Showing papers by "Xiangjie Kong published in 2013"
TL;DR: This paper examines the importance of mobile multimedia recommendation systems from the perspective of three smart communities, namely mobile social learning, mobile event guide, and context-aware services.
Abstract: Due to the rapid growth of Internet broadband access and proliferation of modern mobile devices, various types of multimedia (e.g., text, images, audios, and videos) have become ubiquitously available anytime. Mobile device users usually store and use multimedia contents based on their personal interests and preferences. Mobile device challenges such as storage limitation have, however, introduced the problem of mobile multimedia overload to users. To tackle this problem, researchers have developed various techniques that recommend multimedia for mobile users. In this paper, we examine the importance of mobile multimedia recommendation systems from the perspective of three smart communities, namely mobile social learning, mobile event guide, and context-aware services. A cautious analysis of existing research reveals that the implementation of proactive, sensor-based and hybrid recommender systems can improve mobile multimedia recommendations. Nevertheless, there are still challenges and open issues such as the incorporation of context and social properties, which need to be tackled to generate accurate and trustworthy mobile multimedia recommendations.
51 citations
Posted Content•
TL;DR: In this article, the authors examine the importance of mobile multimedia recommendation systems from the perspective of three smart communities, namely, mobile social learning, mobile event guide and context-aware services, and reveal that the implementation of proactive, sensor-based and hybrid recommender systems can improve mobile multimedia recommendations.
Abstract: Due to the rapid growth of internet broadband access and proliferation of modern mobile devices, various types of multimedia (e.g. text, images, audios and videos) have become ubiquitously available anytime. Mobile device users usually store and use multimedia contents based on their personal interests and preferences. Mobile device challenges such as storage limitation have however introduced the problem of mobile multimedia overload to users. In order to tackle this problem, researchers have developed various techniques that recommend multimedia for mobile users. In this survey paper, we examine the importance of mobile multimedia recommendation systems from the perspective of three smart communities, namely, mobile social learning, mobile event guide and context-aware services. A cautious analysis of existing research reveals that the implementation of proactive, sensor-based and hybrid recommender systems can improve mobile multimedia recommendations. Nevertheless, there are still challenges and open issues such as the incorporation of context and social properties, which need to be tackled in order to generate accurate and trustworthy mobile multimedia recommendations.
50 citations
TL;DR: A priority-based Service Differentiated and Adaptive CSMA/ CA (SDA-CSMA/CA) algorithm to provide differentiated QoS for various Smart Grid applications as well as dynamically initialize backoff exponent according to traffic conditions is proposed.
Abstract: Cyber-Physical Systems (CPS) that collect, exchange, manage information, and coordinate actions are an integral part of the Smart Grid. In addition, Quality of Service (QoS) provisioning in CPS, especially in the wireless sensor/actuator networks, plays an essential role in Smart Grid applications. IEEE 802.15.4, which is one of the most widely used communication protocols in this area, still needs to be improved to meet multiple QoS requirements. This is because IEEE 802.15.4 slotted Carrier Sense Multiple Access/Collision Avoidance (CSMA/CA) employs static parameter configuration without supporting differentiated services and network self-adaptivity. To address this issue, this paper proposes a priority-based Service Differentiated and Adaptive CSMA/CA (SDA-CSMA/CA) algorithm to provide differentiated QoS for various Smart Grid applications as well as dynamically initialize backoff exponent according to traffic conditions. Simulation results demonstrate that the proposed SDA-CSMA/CA scheme significantly outperforms the IEEE 802.15.4 slotted CSMA/CA in terms of effective data rate, packet loss rate, and average delay.
29 citations
20 Aug 2013
TL;DR: A task scheduling-preemptive-priority model is proposed to simulate and analyze typical wireless sensor network using matrix-geometric theory and several merits of the communication task schedule are obtained, including the communicationtask loss rate, the average response time and the wireless sensor occupancy rate.
Abstract: In this paper, a communication task scheduling evaluation model based on the queue model is proposed to analyze the wireless sensor performance parameters. The typical communication task scheduling which deals with all communication tasks scheduling requests and makes actions or responses. A task scheduling-preemptive-priority model is proposed to simulate and analyze typical wireless sensor network using matrix-geometric theory. And then, several merits of the communication task schedule are obtained, including the communication task loss rate, the average response time and the wireless sensor occupancy rate. At last, experiments are conducted to show the performance of our scheme. Simulation results manifest that when sensor usage rate up to 97%, our scheme is feasible for wireless sensor networks.
3 citations
29 Oct 2013
TL;DR: A novel hypergraph-based kernel computation combined with k nearest neighbor (kNN) to predict ratings of users is proposed, which performs better than typical kNN, which is simple and appropriate for online recommending applications.
Abstract: Recommender systems in online marketing websites like Amazon.com and CDNow.com suggest relevant services and favorite products to customers. In this paper, we proposed a novel hypergraph-based kernel computation combined with k nearest neighbor (kNN) to predict ratings of users. In this method, we change regular definition style of hypergraph diffusion kernel. Our comparative studies show that our method performs better than typical kNN, which is simple and appropriate for online recommending applications.
2 citations