Making Location-Aware Computing Working Accurately in Smart Spaces

2011 ◽  
pp. 539-557
Author(s):  
Teddy Mantoro ◽  
Media Ayu ◽  
Maarten Weyn
Keyword(s):  
Dynamic Environment ◽  
Sensor Data ◽  
Smart Environment ◽  
Nearest Neighbour ◽  
Localization Algorithm ◽  
Personal Computing ◽  
Location Aware ◽  
Computing Vision ◽  
User Location

In smart environment, making a location-aware personal computing working accurately is a way of getting close to the pervasive computing vision. The best candidate to determine a user location in indoor environment is by using IEEE 802.11 (Wi-Fi) signals, since it is more and more widely available and installed on most mobile devices used by users. Unfortunately, the signal strength, signals quality and noise of Wi-Fi, in worst scenario, it fluctuates up to 33% because of the reflection, refraction, temperature, humidity, the dynamic environment, etc. We present our current development on a light-weight algorithm, which is easy, simple but robust in producing the determination of user location using WiFi signals. The algorithm is based on “multiple observers” on ?k-Nearest Neighbour. We extend our approach in the estimation indoor-user location by using combination of different technologies, i.e. WiFi, GPS, GSM and Accelerometer. The algorithm is based on opportunistic localization algorithm and fuse different sensor data in order to be able to use the data which is available at the user position and processable in a mobile device.

scholarly journals Determination of Body Parts in Holstein Friesian Cows Comparing Neural Networks and k Nearest Neighbour Classification

Animals ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 50
Author(s):  
Jennifer Salau ◽  
Jan Henning Haas ◽  
Wolfgang Junge ◽  
Georg Thaller
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Body Parts ◽  
Nearest Neighbour ◽  
Data Set ◽  
3D Data ◽  
Holstein Friesian ◽  
Knn Classification ◽  
Friesian Cows

Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is still a widely studied topic and especially challenging when it comes to the partition of objects into predefined segments. In this study, two machine learning approaches were utilized for the recognition of body parts of dairy cows from 3D point clouds, i.e., sets of data points in space. The low cost off-the-shelf depth sensor Microsoft Kinect V1 has been used in various studies related to dairy cows. The 3D data were gathered from a multi-Kinect recording unit which was designed to record Holstein Friesian cows from both sides in free walking from three different camera positions. For the determination of the body parts head, rump, back, legs and udder, five properties of the pixels in the depth maps (row index, column index, depth value, variance, mean curvature) were used as features in the training data set. For each camera positions, a k nearest neighbour classifier and a neural network were trained and compared afterwards. Both methods showed small Hamming losses (between 0.007 and 0.027 for k nearest neighbour (kNN) classification and between 0.045 and 0.079 for neural networks) and could be considered successful regarding the classification of pixel to body parts. However, the kNN classifier was superior, reaching overall accuracies 0.888 to 0.976 varying with the camera position. Precision and recall values associated with individual body parts ranged from 0.84 to 1 and from 0.83 to 1, respectively. Once trained, kNN classification is at runtime prone to higher costs in terms of computational time and memory compared to the neural networks. The cost vs. accuracy ratio for each methodology needs to be taken into account in the decision of which method should be implemented in the application.

scholarly journals Thing Theory

2017 ◽  
pp. 249-265 ◽  
Author(s):  
Sally A. Applin ◽  
Michael D. Fischer
Keyword(s):  
Big Data ◽  
Communication Technologies ◽  
Social Awareness ◽  
The Internet ◽  
Smart Environment ◽  
Thing Theory ◽  
Making Sense ◽  
Location Aware ◽  
Resultant Data ◽  
The Internet Of Things

As healthcare professionals and others embrace the Internet of Things (IoT) and smart environment paradigms, developers will bear the brunt of constructing the IT relationships within these, making sense of the big data produced as a result, and managing the relationships between people and technologies. This chapter explores how PolySocial Reality (PoSR), a framework for representing how people, devices and communication technologies interact, can be applied to developing use cases combining IoT and smart environment paradigms, giving special consideration to the nature of location-aware messaging from sensors and the resultant data collection in a healthcare environment. Based on this discussion, the authors suggest ways to enable more robust intra-sensor messaging through leveraging social awareness by software agents applied in carefully considered healthcare contexts.

GRACE and GRACE-FO Level-1 V04 Data Processing Status

2020 ◽  
Author(s):  
Christopher Mccullough ◽  
Tamara Bandikova ◽  
William Bertiger ◽  
Carmen Boening ◽  
Sung Byun ◽  
...  
Keyword(s):  
Data Processing ◽  
Attitude Determination ◽  
Precise Orbit Determination ◽  
Mass Change ◽  
Sensor Data ◽  
The Earth ◽  
Analysis Center ◽  
Level 1 ◽  
Gravity Recovery

<p>The Gravity Recovery and Climate Experiment Follow-On (GRACE-FO), launched in May 2018, provides invaluable information about mass change in the Earth system, continuing the legacy of GRACE. Fundamental requirements for successful mass change recovery are precise orbit determination and inter-satellite ranging, determination of the relative clock alignment of the ultra-stable oscillators (USOs), precise attitude determination, and accelerometry. NASA/Caltech Jet Propulsion Laboratory is the official Level-1 data processing and analysis center, and is currently processing software version 04. Here we present analysis of the aforementioned GRACE-FO sensor data, as well a preview of an upcoming GRACE reprocessing, and a discussion of measurement performance.</p>

Information Management in Mobile Environments Using a Location-Aware Intelligent Agent System

2011 ◽  
pp. 1-17
Author(s):  
Amrish Vyas ◽  
Victoria Yoon
Keyword(s):  
Intelligent Agent ◽  
Location Based Services ◽  
Agent System ◽  
Content Dissemination ◽  
New Era ◽  
Location Aware ◽  
Spatio Temporal ◽  
Types Of Information ◽  
Push And Pull ◽  
User Location

Recent rise in the level of comfort and demand to access various types of information using mobile devices can be attributed to the advancements in wireless as well as Internet technologies. This demand leads us to the new era of mobile computing. Location-based services (LBS) are engendering new passion in mobile services utilizing users’ location information. Such spatio-temporal information processing entails the need for a dynamic middleware that accurately identifies changing user location and attaches dependent content in real-time without putting extra burden on users. Our work focuses on creating a distributed infrastructure suitable to support such scalable content dissemination. As a result this chapter offers a conceptual framework, location-aware intelligent agent system (LIA) in integration with publish/subscribe middleware to comprehensively address dynamic content dissemination and related issues. We discuss the operational form of our framework in terms of PUSH and PULL strategies.

scholarly journals Sediment Transport in Sewage Pressure Pipes, Part I: Continuous Determination of Settling and Erosion Characteristics by In-Situ TSS Monitoring Inside a Pressure Pipe in Northern Germany

Water ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 2125 ◽  
Author(s):  
Martin Rinas ◽  
Jens Tränckner ◽  
Thilo Koegst
Keyword(s):  
Sediment Transport ◽  
Sensor Data ◽  
Urban Region ◽  
Calibration Data ◽  
Northern Germany ◽  
Erosion Behavior ◽  
Pressure Pipe ◽  
One Year

Continuous measurement systems are widely spread in sewers, especially in non-pressure systems. Due to its relatively low costs, turbidity sensors are often used as a surrogate for other indicators (solids, heavy metals, organic compounds). However, little effort is spent to turbidity sensors in pressurized systems so far. This work presents the results of one year in-situ turbidity/total suspended solids (TSS) monitoring inside a pressure pipe (600 mm diameter) in an urban region in northern Germany. The high-resolution sensor data (5 s interval) are used for the determination of solids sedimentation (within pump pauses) and erosion behavior (within pump sequences). In-situ results from sensor measurements are similar to laboratory results presented in previous studies. TSS is decreasing exponentially in pump pauses under dry weather inflow with an average of 0.23 mg/(L s). During pump sequences, solids eroded completely at a bed shear stress of 0.5 N/m². Sedimentation and erosion behavior changes with the inflow rate. Solids settle faster with increasing inflow: at storm water inflow with an average of 0.9 mg/(L s) and at diurnal inflow variation up to 0.6 mg/(L s) at 12:00 a.m. The results are used as calibration data for a sediment transport simulation in Part II.

Sign in / Sign up

Export Citation Format

Share Document