Filters








356,954 Hits in 3.4 sec

Data Anonymization Approach for Data Privacy

2015 International Journal of Science and Research (IJSR)  
At the time of released data differential privacy preserving mechanism support for individual data hiding , by adding the noise and disclose for the secondary purpose.  ...  Here this are two factor can be help to maximizing the data utility as well as minimizing the risk by using differential privacy preserving method.  ...  Randomized rounding method gives an o (log n) approximation. System Architecture The system architecture shows the complete view of the system.  ... 
doi:10.21275/v4i12.12121502 fatcat:bk4geatopngtrm4uwrxwxkdn2i

Data Appraisal Without Data Sharing [article]

Mimee Xu, Laurens van der Maaten, Awni Hannun
2022 arXiv   pre-print
We propose an efficient data appraisal method based on forward influence functions that approximates data value through its first-order loss reduction on the current model.  ...  A model owner seeking relevant training data from a data owner needs to appraise the data before acquiring it. However, without a formal agreement, the data owner does not want to share data.  ...  C.1 Private Data Appraisal in Federated Learning Scenarios Private data appraisal is studied with differential privacy and federated learning .  ... 
arXiv:2012.06430v2 fatcat:xsnfx35nhravxj3kjgir7z6efm

Differential privacy: its technological prescriptive using big data

Priyank Jain, Manasi Gyanchandani, Nilay Khare
2018 Journal of Big Data  
Availability of data and materials Not applicable. Consent for publication Not applicable. Ethics approval and consent to participate Not applicable.  ...  Data publication architecture; 2. Separated architecture; and 3. Hybridized architecture [12] .  ...  Fig. 1 1 Differential privacy mechanism Fig. 2 2 Differential privacy through noise Fig. 3 Fig. 4 34 Data publication architecture [12] Separated architecture [12] Fig. 8 8 Probability density  ... 
doi:10.1186/s40537-018-0124-9 fatcat:lvmh66kmeja2holyp3osuesxd4

Automated trend analysis of proteomics data using an intelligent data mining architecture

J MALONE, K MCGARRY, C BOWERMAN
2006 Expert systems with applications  
We present an intelligent data mining architecture that incorporates both data-driven and goal-driven strategies and is able to accommodate the spatial and temporal elements of the dataset under analysis  ...  The architecture is able to automatically classify interesting proteins with a low number of false positives and false negatives.  ...  data mining architecture, using differential ratios, described in this paper; (ii) using PCA as a variance analysis method to provide data for the neural network; (iii) using covariance as a variance  ... 
doi:10.1016/j.eswa.2005.09.047 fatcat:n3tzyhtwsfdnxkgqn6qp5uvxkm

Joint Search of Data Augmentation Policies and Network Architectures [article]

Taiga Kashima, Yoshihiro Yamada, Shunta Saito
2021 arXiv   pre-print
The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection.  ...  The proposed method combines differentiable methods for augmentation policy search and network architecture search to jointly optimize them in the end-to-end manner.  ...  Our method jointly explores data augmentation policies and network architectures by combining differentiable methods for each part.  ... 
arXiv:2012.09407v2 fatcat:otozvh2rz5btfn5hd7cacgei4y

DADA: Differentiable Automatic Data Augmentation [article]

Yonggang Li and Guosheng Hu and Yongtao Wang and Timothy Hospedales and Neil M. Robertson and Yongxin Yang
2020 arXiv   pre-print
In this paper, we propose Differentiable Automatic Data Augmentation (DADA) which dramatically reduces the cost.  ...  Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation.  ...  Motivated by the differentiable neural architecture search [5, 19, 26] , we propose a Differentiable Automatic Data Augmentation (DADA) to relax the optimization problem to be differentiable and then  ... 
arXiv:2003.03780v3 fatcat:5qibqs572rbthleb3fwitqtabe

Data analysis [chapter]

2009 Fractured Rock Hydraulics  
solutions 47 2.1 Overview 47 2.2 Differential operators 48 2.3 Uniqueness of solutions 53 2.4 Approximate solution errors 53 2.5 Approximation methods 59 2.5.1 Preliminaries 59 2.5.2 Collocation  ...  Chapter 2 presents some key concepts about approximate solutions. Chapter 3 discuss some data analysis techniques applied to groundwater modelling.  ... 
doi:10.1201/9780203859414-7 fatcat:zmdqk4yjofagbi5pvzwbmo3uem

PDE-Net: Learning PDEs from Data [article]

Zichao Long, Yiping Lu, Xianzhong Ma, Bin Dong
2018 arXiv   pre-print
In this paper, we present an initial attempt to learn evolution PDEs from data.  ...  The basic idea of the proposed PDE-Net is to learn differential operators by learning convolution kernels (filters), and apply neural networks or other machine learning methods to approximate the unknown  ...  Generally speaking, large filters can approximate higher order differential operators or lower order differential operators with higher approximation orders.  ... 
arXiv:1710.09668v2 fatcat:bu6gvt7bfvcfppamy5lhpwcr6m

Taming Data

Alan Aderem, Ilya Shmulevich
2008 Cell Host and Microbe  
These approaches undoubtedly require flexible and adaptable software architectures that can support the rapid development of integrated tools for analyzing heterogeneous data typical in systems biology  ...  In addition, to improve coverage of the innate immunity interactome, over 100,000 known interactions and approximately 2500 pathways from major public databases are also included and intelligently grouped  ... 
doi:10.1016/j.chom.2008.09.011 pmid:18854235 pmcid:PMC3074406 fatcat:rdridyt245gk7ab25dqs6wo3sm

Data-Free Model Extraction [article]

Jean-Baptiste Truong, Pratyush Maini, Robert J. Walls, Nicolas Papernot
2021 arXiv   pre-print
For example, we recover the model's logits from its probability predictions to approximate gradients.  ...  In contrast, we propose data-free model extraction methods that do not require a surrogate dataset. Our approach adapts techniques from the area of data-free knowledge transfer for model extraction.  ...  We show that is is possible to do so and recover approximate logits whose Mean Average Error (MAE) with the true logits is low, on three different victim architecture.  ... 
arXiv:2011.14779v2 fatcat:ayuzmejplfavtmdnngnjrmzwyu

NeuralPDE: Modelling Dynamical Systems from Data [article]

Andrzej Dulny and Andreas Hotho and Anna Krause
2021 arXiv   pre-print
Our model can be applied to any data without requiring any prior knowledge about the governing PDE.  ...  Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs).  ...  They first learn a neural network which approximates the data, then they calculate the derivatives up to a predetermined order.  ... 
arXiv:2111.07671v1 fatcat:z27aumsndzcifpmu7y7kesa5gm

Declarative temporal data models for sensor-driven query processing

Yanif Ahmad, Uğur Çetintemel
2007 Proceedings of the 4th workshop on Data management for sensor networks in conjunction with 33rd International Conference on Very Large Data Bases - DMSN '07  
Pulse is able to guarantee user-defined error bounds between query results from continuous-time data models and sampled data, including cases of null results.  ...  We introduce Pulse, a framework for processing continuous queries over these continuous-time data models.  ...  Section 2 briefly describes Pulse's basic system model, including the data, query and result models, and a high-level overview of the current architecture.  ... 
doi:10.1145/1286380.1286390 dblp:conf/dmsn/AhmadC07 fatcat:pdorh5pi3bgs7ijybq4f45t7ty

Low Power Data Acquisition System for Bioimplantable Devices

Sadeque Reza Khan, M. S. Bhat
2014 Advances in Electronics  
In this paper an energy efficient data acquisition unit is presented which includes low power high bandwidth front-end amplifier and a 10-bit fully differential successive approximation ADC.  ...  Signal acquisition represents the most important block in biomedical devices, because of its responsibilities to retrieve precise data from the biological tissues.  ...  This paper describes a fully differential asynchronous SAR ADC in 1.8 m CMOS technology that uses a charge distribution differential DAC with monotonic capacitor switching architecture designed for energy  ... 
doi:10.1155/2014/394057 fatcat:tgpgos4zkfglpdda5pg6ewns34

Wasserstein Generative Adversarial Networks Based Data Augmentation for Radar Data Analysis

Hansoo Lee, Jonggeun Kim, Eun Kyeong Kim, Sungshin Kim
2020 Applied Sciences  
Recent weather radar data related research has focused on applying machine learning and deep learning to solve complicated problems.  ...  It is a well-known fact that an adequate amount of data is a positively necessary condition in machine learning and deep learning.  ...  The dualpolarization Doppler radar can provide useful information, including corrected reflectivity (CZ), differential reflectivity (DR), specific differential phase shift (KD), and cross-correlation (  ... 
doi:10.3390/app10041449 fatcat:3mefjlgrvrfqtmbeygt2nxilri

Security and privacy for big data: A systematic literature review

Boel Nelson, Tomas Olovsson
2016 2016 IEEE International Conference on Big Data (Big Data)  
Our main focus is on differential privacy, a privacy model which protects individuals' privacy, while still allowing analysts to learn statistical information about a population.  ...  In an age where data is becoming increasingly more valuable as it allows for data analysis and machine learning, big data has become a hot topic.  ...  We also discuss what privacy implications our specific use case has for users, and propose a privacy architecture that relies on differential privacy to guarantee privacy.  ... 
doi:10.1109/bigdata.2016.7841037 dblp:conf/bigdataconf/NelsonO16 fatcat:uiippetep5ea3ote2gzsxd5acm
« Previous Showing results 1 — 15 out of 356,954 results