Article
Green & Sustainable Science & Technology
Claude A. Garcia, Sini Savilaakso, Rene W. Verburg, Natasha Stoudmann, Philip Fernbach, Steven A. Sloman, Garry D. Peterson, Miguel B. Araujo, Jean-Francois Bastin, Juergen Blaser, Laurence Boutinot, Thomas W. Crowther, Helene Dessard, Anne Dray, Scott Francisco, Jaboury Ghazoul, Laurene Feintrenie, Etienne Hainzelin, Fritz Kleinschroth, Babak Naimi, Ivan P. Novotny, Johan Oszwald, Stephan A. Pietsch, Fabien Quetier, Brian E. Robinson, Marieke Sassen, Plinio Sist, Terry Sunderland, Cedric Vermeulen, Lucienne Wilme, Sarah J. Wilson, Francisco Zorondo-Rodriguez, Patrick O. Waeber
Summary: Scholars often overlook the impact of decision-making on the Earth system, but using strategy games can increase the representation of human agency in scenario development and facilitate deliberation between diverse worldviews.
NATURE SUSTAINABILITY
(2022)
Article
Chemistry, Medicinal
Rupesh Agarwal, T. Rajitha Rajeshwar, Jeremy C. Smith
Summary: Structure-based virtual high-throughput screening is commonly used in early-stage drug discovery. This study evaluated the performance of three docking protocols on 173 RNA-small molecule crystal structures. The results showed that Vina and rDock are both applicable for projects without known ligand-protein structures, but their performance is relatively poor compared to protein-target docking methods.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Automation & Control Systems
Md Alamgir Hossain, Evan Gray, Junwei Lu, Md Rabiul Islam, Md Shafiul Alam, Ripon Chakrabortty, Hemanshu Roy Pota
Summary: This article proposes a novel framework, CEMOLS, to improve the prediction accuracy of very short-term wind power generation. The framework combines CEEMDAN, MBO, and LSTM models and demonstrates an improvement in forecasting accuracy compared to the benchmark model.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Biochemical Research Methods
Chenran Wang, Yang Chen, Yuan Zhang, Keqiao Li, Menghan Lin, Feng Pan, Wei Wu, Jinfeng Zhang
Summary: Protein ligand docking is a computational tool for predicting protein functions and screening drug candidates. In this study, a novel reinforcement learning approach called A3C was developed to address the challenging problem of protein ligand docking. The experimental results showed significant improvement in binding site prediction compared to a naive model.
BMC BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Qianlong Dang, Jiawei Yuan
Summary: This paper proposes an evolutionary multitasking algorithm based on the Kalman filter prediction strategy to simultaneously solve multiple optimization tasks through knowledge transfer. Experimental results demonstrate that the algorithm achieves competitive performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Environmental Sciences
Ashok Bragadeshwaran, Vignesh Rajasekar, Kaisan Muhammad Usman, Tamilvanan Ayyasamy, Kumaresan Govindasamy
Summary: The study aims to enhance the performance and emission characteristics of a diesel engine running on biofuel by accurately calibrating its fuel injector control parameters. A novel global model-based calibration approach is used to create optimal split injector control maps, and response surface methodology is employed to establish a relationship between calibration parameters and engine performance parameters. The optimization process resulted in improved brake thermal efficiency and reduced brake specific fuel consumption, but slightly higher NOx emissions compared to diesel fuel.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Automation & Control Systems
Hao Sun, Pengfei Chen, Ziyu Hu, Lixin Wei
Summary: The superior performance of evolutionary multitasking algorithms is attributed to the potential synergy between tasks. Current algorithms only transfer individuals from the source to the target task in a unidirectional process. This approach fails to consider the target task's search preference, leading to underutilization of task synergy. We propose a bidirectional knowledge transfer method that takes into account the target task's search preference when finding transferred individuals. Experimental results show that the proposed algorithm outperforms other comparison algorithms in over 30 benchmarks and exhibits considerable convergence efficiency.
Article
Computer Science, Information Systems
Qi Li, Shuliang Wang, Xianjun Zeng, Boxiang Zhao, Yingxu Dang
Summary: In this paper, a clustering optimization method called HIAC is proposed, which introduces gravitation to force objects in the dataset to move towards similar objects, resulting in a more friendly dataset for clustering algorithms. HIAC is the first method to adopt the selective-addition mechanism and uses a decision graph to identify valid-neighbors. Experimental results show that HIAC significantly improves the accuracy of clustering algorithms and has a shorter runtime compared to similar methods.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Peidi Wang, Yongjie Ma, Minghao Wang
Summary: The focus of research on dynamic multi-objective optimization problems is to design algorithms that can quickly adapt to environmental changes. This study proposes a novel DMOEA that uses particle swarm prediction strategy and prediction adjustment strategy to approximate the Pareto optimal set as accurately as possible, and demonstrates its competitive performance through experiments.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Mahir Patel, Yiwen Gu, Lucas C. Carstensen, Michael E. Hasselmo, Margrit Betke
Summary: Accurate 3D pose tracking of animals is crucial for behavioral studies, yet there is a lack of publicly available datasets for model development in computer vision. In this study, we introduce the Rodent3D dataset, which records animals exploring their environment and/or interacting with each other using multiple cameras and modalities. We propose OptiPose, a baseline model that represents 3D poses as tokens and uses deep-learned context models to pay attention to both spatial and temporal keypoint patterns.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Computer Science, Artificial Intelligence
Carmen Bisogni, Michele Nappi, Chiara Pero, Stefano Ricciardi
Summary: FASHE, based on partitioned iterated function systems (PIFS), represents a method for head pose estimation by handling auto-similarities within domain blocks. Results show that this method performs well on multiple datasets and approaches the levels of the best performing methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Interdisciplinary Applications
Valerie Ouellet, Julien Mocq, Salah-Eddine El Adlouni, Stefan Krause
Summary: Previous criticisms of knowledge-based fuzzy logic modelling have pointed out limitations and weaknesses, while we propose a framework to improve model performance and robustness by addressing sources of error, bias, and incorporating expert disagreement. Clear instructions, expert disagreement consideration, use of short rules and OR operator, and narrow fuzzy sets improve model performance and expand the applicability of the framework to all knowledge-based models requiring expert judgment.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Thermodynamics
Xidong Zheng, Feifei Bai, Ziyang Zeng, Tao Jin
Summary: This paper develops a novel optimization methodology to improve wind power prediction accuracy by reducing and eliminating power quality disturbance. Through dynamic mode decomposition and Wiener filter strategy, the autonomy of PQD is reduced and higher signal-to-noise ratio is achieved. Different complex PQD is considered to compare their effects on deep learning-based wind power prediction accuracy.
Article
Computer Science, Artificial Intelligence
Wei Li, Xinyu Gao, Lei Wang
Summary: Multifactorial optimization is a widely studied optimization problem. This paper introduces an evolutionary multitasking optimization algorithm, EMT-ADT, which utilizes a decision tree to predict and select individuals for knowledge transfer, improving algorithm performance.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Automation & Control Systems
Xiao-Fang Liu, Jun Zhang, Jun Wang
Summary: This article presents a cooperative differential evolution algorithm with an attention-based prediction strategy for dynamic multiobjective optimization. Multiple populations are used to optimize multiple objectives and find subparts of the Pareto front. The algorithm achieves a balanced approximation of the Pareto front and adapts to changes in the environment by using a new attention-based prediction strategy. Experimental results demonstrate the superiority of the proposed method to state-of-the-art algorithms.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Chemistry, Medicinal
Artern Cherkasov, Fuqiang Ban, Osvaldo Santos-Filho, Nels Thorsteinson, Magid Fallahi, Geoffrey L. Hammond
JOURNAL OF MEDICINAL CHEMISTRY
(2008)
Article
Medicine, Research & Experimental
Arif Jetha, Nels Thorsteinson, Yazen Jmeian, Ajitha Jeganathan, Patricia Giblin, Johan Fransson
Article
Biochemistry & Molecular Biology
Juan C. Almagro, Mary Pat Beavers, Francisco Hernandez-Guzman, Johannes Maier, Jodi Shaulsky, Kenneth Butenhof, Paul Labute, Nels Thorsteinson, Kenneth Kelly, Alexey Teplyakov, Jinquan Luo, Raymond Sweet, Gary L. Gilliland
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
(2011)
Article
Pharmacology & Pharmacy
Nels Thorsteinson, Fuqiang Ban, Osvaldo Santos-Filho, Seyed M. H. Tabaei, Solange Miguel-Queralt, Caroline Underhill, Artem Cherlasov, Geoffrey L. Hammond
TOXICOLOGY AND APPLIED PHARMACOLOGY
(2009)