Mobility scooters are popular among people with limited mobility, providing convenient transportation in their communities and thus enhancing their life quality. However, due to various reasons, a high number of mobility scooter accidents have been reported. In this paper, we tackle its safety issues by performing riding behavior stability analysis using both video and motion sensor data. We design a transformer-based cross-modal encoder to generate the embeddings representing the riding stability and develop a binary classifier based on the embeddings to classify riding behaviors as stable or unstable. The advantage of this work is that the multimodal contrastive learning approach enables the neural network to understand the correlations across two modalities for the same events, and to distinguish the unstable riding behaviors from stable, so that incontext stability analysis becomes possible. We have conducted extensive experiments based on real-world mobility scooter riding data labeled by medical practitioners. The results have shown a high level of classification accuracy of our system, across different settings, in ablation study as well as comparative study.

Mobility scooters are critical in facilitating social participation of people with mobility challenges and thus improving their life quality. However, the safety issues of driving mobility scooter are real concerns and may not be assessed in a timely fashion for many patients. In this paper we enable driving posture stability analysis at home or in the community setting for people with mobility challenges by using only video recordings of their driving. In particular, we design a system that extracts upper body keypoints’ 2D coordinates from video frames and builds an autoencoder model to perform stability analysis. We explore two architectures of the autoencoder, with Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN), respectively emphasizing the temporal and spatial relationships of upper body keypoints in driving movements. Evaluations using patients driving posture data collected have shown that both architectures have achieved over 0.99 Precision-Recall Area Under the Curve (AUC), and 0.8 ROC AUC, indicating excellent model accuracy levels.

A mobility scooter is an electrically powered scooter designed for people with restricted mobility [1] . The safety of mobility scooter driving is critical for drivers but often not assessed [2] , [3] . The goal of the project is to assess the safety level of people with neurological conditions driving mobility scooters by classifying their behaviors using mobility sensor data. In this work, we propose a data-driven approach to build time-series deep neural network models for mobility scooter driving behaviors, and thus based on mobility sensor data enable the real-time classification of 5 behaviors, i.e., sudden acceleration, Sudden left turn, Sudden right turn, Sudden break, and non-sudden movement.

Privacy of genomic data has become increasingly significant as genome sequencing is more readily available for research. It is imperative to protect genomic data as we use it for the progression of medicine. In this paper, we propose a new privacy preserving Fisher's Exact Test algorithm for genomic data based on Boneh-Goh-Nissim (BGN) cryptosystem. This is a novel approach that has yet to be done to the best of our knowledge. Due to BGN's homomorphic properties, researchers can keep data private while calculating the correct test results without ever decrypting the data itself. We investigate the usage of the BGN cryptosystem on statistical computations, Fisher's Exact Test in particular, analyzing its security, efficiency, and correctness in the real world of genomic data research. We implement our BGN-based privacy preserving Fisher's Exact Test algorithm and test it extensively using real genomic data from international genome database. The result shows that our algorithm is efficient and practical.