Article
Computer Science, Artificial Intelligence
Hong Yang, Peng Zhang, Haishuai Wang, Chuan Zhou, Zhao Li, Li Gao, Qingfeng Tan
Summary: Dynamic networks are commonly used to describe networks that change over time. This paper addresses the challenging problem of network coarsening in dynamic networks, proposing a new Semi-NetCoarsen approach that aims to maximize the likelihood of observing information diffusion data while minimizing network regularization. The learning function is convex, and experiments on synthetic and real-world datasets validate the performance of the proposed method.
Article
Automation & Control Systems
Muhammad Yasir, Ali Haidar, Muhammad Umar Chaudhry, Muhammad Asif Habib, Aamir Hussain, Elzbieta Jasinska, Zbigniew Leonowicz, Michal Jasinski
Summary: The paper introduces a Spark-based distributed algorithm called "D-HARPP" for mining frequent co-occurring itemsets in big IoT data. Unlike other distributed algorithms, "D-HARPP" makes a single pass over the data without creating candidate itemsets, achieving better runtime performance and consuming less memory. This algorithm is suitable for edge and IoT devices with limited resources.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Business
Maria Assunta Barchiesi, Andrea Fronzetti Colladon
Summary: The study proposed a new methodological approach combining text mining, social network, and big data analytics to assess stakeholders' attitudes towards company core values in Italy. The research identified three predominant core values orientations and three latent ones in the Italian scenario. The contribution of this study lies in extending research on text mining and online big data analytics applied in complex business contexts.
JOURNAL OF BUSINESS RESEARCH
(2021)
Article
Computer Science, Information Systems
Fabio Mercorio, Mario Mezzazanica, Vincenzo Moscato, Antonio Picariello, Giancarlo Sperli
Summary: The framework proposed in this article, named DICO, identifies overlapped communities of authors from Big Scholarly Data by modeling authors' interactions. DICO has three distinctive characteristics: a novel approach for building coauthorship network, a new community detection algorithm based on Node Location Analysis, and provided built-in queries.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Construction & Building Technology
Hui Bi, Zhirui Ye
Summary: The study investigated the travel behavior of ridesourcing users in Chengdu using the LDA model, finding that the mode of life for people in Chengdu is represented by the time frame of Nine to Ten. Ridesourcing is not yet widely used as a commuter tool, and many people work overtime in the evenings, particularly on Saturdays.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Information Systems
Peng-Yu Huang, Wan-Shu Cheng, Ju-Chin Chen, Wen-Yu Chung, Young-Lin Chen, Kawuu W. Lin
Summary: In recent years, knowledge discovery in databases has provided powerful capabilities for discovering meaningful information, leading to a focus on distributed data mining as an important research area. The proposed algorithms based on FP growth offer fast and scalable service in distributed computing environments, showing superior cost-effectiveness and performance.
Article
Psychology, Multidisciplinary
Wei Xu, Finbarr Murphy, Xian Xu, Wenpeng Xing
Summary: This study analyzed Chinese media news from 2009 to 2018 and found that government actions have a significant impact on public attention to cyber risk sources, which in turn have an inverted-U shape impact on societal aversion to these risks. Additionally, news sentiment was strongly correlated with cyber risk perception, providing important insights for regulators and insurers.
COMPUTERS IN HUMAN BEHAVIOR
(2021)
Article
Computer Science, Artificial Intelligence
Angel M. Garcia-Vico, Cristobal Carmona, Pedro Gonzalez, Maria J. del Jesus
Summary: A new approach for extracting descriptive emerging patterns in massive data streams from different sources is proposed in this paper using Apache Kafka and Apache Spark Streaming. The proposed algorithm demonstrates an interpretability improvement of 25% in the extraction of high-interest knowledge and is up to five times faster than another proposal on the processing of the same amount of data, processing up to 750,000 instances in approximately four seconds in experimental studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Liping Yang, Yu Yang, Gervas Batister Mgaya, Bo Zhang, Long Chen, Hongbo Liu
Summary: Mining the relationship structures among investors is crucial for economic development and financial risk prevention in the era of big data. This article introduces fast networking approaches and novel algorithms to explore underlying structures in investment big data, showing higher clustering accuracy and efficiency compared to existing methods. Our method is particularly effective for mining investment structures.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Information Systems
Majid Azadi, Ali Emrouznejad, Fahimeh Ramezani, Farookh Khadeer Hussain
Summary: This article proposes a network data envelopment analysis method to measure the efficiency of cloud service providers, addressing the challenges in performance measurement and provider selection. The results demonstrate the superiority of the proposed method in evaluating and ranking cloud service providers compared to traditional methods.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Ya-zhi Yang, Yong Zhong, Marcin Wozniak
Summary: The algorithm proposed in this study is based on individual learning differences and utilizes big data for personalized learning service recommendations, resulting in improved recommendation accuracy and coverage rate, which is of great significance in actual learning service recommendations.
MOBILE NETWORKS & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Jimmy Ming-Tai Wu, Huiying Zhou, Jerry Chun-Wei Lin, Gautam Srivastava, Mohamed Baza
Summary: The application of RDD in cloud computing provides a good environment for big data analysis. Additionally, combining ML algorithms in edge computing with the SFUP-SP algorithm can further enhance local computing capabilities and accelerate data analysis and user decision-making.
JOURNAL OF GRID COMPUTING
(2023)
Article
Management
Hua Song, Mengyin Li, Kangkang Yu
Summary: This study examines the role of financial service providers in assessing the supply chain credit of small and medium-sized enterprises and how they help SMEs obtain supply chain finance through an established digital platform using big data analytics. The findings suggest that digital platforms sponsored by FSPs have a discriminative effect based on implicit BDA on identifying the quality and potential risks of borrowers, and that tailored information utilised by FSPs has a supportive effect based on explicit BDA in helping SMEs obtain financing.
INTERNATIONAL JOURNAL OF OPERATIONS & PRODUCTION MANAGEMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Ashton Conrad Kappelman, Ashesh Kumar Sinha
Summary: This study explores a dynamic food supply chain using Big Data mining techniques to analyze the impact of decisions on product quality and optimize supplier selection and process parameters. Stochastic optimization methods are employed to maximize profit and reduce rejected products. Experiments demonstrate the superiority of this integrated approach over traditional techniques as problem complexity increases.
COMPUTERS & OPERATIONS RESEARCH
(2021)
Article
Economics
Jennifer L. Castle, Jurgen A. Doornik, David F. Hendry
Summary: This passage discusses methods for handling fat big data, including using principal components analysis and equilibrium correction models to identify cointegrating relations, and using saturation estimation to handle non-stationary fat data. When dealing with a large number of potentially spurious connections, it is important to seek substantive relationships, and big data can be useful if they help ensure that the data generation process is nested in the model.
INTERNATIONAL JOURNAL OF FORECASTING
(2021)