An Improved Self-Training Method for Positive Unlabeled Time Series Classification Using DTW Barycenter Averaging.

Traditional supervised time series classification (TSC) tasks assume that all training data are labeled. However, in practice, manually labelling all unlabeled data could be very time-consuming and often requires the participation of skilled domain experts. In this paper, we concern with the positive unlabeled time series classification problem (PUTSC), which refers to automatically labelling the large unlabeled set U based on a small positive labeled set PL. The self-training (ST) is the most widely used method for solving the PUTSC problem and has attracted increased attention due to its simplicity and effectiveness. The existing ST methods simply employ the one-nearest-neighbor (1NN) formula to determine which unlabeled time-series should be labeled. Nevertheless, we note that the 1NN formula might not be optimal for PUTSC tasks because it may be sensitive to the initial labeled data located near the boundary between the positive and negative classes. To overcome this issue, in this paper we propose an exploratory methodology called ST-average. Unlike conventional ST-based approaches, ST-average utilizes the average sequence calculated by DTW barycenter averaging technique to label the data. Compared with any individuals in PL set, the average sequence is more representative. Our proposal is insensitive to the initial labeled data and is more reliable than existing ST-based methods. Besides, we demonstrate that ST-average can naturally be implemented along with many existing techniques used in original ST. Experimental results on public datasets show that ST-average performs better than related popular methods.

User Context Detection for Relay Attack Resistance in Passive Keyless Entry and Start System.

In modern cars, the Passive Keyless Entry and Start system (PKES) has been extensively installed. The PKES enables drivers to unlock and start their cars without user interaction. However, it is vulnerable to relay attacks. In this paper, we propose a secure smartphone-type PKES system model based on user context detection. The proposed system uses the barometer and accelerometer embedded in smartphones to detect user context, including human activity and door closing event. These two types of events detection can be used by the PKES to determine the car owner's position when the car receives an unlocking or a start command. We evaluated the performance of the proposed method using a dataset collected from user activity and 1526 door closing events. The results reveal that the proposed method can accurately and effectively detect user activities and door closing events. Therefore, smartphone-type PKES can prevent relay attacks. Furthermore, we tested the detection of door closing event under multiple environmental settings to demonstrate the robustness of the proposed method.