Article
Computer Science, Information Systems
Iuliu Alexandru Zamfirache, Radu-Emil Precup, Raul-Cristian Roman, Emil M. Petriu
Summary: This paper introduces a RL-based control approach using PI and GWO algorithm to train NNs, which shows better performance in the experiments.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Chang Tang, Xiao Zheng, Xinwang Liu, Wei Zhang, Jing Zhang, Jian Xiong, Lizhe Wang
Summary: In this paper, we propose a multi-view unsupervised feature selection model (CvLP-DCL) that preserves diversity and consensus learning across views. By projecting each view into a label space, we exploit shared and distinguishing information across different views and preserve the local structure of data using regularizations and similarity graph learning. By constraining row sparsity, discriminative features are selected, improving the model's selection capability.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Jianxin Li, Hao Peng, Yuwei Cao, Yingtong Dou, Hekai Zhang, Philip S. Yu, Lifang He
Summary: Graph neural networks (GNNs) are widely used in deep learning for graph analysis tasks. However, current methods ignore heterogeneity in real-world graphs and fail to capture content-based correlations between nodes. In this paper, we propose a novel HAE framework and a HAE(GNN) model that incorporates meta-paths and meta-graphs for rich, heterogeneous semantics and leverages self-attention mechanism for exploring content-based interactions between nodes.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(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, Artificial Intelligence
David Alexander Tedjopurnomo, Zhifeng Bao, Baihua Zheng, Farhana Choudhury, A. K. Qin
Summary: In this modern era, traffic congestion has become a major source of negative economic and environmental impact on urban areas worldwide. One efficient solution to mitigate congestion is through future traffic prediction. This survey paper provides an up-to-date overview of deep neural networks for traffic prediction, including popular architectures, literature categorization, comparisons, and discussions on challenges and future directions.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Saleh Nagi Alsubari, Sachin N. Deshmukh, Ahmed Abdullah Alqarni, Nizar Alsharif, Theyazn H. H. Aldhyani, Fawaz Waselallah Alsaade, Osamah I. Khalaf
Summary: Fake reviews have gained importance due to the increase in online marketing transactions. This study proposes an intelligent system using n-grams and sentiment scores to detect and classify fake reviews on e-commerce platforms. Four different machine learning techniques were used, and the results outperformed existing methods in terms of accuracy.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoou Ding, Hongzhi Wang, Jiaxuan Su, Muxian Wang, Jianzhong Li, Hong Gao
Summary: This paper studies the method of multiple data cleaning for incomplete and inconsistent data, proposing a four-step framework called Imp3C. It uses a currency determining method and a consistency distance metric to repair dirty data. Experiments demonstrate that Imp3C outperforms existing methods in data repairing.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Review
Computer Science, Artificial Intelligence
Yogesh Kumar, Apeksha Koul, Ruchi Singla, Muhammad Fazal Ijaz
Summary: Artificial intelligence plays a significant role in disease diagnosis, drug discovery, and patient risk identification in healthcare. This article provides a comprehensive survey on the use of artificial intelligence techniques for diagnosing various diseases and compares the quality parameters of different studies.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2022)
Article
Computer Science, Information Systems
Chunfang Deng, Mengmeng Wang, Liang Liu, Yong Liu, Yunliang Jiang
Summary: In this paper, the authors propose an extended feature pyramid network (EFPN) for small object detection. They introduce a feature texture transfer (FTT) module for super-resolving features and extracting regional details, as well as a cross resolution distillation mechanism to enhance the network's ability to perceive details. Experimental results show that the proposed EFPN is computationally and memory efficient, and achieves state-of-the-art results on small object detection datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
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
Arunodaya Raj Mishra, Pratibha Rani Bullet, Kiran Pandey
Summary: The paper introduces a hybrid methodology based on Fermate fuzzy sets to solve the S3PRLP selection problem, which can handle unknown attributes and decision makers' weights. The framework combines CRITIC and EDAS methods, demonstrating good performance in a case study and showing its practicality and feasibility.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Xin Luo, Ye Yuan, Sili Chen, Nianyin Zeng, Zidong Wang
Summary: A latent factor analysis model based on particle swarm optimization algorithm is proposed, which improves the learning rate adaptation while achieving higher prediction accuracy and computational efficiency.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Tareq M. Shami, Ayman A. El-Saleh, Mohammed Alswaitti, Qasem Al-Tashi, Mhd Amen Summakieh, Seyedali Mirjalili
Summary: This paper provides a comprehensive review of particle swarm optimization (PSO), including its basic concepts, variants, applications, and drawbacks. It also reviews research on utilizing PSO to solve feature selection problems and presents potential research directions.
Article
Computer Science, Artificial Intelligence
Jipeng Qiang, Zhenyu Qian, Yun Li, Yunhao Yuan, Xindong Wu
Summary: Analyzing short texts and finding discriminative and coherent latent topics is a crucial task that has attracted much attention in the machine learning research community. This survey provides a comprehensive review of various short text topic modeling techniques and evaluates their performance on real-world datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Review
Computer Science, Artificial Intelligence
Jie Gui, Zhenan Sun, Yonggang Wen, Dacheng Tao, Jieping Ye
Summary: In this paper, a comprehensive review of various GAN methods is provided from the perspectives of algorithms, theory, and applications. The motivations, mathematical representations, and structures of most GAN algorithms are detailed and compared. Theoretical issues related to GANs are also investigated, and the typical applications of GANs in various fields are discussed.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Information Systems
Cheng Yan, Guansong Pang, Xiao Bai, Changhong Liu, Xin Ning, Lin Gu, Jun Zhou
Summary: Person Re-Identification aims to re-identify individuals from different viewpoints using fine-grained appearance differences. A novel pairwise loss function is introduced to enable learning of fine-grained features by penalizing small differences exponentially and large differences moderately. Experimental results show that the proposed loss outperforms popular loss functions and enhances data efficiency.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Information Systems
Christian Meske, Enrico Bunde, Johannes Schneider, Martin Gersch
Summary: Artificial Intelligence (AI) has permeated many aspects of our lives, and this research note discusses the risks of black-box AI, the need for explainability, and previous research on Explainable AI (XAI) in information systems research. The note also explores the origin, objectives, stakeholders, and quality criteria of personalized explanations in XAI, and concludes with an outlook on future XAI research.
INFORMATION SYSTEMS MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Zhenyu Xiao, Lipeng Zhu, Yanming Liu, Pengfei Yi, Rui Zhang, Xiang-Gen Xia, Robert Schober
Summary: This paper provides a comprehensive survey on mmWave beamforming enabled UAV communications and networking, including the technical potential, challenges, technologies, and solutions. It also presents open issues and promising directions for future research in mmWave beamforming enabled UAV communications and networking.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2022)
Article
Computer Science, Hardware & Architecture
Jinrong Chen, Lin Liu, Rongmao Chen, Wei Peng, Xinyi Huang
Summary: This article introduces a method for preserving privacy in a context-aware recommendation system in a two-cloud model. The author adjusts the additive secret sharing scheme and designs secure comparison and division protocols to propose a secure and efficient recommendation system. Experimental results demonstrate the effectiveness of the scheme.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Computer Science, Information Systems
Aytug Onan
Summary: This paper proposes a bidirectional convolutional recurrent neural network architecture for sentiment analysis, which utilizes bidirectional LSTM and GRU layers to extract past and future contexts, and employs a group-wise enhancement mechanism to strengthen important features and weaken less important ones. Experimental results demonstrate that this architecture achieves state-of-the-art performance in sentiment analysis.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
