Search

An approach for monitoring human activities and correlated postures using an earlobe-worn wearable sensor and a deep learning algorithm is proposed. The herein-used miniaturized wearable is called TRACE and is to be mounted on an earlobe, for which smaller movements are expected compared with common locations for wearable devices. This work adopts both biological [heart rate (HR)] and physical [acceleration (ACC)] signals that are simultaneously recorded in real time. The recorded raw data are sensor-fused, adequately labeled, processed, and trained by a deep learning algorithm. Using the data, several deep learning models based on different deep learning algorithms are developed and compared. Among our experimental conditions, the best classification accuracy is achieved when the biological and physical sensor signals are fused and a long-short term memory (LSTM) algorithm is used. The proposed approach successfully classified human activities and postures with high accuracy reaching $>$ 95% for two patterns of daily activities. More specifically, the proposed method achieved 97.83%, 97.31%, and 98.19% accuracy for the deep neural network (DNN), convolutional neural network (CNN), and LSTM models, respectively.

MPEG-4 video streaming service is being regarded as a de facto standard service for current mobile multimedia video streaming services such as video conferencing, voice over IP, and even state-of-the-art digital multimedia broadcasting technology. There have been many illegal users who+ have used copyrighted material without getting permission and/or paying for its use. Therefore, much attention has been paid for Digital Rights Management (DRM) for digital media. We constructed a protection scheme for MPEG-4 video file format, which can be applied, to the video services that are exploiting the MPEG-4 standard. In this protection scheme, minimum segments of every Video Object Plane in a MPEG-4 video file could be encrypted with a symmetric cryptography system like a DES (Data Encryption Standard) so that people who have not received permission and/or paid to use the contents would not be able to view them. We applied this scheme to all kinds of MPEG-4 VOP (Video Object Plane) types, that is I-, P-, and B-VOPs respectively. The prototype system was developed for proofing the feasibility of this scheme for hand-held devices and for mobile multimedia service environment. The efficiency of this scheme is reported at the end of this paper. Index Terms--DRM (Digital Rights Management), Intellectual Property, Mobile, MPEG-4, Multimedia, and Streaming Service

Wireless multimedia streaming applications have been widely propagated with the rapid evolution of mobile handsets and wireless Internet technologies, especially MPEG-4 video streams over wireless communication networks. We propose an efficient methodology for Multimedia DRM which is applicable to the mobile terminal software. The methodology is comprised of the encryption methods on the media data that are encoded with MPEG-4 video format. We constructed 3 methods, one is' the way we can encrypt macroblocks(MBs) of I-VOP(Video Object Plane), another is P-VOP's MBs encryption and the other is the combination of these two methods. They are designed to DRM services for a wireless video streaming ,system without performance degradation that could be a burden to a mobile handset, where there is inherently preferred ,system that costs for low-power, low-network bandwidth. We report competitiveness of these methods on the perspective of performance evaluation with respect to the plain MPEG-4 files. (1) Index Terms--DRM (Digital Rights Management), Encryption, MPEG-4, Mobile Internet, Multimedia