Self-aware systems for the Internet-of-Things

by SiHyeong Park on 2017-04-04 21:01:11

Date : 2017. 04. 10 (Mon) 16:00 Locate : EB5. 533 Presenter : Sihyeong Park   Title : Self-aware systems for the Internet-of-Things Author :  Mischa Möstl,  Johannes Schlatow,  Rolf Ernst,  Henry Hoffmann,  Arif Merchant,  Alexander Shraer Institute of Computer and Network Engineering, TU Braunschweig, Germany Systems Group, University of Chicago Google, Inc. Abstract : The IoT will host a large number of co-existing cyber-physical applications. Continuous change, application interference, environment dynamics and uncertainty lead to complex effects which must be controlled to give performance and application guarantees. Application and platform self-configuration and self-awareness are one paradigm to approach this challenge. They can leverage context knowledge to control platform and application functions and their interaction. They could play a dominant role in large scale cyber-physical systems and ... Continue reading →

57 Views

U-Wear: Software-Defined Ultrasonic Networking for Wearable Devices

by Jinse Kwon on 2017-03-30 21:16:22

Date : 2017. 04. 03 (Mon) 16:00 Locate : EB5. 533 Presenter : Jinse Kwon   Title : U-Wear: Software-Defined Ultrasonic Networking for Wearable Devices Author : G. Enrico Santagati, Tommaso Melodia (Northeastern University, Boston, MA, U.S.A.)   Abstract : Wearable medical sensing devices with wireless capabilities have become the cornerstone of many revolutionary digital health applications that promise to predict and treat major diseases by acquiring and processing health information. Existing wireless wearable devices are connected through radio frequency (RF) electromagnetic wave carriers based on standards such as Bluetooth or WiFi. However, these solutions tend to almost-blindly scale down traditional wireless technologies to the body environment, with little or no attention to the peculiar characteristics of the human body and the severe privacy and security requirements of patients. We contend that this is not the only possible ... Continue reading →

73 Views

CaffePresso: An Optimized Library for Deep Learning on Embedded Accelerator-based platforms

by Do Trung Hai on 2017-03-24 12:46:16

Date: 2017. 03. 27(Mon) 04:00 P.M. Locate: EB5. 533 Presenter: Trunghai Do Title: CaffePresso: An Optimized Library for Deep Learning on Embedded Accelerator-based platforms Author: G. Hegde, Siddhartha, N. Ramasamy, N. Kapre Abstract: Off-the-shelf accelerator-based embedded platforms offer a competitive energy-efficient solution for lightweight deep learning computations over CPU-based systems. Low-complexity classifiers used in power-constrained and performance-limited scenarios are characterized by operations on small image maps with 2- 3 deep layers and few class labels. For these use cases, we consider a range of embedded systems with 5-20W power budgets such as the Xilinx ZC706 board (with MXP soft vector processor), NVIDIA Jetson TX1 (GPU), TI Keystone II (DSP) as well as the Adapteva Parallella board (custom multi-core with NoC). Deep Learning computations push the capabilities of these platforms to the limit through compute-intensive evaluations of multiple 2D convolution ... Continue reading →

95 Views

PrefMiner: mining user's preferences for intelligent mobile notification management

by Jemin Lee on 2017-03-14 11:31:06

Date: 2017. 03. 20(Mon) 04:00 P.M. Locate: EB5. 533 Presenter: Jemin Lee Title: PrefMiner: mining user's preferences for intelligent mobile notification management Author: A. Mehrotra, R. Hendley, and M. Musolesi   Abstract : Mobile notifications are increasingly used by a variety of applications to inform users about events, news or just to send alerts and reminders to them. However, many notifications are neither useful nor relevant to users' interests and, also for this reason, they are considered disruptive and potentially annoying. In this paper we present the design, implementation and evaluation of PrefMiner, a novel interruptibility management solution that learns users' preferences for receiving notifications based on automatic extraction of rules by mining their interaction with mobile phones. The goal is to build a system that is intelligible for users, i.e., not just a "black-box" solution. Rules are shown to users who might decide to accept or ... Continue reading →

116 Views

I am a "Smart" watch, Smart Enough to Know the Accuracy of My Own Heart Rate Sensor

by Jinyoung Choi on 2017-03-08 17:19:17

Date : 2017. 03. 13(Mon) 04:00 P.M. Locate : EB5. 533 Presenter : Jinyoung Choi Title : I am a "Smart" watch, Smart Enough to Know the Accuracy of My Own Heart Rate Sensor Author : Ho-Kyeong Ra, Jungmo Ahn, Hee Jung Yoon, Dukyong Yoon, Sang Hyuk Son, JeonGil Ko   Abstract : With the wide-distribution of smart wearables, it seems as though ubiquitous healthcare can finally permeate into our everyday lives, opening the possibility to realize clinical-grade applications. However, given that clinical applications require reliable sensing, there is a need to understand how accurate healthcare sensors on wearable devices (e.g., heart rate sensors) are. To answer this question, this work starts with a thorough investigation on the accuracy of widely used wearable devices' heart rate sensors. Specifically, we show that when actively moving, heart rate readings can diverge far from the ground truth, and also show that such ... Continue reading →

131 Views

Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications

by Sungyup Lee on 2017-03-06 05:41:50

Date : 2017. 03. 06(Wed) 04:00 P.M. Locate : EB5. 533 Presenter : Sungyup Lee Title : Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications Author : Ala Al-Fuqaha, Senior Member, IEEE, Mohsen Guizani, Fellow, IEEE, Mehdi Mohammadi, Student Member, IEEE, Mohammed Aledhari, Student Member, IEEE, and Moussa Ayyash, Senior Member, IEEE   Abstract : This paper provides an overview of the Internet of Things (IoT) with emphasis on enabling technologies, protocols, and application issues. The IoT is enabled by the latest developments in RFID, smart sensors, communication technologies, and Internet protocols. The basic premise is to have smart sensors collaboratedirectlywithouthumaninvolvementtodeliveranewclass of applications. The current revolution in Internet, mobile, and machine-to-machine (M2M) technologies can be seen as the first phaseoftheIoT.Inthecomingyears,theIoTisexpectedtobridge diverse technologies to ... Continue reading →

98 Views

Protecting Privacy of BLE Device Users

by Ikhee Shin on 2016-12-16 16:04:01

Date : 2016.12.19(Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Ikhee Shin Title : Protecting Privacy of BLE Device Users Author : Kassem Fawaz, Kyu-Han Kim, Kang G. Shin Abstract Bluetooth Low Energy (BLE) has emerged as an attractive technology to enable Internet of Things (IoTs) to interact with others in their vicinity. Our study of the behavior of more than 200 types of BLE-equipped devices has led to a surprising discovery: the BLE protocol, despite its privacy provisions, fails to address the most basic threat of all—hiding the device’s presence from curious adversaries. Revealing the device’s existence is the stepping stone toward more serious threats that include user profiling/fingerprinting, behavior tracking, inference of sensitive information, and exploitation of known vulnerabilities on the device. With thousands of manufacturers and developers around the world, it is very challenging, if not impossible, to envision the ... Continue reading →

253 Views

Idea: A System for Efficient Failure Management in Smart IoT Environments

by Seula Hwang on 2016-12-01 14:19:15

Date : 2016. 12. 05 (Mon) 10:00 A.M. 2016.12.12(Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Seula Hwang Title : Idea: A System for Efficient Failure Management in Smart IoT Environments Author : Palanivel A. Kodeswaran, Ravi Kokku, Sayandeep Sen, Mudhakar Srivatsa Abstract IoT enabled smart environments are expected to proliferate significantly in the near future, particularly in the context of monitoring services for wellness living, patient healthcare and elderly care. Timely maintenance of failed sensors is of critical importance in such deployments to ensure minimal disruption to monitoring services. However, maintenance of large and geographically spread deployments can be a significant challenge. We present Idea that significantly increases the vtime-before-repair for a smart home deployment, thereby reducing the maintenance overhead. Specifically, our approach leverages the facts that (a) there is inherent sensor redundancy when combinations ... Continue reading →

296 Views

Presentation Rehearsal for Graduation thesis

by Jinyoung Choi on 2016-11-07 08:30:33

Date : 2016. 11. 07 (Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Jinyoung Choi   Title : 스마트폰의 상황정보와 스마트워치의 PPG 센서를 이용한 사용자 부정적 감성 예측 모델 Author : Jinyoung Choi   Continue reading →

337 Views

Presentation rehearsal for IEMEK conf' 2016 - 2

by Ikhee Shin on 2016-10-31 09:25:06

Date : 2016. 10. 31 (Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Ikhee Shin   Title : Evaluation of low power features in wearable OS Author : Ikhee Shin, Sungyup Lee, Hyungshin Kim   Abstract : Wearable devices have limited hardware resources because of its small battery capacity. An embedded operating system is necessary to provide services with limited hardware resources. power management is also required to handle services efficiently with a small battery capacity. We introduce Wearbench, a low power feature benchmark for wearable application, and use Wearbench to measure power consumption of embedded operating systems for nanoQplus, FreeRTOS, and ChibiOS. From the result, we suggest how to improve low power feature of embedded operating systems. Proceeding : Proceedings of Institute of Embedded Engineering of Korea 2016, November, 2016 Continue reading →

230 Views

Presentation rehearsal for IEMEK conf' 2016

by Jinse Kwon on 2016-10-30 22:51:11

Date : 2016. 10. 31 (Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Jinse Kwon   Title : A Disaster Warning System Using Ultrasound Modulation and Bluetooth Ad-hoc Network Author : Jinse Kwon, Jemin Lee, Hyungshin Kim   Abstract : A warning system is important to protect people and property from a disaster. Current disaster warning system could easily be collapsed by a disaster because it strongly depends on cell towers for mobile communication. In this paper, we present the ad hoc network to easily and rapidly update the disaster information using the ultrasound modulation and Bluetooth advertising mode in the communication failure state. Our system shows that a smartphone can detect modulation packets up to 720bit/s with bit-error-rate lower than 10-3. In addition, the Bluetooth ad hoc network in an advertising mode reduces the round trip delay between nodes and battery loss by adjusting the advertising period. Proceeding ... Continue reading →

218 Views

Learning sound location from a single microphone

by Do Trung Hai on 2016-10-27 11:07:44

Date : 2016. 11. 14 (Mon) 10:00 A.M. Location: EB5. 533 Presenter: Do Trung Hai   Seminar Title: Learning sound location from a single microphone Author: Ashutosh Saxena; Andrew Y. Ng  (Computer Science Department, Stanford University, CA 94305, USA) Abstract: We consider the problem of estimating the incident angle of a sound, using only a single microphone. The ability to perform monaural (single-ear) localization is important to many animals; indeed, monaural cues are also the primary method by which humans decide if a sound comes from the front or back, as well as estimate its elevation. Such monaural localization is made possible by the structure of the pinna (outer ear), which modifies sound in a way that is dependent on its incident angle. In this paper, we propose a machine learning approach to monaural localization, using only a single microphone and an “artificial pinna” (that distorts sound in a direction-dependent way). Our ... Continue reading →

193 Views

An RF doormat for tracking people's room locations

by Jinse Kwon on 2016-10-16 19:41:39

Date : 2016. 10. 16 (Mon) 10:00 A.M. Locate : EB5. 533 Presenter : Jinse Kwon   Title : An RF doormat for tracking people's room locations Author : Juhi Ranjan,Yu Yao, Kamin Whitehouse (University of Virginia, Charlottesville, VA, USA)   Abstract : Many occupant-oriented smarthome applications such as automated lighting, heating and cooling, and activity recognition need room location information of residents within a building. Surveillance based tracking systems used to track people in commercial buildings, are privacy invasive in homes. In this paper, we present the RF Doormat - a RF threshold system that can accurately track people's room locations by monitoring their movement through the doorways in the home. We also present a set of guidelines and a visualization to easily and rapidly setup the RF-Doormat system on any doorway. To evaluate our system, we perform 580 doorway crossings across 11 different doorways in a home. ... Continue reading →

161 Views

Presentation rehearsal for Smarttention 2016

by Jemin Lee on 2016-08-30 16:26:18

Date : 2016. 08. 31 (Wed) 10:00 A.M. Locate: EB5. 533 Presenter: Jemin Lee Seminar Title: Presentation Rehearsal for Smarttention 2016 I am planning to do a presentation with regard to my work, entitled "Reducing Distraction of Smartwatch Users with Deep Learning" in upcoming workshop. For preperation, the rehearsal will be tomorrow. For more inforamtion, vist http://mhci16.smarttention.com/#program         Continue reading →

208 Views

전달 세미나 : RTCSA 2016

by Seula Hwang on 2016-08-23 20:13:41

Date : 2016. 08. 24 (Wed) 10:00 A.M. Locate : EB5. 533 Presenter : Hwang Seula Seminar Title : Reviews for IWCPS 2016 and RTCSA 2016 Continue reading →

223 Views