What we published


I Sent It: Where Does Slow Data Go to Wait? - Accepted to EuroSys 2019

The EuroSys conference series brings together professionals from academia and industry. It has a strong focus on systems research and development: operating systems, database systems, real-time systems, network middleware, distributed, parallel, or embedded computing systems. EuroSys has become a premier forum for discussing various issues of systems software research and development, including implications related to hardware and applications.

Emerging applications like virtual reality (VR), augmented reality (AR), and 360-degree video aim to exploit the unprecedentedly low latencies promised by technologies like the tactile Internet and mobile 5G networks. Yet these promises are still unrealized. In order to fulfill them, it is crucial to understand where packet delays happen, which impacts protocol performance such as throughput and latency. In this work, we empirically find that sender-side protocol stack delays can cause high end-to-end latencies, though existing solutions primarily address network delays. Unfortunately, however, current latency diagnosis tools cannot even distinguish between delays on network links and delays in the end hosts. To close this gap, we present ELEMENT, a latency diagnosis framework that decomposes end-to-end TCP latency into endhost and network delays, without requiring admin privileges at the sender or receiver. We validate that ELEMENT achieves more than 90% accuracy in delay estimation compared to the ground truth in different production networks. To demonstrate ELEMENT’s potential impact on real-world applications, we implement a relatively simple user-level library that uses ELEMENT to minimize delays. For evaluation, we integrate ELEMENT with legacy TCP applications and show that it can reduce latency by up to 10 times while maintaining throughput and fairness. We finally demonstrate that ELEMENT can significantly reduce the latency of a virtual reality application that needs extremely low latencies and high throughput.

The architecture of ELEMENT

ExLL: an extremely low-latency congestion control for mobile cellular networks - Presented at ACM CoNEXT 2018

ACM CoNEXT (International Conference on emerging Networking EXperiments and Technologies) is major forum for presentations and discussions of novel networking technologies that will shape the future of Internetworking.

Our research work titled “ExLL: an extremely low-latency congestion control for mobile cellular networks” with Shinik Park (UNIST), Jinsung Lee (University of Colorado Boulder), Junseon Kim (UNIST), Jihoon Lee (University of Colorado Boulder), Sangtae Ha (University of Colorado Boulder), and Kyunghan Lee (UNIST) has been presented at CoNEXT’18.

Since the diagnosis of severe bufferbloat in mobile cellular networks, a number of low-latency congestion control algorithms have been proposed. However, due to the need for continuous bandwidth probing in dynamic cellular channels, existing mechanisms are designed to cyclically overload the network. As a result, it is inevitable that their latency deviates from the smallest possible level (i.e., minimum RTT). To tackle this problem, we propose a new low-latency congestion control, ExLL, which can adapt to dynamic cellular channels without overloading the network. To do so, we develop two novel techniques that run on the cellular receiver: 1) cellular bandwidth inference from the downlink packet reception pattern and 2) minimum RTT calibration from the inference on the uplink scheduling interval. Furthermore, we incorporate the control framework of FAST into ExLL’s cellular specific inference techniques. Hence, ExLL can precisely control its congestion window to not overload the network unnecessarily. Our implementation of ExLL on Android smartphones demonstrates that ExLL reduces latency much closer to the minimum RTT compared to other low-latency congestion control algorithms in both static and dynamic channels of LTE networks.

SyncCoding: A Compression Technique Exploiting References for Data Synchronization Services - Presented at IEEE ICNP 2017

Cloud-based data synchronization services such as Dropbox, OneDrive, and Google Drive have attracted a huge number of subscribers and it leads to a tremendous of shared data. How can we utilize the redundancy of these shared data? We have studied it and proposed that a novel network data encoding technique which dynamically eliminates redundancy block of inter-files by previously synchronized or shared (i.e., transmitted) data.

IEEE ICNP (International Conference on Network Protocols, acceptance rate: 18.66%) is one of the premier conferences in the computer networking field, which is run by rigorous papers of 10 pages.


In this work, we raise a question on why the abundant information previously shared between a server and its client is not effectively utilized in the exchange of a new data which may be highly correlated with the shared data. We formulate this question as an encoding problem that is applicable to general data synchronization services including a wide range of Internet services such as cloud data synchronization, web browsing, messaging, and even data streaming. To this problem, we propose a new encoding technique, SyncCoding that maximally replaces subsets of the data to be transmitted with the coordinates pointing to the matching subsets included in the set of relevant shared data, called references. SyncCoding can be easily integrated into a transport layer protocol such as HTTP and enables significant reduction of network traffic. Our experimental evaluations of SyncCoding implemented in Linux shows that it outperforms existing popular encoding techniques, Brotli, LZMA, Deflate, and Deduplication in two practical use networking applications: cloud data sharing and web browsing. The gains of SyncCoding over Brotli, LZMA, Deflate, and Deduplication in the encoded size to be transmitted are shown to be about 12.4%, 20.1%, 29.9%, and 61.2% in the cloud data sharing and about 78.3%, 79.6%, 86.1%, and 92.9% in the web browsing, respectively. The gains of SyncCoding over Brotli, LZMA, and Deflate when Deduplication is applied in advance are about 7.4%, 10.6%, and 17.4% in the cloud data sharing and about 79.4%, 82.0%, and 83.2% in the web browsing, respectively.

[ Overview of the system design and the evaluation scenarios of two use case: 1) Cloud data sharing (left) and 2) Web browsing (right) ]

QuickTalk: New Communication Method for IoT Devices - Presented at ACM UbiComp 2017

Is there a way to easily select the specific IoT device among many devices? And is there a way to share the device with no hassle even to the visitor? We have designed and implemented a new communication method for IoT devices without association process that can be used in proximity.

UbiComp is a top-tier conference in the field of Ubiquitous Computing. The Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) is a premier journal series for research relevant to the post-PC era.


IoT devices are in general considered to be straightforward to use. However, we find that there are a number of situations where the usability becomes poor. The situations include but not limited to the followings: 1) when initializing an IoT device, 2) when trying to control an IoT device which is initialized by another person, and 3) when trying to control an IoT device out of many of the same type. We tackle these situations by proposing a new association-free communication method, QuickTalk. QuickTalk lets a user device such as a smartphone pinpoint and activate an IoT device with the help of an IR transmitter and communicate with the pinpointed IoT device through the broadcast channel of WiFi without a conventional association process. This nature, QuickTalk allows a user device to immediately give a command to a specific IoT device in proximity even when the IoT device is uninitialized, unassociated with the control interface of the user, or associated but visually indistinguishable from others of the same kind. Our experiments of QuickTalk implemented on Raspberry Pi 2 devices show that QuickTalk does its job quickly and intuitively. The end-to-end delay of QuickTalk for transmitting an IoT command is on average about 0.74 seconds, and is upper bounded by 2.5 seconds. We further confirm that even when an IoT device has ongoing data sessions with other devices, which disturb the broadcast channel, QuickTalk can still reliably communicate with the IoT device at the cost of minor throughput degradation.

VehicleSense: A Reliable Sound-based Transportation Mode Recognition System for Smartphones - Presented at IEEE WoWMoM 2017

So far, there have been no previous works with a satisfying performance in terms of a latency, a recognition accuracy and an energy efficiency at the same time. VehicleSense achieves all of these performances simultaneously by utilizing the unique characteristics of a sound of vehicles and implementing accelerometer-based trigger systems.

IEEE WoWMoM (World of Wireless  Mobile and Multimedia Networks) is a conference in the areas of wireless, mobile, and multimedia networking as well as ubiquitous and pervasive systems, which is run by rigorous papers of 9 pages.


A new transportation mode recognition system for smartphones, VehicleSense that is widely applicable to mobile context-aware services is proposed. VehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured from the built-in microphone while being on candidate transportations. To attain high energy efficiency, VehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the microphone of smartphones. Further, to attain high accuracy and low latency, VehicleSense makes use of non-linear filters that can best extract the transportation sound samples.

Our 186-hour log of sound and accelerometer data collected by seven different Android smartphone models confirms that VehicleSense achieves the recognition accuracy of 98.2% with only 0.5 seconds of sound sampling at the power consumption of 26.1 mW on average for all day monitoring.

[ VehicleSense system overview ]

Context-Aware Background Application Scheduling in Interactive Mobile Systems - Published at IEEE JSAC 2017

Today, lots of mobile users want to extend the battery life time of their smartphones. If we can preload and unload applications to the background with the knowledge about future launching pattern, can we reduce the battery consumption of the smartphones? We verified that battery efficiency can be improved and it is showed by real-world measurement.

IEEE JSAC (Journal on Selected Areas in Communications, Impact Factor: 3.672) is a most prestigious journal which covers the entire field of communications and networking.

[ ABSTRACT ]Each individual’s usage behavior on mobile devices depends on a variety of factors, such as time, location, and previous actions. Hence, context-awareness provides great opportunities to make the networking and computing capabilities of mobile systems more personalized and more efficient in managing their resources. To this end, we first reveal new findings from our own Android user experiment: 1) the launching probabilities of applications follow Zipf’s law and 2) inter-running and running times of applications conform to log-normal distributions.We also find contextual dependencies between application usage patterns, for which we classify contexts autonomously with unsupervised learning methods. Using the knowledge acquired, we develop a context-aware application scheduling framework, context-aware application scheduler (CAS), that adaptively unloads and preloads background applications for a joint optimization in which the energy saving is maximized and the user discomfort from the scheduling is minimized. Our trace-driven simulations with 96 user traces demonstrate that the context-aware design of the CAS enables it to outperform existing process scheduling algorithms. Our implementation of the CAS over Android platforms and its end-to-end evaluations verify that its human-involved design indeed provides substantial user-experience gains in both energy and application launching latency.

[ Overall architecture of CAS and its operations over time ]

FM-based Indoor Localization - Published at IEEE TMC 2015

Wireless signals from modern communication systems such as LTE and WiFi are operated in high frequencies (e.g., GHz). If we can utilize a lower frequency like FM radio which goes further and is readily available in most of the countries, can we build a pseudo universal indoor localization system? We have studied it and showed that it has a high potential.

* Many congratulations to YeoCheon Yun! This is YeoCheon Yun's first journal publication.

IEEE TMC (Transactions on Mobile Computing, Impact Factor: 2.912) is a top-notch mobile computing journal.

[ ABSTRACT ]We present ACMI, an FM-based indoor localization system that does not require proactive site profiling. ACMI constructs the fingerprint database based on pure estimation of indoor RSS (received signal strength) distribution, where only the signals transmitted from commercial FM radio stations are used. Based on extensive field measurement study, we established our own signal propagation model that harnesses FM radio characteristics and open information of FM transmission towers in combination with the floor-plan of a building. Output of the model is an RSS fingerprint database. Using the fingerprint database as a knowledge base, ACMI refines a positioning result via the two-step process; parameter calibration and path match- ing, during its runtime. Without site profiling, our evaluation indicates that ACMI in 7 campus locations and 3 downtown buildings using 8 distinguished FM stations finds positions in only about 6 and 10 meters of errors on average, respectively.

[ The indoor FM radio signal map estimated by our system with multiple levels (from left to right) of propagation modeling. ]