A Novel Functional Link Network Stacking Ensemble with Fractal Features for Multichannel Fall Detection

Abstract

Falls are a major health concern and result in high morbidity and mortality rates in older adults with high costs to health services. Automatic fall classification and detection systems can provide early detection of falls and timely medical aid. This paper proposes a novel Random Vector Functional Link (RVFL) stacking ensemble classifier with fractal features for classification of falls. The fractal Hurst exponent is used as a representative of fractal dimensionality for capturing irregularity of accelerometer signals for falls and other activities of daily life. The generalised Hurst exponents along with wavelet transform coefficients are leveraged as input feature space for a novel stacking ensemble of RVFLs composed with an RVFL neural network meta-learner. Novel fast selection criteria are presented for base classifiers founded on the proposed diversity indicator, obtained from the overall performance values during the training phase. The proposed features and the stacking ensemble provide the highest classification accuracy of 95.71% compared with other machine learning techniques, such as Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine. The proposed ensemble classifier is 2.3× faster than a single Decision Tree and achieves the highest speedup in training time of 317.7× and 198.56× compared with a highly optimised ANN and RF ensemble, respectively. The significant improvements in training times of the order of 100× and high accuracy demonstrate that the proposed RVFL ensemble is a prime candidate for real-time, embedded wearable device–based fall detection systems.

Random vector functional link network: recent developments, applications, and future directions

“…Stacking refers to training a meta-learner that works on the outputs from all base learners. In [132], a meta-RVFL is trained to combine the results from all the base RVFL networks with different activation functions. In [133], an individual RVFL network is trained to forecast each sub-series generated by the decomposition, and an incremental RVFL is introduced to aggregate all forecasts.…”

A novel context-aware multimodal framework for persian sentiment analysis

“…In the literature, extensive research has been carried out to develop multimodal models, that demonstrate the significance of multimodal processing over unimodal approaches. Researchers have proposed multimodal processing architectures for a wide range of real-world applications ranging from sentiment analysis [29,30,31,32,33,34,35,36], deception detection [37] to dementia diagnosis and progression prediction [38] and audio-visual speech recognition and enhancement [39,40,41,42].…”