Information Fusion

MATLAB routines for all numerical examples in the manuscript.

data.mat represents the operations of different kinds of nodes acquired from the real information system. count.mat represents that fusing data observed from monitoring nodes, sink nodes and the Internet together. count1.mat, count2.mat, and count3.mat denote the performance of only using nodes in the monitor area, sink area, and the Internet respectively. count12.mat means fusing monitoring nodes and sink nodes. count13.mat means fusing monitoring nodes and the Internet nodes. count23.mat means fusing sink nodes and the Internet nodes. ROCF.mat, ROCN.mat, ROCI.mat, and ROCS.mat denote the ROC curves of NetF and other single features respectively.

This file contains source code and all datasets used in the paper: Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach.

We tested ChatGPT on 25 tasks focusing on solving common NLP problems and requiring analytical reasoning. These tasks include (1) a relatively simple binary classification of texts like spam, humor, sarcasm, aggression detection, or grammatical correctness of the text; (2) a more complex multiclass and multi-label classification of texts such as sentiment analysis, emotion recognition; (3) reasoning with the personal context, i.e., personalized versions of the problems that make use of additional information about text perception of a given user (user’s examples provided to ChatGPT); (4) semantic annotation and acceptance of the text going towards natural language understanding (NLU) like word sense disambiguation (WSD), and (5) answering questions based on the input text. More information in the paper: https://www.sciencedirect.com/science/article/pii/S156625352300177X