> ## Documentation Index > Fetch the complete documentation index at: https://docs.edgeimpulse.com/llms.txt > Use this file to discover all available pages before exploring further. # Multi-label The multi-label feature brings considerable value by preserving the context of longer data samples, simplifying data preparation, and enabling more efficient and effective data analysis. The first improvement is in the way you can analyze and process complex datasets, especially for applications where context and continuity are crucial. With this feature, you can maintain the integrity of longer-duration samples, such as hour-long exercise sessions or night-long sleep studies, without the need to segment these into smaller fragments every time there is a change in activity. This holistic view not only preserves the context but also provides a richer data set for analysis. Then, the ability to select window sizes directly in Edge Impulse addresses a common pain point - data duplication. Without the multi-label feature, you need to pre-process data, either externally or using [transformation jobs](/studio/organizations/custom-blocks/custom-transformation-blocks), creating multiple copies of the same data with different window sizes to determine the optimal configuration. This process is not only time-consuming but also prone to errors and inefficiencies. With multi-label samples, adjusting the window size becomes a simple parameter change in the "[Impulse design](/studio/projects/impulse-design)", streamlining the process significantly. This flexibility saves time, reduces the risk of errors, and allows for more dynamic experimentation with data, leading to potentially more accurate and insightful models.

## Detecting key events in multi-label samples When working with time-series data labeled using the multi-label format, detecting short-duration or critical events (e.g. tamper detection, fall detection or short noises among others) is possible. Edge Impulse provides flexible strategies for assigning labels to windows of data during training and inference to ensure the events represented. During the data acquisition process, it's important to understand the available labeling strategies. Choosing the right approach for handling multi-label events ensure accurate detections. The labeling strategies are selected when designing your impulse in the [Create Impulse](/studio/projects/impulse-design) screen. You need to define your appropriate strategy to detect multi-label events in your data.

## Choosing your window labeling strategy * [Use label at the end of the window](#use-label-at-the-end-of-the-window) for transitions and state-based classification. * [Use label X if anywhere present in the window](#use-label-x-if-anywhere-present-in-the-window) for rare, short, or safety-critical events. * [Use label X if at least Y% of window](#use-label-x-if-at-least-y-of-window) when an event should be present for a minimum duration before it wins the label. * [Use majority label in window](#use-majority-label-in-window) when the dominant activity inside the window is the best training target. ### Use label at the end of the window This strategy assigns the label that is active at the end of each window as the label for the entire window. It works well for scenarios where the primary interest lies in the resulting state or activity of the window such as recognizing sustained motions or transitions. If a sample transitions from `idle` to `running` within a window, and the last timestamp in the window corresponds to `running`, the window will be labeled as `running`. ### Use label X if anywhere present in the window This strategy assigns a label to the window if a specific event label is present anywhere within the windows' duration (e.g. `tamper`, `fall`, etc). It is particularly useful for detecting short or sparse events that may not occupy the full window but are critical to capture when they occur. With this option, you can configure which label(s) to prioritize. If the selected label is found within any part of the window, the window will be assigned to that label, even if the short event occurs alongside other labels.

This approach ensures better coverage for rare or time-sensitive events and improves the model sensitivity to important transitions or anomalies. If multiple selected labels appear within the same window, the label with the highest number of occurrences is assigned to that window. If none of the selected labels are found, Edge Impulse defaults to using the label at the end of the window. ### Use label X if at least Y% of window This strategy is useful when an event should occupy a meaningful portion of the window before it overrides the surrounding context. You choose the label or labels to monitor, then set a minimum percentage threshold for how much of the window one of those labels must cover. For example, if you monitor `fall` with a threshold of `30%`, a window is only labeled as `fall` if at least 30% of the window duration is labeled `fall`. This helps avoid assigning the event label to windows where it only appears as a very short blip. Use this mode when short label flickers are common, or when a rare event should be present long enough to be considered meaningful for training. ### Use majority label in window This strategy assigns the label that occupies the largest portion of the window. It is useful when you want each window to represent the dominant activity rather than the final state or a prioritized short event. For example, if most of a window is labeled `walking` and the final part is labeled `standing`, the window is labeled `walking` as long as `walking` covers the largest share of the samples in that window. Use this mode when labels can change within a window but the dominant label is the most meaningful training target. ## Uploading multi-label samples ### With the CSV Wizard If your dataset is in the CSV format and contains a label column, the [CSV Wizard](/studio/projects/data-acquisition/csv-wizard) is probably the easiest method to import your multi-label data. For example: ``` seconds_elapsed, accX, accY, accZ, label 0.00, 0.14642,-0.01645,-0.00858,idle 0.16, 0.15051,-0.01149,-0.00345,idle 0.32, 0.15546,-0.02141,-0.00342,idle ... 20.48, 0.14347,-0.03758,-0.00369,running 20.56, 0.13447,-0.01657,-0.01520,running 20.72, 0.11453,-0.00961,-0.01021,running ```

Once your CSV Wizard is configured, you can use the [Studio Uploader](/studio/projects/data-acquisition/uploader), the [CLI Uploader](/tools/clis/edge-impulse-cli/uploader) or the [Ingestion API](/apis/ingestion): ### With the Edge Impulse `info.labels` description file The other way is to create an `info.labels` file for your dataset. Edge Impulse will automatically detect this file when you upload your dataset and will use it to set the labels. The `info.labels` file is a JSON file that contains the metadata of your dataset, including the labels. See the [File example](/tools/specifications/data-annotation/ei-labels#file-example) section in the [Edge Impulse labels](/tools/specifications/data-annotation/ei-labels) documentation for more details on the file structure. Ensure you click on the "multi-label" tab when viewing the file examples. **Tip:** you can export a public project dataset that uses the multi-label feature to understand how the `info.labels` is structured. Check the [Additional resources](/studio/projects/data-acquisition/multi-label#additional-resources) section for an example multi-label public project. Once you have your `info.labels` file available, to upload it, you can either use the Studio uploader or the CLI uploader. #### Using the Studio uploader The Studio Uploader will automatically detect the `info.labels` file:

#### Using the CLI Uploader ``` > edge-impulse-uploader * --info-file info.labels Edge Impulse uploader v1.23.0 Endpoints: API: https://studio.edgeimpulse.com Ingestion: https://ingestion.edgeimpulse.com Upload configuration: Label: Not set, will be inferred from file name Category: training Project: Example Multi-label upload (ID: XXXXX) [ 1/11] Uploading training/machine_multilabel_8.json OK (1589 ms) [ 2/11] Uploading testing/machine_multilabel_3.json OK (2024 ms) [ 3/11] Uploading training/machine_multilabel_6.json OK (2176 ms) [ 4/11] Uploading training/machine_multilabel_2.json OK (2224 ms) [ 5/11] Uploading testing/machine_multilabel_1.json OK (2394 ms) [ 6/11] Uploading training/machine_multilabel_8.json OK (2395 ms) [ 7/11] Uploading training/machine_multilabel_9.json OK (2485 ms) [ 8/11] Uploading training/machine_multilabel_7.json OK (2603 ms) [ 9/11] Uploading testing/machine_multilabel_4.json OK (2617 ms) [10/11] Uploading training/machine_multilabel_11.json OK (3426 ms) [11/11] Uploading training/machine_multilabel_10.json OK (3488 ms) Done. Files uploaded successful: 11. Files that failed to upload: 0. ``` ### With the Edge Impulse `structured_labels.labels` description file If you want to use the [Ingestion API](/apis/ingestion), you will need to use the `structured_labels.labels` format. The `structured_labels.labels` file is a JSON file that contains the metadata of your dataset, including the labels. See the [File example](/tools/specifications/data-annotation/ei-structured-labels#file-example) section in the [Edge Impulse structured labels](/tools/specifications/data-annotation/ei-structured-labels) documentation for more details on the file structure. After creating a structured labels file, you can run the following command: ``` curl -X POST \ -H "x-api-key: $EI_PROJECT_API_KEY" \ -H "Content-Type: multipart/form-data" \ -F "data=@updown.3.json" \ -F "data=@structured_labels.labels" \ https://ingestion.edgeimpulse.com/api/training/files ``` You can have a look at this tutorial for a better understanding: [Ingest multi-label data with Edge Impulse API](/tutorials/tools/apis/ingestion/ingest-structured-label-data). ## Visualizing multi-label samples

Please note that you can also hide the sensors in the graph:

## Editing multi-label samples To edit the labels using the UI, click **⋮** -> **Edit labels**. The following model will appear:

Please note that you will need to provide continuous and non-overlapping labels for the full length of your data sample. The format is the like following: ``` [ { "label": "label 1", "startMs": 0, "endMs": 2000 }, { "label": "label 2", "startMs": 2001, "endMs": 4000 }, { "label": "label 3", "startMs": 4001, "endMs": 4500 } ] ``` ## Classifying multi-label data In the **Live classification** tab, you can classify your multi-label test samples:

## Limitations * Labeling UI is available but is only text-based. * Overlapping labels are not supported * The entire data sample needs to have a label, you cannot leave parts unlabeled. Please, leave us a note on the forum or feedback using the **"?"** widget (bottom-right corner) if you see a need or an issue. This can help us prioritize the development or improvement of the features. ## Additional resources * [Edge Impulse labels](/tools/specifications/data-annotation/ei-labels) * [Edge Impulse structured labels](/tools/specifications/data-annotation/ei-structured-labels) * [Coffee Machine Stages - Multi-label data](https://studio.edgeimpulse.com/public/315514/latest)