Activity Images for Human Activity Recognition

Reference

Deep Human Activity Recognition with Localisation of Wearable Sensors

IA. Lawal and S. Bano, IEEE Access, (In press).

Dataset Description

The dataset consists of frequency (activity) images generated from the raw tri-axial accelerometer and gyroscope signal for different human activities (walking, running, standing, laying, climbing and jumping) from seven different on-body locations including head, chest, arm, shin, waist, wrist and thigh. Each sample is a three-channel image of size 28×28×3.

Click here to download this dataset and implementation code

 

HSDPA Network Traffic Dataset

Reference

Improving HSDPA Traffic Forecasting Using Ensemble of Neural Networks

IA. Lawal, SA. Abdulkarim, MK. Hassan and JM. Sadiq, IEEE International Conference on Machine Learning and Applications, 2016.

Dataset Description

The dataset consists of 44160 data points representing the hourly measurement of HSDPA traffic from 60 different cell sites of a Nigerian UMTS-based cellular operator. The hourly records include the value of the down-link traffic in Megabyte (MB), site ID of the measurement location and the time when the recording was made.

Click here to download this dataset