This paper presents early work on a fall detection method using transfer learning method, in conjunction with a long-term effort to combine efficient machine learning and prior personalized musculoskeletal modeling to deploy fall injury mitigation in geriatric subjects. Inspired by the tremendous progress in image-based object recognition with deep convolutional neural networks (DCNNs), we opt for a pre-trained kinematics-based machine learning approach through existing large-scale annotated accelerometry datasets. The accelerometry datasets are converted to images using time-frequency analysis, based on scalograms, by computing the continuous wavelet transform filter bank. Subsequently, data augmentation is performed on these scalogram images to increase accuracy, thereby complementing limited labeled fall sensor data, enabling transfer learning from the existing pre-trained model. The experimental results on publicly available URFD datasets demonstrate that transfer learning leads to a better performance than the existing methods in the case of scarce labeled training data.
Traumatic brain injury (TBI) is a leading cause of disability globally. Many patients develop post-traumatic epilepsy, or recurrent seizures following TBI. In recent years, significant efforts have been made to identify biomarkers of epileptogenesis that may assist in preventing seizure occurrence by identifying high-risk patients. We present a novel method of assessing seizure susceptibility using data from 49 patients enrolled in the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy (EpiBioS4Rx). We employ a machine learning paradigm that utilizes a Random Forest classifier trained with resting-state functional magnetic resonance imaging (fMRI) data to predict seizure outcomes. Following 100 rounds of stratified cross-validation with 70% of resting state fMRI scans as the training set and 30% as the testing set, our model was found to assess seizure outcome in the testing set with 69% accuracy. To validate the method, we compared our results with classification by Support Vector Machines and Neural Network classifiers.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：