Konlakorn Wongpatikaseree

Activity Recognition Using Context-Aware Infrastructure Ontology in Smart Home Domain

Nowadays, activity recognition has been proposed in several researches. It is attractive to improve the ability of the activity recognition system because existing research on activity recognition systems still have an error in an ambiguous cases. In this paper, we introduce the novel technique to improve the activity recognition system in smart home domain. We propose the three contributions in this research. Firstly, we design the context-aware infrastructure ontology for modelling the users context in the smart home. The innovative data, human posture, is added into the users context for reducing the ambiguous cases. Secondly, we propose the concepts to distinguish the activities by object-based and location-based concepts. We also present the description logic (DL) rules for making the human activity decision based on our proposed concepts. Lastly, We conduct the Ontology Based Activity Recognition (OBAR) system for two purposes: to recognize the human activity, and to search the semantic information in the system, called semantic ontology search (SOS) system. The results show the system can recognize the human activity correctly and also reduce the ambiguous case.

OAM: An Ontology Application Management Framework for Simplifying Ontology-Based Semantic Web Application Development

Although the Semantic Web data standards are established, ontology-based applications built on the standards are relatively limited. This is partly due to high learning curve and efforts demanded in building ontology-based Semantic Web applications. In this paper, we describe an ontology application management (OAM) framework that aims to simplify creation and adoption of ontology-based application that is based on the Semantic Web technology. OAM introduces an intermediate layer between user application and programming and development environment in order to support ontology-based data publishing and access, abstraction and interoperability. The framework focuses on providing reusable and configurable data and application templates, which allow the users to create the applications without programming skill required. Three forms of templates are introduced: database to ontology mapping configuration, recommendation rule and application templates. We describe two case studies that adopted the framework: activity recognition in smart home domain and thalassemia clinical support system, and how the framework was used in simplifying development in both projects. In addition, we provide some performance evaluation results to show that, by limiting expressiveness of the rule language, a specialized form of recommendation processor can be developed for more efficient performance. Some advantages and limitations of the application framework in ontology-based applications are also discussed.

Range-based algorithm for posture classification and fall-down detection in smart homecare system

Human posture classification is one of the most challenging issues in smart homecare system. To achieve high classification accuracy, we propose a new algorithm, called range-based algorithm. In this paper, a range means the distance between body parts. The ranges between body parts are investigated to classify the human posture and to detect a possible fall-down accident. Furthermore, we also proposed an adaptive posture window scheme to recognize the human posture in real-time even though human change the posture in different speed. The results reveal that our proposed can classify the human posture and detect fall-down with high accuracy and reliability.

Location-Based Concept in Activity Log Ontology for Activity Recognition in Smart Home Domain

Activity recognition plays an important role in several researches. Nevertheless, the existing researches suffer various kinds of problems when human has a different lifestyle. To address these shortcomings, this paper proposes the activity log in the context-aware infrastructure ontology in order to interlink the history user’s context and current user’s context. In this approach, the location-based concept is built into the activity log for producing the description logic (DL) rules. The relationship between activities in the same location is investigated for making the result of activity recognition more accurately. We also conduct the semantic ontology search (SOS) system for evaluating the effectiveness of our proposed ideas. The semantic data can be retrieved through SOS system, including, human activity and activity of daily living (ADL). The results from SOS system showed the advantage overcome the existing system when uses the location-based concept in activity log ontology.

Context-Aware Posture Analysis in a Workstation-Oriented Office Environment

Among current research trends, correction of the sitting posture is attracting growing attention. Most office workers suffer several health problems during their work. The two greatest causes of health problems in the office environment are simple things. The first is poor sitting posture. Sitting with poor posture in front of a computer for hours causes cumulative damage. The second is an inappropriate workstation environment. The workstation environment is related to good sitting posture. For example, if the desk is too low, the user has to lean forward to look at the display. To address this problem, we propose a sitting posture recognition system that can recognize both human posture and the context of the workstation environment. The proposed system has three components. First, skeleton tracking is used to create a sideways view of the human skeleton. The skeleton model in this research is used to measure the joint angles of the human body. Second, we detect information on objects using a proposed workstation environment tracking system. Three types of features are used to filter the objects from the depth image. Finally, we compare the overall information with a standard sitting posture in a model-matching component. Experimental studies showed that the system can provide the necessary information for analyzing the human posture. A physician or user can apply this information to achieve correct sitting posture or prevent health problems in the office using the provided results.

Architecture for Organizing Context-Aware Data in Smart Home for Activity Recognition System

Knowing human activity in each day is relevant information in several purposes. However, existing activity recognition systems have limitation to identify the human activity because they cannot get the appropriate information for recognition. To address this limitation, we present three relevant components in Context-aware Activity Recognition Engine CARE architecture for organizing context-aware information in home. First, we introduce Context Sensor Network CSN. The CSN provides the raw environment information from the diversity of sensors. Second, data manager component is proposed to process the pre-processing in the raw data from the CSN. The data must be normalized and transformed in order to make the system more efficient. The last component is system repository that composes of three essential tasks for controlling the information in the system. In this paper, the ontology based activity recognition OBAR system is used to evaluate the data from proposed components. The high accuracy of results can refer to the well organization of proposed components.

Analysis of the thermal comfort and power consumption in apartment domain

Nowadays, energy saving in living space is the most popular issue in many countries. Several domains relate to the energy saving issue. One of them is a thermal comfort domain. The ways to analyze and control the room temperature have been proposed in several research works, especially in home domain. However, considering only home structure is not enough for energy management system (EMS) in the city. Other building structures are needed to be identified. In this paper, we aim to analyze the room temperature and the power consumption in an apartment domain. An apartment simulation is developed to simulate the environment data in each room. The results showed that each room in apartment could transfer the heat to other rooms through the walls. The neighbor rooms temperature also affects the use of air-conditioner. When the room temperature is high, the air-conditioner has to operate the maximum power to change the room temperature reaching a suitable comfortable level.