The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition

Abstract

There is a growing interest on using ambient and wearable sensors for human activity recognition, fostered by several application domains and wider availability of sensing technologies. This has triggered increasing attention on the development of robust machine learning techniques that exploits multimodal sensor setups. However, unlike other applications, there are no established benchmarking problems for this field. As a matter of fact, methods are usually tested on custom datasets acquired in very specific experimental setups. Furthermore, data is seldom shared between different groups. Our goal is to address this issue by introducing a versatile human activity dataset recorded in a sensor-rich environment. This database was the basis of an open challenge on activity recognition. We report here the outcome of this challenge, as well as baseline performance using different classification techniques. We expect this benchmarking database will motivate other researchers to replicate and outperform the presented results, thus contributing to further advances in the state-of-the-art of activity recognition methods.

Feature extraction for robust physical activity recognition

“…The proposed system has been also evaluated with another public dataset (OPPOR-TUNITY dataset) demonstrating competitive results (compared to previous work [31]) in two main tasks for home care monitoring: high-level locomotion and mid-level gesture classification. …”

“…The on-body sensors include 7 multi-sensor inertial measurement units with another 12 3D acceleration sensors: 145 signals in total. Since only body-worn sensors are concerned in the evaluation section of the original paper [31], the data from object and ambient sensors are truncated in the following experiments. In terms of activities or classes, this dataset has 3 different sets: 4 types of locomotion (high-level activities); 17 types of gesture (mid-level actions); and low-level actions to objects (which is ignored in this work).…”

“…We retrain and evaluate our system using the same experimental setting as in the original paper [31]: using ADL2 and ADL3 from one subject as the testing set and use Drill, ADL1, ADL4 and ADL5 from the same subject as the training set. We conduct experiments in this configuration for all four subjects and in the two tasks: high-level locomotion (Table 7) and mid-level gestures (Table 8).…”

Robust activity recognition combining anomaly detection and classifier retraining

“…We selected five runs of each subject (tagged ADL1-ADL5) and each run is approximately 20 minutes. The data are publicly available and were also used for a challenge at the SMC 2012 conference [15]. Out of the pool of sensors available in the dataset, we used eight triaxial accelerometers (the sensor setup and abbreviations are shown in Fig.…”

On-line anomaly detection and resilience in classifier ensembles

“…The second dataset, named Opportunity dataset, comprises sensory data of different modalities in a breakfast scenario. The database is fully described by Chavarriaga et al (2013b) and is publicly available as a benchmark for HAR methods.…”