Human motion detection, classification, and perceiving, the dynamics of moving objects in the environment, are crucial in many applications. Many sensors have been used to this detection; the radar represents one of the promising sensors. Kalman filter (KF) and convolutional neural network (CNN) represents a powerful tool for estimation and classification respectively. In this paper, a combination between the KF and CNN have been proposed to detect and classify human behavior. This proposal presents two important points, the precise features map from the combination of Kalman Filter and CNN, as well as the use of the radar, which is working under all circumstances and does not break the privacy. Twenty different experiments with three scenarios for different motion with and without glass wall have been studied, and they are classified. The results show that the overperform of the proposed algorithm and the classification accuracy can reach 98.7%. This advancement of the proposed algorithm depends on the efficient Wigner-Ville short time Fourier transform (STFT) which is used as a feature extractor and make Range-Doppler (RD) map.
This paper presents the results of accompanying classification of tracking for different classes of targets such as a car (moving non-rigid target), moving people (slow moving non-rigid target). The Data are collected using frequency modulation continuous wave (FMCW)radar, while different neural algorithms are considered for classification of targets recorded. A Doppler and Micro Doppler have been used as target features, while short time Fourier transform (STFT) has been used as a feature extraction algorithm. A novel combination between Kalman filter and tree-structured, as well as self-organizing map (SOM) neural network has been proposed as an estimator and classifier, respectively. The results show that the proposed approach is overperformed to the conventional classifier SVM by 1.6% and the gained classification is 92.6%, while the reduction error due to using Kalman filter is 95%.
In the past few years, physical therapy plays a crucial role during rehabilitation. Numerous efforts are made to demonstrate the effectiveness of medical/ clinical and human-machine interface (HMI) applications. One of the most common control methods is using electromyography (EMG) signals generated by muscle contractions to implement the prosthetic human body parts. This paper presents an EMG signal classification system based on the EMG signal. The data is collected from biceps and triceps muscles for six different motions, i.e., bowing, clapping, handshaking, hugging, jumping, and running using a Myo armband with eight electromyography sensors. The Root Mean Square, Difference Absolute Standard Deviation Value, and Principle Component Analysis are used to extract the raw signal data and enhance classification accuracy. The machine learning method is applied, i.e., Support Vector Machine and K-Nearest Neighbors are used for classification; the results show that the K-Nearest Neighbors method achieves a higher accuracy percentage than the SVM. Making high training accuracy for different physical actions helps implement human prosthetic parts to help the people who suffer from an amputee.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.