Jörg Ott

Wei Geng, Nitinder Mohan, Jörg Ott

Edge-cloud inference collaborations are often designed with a routing estimator that decides whether to offload each frame from weak models at the edge to stronger models in the cloud. Existing systems place the routing estimator after the weak detector, so the weak forward pass still runs even on frames that are later offloaded. In this paper, we argue that this weak-conditioned design can be suboptimal when the offload budget varies. First, we present a competitive weak-skipping estimator (0.153 GFLOPs, about 29x lighter than the weak detector at 4.49 GFLOPs) that extracts routing signal from raw pixels, outperforming the common after-weak placement weak-conditioned baselines. Second, we show that neither weak-skipping nor weak-conditioned placement dominates across the full operating curve, and we propose budget-adaptive routing, which selects between them by offload budget via two offline-tuned thresholds. On PASCAL VOC, our budget-adaptive router traces the upper accuracy envelope of both fixed placements across the operating range. Our method reduces per-frame latency by up to 19.1 ms (about 30% lower at rho = 0.9). Besides outperforming SOTA methods, it is surprisingly stronger than the strong model (+1.7 pp over the strong model's peak mAP) at some operating points with far less compute. Artifacts are available at https://github.com/ViGeng/bgt-ada

Michael Haus, Jörg Ott, Aaron Yi Ding

To enable serendipitous interaction for indoor IoT environments, spontaneous device associations are of particular interest so that users set up a connection in an ad-hoc manner. Based on the similarity of light signals, our system named DevLoc takes advantage of ubiquitous light sources around us to perform continuous and seamless device grouping. We provide a configuration framework to control the spatial granularity of user's proximity by managing the lighting infrastructure through customized visible light communication. To realize either proximity-based or location-based services, we support two modes of device associations between different entities: device-to-device and device-to-area. Regarding the best performing method for device grouping, machine learning-based signal similarity performs in general best compared to distance and correlation metrics. Furthermore, we analyze patterns of device associations to improve the data privacy by recognizing semantic device groups, such as personal and stranger's devices, allowing automated data sharing policies.

Yige Zhang, Aaron Yi Ding, Jorg Ott et al.

Telecommunication (Telco) outdoor position recovery aims to localize outdoor mobile devices by leveraging measurement report (MR) data. Unfortunately, Telco position recovery requires sufficient amount of MR samples across different areas and suffers from high data collection cost. For an area with scarce MR samples, it is hard to achieve good accuracy. In this paper, by leveraging the recently developed transfer learning techniques, we design a novel Telco position recovery framework, called TLoc, to transfer good models in the carefully selected source domains (those fine-grained small subareas) to a target one which originally suffers from poor localization accuracy. Specifically, TLoc introduces three dedicated components: 1) a new coordinate space to divide an area of interest into smaller domains, 2) a similarity measurement to select best source domains, and 3) an adaptation of an existing transfer learning approach. To the best of our knowledge, TLoc is the first framework that demonstrates the efficacy of applying transfer learning in the Telco outdoor position recovery. To exemplify, on the 2G GSM and 4G LTE MR datasets in Shanghai, TLoc outperforms a nontransfer approach by 27.58% and 26.12% less median errors, and further leads to 47.77% and 49.22% less median errors than a recent fingerprinting approach NBL.

Saba Ahsan, Varun Singh, Jörg Ott

The availability of high definition video content on the web has brought about a significant change in the characteristics of Internet video, but not many studies on characterizing video have been done after this change. Video characteristics such as video length, format, target bit rate, and resolution provide valuable input to design Adaptive Bit Rate (ABR) algorithms, sizing playout buffers in Dynamic Adaptive HTTP streaming (DASH) players, model the variability in video frame sizes, etc. This paper presents datasets collected in 2013 and 2014 that contains over 130,000 videos from YouTube's most viewed (or most popular) video charts in 58 countries. We describe the basic characteristics of the videos on YouTube for each category, format, video length, file size, and data rate variation, observing that video length and file size fit a log normal distribution. We show that three minutes of a video suffice to represent its instant data rate fluctuation and that we can infer data rate characteristics of different video resolutions from a single given one. Based on our findings, we design active measurements for measuring the performance of Internet video.

Marcin Nagy, Varun Singh, Joerg Ott et al.

In this paper, we propose a new rate control algorithm for conversational multimedia flows. In our approach, along with Real-time Transport Protocol (RTP) media packets, we propose sending redundant packets to probe for available bandwidth. These redundant packets are Forward Error Correction (FEC) encoded RTP packets. A straightforward interpretation is that if no losses occur, the sender can increase the sending rate to include the FEC bit rate, and in the case of losses due to congestion the redundant packets help in recovering the lost packets. We also show that by varying the FEC bit rate, the sender is able to conservatively or aggressively probe for available bandwidth. We evaluate our FEC-based Rate Adaptation (FBRA) algorithm in a network simulator and in the real-world and compare it to other congestion control algorithms.