Acquiring in situ training data for context-aware ubiquitous computing applications

Abstract. Satellite-Derived Bathymetry (SDB) has been used in many applications related to coastal management. SDB can efficiently fill data gaps obtained from traditional measurements with echo sounding. However, it still requires numerous training data, which is not available in many areas. Furthermore, the accuracy problem still arises considering the linear model could not address the non-relationship between reflectance and depth due to bottom variations and noise. Convolutional Neural Networks (CNN) offers the ability to capture the connection between neighbouring pixels and the non-linear relationship. These CNN characteristics make it compelling to be used for shallow water depth extraction. We investigate the accuracy of different architectures using different window sizes and band combinations. We use Sentinel-2 Level 2A images to provide reflectance values, and Lidar and Multi Beam Echo Sounder (MBES) datasets are used as depth references to train and test the model. A set of Sentinel-2 and in-situ depth subimage pairs are extracted to perform CNN training. The model is compared to the linear transform and applied to two other study areas. Resulting accuracy ranges from 1.3 m to 1.94 m, and the coefficient of determination reaches 0.94. The SDB model generated using a window size of 9x9 indicates compatibility with the reference depths, especially at areas deeper than 15 m. The addition of both short wave infrared bands to the four visible bands in training improves the overall accuracy of SDB. The implementation of the pre-trained model to other study areas provides similar results depending on the water conditions.

Download Full-text

In Situ Abnormal Behaviours Detection

Modelling Measurement and Control C ◽

10.18280/mmc_c.811-401 ◽

2020 ◽

Vol 81 (1-4) ◽

pp. 1-6

Author(s):

Chaima Bouali ◽

Olivier Habert ◽

Abderrahim Tahiri

Keyword(s):

Elderly Person ◽

Warning Signs ◽

Activity Level ◽

Home Automation ◽

Context Aware ◽

Behavioural Analysis ◽

Health Related ◽

Relevant Context ◽

Health Complications

This work describes a ‘detection of abnormal activities and health-related changes’ system for an elderly person at her/his home. The analysis is based on the data collected by a domotic box of the market. The box was initially designed to continuously recognize the owner’s daily activities in order to anticipate anomalies and consequently prevent health complications and enhance the rate of disease prevention. The box uses non-intrusive home automation sensors to detect the activity level of the occupants. It is equipped also with other technologies, including humidity sensors, bed and chair sensors to name a few. In order to build a system capable of intercepting warning signs for early intervention, we adopt a Hidden Markov Model based approach that we will initialize beforehand with the activity sequences of the user within a given period. The outcomes of the model paves the way for deducting the final judgement and reporting a relevant context-aware alert to healthcare service experts. Other statistical processes might complete this behavioural analysis later on to enhance the alerts accuracy.

Download Full-text

Context-Awareness and Mobile Devices

Handbook of Research on User Interface Design and Evaluation for Mobile Technology ◽

10.4018/978-1-59904-871-0.ch013 ◽

2008 ◽

pp. 205-217 ◽

Cited By ~ 18

Author(s):

Anind K. Dey ◽

Jonna Häkkilä

Keyword(s):

Human Computer Interaction ◽

Mobile Computing ◽

Ubiquitous Computing ◽

Mobile Devices ◽

Context Awareness ◽

Design Guidelines ◽

Context Aware ◽

Definition Of ◽

Mobile Context ◽

Computer Interaction

Context-awareness is a maturing area within the field of ubiquitous computing. It is particularly relevant to the growing sub-field of mobile computing as a user’s context changes more rapidly when a user is mobile, and interacts with more devices and people in a greater number of locations. In this chapter, we present a definition of context and context-awareness and describe its importance to human-computer interaction and mobile computing. We describe some of the difficulties in building context-aware applications and the solutions that have arisen to address these. Despite these solutions, users have difficulties in using and adopting mobile context-aware applications. We discuss these difficulties and present a set of eight design guidelines that can aid application designers in producing more usable and useful mobile context-aware applications.

Download Full-text

A Seamless Service Management with Context-Aware Handoff Scheme in Ubiquitous Computing Environment

Management of Convergence Networks and Services - Lecture Notes in Computer Science ◽

10.1007/11876601_14 ◽

2006 ◽

pp. 132-141 ◽

Cited By ~ 1

Author(s):

Tae-Hoon Kang ◽

Chung-Pyo Hong ◽

Won-Joo Jang ◽

Shin-Dug Kim

Keyword(s):

Ubiquitous Computing ◽

Service Management ◽

Context Aware ◽

Computing Environment ◽

Ubiquitous Computing Environment ◽

Seamless Service

Download Full-text

The Context-Security Nexus in Ubiquitous Computing

Leadership and Personnel Management ◽

10.4018/978-1-4666-9624-2.ch030 ◽

2016 ◽

pp. 660-679

Author(s):

M. Fahim Ferdous Khan ◽

Ken Sakamura

Keyword(s):

Access Control ◽

Ubiquitous Computing ◽

Context Awareness ◽

Contextual Information ◽

Healthcare Services ◽

Context Aware ◽

Context Sensitive ◽

Access Control Models ◽

Spatio Temporal ◽

The Right

Context-awareness is a quintessential feature of ubiquitous computing. Contextual information not only facilitates improved applications, but can also become significant security parameters – which in turn can potentially ensure service delivery not to anyone anytime anywhere, but to the right person at the right time and place. Specially, in determining access control to resources, contextual information can play an important role. Access control models, as studied in traditional computing security, however, have no notion of context-awareness; and the recent works in the nascent field of context-aware access control predominantly focus on spatio-temporal contexts, disregarding a host of other pertinent contexts. In this paper, with a view to exploring the relationship of access control and context-awareness in ubiquitous computing, the authors propose a comprehensive context-aware access control model for ubiquitous healthcare services. They explain the design, implementation and evaluation of the proposed model in detail. They chose healthcare as a representative application domain because healthcare systems pose an array of non-trivial context-sensitive access control requirements, many of which are directly or indirectly applicable to other context-aware ubiquitous computing applications.

Download Full-text

Integrating National Ecological Observatory Network (NEON) Airborne Remote Sensing and In-Situ Data for Optimal Tree Species Classification

Remote Sensing ◽

10.3390/rs12091414 ◽

2020 ◽

Vol 12 (9) ◽

pp. 1414

Author(s):

Victoria M. Scholl ◽

Megan E. Cattau ◽

Maxwell B. Joseph ◽

Jennifer K. Balch

Keyword(s):

Remote Sensing ◽

Tree Species ◽

Training Data ◽

Data Sets ◽

Airborne Remote Sensing ◽

Species Classification ◽

Crown Diameter ◽

External Data ◽

Data Products

Accurately mapping tree species composition and diversity is a critical step towards spatially explicit and species-specific ecological understanding. The National Ecological Observatory Network (NEON) is a valuable source of open ecological data across the United States. Freely available NEON data include in-situ measurements of individual trees, including stem locations, species, and crown diameter, along with the NEON Airborne Observation Platform (AOP) airborne remote sensing imagery, including hyperspectral, multispectral, and light detection and ranging (LiDAR) data products. An important aspect of predicting species using remote sensing data is creating high-quality training sets for optimal classification purposes. Ultimately, manually creating training data is an expensive and time-consuming task that relies on human analyst decisions and may require external data sets or information. We combine in-situ and airborne remote sensing NEON data to evaluate the impact of automated training set preparation and a novel data preprocessing workflow on classifying the four dominant subalpine coniferous tree species at the Niwot Ridge Mountain Research Station forested NEON site in Colorado, USA. We trained pixel-based Random Forest (RF) machine learning models using a series of training data sets along with remote sensing raster data as descriptive features. The highest classification accuracies, 69% and 60% based on internal RF error assessment and an independent validation set, respectively, were obtained using circular tree crown polygons created with half the maximum crown diameter per tree. LiDAR-derived data products were the most important features for species classification, followed by vegetation indices. This work contributes to the open development of well-labeled training data sets for forest composition mapping using openly available NEON data without requiring external data collection, manual delineation steps, or site-specific parameters.

Download Full-text