Young-Seol Lee

Activity recognition using hierarchical hidden markov models on a smartphone with 3D accelerometer

As smartphone users have been increased, studies using mobile sensors on smartphone have been investigated in recent years. Activity recognition is one of the active research topics, which can be used for providing users the adaptive services with mobile devices. In this paper, an activity recognition system on a smartphone is proposed where the uncertain time-series acceleration signal is analyzed by using hierarchical hidden Markov models. In order to address the limitations on the memory storage and computational power of the mobile devices, the recognition models are designed hierarchy as actions and activities. We implemented the real-time activity recognition application on a smartphone with the Google android platform, and conducted experiments as well. Experimental results showed the feasibility of the proposed method.

Activity recognition with android phone using mixture-of-experts co-trained with labeled and unlabeled data

As the number of smartphone users has grown recently, many context-aware services have been studied and launched. Activity recognition becomes one of the important issues for user adaptive services on the mobile phones. Even though many researchers have attempted to recognize a users activities on a mobile device, it is still difficult to infer human activities from uncertain, incomplete and insufficient mobile sensor data. We present a method to recognize a persons activities from sensors in a mobile phone using mixture-of-experts (ME) model. In order to train the ME model, we have applied global-local co-training (GLCT) algorithm with both labeled and unlabeled data to improve the performance. The GLCT is a variation of co-training that uses a global model and a local model together. To evaluate the usefulness of the proposed method, we have conducted experiments using real datasets collected from Google Android smartphones. This paper is a revised and extended version of a paper that was presented at HAIS 2011.

Extracting meaningful contexts from mobile life log

Life logs include peoples experiences collected from various sources. It is used to support users memory. There are many studies that collect and store life log for personal memory. In this paper, we collect log data from smart phone, derive contexts from the log, and then identify which is meaningful context by using a method based on KeyGraph. To evaluate the proposed method, we show an example of the meaningful places by using contexts and GPS logs collected from two users.

Exploiting mobile contexts for Petri-net to generate a story in cartoons

Recently, various personal information in daily life is stored in mobile devices with sensors. This information reflects heterogeneous aspects of personal life history. People have a tendency to record precious memories from the information in their life. However, it is difficult to extract and summarize the memories from the information. There are many useful traditional ways, such as photograph, video and diary, to record important memories. Especially, writing a diary is beloved as an effective method for a long time because of its effectiveness, remembrance, and empathy of storytelling. This paper proposes a Petri-net based method that organizes mobile contexts to an understandable and interesting story in cartoons. Petri-net based storytelling approach reduces the uncertainty in mobile environment and increases the diversity and causality of a story. A generated story from mobile contexts is compared with personal life history for confirming the usefulness. Also, it is compared with the other method in previous work.

Human activity inference using hierarchical bayesian network in mobile contexts

Since smart phones with diverse functionalities become the general trend, many context-aware services have been studied and launched. The services exploit a variety of contextual information in the mobile environment. Even though it has attempted to infer activities using a mobile device, it is difficult to infer human activities from uncertain, incomplete and insufficient mobile contextual information. We present a method to infer a persons activities from mobile contexts using hierarchically structured Bayesian networks. Mobile contextual information collected for one month is used to evaluate the method. The results show the usefulness of the proposed method.

Mobile context inference using two-layered Bayesian networks for smartphones

Recently, mobile context inference becomes an important issue. Bayesian probabilistic model is one of the most popular probabilistic approaches for context inference. It efficiently represents and exploits the conditional independence of propositions. However, there are some limitations for probabilistic context inference in mobile devices. Mobile devices relatively lacks of sufficient memory. In this paper, we present a novel method for efficient Bayesian inference on a mobile phone. In order to overcome the constraints of the mobile environment, the method uses two-layered Bayesian networks with tree structure. In contrast to the conventional techniques, this method attempts to use probabilistic models with fixed tree structures and intermediate nodes. It can reduce the inference time by eliminating junction tree creation. To evaluate the performance of this method, an experiment is conducted with data collected over a month. The result shows the efficiency and effectiveness of the proposed method.

Hierarchical Probabilistic Network-Based System for Traffic Accident Detection at Intersections

Every year, traffic congestion and traffic accidents have been rapidly increasing in proportion to increasing number of vehicles. Although the roadway design and signal system have been improved to relieve traffic congestion, traffic casualties and property damage do not decrease. The traffic accident is a serious issue of society because vehicle is a primary means of transportation. This paper develops a real-time traffic accident detection system (RTADS): This system helps us to cope with accidents and discover the causes of traffic accident by detecting the accident. We gathered video data recorded at several intersections and used them to detect accidents at different intersections which have different traffic flow and intersection design. However, because the data gathered from intersections have incompleteness, uncertainty and complicated causal dependency between them, we construct probability-based networks which calculate based on the probability for correct accident detection. This system instantly sends the detected result to managers using accident alarm system. RTADS features real time accident detection and analysis of the cause of accidents. In performance evaluation, the proposed system achieved a detection rate of 97% with a correct detection rate of 92% and a false alarm rate of 0.77%.

Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks

Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.

Dynamic quest plot generation using Petri net planning

In most cases, the story of popular RPG games is designed by professional designers as a main content. However, manual design of game content has limitation in the quantitative aspect. Manual story generation requires a large amount of time and effort. Because gamers want more diverse and rich content, so it is not easy to satisfy the needs with manual design. PCG (Procedural Content Generation) is to automatically generate the content of the game. In this paper, we propose a quest generation engine using Petri net planning. As a combination of Petri-net modules a quest, a quest plot is created. The proposed method is applied to a commercial game platform to show the feasibility.

Structure evolution of dynamic Bayesian network for traffic accident detection

Recently, Bayesian network has been widely used to cope with the uncertainty of real world in the field of artificial intelligence. Dynamic Bayesian network, a kind of Bayesian network, can solve problems in dynamic environments. However, as node and state values of node in Bayesian network grow, it is very difficult to define structure and parameter of Bayesian network. This paper proposes a method which generates and evolves structure of dynamic Bayesian network to deal with uncertainty and dynamic properties in real world using genetic algorithm. Effectiveness of the generated structure of dynamic Bayesian network is evaluated in terms of evolution process and the accuracy in a domain of the traffic accident detection.