No abstract

Biometric gait authentication using Personal Mobile Device (PMD) based accelerometer sensors offers a user-friendly, unobtrusive, and periodic way of authenticating individuals on PMD. In this paper, we present a technique for gait cycle extraction by incorporating the Piecewise Linear Approximation (PLA) technique. We also present two new approaches to classify gait features extracted from the cycle-based segmentation by using Support Vector Machines (SVMs); a) pre-computed data matrix, b) pre-computed kernel matrix. In the first approach, we used Dynamic Time Warping (DTW) distance to compute data matrices, and in the later DTW is used for constructing an elastic similarity measure based kernel function called Gaussian Dynamic Time Warp (GDTW) kernel. Both approaches utilize the DTW similarity measure and can be used for classifying equal length gait cycles, as well as different length gait cycles. To evaluate our approaches we used normal walk biometric gait data of 51 participants. This gait data is collected by attaching a PMD to the belt around the waist, on the right-hand side of the hip. Results show that these new approaches need to be studied more, and potentially lead us to design more robust and reliable gait authentication systems using PMD based accelerometer sensor.

This paper gives an insight about the influence of different walking speeds (slow, normal and fast) and surfaces (flat carpeted, grass, gravel and inclined) on gait recognition. Gait recognition is a type of biometric authentication that operates on behavioral characteristics of human beings. This research utilizes wearable sensors, and we have used a commercially available mobile device. Gait data is collected from 48 subjects for six different walk settings in two sessions on different days to measure same-day and cross-day performance. Gait cycles are extracted and compared using dynamic time warping as distance metric. Different parameter settings are evaluated to optimize the cycle extraction process.

Robust and accurate human activity recognition (HAR) systems are essential to many humancentric services within active assisted living and healthcare facilities. Traditional HAR systems mostly leverage a single sensing modality (e.g., either wearable, vision, or radio frequency sensing) combined with machine learning techniques to recognize human activities. Such unimodal HAR systems do not cope well with real-time changes in the environment. To overcome this limitation, new HAR systems that incorporate multiple sensing modalities are needed. Multiple diverse sensors can provide more accurate and complete information resulting in better recognition of the performed activities. This article presents WiWeHAR-a multimodal HAR system that uses combined Wi-Fi and wearable sensing modalities to simultaneously sense the performed activities. WiWeHAR makes use of standard Wi-Fi network interface cards to collect the channel state information (CSI) and a wearable inertial measurement unit (IMU) consisting of accelerometer, gyroscope, magnetometer sensors to collect the user's local body movements. We compute the time-variant mean Doppler shift (MDS) from the processed CSI data and magnitude from the inertial data for each sensor of the IMU. Thereafter, we separately extract various time-and frequencydomain features from the magnitude data and the MDS. We apply feature-level fusion to combine the extracted features, and finally supervised learning techniques are used to recognize the performed activities. We evaluate the performance of WiWeHAR by using a multimodal human activity data set, which was obtained from 9 participants. Each participant carried out four activities, such as walking, falling, sitting, and picking up an object from the floor. Our results indicate that the proposed multimodal WiWeHAR system outperforms the unimodal CSI, accelerometer, gyroscope, and magnetometer HAR systems and achieves an overall recognition accuracy of 99.6%-100%.

We analyze locked and unlocked mobile device usage of 1 960 Android smartphones. Based on approximately 10 TB of mobile device data logs collected by the Device Analyzer project, we derive 6.9 million usage sessions using a screen power state machine based approach. From these session we examine the number of interactions per day, the average interaction duration as well as the total daily device usage time. Findings indicate that on average users interact with their devices 117 minutes a day, separated over 57 interactions -while unlocking their device only 43% of the time (e. g. to check for notifications).