Motion Gesture Recognition via Accelerometer

Accelerometers have been widely embedded in most current mobile devices, enabling easy and intuitive operations. This paper proposes a Motion Gesture Recognition system (MGRA) based on accelerometer data only, which is entirely implemented on mobile devices and can provide users with real-time interactions. A robust and unique feature set is enumerated through the time domain, the frequency domain and singular value decomposition analysis using our motion gesture set containing 11,110 traces. The best feature vector for classification is selected, taking both static and mobile scenarios into consideration. MGRA exploits support vector machine as the classifier with the best feature vector. Evaluations confirm that MGRA can accommodate a broad set of gesture variations within each class, including execution time, amplitude and non-gestural movement. Extensive evaluations confirm that MGRA achieves higher accuracy under both static and mobile scenarios and costs less computation time and energy on an LG Nexus 5 than previous methods.

Smartphone Authentication on Motion Gesture with a 3-D Accelerometer

Smartphones have become prevalent in our lives with various of apps, such as email, social networking and electronic payment. Since these apps store privacy and sensitive information in smartphones, user authentication is increasingly crucial for privacy protection. Existing researches demonstrated the feasibility of motion gesture authentication with accelerometer. However, the distinguishing features hiding in the acceleration traces of motion gestures remain unknown. In this project, we present our scheme of Smartphone Authentication on Motion Gestures by focusing on feature extraction and select the best feature vector. SAMG confirms that authentication on statistical features from raw acceleration series has higher accuracy, shoulder surfing resistance, easy to remember and lower overhead.

Time Synchronization Mechanism for Underwater Sensor Networks

Time synchronization is the fundamental problem in distributed sensor networks. Specifically, time stamp is an important element of sensing data. Time synchronization for Underwater Sensor Networks (UWSNs) is more challenging because of two unique characteristics.First, UWSNs communicate through acoustic signals with low propagation speed, leading to significant propagation delay comparing to RF signals. Second, the restricted mobility of sensor nodes caused by ocean current, wind or tide brings new challenge to propagation delay estimation. In order to face the long propagation delay and mobility of sensor nodes in UWSNs, several protocols have been proposed. However, all existing UWSN synchronization protocols focus on single-hop based synchronization. For multi-hop scenario, all these protocols can only be applied in hop by hop manner since not all unsynchronized nodes can communicate with beacons directly. In this project, we focus on synchronization in multi-ho UWSNs, and propose correlation solutions. Simulation results confirm that our methods have achieved comprehensive performance improvement on synchronization accuracy, message overhead and time cost.