Article
Construction & Building Technology
Yipeng Liu, Junwu Wang, Shanrong Tang, Jiaji Zhang, Jinyingjun Wan
Summary: Construction accident investigation reports are difficult to analyze due to the voluminous Chinese text. To overcome this problem, a novel approach combining text mining techniques and LDA models is proposed to identify the key factors leading to safety accidents in the Chinese construction industry.
Article
Computer Science, Hardware & Architecture
Jialin Ma, Zhaojun Wang, Hai Guo, Qian Xie, Tao Wang, Bolun Chen
Summary: Syndrome differentiation-based treatment is a key characteristic of Traditional Chinese Medicine (TCM). This paper proposes a novel Symptom-Syndrome Topic Model (SSTM) that combines TCM theory with data mining algorithms to improve the effectiveness of syndrome differentiation.
COMPUTER SYSTEMS SCIENCE AND ENGINEERING
(2022)
Article
Business
Junhan Kim, Youngjung Geum
Summary: This study proposes a systematic and concrete framework to develop data-driven technology roadmaps, consisting of three phases: layer mapping, contents mapping, and opportunity finding. This contributes to the field by providing a systematic method for data-driven roadmapping and offering data-driven evidence for more reasonable decision-making by experts.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Computer Science, Artificial Intelligence
Weidong Zhao, Lin Zhu, Ming Wang, Xiliang Zhang, Jinming Zhang
Summary: This paper proposes a method named WTL-CNN that combines word2vec, a topic-based TF-IDF algorithm, and an improved convolutional neural network to address the issue of word2vec model ignoring the importance of a single word. The WTL-CNN model has been evaluated and compared with seven contrast models, showing high accuracy in news text classification.
CONNECTION SCIENCE
(2022)
Article
Agronomy
Jiyoung Ha, Seunghyun Lee, Sangtae Kim
Summary: This study analyzed the influence relationship between news articles on onions and the consumer selling price of onions in Korea. The findings showed that hypermarket onion sales, onion supply and demand stabilization measures, and inflation had a significant impact on the selling price of onions.
Article
Computer Science, Information Systems
Jiashu Zhao, Jimmy Xiangji Huang, Hongbo Deng, Yi Chang, Long Xia
Summary: In this article, a Latent Dirichlet Allocation (LDA) based topic-graph probabilistic personalization model for Web search is proposed. The model represents a user graph using a latent topic graph and estimates the probabilities of user interest and non-interest in topics simultaneously. For a user's query, webpages relevant to the interested topics are promoted, while webpages relevant to the non-interesting topics are penalized. The effectiveness of the proposed model is demonstrated through experiments on a real user search log collection.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Dongbin He, Yanzhao Ren, Abdul Mateen Khattak, Xinliang Liu, Sha Tao, Wanlin Gao
Summary: This study introduced a novel two-phase neural embedding framework with redundancy-aware sorting process to optimize topic labeling, improve the effectiveness of the labeling system, and discover more meaningful topic labels.
Article
Computer Science, Artificial Intelligence
Dejian Yu, Bo Xiang
Summary: Artificial Intelligence (AI) has significantly impacted various aspects of social life. This study analyzed 177,204 documents published from 1990 to 2021 in AI research and used the LDA model to extract 40 topics from the abstracts. The study identified 7 subfields in the AI field and aggregated the results to understand research characteristics from different perspectives. These findings are valuable for researchers and institutions in selecting research directions and for newcomers to comprehend the dynamics of the field.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Analytical
Beakcheol Jang, Myeonghwi Kim, Inhwan Kim, Jong Wook Kim
Summary: Diseases are spreading rapidly due to globalization, and the internet data can be leveraged to provide accurate and timely disease information. This study develops an infectious disease surveillance system using deep learning algorithm and various visualization techniques to present disease data.
Article
Computer Science, Cybernetics
Weihong Han, Zhihong Tian, Chunsheng Zhu, Zizhong Huang, Yan Jia, Mohsen Guizani
Summary: This article proposes a word-distributed sensitive topic representation model (WDS-LDA) based on hybrid human-AI. By introducing human cognitive ability and cognitive models, the accuracy of the topic model is improved. Tests show that the WDS-LDA algorithm enhances the importance of representative words and the distinction among different topic words, effectively improving the precision of subsequent algorithms.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Yeo Jin Jung, Youngmin Kim
Summary: In recent decades, there has been a significant growth in incorporating sustainability into marketing. This study examines the trends in sustainability and marketing by analyzing 2147 articles published between 2010 and 2020. The research shows a shift towards a focus on environmental and industrial technology in the field of sustainability and marketing.
Article
Psychology, Multidisciplinary
Joonbeom Park, Woojoo Choi, Sang-Uk Jung
Summary: This study utilized Twitter data to analyze the development of ESG-related topics and the public's sentiment toward ESG. Through topic modeling and sentiment analysis, the hidden structure of ESG and the public's reactions were revealed.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Green & Sustainable Science & Technology
Young-joo Ahn, Katie Bokyun Kim, Jin-young Kim
Summary: This study aims to extract topics from news articles on DMZ tourism published between 1990 and 2020 by using LDA. The results found that news articles on DMZ tourism can provide considerable information on political, social, and environmental issues. The study identifies the trends and characteristics of topics over the past 30 years and highlights important issues related to DMZ tourism that can promote tourism products and content.
Article
Environmental Sciences
D. Tomojiri, K. Takaya, T. Ise
Summary: The study used the LDA model to infer the research topics about anthropogenic marine debris (AMD) and provide an overview of the research area. The results showed that the AMD research topics were mostly applied topics in interdisciplinary or transdisciplinary research areas. Furthermore, topics related to plastic pollution exhibited an upward trend, while those dealing with spatiotemporal dynamics and distribution patterns of marine debris showed a downward trend.
MARINE POLLUTION BULLETIN
(2022)
Article
Business
Munan Li, Wenshu Wang, Keyu Zhou
Summary: With the spillover of knowledge in the field of AI, exploring the technology emergence (TE) and technology opportunities (TO) related to AI has become increasingly important. The proposed coupling analysis and computing framework provide new insights for exploring specific topics in AI, enriching methodologies for technical opportunity analysis.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Computer Science, Artificial Intelligence
Jianbing Xiahou, Fan Lin, Qihua Huang, Wenhua Zeng
NEURAL COMPUTING & APPLICATIONS
(2018)
Article
Computer Science, Artificial Intelligence
Xiuze Zhou, Weibo Shu, Fan Lin, Beizhan Wang
APPLIED SOFT COMPUTING
(2018)
Article
Mathematics, Interdisciplinary Applications
Chenxi Huang, Yisha Lan, Sirui Chen, Qing Liu, Xin Luo, Gaowei Xu, Wen Zhou, Fan Lin, Yonghong Peng, Eddie Y. K. Ng, Yongqiang Cheng, Nianyin Zeng, Guokai Zhang, Wenliang Che
Article
Computer Science, Information Systems
Kangkang Li, Xiuze Zhou, Fan Lin, Wenhua Zeng, Beizhan Wang, Gil Alterovitz
INFORMATION SCIENCES
(2019)
Article
Computer Science, Artificial Intelligence
Yuanguo Lin, Shibo Feng, Fan Lin, Wenhua Zeng, Yong Liu, Pengcheng Wu
Summary: This paper introduces a novel course recommendation framework named DARL, which aims to enhance the adaptivity of the recommendation model by automatically capturing users' dynamic interests and adaptively updating the attention weight of courses to improve recommendation accuracy. Empirical experiments on two real-world MOOCs datasets show that DARL significantly outperforms state-of-the-art course recommendation methods in major evaluation metrics.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Qian Hu, Fan Lin, Beizhan Wang, Chunyan Li
Summary: In recent years, there has been a growing interest in applying machine learning to existing graphs and networks. The paper proposes a novel method, MBRep, for higher-order representation learning based on triangle motif embedding in a network, showing effectiveness in link prediction and adaptability in real-world datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yuanguo Lin, Fan Lin, Wenhua Zeng, Jianbing Xiahou, Li Li, Pengcheng Wu, Yong Liu, Chunyan Miao
Summary: In this paper, a novel personalized course recommendation model named HELAR is proposed, which addresses the trade-off between exploration and exploitation in existing methods through a profile constructor with autonomous learning ability and a novel policy gradient method. Extensive experimental results demonstrate the superiority of the HELAR model over other methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yuanguo Lin, Fan Lin, Lvqing Yang, Wenhua Zeng, Yong Liu, Pengcheng Wu
Summary: This paper proposes a context-aware reinforcement learning method, named HRRL, for efficient course recommendation by utilizing recurrent reinforcement learning and attention mechanism. Experimental results demonstrate the superiority of this method over existing baselines.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Li Li, Fan Lin, Jianbing Xiahou, Yuanguo Lin, Pengcheng Wu, Yong Liu
Summary: Recommender systems have achieved great success in various fields but face new challenges due to privacy concerns. Federated learning, as a privacy-preserving machine learning technique, provides potential solutions. However, existing federated recommendation methods have limitations in considering organizational participants and modeling preference evolution. To address these limitations, we propose the FedSeqRec framework and demonstrate its superiority through experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yuanguo Lin, Shibo Feng, Fan Lin, Jianbing Xiahou, Wenhua Zeng
Summary: Course recommendation technology is crucial in online learning, but the challenges of characterizing learners' preferences and learning effective recommendation strategies remain. To address these issues, we propose a multi-scale Reinforced Profile for Personalized Recommendation (RPPR) framework, which combines deep reinforcement learning and attention mechanism to construct learners' profiles and adaptively adjust recommendation strategies.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yuanguo Lin, Yong Liu, Fan Lin, Lixin Zou, Pengcheng Wu, Wenhua Zeng, Huanhuan Chen, Chunyan Miao
Summary: Recommender systems have become widely used in finding useful information in different real-life scenarios. Reinforcement Learning has emerged as a popular research topic in recommender systems due to its interactive nature and autonomous learning ability. Empirical results demonstrate that RL-based recommendation methods often outperform supervised learning methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Biochemical Research Methods
Chenxi Huang, Yisha Lan, Gaowei Xu, Xiaojun Zhai, Jipeng Wu, Fan Lin, Nianyin Zeng, Qingqi Hong, E. Y. K. Ng, Yonghong Peng, Fei Chen, Guokai Zhang
Summary: The study proposed a deep residual segmentation network based on attention mechanism for segmenting lumen contour in IVOCT images. By utilizing data augmentation, residual network, attention mechanism, and pyramid feature extraction structure, the proposed network achieves better learning of contour details with strong robustness and accuracy for IVOCT lumen contour segmentation.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Computer Science, Information Systems
Qian Hu, Fan Lin, Beizhan Wang, Chunyan Li
Article
Mathematical & Computational Biology
Liyan Chen, Beizhan Wang, Zhihong Zhang, Fan Lin, Yihan Ma
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2017)
Article
Computer Science, Information Systems
Lu Liu, Fan Lin, Beizhan Wang, Kangkang Li, Meng Xiao, Jianbing Xiahou, Pengcheng Wu