scholarly journals Transfer function based adaptive decompression for volume rendering of large medical data sets

2005 ◽  
Author(s):  
P. Ljung ◽  
C. Lundstrom ◽  
A. Ynnerman ◽  
K. Museth
Keyword(s):  
Transfer Function ◽  
Volume Rendering ◽  
Medical Data ◽  
Data Sets

scholarly journals Tensor volume exploration using attribute space representatives

2020 ◽  
Author(s):  
Jochen Jankowai ◽  
Robin Skånberg ◽  
Daniel Jönsson ◽  
Anders Ynnerman ◽  
Ingrid Hotz
Keyword(s):  
Transfer Function ◽  
Volume Rendering ◽  
Tensor Field ◽  
Complex Geometry ◽  
Scalar Fields ◽  
Data Sets ◽  
Tensor Fields ◽  
Directional Information ◽  
3D Volume ◽  
Attribute Space

While volume rendering for scalar fields has been advanced into a powerful visualisation method, similar volumetric representations for tensor fields are still rare. The complexity of the data challenges not only the rendering but also the design of the transfer function. In this paper we propose an interface using glyph widgets to design a transfer function for the rendering of tensor data sets. Thereby the transfer function (TF) controls a volume rendering which represents sought after tensor-features and a texture that conveys directional information. The basis of the design interface is a two-dimensional projection of the attribute space. Characteristicrepresentatives in the form of glyphs support an intuitive navigation through the attribute space. We provide three different options to select the representatives: automatic selection based on attribute space clustering, uniform sampling of the attribute space, or manually selected representatives. In contrast to glyphs placed into the 3D volume, we use glyphs with complex geometry as widgets to control the shape and extent of the representatives. In the final rendering the glyphs with their assigned colors play a similar role as a legend in an atlas like representation. The method provides an overview of the tensor field in the 3D volume at the same time as it allows the user to explore the tensor field in an attribute space. We demonstrate the flexibility of our approach on tensor fields for selected data sets with very different characteristics.

scholarly journals Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1573
Author(s):  
Loris Nanni ◽  
Giovanni Minchio ◽  
Sheryl Brahnam ◽  
Gianluca Maguolo ◽  
Alessandra Lumini
Keyword(s):  
Vector Space ◽  
Image Classification ◽  
Ad Hoc ◽  
Feature Space ◽  
Medical Data ◽  
Training Data ◽  
Data Sets ◽  
Large Set ◽  
Clustering Methods ◽  
Siamese Networks

Traditionally, classifiers are trained to predict patterns within a feature space. The image classification system presented here trains classifiers to predict patterns within a vector space by combining the dissimilarity spaces generated by a large set of Siamese Neural Networks (SNNs). A set of centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system’s performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.

scholarly journals On the Prediction of Solar Cycles

Solar Physics ◽  
2021 ◽  
Vol 296 (1) ◽  
Author(s):  
V. Courtillot ◽  
F. Lopes ◽  
J. L. Le Mouël
Keyword(s):  
Solar Activity ◽  
Solar Cycle ◽  
Transfer Function ◽  
Singular Spectrum Analysis ◽  
Activity Cycle ◽  
Solar Activity Cycle ◽  
Planetary Motion ◽  
Data Sets ◽  
Solar Cycles ◽  
Jovian Planets

AbstractThis article deals with the prediction of the upcoming solar activity cycle, Solar Cycle 25. We propose that astronomical ephemeris, specifically taken from the catalogs of aphelia of the four Jovian planets, could be drivers of variations in solar activity, represented by the series of sunspot numbers (SSN) from 1749 to 2020. We use singular spectrum analysis (SSA) to associate components with similar periods in the ephemeris and SSN. We determine the transfer function between the two data sets. We improve the match in successive steps: first with Jupiter only, then with the four Jovian planets and finally including commensurable periods of pairs and pairs of pairs of the Jovian planets (following Mörth and Schlamminger in Planetary Motion, Sunspots and Climate, Solar-Terrestrial Influences on Weather and Climate, 193, 1979). The transfer function can be applied to the ephemeris to predict future cycles. We test this with success using the “hindcast prediction” of Solar Cycles 21 to 24, using only data preceding these cycles, and by analyzing separately two 130 and 140 year-long halves of the original series. We conclude with a prediction of Solar Cycle 25 that can be compared to a dozen predictions by other authors: the maximum would occur in 2026.2 (± 1 yr) and reach an amplitude of 97.6 (± 7.8), similar to that of Solar Cycle 24, therefore sketching a new “Modern minimum”, following the Dalton and Gleissberg minima.

Sparse Matrix Approach in Neural Networks for Effective Medical Data Sets Classifications

2020 ◽  
Vol 6 (2) ◽  
pp. 90-97
Author(s):  
Sagir Masanawa ◽  
Hamza Abubakar
Keyword(s):  
Intelligent System ◽  
Sparse Matrix ◽  
Data Classification ◽  
Medical Data ◽  
Data Sets ◽  
Matrix Approach ◽  
Neural Network Learning ◽  
Network Learning ◽  
Hybrid Intelligent System ◽  
Medical Data Classification

In this paper, a hybrid intelligent system that consists of the sparse matrix approach incorporated in neural network learning model as a decision support tool for medical data classification is presented. The main objective of this research is to develop an effective intelligent system that can be used by medical practitioners to accelerate diagnosis and treatment processes. The sparse matrix approach incorporated in neural network learning algorithm for scalability, minimize higher memory storage capacity usage, enhancing implementation time and speed up the analysis of the medical data classification problem. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. The proposed intelligent classification system maximizes the intelligently classification of medical data and minimizes the number of trends inaccurately identified. To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Hepatitis, SPECT Heart and Cleveland Heart from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity. The results were analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system was effective in undertaking medical data classification tasks.

scholarly journals Future of Medical Research in Rare Diseases and Cancers: Shift from Pharma to Biotech and the Golden Age of Medical Advancement

2017 ◽  
Vol 6 (2) ◽  
pp. 12
Author(s):  
Abhith Pallegar
Keyword(s):  
Big Data ◽  
Medical Research ◽  
Rare Diseases ◽  
Network Effects ◽  
Medical Knowledge ◽  
Economic Cost ◽  
Medical Data ◽  
Data Sets ◽  
Leading Role ◽  
Diverse Data

The objective of the paper is to elucidate how interconnected biological systems can be better mapped and understood using the rapidly growing area of Big Data. We can harness network efficiencies by analyzing diverse medical data and probe how we can effectively lower the economic cost of finding cures for rare diseases. Most rare diseases are due to genetic abnormalities, many forms of cancers develop due to genetic mutations. Finding cures for rare diseases requires us to understand the biology and biological processes of the human body. In this paper, we explore what the historical shift of focus from pharmacology to biotechnology means for accelerating biomedical solutions. With biotechnology playing a leading role in the field of medical research, we explore how network efficiencies can be harnessed by strengthening the existing knowledge base. Studying rare or orphan diseases provides rich observable statistical data that can be leveraged for finding solutions. Network effects can be squeezed from working with diverse data sets that enables us to generate the highest quality medical knowledge with the fewest resources. This paper examines gene manipulation technologies like Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) that can prevent diseases of genetic variety. We further explore the role of the emerging field of Big Data in analyzing large quantities of medical data with the rapid growth of computing power and some of the network efficiencies gained from this endeavor. 

GRASP for Instance Selection in Medical Data Sets

2010 ◽  
pp. 53-60 ◽  
Author(s):  
Alfonso Fernández ◽  
Abraham Duarte ◽  
Rosa Hernández ◽  
Ángel Sánchez
Keyword(s):  
Medical Data ◽  
Instance Selection ◽  
Data Sets
Sign in / Sign up

Export Citation Format

Share Document