Abstract
Human Activity Recognition has been a dynamic research area in recent years. Various methods of collecting data and analyzing them to detect activity have been well investigated. Some machine learning algorithms have shown excellent performance in activity recognition, based on which many applications and systems are being developed. Unlike this, the prediction of the next activity is an emerging field of study. This work proposes a conceptual model that uses machine learning algorithms to detect activity from sensor data and predict the next activity from the previously seen activity sequence. We created our activity recognition dataset and used six machine learning algorithms to evaluate the recognition task. We have proposed a method for the next activity prediction from the sequence of activities by converting a sequence prediction problem into a supervised learning problem using the windowing technique. Three classification algorithms were used to evaluate the next activity prediction task. Gradient Boosting performs best for activity recognition, yielding 87.8% accuracy for the next activity prediction over a 16-day timeframe. We have also measured the performance of an LSTM sequence prediction model for predicting the next activity, where the optimum accuracy is 70.90%.
Highlights
Rapid advancement in machine learning addresses a significant area of research, recognition, and human activity prediction
We propose to record data from a wrist wearable device because wrists are engaged in most activities in daily life, and the position is ideal for collecting data for activity recognition purposes [5]
We have investigated six machine learning algorithms: Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting (GB) to recognize activities
Summary
Rapid advancement in machine learning addresses a significant area of research, recognition, and human activity prediction. A system that recognizes activity and stores activity information (e.g., activity name, timestamp, etc.) can be used for activity prediction For activity recognition, it requires data for training a machine learning model. Our work includes data collection using a wearable device to build a recognition model to recognize the activity. We intend to collect data from sensors positioned at the wrist, recognize activity and predict the possible activity of a specific user in the nearest future by implementing machine learning models. The study schemes to propose a model to recognize human activity from the data collected by the sensors of a wristwearable device and predict the possible activity from the sequence of previous activities.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have