Article
Computer Science, Interdisciplinary Applications
Tommaso Di Ianni, Raag D. Airan
Summary: In this study, we developed an image reconstruction method using deep learning for functional ultrasound imaging, which can achieve high-quality imaging with less data. We trained neural networks to reconstruct time series of power Doppler images and detect small changes in cerebral blood volume.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Review
Behavioral Sciences
Chunliang Feng, Simon B. Eickhoff, Ting Li, Li Wang, Benjamin Becker, Julia A. Camilleri, Sebastien Hetu, Yi Luo
Summary: The study found that different brain regions involved in various social interactions mainly mapped onto the default mode network, salience network, subcortical network, and central executive network, respectively involved in social cognition, motivation, and cognitive control. This discovery provides a heuristic integrative framework for understanding human social life from the perspective of component processes and network integration.
NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS
(2021)
Editorial Material
Chemistry, Multidisciplinary
Yuhua Liu, Wei Zhang
Summary: The economical and high-efficiency synthesis of single-atom catalysts is a significant challenge due to the complexity of equipment and processes required for both top-down and bottom-up synthesis methods. However, a facile three-dimensional printing approach has now emerged, allowing for the direct and automatic preparation of target materials with specific geometric shapes from a solution of printing ink and metal precursors.
COMMUNICATIONS CHEMISTRY
(2023)
Article
Neurosciences
Angela R. Laird
Summary: This review explores the evolution of data sharing in magnetic resonance imaging and the challenges and progress in reproducible data analyses. It emphasizes the ethical conduct relevant to analyses of large, open datasets and the responsibility of researchers to prevent further stigmatization of historically marginalized racial and ethnic groups.
Article
Nanoscience & Nanotechnology
Zhilong Wang, Yanqiang Han, Xirong Lin, Junfei Cai, Sicheng Wu, Jinjin Li
Summary: Lead-free double perovskites are considered stable and environmentally friendly optoelectronic alternatives, but their indirect band gaps and high effective masses may limit their efficiency. The proposed ensemble learning workflow successfully screened out six suitable candidates from over 23,314 unexplored double perovskites, two of which exhibit promising characteristics for application in photovoltaic devices. This machine learning approach greatly shortens the screening process and can significantly promote the development of photovoltaic technology.
ACS APPLIED MATERIALS & INTERFACES
(2022)
Article
Computer Science, Artificial Intelligence
Daniel Bauer, Florian Froese, Luis Garces-Erice, Chris Giblin, Abdel Labbi, Zoltan A. Nagy, Niels Pardon, Sean Rooney, Peter Urbanetz, Pascal Vetsch, Andreas Wespi
Summary: Over the past three years, the authors have been operating a large-scale data processing platform on an OpenStack private cloud instance, providing analytics for a wide variety of corporate data assets to globally distributed teams. They control every layer of the stack and report their experiences in building and operating such a system, including their technical choices and how they evolved based on actual workloads.
Editorial Material
Multidisciplinary Sciences
Xiang Shi, Peining Chen, Huisheng Peng
Summary: Large-area display textiles can be produced by weaving transparent conductive weft and luminescent warp fibers using an industrial rapier loom. Integrating interactive functionalities, such as a keyboard and power supply, with the display textile forms an electronic textile system. Weaving textiles with integrated interactive functionalities allows them to serve as a communication tool.
Article
Computer Science, Interdisciplinary Applications
Valentina Zelaya Mendizabal, Marc Boulle, Fabrice Rossi
Summary: G-Enum histograms are a fast and fully automated method for constructing irregular histograms. By using the Minimum Description Length principle (MDL), this method derives two model selection criteria and achieves linearithmic time complexity. The effectiveness of the method is demonstrated through comparisons with other automated methods on synthetic and real-world data sets.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2023)
Article
Engineering, Industrial
Chenhao Zhou, Aloisius Stephen, Xinhu Cao, Shuhong Wang
Summary: This study introduces a data-driven business intelligence system for optimizing sorting operations in a logistics company, reducing man-hours and improving service level efficiency.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2021)
Article
Neurosciences
Zhenfu Wen, Zhe Sage Chen, Mohammed R. Milad
Summary: The study found that functional connectivity increased across the entire brain during fear extinction learning, predicting the performance of extinction memory. These results support recent research implicating distributed brain regions in learning, consolidation, and expression of fear extinction memory in the human brain.
Article
Nutrition & Dietetics
Arsalan Shahid, Dana M. Lewis
Summary: This paper evaluates glucose variability of open-source automated insulin delivery (AID) technologies using a large-scale data set and affirms the previous studies' findings.
Article
Biochemical Research Methods
Konstantinos Tzanakis, Tim W. Nattkemper, Karsten Niehaus, Stefan P. Albaum
Summary: MetHoS is an automated web-based software platform for processing and analyzing large-scale metabolomics data sets using mass spectrometry. It utilizes a big data framework for parallel processing and distributed storage, enabling comprehensive analysis of hundreds or even thousands of experiments.
BMC BIOINFORMATICS
(2022)
Article
Public, Environmental & Occupational Health
Jingsong Wu, Yang Li, Lianhua Yin, Youze He, Tiecheng Wu, Chendong Ruan, Xidian Li, Jianhuang Wu, Jing Tao
Summary: The aim of this study is to build a model that can automatically predict the balance ability of the elderly. Through the recursive feature elimination algorithm, the input feature dimension of the model was successfully reduced from 61 to 13 dimensions. The proposed method showed high prediction accuracy and classification performance in the tests, making it suitable for large-scale physical examinations.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Psychiatry
Rayus Kuplicki, James Touthang, Obada Al Zoubi, Ahmad Mayeli, Masaya Misaki, Robin L. Aupperle, T. Kent Teague, Brett A. McKinney, Martin P. Paulus, Jerzy Bodurka
Summary: Neuroscience studies require robust bioinformatic support and expertise to preprocess and integrate high-dimensional datasets. This study introduces a scalable data management infrastructure supporting multiple analytics workflows and utilizing the BIDS format for various types of data, demonstrating its utility through exemplar results.
FRONTIERS IN PSYCHIATRY
(2021)
Article
Transportation Science & Technology
Xin Xia, Zonglin Meng, Xu Han, Hanzhao Li, Takahiro Tsukiji, Runsheng Xu, Zhaoliang Zheng, Jiaqi Ma
Summary: In this paper, an automated driving system (ADS) data acquisition and analytics platform for vehicle trajectory extraction, reconstruction, and evaluation based on connected automated vehicle (CAV) cooperative perception is presented. The platform processes sensor data from multi-CAVs and extracts objects' identity, position, speed, and orientation information. Various methods, such as deep learning-based object detection, late fusion scheme, and Kalman filter, are used for data processing and object tracking. The results demonstrate the effectiveness of the proposed platform and its potential applications in transportation research and ADS development.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)