An Approach for Chart Description Generation in Cyber–Physical–Social System

Chen, Liang; Zhao, Kangting

doi:10.3390/sym13091552

Cited by 10 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Smart city implementations are also referred to in the highest CPSS paper citations [15,18,92,93]. Other CPSS implementations explored within the recent novel literature include smart wearable devices, data center cooling systems, industrial chart data processing, and electricity savings [22,[94][95][96]. The gaming industry is additionally iden-tified as a CPSS, with research in this space aligning with opportunities to crowd-source task allocation and optimization problems relying on the interaction of people with digital systems [97].…”

Section: Role Of Cpss With Recent Smart Applicationsmentioning

confidence: 99%

A Holistic Review of Cyber–Physical–Social Systems: New Directions and Opportunities

Sobb,

Turnbull,

Moustafa

2023

Sensors

View full text Add to dashboard Cite

A Cyber–Physical–Social System (CPSS) is an evolving subset of Cyber–Physical Systems (CPS), which involve the interlinking of the cyber, physical, and social domains within a system-of-systems mindset. CPSS is in a growing state, which combines secure digital technologies with physical systems (e.g., sensors and actuators) and incorporates social aspects (e.g., human interactions and behaviors, and societal norms) to facilitate automated and secure services to end-users and organisations. This paper reviews the field of CPSS, especially in the scope of complexity theory and cyber security to determine its impact on CPS and social media’s influence activities. The significance of CPSS lies in its potential to provide solutions to complex societal problems that are difficult to address through traditional approaches. With the integration of physical, social, and cyber components, CPSS can realize the full potential of IoT, big data analytics, and machine learning, leading to increased efficiency, improved sustainability and better decision making. CPSS presents exciting opportunities for innovation and advancement in multiple domains, improving the quality of life for people around the world. Research challenges to CPSS include the integration of hard and soft system components within all three domains, in addition to sociological metrics, data security, processing optimization and ethical implications. The findings of this paper note key research trends in the fields of CPSS, and recent novel contributions, followed by identified research gaps and future work.

show abstract

Section: Role Of Cpss With Recent Smart Applicationsmentioning

confidence: 99%

A Holistic Review of Cyber–Physical–Social Systems: New Directions and Opportunities

Sobb,

Turnbull,

Moustafa

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The most processed chart types are bar, line, and pie chart. Scatter plot is researched in [ 20 , 21 ], and area and radar chart in ChartSense [ 18 ]. The developed algorithms often rely on low-level knowledge, and the diversity of chart types creates further challenges.…”

Section: Related Workmentioning

confidence: 99%

Data Extraction of Circular-Shaped and Grid-like Chart Images

Bajić

Job

2022

J. Imaging

View full text Add to dashboard Cite

Chart data extraction is a crucial research field in recovering information from chart images. With the recent rise in image processing and computer vision algorithms, researchers presented various approaches to tackle this problem. Nevertheless, most of them use different datasets, often not publicly available to the research community. Therefore, the main focus of this research was to create a chart data extraction algorithm for circular-shaped and grid-like chart types, which will accelerate research in this field and allow uniform result comparison. A large-scale dataset is provided containing 120,000 chart images organized into 20 categories, with corresponding ground truth for each image. Through the undertaken extensive research and to the best of our knowledge, no other author reports the chart data extraction of the sunburst diagrams, heatmaps, and waffle charts. In this research, a new, fully automatic low-level algorithm is also presented that uses a raster image as input and generates an object-oriented structure of the chart of that image. The main novelty of the proposed approach is in chart processing on binary images instead of commonly used pixel counting techniques. The experiments were performed with a synthetic dataset and with real-world chart images. The obtained results demonstrate two things: First, a low-level bottom-up approach can be shared among different chart types. Second, the proposed algorithm achieves superior results on a synthetic dataset. The achieved average data extraction accuracy on the synthetic dataset can be considered state-of-the-art within multiple error rate groups.

show abstract

ACCirO: A System for Analyzing and Digitizing Images of Charts with Circular Objects

Daggubati,

Sreevalsan-Nair

2022

Computational Science – ICCS 2022

View full text Add to dashboard Cite

An Approach for Chart Description Generation in Cyber–Physical–Social System

Cited by 10 publications

References 41 publications

A Holistic Review of Cyber–Physical–Social Systems: New Directions and Opportunities

A Holistic Review of Cyber–Physical–Social Systems: New Directions and Opportunities

Data Extraction of Circular-Shaped and Grid-like Chart Images

ACCirO: A System for Analyzing and Digitizing Images of Charts with Circular Objects

Contact Info

Product

Resources

About