question: "What do I do with all of this data?" The goal of this book is to help answer that question. It is our viewpoint that in social and behavioral research, to answer the question "What do I do with all of this data?", one needs to know the latest advances in the algorithms and think deeply about the interplay of statistical algorithms, data, and theory. An important distinction between this book and most other books in the area of machine learning is our focus on theory"--

[Abstract] Scholars and practitioners are defining new types of interactions between humans and machine learning algorithms that we can group under the umbrella term of Human-in-the-Loop Machine Learning (HITL-ML). This paper is focused on implementing two approaches to this topic—Iterative Machine Teaching (iMT) and Active Learning (AL)—and analyzing how to integrate them in the learning loop. iMT is a variation of Machine Teaching in which a machine acts as a teacher that tries to transfer knowledge to a machine learning model. The focus of the problem in iMT is how to obtain the optimal training set given a machine learning algorithm and a target model. The idea is to learn a target concept with a minimal number of iterations with the smallest dataset. Active Learning, in contrast, is a specialized type of supervised learning in which humans are incorporated in the loop to act as oracles that analyze unlabeled data. AL allows us to achieve greater accuracy with less data and less training. Our proposal to incorporate iMT and AL into the machine learning loop is to use iMT as a technique to obtain the "Minimum Viable Data (MVD)" for training a learning model, that is, a dataset that allows us to increase speed and reduce complexity in the learning process by allowing to build early prototypes. Next, we will use AL to refine this first prototype by adding new data in an iterative and incremental way. We carried out several experiments to test the feasibility of our proposed approach. They show that the algorithms trained with the teachers converge faster than those that have been trained in a conventional way. Also, AL helps the model to avoid getting stuck and to keep improving after the first few iterations. The two approaches investigated in this paper can be considered complementary, as they correspond to different stages in the learning process. ; This work has been supported by the State Research Agency of the Spanish Government (grant PID2019-107194GB-I00 / AEI / 10.13039/501100011033) and by the Xunta de Galicia (grant ED431C 2018/34) with the European Union ERDF funds. We wish to acknowledge the support received from the Centro de Investigaci ́on de Galicia "CITIC", funded by Xunta de Galicia and the European Union (European Regional Development Fund- Galicia 2014-2020 Program, grant ED431G 2019/01). ; Xunta de Galicia; ED431C 2018/34 ; Xunta de Galicia; ED431G 2019/01

Against the background of the growing use of machine learning (ML) based technologies by the military, our article calls for an analytical perspective on ML platforms to understand how ML proliferates across the military and to what effects. Adopting a material–technical perspective on platforms as developed within new media studies, and bringing this literature to critical security studies, we suggest that a focus on platforms and the technical work they do is needed to understand how digital technologies are emerging and shaping security practices. Through a detailed study of Google's open-source ML platform TensorFlow and a discussion of the US Department of Defense Algorithmic Warfare Cross-Functional Team, or Project Maven, we make two broader contributions. First, we identify a broader "platformization" of the military, with which we refer to the growing involvement and permeation of the (technomaterial) ML platform as the infrastructure that enables new practices of decentralized and experimental algorithm development across the military. Second, we draw out how this platformization is accompanied by new entanglements between the military and actors in the corporate domain, especially Big Tech, which play a key role in this context, as well as the open-source community that is organized around these platforms.

COVID-19 outbreaks only affect the lives of people, they result in a negative impact on the economy of the country. On Jan. 30, 2020, it was declared as a health emergency for the entire globe by the World Health Organization (WHO). By Apr. 28, 2020, more than 3 million people were infected by this virus and there was no vaccine to prevent. The WHO released certain guidelines for safety, but they were only precautionary measures. The use of information technology with a focus on fields such as data Science and machine learning can help in the fight against this pandemic. It is important to have early warning methods through which one can forecast how much the disease will affect society, on the basis of which the government can take necessary actions without affecting its economy. A deep CNN architecture has been proposed in this paper for the diagnosis of COVID-19 based on the chest X-ray image classification. Due to the nonavailability of sufficient-size and good-quality chest X-ray image dataset, an effective and accurate CNN classification was a challenge. To deal with these complexities such as the availability of a very-small-sized and imbalanced dataset with image-quality issues, the dataset has been preprocessed in different phases using different techniques to achieve an effective training dataset for the proposed CNN model to attain its best performance. preprocessing stages of the datasets performed in this study include dataset balancing, medical experts' image analysis, and data augmentation. experimental results have shown the overall accuracy as high as 99.5% which demonstrates the good capability of the proposed CNN model in the current application domain.

The book covers tools in the study of online social networks such as machine learning techniques, clustering, and deep learning. A variety of theoretical aspects, application domains, and case studies for analyzing social network data are covered. The aim is to provide new perspectives on utilizing machine learning and related scientific methods and techniques for social network analysis. Machine Learning Techniques for Online Social Networks will appeal to researchers and students in these fields.

Nonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potentially consume far less power than digital processors. So far they have been successfully employed for signal processing using the Reservoir Computing paradigm. In this paper we show that their range of applicability can be greatly extended if we use gradient descent with backpropagation through time on a model of the system to optimize the input encoding of such systems. We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach. The results presented here demonstrate that common gradient descent techniques from machine learning may well be applicable on physical neuro-inspired analog computers. ; P.B., M.H. and J.D. acknowledge support by the interuniversity attraction pole (IAP) Photonics@be of the Belgian Science Policy Office, the ERC NaResCo Starting grant and the European Union Seventh Framework Programme under grant agreement no. 604102 (Human Brain Project). M.C.S. and I.F. acknowledge support by MINECO (Spain), Comunitat Autónoma de les Illes Balears, FEDER, and the European Commission under Projects TEC2012-36335 (TRIPHOP), and Grups Competitius. M.H. and I.F. acknowledge support from the Universitat de les Illes Balears for an Invited Young Researcher Grant. ; Peer Reviewed