Paper Reading AI Learner

A Fourier Domain Feature Approach for Human Activity Recognition & Fall Detection

2020-03-11 10:49:11
Asma Khatun, Sk. Golam Sarowar Hossain

Abstract

Elder people consequence a variety of problems while living Activities of Daily Living (ADL) for the reason of age, sense, loneliness and cognitive changes. These cause the risk to ADL which leads to several falls. Getting real life fall data is a difficult process and are not available whereas simulated falls become ubiquitous to evaluate the proposed methodologies. From the literature review, it is investigated that most of the researchers used raw and energy features (time domain features) of the signal data as those are most discriminating. However, in real life situations fall signal may be noisy than the current simulated data. Hence the result using raw feature may dramatically changes when using in a real life scenario. This research is using frequency domain Fourier coefficient features to differentiate various human activities of daily life. The feature vector constructed using those Fast Fourier Transform are robust to noise and rotation invariant. Two different supervised classifiers kNN and SVM are used for evaluating the method. Two standard publicly available datasets are used for benchmark analysis. In this research, more discriminating results are obtained applying kNN classifier than the SVM classifier. Various standard measure including Standard Accuracy (SA), Macro Average Accuracy (MAA), Sensitivity (SE) and Specificity (SP) has been accounted. In all cases, the proposed method outperforms energy features whereas competitive results are shown with raw features. It is also noticed that the proposed method performs better than the recently risen deep learning approach in which data augmentation method were not used.

Abstract (translated)

URL

https://arxiv.org/abs/2003.05209

PDF

https://arxiv.org/pdf/2003.05209.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot