Article
Geochemistry & Geophysics
Jeff Dozier
Summary: Digital elevation models (DEMs) are widely used for calculating illumination geometry and correcting remotely sensed data for topographic effects. However, in mountainous areas, the shading caused by nearby terrain needs to be taken into account.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Zebin Wu, Jin Sun, Yi Zhang, Zhihui Wei, Jocelyn Chanussot
Summary: This article surveys the state-of-the-art methods for processing remotely sensed big data and thoroughly investigates existing parallel implementations. The study shows that cloud computing is the most promising solution for efficient and scalable processing of remotely sensed big data, with scheduling strategies being crucial for fully exploiting parallelism.
PROCEEDINGS OF THE IEEE
(2021)
Article
Computer Science, Hardware & Architecture
Yang Song, Helin Jin, Hongzhi Wang, You Liu
Summary: This study aimed to optimize the computation of complex expressions through graph modeling and simplification algorithms. Experimental results demonstrate that the proposed method effectively reduces computation costs.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Manar A. Elmeiligy, Ali I. El Desouky, Sally M. Elghamrawy
Summary: With the increasing daily production of data, indexing, storing, and retrieving huge amounts of data have become common problems. This paper proposes a new indexing structure called ParISSS for multi-dimensional big data, which outperforms other indexing systems.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Automation & Control Systems
Ashish Kumar Tripathi, Kapil Sharma, Manju Bala, Akshi Kumar, Varun G. Menon, Ali Kashif Bashir
Summary: This study introduces a novel clustering method based on metaheuristic and MapReduce to address big data problems. By leveraging the searching potential of military dog squad and utilizing the MapReduce architecture to handle large datasets, the optimization effectiveness is improved. Experimental results demonstrate that the new method outperforms other algorithms in terms of clustering accuracy and computation times.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Seyed Morteza Nabavinejad, Maziar Goudarzi
Summary: Reserved instances offered by cloud providers allow users to reserve resources and computing capacity for a specific period of time at a significantly lower hourly rate. However, estimating the resource demand of big data processing jobs is challenging due to various factors, which can be optimized using the Reserved Instances Stochastic Allocation (RISA) approach to maximize profit and increase net profit by up to 10x compared to previous approaches.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2021)
Article
Computer Science, Information Systems
Hui Dou, Kang Wang, Yiwen Zhang, Pengfei Chen
Summary: To achieve better performance, big data processing frameworks usually have a large number of performance-critical configuration parameters. Manually configuring these parameters is time-consuming, so there is a need for automatic tuning. This paper proposes a black-box approach, ATConf, to automatically tune the configuration parameters for BDPFs. Experimental results show that ATConf can reduce the execution time by 46.52% compared to the default configuration.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Environmental Sciences
Weikang Zhang, Haihang You, Chao Wang, Hong Zhang, Yixian Tang
Summary: Interferometric synthetic aperture radar (InSAR) has rapidly developed and is considered an important method for monitoring surface deformation, benefiting from growing data quantities and improving data quality. Handling SAR big data poses challenges for algorithms and pipeline, particularly in large-scale SAR data processing. This paper designs parallel time-series InSAR processing models based on multi-thread technology to achieve high efficiency. The models focus on parallelizing critical algorithms and have shown a significant performance improvement. The paper also introduces a parallel optimization tool, STAR, which addresses the problem of low CPU utilization in the InSAR processing pipeline.
Article
Computer Science, Information Systems
Gabriel M. Alves, Paulo E. Cruvinel
Summary: In the field of high-resolution tomography, the increasing volume of tomographic projections and data has demanded new computational approaches for their reconstruction and processing. This paper presents a new approach that optimizes the set of projections, parallelizes the reconstruction algorithm, and processes the data in a distributed manner. The developed method, implemented in a big data environment, proved to be useful for high-resolution tomography analyses of agricultural samples, contributing to the sustainability and competitiveness of the production process.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yicheng Yang, Jae Kwang Kim, In Ho Cho
Summary: The fractional hot-deck imputation (FHDI) is a general imputation method for handling multivariate missing data. However, it lacks efficiency when dealing with big incomplete data. To overcome this limitation, a parallel version called P-FHDI is developed, which shows favorable speedup for large incomplete datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Rasim M. Alguliyev, Ramiz M. Aliguliyev, Lyudmila Sukhostat
Summary: This article introduces a new parallel batch clustering algorithm based on the k-means algorithm, which reduces computation complexity by splitting the dataset into multiple partitions and proposes a method to determine the optimal batch size. Experimental results show the practical applicability of this method for handling Big Data.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Seungwoo Seo, Jong-Moon Chung
Summary: Security and processing speed are key challenges in big data systems, necessitating coordinated design of security and performance techniques to counter various attacks. The TSAF scheme provides enhanced processing performance while protecting big data systems from malicious node attacks, ensuring fulfillment of processing requirements within 80% of the task completion time.
Article
Engineering, Civil
Juan C. Perafan-Villota, Oscar H. Mondragon, Walter M. Mayor-Toro
Summary: The study focuses on utilizing computer vision and parallel distributed systems for fast processing of traffic video data to automatically determine traffic density, identify dangerous driving behaviors, and detect accidents with high accuracy. It involves the use of Convolutional Neural Network (CNN) and Kalman filters for vehicle detection and tracking, as well as a low-cost distributed infrastructure based on Hadoop and Spark frameworks for efficient data processing.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Jinxing Lin, Mingjie Lu, Yongjiang Jiang, Rong Fu, Xianyong Peng, Edmond Q. Q. Wu
Summary: This paper discusses the optimization of wide working conditions operational performance of steam turbine units in coal-fired thermal power plants. A method based on big data association rule mining is proposed to establish relationships between key operating parameters and heat consumption rate, and determine optimal target values. A new association rule mining algorithm is proposed to handle sparse data, and a parallel implementation on Apache Spark platform is provided for efficient processing of large-scale data. A case study demonstrates that the proposed optimization method can significantly reduce heat consumption rate and improve economic benefits.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Ivano Notarnicola, Ying Sun, Gesualdo Scutari, Giuseppe Notarstefano
Summary: This study focuses on distributed big-data nonconvex optimization in multiagent networks. A novel distributed solution method is proposed, where agents update one block of the entire decision vector in an uncoordinated fashion to address nonconvexity and reduce communication overhead in large-scale problems. Numerical results demonstrate the effectiveness of the algorithm and highlight the impact of block dimension on communication overhead and convergence speed.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2021)