Article
Chemistry, Multidisciplinary
Yongshun Shen, Yuzhen Zhao
Summary: This paper proposes a new type of spiking neural P system (SNP) called RDGRSNP systems. In RDGRSNP systems, the rules in neurons can change based on the substances within them. The Turing universality of RDGRSNP systems is demonstrated with both a number-generating device and a number-accepting device. A small universal RDGRSNP system for function computation using 68 neurons is provided, which requires fewer neurons compared to other SNP system variants.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Zhang Sun, Luis Valencia -Cabrera, Guimin Ning, Xiaoxiao Song
Summary: Spiking neural P systems are an abstraction of the structure and function of nervous systems and neurons. SNP-WOD systems, a new class of these systems, remove the mechanism of duplication and allow for the amplification of pulses during the firing of spiking rules. These systems have computational properties and can generate numbers.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Xiaoxiao Song, Luis Valencia-Cabrera, Hong Peng, Jun Wang
Summary: This paper introduces a new neural computing model - spiking neural P systems with autapses (SNP-AU systems) and demonstrates their ability to generate Turing-computable numbers. By building an SNP-AU system with 53 neurons and providing a universal machine, the universality of its computing function is shown.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Suxia Jiang, Yijun Liu, Bowen Xu, Junwei Sun, Yanfeng Wang
Summary: In this study, asynchronous numerical spiking neural (ANSN) P systems are investigated by combining set theory and threshold control strategy. It is proved that ANSN P systems are Turing universal and capable of processing information.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Yuping Liu, Yuzhen Zhao
Summary: This work introduces the phenomenon of lateral inhibition in biological nervous systems into spiking neural P systems and proposes SN P systems with lateral inhibition (LISN P systems). By adjusting the lateral distance, lateral inhibition can affect the information transmission between neurons, and the designed LISN P systems can be used to generate arbitrary numbers and perform function computation, demonstrating computational completeness.
Article
Computer Science, Artificial Intelligence
Xiaoxiao Song, Luis Valencia-Cabrera, Hong Peng, Jun Wang, Mario J. Perez-Jimenez
Summary: This paper introduces SNP-DS systems as a powerful computing model based on the characteristics and communication of neurons, with the feature of neurons receiving spikes at different instants through delaying synapses. Additionally, two small universal SNP-DS systems are constructed to compute functions, with a simulator provided for experimental validation.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zeqiong Lv, Tingting Bao, Nan Zhou, Hong Peng, Xiangnian Huang, Agustin Riscos-Nunez, Mario J. Perez-Jimenez
Summary: The paper introduces a new variant of spiking neural P systems, called SNP-ECR systems, which are distributed parallel computing models with a stronger firing control mechanism. The new spiking rule ECR allows neurons to send different numbers of spikes, providing greater flexibility in computation. It is proven that SNP-ECR systems are Turing universal as number generating/accepting devices and can function as universal function computing devices.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Computer Science, Information Systems
Yuzhen Zhao, Yongshun Shen, Xuefu Liu, Yueguo Luo, Wenke Zang, Xiyu Liu
Summary: Spiking neural P systems (SNP systems) are enhanced with long-term potentiation/depression mechanisms from biological neural systems, allowing them to dynamically adjust synaptic weights based on environmental changes. This improves their learning ability and intelligence. A novel type of SNP system, called SNP systems with long-term potentiation and depression (LTPD-SNP systems), is developed. The weights of synapses in LTPD-SNP systems change dynamically based on the spikes' intensity, timing, and their own properties. The universality of LTPD-SNP systems is proven and their computational efficiency is studied in solving the SAT problem. Additionally, an anomaly detection method for AC engines based on LTPD-SNP systems is constructed to demonstrate their learning capabilities. This work enhances the learning ability and intelligence of SNP systems and provides insights for creating brain-like intelligent computational models.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Liping Wang, Xiyu Liu, Minghe Sun, Yuzhen Zhao
Summary: In this paper, a new variant of evolution-communication spiking neural P systems, called ECSNP-ER systems, is proposed and developed. ECSNP-ER systems incorporate energy request rules in addition to spike-evolution rules and spike-communication rules. The definition, structure, and operations of ECSNP-ER systems are presented in detail. It is shown that ECSNP-ER systems have the same computational capabilities as Turing machines and can solve NP-complete problems, such as the SAT problem, in linear time.
Article
Engineering, Chemical
Xiyu Liu, Qianqian Ren
Summary: The spiking neural membrane computing models (SNMC models) proposed in this paper combine neural network structure and data processing methods to improve the shortcomings of current spiking neural P systems (SNP) in numerical calculations. In SNMC models, the state of each neuron is represented by a real number, and there are new rules for neurons with time delay. The Turing universality of the SNMC model as a number generator and acceptor is also demonstrated.
Article
Computer Science, Artificial Intelligence
Tingfang Wu, Qiang Lyu, Linqiang Pan
Summary: This study explores spiking neural P systems (SNP systems) and their variant evolution-communication SNP (ECSNP) systems, demonstrating the Turing universality of ECSNP systems as number-generating devices and highlighting the critical impact of the quantity of spikes in neurons on the computational power of ECSNP systems.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Engineering, Chemical
Xiu Yin, Xiyu Liu, Minghe Sun, Qianqian Ren
Summary: NSNVC P systems are a novel type of neural P systems with a variable consumption strategy, introducing delay features and variable consumption strategy for number generating and function computing. They possess distributed parallel computing models and Turing universality.
Article
Computer Science, Information Systems
Tingfang Wu, Luping Zhang, Qiang Lyu, Yu Jin
Summary: Asynchronous spiking neural P (AsynSN P) systems are distributed and parallel computational models inspired by biological neurons. This study introduces a control mechanism of local synchronization at the rule level and examines the computational power of different systems. The results show that local synchronization of rules can improve the computational capability of the systems.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Jianping Dong, Gexiang Zhang, Biao Luo, Qiang Yang, Dequan Guo, Haina Rong, Ming Zhu, Kang Zhou
Summary: This paper proposes a distributed adaptive optimization spiking neural P system (DAOSNPS) that can solve combinatorial optimization problems without the help of evolutionary algorithms or swarm intelligence algorithms. Extensive experiments demonstrate its superiority over other methods.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Theory & Methods
Tingfang Wu, Luping Zhang, Linqiang Pan
Summary: The study introduced a new spike distribution mechanism in spiking neural P systems (SNP systems) and investigated their computational power, demonstrating their Turing universality. It was shown that a universal SNP system can be constructed with just 6 or 15 neurons with the proposed spike distribution mechanism, which is more efficient in terms of the number of neurons required compared to the classical model.
THEORETICAL COMPUTER SCIENCE
(2021)
Article
Biochemical Research Methods
Yajie Meng, Changcheng Lu, Min Jin, Junlin Xu, Xiangxiang Zeng, Jialiang Yang
Summary: In this study, a novel neural collaborative filtering approach is proposed for drug repositioning, which utilizes deep-learning approaches based on a heterogeneous network. The approach takes advantage of localized information in different networks and models the complex drug-disease associations effectively. The effectiveness of the approach is verified through benchmarking comparisons and validated against clinical trials and authoritative databases.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Bosheng Song, Xiaoyan Luo, Xiaoli Luo, Yuansheng Liu, Zhangming Niu, Xiangxiang Zeng
Summary: The spatial structures of proteins are important for their functions, but the limited quantity of known protein structures restricts their application in prediction methods. Utilizing predicted protein structure information can improve sequence-based prediction methods. TAGPPI is a novel framework that uses only protein sequences to predict protein-protein interactions and extracts spatial structure information from contact maps to improve prediction performance.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Jianqiang Li, Tao Sun, Qiuzhen Lin, Min Jiang, Kay Chen Tan
Summary: This article proposes a clustering-based transfer (CBT) learning method to solve dynamic multiobjective optimization problems (DMOPs), aiming to reduce negative transfer and improve the effectiveness of transferred solutions. The method guides knowledge transfer through clustering and transfer learning operations, and trains an accurate prediction model to identify promising solutions for the new environment. Empirical studies have validated the effectiveness of the proposed method.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Haokai Hong, Kai Ye, Min Jiang, Donglin Cao, Kay Chen Tan
Summary: This paper proposes a large-scale multiobjective optimization algorithm LMOPPM based on the probabilistic prediction model, which improves the diversity and convergence of the population through importance sampling and a trend prediction model. The proposed algorithm provides significant improvements in terms of performance and computational efficiency in large-scale multiobjective optimization.
Article
Computer Science, Artificial Intelligence
Jia Zhang, Hanrui Wu, Min Jiang, Jinghua Liu, Shaozi Li, Yong Tang, Jinyi Long
Summary: In many real-world application domains, objects often belong to multiple class labels, which leads to the multi-label learning problem. The quality of available features greatly affects the performance of multi-label learning, but the data usually contain many irrelevant, redundant, or noisy features. As a result, feature selection methods have been extensively studied to select meaningful features for multi-label learning. However, existing methods often fail to consider label-specific features and are inefficient in utilizing labeling information. In this paper, we propose a new group-preserving label-specific feature selection framework to address these issues, and extensive experiments demonstrate its advantages.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Biochemical Research Methods
Yanyan Li, Bosheng Song, Xiangxiang Zeng
Summary: The article introduces neural-like P systems with plasmids (NP P systems) which are inspired by bacteria's DNA processing. It also presents NPMC P systems, which use multiple channels for communication between bacteria and explores their computation power.
IEEE TRANSACTIONS ON NANOBIOSCIENCE
(2023)
Article
Biochemical Research Methods
Xixi Yang, Zhangming Niu, Yuansheng Liu, Bosheng Song, Weiqiang Lu, Li Zeng, Xiangxiang Zeng
Summary: Prediction of drug-target affinity is crucial in drug discovery. Existing deep learning methods focus on single modality inputs, while our proposed Modality-DTA leverages the multimodality of drugs and targets for better prediction performance. Experimental results demonstrate the superiority of Modality-DTA over existing methods in all metrics.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Xuan Lin, Zhe Quan, Zhi-Jie Wang, Yan Guo, Xiangxiang Zeng, Philip S. S. Yu
Summary: Effectively identifying compound-protein interactions (CPIs) is crucial for new drug design. We propose a deep learning framework named GraphCPI, which captures the structural information of compounds and leverages the chemical context of protein sequences. Our method shows competitiveness and feasibility in extensive experiments based on widely-used CPI datasets.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Lingjie Li, Manlin Xuan, Qiuzhen Lin, Min Jiang, Zhong Ming, Kay Chen Tan
Summary: This article proposes a new evolutionary multitasking algorithm for feature selection in high-dimensional classification. It generates multiple relevant low-dimensional feature selection tasks using different filtering methods and solves them efficiently through knowledge transfer using a modified competitive swarm optimizer. Experimental results show that the proposed EMT-based method outperforms several state-of-the-art feature selection methods on 18 high-dimensional datasets.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Zhenzhong Wang, Haokai Hong, Kai Ye, Guang-En Zhang, Min Jiang, Kay Chen Tan
Summary: This paper proposes a GAN-based manifold interpolation framework for solving large-scale multiobjective optimization problems. Experimental results demonstrate significant improvements in solving LSMOPs using this framework.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Guodong Du, Jia Zhang, Min Jiang, Jinyi Long, Yaojin Lin, Shaozi Li, Kay Chen Tan
Summary: This article proposes a label enhancement method to solve the problem of class imbalance in a graph manner, which estimates the numerical label and trains the inductive model simultaneously. The experimental results demonstrate the superior performance of the proposed method in single-label and multilabel class-imbalance learning.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Ying Xu, Chong Xu, Huan Zhang, Lei Huang, Yiping Liu, Yusuke Nojima, Xiangxiang Zeng
Summary: This article proposes a new metric to calculate the contribution of each decision variable to the optimization objectives, and based on this, a multiobjective evolutionary algorithm called DVCOEA is introduced. The experimental results show that DVCOEA is a competitive approach for solving large-scale multi/many-objective problems.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Haokai Hong, Min Jiang, Gary G. Yen
Summary: The large-scale multiobjective optimization problem (LSMOP) involves optimizing multiple conflicting objectives and hundreds of decision variables. Existing algorithms often focus on improving performance but pay little attention to improving insensitivity. We propose an evolutionary algorithm based on Monte Carlo tree search to improve the performance and insensitivity of solving LSMOPs.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Qiuzhen Lin, Yulong Ye, Lijia Ma, Min Jiang, Kay Chen Tan
Summary: This article introduces a new dynamic multiobjective evolutionary algorithm (DMOEA), called KTM-DMOEA, with Knowledge Transfer and Maintenance, which aims to alleviate negative transfer and enhance optimization efficiency. Two strategies, namely knowledge transfer prediction (KTP) and knowledge maintenance sampling (KMS), are proposed to extract useful knowledge and generate a superior initial population, resulting in improved performance.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zefeng Wang, Junfeng Yao, Meiyan Xu, Min Jiang, Jinsong Su
Summary: Considerable progress has been made in utilizing deep learning techniques, particularly the Transformer-based network, for improving the recognition accuracy of sparse surface electromyography (sEMG) signals. The proposed network achieves higher accuracy with fewer parameters and lower computational cost compared to traditional approaches such as CNN and RNN.
PATTERN RECOGNITION
(2024)
