• Architectural research
• /
• 제12권2호
• /
• pp.15-22
• /
• 2010

Our prediction model is based on the development of "Semantic Location Model." It embodies geometrical and topological information which can increase the efficiency in prediction and make it easy to manipulate the prediction model. Data mining is being implemented to extract the inhabitant's location patterns generated day by day. As a result, the self-learning system will be able to semantically predict the inhabitant's location in advance. This context-aware system brings about the key component of the ubiquitous computing environment. First, we explain the semantic location model and data mining methods. Then the location prediction model for the ubiquitous computing system is described in details. Finally, the prototype system is introduced to demonstrate and evaluate our prediction model.

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.97-104
• /
• 2017

Location prediction has been successfully utilized to provide high quality of location-based services to customers in many applications. In its usual form, the conventional type of location prediction is to predict future locations based on user's past movement history. However, as location prediction needs are expanded into much complicated cases, it becomes necessary quite frequently to make inference on the locations that target user visited in the past. Typical cases include the identification of locations that infectious disease carriers may have visited before, and crime suspects may have dropped by on a certain day at a specific time-band. Therefore, primary goal of this study is to predict locations that users visited in the past. Information used for this purpose include user's demographic information and movement histories. Data mining classifiers such as Bayesian network, neural network, support vector machine, decision tree were adopted to analyze 6868 contextual dataset and compare classifiers' performance. Results show that general Bayesian network is the most robust classifier.

• ETRI Journal
• /
• 제30권3호
• /
• pp.421-431
• /
• 2008

In this paper, we offer a new technique to discover frequent spatiotemporal patterns from a moving object database. Though the search space for spatiotemporal knowledge is extremely challenging, imposing spatial and timing constraints on moving sequences makes the computation feasible. The proposed technique includes two algorithms, AllMOP and MaxMOP, to find all frequent patterns and maximal patterns, respectively. In addition, to support the service provider in sending information to a user in a push-driven manner, we propose a rule-based location prediction technique to predict the future location of the user. The idea is to employ the algorithm AllMOP to discover the frequent movement patterns in the user's historical movements, from which frequent movement rules are generated. These rules are then used to estimate the future location of the user. The performance is assessed with respect to precision and recall. The proposed techniques could be quite efficiently applied in a location-based service (LBS) system in which diverse types of data are integrated to support a variety of LBSs.

• 한국컴퓨터정보학회논문지
• /
• 제22권10호
• /
• pp.121-128
• /
• 2017

In this paper, we propose a multi-label classification method in which multi-label classification estimation techniques are applied to resolving location prediction problem. Most of previous studies related to location prediction have focused on the use of single-label classification by using contextual information such as user's movement paths, demographic information, etc. However, in this paper, we focused on the case where users are free to visit multiple locations, forcing decision-makers to use multi-labeled dataset. By using 2373 contextual dataset which was compiled from college students, we have obtained the best results with classifiers such as bagging, random subspace, and decision tree with the multi-label classification estimation methods like binary relevance(BR), binary pairwise classification (PW).

• Journal of Communications and Networks
• /
• 제17권6호
• /
• pp.568-581
• /
• 2015

Predicting locations of users with portable devices such as IP phones, smart-phones, iPads and iPods in public wireless local area networks (WLANs) plays a crucial role in location management and network resource allocation. Many techniques in machine learning and data mining, such as sequential pattern mining and clustering, have been widely used. However, these approaches have two deficiencies. First, because they are based on profiles of individual mobility behaviors, a sequential pattern technique may fail to predict new users or users with movement on novel paths. Second, using similar mobility behaviors in a cluster for predicting the movement of users may cause significant degradation in accuracy owing to indistinguishable regular movement and random movement. In this paper, we propose a novel fusion technique that utilizes mobility rules discovered from multiple similar users by combining clustering and sequential pattern mining. The proposed technique with two algorithms, named the clustering-based-sequential-pattern-mining (CSPM) and sequential-pattern-mining-based-clustering (SPMC), can deal with the lack of information in a personal profile and avoid some noise due to random movements by users. Experimental results show that our approach outperforms existing approaches in terms of efficiency and prediction accuracy.

• 한국산학기술학회논문지
• /
• 제12권1호
• /
• pp.451-458
• /
• 2011

최적 이동 경로 탐색이나 스케줄링 경로 예측 등 최적의 위치 기반 서비스 제공을 위하여 이동 객체의 위치 이력 데이터들에 대한 시공간적 속성들을 고려한 이동 객체들의 의미 있는 이동 패턴 추출 기법이 요구된다. 이에 본 논문에서는 의미 있는 이동 패턴 추출을 위하여 이동 객체의 연속적 위치 변화를 보다 효과적으로 패턴화하고 2차원 공간 영역으로의 인덱싱을 위한 $R^*$-tree 기반의 이동 객체 위치 속성 일반화 기법을 제안한다. 제안한 위치 일반화 방법은 이동 객체들의 각 공간 영역 데이터를 이용하여 영역 간의 시간 간격에 대한 제약을 만족하는 이동 시퀀스를 생성하며, 생성된 이동 시퀀스들을 통하여 의미 있는 이동 패턴들을 추출한다. 추출된 이동 패턴들은 최적의 위치기반 서비스를 위한 이동 객체의 시간 패턴 마이닝이나 객체의 이동 추이 분석 등에 효과적으로 이용될 수 있다.

• 정보처리학회논문지D
• /
• 제16D권3호
• /
• pp.307-316
• /
• 2009

이 논문에서는 자동 원격 검침(AMR) 시스템에서 수집되는 전력 사용량 데이터의 분석 결과를 실세계에 적용하기 위하여 시간과 공간의 변화에 따른 전력 소비 패턴의 주기성 탐사를 위한 시공간 데이터마이닝 기법을 제안하였다. 첫째, 고객의 전력 사용 목적에 따른 군집 분석을 위하여 분할 군집화 기법을 적용하였다. 둘째, 3차원 큐브 마이닝 기법을 적용하여 고객의 전력 소비 데이터가 갖는 시간 속성과 공간 속성에 대한 패턴을 탐색하였다. 셋째, 다양한 시간 도메인에서의 주기 패턴 발견을 위한 캘린더 패턴 마이닝 기법을 이용하여 탐사된 패턴들이 갖고 있는 시간 속성의 의미와 관계를 분석 및 예측하였다. 제안된 시공간 데이터마이닝 기법을 평가하기 위해 한국 전력 연구원에서 구축된 GIS-AMR 시스템에 의해 제공되는 고압 전력 소비 고객 3,256명의 2007년 1월부터 4월까지 총 266,426건의 데이터로부터 시간의 주기성 및 공간적 특성을 포함한 전력 소비 패턴을 분석하였다. 제안한 분석 기법을 통하여 특정 그룹에 속한 각각의 대표 프로파일이 시간과 공간상에서 갖는 주기성을 발견하였다.

• Geomechanics and Engineering
• /
• 제29권2호
• /
• pp.113-131
• /
• 2022

A rockburst is a common disaster in deep-tunnel excavation engineering, especially for high-geostress areas. An anomalously low friction effect is one of the most important inducements of rockbursts. To elucidate the correlation between an anomalously low friction effect and a rockburst, we establish a two-dimensional prediction model that considers the discontinuous structure of a rock mass. The degree of freedom of the rotation angle is introduced, thus the motion equations of the blocks under the influence of a transient disturbing force are acquired according to the interactions of the blocks. Based on the two-dimensional discontinuous block model of deep rock mass, a rockburst prediction model is established, and the initiation process of ultra-low friction rockburst is analyzed. In addition, the intensity of a rockburst, including the location, depth, area, and velocity of ejection fragments, can be determined quantitatively using the proposed prediction model. Then, through a specific example, the effects of geomechanical parameters such as the different principal stress ratios, the material properties, a dip of principal stress on the occurrence form and range of rockburst are analyzed. The results indicate that under dynamic disturbance, stress variation on the structural surface in a deep rock mass may directly give rise to a rockburst. The formation of rockburst is characterized by three stages: the appearance of cracks that result from the tension or compression failure of the deformation block, the transformation of strain energy of rock blocks to kinetic energy, and the ejection of some of the free blocks from the surrounding rock mass. Finally, the two-dimensional rockburst prediction model is applied to the construction drainage tunnel project of Jinping II hydropower station. Through the comparison with the field measured rockburst data and UDEC simulation results, it shows that the model in this paper is in good agreement with the actual working conditions, which verifies the accuracy of the model in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• 지질공학
• /
• 제34권1호
• /
• pp.1-12
• /
• 2024

우리나라는 1980년까지 광물 지하자원 개발을 활발히 수행하였으나 이후 생산원가 대비 사업성이 크게 줄어들면서 많은 수의 폐광산이 발생되었다. 그 중 대부분은 광산개발 중단 후 오랜 시간이 지나 잔류성 침하가 발생할 가능성이 높은 상태에 있다. 하지만 그 발생 시기와 위치를 정확히 예측하기는 어려움이 있다. 따라서, 본 연구에서는 실제 지반침하가 발생한 사례를 분석하여 연속체 수치해석을 통해 지반침하의 발생 위치나 규모에 대한 예측 가능성을 살펴보고자 한다. 연구지역은 양산단층과 모량단층 사이에 위치하여 이들에 규제받는 ○○광산 지역이며, 이 지역에서는 2005~2009년에 걸쳐 3회의 지반침하가 발생된 바 있다. 지반침하지를 대상으로 시추조사 및 전기비저항 탐사를 수행하여 지층의 분포를 파악하였고, 실내시험을 통해 수치해석 시 적용되는 지반의 물리·역학적 특성을 파악하였다. 수치해석 결과 소성영역이 실제 지반침하 범위를 포함하는 형태로 나타나 연속체 해석으로도 채굴적에 의한 침하지 발생 위치 및 규모를 예측하는데 활용할 수 있을 것으로 판단된다.