Yi Xie

An energy-efficient task scheduling for mobile devices based on cloud assistant

Abstract Mobile cloud computing is an emerging service model to extend the capability and the battery life of mobile devices. Mostly one network application can be decomposed into fine-grained tasks which consist of sequential tasks and parallel tasks. With the assistance of mobile cloud computing, some tasks could be offloaded to the cloud for speeding up executions and saving energy. However, the task offloading results in some additional cost during the communication between cloud and mobile devices. Therefore, this paper proposes an energy-efficient scheduling of tasks, in which the mobile device offloads appropriate tasks to the cloud via a Wi-Fi access point. The scheduling aims to minimize the energy consumption of mobile device for one application under the constraint of total completion time. This task scheduling problem is reconstructed into a constrained shortest path problem and the LARAC method is applied to get the approximate optimal solution. The proposed energy-efficient strategy decreases 81.93% of energy consumption and 25.70% of time at most, compared with the local strategy. Moreover, the applicability and performance of the proposed strategy are verified in different patterns of applications, where the time constraint, the workload ratio between communication and computation are various.

Research on Cloud Databases: Research on Cloud Databases

With the recent development of cloud computing, the importance of cloud databases has been widely acknowledged. Here, the features, influence and related products of cloud databases are first discussed. Then, research issues of cloud databases are presented in detail, which include data model, architecture, consistency, programming model, data security, performance optimization, benchmark, and so on. Finally, some future trends in this area are discussed.

Evaluation of local features and classifiers in BOW model for image classification

Bag-of-word (BOW) is used in many state-of-the-art methods of image classification, and it is especially suitable for multi-class classification. Many kinds of local features and classifiers are applicable for the BOW model. However, it is unclear which kind of local feature is the most distinctive and meanwhile robust, and which classifier can optimize classification performance. In this paper, we discuss the implementation choices in the BOW model. Further, we evaluate the influences of local features and classifiers on object and texture recognition methods in the framework of the BOW model. To evaluate the implementation choices, we use two popular datasets: the Xerox7 dataset and the UIUCTex dataset. Extensive experiments are carried out to compare the performance of different detectors, descriptors and classifiers in term of classification accuracy on the object category dataset and the texture dataset. We find that the combinational detector which combines the MSER detector with the Hessian-Laplacian detector is efficient to find discriminative regions. We also find that the SIFT descriptor performs better than the other descriptors for image classification, and that the SVM classifier with the EMD kernel is superior to other classifiers. More than that, we propose an EMD spatial kernel to encode the spatial information of local features. The EMD spatial kernel is implemented on the Xerox7 dataset, the 4-class VOC2006 dataset and the 4-class Caltech101 dataset. The experimental results show that the proposed kernel outperforms the EMD kernel which does not consider the spatial information in image classification.

Maintaining Internal Consistency of Report for Real-Time OLAP with Layer-Based View

Maintaining internal consistency of report is an important aspect in the field of real-time data warehouses. OLAP and Query tools were initially designed to operate on top of unchanging, static historical data. In a real-time environment, however, the results they produce are usually negatively influenced by data changes concurrent to query execution, which may result in some internal report inconsistency. In this paper, we propose a new method, called layer-based view approach, to appropriately and effectively maintain report data consistency. The core idea is to prevent the data involved in an OLAP query from being changed through using lock mechanism, and avoid the confliction between read and write operations with the help of layer mechanism. Our approach can effectively deal with report consistency issue, while at the same time avoiding the query contention between read and write operations under real-time OLAP environment.

An auto-adaptive background subtraction method for Raman spectra

Background subtraction is a crucial step in the preprocessing of Raman spectrum. Usually, parameter manipulating of the background subtraction method is necessary for the efficient removal of the background, which makes the quality of the spectrum empirically dependent. In order to avoid artificial bias, we proposed an auto-adaptive background subtraction method without parameter adjustment. The main procedure is: (1) select the local minima of spectrum while preserving major peaks, (2) apply an interpolation scheme to estimate background, (3) and design an iteration scheme to improve the adaptability of background subtraction. Both simulated data and Raman spectra have been used to evaluate the proposed method. By comparing the backgrounds obtained from three widely applied methods: the polynomial, the Baeks and the airPLS, the auto-adaptive method meets the demand of practical applications in terms of efficiency and accuracy.

Characterizing mobile *-box applications

With the increasing use of multiple electronic devices including tablets, PCs, and mobile devices, Personal Cloud Storage (PCS) services, such as Dropbox and Box, have gained huge popularity. Recent research has used the PC clients of a few PCS services to study the network architectures and performance of these services. The mobile clients deserve a further study because the study of PC clients does not necessarily represent the system and network demand with mobile clients. In this paper, we conduct the first systematic investigation on six popular PCS services to reveal their internals and measure their performance. By dissecting their protocols and conducting cross-layer examinations, we obtain interesting observations, identify design issues, and suggest solutions to remedy these issues. Moreover, we propose an efficient method to measure the response latency of PCS servers by exploiting their open APIs.

Centralizing the Power Saving Mode for 802.11 Infrastructure Networks

With the rapid development of wireless networks, efficient energy management for wireless LAN (WLAN) has become an important problem, because mobile devices’ availability is determined by their stringent batteries power. Quite a few sources of energy consumption have been identified (Narseo et al., 2010), among which the wireless communication component uses up a significant amount of energy. For instance, the Motorola Droid phone consumes around 200mW with the backlight off, close to 400mW with the backlight on, and over 800mW when the Wi-Fi radio is active (Zeng et al., 2011). This chapter focuses on improving the energy efficiency of wireless communication component, because they may consume up to 50% of the total energy. Various mechanisms have been proposed to balance between communication quality and energy consumption for wireless devices, for example, power saving mode (PSM) that puts an idle client into a low-power mode (Gast, 2005), transmission power control (Nuggehalli et al., 2002), packet transmission scheduling (Qiao et al., 2003; Tarello et al., 2005), and some cross-layer methods (Anastasi et al., 2007). They investigate the trade-off between energy consumption and throughput (Gao et al., 2010; Zhang & Chanson, 2003), delay (Guha et al., 2010; Nuggehalli et al., 2002; 2006), or network utility (Chiang & Bell, 2004). In this chapter, we propose a centralized PSM (C-PSM), an AP-centric deployment of the IEEE 802.11 PSM, to optimize power saving and multiple performance metrics for infrastructure networks which are widely deployed in enterprise, campus, and metropolitan networks. In these networks, wireless clients (e.g., laptops, PDAs and mobile phones) using the IEEE 802.11 infrastructure mode connect to the Internet through an access point (AP). The experiment results show that significant improvements can be obtained from the new deployment of C-PSM. The IEEE 802.11 PSM, widely used in WLAN, allows an idle client to go into a sleep mode. Hereafter, we use PSM to refer to the IEEE 802.11 PSM. The clients save energy by sleeping while wakes up periodically to receive beacon frames from AP. The beacon frame, sent by an access point (AP) every beacon interval (BI), indicates whether clients have frames buffered at the AP. Each client’s wake-up frequency is determined by a PSM parameter listen interval (LI). Both BI and LI are configurable, and their settings directly influence the PSM’s performance shown by the analysis of section 4. Unfortunately, the protocol does not prescribe how the BI 1

Online co-training ranking SVM for visual tracking

Online learned tracking is widely used to handle the appearance changes of object because of its adaptive ability. Learning to rank technique has attracted much attention recently in visual tracking. But the tracking method with online learning to rank suffers from the error accumulation problem during the self-training process. To solve this problem, we propose an online learning to rank algorithm in the co-training framework for robust visual tracking. A co-training algorithm combined with ranking SVM collects features and unlabeled data for training. Two ranking SVMs are built with different types of features accordingly and dynamically fused into a semi-supervised learning process. This semi-supervised learning approach is updated online to resist the occlusion and adapt to the changes of objects appearance. Many experiments on challenging sequences have shown that the proposed algorithm is more effective than the state-of-the-art methods.

AProbing: Estimating available bandwidth using ACK pair probing

Available bandwidth estimation is an effective way to understand the situations of networks and applications. The packet pair technique analyzes the inter-arrival time of packet pair for the available bandwidth estimation in an end-to-end path. The inter-arrival time of packet pair is mostly caused by the queuing delay of narrow link which is sensitive to cross traffic. This paper proposes a new method using ACK pair probing (AProbing) to estimate end-to-end available bandwidth. It improves the packet pair technique with the probe gap model (PGM) which reduces the influences of cross traffic, and reconstructs the acknowledgements (ACKs) of Transmission Control Protocol (TCP) which reduces the overhead of measurement. AProbing has been implemented and verified in NS-3. The simulation results show that the accuracy of AProbing is similar with that of Pathload and 10% higher than the accuracies of Pathchirp and Cprobe. Moreover, AProbing significantly decreases the overhead of bandwidth estimation compared with these existed methods.

An adaptive PSM mechanism in WLAN based on traffic awareness

Wireless devices consume large amount of energy during wireless communication. Since the energy storage of battery is limited, improving energy efficiency has become an important approach to prolong the lifetime of device. IEEE 802.11 protocol supports power save mode (PSM) in wireless local area networks (WLANs). But the standard PSM cannot adapt to the changes of traffic load or channel conditions. Therefore, this paper proposes an adaptive PSM mechanism (APSM) which improves energy efficiency of wireless devices in a WLAN with access point (AP). According to the current channel condition and traffic load, the AP gives devices with different priorities when they fetch buffered packets. The devices can adaptively adjust listening intervals according to network traffic and adopt different congestion windows when the network topology changes. APSM has been implemented and evaluated in NS-2. The simulation results have shown that the device using APSM can save 58% energy at most compared with the one using the standard PSM.