A Survey on Data-driven Performance Tuning for Big Data Analytics Platforms

Costa, Rogério Luís de Carvalho; Moreira, José; Pintor, Paulo; Santos, Veronica dos; Lifschitz, Sérgio

doi:10.1016/j.bdr.2021.100206

Cited by 13 publications

(4 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also compared their performance under different iterations and the changes in classification error curves. In addition, we also recorded the time required for image classification to evaluate the computational efficiency of different methods [17]. Through the above comparative experiments, we can comprehensively evaluate the performance of our method in aerospace image classification and compare it with traditional methods to verify the advantages and effectiveness of our method.…”

Section: Experimental Subjectsmentioning

confidence: 99%

Research on Space Image Fast Classification Based on Big Data

Wang,

Chen

2023

SCPE

View full text Add to dashboard Cite

In order to improve the accuracy and effect of space image classification, the author proposes a space image classification method based on Big data analysis, aiming at the shortcomings of low accuracy and long time of current image classification. First, analyze the current research progress of image classification, find out the shortcomings of different classification methods, then collect aerospace images, preprocess the images, and use big data analysis technology to establish image classifiers, image classification was performed using an image classifier, and finally simulation experiments were conducted with other methods for image classification. The results indicate that: The average classification time of this method for aerospace images is 3.5 minutes, which saves 14 minutes and 29 minutes compared to traditional method 1 and traditional method 2, respectively. This indicates that this method has the shortest image classification time and improves the classification efficiency of aerospace images. This method has been proven to have high accuracy in image classification, the shortest classification time, and significant advantages compared to other image classification methods.

show abstract

Section: Experimental Subjectsmentioning

confidence: 99%

Research on Space Image Fast Classification Based on Big Data

Wang,

Chen

2023

SCPE

View full text Add to dashboard Cite

show abstract

“…In the big data processing context, data processing paradigms are classified under two categories that are batch and streaming processing [28][29] [30].…”

Section: Data Processing Paradigmsmentioning

confidence: 99%

A Comparative Perspective on Technologies of Big Data Value Chain

Aydin

2023

IEEE Access

View full text Add to dashboard Cite

Data is one of the most valuable assets in the digital era because it may conceal hidden valuable insights. Diverse organizations in diverse domains overcome the challenges of the big data value chain by employing a wide range of technologies to meet their needs and achieve a variety of goals to support their decision-making. Due to the significance of data-oriented technologies, this paper presents a model of the big data value chain based on technologies used in the acquisition, storage, and analysis of data. The following are the paper's contributions: First, a model of the big data value chain is developed to illustrate a comprehensive representation of the big data value chain that depicts the relationships between the characteristics of big data and the technologies associated with each category. Second, in contrast to previous research, this paper presents an overview of technologies for each category of the big data value chain. The third contribution of this paper is to assist researchers and developers of data-intensive systems in selecting the appropriate technology for their specific application development use cases by providing examples of applications and use cases from prominent papers in a variety of fields and by describing the capabilities and stages of the technologies being presented so that the right technology is used at the right time in the big data collection, processing, storage, and analytics tasks.

show abstract

“…The denormalization method, known as accelerating the response time of the database by adding rows or columns that are not needed in the database system, is used instead of the OLAP system, which requires additional costs [20]. The denormalization method is a widely used technique to improve the performance of the database system [21][22][23][24]. On the other hand, NoSQL database systems, which have flexible schemas for modern applications and are specially designed for certain data models, have become widespread due to their practical use, ease of development, and performance [25,26].…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach to Improve the Performance of the Database Storing Big Data with Time Information

Taşyürek

2022

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Big data is defined as data sets that are too large and/or complex to be processed by classical data processing methods. Big data analysis is essential because it enables more competent business movements, more efficient operations, and higher profits by using the data of institutions and organizations. However, large datasets are difficult to analyze because they are produced quickly, require large storage areas in computer systems, and the diversity of their data. In this study, a new approach using the denormalization method is proposed to accelerate the response time of the database in database systems where large volumes of data containing historical information are stored. Denormalization is defined as the process of adding rows or columns that are not needed to increase the reading performance of the database to the database system that has been normalized. In the proposed approach in this study, a large-volume dataset consisting of real spatial data belonging to Kayseri Metropolitan Municipality, containing temporal information and having approximately 96,000,000 row records, was used. In the proposed approach, the response time of the query is accelerated by recording the time information as numbers to increase the query performance of large volumes of data recorded in date format due to the temporal query process. The performance of the proposed method is compared with the performance of the normalization method using actual data on Microsoft SQL Server and Oracle database systems. The method proposed in the experimental evaluations shows that it works approximately eight times faster. In addition, the experimental results showed that the proposed method improves query performance more than the normalization-based method as the data size increases.

show abstract

A Survey on Data-driven Performance Tuning for Big Data Analytics Platforms

Cited by 13 publications

References 55 publications

Research on Space Image Fast Classification Based on Big Data

Research on Space Image Fast Classification Based on Big Data

A Comparative Perspective on Technologies of Big Data Value Chain

A Novel Approach to Improve the Performance of the Database Storing Big Data with Time Information

Contact Info

Product

Resources

About