SAND: Semi-Supervised Adaptive Novel Class Detection and Classification over Data Stream

Authors: Ahsanul Haque, Latifur Khan, Michael Baron

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiment results on benchmark and synthetic data sets show effectiveness of the proposed approach.
Researcher Affiliation Academia Ahsanul Haque and Latifur Khan Department of Computer Science The University of Texas at Dallas Richardson, Texas 75080 Email: {ahsanul.haque, lkhan}@utdallas.edu Michael Baron Department of Mathematical Sciences The University of Texas at Dallas Richardson, Texas 75080 Email: mbaron@utdallas.edu
Pseudocode Yes Algorithm 1 Change detection algorithm
Open Source Code No The paper does not provide any link or explicit statement about the availability of the source code for the methodology described.
Open Datasets Yes Forest Cover is obtained from the UCI repository as explained in (Masud et al. 2011). ... Physical Activity Monitoring data set (PAMAP) from UCI (Reiss and Stricker 2012). Powersupply (Zhu 2010) data set... Hyper Plane (Zhu 2010)... Syn RBF@X are synthetic data sets generated using Random RBFGenerator Drift of MOA (Bifet et al. 2010) framework...
Dataset Splits No The paper does not specify explicit training/validation/test splits by percentages or sample counts, nor does it mention using cross-validation for the general experimental setup. It discusses using initial training data and updating models with new data chunks in a streaming context.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments (e.g., CPU, GPU models, memory).
Software Dependencies No The paper mentions general software components and algorithms like 'k-NN', 'K-means', 'DBSCAN', 'CUSUM', and 'MOA framework' but does not specify any version numbers for these or other software dependencies used in their implementation.
Experiment Setup Yes We use α = 0.05 and Δ = 100 in our experiments, which are also widely used in the literature. ... We set t = 6 and q = 50 in SAND using cross validation.