Real Mobile System Research Articles

Mobile Contextual Recommender System for Online Social Media

Exponential growth of media consumption in online social networks demands effective recommendation to improve the quality of experience especially for on-the-go mobile users. By means of large-scale trace-driven measurements over mobile Twitter traces from users, we reveal the significance of affective features in shaping users’ social media behaviors. Existing recommender systems however, rarely support such psychological effect in real-life. To capture such effect, in this paper we propose Kaleido, a real mobile system that achieves an online social media recommendation solution by taking affective context into account. Specifically, we design a machine learning mechanism to infer the affective pulse of online social media. Furthermore, a cluster-based latent bias model (LBM) is provided for jointly training the affective pulse as well as user’s behavior, location, and social contexts. Our comprehensive trace-driven experiments on Android prototype expose a superior prediction accuracy of 87 percent, which has 25 percent accuracy superior to existing mobile recommender systems. Moreover, by enabling users to offload their machine learning procedures to the deployed edge-cloud testbed, our system achieves speed-up of a factor of 1,000 against the local data training execution on smartphones.

Enhancing Mobile Networks With Software Defined Networking and Cloud Computing

In the past decade, mobile devices and applications have experienced an explosive growth, and users are expecting higher data rates and better quality services every year. In this paper, we propose several ideas to increase the functionality and capacity of wireless networks using software-defined networking (SDN) and cloud computing technologies. Connections between users and services in mobile networks typically have to pass through a required set of middleboxes. The complex routing is one of the major impetus for the SDN paradigm, which enables flexible policy-aware routing in the next generation mobile networks. In addition, the high costs of middleboxes and limited capabilities of mobile devices call for revolutionary virtualization technologies enabled by cloud computing. Based on these, we consider an online routing problem for mobile networks with SDN and cloud computing. In this problem, connection requests are given one at a time (as in a real mobile system), and the objective is to steer traffic flows to maximize the total amount of traffic accepted over time, subject to capacity, budget, policy, and quality of service constraints. A fast log-competitive approximation algorithm is developed based on time-dependent duals.

Stable fully-printed polymer resistive read-only memory and its operation in mobile readout system

The read-only memory (ROM) is a key component for a wide range of printed electronics applications. The resistive type ROM based on conductive polymer poly(3,4-ethylenedioxythiophene) doped with poly(styrene sulfonate) (PEDOT: PSS) would be a promising technology of choice, which can be “manufactured-on-demand” via digital printing for high throughput and material saving. However, the instability issues associated with the conventional PEDOT: PSS and its interface with contact electrodes would be a critical hurdle preventing the technology from practical applications. This work proves that, by removing the hydrophilic acidic groups in conventional PEDOT: PSS, these instability issues can be well addressed. The ROM tags fabricated based on the modified PEDOT: PSS of neutral pH and inkjet printed silver electrodes present extremely stable performance under both aging and electrical stress tests in air ambient. A self-designed memory readout circuit board, communicating with mobile phone through near field communication, is also implemented to demonstrate the feasibility of using the ROM tags in real mobile systems. It is shown that, without any encapsulation, the ROMs can have stable output under high humidity condition (>60% RH), after either being stored in the ambient condition for 30 days or being operated after 20000 reading cycles.

Hysteresis plus Timer based Handover Initiation Algorithm for Microcellular Systems

This paper presents a new handover initiation algorithm based on relative signal strength measurements without averaging, and a timer. The performance metrics used are average number of handovers per cell boundary crossing, and handover initiation delay. Both of these, need to be minimized. Proposed algorithm was compared with the algorithms based on both hysteresis margin, and averaging of signal strength measurements. Our results show that the new algorithm yields the same performance as that obtained through the latter. Since the algorithm does not use averaging of the signal strength measurements, its implementation in real mobile systems is quite easy, which proves the usefulness of the proposed algorithm. Moreover, averaging always makes the handover process sluggish. The present algorithm does not use signal strength averaging. This fact yields a fast handover initiation algorithm, making it particularly suitable for implementation in microcellular systems.