• ETRI Journal
• /
• v.30 no.3
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.1909-1928
• /
• 2020

Predicting human mobility has always been an important task in Location-based Social Network. Previous efforts fail to capture spatial dependence effectively, mainly reflected in weakening the location topology information. In this paper, we propose a neural network-based method which can capture spatial-temporal dependence to predict the next location of a person. Specifically, we involve a graph convolutional network (GCN) based on a seq2seq framework to capture the location topology information and temporal dependence, respectively. The encoder of the seq2seq framework first generates the hidden state and cell state of the historical trajectories. The GCN is then used to generate graph embeddings of the location topology graph. Finally, we predict future trajectories by aggregated temporal dependence and graph embeddings in the decoder. For evaluation, we leverage two real-world datasets, Foursquare and Gowalla. The experimental results demonstrate that our model has a better performance than the compared models.

• Asia pacific journal of information systems
• /
• v.34 no.2
• /
• pp.565-584
• /
• 2024

More than 1 million automobile insurance repairs occur per year globally, and the related repair costs add up to astronomical amounts. Insurance companies and repair shops are spending a great deal of money on manpower every year to claim reasonable insurance repair costs. For this reason, promptly predicting insurance claims for vehicles in accidents can help reduce social costs related to auto insurance. Several recent studies have been conducted in auto insurance repair prediction using variables such as photos of vehicle damage. We propose a new model that reflects auto insurance repair characteristics to predict auto insurance repair claims through an association rule method that combines gradient descent and location information. This method searches for the appropriate number of rules by applying the gradient descent method to results generated by association rules and eventually extracting main rules with a distance filter that reflects automobile part location information to find items suitable for insurance repair claims. According to our results, predictive performance could be improved by applying the rule set extracted by the proposed method. Therefore, a model combining the gradient descent method and a location-based association rule method is suitable for predicting auto insurance repair claims.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.6B
• /
• pp.375-381
• /
• 2007

This paper focuses on the prediction algorithm among the context-awareness technologies. With a representative algorithm, Bayesian Networks, it is difficult to realize a context-aware as well as to decrease process time in real-time environment. Moreover, it is also hard to be sure about the accuracy and reliability of prediction. One of the simplest algorithms is the sequential matching algorithm. We use it by adding the proposed Cache Scheme. It is adequate for a context-aware service adapting user's habit and reducing the processing time by average 48.7% in this paper. Thus, we propose a design method of user location prediction algorithm that uses sequential matching with the cache scheme by taking user's habit or behavior into consideration. The novel approach will be dealt in a different way compared to the conventional prediction algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.4
• /
• pp.143-149
• /
• 2012

MANET is a network that is a very useful application to build network environment in difficult situation to build network infrastructure. But, nodes that configures MANET have difficulties in data retrieval owing to resources which aren't enough and mobility. Therefore, caching scheme is required to improve accessibility and availability for frequently accessed data. In this paper, we proposed a technique that utilize mobility prediction of nodes to retrieve quickly desired information and improve data availability. Mobility prediction of modes is performed through distance calculation using location information. We used technique which global cluster table and local member table is managed by cluster head to reduce data consistency and query latency time. We compared COCA and CacheData and experimented to confirm performance of proposed scheme in this paper and efficiency of the proposed technique through experience was confirmed.

• Journal of KIISE:Databases
• /
• v.31 no.5
• /
• pp.479-491
• /
• 2004

Location information of mobile objects is applied to vehicle tracking, digital battlefields, location based services, and telematics. Their location coordinates are periodically measured and stored in the application systems. The linear function is mainly used to estimate the location information that is not in the system at the query time point. However, a new method is needed to improve uncertainties of the location representation, because the location estimation by linear function induces the estimation error. This paper proposes an application method of the cubic spline interpolation in order to reduce deviation of the location estimation by linear function. First, we define location information of the mobile object moving on the two-dimensional space. Next, we apply the cubic spline interpolation to location estimation of the proposed data model and describe algorithm of the estimation operation. Finally, the precision of this estimation operation model is experimented. The experimentation comes out more accurate results than the method by linear function, although the proposed location estimation function uses the small amount of information. The proposed method has an advantage that drops the cost of data storage space and communication for the management of location information of the mobile objects.

• Korean Journal of Hydrosciences
• /
• v.7
• /
• pp.125-137
• /
• 1996

The subject of the paper is the selection of the number and location of raingauge stations among existing ones for the computation of mean areal precipitation and for use as input of real-time flow prediction models. The weighted average method developed by National Weather Service was used to compute MAP over the Boone River basin in Iowa with a 40 year daily data set. Two different searching methods were used to find local optimal solutions. An operational rainfall-runoff model was used to determine the optimal location and number of stations for flow prediction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.7
• /
• pp.3150-3170
• /
• 2016

In Intelligent Transportation Systems (ITS), logistics distribution and mobile e-commerce, the real-time, accurate and reliable vehicle trajectory prediction has significant application value. Vehicle trajectory prediction can not only provide accurate location-based services, but also can monitor and predict traffic situation in advance, and then further recommend the optimal route for users. In this paper, firstly, we mine the double layers of hidden states of vehicle historical trajectories, and then determine the parameters of HMM (hidden Markov model) by historical data. Secondly, we adopt Viterbi algorithm to seek the double layers hidden states sequences corresponding to the just driven trajectory. Finally, we propose a new algorithm (DHMTP) for vehicle trajectory prediction based on the hidden Markov model of double layers hidden states, and predict the nearest neighbor unit of location information of the next k stages. The experimental results demonstrate that the prediction accuracy of the proposed algorithm is increased by 18.3% compared with TPMO algorithm and increased by 23.1% compared with Naive algorithm in aspect of predicting the next k phases' trajectories, especially when traffic flow is greater, such as this time from weekday morning to evening. Moreover, the time performance of DHMTP algorithm is also clearly improved compared with TPMO algorithm.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.1-13
• /
• 2007

The necessity of future index is increasing to predict the future location of moving objects promptly for various location-based services. A representative research topic related to future index is the probability trajectory prediction technique that improves reliability using the past trajectory information of moving objects in the road network environment. However, the prediction performance of this technique is lowered by the heavy load of extensive future trajectory search in long-range future queries, and its index maintenance cost is high due to the frequent update of future trajectory. Thus, this paper proposes the Probability Cell Trajectory-Tree (PCT-Tree), a cell-based future indexing technique for efficient long-range future location prediction. The PCT-Tree reduces the size of index by rebuilding the probability of extensive past trajectories in the unit of cell, and improves the prediction performance of long-range future queries. In addition, it predicts reliable future trajectories using information on past trajectories and, by doing so, minimizes the cost of communication resulting from errors in future trajectory prediction and the cost of index rebuilding for updating future trajectories. Through experiment, we proved the superiority of the PCT-Tree over existing indexing techniques in the performance of long-range future queries.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.5
• /
• pp.587-596
• /
• 2008

For Wireless internet service in Metropolitan area, optimum location selection for base station and cell planning are critical process in determining service coverage by accurate prediction of Wave Propagation Characteristics. Due to different kinds of characteristics in service area such as lay of land, natural feature and material, height and width of artificially made building, it has a great impact on the transmission and distance recovery of wireless network service. Therefore, these facts may cause substantial barriers in predicting & analyzing the expected level of service quality and providing it to subscribers. In this thesis, we have simulated the process to improve quality and coverage of the service by adjusting the location of Base station and the antenna angle that influence the service after the basic location of base station is selected according to the wave prediction model. Based on this simulations test, we have demonstrated the results in which subscribers would get higher quality of wireless internet service along with bigger coverage and the improved quality in the same service coverage area through optimization process of base station.