Papers with Code 아카이브

Time Series Analysis

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
12
평가표
3
보존된 평가 기록
14

Time Series Analysis is a statistical technique used to analyze and model time-based data. It is used in various fields such as finance, economics, and engineering to analyze patterns and trends in data over time. The goal of time series analysis is to identify the underlying patterns, trends, and seasonality in the data, and to use this information to make informed predictions about future values.

<span style="color:grey; opacity: 0.6">( Image credit: Autoregressive CNNs for Asynchronous Time Series )</span>

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

Equilibrium-Traffic-Networks

This repository contains three graph datasets for the UE traffic assignment problem on Sioux-Falls, Eastern-Massachusetts and Anaheim networks in both dgl and pyg formats. The datasets are generated and used to train and evaluate models for solving the User Equilibrium (UE) problem on three transportation networks: - ** Sioux-Falls** - ** Eastern-Massachusetts** - **Anaheim ** These networks are sourced from the well-known "transport networks for research" repository. These datasets are generated for the study "A hybrid deep-learning-metaheuristic framework for bi-level network design problems" by Bahman Madadi and Gonçalo H. de Almeida Correia, published in Expert Systems with Applications. ## Metadata Detailed information can be found in the Metadata.md file. ## Links - Figshare Dataset Repository: Link ## References - Article: A hybrid deep-learning-metaheuristic framework for bi-level network design problems - Link - GitHub Repository: HDLMF_GIN-GA - Link - Primary Figshare Data Repository: Link Note: This dataset is maintained at Figshare.

ESA-AD

ESA Anomaly Dataset is the first large-scale, real-life satellite telemetry dataset with curated anomaly annotations originated from three ESA missions. We hope that this unique dataset will allow researchers and scientists from academia, research institutes, national and international space agencies, and industry to benchmark models and approaches on a common baseline as well as research and develop novel, computational-efficient approaches for anomaly detection in satellite telemetry data. The dataset results from the work of an 18-month project carried by an industry Consortium composed of Airbus Defence and Space, KP Labs and the European Space Agency’s European Space Operations Centre. The project, funded by the European Space Agency (ESA), is part of the Artificial Intelligence for Automation (A²I) Roadmap (De Canio et al., 2023), a large endeavour started in 2021 to automate space operations by leveraging artificial intelligence.

FedTADBench

FedTADBench is a federated time series anomaly detection benchmark. It covers 5 time series anomaly detection algorithms, 4 federated learning frameworks, and 3 time series anomaly detection datasets. Source: [FedTADBench: Federated Time-Series Anomaly Detection Benchmark (https://arxiv.org/pdf/2212.09518v1.pdf)

FinSen

Enhancing Financial Market Predictions: Causality-Driven Feature Selection This paper introduces FinSen dataset that revolutionizes financial market analysis by integrating economic and financial news articles from 197 countries with stock market data. The dataset’s extensive coverage spans 15 years from 2007 to 2023 with temporal information, offering a rich, global perspective 160,000 records on financial market news. Our study leverages causally validated sentiment scores and LSTM models to enhance market forecast accuracy and reliability. # Our FinSen Dataset arXiv Pytorch 1.5 License: MIT This repository contains the dataset for Enhancing Financial Market Predictions: Causality-Driven Feature Selection, which has been accepted in ADMA 2024. If the dataset or the paper has been useful in your research, please add a citation to our work: @article{liang2024enhancing, title={Enhancing Financial Market Predictions: Causality-Driven Feature Selection}, author={Liang, Wenhao and Li, Zhengyang and Chen, Weitong}, journal={arXiv e-prints}, pages={arXiv--2408}, year={2024} } ### Datasets [FinSen] can be downloaded manually from the repository as csv file. Sentiment and its score are generated by FinBert model from the Hugging Face Transformers library under the identifier "ProsusAI/finbert". (Araci, Dogu. "Finbert: Financial sentiment analysis with pre-trained language models." arXiv preprint arXiv:1908.10063 (2019).) We only provide US for research purpose usage, please contact w.liang@adelaide.edu.au for other countries (total 197 included) if necessary. We also provide other NLP datasets for text classification tasks here, please cite them correspondingly once you used them in your research if any. 1. 20Newsgroups. Joachims, T., et al.: A probabilistic analysis of the rocchio algorithm with tfidf for text categorization. In: ICML. vol. 97, pp. 143–151. Citeseer (1997) 2. AG News. Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Advances in neural information processing systems 28 (2015) 3. Financial PhraseBank. Malo, P., Sinha, A., Korhonen, P., Wallenius, J., Takala, P.: Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology 65(4), 782–796 (2014) ### Dataloader for FinSen We provide the preprocessing file finsen.py for our FinSen dataset under dataloaders directory for more convienient usage. ### Models - Text Classification 1. DAN-3. 2. Gobal Pooling CNN. ### Models - Regression Prediction 1. LSTM ### Using Sentiment Score from FinSen Predict Result on S&P500 ### Dependencies The code is based on PyTorch under code frame of https://github.com/torrvision/focal_calibration, please cite their work if you found it is useful. :smiley: ☺ Happy Research !

HASCD

HASCD (Human Activity Segmentation Challenge Dataset) contains 250 annotated multivariate time series capturing 10.7 h of real-world human motion smartphone sensor data from 15 bachelor computer science students. The recordings capture 6 distinct human motion sequences designed to represent pervasive behaviour in realistic indoor and outdoor settings. The data set serves as a benchmark for evaluating machine learning workflows.

Korea Composite Stock Price Index

The data contains the following attributes for Korea Stock Price Index (KOSPI) for January 2000–December 2016: 1. Date (YYYY.M(M).D(D)) 2. Opening Price for the date, PX_OPEN 3. Highest Price for the date, PX_HIGH 4. Lowest Price for the date, PX_LOW 5. Closing Price for the date, PX_LAST 6. Total volume traded on the date, PX_VOLUME The total number of cases comprises 4203 trading days, and historical data is obtained from Bloomberg.

MLO-Cn2

The Mauna Loa Seeing Study was performed by the EOL/Integrated Surface Flux System team, capturing surface meteorology and flux products at the Mauna Loa Observatory in Hawaii. The MLO-Cn2 dataset enables researchers to evaluate physics-inspired models for optical turbulence ($C_n^2$), as well as develop new models from sonic anemometer data. ## Summary Sonic anemometers were deployed during Summer 2006 at the Mauna Loa Observatory, Hawaii to quantify the atmospheric seeing quality, to help NCAR/HAO plan current and future telescope observations. This study was intended to replicate measurements made previously for planning the Advanced Technology Solar Telescope (ATST). Deployment and operations for this study were done by HAO staff, and ISFF provided equipment and some data management support. ## Details Identifiers * Local archive identifier: 160.007 * doi:10.26023/CQR2-TQJ9-AH10 https://doi.org/10.26023/CQR2-TQJ9-AH10 Related projects * MLO_CN2: Mauna Loa Seeing Study (Cn-squared study) https://data.eol.ucar.edu/project/MLO_CN2 Additional information * Frequency: 5 minute * Language: English Categories * Surface Platforms * Flux Tower * NCAR/EOL Integrated Surface Flux System - ISFS Instruments * Eddy Correlation Devices * Sonic Anemometer * Surface Flux * Surface Meteorology Related links * homepage: MLO_CN2 project main web page http://www.eol.ucar.edu/isf/projects/MLO_CN2/ * info: Integrated Surface Flux System https://www.eol.ucar.edu/observing_facilities/isfs * homepage: MLO_CN2 Project Homepage https://www.eol.ucar.edu/field_projects/mlocn2 Temporal coverage * Begin datetime: 2006-06-09 00:00:00 * End datetime: 2006-08-08 23:59:59 Spatial coverage * Maximum (North) Latitude: 19.53 * Minimum (South) Latitude: 19.53 * Minimum (West) Longitude: -155.57 * Maximum (East) Longitude: -155.57 Primary contact information * pointOfContact: EOL Data Support datahelp@eol.ucar.edu https://data.eol.ucar.edu/contact/show/1 Additional contact information * author: NSF NCAR/EOL ISFS Team https://data.eol.ucar.edu/contact/show/3140 Alternate metadata formats * DataCite: https://data.eol.ucar.edu/dataset/160.007?format=datacite * ISO/TC 211: https://data.eol.ucar.edu/dataset/160.007?format=isotc211

MODIS AOD (imputed)

Structured atmospheric data for AI/ML Long-term, pre-processed, atmospheric datasets for use in Machine Learning/AI based forecasting. Initially intended to predict AOD, however can be adapted for prediction of other atmospheric particles. Machine Learning ready NumPy* dataset constructed by pre-processing selected atmospheric variables at 5 pressure levels form ERA5 reanalysis (resulting in 35 features) and AOD data from MODIS on board of Aqua and Terra satellites. This is a long-term daily dataset which spans 20 years from 1st Jan 2003 to 31st Dec 2022 and is homogeneously structured into 1ºx1º grid cells. Missing days and AOD values from MODIS were imputed using Lattice Kriging method (Python code used for imputation included as Jupyter Notebook 'Combine_impute_AOD.ipynb'), but raw (unimputed) MODIS data are also available. All datasets were created for a purpose of training Convolutional Neural Network model designed to forecast Saharan dust (DustNet). These datasets can also be used to train other ML models, or indeed to forecast other variables. This dataset was used to train the DustNet model and predict 24-hr ahead AOD. Please see doi: 10.5281/zenodo.10722953 for further details on predicting AOD and the DustNet model code. *datasets are NumPy arrays (v1.23) created in Python v3.8.18.

MOSAD

MOSAD (Mobile Sensing Human Activity Data Set) is a multi-modal, annotated time series (TS) data set that contains 14 recordings of 9 triaxial smartphone sensor measurements (126 TS) from 6 human subjects performing (in part) 3 motion sequences in different locations. The aim of the data set is to facilitate the study of human behaviour and the design of TS data mining technology to separate individual activities using low-cost sensors in wearable devices.

MTic

Periodic Tic sounds (T0=1s) sampled at 16kHz with duration of nearly 10s.

MultiSenseBadminton

The sports industry is witnessing an increasing trend of utilizing multiple synchronized sensors for player data collection, enabling personalized training systems with multi-perspective real-time feedback. Badminton could benefit from these various sensors, but there is a scarcity of comprehensive badminton action datasets for analysis and training feedback. Addressing this gap, this paper introduces a multi-sensor badminton dataset for forehand clear and backhand drive strokes, based on interviews with coaches for optimal usability. The dataset covers various skill levels, including beginners, intermediates, and experts, providing resources for understanding biomechanics across skill levels. It encompasses 7,763 badminton swing data from 25 players, featuring sensor data on eye tracking, body tracking, muscle signals, and foot pressure. The dataset also includes video recordings, detailed annotations on stroke type, skill level, sound, ball landing, and hitting location, as well as survey and interview data. We validated our dataset by applying a proof-of-concept machine learning model to all annotation data, demonstrating its comprehensive applicability in advanced badminton training and research.

Narvik Road Dataset

DIT4BEARs Internship Project (at UiT-The Arctic University of Norway) Dataset The dataset contains data of 5 months including weather conditions, friction coefficient, distance traveled, wind speed, surface temperature, air temperature, etc. This dataset was provided by DIT4BEARs for the Smart Road Internship Project at UiT-The Arctic University of Norway It can be used for weather forecasting, road friction forecasting, smart road proposition, minimization of accident rate in Barren Euro-Arctic regions.

NBA player performance prediction dataset

The dataset covers the 2022-23 NBA regular season (2022-10-18 to 2023-01-20) which contains 691 games in 92 game days. There are 582 active players among the 30 teams. Besides 7 basic statistics, we collected 3 tracking statistics, and 3 advanced statistics. We use tracking statistics to more accurately reflect players' movements on the court, and advanced statistics to more properly represent a player's effectiveness and contribution to the game. Together, these two types of data give us a better understanding of factors that are not visible on the scoreboard.

ODDS

Outliers or anomalies are instances that do not conform to the norm of a dataset. Outlier detection is an important data mining problem that has been researched within diverse research areas and applications domains such as intrusion detection, fraud detection, unusual event detection, disease condition detection etc. The exact notion of an outlier is different for different application domains. Hence, applying a technique developed for one domain to another is not straightforward. Moreover, availability of labeled data for training/validation of outlier detection methods is scarce and often noise contained in data tends to be similar to outliers, thus makes it difficult to distinguish them. Because of these challenges outlier detection is not an easy problem to solve. Furthermore, research on outlier detection has been held back by the lack of good benchmark datasets with ground truths. Existing benchmarks are typically either proprietary or else very artificial. Moreover, existing real-world outlier/anomaly detection datasets lack the availability of ground truth. In ODDS, we openly provide access to a large collection of outlier detection datasets with ground truth (if available). Our focus is to provide datasets from different domains and present them under a single platform for the research community. As such, we arrange the datasets based on their types into different tables in ODDS library. The ODDS library is being actively developed since summer 2016 and is growing as a result of our research pursuits in outlier/anomaly mining and also to help the corresponding research community. Researchers are welcome to share their datasets with us to include in ODDS library by emailing srayana@cs.stonybrook.edu.

Regional AQ Datasets

The primary environmental health threat in the WHO European Region is air pollution, impacting the daily health and well-being of its citizens significantly. To effectively understand the impact, and dynamics of air quality a detailed investigation of different environmental, weather, and land cover indices is appropriate. To this end, this paper introduces three European cities’ spatiotemporal datasets, customized for air pollution monitoring at a regional level. The datasets are composed of major air quality, weather measurements and land use information. The duration is approximately from 2020 to 2023 with an hourly temporal resolution and a spatial resolution of 0.005°. The temporal and spatiotemporal datasets are publicly released aiming to provide a solid foundation for researchers, analysts, and practitioners to conduct in-depth analyses of air pollution dynamics.

Santa Clara Reservoir Levels

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

Sen4AgriNet

A Sentinel-2 based time series multi country benchmark dataset, tailored for agricultural monitoring applications with Machine and Deep Learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the Land Parcel Identification System (LPIS) for harmonizing country wide labels. Sen4AgriNet is the only multi-country, multi-year dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives.

SKF-BLS Dataset

This dataset is developed to estimate bearing loads under various operating conditions (rotational speed, axial and radial loads) using data from temperature and vibration sensors. These sensor modalities provide complementary information: vibration signals indicate the magnitude of the load, while temperature measurements reveal the spatial distribution of the load within the bearing. The dataset emulates a real-world deployment scenario of a virtual sensor, mirroring scenarios where a physical sensor's operational life is limited, such as when a sensor roller collecting field data experiences premature battery depletion. It contains 55 unique operating conditions, defined by axial load (Fx), radial load (Fy), and rotational speed.

USNA-Cn2 (long-term)

The USNA long-term scintillation study is a continuing effort to characterize and measure optical turbulence in the near-maritime boundary layer. ## Summary The field campaign utilized a ScinTec BLS450 scintillometer to characterize the strength of optical turbulence over a link approximately 3 [m] above the river’s surface between January 1\textsuperscript{st}, 2020, and July 26\textsuperscript{th}, 2023. This field campaign included a range of meteorological and oceanographic measurements from nearby NOAA, National Data Buoy Center (NDBC), and Academy weather stations. The long-term dataset covers the period between January 1\textsuperscript{st}, 2020 and July 14\textsuperscript{th}, 2022. This data set includes local measurements made with a Davis Vantage Pro2 weather station, as well as water conditions from the NDBC Thomas Point data buoy. ## Details Additional Information * Frequency: 1 minute * Language: English Categories * Surface Platforms * National Data Buoy Center station TPLM2 Instruments * ScinTec BLS450 * Davis Vantage Pro2 Temporal coverage * Begin datetime: 2020-01-01 00:00:00 * End datetime: 2022-07-14 00:00:00 Spatial coverage * Maximum (North) Latitude: 38.98 * Minimum (South) Latitude: 38.98 * Minimum (West) Longitude: -76.48 * Maximum (East) Longitude: -76.48 Primary contact information * author: Chris Jellen cjellen@microsoft.com

USNA-Cn2 (short-duration)

The USNA long-term scintillation study is a continuing effort to characterize and measure optical turbulence in the near-maritime boundary layer. ## Summary The field campaign utilized a ScinTec BLS450 scintillometer to characterize the strength of optical turbulence over a link approximately 3 [m] above the river’s surface between January 1\textsuperscript{st}, 2020, and July 26\textsuperscript{th}, 2023. This field campaign included a range of meteorological and oceanographic measurements from nearby NOAA, National Data Buoy Center (NDBC), and Academy weather stations. The short-duration dataset includes measured $C_n^2$ along with atmospheric and oceanographic parameters from a co-located NOAA COOPS observation station between June 1\textsuperscript{st}, 2021, and September 1\textsuperscript{st}, 2021. ## Details Additional information * Frequency: 6 minute * Language: English Categories * Surface Platforms * NOAA Coastal Observation Station 8575512 Instruments * ScinTec BLS450 * Davis Vantage Pro2 Temporal coverage * Begin datetime: 2021-06-01 00:00:00 * End datetime: 2021-09-01 00:00:00 Spatial coverage * Maximum (North) Latitude: 38.98 * Minimum (South) Latitude: 38.98 * Minimum (West) Longitude: -76.48 * Maximum (East) Longitude: -76.48 Primary contact information * author: Chris Jellen cjellen@microsoft.com

Beam-Level (5G) Time-Series Dataset

This dataset presents a novel, multi-variate time series specifically designed for advancing research in spatio-temporal forecasting. The primary goal of this dataset is to facilitate the accurate prediction of traffic throughput volumes across 5G communication networks.

Monopedal Gaits

The dataset comprises time-series data capturing distinct periodic motions (gaits) of an energetically conservative one-legged hopper. Due to energy conservation, all gaits form a continuous one-dimensional family and undergo bifurcations as the internal energy varies, leading to different motion patterns such as in-place hopping, forward hopping, and backward hopping. The dataset is intended to advance surrogate modeling techniques for bifurcation analysis in hybrid dynamical systems, a complex class of models that represent non-smooth dynamic behaviors. The corresponding paper, discussing the system and how the data is generated, can be found in: Connecting Gaits in Energetically Conservative Legged Systems.

PJM(AEP)

PJM Hourly Energy Consumption Data PJM Interconnection LLC (PJM) is a regional transmission organization (RTO) in the United States. It is part of the Eastern Interconnection grid operating an electric transmission system serving all or parts of Delaware, Illinois, Indiana, Kentucky, Maryland, Michigan, New Jersey, North Carolina, Ohio, Pennsylvania, Tennessee, Virginia, West Virginia, and the District of Columbia. The hourly power consumption data comes from PJM's website and are in megawatts (MW). The regions have changed over the years so data may only appear for certain dates per region.

SMCOVID19-CT

We present a real data analysis of a CT experiment that was conducted in Italy for 8 months and involved more than 100,000 CT app users. SM-Covid-19 uses a NO-SQL data storage system to ensure scalability and performance. At regular intervals, SM-Covid-19 backend generates a complete dump of the dataset. The dump is converted into a relational database stored into a CSV formatted file to allow the open data to be easy to consult and process. The CSV file is structured as follows: PID1 and PID2 fields are pre-processed via SHA256 hash with a seed stored into the SoftMining backend system. The CSV is finally cleaned to remove duplicates. • Date of the contact (dd/MM/YYYY) • Time of the contact (HH:MM:SS) • PID1 (256-bit hex) • PID2 (256-bit hex) • Contact duration (Integer, in seconds) Contact distance (Float, in meters)

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.