Article
Computer Science, Information Systems
Tao Shang, Feng Zhang, Xingyue Chen, Jianwei Liu, Xinxi Lu
Summary: Identity-based remote data auditing schemes can verify data integrity and provide simple identity authentication and management for multiple users. However, prior research in this area lacks support for dynamic operations. This paper proposes a new scheme that supports dynamic data operations using Merkle hash tree structure to improve efficiency and integrity assurance.
IEEE TRANSACTIONS ON BIG DATA
(2021)
Article
Ecology
R. Hernandez-Clemente, A. Hornero, V. Gonzalez-Dugo, M. Berdugo, J. L. Quero, J. C. Jimenez, F. T. Maestre
Summary: Models derived from satellite image data are needed to monitor the status of terrestrial ecosystems at a large scale. However, there is a lack of remote sensing-based approach for quantifying soil multifunctionality globally. This study aimed to develop a soil multifunctionality model using field data and remote sensing indicators (RSI) from a Landsat dataset. The results showed that a multi-variable RSI model improved the accuracy of quantifying soil multifunctionality. The correlation between RSI and soil variables varied across different RSI.
REMOTE SENSING IN ECOLOGY AND CONSERVATION
(2023)
Article
Oceanography
Philip R. Hollyman, Marta Soeffker, Jim Roberts, Oliver T. Hogg, Vladimir V. Laptikhovsky, Jose P. Queiros, Chris Darby, Mark Belchier, Martin A. Collins
Summary: The South Sandwich Islands is a biologically rich area with clear differences in fish and invertebrate communities across its latitudinal range, driven by environmental factors such as seawater temperature. Climate change may alter these communities with poleward shifts in species ranges.
DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY
(2022)
Article
Economics
Caio Pieroni, Mariana Giannotti, Bianca B. Alves, Renato Arbex
Summary: This study analyzed the temporal and spatial patterns of urban transit movements in precarious settlement areas in Sao Paulo, Brazil using smart card data mining. The results revealed differences in travel behavior between low-income residents from precarious settlements and middle/high-income-class residents, with a focus on identifying low-paid employment travel patterns. The empirical evidence highlights smart card data's potential in uncovering low-paid employment spatial and temporal patterns.
JOURNAL OF TRANSPORT GEOGRAPHY
(2021)
Article
Environmental Sciences
Jionghua Wang, Haowen Luo, Wenyu Li, Bo Huang
Summary: This study develops a method of function label classification using integrated features derived from remote sensing and crowdsensing data, and verified on a dataset from Shenzhen, China. It was found that basic building attributes and POIs contributed most to the classification process, while crowdsensing data becomes increasingly important in more complicated classification tasks.
Article
Computer Science, Artificial Intelligence
Chenxia Jin, Fachao Li, Shijie Ma, Ying Wang
Summary: Obtaining comprehensible classification rules is crucial in real applications, and decision-tree methods are commonly used. However, their performance is unsatisfactory and lacks theoretical support in big data scenarios. This study introduces a sampling-based classification rule mining (SCRM) method to improve the adaptability and generalization ability of classification rules in big data environments. The SCRM was evaluated using seven UCI datasets and showed good classification ability.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Business
Liane W. Y. Lee, Piyush Sharma, Bradley R. Barnes
Summary: This study used big data to examine perceptions of guanxi outside China, finding that guanxi is heavily influenced by geopolitical and public health issues, with significant variations in attitudes across different countries.
JOURNAL OF BUSINESS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Amin Shokrzade, Mohsen Ramezani, Fardin Akhlaghian Tab, Mahmud Abdulla Mohammad
Summary: A new fast and robust kNN finding framework is introduced in this paper to deal with big datasets. The training data samples are grouped based on mini-classifiers' outputs, and a tree structure is used for partition indexing, finding the corresponding group of relevant data samples to an input. Experimental results show better performance in most cases and comparable performance on other cases of big data problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Claudio Agostino Ardagna, Valerio Bellandi, Michele Bezzi, Paolo Ceravolo, Ernesto Damiani, Cedric Hebert
Summary: The paper proposes an approach based on Model-Driven Engineering technology to support automation of Big Data Analytics. By defining an abstract Big Data platform and smart engines to meet customer requirements, the Big Data pipeline is able to execute analytics on a specific platform. This method is experimentally evaluated in the real-world scenario of SAP's threat detection system, showing promising results.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Review
Engineering, Civil
Kai Lu, Jiangtao Liu, Xuesong Zhou, Baoming Han
Summary: The operations, management, and planning of urban transit systems have evolved significantly with the use of various transit data collection technologies, which include automated fare collection, GPS, smartphones, and face identification. Detailed sensor data in urban transit systems are crucial for observing passenger travel behavior, rescheduling operation plans, and adjusting policy decisions. This review classifies data collecting technologies into traditional and advanced groups, and identifies passenger behavior, operation optimization, and policy applications as key branches for transit data applications.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Uma Narayanan, Paul Varghese, Shelbi Joseph
Summary: This paper presents a solution for addressing the challenges of big data security in cloud computing. It introduces a novel system architecture called SADS-Cloud, which includes three processes: big data outsourcing, big data sharing, and big data management. The solution utilizes various encryption algorithms and data organization methods to ensure the security of big data in the cloud environment.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Chemistry, Multidisciplinary
Soheil Rezaee, Abolghasem Sadeghi-Niaraki, Maryam Shakeri, Soo-Mi Choi
Summary: This research aims to design a personalized AR based on a tourist system that retrieves big data according to users' demographic contexts. By predicting the type of tourist attraction and extracting correct data for users, using decision-making methods, the research showed better performance of decision tree compared to SVM in predicting tourist attraction types.
APPLIED SCIENCES-BASEL
(2021)
Article
Construction & Building Technology
Zaobao Liu, Long Li, Xingli Fang, Wenbiao Qi, Jimei Shen, Hongyuan Zhou, Yulong Zhang
Summary: This article developed a time-related intelligent model for tunnel lithology prediction using TBM construction big data, with the global-attention-mechanism-based LSTM network outperforming conventional LSTM network and other models in accuracy and F1 scores. The results could help TBM drivers adjust operational parameters in real time for high-efficient tunnel construction.
AUTOMATION IN CONSTRUCTION
(2021)
Review
Biology
Paula Arribas, Carmelo Andujar, Kristine Bohmann, Jeremy R. DeWaard, Evan P. Economo, Vasco Elbrecht, Stefan Geisen, Marta Goberna, Henrik Krehenwinkel, Vojtech Novotny, Lucie Zinger, Thomas J. Creedy, Emmanouil Meramveliotakis, Victor Noguerales, Isaac Overcast, Helene Morlon, Anna Papadopoulou, Alfried P. Vogler, Brent C. Emerson
Summary: Metazoan metabarcoding is an important strategy for biodiversity inventorying, but differences in workflows might compromise data integration. To address this issue, a modular framework for harmonized data generation was proposed, focusing on terrestrial arthropods. Key points for harmonization were identified and guidelines were provided to reduce methodological options and promote best practice.
Article
Computer Science, Information Systems
Qi Li, Mingyu Cheng, Junfeng Wang, Bowen Sun
Summary: Phishing emails are becoming more complex, making existing detection methods inadequate. This article introduces an LSTM-based phishing detection method that achieves 95% accuracy through sample expansion and testing stages.
IEEE TRANSACTIONS ON BIG DATA
(2022)
