Dongjun Suh

Ubi-Floor: Design and Pilot Implementation of an Interactive Floor System

Ubi-floor is designed as an interactive floor system which allows user to interact with a floor based smart environment. Concerning context aware floor system, previous researches typically dealt with simple ideas of using gate pattern recognition supported by piezoelectric sensing devices or personal identification mediated by body weight estimation that cannot fully support position dependent context-awareness not to mention interactive interfaces based on it. This paper describes the design and implementation of an interactive floor system that is capable of dealing with various context aware multimedia applications such as visual displays, floor based games, navigation through geographical maps and recording or playing video memo triggered by the menu selections through foot step tracking interface. In addition, this pilot system is recognized as a highly scalable modular prototype of an innovative digital floor system applicable to diversified ubiquitous environments. Furthermore, the system is likely to provide highly enhanced usability of a smart floor system largely affected by various applications that could be adopted. Our further study will include the integration of this ubi-floor platform with various applications in the domain of ubiquitous computing.

Modularized multimedia framework for multi-modal and multi-functional interactions

Smart Architectural Surface is a novel and highly integrated planar construct for diversified smart home services with networked smart cell units equipped with various sensing, cognition and actuation capabilities that would allow run-time polymorphism as the basis for functional changes for various event-driven operation scenarios. The SAS system can demonstrate the outcomes of collective intelligence that are mediated by various multi-modal interactions. Current SAS prototype is capable of polymorphous functional changes for dynamically adjustable electronic wallpaper, location/distance-aware video conferencing, personalized information browser, and automatic responses to various unintended events. Future applications would harness machine learning and machine vision techniques and will explore the advantages of having computational ecology of its digital modular units constituting smart wall system for multi-modal and multi-functional interactions.

Auto-localized multimedia platform based on a modular Cyber Physical System aligned in a two-dimensional grid

In this research, a smart mechanism to automatically configure the relative locations of clustered intelligent nodes arranged in a grid pattern is introduced. If an intelligent node knows the relative location of more than one neighboring node, its location can be recognized. By studying the feature of the grid structure and the short-range infrared signal communication method between the adjacent nodes, the location of an intelligent node and the location map construction of the whole system are configured automatically at each node. The algorithms in this study are tested by a cross-module image or video display task with modularized and reconfigurable digital surface, a modular Cyber-Physical System platform which has stacked ‘smart modules’ each of which has smart sensing and multimedia node with infra-red transceivers at four corners. Exemplary applications demonstrate the feasibility of the system in its scalability and practicality as well as performance by being applied to various spatially reconfigurable multimedia platforms.

Autonomous Lighting Control Based on Adjustable Illumination Model

Autonomous lighting control systems require a numerical illumination model in which the light level output in a room can be expected according to given dimming control inputs. Stationary illumination models, such as the zonal cavity method and the point by point method, might be difficult to adjust the model to on-site environments in which are suffused with various shading artifacts unconsidered in a preceding simulation stage. Thus, this paper suggests an adjustable illumination model through Neural Network which can fit the model to the environments by a learning technology. Secondly, the autonomous lighting control can be realized by using the inverse of the illumination model. A small-sized replica of an actual lighting space is used for evaluation of our approach.

LAMF: Lighting Adjustment for Mood by Food: RFID Based Context Aware Food Ordering and Lighting Control System at Restaurants

A Ubiquitous environment is expected to provide appropriate services based on the identified context regardless of time and place. For satisfying this demand, activated communication among participating objects is essential. RFID is in the spotlight as communication means due to its economic feasibility and expandability and has been attempted to be applied to various domains. The system proposed in this research is a part of smart restaurant system that automatizes food order, bill payment and mood associated lighting control depending on the served food types supported mainly by the RFID technology. This efficient and innovative system could not only reduce time and cost for managing a restaurant but also provides synthesized real-time mood lighting for the customers to enhance their emotion rich dining experiences.

Perceived Quality Measurement Model Supporting Full Session Mobility in Multimedia Service Delivery

Context-awareness is associated with the concept of machines being able to both recognize and react to the surrounding environment, which has accelerated multimedia computing technology to provide user-oriented intelligent services. The goal of this research focuses on the modeling of video quality measurement in seamless video service delivery process considering the mobility patterns of users. Mobility supporting schemes providing seamless multimedia services are classified into host mobility and user mobility. The former refers to a host-level handoff while the latter indicates a user-level handoff. In host-level handoff, the decisive factors affecting the quality of video contents consumption are the total distance between hosts, the distance to resume streaming while the user is in mobility mode as well as the screen size of the end host. The influential parameters affecting the degree of video quality and seamlessness are evaluated by a subjective quality assessment and then a perceived video quality model was developed, accordingly. In addition, the optimal video delivery switching point to enable user mobility based video service is studied through the quality analysis of host mobility services at varying distances among the hosts. Experimental results show that the proposed quality model has high correlation with assessed quality and is useful to enable an adequate seamless mobility for multimedia service delivery.

Exploration of heuristic rules for green home design decision support system

Through a serious of energy simulation sessions, it is possible to compare energy performance pertaining to the different internal layouts applicable to typical apartment housing units to identify generalized rules for residential building design strategies and generating energy-saving alternatives. We explored the impact of different attributes of the internal walls such as length, material, geometry, and location on the heating load profiles by using multiple sensitivity analyses based on the Design Builder simulation tool. The results are summarized into a set of heuristic rules for evaluating apartment units internal layout design alternatives to maximize their energy performance.

Hybrid Particle Swarm Optimization for Multi-Sensor Data Fusion

A hybrid particle swarm optimization (PSO), able to overcome the large-scale nonlinearity or heavily correlation in the data fusion model of multiple sensing information, is proposed in this paper. In recent smart convergence technology, multiple similar and/or dissimilar sensors are widely used to support precisely sensing information from different perspectives, and these are integrated with data fusion algorithms to get synergistic effects. However, the construction of the data fusion model is not trivial because of difficulties to meet under the restricted conditions of a multi-sensor system such as its limited options for deploying sensors and nonlinear characteristics, or correlation errors of multiple sensors. This paper presents a hybrid PSO to facilitate the construction of robust data fusion model based on neural network while ensuring the balance between exploration and exploitation. The performance of the proposed model was evaluated by benchmarks composed of representative datasets. The well-optimized data fusion model is expected to provide an enhancement in the synergistic accuracy.

A Knowledge-Based Energy Management Model that Supports Smart Metering Networks for Korean Residential Energy Grids

Abstract The various energy management technologies that are required in order to deliver effective energy demand responses have resulted from the integrated use of digital technologies with energy grids. Therefore, the core technologies for smart metering infrastructure are regarded as a key issue in the design of future energy grids. The proposed knowledge-based model that supports advanced metering networks is capable of estimating energy consumption according to the characteristics of residential buildings. The energy consumption data is analyzed according to the residential building’s properties, which can significantly affect the energy consumption pattern. Therefore, appropriately designed models for energy consumption patterns with respect to identifying each energy consumption feature’s potential impact can be applied to create smart metering networks for future energy grid environments. This study introduces a knowledge-based model that considers both the energy and building management profiles. Then, case studies for the estimation of the energy consumption are presented. The proposed model could be effectively utilized in managing the energy demand response process with respect to market prices and residential energy shortages, and it provides a good reference for designing energy demand response strategies in Korean residential energy grid environments.

Estimation of Water Demand in Residential Building Using Machine Learning Approach

This paper shows an estimation model for residential water consumption using machine learning approach in Korea. We verify the diversifying elements constituting apartment buildings as input datasets for the Back- Propagation Neural Network (BPNN), the most novel supervised learning neural network based model in accordance with the empirical water use data. A water use prediction for residential buildings is a complex and nonlinear function of geographic, climatic, and morphological variables of buildings. For the verification purpose, empirical data sets consisting of water usage data retrieved from multiple residential apartment buildings in Korea were analyzed as case studies. The proposed model accurately forecast water uses for each examined residential apartment buildings. The results of the proposed models could offer a reliable water supply to meet the useful needs of customers and the local community while facilitating the efficient consumption of water.