The advance of hardware has allowed edge devices to carry out varying applications, including computation-intensive machine learning tasks. This paper targets a real-time application of detecting objects on streaming videos with a tightened requirement on processing overhead. While the edge device still lacks the computation power to apply the object detection algorithm on every video frame, this paper integrates cloud-side servers in the solution as much prior work has attempted. However, our design is different from the conventional off-loading solutions that delegate the computation tasks to the cloud servers. We present a solution named CODS where the computation tasks are still conducted by the edge devices while the cloud server provides useful guidelines for choosing appropriate analysis algorithms. We implement our solution with the Jetson Nano device and evaluate it with videos from representative datasets. The results show that CODS is quite effective and superior to baseline alternatives.

Augmented reality (AR) is an emerging technology that weaves virtual objects into physical environments, and enables users to interact with them through viewing devices. This paper targets on multi-user AR applications, where virtual objects (VOs) placed by a user can be viewed by other users. We develop a practical framework that supports the basic multi-user AR functions of placing and viewing VOs, and our system can be deployed on off-the-shelf smartphones without special hardware. The main technical challenge we address is that when facing the exact same scene, the user who places the VO and the user who views the VO may have different view angles and distances to the scene. This setting is realistic and the traditional solutions yield a poor performance in terms of the accuracy. In this work, we have developed a suite of algorithms that help the viewers accurately identify the same scene and restore the VO under a moderate range of view angle difference. We have prototyped our system, and the experimental results have shown significant performance improvements. Our source codes and demos can be accessed at https://github.com/PROMAR2019.

Apache Spark is an in-memory analytic framework that has been adopted in the industry and research fields. Two memory managers, Static and Unified, are available in Spark to allocate memory for caching Resilient Distributed Datasets (RDDs) and executing tasks. However, we found that the static memory manager (SMM) lacks flexibility, while the unified memory manager (UMM) puts heavy pressure on the garbage collection of JVM on which Spark resides. To address these issues, we design an auto-tuning memory manager (ATuMm) to support dynamic memory allocation with the consideration of both memory demands and latency introduced by garbage collection. We implement our new memory manager in Spark 2.2.0 and evaluate it by conducting experiments in a real Spark cluster. Our experimental results show that our auto-tuning memory manager can reduce the total garbage collection time and thus further improve the performance (i.e., reduced latency) of Spark applications, compared to the existing Spark memory management solutions.

Mobile Augmented Reality (MAR) represents an emerging category of applications that bring users interactive experiences with the physical experiencesnvironment. In such applications, users can place virtual objects in real-world space, and view them through a camera view. In this work, we develop a framework that supports multi-users interactions for MAR apps, where one user places a virtual object that can be recognized by other users.

The emergence of Edge Computing and the success of Internet of Thing and (IoT) has tremendously changed the way we think about data computing. With edge devices changing from data producer to both data producer and consumer, the chance for processing large data sets with Big Data on a cloud of IoT devices is more realistic. In Big Data systems such as Hadoop-Yarn, Spark, Pig, etc., the shuffling stage is by far the most dominant source of network traffic. Unreliable performance of network will greatly impact the shuffling process. Since IoT devices mostly rely on wireless network based on 802.11, providing proper throughput to big data computing system is an important challenge that needs to be address. In this paper, we argue that a cluster of IoT computers can support big data by considering the information fed by the big data applications. We propose a cross-layer framework that uses the application layer information to guide the packet scheduling at the link layer. We implement our system as an extension module in Hadoop-Yarn system. The experimental evaluation shows significant performance improvement.

Erasure Coding based Storage (ECS) is replacing tradition replica-based systems because of its low storage overhead. In an ECS, however, every task needs to fetch remote pieces of data for its execution, and data verification is missing in the current framework. As security issues keep rising and there have been security incidents occurred in big data platforms, the compromised nodes in a computing cluster may manipulate its hosted data fed for other nodes yielding misleading results. Without replicas, it is quite challenging to efficiently verify the data integrity in ECS. In this paper, we develop ROVER, which is an efficient and verifiable ECS for big data platforms. In ROVER, every piece of data is monitored by its checksums stored on a set of witnesses. Bloom filter technique is used on each witness to efficiently keep the records of the checksums. The data verification is based on the majority voting. ROVER also supports a quick reconstruction of Bloom Filter when a node recovers from a failure. We present a complete system framework, security analysis, and a guideline for setting the parameters. The implementation and evaluation show that ROVER is robust and efficient against the attack from the compromised nodes.

Big data processing frameworks such as Hadoop have been widely adopted to process a large volume of data. A lot of prior work has focused on the allocation of resources and the execution order of jobs/tasks to improve the performance in a homogeneous cluster. In this paper, we investigate storage layer design in a heterogeneous system considering a new type of bundled jobs where the input data and associated application jobs are submitted in a bundle. Our goal is to break the barrier between resource management and the underlying storage layer, and improve data locality, an important performance factor for resource management, from the aspect of storage system. We develop a sampling-based randomized algorithm for the network file system to determine the placement of input data blocks. The main idea is to query a selected set of candidate nodes, and estimate their workload at run time combining centralized and per-node information. The node with the smallest workload is selected to host the data block. Our evaluation is based with system implementation and comprehensive experiments on NSF CloudLab platforms. We have also conducted simulation for large-scale clusters. The results show significant performance improvements in terms of execution time and data locality.