Article
Business
Sumana Biswas, Ismail Ali, Ripon K. Chakrabortty, Hasan Huseyin Turan, Sondoss Elsawah, Michael J. Ryan
Summary: In this research, a dynamic model for product family evolution combined with forecasting is proposed, taking into account market demand, customer needs, and technological requirements. The evaluations of product family evolution are based on Grey Relational Analysis and Fuzzy Analytical Hierarchy Process. A data-driven neural network-based forecasting model is also introduced. Numerical simulation and a case study of Apple's iPhone product family demonstrate the effectiveness of the developed approach in identifying influential key design features and best performed products for future product evolution.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2022)
Article
Energy & Fuels
Wenya Wang, Liwei Fan, Zhenfu Li, Peng Zhou, Xue Chen
Summary: The global coal trade continues to grow, adversely affecting the environment and supply security. Competitive relationships in global coal import trade are intensifying, especially in the Asian-Pacific region. It is recommended to focus more on the record-high levels of coal competition in Asia and develop more appropriate coal utilization methods.
Article
Neurosciences
Xiangjuan Ren, Hang Zhang, Huan Luo
Summary: Reasoning the hidden relational structure from sequences of events is a crucial cognitive ability in humans. This study explores the neural implementation of this process using EEG recordings and a probabilistic sequential prediction task. The results show that human brains can compute the temporal statistical relationship among discrete inputs and construct new abstract graph-like knowledge based on it.
PROGRESS IN NEUROBIOLOGY
(2022)
Article
Automation & Control Systems
Anastasia Nikolakopoulou, Moo Sun Hong, Richard D. Braatz
Summary: This article presents a synthesis method for full dynamic state feedback controllers and state and output observers that have guaranteed properties for systems approximated by dynamic artificial neural networks. The method uses linear matrix inequalities and quadratic Lyapunov function to derive sufficient conditions for controller synthesis and observer design. It is applicable to the practical situation where the steady-state values for the control input are not known.
Article
Computer Science, Hardware & Architecture
Guan-Yi Jheng, Yi-Cheng Chen, Hung-Ming Liang
Summary: This study introduces a new representation for dynamic social networks and proposes a new type of pattern - evolution pattern. The development of an evolution pattern miner (EPMiner) is aimed at efficiently discovering evolution characteristics in dynamic networks. Experimental results demonstrate the efficiency and scalability of EPMiner in extracting interaction evolution, with practical applicability shown on real datasets.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Automation & Control Systems
Bailun Zhang, Jing Zhang, Yongming Han, Zhiqiang Geng
Summary: The article presents a novel DSS modeling method based on OESN-CMI-IDE, which achieves better prediction results for the melt index through calculating mutual information and optimizing parameters.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yi-Zhu Su, Wei-Chang Yeh
Summary: This study proposes a time-related Binary-Addition Tree-based method that considers more decision variables and parameters to evaluate the resilience of the network system and provide protection and recovery strategies to deal with attacks that interfere with the system.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Kaveh Kadkhoda Mohammadmosaferi, Hassan Naderi
Summary: The study introduces the AFIF method, which efficiently extracts structural features from social networks and predicts future changes in community evolution.
COMPUTER COMMUNICATIONS
(2021)
Article
Neurosciences
Zening Fu, Armin Iraji, Jessica A. Turner, Jing Sui, Robyn Miller, Godfrey D. Pearlson, Vince D. Calhoun
Summary: The study suggests that the brain reconfigures itself through the co-evolution of activity and connectivity, where schizophrenia patients spend more time in weakly connected and activated states and less time in strongly connected and activated states. Additionally, schizophrenia patients show lower efficiency in thalamic regions within strong states, and the atypical fractional occupancy of a specific brain state is correlated with individual attention performance.
Article
Business, Finance
Wei Liu, Qianting Ma, Xiaoxing Liu
Summary: This paper constructs a stock correlation network model in the Chinese new energy market and investigates its dynamic evolution and influencing factors. The findings suggest that the network exhibits small world feature, and the network entropy effectively captures the change direction of network structure and describes market volatility. Moreover, the ranking of network centrality in the new energy market is primarily influenced by internal characteristic variables of new energy enterprises.
FINANCE RESEARCH LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Wei-Chia Huang, Chiao-Ting Chen, Chi Lee, Fan-Hsuan Kuo, Szu-Hao Huang
Summary: With advances in FinTech, the finance industry aims to enhance efficiency through technology, with robo-advisors being a highly desired financial service. A combination of algorithms and information fusion is used to forecast future market situations by determining rules and implicit correlations between collected data. This paper introduces a deep learning fusion model based on graph structure and attention mechanism to study interaction between time-series financial variables, improving trend and volatility prediction accuracy and developing a pairs trading application.
INFORMATION FUSION
(2023)
Article
Automation & Control Systems
Yang Yu, Zhenyu Lei, Yirui Wang, Tengfei Zhang, Chen Peng, Shangce Gao
Summary: This research introduces a differential evolution algorithm based on a dynamic scale-free network to address the limitations of traditional artificial neuron networks. Experimental results on benchmark datasets and a photovoltaic power forecasting problem demonstrate that the proposed algorithm outperforms other methods.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Energy & Fuels
Ruobin Gao, Ruilin Li, Minghui Hu, Ponnuthurai Nagaratnam Suganthan, Kum Fai Yuen
Summary: This paper proposes a novel approach for wave height prediction using dynamic ensemble deep Echo state networks. The suggested model outperforms state-of-the-art approaches in statistical analysis on multiple datasets.
Article
Mathematics
Yifei Yang, Sichen Tao, Haichuan Yang, Zijing Yuan, Zheng Tang
Summary: Complex networks, formed by intricate connections in complex systems, provide insights into the underlying principles governing system behavior. This paper challenges the notion of a direct link between algorithm performance and complex network structure through experimental evidence. By analyzing dynamic complex network structures of five algorithms across three different problems and incorporating mathematical distributions, we generate novel insights and refine previous conclusions. Our aim is to redirect research on the interplay between complex networks and evolutionary computation towards dynamic network structures, elucidating the essence of exploitation and exploration in evolutionary algorithms.
Article
Multidisciplinary Sciences
Abayomi S. Olabode, Garway T. Ng, Kaitlyn E. Wade, Mikhail Salnikov, Heather E. Grant, David W. Dick, Art F. Y. Poon
Summary: This study developed a new clustering method to analyze HIV-1 genomes, revealing that most of the genomes exhibit recombination. It also proposed an informative framework for HIV-1 classification.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)