Review
Genetics & Heredity
Giovanna Cilluffo, Salvatore Fasola, Giuliana Ferrante, Velia Malizia, Laura Montalbano, Stefania La Grutta
Summary: This review provides an overview of Machine Learning techniques in pharmacogenetics over the past decade, highlighting their potential in improving knowledge and the distinction between supervised and unsupervised techniques based on research goals.
Article
Quantum Science & Technology
Soumik Adhikary
Summary: The study introduces a supervised quantum classifier training algorithm that utilizes the property of quantum entanglement, achieving successful binary classification on benchmark datasets.
QUANTUM INFORMATION PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Xiao Wang, Daisuke Kihara, Jiebo Luo, Guo-Jun Qi
Summary: The study introduces a new EnAET framework to enhance semi-supervised learning methods with self-supervised information. Experimental results demonstrate that the EnAET framework significantly improves the performance of semi-supervised algorithms, even in scenarios with a limited number of images, and can greatly enhance supervised learning as well.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Automation & Control Systems
Rachna Vaish, U. D. Dwivedi, Saurabh Tewari, S. M. Tripathi
Summary: The study focuses on providing a comprehensive review of machine learning-based power system fault diagnosis, addressing the issues in conventional fault diagnosis and presenting a framework for machine learning-based fault diagnosis. Various unsupervised and supervised learning techniques are discussed, along with a brief overview of reinforcement learning and transfer learning in the context of power system fault diagnosis. Additionally, the research trends, key issues, and directions for future research are highlighted.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Review
Microbiology
Stephen J. Goodswen, Joel L. N. Barratt, Paul J. Kennedy, Alexa Kaufer, Larissa Calarco, John T. Ellis
Summary: This article explores the significance and potential applications of machine learning in the field of microbiology, emphasizing its role in predicting and diagnosing microbiological issues, and encouraging researchers to join the machine learning revolution in this field.
FEMS MICROBIOLOGY REVIEWS
(2021)
Review
Microbiology
Stephen J. Goodswen, Joel L. N. Barratt, Paul J. Kennedy, Alexa Kaufer, Larissa Calarco, John T. Ellis
Summary: Understanding the intricacies of microorganisms at the molecular level requires vast amounts of data and the application of machine learning;
The use of machine learning in addressing biological problems is expected to grow at an unprecedented rate;
The hope is to inspire microbiologists and other related researchers to join the emerging machine learning revolution.
FEMS MICROBIOLOGY REVIEWS
(2021)
Review
Cardiac & Cardiovascular Systems
Nicolai P. Ostberg, Mohammad A. Zafar, John A. Elefteriades
Summary: Machine learning has experienced significant advancements in the past decade and is poised to have a major impact on the future of surgery, particularly in thoracic surgery. Techniques such as supervised learning, unsupervised learning, and reinforcement learning can improve care, but there are also limitations such as lack of interpretability and difficulties with clinical implementation. Overall, ML technologies hold great promise to enhance cardiac surgical practices.
EUROPEAN JOURNAL OF CARDIO-THORACIC SURGERY
(2021)
Review
Computer Science, Interdisciplinary Applications
Veenu Rani, Syed Tufael Nabi, Munish Kumar, Ajay Mittal, Krishan Kumar
Summary: Machine learning has made significant advances in image processing. Supervised learning relies on labeled data, while unsupervised learning learns from unlabeled data. Self-supervised learning is a type of unsupervised learning that enhances computer vision tasks. This review article provides an in-depth exploration of self-supervised learning and its applications, discussing terms, learning types, and challenges encountered in the process.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Review
Chemistry, Multidisciplinary
Tiancheng Pu, Jiaqi Ding, Fanxing Zhang, Ke Wang, Ning Cao, Emiel J. M. Hensen, Pengfei Xie
Summary: This review summarizes recent progress in the synthesis, characterization, structure-property relationship, and computational studies of dual-atom catalysts (DACs) in the field of thermocatalysis, electrocatalysis, and photocatalysis. The combination of qualitative and quantitative characterization, cooperation with DFT insights, synergies and superiorities of DACs compared to counterparts, high-throughput catalyst exploration, and screening with machine-learning algorithms are highlighted. Undoubtedly, we can expect more fascinating developments in the field of DACs as tunable catalysts.
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
(2023)
Article
Computer Science, Artificial Intelligence
Maciej Grzenda, Stanislaw Kazmierczak, Marcin Luckner, Grzegorz Borowik, Jacek Mandziuk
Summary: Applying machine learning to multi-factor authentication is popular, but there is no comprehensive methodology to evaluate ML-based biometric systems. This paper proposes a general methodology for evaluating impostor recognition using biometric traits, including creating balanced learning and testing sets, determining the number of instances from different users, and considering the impact of impostor and user behavior data. The paper also suggests using real data to enhance impostor detection. By applying this methodology, certain ML-based approaches achieved low false acceptance rates and false rejection rates.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Physics, Multidisciplinary
Bartosz Regula
Summary: This paper presents a new resource monotone that can rule out all transformations, probabilistic or deterministic, between states in any quantum resource theory. The results obtained from this approach provide significant improvements for probabilistic distillation protocols, allowing for better error and overhead bounds. The monotone also serves as a necessary and sufficient condition for state convertibility.
PHYSICAL REVIEW LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Vahideh Shirmohammadli, Behraad Bahreyni
Summary: This tutorial discusses the applications of machine learning in sensor technology, focusing on the fundamental stages of creating data-driven models based on simple machine learning algorithms. Case studies demonstrate the importance of choosing appropriate features, algorithms, and determining environmental conditions from sensor data.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Aerospace
Charissa L. Campbell, Shiv Meka, Daniel Marrable, Andrew L. Rohl, Kevin Chai, Gretchen K. Benedix, Christina L. Smith, John E. Moores
Summary: An algorithm using Computer Vision (CV) and machine learning has been developed to calculate cloud parameters directly from Martian water-ice cloud properties. Testing on a previous data set showed promising results when the algorithm matched well with manual results under certain conditions, but performed less accurately in other conditions such as lighting changes, multiple cloud decks, or camera artifacts. Improvements are needed for the algorithm to more accurately measure cloud parameters under a variety of conditions.
Article
Computer Science, Artificial Intelligence
Ivona Colakovic, Saso Karakatic
Summary: Most machine learning research focuses on improving the correctness of outcomes, but the negative impact of these outcomes can be significant if certain groups of data are marginalized or discriminated against. Recent papers have started addressing the unfair treatment of certain data groups, but they primarily focus on a single sensitive feature. In this paper, a FairBoost algorithm is proposed to mitigate unfairness in classification tasks, taking into consideration both fairness and accuracy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Mohammad A. Khalilzadeh, Soo Young Kim, Ho Won Jang, Rafael Luque, Rajender S. Varma, Richard A. Venditti, Mohammadreza Shokouhimehr
Summary: This review article presents the progress in utilizing carbohydrate-based nanostructured catalysts for organic transformations. These catalysts have abundant sources, low cost, and renewability, and can be applied in greener and environmentally friendly processes.
MATERIALS TODAY CHEMISTRY
(2022)
Article
Physics, Multidisciplinary
Cristhiano Duarte
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2020)
Article
Physics, Multidisciplinary
Johan Aberg, Ranieri Nery, Cristhiano Duarte, Rafael Chaves
PHYSICAL REVIEW LETTERS
(2020)
Article
Quantum Science & Technology
Roberto D. Baldijao, Rafael Wagner, Cristhiano Duarte, Barbara Amaral, Marcelo Terra Cunha
Summary: Quantum Darwinism suggests that the proliferation of redundant information is crucial for the emergence of objectivity from the quantum world. Research indicates that if the environment effectively encodes the proliferated information, classical objectivity can be unambiguously said to have emerged under quantum Darwinism.
Article
Optics
Matthew Leifer, Cristhiano Duarte