A multilabel classification approach for complex human activities using a combination of emerging patterns and fuzzy sets

Abstract

In our daily lives, humans perform different Activities of Daily Living (ADL), such as cooking, and studying. According to the nature of humans, they perform these activities in a sequential/simple or an overlapping/complex scenario. Many research attempts addressed simple activity recognition, but complex activity recognition is still a challenging issue. Recognition of complex activities is a multilabel classification problem, such that a test instance is assigned to a multiple overlapping activities. Existing data-driven techniques for complex activity recognition can recognize a maximum number of two overlapping activities and require a training dataset of complex (i.e. multilabel) activities. In this paper, we propose a multilabel classification approach for complex activity recognition using a combination of Emerging Patterns and Fuzzy Sets. In our approach, we require a training dataset of only simple (i.e. single-label) activities. First, we use a pattern mining technique to extract discriminative features called Strong Jumping Emerging Patterns (SJEPs) that exclusively represent each activity. Then, our scoring function takes SJEPs and fuzzy membership values of incoming sensor data and outputs the activity label(s). We validate our approach using two different dataset. Experimental results demonstrate the efficiency and superiority of our approach against other approaches.

Activity recognition based on spatio-temporal features with transfer learning

“…Sakr et al [16] highlight that while primary activity recognition has been explored extensively, intricate activity recognition remains challenging [17]. Recognizing complex activities involves multilabel classification [18], where a single test instance is categorized into multiple concurrent activities.…”

Analysis of Covid 19 Data in Indonesia Using Supervised Emerging Patterns

“…Data preparation consists of all activities to build a database that will be entered into the modeling tool from the initial raw data or create a new database for data mining setup. Data preparation includes all activities to build data sets that will be processed in the modeling process using the Jumping Emerging Pattern (JEP) algorithm to extract information [9].…”

A review of wearable sensors based monitoring with daily physical activity to manage type 2 diabetes

“…Wearable devices [51] are now highly used for human activity recognition [52]. They are used as a predictor for any abnormal health cases [53,54].…”