The TPC workshop is hosted by Professor Jie Gao.
Tentative agenda:
08:00-08:10 Introduction and Opening Remarks
08:10-08:35 Rui Tan (Nanyang Technological University) "Deep Room Recognition using Inaudible Echos".
Recent years have seen the increasing need of location awareness by mobile applications. This paper presents a room-level indoor localization approach based on the measured room's echos in response to a two-millisecond single-tone inaudible chirp emitted by a smartphone's loudspeaker. In contrast to other acoustics-based room recognition systems that record full-spectrum audio for up to ten seconds, our approach records audio in a narrow inaudible band for 0.1 seconds only, respecting well the user's privacy. However, the short-time and narrow-band audio record carries limited information about the room's characteristics, presenting challenges to the design of effective room recognition algorithms. This paper applies deep learning to capture the subtle differences in the rooms' acoustic responses. Our extensive experiments based on real echo data show that a multilayer convolutional neural network fed with the spectrogram of the inaudible echos achieve the best performance, compared with alternative designs using other raw data forms and deep models. Based on this result, we design a RoomRecognize cloud service and its mobile client library that enable the mobile application developers to readily implement the room recognition functionality without resorting to any existing infrastructures and add-on hardware to smartphones. The RoomRecognize also supports a participatory learning mode where the users can contribute training data that can be collected and labeled easily. Evaluation shows that RoomRrecognize achieves 95% accuracy in differentiating 22 rooms.
08:35-09:00 Jorge Ortiz (IBM Research), "Adding Intelligence to the Internet of Things ".
The Internet-of-Things (IoT) has seen explosive growth in recent years. The number of IoT devices in use has doubled in the last three years -- over 8 Billion devices in use today -- and is expected to double again by 2020. The potential impact IoT will have on society is massive, with growth in such areas as intelligent buildings, smart infrastructure, and healthcare. However, the true value of these deployments cannot be realized without intelligent tools that automate or help end users deal with scale effectively -- both in the number and diversity of devices. In this talk, I will discuss a set of technical challenges in several IoT application domains, including smart buildings and commercial IoT device management. More specifically, I will describe the challenges with metadata management in the built environment and how transfer learning and active learning can help address them. I will also present results from a study that aims to identify IoT devices in the wild by analyzing and classifying their network traffic.
09:00-09:25 Andrew Markham (University of Oxford), "Long-Range IMU-Aided Magneto-Inductive Localization for Trackworker Safety ".
Localisation is of importance for many applications. Our motivating scenarios are short-term construction work and emergency rescue. Not only is accuracy necessary, these scenarios also require rapid setup and robustness to environmental conditions. These requirements preclude the use of many traditional methods e.g. vision-based, laser-based, Ultra-wide band (UWB) and Global Positioning System (GPS)-based localisation systems. To solve these challenges, we introduce iMag, an accurate and rapidly deployable inertial magneto-inductive (MI) localisation system. It localises monitored workers using a single MI transmitter and inertial measurement units with minimal setup effort. However, MI location estimates can be distorted and ambiguous. To solve this problem, we suggest a novel method to use MI devices for sensing environmental distortions, and use these to correctly close inertial loops. By applying robust simultaneous localisation and mapping (SLAM), our proposed localisation method achieves excellent tracking accuracy, and can improve performance significantly compared with only using an inertial measurement unit (IMU) and MI device for localisation.
09:25-09:50 Chenren Xu (Peking University), "PassiveVLC: Enabling Practical Visible Light Backscatter Communication for Battery-free IoT Applications".
This talk presents PassiveVLC, a ultra-low power communication subsystem for IoT connectivity. It is based on the idea of modulating the light retroreflection with a commercial LCD shutter to realize a passive optical transmitter and thus visible light backscatter communication. PassiveVLC system enables a battery-free tag device to perform passive communication with the illuminating LEDs over the same light carrier, is flexible with tag orientation, robust to ambient lighting conditions, and can achieve up to 1 kbps uplink speed.
09:50-10:05 Break
10:05-10:30 Tam Vu (University of Colorado, Denver), "Passively Sensing Drone Using Radio Signals".
10:30-10:55 Hae Young Noh (Carnegie Mellon University), "Structure as Sensors: Indirect Monitoring of Humans and Environments ".
10:55-11:20 Rong Zheng (McMaster University), "Asynchronous Acoustic Indoor Positioning "
Acoustic ranging based indoor positioning solutions have the advantage of higher ranging accuracy and better compatibility with commercial-off-the-self consumer devices. However, similar to other time-domain based approaches using Time-of-Arrival and Time-Difference-of-Arrival, they suffer from performance degradation in presence of multi-path propagation and low received signal-to-noise ratio (SNR) in indoor environments. In this talk, we present ARABIS, a robust and low-cost acoustic positioning system (IPS) for mobile devices. We design a low-cost acoustic board custom-designed to support large operational ranges and extensibility. To mitigate the effects of low SNR and multi-path propagation, a robust algorithm is devised that takes advantage of redundant TDoA estimates. Experiments have been carried in two testbeds of sizes 10.67m by 7.76m and 15m by 15m, one in an academic building and one in a convention center. The proposed system achieves average and 95% quantile localization errors of 7.4cm and 16.0cm in the first testbed with 8 anchor nodes and average and 95\% quantile localization errors of 20.4cm and 40.0cm in the second testbed with 4 anchor nodes only.
11:20-11:45 Junehwa Song (KAIST), TBD
11:45-12:10 Guoliang Xing (Michigan State University), TBD
12:10 Lunch at Student Activity Center (SAC)
