Splitting Large Medical Data Sets Based on Normal Distribution in Cloud Environment

Zhang, Haolan; Zhao, Yuchao; Pang, Chaoyi; He, Jing

doi:10.1109/tcc.2015.2462361

Cited by 25 publications

(10 citation statements)

References 16 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A segment of a large dataset with proper size will inherit the original dataset's characteristics. As observed in the previous work, 18 some EEG datasets follow ND and some follow PD. based on this theory, splitting and extracting a smaller size of segment from a large EEG dataset can still contain the crucial data information.…”

Section: A Multiagent‐based Segpa Model For Eeg Analysissupporting

confidence: 77%

“…Therefore, a 16‐channel EEG cap running for 10 minutes experiment will generate 60 000 × 16 data items. In order to reduce the time latency in EEG data analytical process, we adopt data segmentation/splitting methods developed in our previous work 18,19 …”

Section: A Multiagent‐based Segpa Model For Eeg Analysismentioning

confidence: 99%

“…Based on the previous segmentation method, 18 we further extend and develop the following algorithm, which combines ND and PD segmentation methods.…”

Section: A Multiagent‐based Segpa Model For Eeg Analysismentioning

confidence: 99%

See 2 more Smart Citations

Complex brain activity analysis and recognition based on multiagent methods

Zhang

Liu

Dowens

2020

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Brain activity recognition research has been a challenging area for many decades since Hans Berger described electroencephalogram (EEG) in 1929. Many previous researches cannot successfully identify EEG status due to dynamic brain activities and complicated brain correlation. This article adopts multiagent‐based methods to analyze EEG datasets, which can enhance the analytical efficiency through incorporating autonomous, self‐coordination characteristics of agents. Intelligent agents are autonomous applications that can improve system compatibility. The preliminary results indicate that the combination of time‐dependency correlation method with multiagent method is an efficient solution for brain activity recognition.

show abstract

Section: A Multiagent‐based Segpa Model For Eeg Analysissupporting

confidence: 77%

Section: A Multiagent‐based Segpa Model For Eeg Analysismentioning

confidence: 99%

See 1 more Smart Citation

Complex brain activity analysis and recognition based on multiagent methods

Zhang

Liu

Dowens

2020

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…In their research [27], Zhang, Zhao, Pang et al showed that the UV decomposition method cannot reduce large datasets when the dataset is very large.…”

Section: Sampling For Big Datamentioning

confidence: 99%

Digital Transformation: After the Big Data, What Next?

Udofia¹,

Buduka²,

Akpabio

et al. 2020

Day 1 Tue, August 11, 2020

View full text Add to dashboard Cite

Our definition of ‘The Big Data’ is the ability of having all the data set at the point of decision-making. Several documented research shows that less than 5% of all the data acquired in the oil and gas industry are actually utilised. Despite these challenges most operating assets, still keep acquiring more data and creating data-load that are never utilised or put into use. This paper aims to demonstrate the reason(s) why we have this data-load and instigate a solution path in managing this challenge for value realisation. Data is a corporate asset in any organisation but the default ‘silo’ work culture in most operating asset makes it difficult to get the relevant insight from these data. Organisation must be deliberate in creating the right data architecture from the data process domain through into the distributed control system, into the data historian, then within the data platform and the visualization realm and finally into the workflow domain. It is at the workflow domain that we get the ‘game-changer’ otherwise called value. This is the differentiating factor in delivering the ‘Big Data’ into the space of benefit realisation. This was what was achieved in a field in Niger Delta and has been shared compared to global best practice. The documented result from this case study showed that any data architecture should be framed to address asset business need, right from the data process domain function through to the data historian into the workflow level where the business objective is addressed. Data must be application-centric accounting for scalability, accessibility, security and business performance. Assets need to be clear on why they are acquiring data and not just continuous acquisition of more data with the resultant effect of data-load without answering the question; what next after data acquisition? This paper provides the answer of what next after data acquisition and serves as a quick reference tool for similar challenge elsewhere, not limited to the oil and gas industry.

show abstract

“…The advantages are not limited to revealing certain features between medical images but include providing doctors with richer and more valuable information, helping them identify, diagnose and treat abnormalities more effectively. Moreover, it can be used to build a unified standard large-scale medical image database in order to gain a deeper understanding of the imaging and pathological features of complex and rare diseases [16].…”

Section: Introductionmentioning

confidence: 99%

HS–GS: A Method for Multicenter MR Image Standardization

et al. 2020

View full text Add to dashboard Cite

The access to and sharing of medical image data is essential to accelerate the research progress of complex diseases and sudden disease outbreaks. Multicenter image data is collected from different medical institutions, and the contrast and brightness of the images are significantly different, making it difficult to use the images directly. Herein, we introduce a standardized method based on magnetic resonance imaging, referred to as Histogram specification-grid search (HS-GS), which is mainly used to eliminate differences in image contrast and brightness. A Gaussian probability density function with adjustable parameters is used to generate the cumulative distribution function, and the transfer function required for the HS mapping is constructed to obtain standardized image sets based on the controllable parameters. The image sets are used to perform the GS task of radiomics classification to find the optimal controllable parameter combination and classification results, and then obtain the optimal standardized image sets. We used HS-GS to test and verify the predictive ability of the standardized mixed image sets for glioma grading, and compared it with existing methods. The experiments indicate that the standardized image sets generated by the HS-GS algorithm retain excellent stability after mixing and also show excellent classification performance. This novel image set standardization technique has proven to be a promising solution for integration into medical expert systems.

show abstract

Splitting Large Medical Data Sets Based on Normal Distribution in Cloud Environment

Cited by 25 publications

References 16 publications

Complex brain activity analysis and recognition based on multiagent methods

Complex brain activity analysis and recognition based on multiagent methods

Digital Transformation: After the Big Data, What Next?

HS–GS: A Method for Multicenter MR Image Standardization

Contact Info

Product

Resources

About