Sun-Young Ihm

A Decision Tree-Based Classification Model for Crime Prediction

The growing availability of information technologies has enabled law enforcement agencies to collect detailed data about various crimes. Classification techniques can be applied to these data to build decision-aid tools and facilitate investigations of law enforcement agencies. In this paper, we propose an approach for constructing a decision tree based classification model for a crime prediction. Proposed model assists law enforcement agencies in discovering crime patterns and predicting future trends. We provide an implementation and analysis of our proposed method.

Approximate convex skyline: a partitioned layer-based index for efficient processing top- k queries

A top-k query returns k tuples with the highest (or the lowest) scores from a relation. Layer-based methods are the representative ones for processing top-k queries efficiently. These methods construct a list of layers, where the ith layer contains the tuples that can potentially be the top-i answer. Thus, the layer-based methods can answer top-k queries by reading at most k layers. To construct layers, the existing layer-based methods use convex skyline, convex hull or skyline methods. Among them, the convex skyline is constructed by computing the convex hull over the skyline. Accordingly, the layer size of the convex skyline is relatively smaller than those of the convex hull, and the index building time is relatively shorter than those of the skyline. However, for large and high-dimensional databases, the convex skyline suffers from long index building time and large memory usage, because most objects can become the skyline points. This paper focuses on how to build an index, which contains a smaller number of objects comparing to the skyline and uses less time to construct an index comparing to the convex skyline. Specifically, we propose a method, called the Approximate Convex Skyline Enhanced (simply, AppCSE), which reduces the index building time and memory usage of the convex skyline. In the proposed method, we first construct the skyline, and then, partition the region of the skyline into multiple subregions, and compute the convex hull in each subregion with virtual objects. After that, AppCSE combines the objects obtained by computing the convex hull. Through various experiments with synthetic and real datasets, we demonstrate that the proposed method significantly reduces the index building time and memory usage comparing to the existing methods. In addition, we show that the degradation of query performance is negligible when using AppCSE as the layering scheme.

Event Detection in Wireless Sensor Networks: Survey and Challenges

In typical wireless sensor networks (WSNs), sensor nodes have limited resources such as battery power, computing capability and memory. Creating an event detection method comprising with those resource limitations is not an easy task and this sets several challenges. In this paper, we first describe challenges in event detection in WSNs. Then, we investigate the previous studies that have been done for solving those challenges.

Skyline-Based Aggregator Node Selection in Wireless Sensor Networks

In order to achieve the equal usage of limited resources in the wireless sensor networks (WSNs), we must aggregate the sensor data before passing it to the base station. In WSNs, the aggregator nodes perform a data aggregation process. Careful selection of the aggregator nodes in the data aggregation process results in reducing large amounts of communication traffic in the WSNs. However, network conditions change frequently due to sharing of resources, computation load, and congestion on network nodes and links, which makes the selection of the aggregator nodes difficult. In this paper, we study an aggregator node selection method in the WSNs. We formulate the selection process as a top-k query problem, where we efficiently solve the problem by using a modified Sort-Filter-Skyline (SFS) algorithm. The main idea of our approach is to immediately perform a skyline query on the sensor nodes in the WSNs, which enables to extract a set of sensor nodes that are potential candidates to become an aggregator node. The experiments show that our method is several times faster compared to the existing approaches.

Efficient duality-based subsequent matching on time-series data in green computing

Green computing is the study and practice of efficiently using computers resources. The main purpose of green computing is to achieve an algorithmic efficiency by designing resource-efficient, accurate and energy-efficient algorithms. It is important to achieve the algorithmic efficiency in handling time-series data. One of the main tasks in handling time-series data is to find subsequence matches similar to a given query sequence. The state-of-the-art methods to find subsequence matches in time-series data produce many false alarms by filtering points through comparing only one query window with its corresponding data window. In this paper, we propose a subsequence matching method for green computing, which is called the Efficient Duality-based Subsequence Matching (simply, E-Dual Match). E-Dual Match handles all possible query windows for determining candidates. Hence, E-Dual Match not only reduces the false alarms, and improves the performance compared to Dual Match, but also does so by considering the main requirements of the green computing. In other words, E-Dual Match efficiently uses limited computer resources, accurate and energy-efficient. Experiment results show that E-Dual Match reduces the number of candidates by up to 4.90 times over Dual Match, and improves the subsequence matching time by up to 2.35 times over Dual Match. We also show that E-Dual Match reduces the number of data page accesses by up to 3.04 times over Dual Match.

A Music Recommendation Method with Emotion Recognition Using Ranked Attributes

Emotion recognition field can be useful for music discovery and recommendation, because emotions can precisely describe the actual habits of a listener. In this paper, we propose a new concept called Ranked Attributes that are useful to make reasonable music recommendations. More precisely, we propose to consider additional attributes to emotion, such as weather and time, and build a Ranked Attributes Tree (RAT) that enables to recommend a music piece based on a combination of all ranked attributes. In this paper, we describe the following parts of the proposed method: database design, voice and emotion recognition, and music recommendation.

App Analytic: A Study on Correlation Analysis of App Ranking Data

In recent years, app store and android market have experienced a significant growth in terms of app numbers. Since we discover 85% of apps through the ranks, it is important to develop effective app ranking analyzing tools. In this paper, we present a method called App Analytic. In our method, we explore correlations of app ranking data about popular social networking sites. Specifically, we analyze correlations between various characteristics of social networking sites on Internet and android market. The results of correlation analysis reveal that there is a strong positive correlation of the number of app downloads with the number of registered users and page rank. We also provide an in-depth analysis on the major factors that impact the correlations.

An Efficient Index Building Algorithm for Selection of Aggregator Nodes in Wireless Sensor Networks

In wireless sensor networks (WSNs), aggregator nodes perform the data aggregation process. Thus, careful selection of the aggregator nodes is needed to reduce network traffic in data aggregation process and prolong overall lifetime of the network. In this paper, we formulate selection process of the aggregator nodes as a top-k query problem. To answer the top-k queries efficiently in the large-scale WSNs, building and using the indexes are important. Thus, we propose an efficient index building algorithm for selection of aggregator nodes, called the Approximate Convex Hull Index (simply, aCH-Index). The main idea of our approach is to construct a convex hull over the sensor nodes in the WSNs, which enables speeding up the extraction of a set of sensor nodes that are potential candidates to become an aggregator node. In order to do so, the aCH-Index computes the skyline over the entire set of the sensor nodes, partitions the region into multiple subregions to reduce the computing time of convex hull in all origins, and then computes the convex hull in each subregion. Through the experiments with synthetic data, we show that aCH-Index outperforms the existing methods.

A Study on Skyline Processing Using Hyperplane Projections in Multidimensional Sensor Data

In sensor networks, data has many attributes and these attributes will be real values like temperature or moisture conditions. In this paper, we handle these sensor data with skyline processing for searching the data. Skyline processing is the one of representative method for top-k query processing. A top-k query returns k tuples with the lowest score from multidimensional relation consists of sensor data. We propose a method which improves the plane-project-parallel-skyline by eliminating data tuples. Our approach computes the approximate skyline once again when the number of data tuples in the subspace is bigger than other subspaces.

Adaptive convex skyline: a threshold-based project partitioned layer-based index for efficient-processing top-k queries in entrepreneurship applications

Many entrepreneurship applications use data as the core concept of their business to better understand the needs of their customers. However, as the size of databases used by these entrepreneurship applications grows and as more users access data through various interactive interfaces, obtaining the result for a top-k query may take long time if the query matches millions of the tuples in the database. Traditionally, layer-based indexing methods are representative for processing top-k queries efficiently. These methods form tuples into a list of layers where the ith layer holds the tuples that can be the top-i answer. Layer-based indexing methods enable us to obtain top-k answers by accessing at most k layers. Most of these methods achieve high accuracy of query answer at the expense of enlarged index construction time. However, we can adjust between accuracy and index construction time to achieve an optimal performance. Thus in this paper, we propose a method, called the adaptive convex skyline (AdaptCS) for efficient-processing top-k queries in entrepreneurship applications. AdaptCS first prunes the data with a virtual threshold point and finds skyline points over the pruned data. Here, by adjusting virtual threshold we are able to achieve optimal performance. Then, AdaptCS divides the skyline into m subregions with projection partitioning method and constructs the convex hull m times for each subregion with virtual objects. Lastly, AdaptCS combines the objects obtained by computing the convex hull. The experimental results show that the proposed method outperforms the existing methods.