{
"fetched_at": "2026-10-19T09:50:20Z",
"source_url": "https://www.kaggle.com/competitions/IPM3211-City-Heat-Noise/data",
"pages": [
{
"name": "data-description",
"content": "## Cozie data\n\n| Field name | Type | Unit | Description |\n|---------------------------------|-----------|------|-------------|\n| `id_participant` | string | - | Unique identifier for each participant |\n| `id_unique` | string | - | Unique identifier for row |\n| `index` | timestamp | time |Timestamp (UTC) of when micro survey was submitted, also serves as index |\n| `q_activity_category_alone` | string | - | Response to watch survey question 'Category of activity? (alone)' |\n| `q_activity_category_group` | string | - | Response to watch survey question 'Category of activity? (group)' |\n| `q_alone_group` | string | - | Response to watch survey question 'Alone or in a group?' \n| `q_earphones` | string | - | Response to watch survey question 'Wearing earphones?' |\n| `q_location` | string | - | Response to watch survey question 'Where are you?' |\n| `q_location_office` | string | - | Response to watch survey question 'What kind of office' |\n| `q_location_transport` | string | - | Response to watch survey question 'What kind of transport?' |\n| `q_noise_kind` | string | - | Response to watch survey question 'What kind of noise?' |\n| `q_noise_nearby` | string | - | Response to watch survey question 'Noise distractions nearby? (without earphones)' |\n| `q_thermal_preference` | string | - | Response to watch survey question 'Thermally, what do you prefer now?' |\n| `ts_audio_exposure_environment` | float | dB(A)| Noise level, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/3081271-environmentalaudioexposure) |\n| `ts_heart_rate` | float | bpm | Heart rate, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/1615138-heartrate)|\n| `ts_oxygen_saturation` | float | % | Blood oxygen saturation provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/1615377-oxygensaturation) |\n| `ts_resting_heart_rate` | float | bpm | Resting heart rate, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/2867756-restingheartrate) |\n| `ts_stand_time` | float | min | Stand time, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/3174858-applestandtime) |\n| `ts_step_count` | float | steps | Number of steps walked, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/1615548-stepcount) |\n| `ts_walking_distance` | float | m | Distance walked, provided by [Apple HealthKit](https://developer.apple.com/documentation/healthkit/hkquantitytypeidentifier/1615230-distancewalkingrunning) |\n| `ws_latitude` | float | ° | Latitude |\n| `ws_longitude` | float | ° | Longitude |\n| `ws_survey_count` | float | - | Increasing counter for each micro-survey response. Resets when Cozie app is (re-)installed. |\n| `ws_timestamp_location` | datetime | time | Timestamp of the location measurement |\n| `ws_timestamp_start` | datetime | time | Timestamp of when micro survey was started |\n| `dT` | float | min | Duration between the current and the previous watch survey response in minutes |\n\n## Spatial Indicators\nThe spatial indicators (building morphology, population, point of interest) are only available for data points within Singapore.\nFor more information on the spatial indicators please refer to [Table 1](https://www.nature.com/articles/s41597-023-02578-1/tables/1) of [Yap, W., Biljecki, F. A Global Feature-Rich Network Dataset of Cities and Dashboard for Comprehensive Urban Analyses. Sci Data 10, 667 (2023). ](https://www.nature.com/articles/s41597-023-02578-1)\n\n\n| **Building Morphology** | | | |\n|-------------------------------|-------|-----|------------------------|\n| `Footprint Proportion` | float | % | Footprint proportion |\n| `Footprint Mean` | float | m2 | Mean area |\n| `Footprint Stdev` | float | m2 | Area standard deviation |\n| `Perimeter Total` | float | m | Total perimeter |\n| `Perimeter Mean` | float | m | Mean perimeter |\n| `Perimeter Stdev` | float | m | Perimeter standard deviation |\n| `Complexity Mean` | float | m | Complexity mean |\n| `Complexity Stdev` | float | m | Complexity standard deviation |\n| `Building Count` | float | count | No. of buildings |\n| **Population** | | | |\n| `PopSum` | float | count | Total Population | \n| `Men` | float | count | Male population | \n| `Women` | float | count | Female population | \n| `Elderly` | float | count | Elderly (aged 60+ years) population | \n| `Youth` | float | count | Young (15-24 years) population | \n| `Children` | float | count | Child (<5 years) population | \n| **Point of Interest** | | | |\n| `Civic` | float | count | Civic amenities |\n| `Commercial` | float | count | Commercial amenities |\n| `Entertainment` | float | count | Entertainment amenities |\n| `Food` | float | count | Food amenities |\n| `Healthcare` | float | count | Healthcare amenities |\n| `Institutional` | float | count | Institutional amenities |\n| `Recreational` | float | count | Recreational amenities |\n| `Social` | float | count | Social amenities |\n| `Green View Mean` | float | - | Green view index |\n| `Green View Stdev` | float | - | Green view index, standard deviation |\n| `Sky View Mean` | float | - | Sky view index |\n| `Sky View Stdev` | float | - | Sky view index, standard deviation |\n| `Building View Mean` | float | - | Building view index |\n| `Building View Stdev` | float | - | Building view index, standard deviation |\n| `Road View Mean` | float | - | Road view index |\n| `Road View Stdev` | float | - | Road view index, standard deviation |\n| `Visual Complexity Mean` | float | - | Visual complexity index |\n| `Visual Complexity Stdev` | float | - | Visual complexity index, standard deviation |\n\n\n## Weather data\n| Measurement | Unit | Accuracy |\n|-------------------------|------|------------|\n| Air temperature | °C | ±0.1°C |\n| Relative humidity | % | ±1% |\n| Rain fall | mm | 2% at 1 l/h (0.26 gal/h) |\n| Wind speed | knots | 0-35 m/s: ±0.3 m/s or ±3 % whichever is greater
35 m/s ... 60 m/s: ±5 % | \n| Wind direction | ° | ±3° |\n\nSource: [National Environment Agency (NEA) via data.gov.sg](https://beta.data.gov.sg/collections/1459/view)",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Description",
"content": "\n\nThe data collection process for this competition utilizes the open-source [Cozie Apple platform](https://cozie-apple.app/). This mobile and smartwatch application for iOS devices allows people to complete a watch-based micro-survey and provide real-time feedback about environmental conditions via their Apple Watch. It leverages the built-in sensors of the smartwatch to collect physiological (e.g., heart rate, activity), environmental (sound level), and location (latitude and longitude) data. The deployment for this work includes watch survey responses from 106 people, who each provided at least 100 micro-survey responses from October 2022 to August 2023. For each survey response location, digital-twin-created spatial indicators were calculated using the [Urbanity python package](https://github.com/winstonyym/urbanity).\n\nThe goal of the competition is to predict the values of the columns `q_noise_nearby`, `q_noise_kind`, `q_earphones`, `q_thermal_preference `as well as possible.",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "rules",
"content": "There are no rules for this competition as the score is less important that the submitted notebooks.",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Evaluation",
"content": "## Metric\nThe evaluation metric for this competition is *accuracy*. The metric is calculated as:\n\n$$accuracy = \\frac{TP+ TN}{TP+TN+FP+FN}$$\n\nWhere:\n\n- TP is *true positive*, positive cases predicted as positive\n- TN is *true negative*, negative cases predicted as negative\n- FP is *false positive*, negative cases predicted as positive\n- FN is *false negative*, positive cases predicted as negative\n- TP+TN+FP+FN is equivalent to the number of cases predicted\n\nAs we have four targets here (`q_noise_nearby`, `q_noise_kind`, `q_earphones`, `q_thermal_preference`), accuracy for each target column is calculated and the average of the four of them is returned.\n\n## Notebook Submissions\nYou can make submissions directly from Kaggle Notebooks. By adding your teammates as collaborators on a notebook, you can share and edit code privately with them.\n\n## Submission File\nFor each `id_unique` in the test set, you must predict the target variables: `q_noise_nearby`, `q_noise_kind`, `q_earphones`, `q_thermal_preference`. The file should contain a header and have the following format:\n\n```python\nid_unique,q_noise_nearby,q_noise_kind,q_earphones,q_thermal_preference\n1,None,Not applicable,Not applicable,Cooler\n2,A little,Appliances,No earphones,No change,Public\n3,A little,Talking,No earphones,Cooler\n```",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Useful Links",
"content": "## Tutorials for this Data/Competition\n- [Base Model Development and Analysis Example](https://www.kaggle.com/code/mariofrei/ipm3211-base-analysis-and-model-example)\n- [ML Model Tuning Example](https://www.kaggle.com/code/ponybiam/ipm3211-ml-tuning-and-feature-engineering)\n- [Data Visualization Example](https://www.kaggle.com/code/mariofrei/ipm3211-visualization)\n\n## General ML Tutorials (from edX Section 4)\n- [Preprocessing pt. 1: data transformation](https://www.kaggle.com/ponybiam/preprocessing-pt-1-data-transformation)\n- [Preprocessing pt. 2: encoding categorical variables](https://www.kaggle.com/ponybiam/preprocessing-pt-2-encoding-categorical-variable/)\n- [Preprocessing pt. 3: handling missing values](https://www.kaggle.com/ponybiam/preprocessing-pt-3-handling-missing-values)\n- [Feature engineering pt. 1: simple features](https://www.kaggle.com/code/ponybiam/feature-engineering-1-simple-features/notebook)\n- [Feature engineering pt. 2: clustering & PCA](https://www.kaggle.com/ponybiam/feature-engineering-pt-2-clustering-pca)\n- [Feature engineering pt. 3: target encoding](https://www.kaggle.com/ponybiam/feature-engineering-pt-3-target-encoding)\n\n## Kaggle courses\n- [Python](https://www.kaggle.com/learn/python)\n- [Pandas](https://www.kaggle.com/learn/pandas)\n- [Intermediate machine learning](https://www.kaggle.com/learn/intermediate-machine-learning)\n- [Feature Engineering](https://www.kaggle.com/learn/feature-engineering)[[",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
},
{
"name": "Acknowledgments",
"content": "[Abstract vector created by upklyak - www.freepik.com](https://www.freepik.com/vectors/abstract)",
"isPublished": false,
"hasIsPublished": false,
"postTitle": "",
"hasPostTitle": false,
"mimeType": "",
"hasMimeType": false
}
]
}