Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail significant computation, Glimpse runs them on server machines. When the latency between the server and mobile device is higher than a frame-time, this approach lowers object recognition accuracy. To regain accuracy, Glimpse uses an active cache of video frames on the mobile device. A subset of the frames in the active cache are used to track objects on the mobile, using (stale) hints about objects that arrive from the server from time to time. To reduce network bandwidth usage, Glimpse computes trigger frames to send to the server for recognizing and labeling. Experiments with Android smartphones and Google Glass over Verizon, AT&T, and a campus Wi-Fi network show that with hardware face detection support (available on many mobile devices), Glimpse achieves precision between 96.4% to 99.8% for continuous face recognition, which improves over a scheme performing hardware face detection and server-side recognition without Glimpse's techniques by between 1.8-2.5×. The improvement in precision for face recognition without hardware detection is between 1.6-5.5×. For road sign recognition, which does not have a hardware detector, Glimpse achieves precision between 75% and 80%; without Glimpse, continuous detection is non-functional (0.2%-1.9% precision).

Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail significant computation, Glimpse runs them on server machines. To achieve high accuracy, Glimpse uses an active cache of video frames on the mobile device. A subset of the frames in the active cache are used to track objects on the mobile, using (stale) hints about objects that arrive from the server from time to time. To reduce network bandwidth usage, Glimpse computes trigger frames to send to the server for recognizing and labeling.

Over the past two or three years, wireless cellular networks have become faster than before, most notably due to the deployment of LTE, HSPA+, and other similar networks. LTE throughputs can reach many megabits per second and can even rival WiFi throughputs in some locations. This paper addresses a fundamental question confronting transport and application-layer protocol designers: which network should an application use? WiFi, LTE, or Multi-Path TCP (MPTCP) running over both?

Cloud computing infrastructures are increasingly being used by network-intensive applications that transfer significant amounts of data between the nodes on which they run. This paper shows that tenants can do a better job placing applications by understanding the underlying cloud network as well as the demands of the applications. To do so, tenants must be able to quickly and accurately measure the cloud network and profile their applications, and then use a network-aware placement method to place applications. This paper describes Choreo, a system that solves these problems. Our experiments measure Amazon's EC2 and Rackspace networks and use three weeks of network data from applications running on the HP Cloud network. We find that Choreo reduces application completion time by an average of 8%-14% (max improvement: 61%) when applications are placed all at once, and 22%-43% (max improvement: 79%) when they arrive in real-time, compared to alternative placement schemes.

The 3G/LTE wireless interface is a significant contributor to battery drain on mobile devices. A large portion of the energy is consumed by unnecessarily keeping the mobile device's radio in its "Active" mode even when there is no traffic. This paper describes the design of methods to reduce this portion of energy consumption by learning the traffic patterns and predicting when a burst of traffic will start or end. We develop a technique to determine when to change the radio's state from Active to Idle, and another to change the radio's state from Idle to Active. In evaluating the methods on real usage data from 9 users over 28 total days on four different carriers, we find that the energy savings range between 51% and 66% across the carriers for 3G, and is 67% on the Verizon LTE network. When allowing for delays of a few seconds (acceptable for background applications), the energy savings increase to between 62% and 75% for 3G, and 71% for LTE. The increased delays reduce the number of state switches to be the same as in current networks with existing inactivity timers.