Article
Computer Science, Artificial Intelligence
Jieyu Zhang, Miqing Li, Weibo Liu, Stanislao Lauria, Xiaohui Liu
Summary: This paper proposes a novel food recommendation approach based on many-objective optimization (MaOO). By transforming the recommendation problem into an MaOO problem with four different objectives, i.e., user preferences, nutritional values, dietary diversity, and user diet patterns, the designed approach provides a more balanced way of recommending food compared to classical recommendation methods that only consider individuals' food preferences.
Review
Biochemistry & Molecular Biology
Jianbo Fu, Feng Zhu, Cheng-Jian Xu, Yang Li
Summary: Metabolic processes play a crucial role in immune regulation. Metabolomics provides a comprehensive approach to study the interactions between metabolism and immunity in physiology and disease. This review discusses recent technological developments in metabolomics and its integration with other omics approaches, providing guidance for researchers in the field of immune research.
Article
Computer Science, Hardware & Architecture
Ying-Chang Liang, Ruizhe Long, Qianqian Zhang, Dusit Niyato
Summary: This article introduces a novel paradigm for wireless communication called symbiotic communication (SC), where relevant radio systems form a symbiotic relationship through intelligent resource/service exchange. By leveraging the concept of ecosystems in biology, the SC paradigm provides a fresh perspective and guidelines for radio resource management and the design of future wireless communication systems.
IEEE WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Simon Lacoste-Julien
Summary: This article proposes a more robust variance reduction method called AdaSVRG, which uses the adaptive gradient method AdaGrad for optimization. Experimental results demonstrate the robustness and superior performance of AdaSVRG in terms of step-size selection.
Article
Computer Science, Artificial Intelligence
Menglong Lin, Tao Chen, Honghui Chen, Bangbang Ren, Mengmeng Zhang
Summary: The design of System of Systems (SoS) has been a topic of great concern, especially in military applications. This paper proposes a deep reinforcement learning approach called DRL-SoSDP to address the challenges of SoS architecting. By combining artificial intelligence techniques and actor-critic algorithms, DRL-SoSDP achieves superior results in solution quality and computation time, even in large scale cases.
ADVANCED ENGINEERING INFORMATICS
(2023)
Review
Biochemical Research Methods
Wenying Yan, Guang Hu
Summary: By utilizing structural networks, high-throughput modeling of protein functional sites and protein dynamics can be achieved. In the future, the integration of biomolecular networks may be leveraged to develop a modeling framework that addresses protein structure-based functions.
CURRENT BIOINFORMATICS
(2022)
Review
Biotechnology & Applied Microbiology
Liang Xiang, Guoqiang Li, Luan Wen, Cong Su, Yong Liu, Hongzhi Tang, Junbiao Dai
Summary: This review discusses the use of synthetic biology tools to accelerate microbial degradation of environmental pollutants, including building chassis cells and designing strategies for modifying target organisms. Future research in this field faces challenges and opportunities.
SYNTHETIC AND SYSTEMS BIOTECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Mincan Li, Zidong Wang, Kenli Li, Xiangke Liao, Kate Hone, Xiaohui Liu
Summary: This article introduces a novel layered MAS model that addresses the multitask multiagent allocation problem using deep Q-learning and MSDE methods. The MSDE-SPEA2-based method is proposed to tackle many-objective optimization problem with various objectives like task allocation, completion time, agent satisfaction, etc.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Engineering, Multidisciplinary
Zeou Hu, Kiarash Shaloudegi, Guojun Zhang, Yaoliang Yu
Summary: In this work, federated learning is formulated as multi-objective optimization and a new algorithm called FedMGDA+ is proposed, which guarantees fairness and robustness while maintaining individual performance for participating users.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Automation & Control Systems
Chen Gao, Zidong Wang, Xiao He, Qing-Long Han
Summary: This article tackles the consensus control problem for a general class of linear multiagent systems subject to actuator imperfections, proposing a two-step saturation-resistant approach to mitigate the side effects. By utilizing state information from neighboring agents and introducing the domain of attraction (DOA) for MASs, the controller is optimized to expand the DOA and solve a set of matrix inequalities. Simulation examples are presented to demonstrate the effectiveness of the developed approach.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Editorial Material
Chemistry, Multidisciplinary
Chong Liu
Summary: The combination of electrochemistry and nanotechnology allows for spatio-temporal control at the nanoscale for nonequilibrium chemical and biological systems in liquid solutions.
Article
Automation & Control Systems
Mohamadreza Ahmadi, Nils Jansen, Bo Wu, Ufuk Topcu
Summary: Partially observable Markov decision processes (POMDPs) provide a modeling framework for sequential decision making under uncertainty in AI. The complexity of POMDPs is addressed by applying control theory techniques to analyze discrete-time switched systems and estimate reachable belief spaces. Safety and performance requirements are verified using barrier certificate theorems, and computations can be decomposed and solved in parallel, ultimately implemented as a set of sum-of-squares programs.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2021)
Article
Biotechnology & Applied Microbiology
Joseph A. Rollin, Yannick J. Bomble, Peter C. St John, Addison K. Stark
Summary: Bioprocesses offer opportunities for chemical process innovation, but strain engineering and microbial systems remain unpredictable and expensive. Purified cell-free technologies can mitigate these limitations, allowing for predictive modeling and control of reaction conditions.
BIOCHEMICAL ENGINEERING JOURNAL
(2021)
Review
Chemistry, Multidisciplinary
Joao C. A. Oliveira, Johanna Frey, Shuo-Qing Zhang, Li-Cheng Xu, Xin Li, Shu-Wen Li, Xin Hong, Lutz Ackermann
Summary: The recent merger of machine learning with molecular synthesis has led to significant advancements in organic synthesis and catalysis, relying on chemical databases, molecular descriptors, and ML algorithms for efficient prediction.
TRENDS IN CHEMISTRY
(2022)
Review
Physiology
Gianluigi Mazzoccoli
Summary: Biological processes and physiological functions in living beings exhibit oscillations driven by the biological clock. Increasing evidence suggests the presence of non-trivial quantum phenomena in biological systems. Rhythmic changes at the molecular level play a crucial role in supporting electrochemical processes and quantum effects.
FRONTIERS IN PHYSIOLOGY
(2022)