Wearable Sensing Framework for Human Activity Monitoring Mostafa Uddin, Ahmed Salem, Ilho Nam, and Tamer Nadeem Old Dominion University {muddin, asalem, inam, nadeem}@cs.odu.edu ABSTRACT Wearable computation is getting integrated into our daily life day by day. In this work, we propose a generic frame- work to continuously monitor users’ daily activities. The framework proposes light computation tasks on the wear- able device to reduce the amount of data communicated be- tween the wearable, and its host. A 9-axis wristbands are being used to collect user’s activities. The collected signals are subject to light weight preprocessing and segmentation on the wearable device prior sending to the host, were it goes through activity detection algorithms. In this paper, we elaborate the feasibility of the proposed framework thru presenting two case studies. Categories and Subject Descriptors C.2.1 [Computer Communication and Networks]: Net- work Architecture and Design—Wireless communication ; C.5.3 [Computer System Implementation]: Microcomputers— Portable devices ; I.2.10 [Artificial Intelligence]: Vision and Scene Understanding—Motion Keywords Wearable Computing, Activity monitor, Inertial measure- ment unit, Data Communication, BLE 1. INTRODUCTION Recently, wearable devices got a lot of interests and wide acceptance due to their small sizes, reasonable computation power, and practical power capabilities. These wearable de- vices loaded with sensors (e.g. accelerometer, gyroscope) provides a good candidate to monitor users’ daily behavior (e.g. walking, jogging, smoking) [4]. Nowadays wearable de- vices are used in several domains (e.g. activity detection), were health monitoring is one of the prominent. Recent advancement of wearable technology have resulted in utilization of wearable and non-intrusive systems for health and activity monitoring. Such continuous monitoring of life Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. WearSys’15, May 18, 2015, Florence, Italy. Copyright c  2015 ACM 978-1-4503-3500-3/15/05 ...$15.00. http://dx.doi.org/10.1145/2753509.2753513. Figure 1: 9-axis IMU wearable device and daily activities, motivate the users to maintain healthy living style. Moreover, wearable technology has empowered the user to quantify, and take control of their lifestyle. In the long run, such consciousness among people will help the soci- ety to be healthy and productive. Maintaining such healthy life will also reduce the cost of health-care by allowing the people to spend less time in the hospital or make fewer visit to the doctor. Wearable technology faces three main challenges: commu- nication capacity, computation power, and limited energy of the wearable device [10]. In this paper, we propose a frame- work to continuously monitor user activity using wearable devices. The framework provides a mechanism for wearable device to reduce the overhead of data communication. Thus, it allows wearable device to manage its power consumption in more efficient way. Furthermore, the proposed frame- work reduces the typical data processing overhead required by the monitoring applications. Moreover, it provides more flexibility for the applications to configure their monitoring requirements. In the proposed framework we split the activity monitor- ing task between both the wearable device and a correspond- ing host such as the smartphone. The wearable device is responsible for collection, cleaning, and segmentation of the raw data. On the other hand, the monitoring application on the host device will process these data segments according to its activity detection interest.