Loading...
Loading...
Traffic data, public transit, aviation, shipping, ride-hailing, accident records
9,546 datasets
Yağmur Özinal Avşar proposes a novel machine learning method, Embedding-XGBoost (E-XGB), for classifying traffic crash types. The model was trained and tested on 10 years of crash data from central districts in İzmir, Türkiye, specifically Bornova, Karşıyaka, and Konak. The method achieved an accuracy of 85.42% using only 10 selected features and outperformed several benchmark algorithms.
Geoscience Australia's Australian Maritime Boundaries (AMB) 2020 data is a digital representation of Australia's maritime zones. The data includes territorial baselines, outer limits, and international treaty boundaries, covering waters adjacent to the mainland, offshore islands, and External Territories. It was published in December 2020 in consultation with other Commonwealth agencies.
Approximately 20,000 crash locations on New South Wales State highways and freeways were mapped using the Australian Map Grid over a two and a half year period. The data identified 20 rural sites with high crash frequency, defined as 200-meter road segments. This report was produced by the NSW Government.
Geoscience Australia's Australian Maritime Boundaries (AMB) data is a digital representation of Australia's maritime limits and zones. The dataset includes territorial baselines, outer limits of maritime zones, and boundaries from treaties with neighboring countries, covering waters adjacent to the mainland, offshore islands, and External Territories. This version, updated in May 2014, incorporates technical amendments based on user feedback and is published in consultation with other Commonwealth agencies.
Australia's maritime jurisdiction, including external territories, is represented in this geospatial dataset. Geoscience Australia developed the data, which shows territorial straight baselines, outer limits of maritime zones, and international treaty boundaries. The dataset currency is August 2019 and it reflects updates from the 2018 Timor Sea Treaty.
Geoscience Australia's digital representation of Australia's maritime limits and boundaries as established under the Seas and Submerged Lands Act 1973. The data includes territorial baselines, outer limits of maritime zones, and boundaries from treaties with neighboring countries, covering waters from 7°S to 70°S and 40°E to 175°E. This 2014 version incorporates technical amendments based on user feedback and is published in consultation with other Commonwealth agencies.
Penalty Charge Notice (PCN) transactional records from the London Borough of Camden's parking management system for the 2019-20 period. The data includes notices issued by Civil Enforcement Officers on-street and via CCTV, with attribution for contravention code, ticket type, street, parking restriction, vehicle category, and case status. A 'Spatial Accuracy' column indicates the source of location data, which may be GPS from an officer's device, a fixed CCTV camera location, or unknown.
A research dataset accompanies a paper on mitigating posterior collapse in hierarchical variational autoencoders. The data likely contains training metrics, model configurations, and experimental results from the University of Amsterdam. The paper proposes a spectral smoothing technique and analyzes phase transitions in the VAE loss.
A historical case series of 2,096 reported tuberculosis cases in indigenous children and adolescents in Brazil from 2006 to 2016. The data includes clinical and sociodemographic characteristics, treatment outcomes, and factors associated with dropout and death. The study was authored by Paulo Victor de Sousa Viana and uses multinomial logistic regression to analyze the data.
Large Urban Regions (LURs) are constructed as aggregations of continuous statistical units around an economic core to facilitate national and global city comparisons. The delineation uses four principal urban concepts: local administrative units (MUNI), Morphological Urban Areas (MUA), Functional Urban Areas (FUA), and the resulting LURs. Implementation criteria likely include population distribution, road networks, airport access, distance from a core, and the presence of multinational firms.
Digital orthophotos document forest areas affected by bark beetle infestation in the Gesäuse region. The imagery has a 20-centimeter ground resolution and is available in both RGB and color-infrared (CIR) formats. The dataset is provided under a CC-BY-4.0 license by a cooperation of OGD Österreich and Wikimedia Österreich.
399 randomly sampled accident records from a total of 143,262 occurrences at a hospital emergency service in Maceió, Brazil, in 2009. Gisetti Corina Gomes Brandão authored this exploratory study using secondary data from the Ministry of Health. The sample reveals that 76.19% of victims were men, with the highest incidence of accidents occurring in the afternoon and evening.
TAU Urban Acoustic Scenes 2019 evaluation dataset consists of 10-second audio segments from 10 distinct acoustic scenes in urban environments. The dataset contains a total of 20 hours of audio. It was created by Toni Heittola of Tampere University.
Tampere University's development dataset contains 40 hours of 10-second audio segments. The audio is organized into 10 distinct acoustic scenes common in urban environments, such as airports, metro stations, and parks. Each scene includes 1440 segments, totaling 240 minutes of audio per scene.
40 hours of audio from 10 distinct urban acoustic scenes, each represented by 1440 ten-second segments. The development dataset, created by Toni Heittola of Tampere University, supports research in environmental sound classification. It includes scenes such as airports, metro stations, pedestrian streets, and urban parks.
8640 ten-second audio segments capture 10 distinct urban acoustic scenes, totaling 24 hours of audio. Each scene, such as airport, shopping mall, and various transportation modes, is represented by 864 segments (144 minutes). The dataset is designed for developing and benchmarking machine listening models in urban environments.
Phase II of a three-phase effort collected approximately 2,000,000 vehicle miles and almost 43,000 hours of naturalistic driving data over 12 to 14 months per vehicle. The study, sponsored by the National Highway Traffic Safety Administration and the Virginia Department of Transportation, involved 241 primary and secondary drivers using instrumented vehicles, 78 of which were privately owned. The resulting database contains video and sensor data on extreme driving behaviors, crashes, near-crashes, and incidents, classified into an epidemiological-style event database.
An overview of official meeting zones in Vienna, which are traffic-relaxed areas where driving is only permitted for through traffic. The dataset likely contains the locations and speed limits for these zones. It is provided by Cooperation OGD Österreich and Wikimedia Österreich under a CC-BY-4.0 license.
Sawera Qureshi's dataset contains a 5-fold cross-validation configuration for classifying aviation safety occurrence reports. The underlying data comprises 53,770 aviation occurrence summaries from the Transportation Safety Board of Canada, spanning an 80-year period. The dataset was last updated on 2026-05-21.
53,770 aviation occurrence summaries from the Transportation Safety Board of Canada, spanning an 80-year period. The dataset was used to train and evaluate machine learning classifiers for automated report triage. It was authored by Sawera Qureshi and last updated on 2026-05-21.