This dataset represents sensor events collected in the CASAS smart apartment testbed at Washington State University. Data are collected for 26 pairs of participants, 52 participants in total. Each file represents two participants, Person A and Person B, in the apartment at the same time performing fifteen ADL activities. Some activities are performed separately but in parallel, others are collaborative between the two people. Thisresource is valuable for designing and validating activity recognition algorithms for data collected in realistic settings where multiple residents live in a smart home. Note: Other CASAS smart home and smartwatch datasets are also available, look for more at https://zenodo.org/communities/casas. The tasks are: Fill medication dispenser in the kitchen using items obtained from the cabinet. Return items to the cabinet when done. (Person A) Hang up clothes in the hallway closet. The clothes are laid out on the couch in the living room. (Person B) Move the couch and coffee table to the other side of the living room. (Person B)Request help from Person A (Person A will stop dispenser task to help and finish dispenser task when done with this task) Sit on the couch and read a magazine. (Person B) Water plants located around the apartment. Use the watering can located in the hallway closet. Return the watering can to the closet when finished. (Person A) Sweep the kitchen floor using the broom and dust pan located in the kitchen closet. Return the tools to the closet when finished. (Person B) Play a game of checkers for a maximum of five minutes. (Persons A and B) Set out ingredients for dinner in the kitchen. (Person A) Set dining room table for dinner. (Person B) Read a magazine on the living room couch. (Person A) Simulate paying an electric bill. Retrieve a check, a pen, and an envelope from the cupboard underneath the television in the living room. Use the telephone book in the dining room to look up a number for a utility company to confirm the amount on the bill. (Person B) Request help from Person A to find number for utility company (Person A will stop current task to help and finish task when done helping) Gather food for a picnic from the kitchen cupboard and pack them in a picnic basket. (Person A) Retrieve dishes from a kitchen cabinet. (Person B) Request help from Person A to identify cabinet in which the dishes are located. (Person A will stop current task to help and finish task when done helping) Pack supplies in the picnic basket. (Person B) Pack food in the picnic basket and bring the basket to the front door of the apartment. (Person A) The files are named according to the participant pair number. There is one sensor reading in each row. The columns represent the date, time, sensor, message, task number for Person A, and task number for Person B. A floorplan of the smart apartment is provided in Chinook.png, together with the locations of the sensors. A zoomed-in look at the Chinook cabinet with sensors is provided in Chinook_Cabinet.png. The sensors are categorized (and named) as: M01 - M51: PIR motion detectors, reporting ON when detected motion starts and OFF when it stops I01 - I08: item use sensors for (in order) oatmeal, raisins, brown sugar, bowl, measuring spoon, medicine container, pot, phone book (present or absent indicating item is on sensor or not) D01 - D12: door sensors on cabinets (open or close) AD1-A and AD1-B: water sensors for kitchen sink (value indicates level) AD1-C: burner sensor (value indicates level) P01: phone use sensor T01 - T03: temperature sensors

Citation: Please cite the following paper when using this dataset:Singla, G., Cook, D. & Schmitter-Edgecombe, M. (2009). Recognizing independent and joint activities among multiple residents in smart environments. Ambient Intelligence and Humanized Computing Journal, 1(1):57-63. doi: 10.1007/s12652-009-0007-1