• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.135-142
• /
• 2021

Estimating the locations of workers in a shipyard is beneficial for a variety of applications such as selecting potential forwarders for transferring data in IoT services and quickly rescuing workers in the event of industrial disasters or accidents. In this work, we propose a human movement stream processing system for estimating worker locations in shipyards based on Apache Spark and TensorFlow serving. First, we use Apache Spark to process location data streams. Then, we design a worker location prediction model to estimate the locations of workers. TensorFlow serving manages and executes the worker location prediction model. When there are requirements from clients, Apache Spark extracts input data from the processed data for the prediction model and then sends it to TensorFlow serving for estimating workers' locations. The worker movement data is needed to evaluate the proposed system but there are no available worker movement traces in shipyards. Therefore, we also develop a mobility model for generating the workers' movements in shipyards. Based on synthetic data, the proposed system is evaluated. It obtains a high performance and could be used for a variety of tasksin shipyards.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.503-508
• /
• 2010

Recently, the advance of mobile devices has made various services possible beyond simple communication. One of services is the predicting the future path of users and providing the most suitable location based service based on the prediction results. Almost of these prediction methods are based on previous path data. Thus, calculating similarities between current location information and the previous trajectories for path prediction is an important operation. The collected trajectory data have a huge amount of location information generally. These information needs the high computational cost for calculating similarities. For reducing computational cost, the meaningful location based trajectory model approaches are proposed. However, most of the previous researches are considering only the physical information such as stay time and the distance for extracting the meaningful locations. Thus, they will probably ignore the characteristics of users for meaningful location extraction. In this paper, we suggest a meaningful location extracting and trajectory simplification approach considering the stay time, distance, and additionally interaction information of user. The method collects the location information using GPS device and interaction information between the user and the others. Using these data, the proposed method defines the proximity of the people who are related with the user. The system extracts the meaningful locations based on the calculated proximities, stay time and distance. Using the selected meaningful locations the trajectories are simplified. For verifying the usability of the proposed method, we collect the behavioral data of smart phone users. Using these data, we measure the suitability of meaningful location extraction method, and the accuracy of prediction approach based on simplified trajectories. Following these result, we confirmed the usability of proposed method.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.527-532
• /
• 2014

Recently, due to the proliferation of mobile smart devices, the inovation of bigdata, which analyzes and processes massive data collected from various sensors implaned in smart devices, expands to LBSs. Many location prediction techniques for moving objects have been studied in literature. However, as the majority of studies perform location prediction which depends on specific applications, they hardly reflect the technical requirements of next-generation spatio-temporal information services. Therefore, this paper proposes the design of general-purpose distributed moving object prediction query processing framework that is capable of performing primitive and various types of queries effectively based on massive spatio-temporal data of moving objects in real-world space networks.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2011.10a
• /
• pp.488-493
• /
• 2011

Authors previously suggested the design sensitivity analysis based on transmissibility function and identified the sensitivity of measured point over the small modification of system dynamics. On the other hand, the acceleration data will not reveal the strain information at the same location and authors suggested energy isoclines that successfully predict the fatigue damage on the interesting location to overcome the drawback of acceleration over fatigue society. Both of methodologies, sensitivity analysis and fatigue damage prediction, commonly use the response acceleration response as main indicator. In this paper, authors investigate the advanced method of vibration fatigue prediction using design sensitivity analysis to enhance the accuracy of predicted accumulated fatigue. Uni-axial vibration testing is performed with finite element model of a simple notched specimen and the prediction of fatigue damage at notched location is conducted for accelerations at different measurement locations that show different sensitivity contribution, either.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.8
• /
• pp.57-64
• /
• 2004

This study deals with the prediction of defect location which can be occurred in structure. The existing methods was very difficult to be applied to predict it, because of complex numerical formula. The triangulation method proposed in this study can predict the source location easily with small amount of data. The arrival time of wave can be directly converted into the distance between sensors. For this purpose, the propagation velocity was measured by Rayleigh wave, and the propagation behavior was analyzed. The welded workpiece is adapted to investigate for the consideration of jointed part in structure, The propagation velocity of signal was measured in welded workpiece and the revised algorithm of source location was proposed.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.2
• /
• pp.160-171
• /
• 2008

MU's mobility patterns can be found from a movement history data. The prediction accuracy and model complexity depend on the degree of application of history data. The more data we use, the more accurate the prediction is. As a result, the location management cost is reduced, but complexity of the model increases. In this paper, we classify MU's mobility patterns into four types. For each type, we find the respective optimal number of application of history data, and predictive location area by using the simulation. The optimal numbers of four types are shown to be different. When we use more than three application of history data, the simulation time and data storage are shown to increase very steeply.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2007.11a
• /
• pp.388-394
• /
• 2007

In wireless network, we propose a predictive location update scheme which considers mobile user's(MU's) mobility patterns. MU's mobility patterns can be found from a movement history data. The prediction accuracy and model complexity depend on the degree of application of history data. The more data we use, the more accurate the prediction is. As a result, the location management cost is reduced, but complexity of the model increases. In this paper, we classify MU's mobility patterns into four types. For each type, we find the respective optimal number of application of history data, and predictive location area by using the simulation. The optimal numbers of four types are shown to be different. When we use more than three application of history data, the simulation time and data storage are shown to increase very steeply.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.278-281
• /
• 2011

Mobile devices equipped with various sensors have the potential of providing context-aware services. Location is one of the most common forms of context, which can be applied to diverse applications. In this paper, we present methods for learning and predicting users' routes between significant locations, e.g., home and workplaces, based on personal GPS data. A user's significant locations and routes between them are learned by a set of rules as well as clustering. When the user is moving, our methods can predict which of the learned routes is being taken now. After the route prediction, the user's next location can also be inferred. Our methods have been applied to the real GPS datasets from four subjects. For the next location prediction task, the achieved accuracy was 84.8%.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.237-242
• /
• 2005

Predicting the cellular location of an unknown protein gives a valuable information for inferring the possible function of the protein. For more accurate prediction system, we need a good feature extraction method that transforms the raw sequence data into the numerical feature vector, minimizing information loss. In this paper, we propose new methods of extracting underlying features only from the sequence data by computing pairwise sequence alignment scores. In addition, we use composition based features to improve prediction accuracy. To construct an SVM ensemble from separately trained SVM classifiers, we propose specificity based weighted majority voting. The overall prediction accuracy evaluated by the 5-fold cross-validation reached 88.53% for the eukaryotic animal data set. By comparing the prediction accuracy of various feature extraction methods, we could get the biological insight on the location of targeting information. Our numerical experiments confirm that our new feature extraction methods are very useful for predicting subcellular localization of proteins.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.91-98
• /
• 2023

With the increasing flood damage by frequently localized heavy rains, flood prediction research are being conducted to prevent flooding damage in advance. In this paper, we present a machine-learning scheme for developing a flooding depth and location prediction model using real-time rainfall data. This scheme proposes a dataset configuration method using the data as input, which can robustly configure various rainfall distribution patterns and train the model with less memory. These data are composed of two: valid total data and valid local. The one data that has a significant effect on flooding predicted the flooding location well but tended to have different values for predicting specific rainfall patterns. The other data that means the flood area partially affects flooding refers to valid local data. The valid local data was well learned for the fixed point method, but the flooding location was not accurately indicated for the arbitrary point method. Through this study, it is expected that a lot of damage can be prevented by predicting the depth and location of flooding in a real-time manner.