Data Science and Designing for Privacy

2016 ◽  
Vol 20 (1) ◽  
pp. 51-68
Author(s):  
Michael Falgoust ◽  
Keyword(s):  
Data Science ◽  
Personal Information ◽  
Information Age ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Informational Privacy ◽  
Design Constraint ◽  
Classical Models ◽  
Privacy Problem

Unprecedented advances in the ability to store, analyze, and retrieve data is the hallmark of the information age. Along with enhanced capability to identify meaningful patterns in large data sets, contemporary data science renders many classical models of privacy protection ineffective. Addressing these issues through privacy-sensitive design is insufficient because advanced data science is mutually exclusive with preserving privacy. The special privacy problem posed by data analysis has so far escaped even leading accounts of informational privacy. Here, I argue that accounts of privacy must include norms about information processing in addition to norms about information flow. Ultimately, users need the resources to control how and when personal information is processed and the knowledge to make information decisions about that control. While privacy is an insufficient design constraint, value-sensitive design around control and transparency can support privacy in the information age.

scholarly journals Visualizing Denmark's Cultural Heritage

2020 ◽  
Author(s):  
Stefan Jänicke
Keyword(s):  
Cultural Heritage ◽  
Data Science ◽  
Large Data ◽  
Large Data Sets ◽  
Original Version ◽  
Visual Design ◽  
Data Sets

Visualization as a method to reveal patterns in large data sets is a powerful tool to build bridges between data science and other research disciplines. The value of visual design is documented with a showcase on the Dansk biografisk Lexikon. The original version of this article was published in the 2020 November issue of Aktuel Naturvidenskab.

scholarly journals Challenges and Opportunities of Building Fast GBDT Systems

2021 ◽  
Author(s):  
Zeyi Wen ◽  
Qinbin Li ◽  
Bingsheng He ◽  
Bin Cui
Keyword(s):  
Data Science ◽  
Cluster Computing ◽  
Online Advertising ◽  
Large Data ◽  
Large Data Sets ◽  
Gradient Boosting ◽  
Data Sets ◽  
Survey Paper ◽  
Advantages And Disadvantages ◽  
Challenges And Opportunities

In the last few years, Gradient Boosting Decision Trees (GBDTs) have been widely used in various applications such as online advertising and spam filtering. However, GBDT training is often a key performance bottleneck for such data science pipelines, especially for training a large number of deep trees on large data sets. Thus, many parallel and distributed GBDT systems have been researched and developed to accelerate the training process. In this survey paper, we review the recent GBDT systems with respect to accelerations with emerging hardware as well as cluster computing, and compare the advantages and disadvantages of the existing implementations. Finally, we present the research opportunities and challenges in designing fast next generation GBDT systems.

scholarly journals Data Science Methods for Psychology

Psychology ◽  
2020 ◽  
Author(s):  
Jeffrey Stanton
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Data Analysis ◽  
Data Collection ◽  
Data Science ◽  
Large Data ◽  
Large Data Sets ◽  
Predictive Analysis ◽  
Data Sets ◽  
The Impact

The term “data science” refers to an emerging field of research and practice that focuses on obtaining, processing, visualizing, analyzing, preserving, and re-using large collections of information. A related term, “big data,” has been used to refer to one of the important challenges faced by data scientists in many applied environments: the need to analyze large data sources, in certain cases using high-speed, real-time data analysis techniques. Data science encompasses much more than big data, however, as a result of many advancements in cognate fields such as computer science and statistics. Data science has also benefited from the widespread availability of inexpensive computing hardware—a development that has enabled “cloud-based” services for the storage and analysis of large data sets. The techniques and tools of data science have broad applicability in the sciences. Within the field of psychology, data science offers new opportunities for data collection and data analysis that have begun to streamline and augment efforts to investigate the brain and behavior. The tools of data science also enable new areas of research, such as computational neuroscience. As an example of the impact of data science, psychologists frequently use predictive analysis as an investigative tool to probe the relationships between a set of independent variables and one or more dependent variables. While predictive analysis has traditionally been accomplished with techniques such as multiple regression, recent developments in the area of machine learning have put new predictive tools in the hands of psychologists. These machine learning tools relax distributional assumptions and facilitate exploration of non-linear relationships among variables. These tools also enable the analysis of large data sets by opening options for parallel processing. In this article, a range of relevant areas from data science is reviewed for applicability to key research problems in psychology including large-scale data collection, exploratory data analysis, confirmatory data analysis, and visualization. This bibliography covers data mining, machine learning, deep learning, natural language processing, Bayesian data analysis, visualization, crowdsourcing, web scraping, open source software, application programming interfaces, and research resources such as journals and textbooks.

scholarly journals Data Cleaning Techniques for Large Data Sets

2020 ◽  
Vol 8 (6) ◽  
pp. 4453-4456
Keyword(s):  
Decision Making ◽  
Data Science ◽  
Missing Values ◽  
Data Cleaning ◽  
Large Data ◽  
Large Data Sets ◽  
Decision Making Process ◽  
Data Sets ◽  
Multiple Sources ◽  
Data Set

In today’s emerging era of data science where data plays a huge role for accurate decision making process it is very important to work on cleaned and irredundant data. As data is gathered from multiple sources it might contain anomalies, missing values etc. which needs to be removed this process is called data pre-processing. In this paper we perform data preprocessing on news popularity data set where extraction , transform and loading (ETL) is done .The outcome of the process is cleaned and refined news data set which can be used to do further analysis for knowledge discovery on popularity of news . Refined data give accurate predictions and can be better utilized in decision making process

scholarly journals Reuse Of Clinical Data

2014 ◽  
Vol 23 (01) ◽  
pp. 52-54 ◽  
Author(s):  
C. Safran
Keyword(s):  
Clinical Data ◽  
Data Science ◽  
Large Data ◽  
Daily Practice ◽  
Health Data ◽  
Large Data Sets ◽  
Care Process ◽  
Data Sets ◽  
Societal Benefit ◽  
Practice Of Medicine

Summary Objectives: To provide an overview of the benefits of clinical data collected as a by-product of the care process, the potential problems with large aggregations of these data, the policy frameworks that have been formulated, and the major challenges in the coming years. Methods: This report summarizes some of the major observations from AMIA and IMIA conferences held on this admittedly broad topic from 2006 through 2013. This report also includes many unsupported opinions of the author. Results: The benefits of aggregating larger and larger sets of routinely collected clinical data are well documented and of great societal benefit. These large data sets will probably never answer all possible clinical questions for methodological reasons. Non-traditional sources of health data that are patient-sources will pose new data science challenges. Conclusions: If we ever hope to have tools that can rapidly provide evidence for daily practice of medicine we need a science of health data perhaps modeled after the science of astronomy.

An example of spectrum imaging used for comparison of EELS quantitative analysis techniques on Al-Li

1991 ◽  
Vol 49 ◽  
pp. 726-727
Author(s):  
John A. Hunt
Keyword(s):  
Quantitative Analysis ◽  
Large Data ◽  
Difference Spectrum ◽  
Large Data Sets ◽  
Foil Thickness ◽  
Data Sets ◽  
Analysis Techniques ◽  
Spectrum Imaging ◽  
Normal Spectrum ◽  
Electron Energy Loss

Spectrum-imaging is a useful technique for comparing different processing methods on very large data sets which are identical for each method. This paper is concerned with comparing methods of electron energy-loss spectroscopy (EELS) quantitative analysis on the Al-Li system. The spectrum-image analyzed here was obtained from an Al-10at%Li foil aged to produce δ' precipitates that can span the foil thickness. Two 1024 channel EELS spectra offset in energy by 1 eV were recorded and stored at each pixel in the 80x80 spectrum-image (25 Mbytes). An energy range of 39-89eV (20 channels/eV) are represented. During processing the spectra are either subtracted to create an artifact corrected difference spectrum, or the energy offset is numerically removed and the spectra are added to create a normal spectrum. The spectrum-images are processed into 2D floating-point images using methods and software described in [1].

Cluster analysis for large data sets: applications to individual aerosol particles from the mid-pacific

1992 ◽  
Vol 50 (2) ◽  
pp. 1488-1489
Author(s):  
Thomas W. Shattuck ◽  
James R. Anderson ◽  
Neil W. Tindale ◽  
Peter R. Buseck
Keyword(s):  
Cluster Analysis ◽  
Chemical Reactivity ◽  
Large Data ◽  
Large Data Sets ◽  
Particle Analysis ◽  
Data Sets ◽  
Halogen Chemistry ◽  
Complete Study ◽  
Components Analysis ◽  
Automated Scanning

Individual particle analysis involves the study of tens of thousands of particles using automated scanning electron microscopy and elemental analysis by energy-dispersive, x-ray emission spectroscopy (EDS). EDS produces large data sets that must be analyzed using multi-variate statistical techniques. A complete study uses cluster analysis, discriminant analysis, and factor or principal components analysis (PCA). The three techniques are used in the study of particles sampled during the FeLine cruise to the mid-Pacific ocean in the summer of 1990. The mid-Pacific aerosol provides information on long range particle transport, iron deposition, sea salt ageing, and halogen chemistry.Aerosol particle data sets suffer from a number of difficulties for pattern recognition using cluster analysis. There is a great disparity in the number of observations per cluster and the range of the variables in each cluster. The variables are not normally distributed, they are subject to considerable experimental error, and many values are zero, because of finite detection limits. Many of the clusters show considerable overlap, because of natural variability, agglomeration, and chemical reactivity.

NVESTIGATION OF THE EFFICIENCY OF DISTRIBUTED INFORMATION SYSTEMS BASED ON THE PROCESSING OF LARGE AMOUNTS OF DATA

2019 ◽  
Author(s):  
Mykhajlo Klymash ◽  
Olena Hordiichuk — Bublivska ◽  
Ihor Tchaikovskyi ◽  
Oksana Urikova
Keyword(s):  
Distributed Systems ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Data Decomposition ◽  
Distributed Information ◽  
Software Model ◽  
Computing Performance ◽  
Mapreduce Model ◽  
Singular Data

In this article investigated the features of processing large arrays of information for distributed systems. A method of singular data decomposition is used to reduce the amount of data processed, eliminating redundancy. Dependencies of com­putational efficiency on distributed systems were obtained using the MPI messa­ging protocol and MapReduce node interaction software model. Were analyzed the effici­ency of the application of each technology for the processing of different sizes of data: Non — distributed systems are inefficient for large volumes of information due to low computing performance. It is proposed to use distributed systems that use the method of singular data decomposition, which will reduce the amount of information processed. The study of systems using the MPI protocol and MapReduce model obtained the dependence of the duration calculations time on the number of processes, which testify to the expediency of using distributed computing when processing large data sets. It is also found that distributed systems using MapReduce model work much more efficiently than MPI, especially with large amounts of data. MPI makes it possible to perform calculations more efficiently for small amounts of information. When increased the data sets, advisable to use the Map Reduce model.

Using Large Data Sets and Statistical Tools to Define “Failure” and Demonstrate the Safety of DPR

2018 ◽  
Vol 2018 (6) ◽  
pp. 38-39
Author(s):  
Austa Parker ◽  
Yan Qu ◽  
David Hokanson ◽  
Jeff Soller ◽  
Eric Dickenson ◽  
...  
Keyword(s):  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Statistical Tools
Sign in / Sign up

Export Citation Format

Share Document