Article
Geochemistry & Geophysics
Zhengxiang He, Pingan Peng, Liguan Wang, Yuanjian Jiang
Summary: PickCapsNet is a scalable capsule network for P-wave arrival picking without feature extraction, employing recent advances in artificial intelligence. The method demonstrates high accuracy and stability in the identification of P-wave arrival times, outperforming other methods in practical applications.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Chemistry, Analytical
Nebojsa Bacanin, Catalin Stoean, Miodrag Zivkovic, Dijana Jovanovic, Milos Antonijevic, Djordje Mladenovic
Summary: The extreme learning machine is a fast and efficient model, but its performance heavily depends on the weights and biases within the hidden layer. This study proposes a multi-swarm hybrid optimization approach for determining optimal or near optimal weights and biases, using three swarm intelligence meta-heuristics. The proposed method outperforms other similar approaches in terms of generalization performance.
Review
Biochemistry & Molecular Biology
Noam Auslander, Ayal B. Gussow, Eugene V. Koonin
Summary: The exponential growth of biomedical data in recent years has led to the application of various machine learning techniques in biology and clinical research. These methods enable automatic feature extraction, selection, and predictive model generation for efficient study of complex biological systems. Despite facing challenges, integrating machine learning techniques with established bioinformatics approaches presents unique opportunities to overcome these challenges.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Physics, Multidisciplinary
Daisuke Yoneoka, Bastian Rieck
Summary: We investigate selection bias in meta-analyses by assuming the existence of researchers (meta-analysts) who selectively choose a subset of studies based on arbitrary inclusion and/or exclusion criteria to achieve desired results. Regardless of the actual effectiveness of a treatment, our theoretical analysis shows that meta-analysts can falsely obtain (non)significant overall treatment effects when the number of studies is sufficiently large. We validate our theoretical findings through extensive simulation experiments and practical clinical examples, demonstrating the potential for cherry-picking in standard methods for meta-analyses.
Article
Geochemistry & Geophysics
Omar M. Saad, Yangkang Chen
Summary: The study on earthquake detection using Capsule Neural Network (CapsNet) has shown promising results, with high accuracy in Southern California seismic data and good performance in other seismic regions. CapsNet also demonstrates a low false alarm rate for seismic noise and high detection accuracy for microearthquakes, highlighting its potential for earthquake detection applications.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Management
Nicos Savva, Laurens Debo, Robert A. Shumsky
Summary: Hospitals worldwide are reimbursed based on diagnosis related groups (DRGs), which divides patients into meaningful groups and provides a fixed fee per episode. This scheme encourages cost reduction but may lead to cherry-picking of patients. Expanding the number of DRG classes aims to reduce cost heterogeneity, but fails to completely eliminate cherry-picking. Additionally, if hospitals can upcode patients, it amplifies the cherry-picking incentives. Potential solutions involving yardstick competition based on input statistics are examined.
MANAGEMENT SCIENCE
(2023)
Article
Biochemistry & Molecular Biology
Sudhir Kumar, Sudip Sharma
Summary: Evolutionary Sparse Learning (ESL) is a supervised machine learning approach with sparsity constraints that builds models using only the most important genomic loci to explain phylogenetic hypotheses or trait presence/absence. ESL does not involve traditional parameters, but directly utilizes sequence variation concordance. ESL offers a natural way to combine different data types and has the potential to drive the development of new computational methods.
MOLECULAR BIOLOGY AND EVOLUTION
(2021)
Article
Biochemistry & Molecular Biology
Julia Haag, Dimitri Hoehler, Ben Bettisworth, Alexandros Stamatakis
Summary: This study introduces a method to predict the level of difficulty in phylogenetic analysis datasets and presents a tool for accurate prediction. The tool can increase user awareness of signal and uncertainty in phylogenetic analysis and assist in selecting appropriate analysis setups and search algorithms.
MOLECULAR BIOLOGY AND EVOLUTION
(2022)
Article
Economics
Niina Pietarinen, Teemu Harrinkari, Maria Brockhaus, Natalya Yakusheva
Summary: This study examines the portrayal and translation of sustainability in Finnish forest policy documents, and highlights the risk of a forest-based bioeconomy continuing existing forestry practices without challenging current problematizations and proposed solutions. The research aims to provide a nuanced understanding of the opportunities and risks associated with a forest-based bioeconomy and inform current and future forest policy reviews.
FOREST POLICY AND ECONOMICS
(2023)
Article
Geochemistry & Geophysics
Li Ren, Fuchun Gao, Yulang Wu, Paul Williamson, George A. McMechan, Wenlong Wang
Summary: In this paper, a CNN-based machine learning method is proposed to automatically pick multimode surface wave dispersion curves. By modifying the U-net architecture and combining multiple attributes for picking constraint, as well as using a comprehensive loss function and pre-training algorithm, the efficiency and accuracy of the algorithm are improved.
GEOPHYSICAL JOURNAL INTERNATIONAL
(2023)
Article
Business
Inaki Heras-Saizarbitoria, Laida Urbieta, Olivier Boiral
Summary: This study analyzes the engagement of 1370 organizations from 97 countries with the SDGs, finding that the majority of organizations' engagement with the SDGs is superficial, indicating a process of SDG-washing to some extent.
CORPORATE SOCIAL RESPONSIBILITY AND ENVIRONMENTAL MANAGEMENT
(2022)
Article
Food Science & Technology
Ziwei Wang, Lin Zhou, Wenqian Hao, Yu Liu, Xia Xiao, Xiao Shan, Chenning Zhang, Binbin Wei
Summary: This study compared the total phenolic content (TPC), total flavonoid content (TFC), and in vitro antioxidant activities of 21 batches of Chinese cherries, and established a method based on UPLC-QTOF/MS metabolomics and machine learning algorithms to distinguish the cherry species. The results showed that P. tomentosa had higher TPC and TFC, with average content differences of 12.07 times and 39.30 times, respectively, and exhibited better antioxidant activity. Various differential compounds were identified, including flavonoids, organooxygen compounds, and cinnamic acids and derivatives. Machine learning algorithms achieved high prediction accuracy, with support vector machine (SVM) at 85.7%, and random forest (RF) and back propagation neural network (BPNN) both at 100%.
FOOD RESEARCH INTERNATIONAL
(2023)
Article
Business, Finance
Jonathan A. Wiley, Hana Nguyen
Summary: This study examines the impact of the launch of US opportunity zones on industrial property prices. The results show that there is a significant increase in transaction premiums in eligible tracts compared to similar tracts that were not included in the program. These premiums are mainly concentrated in properties with excess land available, suggesting that the program incentivizes development options. The study also finds that areas with high employment and population growth show significant transaction premiums. Overall, there is no evidence to suggest that the share of commercial real estate transactions to opportunity zones has increased following the legislation.
REAL ESTATE ECONOMICS
(2022)
Article
Geochemistry & Geophysics
Jinghe Li, Mengkun Ran, Weike Tong, Yehui Cao, Luxi Cai, Xiaoyi Ou, Tingwei Yang
Summary: Efficient seismic phase picking is crucial for seismic signal processing. A novel transductive transfer-learning-based support vector machine (TTL-SVM) algorithm is proposed for seismic phase picking when training samples are insufficient. This algorithm shows remarkable results compared to traditional approaches, providing an alternative for seismic phase picking in datasets with limited training samples.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Theory & Methods
Remie Janssen, Yukihiro Murakami
Summary: This paper introduces cherry-picking networks, a type of network that can be simplified by cherry-picking sequences. It demonstrates how to compare and distinguish these networks using their sequences. Additionally, it characterizes reconstructible cherry-picking networks and shows that the problem of checking network containment can be solved by computing cherry picking sequences in linear time.
THEORETICAL COMPUTER SCIENCE
(2021)