Keum-Sung Hwang

Landmark detection from mobile life log using a modular Bayesian network model

Mobile devices can now handle a great deal of information thanks to the convergence of diverse functionalities. Mobile environments have already shown great potential in terms of providing customized services to users because they can record meaningful and private information continually for long periods of time. Until now, most of this information has been generally ignored because of the limitations of mobile devices in terms of power, memory capacity and speed. In this paper, we propose a novel method that efficiently infers landmarks for users to overcome these problems. This method uses an effective probabilistic Bayesian network model for analyzing various kinds of log data in mobile environments, which were modularized in this paper to decrease complexity. We also present a cooperative inference method, and the proposed methods were evaluated with mobile log data generated and collected in the real world.

Exploiting indoor location and mobile information for context-awareness service

Personal mobile devices such as cellular phones, smart phones and PMPs have advanced incredibly in the past decade. The mobile technologies make research on the life log and user-context awareness feasible. In other words, sensors in mobile devices can collect the variety of users information, and various works have been conducted using that information. Most of works used a users location information as the most useful clue to recognize the user context. However, the location information in the conventional works usually depends on a GPS receiver that has limited function, because it cannot localize a person in a building and thus lowers the performance of the user-context awareness. This paper develops a system to solve such problems and to infer a users hidden information more accurately using Bayesian network and indoor-location information. Also, this paper presents a new technique for localization in a building using a decision tree and signals for the Wireless LAN because the decision tree has many advantages which outweigh other localization techniques.

Modular bayesian networks for inferring landmarks on mobile daily life

Mobile devices get to handle much information thanks to the convergence of diverse functionalities. Their environment has great potential of supporting customized services to the users because it can observe the meaningful and private information continually for a long time. However, most of the information has been generally ignored because of the limitations of mobile devices. In this paper, we propose a novel method that infers landmarks efficiently in order to overcome the problems. It uses an effective probabilistic model of Bayesian networks for analyzing various log data on the mobile environment, which is modularized to decrease the complexity. The proposed methods are evaluated with synthetic mobile log data generated.

Generating cartoon-style summary of daily life with multimedia mobile devices

Mobile devices are treasure boxes of personal information containing users context, personal schedule, diary, short messages, photos, and videos. Also, users usage information on Smartphone can be recorded on the device and they can be used as useful sources of high-level inference. Furthermore, stored multimedia contents can be also regarded as relevant evidences for inferring users daily life. Without users consciousness, the device continuously collects information and it can be used as an extended memory of human users. However, the amount of information collected is extremely huge and it is difficult to extract useful information manually from the raw data. In this paper, AniDiary (Anywhere Diary) is proposed to summarize users daily life in a form of cartoonstyle diary. Because it is not efficient to show all events in a day, selected landmark events (memorable events) are automatically converted to the cartoon images. The identification of landmark events is done by modeling causal-effect relationships among various events with a number of Bayesian networks. Experimental results on synthetic data showed that the proposed system provides an efficient and user-friendly way to summarize users daily life.

Evolving diverse hardwares using speciated genetic algorithm

Evolvable hardware (EHW) has become an attractive topic recently because such hardware can reconfigure itself to adapt to the environment it is embedded in. EHW uses a genetic algorithm (GA), which is one of the evolutionary algorithms, to search for the goal hardware. In this paper, we propose EHW using a speciated GA that can evolve diverse circuits with single-step evolution. The speciation algorithm helps to find diverse solutions as the result of the evolution, and maintains the diversity during the evolution. We have applied a fitness-sharing method for speciation to the EHW of a 6-multiplexer, and have obtained diverse hardware structures. Also, we have found a circuit in 35% less generations than we did with a conventional genetic algorithm.

Improving evolvable hardware by applying the speciation technique

Evolvable hardware (EHW) has recently become a highly attractive topic of study because it offers a way of adapting hardware to a given embedded environment. However, it is not easy to evolve hardware efficiently and effectively, so many challenges continue to exist when trying to solve problems. In this paper, we propose a method that uses the speciation technique to enable diverse circuits to evolve efficiently by the process of one-step evolution. As a result of studying the landscape contained in the EHW example, we have found complicated spaces contain many peaks that can lead to deceptions when using the evolving process, and the speciation technique profits from the evolution of EHW. We also studied that the speciated hardware ensemble might be a good candidate for more complex and rigorous function. In the experiments, we applied the fitness sharing method as the speciation technique, and obtained diverse hardware modules, then ascertained the efficiency of these structures. We also show that several useful extra functions and better overall performance can be obtained by analyzing diverse circuits with the speciation technique.

Modular Bayesian Network Learning for Mobile Life Understanding

Mobile devices can now handle a great deal of information thanks to the convergence of diverse functionalities. Mobile environments have already shown great potential in terms of providing customized services to users because they can record meaningful and private information continually for long periods of time. Until now, most of this information has been generally ignored because of the limitations of mobile devices in terms of power, memory capacity and speed. In this paper, we propose a novel method that efficiently infers semantic information and overcome the problems. This method uses an effective probabilistic Bayesian network model for analyzing various kinds of log data in mobile environments, which were modularized in this paper to decrease complexity. We also discuss how to discover and update the Bayesian inference model by using the proposed BN learning method with training data. The proposed methods were evaluated with artificial mobile log data generated and collected in the real world.

A Lifelog Browser for Visualization and Search of Mobile Everyday-Life

Mobile devices can now handle a great deal of information thanks to the convergence of diverse functionalities. Mobile environments have already shown great potential in terms of providing customized service to users because they can record meaningful and private information continually for long periods of time. The research for understanding, searching and summarizing the everyday-life of human has received increasing attention in recent years due to the digital convergence. In this paper, we propose a mobile life browser, which visualizes and searches humans mobile life based on the contents and context of lifelog data. The mobile life browser is for searching the personal information effectively collected on his/her mobile device and for supporting the concept-based searching method by using concept networks and Bayesian networks. In the experiments, we collected the real mobile log data from three users for a month and visualized the mobile lives of the users with the mobile life browser developed. Some tests on searching tasks confirmed that the result using the proposed concept-based searching method is promising.

A Bayesian Network Framework for Vision Based Semantic Scene Understanding

For a robot to understand a scene, we have to infer and extract meaningful information from vision sensor data. Since scene understanding consists in recognizing several visual contexts, we have to extract these contextual cues and understand their relationships. However, context extraction from visual information is difficult due to uncertain information in variable environments, imperfect nature of the feature extraction methods and high computational complexity of reasoning from the complex relationship. In order to manage the uncertainties effectively, in this paper, we adopted Bayesian probabilistic approach, and proposed a Bayesian network framework that synthesizes the low level features and the high level semantic cues. It contains how to develop and utilize an integrated Bayesian network model. In the experimental results of two applications, the efficacy of the proposed framework is shown.

Robotic intelligence with behavior selection network for Bayesian network ensemble

Scene understanding is an important and difficult problem in intelligent robotics and computer vision. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty and powerful to model high-level contexts. Moreover, Bayesian network can be adapted to environment efficiently by learning. In this paper, we propose a Bayesian network ensemble technique based on behavior selection network. The method includes how to handle uncertainty based on probabilistic approach, and how to combine multiple Bayesian networks. An experiment with a mobile robot simulation presents how the proposed ensemble method works and can be used effectively.