Yang Koo Lee

Air Pollution Monitoring System based on Geosensor Network

Environment Observation and Forecasting System(EOFS) is a application for monitoring and providing a forecasting about environmental phenomena. We design an air pollution monitoring system which involves a context model and a flexible data acquisition policy. The context model is used for understanding the status of air pollution on the remote place. It can provide an alarm and safety guideline depending on the condition of the context model. It also supports the flexible sampling interval change for effective the tradeoff between sampling rates and battery lifetimes. This interval is changed depending on the pollution conditions derived from the context model. It can save the limited batteries of geosensors, because it reduces the number of data transmission.

Online discovery of Heart Rate Variability patterns in mobile healthcare services

Recent years, advances in day-to-day wearable sensors have led to the development of low powered physiological sensor platforms, which can be integrated in body area networks, a new enabling technology for real-time health monitoring. The bottleneck in health state awareness is the algorithm that has to interpret the sensor data. Nowadays Coronary Heart Disease (CHD) is still the leading cause of death. Many classification techniques such as decision tree and neural networks proposed for an early detection of individual at risk for CHD are not able to continuously detect heart state based on sensor data stream. In this study, we propose an online three-layer neural network to recognize Heart Rate Variability (HRV) patterns related to CHD risk in consideration of daily activities. ECG sensor data is preprocessed using Poincare plot encoding. Incremental learning is utilized to train the network with new data without forgetting the previously learned patterns. The algorithm is named Poincare-based HRV patterns discovering Incremental Artificial neural Network (PHIAN). When a sample is presented, the nodes in the hidden layer of PHIAN compete for determining the node with the highest similarity to the input. Error variables associated with the neuron units are used as criteria for new node insertion in hopes of allowing the network to learn new patterns and reducing classification error. However, the node insertion has to be stopped in the overlapping decision areas. We suppose that the overlaps between classes have lower probability than the centric part of the classes. Therefore, after a period of learning we remove the nodes with no neighbor. Plus, the error probability density is taken into account instead of input probability density. Finally, the predictive capability of PHIAN is compared with three previous classification models, namely Self-Organizing Map (SOM), Growing Neural Gas (GNG), and Multilayer Perceptron (MLP) in terms of classification error and network structure. The results show that PHIAN outperforms the existing techniques. Our proposed model can be efficiently applied to early detection of abnormal conditions and prevent the abnormal becoming serious.

A Framework of In-Situ Sensor Data Processing System for Context Awareness

We propose a framework of the context awareness system which processes a large amount of sensor data from the application areas. The proposed framework consists of a context acquisition, a knowledge base, a rule manager, and a context information manager, etc. we implement the proposed framework of in-situ sensor data processing system that manages the data transmitted from various sensors and notifies the manager of the alarm message for specific conditions. Our proposed framework is able to be applied to the prevention of a forest fire, the warning system for detecting environmental pollution, etc.

Design and Implementation of a System for Environmental Monitoring Sensor Network

In this paper, we propose a system architecture for handling and storing sensor data stream in real-time to support the spatial and/or temporal queries besides continuous queries. We exploit a segment-based method to store the sensor data stream and reduce the managed tuples without any loss of information, which lead to the improvement of the accuracy of query results. In addition, we offer a method to reduce the cost of join operations in processing spatiotemporal queries by filtering out the list of irrelevant sensors from the query range before making the join operation. We then present a design of the system architecture for processing spatial and/or temporal queries. Finally, we implement a climate monitoring application system.

A System Architecture for Monitoring Sensor Data Stream

A wireless sensor network consists of many sensors that collect and transmit physical or environmental conditions at different locations to a server continuously. Many researches mainly focus on processing continuous queries on real-time data stream. However, they do not concern the problem of storing the historical data, which is mandatory to the historical queries. In this paper, we propose a system architecture for handling and storing sensor data stream in real-time to support the spatial and/or temporal queries besides continuous queries. We exploit a segment-based method to store the sensor data stream and reduce the managed tuples without any loss of information, which lead to the improvement of the accuracy of query results. In addition, we offer a method to reduce the cost of join operations in processing spatiotemporal queries by filtering out the list of irrelevant sensors from the query range before making the join operation. We then present a design of the system architecture for processing spatial and/or temporal queries. Finally, we implement a climate monitoring application system based on our proposed system architecture.

Supporting top-k aggregate queries over unequal synopsis on internet traffic streams

Queries that return a list of frequently occurring items are important in the analysis of real-time Internet packet streams. While several results exist for computing Top-k queries using limited memory in the infinite stream model (e.g., limited-memory sliding windows). To compute the statistics over a sliding window, a synopsis data structure can be maintained for the stream to compute the statistics rapidly. Usually, a Top-k query is always processed over an equal synopsis, but its very hard to implement over an unequal synopsis because of the resulting inaccurate approximate answers. Therefore, in this paper, we focus on periodically refreshed Top-k queries over sliding windows on Internet traffic streams; we present a deterministic DSW (Dynamic Sub-Window) algorithm to support the processing of Top-k aggregate queries over an unequal synopsis and guarantee the accuracy of the approximation results.

A technique for extracting behavioral sequence patterns from GPS recorded data

The mobile wireless market has been attracting many customers. Technically, the paradigm of anytime-anywhere connectivity raises previously unthinkable challenges, including the management of million of mobile customers, their profiles, the profiles-based selective information dissemination, and server-side computing infrastructure design issues to support such a large pool of users automatically and intelligently. In this paper, we propose a data mining technique for discovering frequent behavioral patterns from a collection of trajectories gathered by Global Positioning System. Although the search space for spatiotemporal knowledge is extremely challenging, imposing spatial and temporal constraints on spatiotemporal sequences makes the computation feasible. Specifically, the mined patterns are incorporated with synthetic constraints, namely spatiotemporal sequence length restriction, minimum and maximum timing gap between events, time window of occurrence of the whole pattern, inclusion or exclusion event constraints, and frequent movement patterns predictive of one ore more classes. The algorithm for mining all frequent constrained patterns is named cAllMOP. Moreover, to control the density of pattern regions a clustering algorithm is exploited. The proposed method is efficient and scalable. Its efficiency is better than that of the previous algorithms AllMOP and GSP with respect to the compactness of discovered knowledge, execution time, and memory requirement.

Extract and Maintain the Most Helpful Wavelet Coefficients for Continuous K-Nearest Neighbor Queries in Stream Processing

In the real-time series streaming environments, such as data analysis in sensor networks, online stock analysis, video surveillance and weather forecasting, similarity search, which aims at retrieving the similarity between two or more streams, is a hot issue in the recent years. How to find continuous k-nearest neighbors (CKNN) queries has been one of the most common applications in computing on DSMS. In this paper, we developed traditional skylines technique and propose W-Skyline to process CKNN queries as a bandwidth efficient approach over distributed streams. It tries to use of wavelet transformations as a dimensionality reduction technique to permit efficient similarity search over time-series data in memory. Finally, we will give an extensive experimental study with real-time data sets that verifies the effectiveness of our W-Skyline transformation approach in similarity search and CKNN discovery within arbitrary ranges in the time series streaming environments.

A Prototype of Multimedia Metadata Management System for Supporting the Integration of Heterogeneous Sources

With the advances in information technology, the amount of multimedia metadata captured, produced, and stored is increasing rapidly. As a consequence, multimedia content is widely used for many applications in todays world, and hence, a need for organizing multimedia metadata and accessing it from repositories with vast amount of information has been a driving stimulus both commercially and academically. MPEG-7 is expected to provide standardized description schemes for concise and unambiguous content description of data/documents of complex multimedia types. Meanwhile, other metadata or description schemes, such as Dublin Core, XML, TV-Anytime etc., are becoming popular in different application domains. In this paper, we present a new prototype Multimedia Metadata Management System. Our system is good at sharing the integration of multimedia metadata from heterogeneous sources. This system enables the collection, analysis and integration of multimedia metadata semantic description from some different kinds of services. (UCC, IPTV, VOD and Digital TV et al.)

Higher-Accuracy for Identifying Frequent Items over Real-Time Packet Streams

In this paper, we classified the synopses data structure into two major types, the Equal Synopses and Unequal Synopses. Usually, a Top-k query is always processed over equal synopses, but Top-k query is very difficult to implement over unequal synopses because of resulting inaccurate approximate answers. Therefore, we present a Dynamic Synopsis which is developed by DSW (Dynamic Sub-Window) algorithm to support the processing of Top-k aggregate queries over unequal synopses and guarantee the accuracy of the approximation results. Our experiment results show that using Dynamic Synopses have significant performance benefits of improving the accuracy of approximation answers on real time traffic analyses over packet streaming networks.