This paper presents a cost-effective, low-power approach to unintentional fall detection using knowledge distillation-based LSTM (Long Short-Term Memory) models to significantly improve accuracy.
Existing action recognition methods mainly focus on joint and bone information in human body skeleton data due to its robustness to complex backgrounds and dynamic characteristics of the environments.
First, we present a human pose based fall representation which is invariant to appearance characteristics.
Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements.
Ranked #5 on Knowledge Distillation on ImageNet
Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images.
Ranked #10 on Document Layout Analysis on PubLayNet val
Automatic classification of epileptic seizure types in electroencephalograms (EEGs) data can enable more precise diagnosis and efficient management of the disease.
On that note, in this paper, we explore the application of machine learning algorithms for multi-class seizure type classification.
We achieve this by training directly a binary hardware crossbar that accommodates the TrueNorth axon configuration constrains and we propose a different neuron model.
Previous work has achieved this by training a network to learn continuous probabilities and deployment to a neuromorphic architecture by random sampling these probabilities.