No abstract

Mobile activity recognition is significant to the development of human-centric pervasive applications including elderly care, personalized recommendations, etc. Nevertheless, the distribution of inertial sensor data can be influenced to a great extent by varying users. This means that the performance of an activity recognition classifier trained by one user’s dataset will degenerate when transferred to others. In this study, we focus on building a personalized classifier to detect four categories of human activities: light intensity activity, moderate intensity activity, vigorous intensity activity, and fall. In order to solve the problem caused by different distributions of inertial sensor signals, a user-adaptive algorithm based on K-Means clustering, local outlier factor (LOF), and multivariate Gaussian distribution (MGD) is proposed. To automatically cluster and annotate a specific user’s activity data, an improved K-Means algorithm with a novel initialization method is designed. By quantifying the samples’ informative degree in a labeled individual dataset, the most profitable samples can be selected for activity recognition model adaption. Through experiments, we conclude that our proposed models can adapt to new users with good recognition performance.

We investigate the fundamental relationship between node density and transmission delay in large-scale wireless ad hoc networks with unreliable links from percolation perspective. Previous works[11][2][10] have already showed the relationship between transmission delay and distance from source to destination. However, it still remains as an open question how transmission delay varies in accordance with node density. Answering this question can provide guidance for determining the number of nodes to meet the delay requirement when designing ad hoc networks. In this paper, we study the impact of node density λ on the ratio of delay and distance, denoted by γ(λ). We analytically characterize the properties of γ(λ) as a function of λ. And then we present upper and lower bounds to γ(λ). Next, we take propagation delay into consideration and obtain further results on the upper and lower bounds of γ(λ). Finally, we make simulations to verify our theoretical analysis.

We propose a Generative Transfer Network (GTNet) for zero-shot object detection (ZSD). GTNet consists of an Object Detection Module and a Knowledge Transfer Module. The Object Detection Module can learn large-scale seen domain knowledge. The Knowledge Transfer Module leverages a feature synthesizer to generate unseen class features, which are applied to train a new classification layer for the Object Detection Module. In order to synthesize features for each unseen class with both the intra-class variance and the IoU variance, we design an IoU-Aware Generative Adversarial Network (IoUGAN) as the feature synthesizer, which can be easily integrated into GTNet. Specifically, IoUGAN consists of three unit models: Class Feature Generating Unit (CFU), Foreground Feature Generating Unit (FFU), and Background Feature Generating Unit (BFU). CFU generates unseen features with the intra-class variance conditioned on the class semantic embeddings. FFU and BFU add the IoU variance to the results of CFU, yielding class-specific foreground and background features, respectively. We evaluate our method on three public datasets and the results demonstrate that our method performs favorably against the state-of-the-art ZSD approaches.

No abstract

No abstract

No abstract

No abstract