Predicting Sensor Events, Activities, and Time of Occurrence Using Binary Sensor Data From Homes With Older Adults

Abstract

We present a comprehensive study of state-of-the-art algorithms for the prediction of sensor events and activities of daily living in smart homes. Data have been collected from eight smart homes with real users and 13-17 binary sensors each-including motion, magnetic, and power sensors. We apply two probabilistic methods, namely Sequence Prediction via Enhanced Episode Discovery and Active LeZi, as well as Long Short-Term Memory Recurrent Neural Network, in order to predict the next sensor event in a sequence. We compare these with respect to the required number of preceding sensor events to predict the next, the necessary amount of data to achieve good accuracy and convergence, as well as varying the number of sensors in the dataset. The best-performing method is further improved by including information on the time of occurrence to predict the next sensor event only, and in addition to predict both the next sensor event and the mean time of occurrence in the same model. Subsequently, we apply transfer learning across apartments to investigate its applicability, advantages, and limitations for this setup. Our best implementation achieved an accuracy of 77-87% for predicting the next sensor event, and an accuracy of 73-83% when predicting both the next sensor event and the mean time elapsed to the next sensor event. Finally, we investigate the performance of predicting daily living activities derived from the sensor events. We can predict activities with an accuracy of 61-90%, depending on the apartment. INDEX TERMS Binary sensor, probabilistic method, recurrent neural network, sequence and time prediction, transfer learning.

Involving older adults in technology research and development discussions through dialogue cafés

“…Eight residents were recruited to the trial. The results from this study are presented in another paper [ 46 ].…”

“…Assistive technologies are new digital solutions that may include new, portable communication platforms in the community health services at home, tablets for communication in assisted living facilities, monitoring devices to be used at home, etc. (for a full list, see the literature review in Forsberg et al 2020 [ 7 ]. Research and technology related to such a digital transformation, including changes at the organisational level within the health care and business sectors, and at the individual level [ 8 ], are therefore currently of high priority.…”

“…For more information about the design of the project and results, see also Zouganeli et al2017 [ 34 ]. Holthe et al [ 16 , 35 , 36 ], Casagrande [ 7 ], Holthe [ 12 ] and Thorstensen [ 37 ].…”

A Multi-task Learning Model for Daily Activity Forecast in Smart Home

“…Since the time forecast relied heavily on the activity label predicted in the previous step, error propagation easily occured [15]. The combination of LSTM and k-means was used to solve the prediction problem of the next sensor event, but they were essentially independent models for sensor and trigger time forecast [31]. To our best knowledge, all of prior forecast strategies dealt with a certain forecast task independently without the parallel training of the two tasks.…”

Binary Sensors-Based Privacy-Preserved Activity Recognition of Elderly Living Alone Using an RNN

“…Various indoor activity detection models have been proposed [ 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 ], most of which use ML to recognize the activities. As stated in [ 74 ], deep learning and RNN models have promising results and need to be investigated further for non-intrusive activity recognition.…”