• Journal of Computing Science and Engineering
• /
• v.5 no.1
• /
• pp.71-84
• /
• 2011

Pervasive applications such as digital memories or patient monitors collect a vast amount of data. One key challenge in these systems is how to extract interesting or unusual information. Because users cannot anticipate their future interests in the data when the data is stored, it is hard to provide appropriate indexes. As location-tracking technologies, such as global positioning system, have become ubiquitous, digital cameras or other pervasive systems record location information along with the data. In this paper, we present an automatic approach to identify unusual data using location information. Given the location information, our system identifies unusual days, that is, days with unusual mobility patterns. We evaluated our detection system using a real wireless trace, collected at wireless access points, and demonstrated its capabilities. Using our system, we were able to identify days when mobility patterns changed and differentiate days when a user followed a regular pattern from the rest. We also discovered general mobility characteristics. For example, most users had one or more repeating mobility patterns, and repeating mobility patterns did not depend on certain days of the week, except that weekends were different from weekdays.

• Journal of the Society of Disaster Information
• /
• v.13 no.1
• /
• pp.89-95
• /
• 2017

The cases of animals unusual behavior have been reported occasionally before a major disaster occurs. Could animals unusual behavior associated with a major disaster occurrence, if so, could we foreknow a disaster occurrence? The purpose of study is to quest an answer through literature reviews on the relation between animals unusual behavior and premonitory symptoms of an earthquake. These empirical studies are classified three parts according as methodological framework; statistical analysis, experimental analysis, observation analysis. The results are simply divided as two, 'animals unusual behavior may be seen as a precursor of pre-disaster phenomena' and 'difficult to see.' A number of studies have been performed abroad, however there is no one in Korea. Most of the studies point out common limitations-difficult to verify the reliability of data, accidentally get and fewer samples of data, difficulty of ensuring appropriate data, etc. That is why more related research with animals unusual behavior and disaster occurrence is needed to validate cause-and-effect relation of animal unusual behavior and pre-disaster phenomena.

• Journal of the Korean association of regional geographers
• /
• v.12 no.4
• /
• pp.461-474
• /
• 2006

This paper aims to analyze regional characteristics of unusual temperature events on summer and winter. The major data used in this study are the daily mean temperature of summer (June-August) and winter (December-February) and wind field on 850 hPa height. Regions of unusual temperature are divided into five regions by the monthly frequency of unusual temperature occurrence. The divided regions are following as: the middle east coastal region (I) where the summer unusual high temperature occurrence frequency is highest; the Gyunggi west coastal and northern middle inland region (II) where winter unusual low temperature occurrence frequency is highest and winter unusual high temperature occurrence frequency is low; the western middle and south region (III) where unusual temperature occurrence ratio is not concentrated on specific season; the forest and southern east region (IV) where unusual high temperature is low; and the south coastal and Jeju island region (V) where winter unusual high temperature is highest.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.471-479
• /
• 2003

Moving averages are the most popular statistics in analyzing time-series data like stock indices. However, moving averages are quite sensitive to unusual observations. In other words, they are not robust against unusual observations. We introduce the moving averages in terms of an M-estimator, and show how we can take advantages of using the proposed moving averages in fitting the data more than usual moving averages.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.183-193
• /
• 2022

Smart cities are expected to provide residents with convenience via various agents such as CCTV, delivery robots, security robots, and unmanned shuttles. Environmental data collected by various agents can be used for various purposes, including advertising and security monitoring. This study suggests a surveillance map data framework for efficient and integrated multimodal data representation from multi-agents. The suggested surveillance map is a multilayered global information grid, which is integrated from the multimodal data of each agent. To confirm this, we collected surveillance map data for 4 months, and the behavior patterns of humans and vehicles, distribution changes of elevation, and temperature were analyzed. Moreover, we represent an anomaly detection algorithm based on a surveillance map for security service. A two-stage anomaly detection algorithm for unusual situations was developed. With this, abnormal situations such as unusual crowds and pedestrians, vehicle movement, unusual objects, and temperature change were detected. Because the surveillance map enables efficient and integrated processing of large multimodal data from a multi-agent, the suggested data framework can be used for various applications in the smart city.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.11
• /
• pp.795-800
• /
• 2013

Early detection of oestrus in Korean cows is one of the important issues in maximizing the economic benefit. Although various methods have been proposed, we still need to improve the performance of the oestrus detection system. In this paper, we propose a video surveillance system which can detect unusual behavior of multiple cows including the mounting activity. The unusual behavior detection is to detect the dangerous or abnormal situations of cows in video coming in real time from a surveillance camera promptly and correctly. The prototype system for unusual behavior detection gets an input video from a fixed location camera, and uses the motion vector to represent the motion information of cows in video, and finally selects a SVDD (one of the most well-known types of one-class SVM) as a detector by reinterpreting the unusual behavior into an one class decision problem from the practical points of view. The experimental results with the videos obtained from a farm located in Jinju illustrate the efficiency of the proposed method.

• Atmosphere
• /
• v.28 no.4
• /
• pp.491-507
• /
• 2018

This study collected and analyzed records related to the Asian dust phenomenon in Korean history books. I collected a wide range of records from diverse sources and identified data for analysis. 290 records were selected through this process. These records provide a variety of information including the occurrence time and duration of the phenomenon, other natural phenomenon occurring at the same date, descriptions of the phenomenon, and so on. Reports on, Asian dust in the historical records was not continuous or uniform. However, their appearance in certain months of the year is similar to that observed in modern times. In addition, I collected 90 records showing it that can be largely divided into two viewpoints which they were a natural calamity or an unusual phenomenon. Generally, natural phenomenons in historical books are mostly recorded in viewpoint of unusual phenomenon. Nevertheless, research result verified the record as actual observational data. Consequentially, it also indicates that this data is important for research from a meteorological point of view. I think that the data collected through this study can be helpful to modern meteorological studies related to the Asian dust phenomenon.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.9
• /
• pp.728-735
• /
• 2013

In this paper, we present a method of transmitting ECG signals in real-time mobile environment to be possible to implement the ubiquitous healthcare system. Because of the excessive amount of data transmission of ECG signals, it is necessary to propose a limitation to the real-time transmission. We propose a real-time electrocardiographic monitoring system based on the proposal of unusual waveform detection algorithm which detects the R-wave distortions from the arrhythmia ECG signals having unusual waveform of about 10% on average. It is very effective in terms of time and cost for medical staffs to monitor and analyze ECG signals for a long period of time. Monitoring unusual waveform by gradually adjusting the threshold values of potential and kurtosis makes the amount of data transmitted decrease and significance level of waveform to be enhanced. The unusual waveform detection algorithm is implemented with ubiquitous environment inter-working device client. It is applicable to ubiquitous healthcare system capable of real-time monitoring the ECG signal. While ensuring the mobility, it allows for real-time continuous monitoring of ECG signals.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.915-926
• /
• 2020

Outlier detection methods help one to identify unusual instances in data that may correspond to erroneous, exceptional, or surprising events or behaviors. This work studies conditional outlier detection, a special instance of the outlier detection problem, in the context of incorrect data label identification. Unlike conventional (unconditional) outlier detection methods that seek abnormalities across all data attributes, conditional outlier detection assumes data are given in pairs of input (condition) and output (response or label). Accordingly, the goal of conditional outlier detection is to identify incorrect or unusual output assignments considering their input as condition. As a solution to conditional outlier detection, this paper proposes the ratio-based outlier scoring (ROS) approach and its variant. The propose solutions work by adopting conventional outlier scores and are able to apply them to identify conditional outliers in data. Experiments on synthetic and real-world image datasets are conducted to demonstrate the benefits and advantages of the proposed approaches.

• The Journal of Industrial Distribution & Business
• /
• v.6 no.3
• /
• pp.5-8
• /
• 2015

Purpose - This article's aim is to examine how the utilization of existing and future decision-support systems will lead to a change in the auditing process. Research design, data, and methodology - An information system is a special decision-support system that combines information obtained from various sources and communicates among them to help in assessing appropriate complex financial decisions. This paper analyzes techniques such as data and text mining as components of decision-support systems to be used in the auditing process. Results - We present views about how existing decision-support systems will lead to a change in audits. Auditors, who currently collect significant data manually, will in the future move towards management through complex decision-support systems. Conclusions - Although some internal audit functions are integrated into systems of continuous monitoring, the use of such systems remains limited. Thus, instead of multiple decision-support systems, a unified decision-support system can be deployed for this that includes sensors integrated within a company in different contexts (e.g., production, sales, and accounting) that continually monitors violations of controls, unusual patterns, and unusual transactions.