scholarly journals Meta-Parameter Selection for Embedding Generation of Latency Spaces in Auto Encoder Analytics †

2021 ◽  
Vol 5 (1) ◽  
pp. 30
Author(s):  
Maria Walch ◽  
Peter Schichtel ◽  
Dirk Lehmann ◽  
Amala Paulson
Keyword(s):  
Data Analysis ◽  
Visual Analysis ◽  
Parameter Selection ◽  
Data Sets ◽  
Parameter Setting ◽  
Selection For

Picking an appropriate parameter setting (meta-parameters) for visualization and embedding techniques is a tedious task. However, especially when studying the latent representation generated by an autoencoder for unsupervised data analysis, it is also an indispensable one. Here we present a procedure using a cross-correlative take on the meta-parameters. This ansatz allows us to deduce meaningful meta-parameter limits using OPTICS, DBSCAN, UMAP, t-SNE, and k-MEANS. We can perform first steps of a meaningful visual analysis in the unsupervised case using a vanilla autoencoder on the MNIST and DeepVALVE data sets.

scholarly journals Visual Data Analysis Technology Based on Data Center

2022 ◽  
Vol 2146 (1) ◽  
pp. 012016
Author(s):  
Tianjun Wang ◽  
Cengceng Wang ◽  
Jiangtao Guo ◽  
dildar alim
Keyword(s):  
Data Analysis ◽  
Visual Analysis ◽  
Recognition Rate ◽  
Development Trend ◽  
Data Sets ◽  
Visual Data ◽  
Visualization Technology ◽  
Processing And Storage ◽  
And Storage ◽  
Crucial Part

Abstract Today, people are in an information explosion society, and visualization technology(VT) is an inevitable product of the development of the information society. With the emergence of multimedia products such as computers, networks, and communications, humans are paying more and more attention to data processing. Many countries in the world have already begun research in this area and have achieved remarkable results. VT is a core part of data analysis, also known as information processing and storage technology. It has a very extensive and important application in the field of data management. However, because the key information hidden in the data is often immersed in the massive data, it is necessary to filter the data information efficiently, and the visualization data analysis technology is a crucial part. This article adopts the experimental analysis method, which aims to provide a new method to solve the problems of traditional technology and the challenges that may arise in the future by further understanding the existing visual data analysis technology and development trend. According to the research results, the recognition rate of the optimized color visualization features under different classifiers is higher than that of the original emotional features. It can be seen that visual analysis technology is not limited to data sets with physical meaning, but can also be applied to abstract feature sets such as emotional features.

Research on Parameter Distribution of Interval Deleted Data with Turnbull Estimation

2012 ◽  
Vol 605-607 ◽  
pp. 780-783
Author(s):  
Jin Huang Wu ◽  
Jun Sheng Wang ◽  
Hai Bo Liu ◽  
Jun Wei Lei
Keyword(s):  
Data Analysis ◽  
Data Distribution ◽  
Reliability Assessment ◽  
Selection Method ◽  
Parameter Selection ◽  
Selection Problem ◽  
Parameter Distribution ◽  
Standard Curve ◽  
Packet Data ◽  
Selection For

A kind of selection method of parameter distribution is proposed to solve the distributive parameter selection problem of packet data by using common Turnbull estimated curve as a standard curve. This method can meet the requirements of data distributive selection for data analysis such as reliability assessment, and it can guide the engineering and technical researchers to choose a reasonable fitting of the data distribution, and to improve the accuracy and efficiency of reliability assessment

DTI data analysis: application of fiber tracking to group averaged data sets

2010 ◽  
Vol 41 (01) ◽  
Author(s):  
HP Müller ◽  
A Unrath ◽  
A Riecker ◽  
AC Ludolph ◽  
J Kassubek
Keyword(s):  
Data Analysis ◽  
Fiber Tracking ◽  
Data Sets ◽  
Analysis Application

Justifying the data analytical choice in single case research in relation to the expected data pattern

2019 ◽  
Author(s):  
Rumen Manolov
Keyword(s):  
Data Analysis ◽  
Visual Analysis ◽  
Multilevel Models ◽  
Single Case ◽  
Analytical Techniques ◽  
Real Data ◽  
Small Scale ◽  
Data User ◽  
Single Case Research ◽  
User Friendly

The lack of consensus regarding the most appropriate analytical techniques for single-case experimental designs data requires justifying the choice of any specific analytical option. The current text mentions some of the arguments, provided by methodologists and statisticians, in favor of several analytical techniques. Additionally, a small-scale literature review is performed in order to explore if and how applied researchers justify the analytical choices that they make. The review suggests that certain practices are not sufficiently explained. In order to improve the reporting regarding the data analytical decisions, it is proposed to choose and justify the data analytical approach prior to gathering the data. As a possible justification for data analysis plan, we propose using as a basis the expected the data pattern (specifically, the expectation about an improving baseline trend and about the immediate or progressive nature of the intervention effect). Although there are multiple alternatives for single-case data analysis, the current text focuses on visual analysis and multilevel models and illustrates an application of these analytical options with real data. User-friendly software is also developed.

Sign in / Sign up

Export Citation Format

Share Document