Back to the App List

Time Series Anomaly Detection with Isolation Forest

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

$0.00
More Information
Time Series Anomaly Detection with Isolation Forest
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

Related models