Article
Computer Science, Artificial Intelligence
Hongyi Li, Ying Wu, Mou Chen, Renquan Lu
Summary: This article proposes a fault-tolerant adaptive multigradient recursive reinforcement learning event-triggered tracking control scheme for strict-feedback discrete-time multiagent systems. The scheme improves system stability and tracking accuracy by introducing a new event-triggered control strategy, adaptive compensation technique, and multigradient recursive RL algorithm.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Sasha Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla P. Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio
Summary: This article discusses the importance of machine learning in reducing greenhouse gas emissions and helping society adapt to climate change. It identifies existing gaps and proposes solutions and opportunities.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Yuqiao Liu, Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Kay Chen Tan
Summary: Deep neural networks have achieved great success in many applications, but their architectures require labor-intensive and expert-designed processes. Neural architecture search (NAS) technology enables automatic design of architectures, with evolutionary computation (EC) methods gaining attention and success. However, there is currently no comprehensive summary of EC-based NAS algorithms.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yao Liu, Tanping Zhou, Zelun Yue, Wenchao Liu, Yiliang Han, Qi Li, Xiaoyuan Yang
Summary: Privacy protection of biometrics-based on cloud computing is attracting attention. An efficient and privacy-preserving online fingerprint authentication scheme called e-Finga was proposed. However, the temporary fingerprint in this scheme was found to have the risk of leaking the user's fingerprint characteristics. To counter this, a temporary fingerprint attack method was proposed and a secure e-finger scheme was developed. Experiments showed that the secure e-finger scheme can resist the temporary fingerprint attack.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Linfeng Tang, Jiteng Yuan, Jiayi Ma
Summary: This paper proposes a semantic-aware real-time image fusion network (SeAFusion), which effectively boosts the performance of high-level vision tasks on fused images and outperforms existing alternatives in terms of maintaining pixel intensity distribution and preserving texture detail.
INFORMATION FUSION
(2022)
Review
Computer Science, Information Systems
Elvira Ismagilova, Laurie Hughes, Nripendra P. Rana, Yogesh K. Dwivedi
Summary: The complex and interdependent nature of smart cities poses significant challenges for designers, integrators, and administrators. Research on security, privacy, and risks in smart cities has increased, providing valuable insights and guidance for future studies.
INFORMATION SYSTEMS FRONTIERS
(2022)
Article
Computer Science, Artificial Intelligence
Mei Liu, Liangming Chen, Xiaohao Du, Long Jin, Mingsheng Shang
Summary: This article proposes a novel method of using gradient activation function to address issues in deep neural networks. Theoretical and experimental evidence demonstrate the effectiveness of this method, which can be applied to various neural networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Diksha Khurana, Aditya Koli, Kiran Khatter, Sukhdev Singh
Summary: This paper discusses the different levels and components of NLP, introduces the history and application fields of NLP, and provides a detailed discussion on the current state, trends, and challenges of NLP. It also discusses available datasets, models, and evaluation metrics in NLP.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Xiaoming Li, Hao Liu, Weixi Wang, Ye Zheng, Haibin Lv, Zhihan Lv
Summary: This study aims to analyze massive data generated in smart city IoT through big data analysis, introducing deep learning and multi-hop transmission technology to construct a smart city DTs multi-hop transmission IoTBDA system. The performance analysis of the system shows significant improvements in energy efficiency and prediction accuracy.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Review
Computer Science, Theory & Methods
Bam Bahadur Sinha, R. Dhanalakshmi
Summary: This paper discusses the important components, new technologies, security issues, challenges, and future trends of IoT in the agriculture domain. The goal is to help potential researchers identify relevant IoT problems and adopt suitable technologies based on application requirements. The significance of IoT and Data Analytics for smart agriculture is emphasized.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Qiang Lai, Zhiqiang Wan, Hui Zhang, Guanrong Chen
Summary: This article presents a design of a new Hopfield neural network that can generate multiscroll attractors by utilizing a new memristor as a synapse in the network. The memristor is constructed with hyperbolic tangent functions and its parameters can effectively control the number of double scrolls in an attractor. Numerical analysis reveals amplitude control effects and quantitatively controllable multistability. Furthermore, a novel image encryption scheme based on the proposed memristive neural network is designed and evaluated, demonstrating good encryption performances.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Review
Computer Science, Information Systems
Jian Wang, Siyuan Lu, Shui-Hua Wang, Yu-Dong Zhang
Summary: Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN) that converges faster than traditional methods with promising performance. This paper provides a comprehensive review on ELM, focusing on theoretical analysis, improvements for stability, efficiency, and accuracy, as well as its applications in medical imaging and discussions on controversies. The aim is to report advances and explore future perspectives.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Alysa Ziying Tan, Han Yu, Lizhen Cui, Qiang Yang
Summary: With the rapid advancement of artificial intelligence, there is increasing concern about data privacy. Federated Learning (FL) has become popular as a privacy-preserving training method for machine learning models. In this survey, personalized FL is explored to address the challenges of FL on heterogeneous data.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Divya Saxena, Jiannong Cao
Summary: This study provides a comprehensive survey of the advancements in design and optimization solutions for Generative Adversarial Networks (GANs). It proposes a new taxonomy to structure the solutions and discusses different GAN variants within each solution and their relationships. Promising research directions in this rapidly growing field are also presented.
ACM COMPUTING SURVEYS
(2022)
Article
Automation & Control Systems
Yulin Li, Ben Niu, Guangdeng Zong, Jinfeng Zhao, Xudong Zhao
Summary: This article proposes an adaptive neural finite-time control strategy for stochastic nonlinear systems, which combines neural network approximation and backstepping technique, constructs a time-varying barrier Lyapunov function, and solves the difficulty arising from saturation nonlinearity.
With the proposed control strategy, it is guaranteed that system signals are bounded, the reference signal is tracked within a finite time, and system states do not violate constraints.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yong-Sheng Ma, Wei-Wei Che, Chao Deng, Zheng-Guang Wu
Summary: This article addresses the problem of distributed model-free adaptive control for learning nonlinear multiagent systems subjected to denial-of-service attacks. An improved dynamic linearization method is proposed to obtain an equivalent linear data model, and an attack compensation mechanism is developed to alleviate the influence of DoS attacks. A novel learning-based DMFAC algorithm is developed based on the equivalent linear data model and the attack compensation mechanism to resist DoS attacks, providing a unified framework to solve various control problems.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Linfeng Tang, Jiteng Yuan, Hao Zhang, Xingyu Jiang, Jiayi Ma
Summary: This paper proposes a progressive image fusion network based on illumination-aware, termed as PIAFusion, which adaptively maintains the intensity distribution of salient targets and preserves texture information in the background. The method achieves superior results in target maintenance and texture preservation compared to existing alternatives.
INFORMATION FUSION
(2022)
Article
Computer Science, Theory & Methods
Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler
Summary: Transformer model architectures have gained significant attention due to their effectiveness in various domains. In the field of natural language processing, Transformers have become essential in deep learning. This article aims to provide an organized overview of recent efficiency-focused X-former models, improving upon the original Transformer architecture by enhancing computational and memory efficiency.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Theory & Methods
Wei Yang Bryan Lim, Jer Shyuan Ng, Zehui Xiong, Jiangming Jin, Yang Zhang, Dusit Niyato, Cyril Leung, Chunyan Miao
Summary: This article introduces the concepts of federated learning and edge intelligence, proposes a hierarchical federated learning framework to address communication inefficiency, and discusses the resource allocation and incentive mechanism design problem in this framework.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Catherine D. Schuman, Shruti R. Kulkarni, Maryam Parsa, J. Parker Mitchell, Prasanna Date, Bill Kay
Summary: This article reviews recent advances in neuromorphic computing algorithms and applications, highlighting their attractive characteristics for the future of computing. The authors also discuss opportunities for future development of algorithms and applications on these systems.
NATURE COMPUTATIONAL SCIENCE
(2022)
