On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “geo-tagged”

CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputationcs.LG

CDSA uses self-attention to impute missing values in multivariate, geo-tagged time series data.

problem Missing values in multivariate, geo-tagged time series data.

method Cross-Dimensional Self-Attention (CDSA) for sequence modeling across time, location, and sensor measurements.

result CDSA outperforms state-of-the-art methods in imputation and forecasting on real-world datasets.

self-attention time series geo-tagged imputation multivariate

2019-05-23abs ↗pdf ↗

Twitmo: A Twitter Data Topic Modeling and Visualization Package for Rcs.IR

Twitmo analyzes geo-tagged Twitter data for topic modeling and visualization.

problem Analyzing public discourse on Twitter for various topics, parties, or individuals.

method Collects and preprocesses geo-tagged Tweets, applies LDA, CTM, STM, and visualizes results.

result Automatic pooling of Tweets into pseudo-documents improves topic coherence.

Twitter Topic Modeling Visualization Geo-Tagged Tweets Latent Dirichlet Allocations

2022-07-08abs ↗pdf ↗

Global Public Sentiment on Decentralized Finance: A Spatiotemporal Analysis of Geo-tagged Tweets from 150 Countriesecon.GN

Study analyzes global public sentiment on DeFi from 2012-2022.

problem Global public sentiment on DeFi is understudied.

method Sentiment analysis, spatial econometrics, clustering, topic modeling.

result Economic development significantly influences DeFi engagement, especially after 2015.

Decentralized Finance Sentiment Analysis Geopolitical Factors Global Public Opinion Economic Development

2024-09-01abs ↗pdf ↗

DNN-based Localization from Channel Estimates: Feature Design and Experimental Resultscs.NI

DNNs improve localization from channel estimates, overcoming practical impairments.

problem Improving localization accuracy from channel estimates in Massive MIMO systems.

method Principled feature design for DNNs invariant to practical impairments.

result DNN achieves high localization accuracy and generalization capability.

DNN Localization Channel State Information Massive MIMO Feature Design

2020-03-20abs ↗pdf ↗

Deriving the Traveler Behavior Information from Social Media: A Case Study in Manhattan with Twittercs.SI

This study uses Twitter to analyze traveler behavior in Manhattan.

problem Analyzing traveler behavior using social media data.

method Systematic method to extract displacement information from geo-tagged tweets.

result Twitter reveals unique demographics and travel behavior patterns.

travel behavior social media Manhattan Twitter displacement analysis

2021-01-27abs ↗pdf ↗

Modeling Food Popularity Dependencies using Social Media datacs.SI

Analyze food popularity trends using social media data.

problem Identify trends and popularity of cuisine types across space and time.

method Use off-the-shelf machine learning techniques, Kernel Density Estimation, and Bayesian Networks.

result Model dependencies among food cuisines popularity.

social media food popularity Bayesian Networks Kernel Density Estimation New York City

2019-06-26abs ↗pdf ↗

Joint Mapping and Calibration via Differentiable Sensor Fusioncs.CV

We leverage automatic differentiation (AD) and probabilistic programming to develop an end-to-end optimization algorithm for batch triangulation of a large number of unknown objects. Given noisy detections extracted from noisily geo-located street level imagery without depth information, we jointly estimate the number …

2018-11-21abs ↗pdf ↗

USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activitycs.LG

USTAR combines multiple social media modalities to model user-guided activities.

problem Lack of comprehensive spatiotemporal activity models using all social media modalities.

method Online learning method embedding locations, time, text, and users into a single space, incorporating NGTSM and GTSM records, and using collaborative filtering.

result USTAR significantly improves region and keyword retrieval compared to state-of-the-art methods.

social media spatiotemporal activity user-guided behavior collaborative filtering online learning

2019-10-23abs ↗pdf ↗