Article
Chemistry, Multidisciplinary
Katsuhisa Matsumoto, Tomoyuki Miyao, Kimito Funatsu
Summary: In this study, a ranking-oriented QSAR model was utilized for activity prediction in ligand-based drug design, showing promising results when compared to traditional methods. Accumulated experimental data and rigorous validation demonstrated that models trained on compounds from similar assays were equally effective as those trained on compounds from all assays.
Article
Geochemistry & Geophysics
Peng Lin, Suping Peng, Yang Xiang, Chuangjian Li, Xiaoqin Cui, Wenkai Zhang
Summary: Random noise attenuation is crucial in seismic data processing for accurate structural imaging and data inversion. A novel low-rank approximation method using CUR matrix decomposition is proposed to address this issue. The CUR decomposition decomposes a matrix into three matrices, C, U, and R, to obtain a low-rank approximation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Ecology
Parvez Rana, Jari Vauhkonen
Summary: In this study, a stochastic multicriteria acceptability analysis was proposed to incorporate decision-makers' preferences into the spatial forest management prioritization in a Scandinavian boreal forest landscape. The potential of the landscape for different management alternatives was quantified using proxies based on airborne laser scanning. The stochastic approach allowed for the estimation of decision strength considering uncertainties in both proxy values and preferences.
LANDSCAPE AND URBAN PLANNING
(2023)
Article
Computer Science, Hardware & Architecture
JiaYan Chen, ZhuoFu Yan, Rong Fan
Summary: China's urban rail transit construction projects face challenges such as inconsistent planning and execution, lack of alignment with urban development, lengthy timelines, sub-optimal land utilization, and wastage of resources. To address these issues, it is crucial to enhance land utilization around stations, implement scientific planning, and adopt intelligent management for underground space development. This study focuses on the integrated development of urban rail transit stations and their cities to improve land utilization and cater to the diverse needs of residents. This approach can alleviate traffic pressure, stimulate economic growth, reduce pollution, conserve urban space resources, and address issues related to rail transit development.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Biochemical Research Methods
Steven Shave, John C. Dawson, Abdullah M. Athar, Cuong Q. Nguyen, Richard Kasprowicz, Neil O. Carragher
Summary: Phenonaut is a Python software package designed to address the data workflow needs of migration, control, integration, and auditability in the application of literature and proprietary techniques for data source and structure agnostic workflow creation.
Article
Multidisciplinary Sciences
Itsuki Kanemura, Katsunori Kitano
Summary: Humans perceive the external world by integrating information from different modalities, but the mechanism behind this is still unclear. A model using two reservoir computing systems was able to detect stimulus patterns that repeatedly appear in a time series signal. The model was self-organized and could detect each fluctuation pattern. The original version of the model, which incorporated feedback from appropriately learned sensory modules, performed the best compared to alternative versions.
SCIENTIFIC REPORTS
(2023)
Article
Ecology
Parvez Rana, Jari Vauhkonen
Summary: The mapping of ecosystem service provisioning often does not take into account decision-makers' preferences. Analyzing related uncertainties can be computationally demanding in landscapes with a large number of spatial units. This study proposes a stochastic multicriteria acceptability analysis to incorporate decision-makers' preferences into spatial forest management prioritization.
LANDSCAPE AND URBAN PLANNING
(2023)
Article
Computer Science, Artificial Intelligence
Malik Yousef, Ege Ulgen, Osman Ugur Sezerman
Summary: Traditional gene selection approaches often neglect biologically relevant genes, while our proposed CogNet is a new computational method that utilizes biological knowledge for gene classification and ranking in computational modeling tasks.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
ZhaoZhao Zhang, YingQin Zhu, XiaoHui Wang, Wen Yu
Summary: In this study, the ideas of adaptation method were extended to commonly used behavioural spaces to construct an echo state network behavioural space. The factors influencing behavioural space search complexity were investigated, and an optimization algorithm using a novel search genetic algorithm was proposed. The method of shrinking the search space based on the characteristics of the behaviour space distribution was introduced.
Article
Microbiology
Hyeonjung Ham, Taesung Park
Summary: In the field of microbiome analysis, various statistical methods exist for identifying differentially expressed features, but inconsistencies in significance results across methods make it difficult to determine the importance of microbiome taxa. Integrating results from different statistical methods is important, and Cauchy combination test was found to be the most suitable for microbiome data analysis, providing the best combined p-value while controlling type 1 error rates. Real data application in colorectal cancer microbiome data showed that Cauchy combination test highlighted microbiome taxa associated with colorectal cancer.
FRONTIERS IN MICROBIOLOGY
(2022)
Article
Engineering, Electrical & Electronic
YaoGuang Li, HeChi Gan
Summary: This paper constructs a multi-source data fusion model based on an ensemble learning algorithm to process and predict tourism information from many famous scenic spots in China. By using sensor detection technology, the model shows high learning ability and trend prediction ability in tourism data processing, providing necessary information support for tourists.
JOURNAL OF SENSORS
(2021)
Article
Computer Science, Artificial Intelligence
Xiang Lan, Yahong Hu, Youbai Xie, Xianghui Meng, Yilun Zhang, Qiangang Pan, Yishen Ding
Summary: Based on the basic law of Design Science, new product design relies on existing design knowledge. To improve design quality and reduce design time, knowledge integration is used in product function design by effectively utilizing existing knowledge. The complexity of product design and the abundance of design knowledge make it increasingly difficult for traditional traversal-based algorithms to complete knowledge integration within an acceptable time frame.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Chemistry, Medicinal
Yuanqing Tang, Zhi Li, Mansoor Ani Najeeb Nellikkal, Hamed Eramian, Emory M. Chan, Alexander J. Norquist, D. Frank Hsu, Joshua Schrier
Summary: Combinatorial fusion analysis (CFA) is an effective approach for combining multiple scoring systems to improve prediction quality and address data quality issues. By combining diverse machine learning models, better prediction results can be achieved.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2021)
Article
Computer Science, Artificial Intelligence
Heonho Kim, Unil Yun, Yoonji Baek, Hyunsoo Kim, Hyoju Nam, Jerry Chun-Wei Lin, Philippe Fournier-Viger
Summary: High utility pattern mining (HUPM) discovers meaningful patterns by considering item features and utility from non-binary data, and various techniques have been proposed for processing stream data based on high utility pattern mining, which uses a sliding window approach. Our proposed algorithm considers the latest data from damped stream data significantly, dividing data into fixed-sized batches and processing each batch's importance in the window differently based on added time using a decaying factor. Experimental results show that our method outperforms competitors in terms of run time, memory usage, and scalability testing.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Qin Jiang, Xi-Le Zhao, Jie Lin, Ya-Ru Fan, Jiangtao Peng, Guo-Cheng Wu
Summary: Recently, low-rank matrix/tensor-based methods have gained attention for recovering multi-dimensional multimedia data. However, the assumption of low rank is often violated due to diverse local similarity. In this article, a size-adaptive super-tensor is proposed to flexibly exploit local similarity at different scales. The proposed method outperforms other competing methods in recovering multimedia data.
KNOWLEDGE-BASED SYSTEMS
(2023)
