Skip to the beginning of the images gallery

Time Series Anomaly Detection with Isolation Forest

Lightweight anomaly detector for time series data using Isolation Forest, designed for edge environments.

$0.00

app details

Model Type

QCS6490, i.MX 8M Plus, MX93, MX95, Genio700, Titan 300

Framework

scikit-learn

Algorithm

Isolation Forest

Technical Details

Univariate time series model trained on historical energy data from the French market. Features include lagged values, rolling statistics, and temporal encodings. Deployed as a serialized .pkl file for scikit-learn-based inference on CPU environments.

Use Cases

Forecasting and Operational Optimization

Supported IoT Devices

AI optimized hardware Fanless embedded PCs Modules

supported chipsets

Intel® Core™ i3 Qualcomm® Dragonwing QCS6490 Qualcomm® Dragonwing QCS5430 NXP i.MX 8M Plus NXP i.MX 95

Performance Benchmark

Hardware

Latency (ms)

Memory Usage

Processing unit

SECO SOM-SMARC-QCS6490

310.07 ms

11.59 MB

CPU

SECO SOM-SMARC-iMX8Plus

2407 ms

11.59 MB

CPU

SECO SOM-SMARC-MX95

1675 ms

11.59 MB

CPU

SECO Titan 300 TGL-UP3 AI

195.16 ms

11.59 MB

CPU

SECO SOM-SMARC-iMX8Plus

2425 ms

11.59 MB

NPU

Time Series Anomaly Detection with Isolation Forest

Leave your message here

Related models