Filter Results
880 results
We present a method for measuring influences between time series that are sample path dependent. This method may be viewed as a sample path dependent extension of directed information, which is fully defined by the joint distribution of a pair of processes. This enables us to look beyond whether one process influences another to find specific patterns for which a high level of influence is witnesses. This capsule provides code for estimating the causal measure between two times series using a context tree weighting (CTW) sequential prediction algorithm. In addition to Python code which implements the CTW algorithm, we provide a Jupyter notebook demonstrating the usage of the CTW implementation. We also provide two notebooks for recreating the results from the associated manuscript. One of these notebooks is associated with the simulations and the other applies our methods to real stock market data.
Data Types:
  • Software/Code
This capsule provides simple test cases for exporting ns-3 scripts as FMUs for Co-Simulation. The usage of the exported FMUs is demonstrated with the help of simple Python scripts.
Data Types:
  • Software/Code
We propose a new variational model for nonlinear image fusion. Our approach incorporates the osmosis model proposed in Vogel et al. (2013) and Weickert et al. (2013) as an energy term in a variational model. The osmosis energy is known to realize visually plausible image data fusion. As a consequence, our method is invariant to multiplicative brightness changes. On the practical side, it requires minimal supervision and parameter tuning and can encode prior information on the structure of the images to be fused. We develop a primal-dual algorithm for solving this new image fusion model and we apply the resulting minimisation scheme to multi-modal image fusion for face fusion, colour transfer and some cultural heritage conservation challenges. Visual comparison to state-of-the-art proves the quality and flexibility of our method.
Data Types:
  • Software/Code
Intrusion detection is only the initial part of the security system for an industrial control system. Because of the criticality of the industrial control system, professionals still make the most important security decisions. Therefore, a simple intrusion alarm has a very limited role in the security system, and intrusion detection models based on deep learning struggle to provide more information because of the lack of explanation. This limits the application of deep learning methods to industrial control network intrusion detection. We analyzed the distribution of classification-related information and irrelevant information for each layer of a deep learning model from the perspective of information and found that the hidden layer of a deep learning classification model can be analyzed. We designed a layer-wise relevance propagation method to map related information to the input layer so that it can be understood by humans, which should help professionals lock and address intrusion threats more quickly.
Data Types:
  • Software/Code
This toolbox contains Matlab codes for time-varying multivariate autoregressive (TV-MVAR) modeling. MVAR models are usually applied to investigate couplings between various time-series in frequency domain. Herein, changes in the model parameters are tracked using the conventional Kalman Filer (KF) and a proposed modified KF. Model order selection and hyperparameter optimization is realized using Genetic Algorithms, significantly improving accuracy and run-time. Residual heteroskedasticity is tackled by using Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models leading to more accurate representations of the strength and directionality of the underlying couplings.
Data Types:
  • Software/Code
Demonstrates the ability of SReachTools to perform verification of stochastic linear time-varying systems over large state spaces and long time horizons.
Data Types:
  • Software/Code
This capsule provides an implementation of the method for joint depth upsampling and hole filling based on a locally linear model for the depth and a matting formulation. The method was proposed and is described in the paper mentioned below.
Data Types:
  • Software/Code
Abstract Imbalanced classification is a challenging issue in data mining and machine learning. To address this issue, a large number of solutions have been proposed. In this paper, we introduce an R library called IRIC, which integrates a wide set of solutions for binary imbalanced classification. IRIC not only provides a new implementation of some state-of-art techniques for imbalanced classification, but also improves the efficiency of model building using parallel techniques. The library and its source code are made freely available.
Data Types:
  • Software/Code
Hospitals often set protocols based on well defined standards to maintain the quality of patient reports. To ensure that the clinicians conform to the protocols, quality assurance of these reports is needed. Patient reports are currently written in free-text format, which complicates the task of quality assurance. In this paper, we present a machine learning based natural language processing system for automatic quality assurance of radiology reports on breast cancer. This is achieved in three steps: we i) identify the top-level structure (headings) of the report, ii) classify the report content into the top-level headings, iii) convert the free-text detailed findings in the report to a semi-structured format (post-structuring). Top level structure and content of report were predicted with an F1 score of 0.97 and 0.94, respectively using Support Vector Machine (SVM) classifiers. For automatic structuring, our proposed hierarchical Conditional Random Field (CRF) outperformed the baseline CRF with an F1 score of 0.78 vs 0.71. The determined structure of the report is represented in semi-structured XML format of the free-text report, which helps to easily visualize the conformance of the findings to the protocols. This format also allows easy extraction of specific information for other purposes such as search, evaluation and research.
Data Types:
  • Software/Code
A set of MATLAB codes for (1) calculating spectrogram; (2) reconstructing the signal from its spectrogram; (3) designing a perfectly reconstructing synthesis window; (4) computing instantaneous frequency (IF); (5) obtaining differential window for IF calculation; and (6) calculating instantaneous-phase-corrected (iPC) spectrogram explained in the tutorial paper entitled "Representation of complex spectrogram via phase conversion".
Data Types:
  • Software/Code
8