22 Complex fine-grained activity contexts (i) Locomotive (walk indoors and run indoors); (ii) semantic (use refrigerator, clean utensil, cooking, sit and eat, use bathroom sink, standing, and talking); (iii) transitional (indoor to outdoor, outdoor to indoor, walk upstairs, and walk downstairs); and (iv) postural/relatively stationary (just stand, stand and lean on wall, lying on bed, sit on bed, sit on desk chair, lying on floor, sit on floor, lying on sofa, sit on sofa, and sit on commode).
2 two separate home environments. User 1: 22 activities, user 2: 19 activities. Every user’s series of selected activities consisted of an average of 45 minutes of sensor data collection.
3 triaxial acceleration data in the dataset of Activity Recognition Challenge [16], 5.5 seconds. 300,000 records or 2300 windows (window length is 128) for each wrist of a subject.
3 (friends and family), age (26, 24, and 44) Big data: 176 minutes of sampled data, 10,560 seconds of raw data, and electroencephalogram with 5 million lines