• Annals of Laboratory Medicine
• /
• v.38 no.6
• /
• pp.512-517
• /
• 2018

Background: Complete blood count (CBC) results play an important role in peripheral blood smear (PBS) examinations. Many descriptions in PBS reports may simply be translated from CBC parameters. We developed a computer program that automatically generates a PBS draft report based on CBC parameters and age- and sex-matched reference ranges. Methods: The Java programming language was used to develop a computer program that supports a graphical user interface. Four hematology analyzers from three different laboratories were tested: Sysmex XE-5000 (Sysmex, Kobe, Japan), Sysmex XN-9000 (Sysmex), DxH800 (Beckman Coulter, Brea, CA, USA), and ADVIA 2120i (Siemens Healthcare Diagnostics, Eschborn, Germany). Input data files containing 862 CBC results were generated from hematology analyzers, middlewares, or laboratory information systems. The draft reports were compared with the content of input data files. Results: We developed a computer program that reads CBC results from a data file and automatically writes a draft PBS report. Age- and sex-matched reference ranges can be automatically applied. After examining PBS, users can modify the draft report based on microscopic findings. Recommendations such as suggestions for further evaluations are also provided based on morphological findings, and they can be modified by users. The program was compatible with all four hematology analyzers tested. Conclusions: Our program is expected to reduce the time required to manually incorporate CBC results into PBS reports. Systematic inclusion of CBC results could help improve the reliability and sensitivity of PBS examinations.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.635-638
• /
• 2006

Regression of conventional prediction techniques in data mining uses the model which is generated from the training step. This model is applied to new input data without any change. If this model is applied directly to time series, the rate of prediction accuracy will be decreased. This paper proposes an incremental regression for time series prediction like typhoon track prediction. This technique considers the characteristic of time series which may be changed over time. It is composed of two steps. The first step executes a fractional process for applying input data to the regression model. The second step updates the model by using its information as new data. Additionally, the model is maintained by only recent data in a queue. This approach has the following two advantages. It maintains the minimum information of the model by using a matrix, so space complexity is reduced. Moreover, it prevents the increment of error rate by updating the model over time. Accuracy rate of the proposed method is measured by RME(Relative Mean Error) and RMSE(Root Mean Square Error). The results of typhoon track prediction experiment are performed by the proposed technique IMLR(Incremental Multiple Linear Regression) is more efficient than those of MLR(Multiple Linear Regression) and SVR(Support Vector Regression).

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• New & Renewable Energy
• /
• v.20 no.1
• /
• pp.88-94
• /
• 2024

This study explored the potential and implementation of renewable energy sources in Sri Lanka, focusing on the theoretical potential of solar and wind energy to develop self-reliant energy models. Using advanced climate data from the European Centre for Medium-Range Weather Forecasts and Global Solar/Wind Atlas provided by the World Bank, we assessed the renewable energy potential across Sri Lanka. This study proposes off-grid and minigrid systems as viable solutions for addressing energy poverty in rural regions. Rural villages were classified based on solar and wind resources, via which we proposed four distinct energy self-reliance models: Renewable-Dominant, Solar-Dominant, Wind-Dominant, and Diesel-Dominant. This study evaluates the economic viability of these models considering Sri Lanka's current energy market and technological environment. The outcomes highlight the necessity for employing diversified energy strategies to enhance the efficiency of the national power supply system and maximize the utilization of renewable resources, contributing to Sri Lanka's sustainable development and energy security.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2007

This research note introduces the procedure of the quality control and quality assurance applied to the eddy covariance data collected at the two KoFlux sites (i.e., Gwangneung forest and Haenam farmland). The quality control was conducted through several steps based on micrometeorological theories and statistical tests. The data quality was determined at each step of the quality control procedure and was denoted by five different quality flags. The programs, which were used to perform the quality control, and the quality assessed data are available at KoFlux website (http://www.koflux.org/).

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.410-413
• /
• 2008

Existing Outlier detections have been widely studied in geosensor networks. Recently, machine learning and data mining have been applied the outlier detection method to build a model that distinguishes outliers based on anchored criterion. However, it is difficult for the existing methods to detect outliers against incoming time-variant data, because outlier detection needs to monitor incoming data and classify irregular attacks. Therefore, in order to solve the problem, we propose a time-variant outlier detection using 2-dimensional grid method based on unanchored criterion. In the paper, outliers using geosensor data was performed to classify efficiently. The proposed method can be utilized applications such as network intrusion detection, stock market analysis, and error data detection in bank account.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.721-723
• /
• 2003

Aggregation is an operation that returns a result value through a computational process on the data which satisfy a certain condition. Recently many applications use aggregation to analyze spatiotemporal data. Although spatiotemporal data change its states over time, previous aggregation works have only dealt with spatial or temporal aspect of object. In this paper we propose spatiotemporal aggregate functions that operate on spatiotemporal data. The proposed algorithms are evaluated through some implementation results. The experiment results show that the proposed aggregate functions are applicable to spatiotemporal data efficiently.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.716-718
• /
• 2004

The false alarm data in intrusion detection systems are divided into false positive and false negative. The false positive makes bad effects on the performance of intrusion detection system. And the false negative makes bad effects on the efficiency of intrusion detection system. Recently, the most of works have been studied the data mining technique for analysis of alert data. However, the false alarm data not only increase data volume but also change patterns of alert data along the time line. Therefore, we need a tool that can analyze patterns that change characteristics when we look for new patterns. In this paper, we focus on the false positives and present a framework for analysis of false alarm pattern from the alert data. In this work, we also apply incremental data mining techniques to analyze patterns of false alarms among alert data that are incremental over the time. Finally, we achieved flexibility by using dynamic support threshold, because the volume of alert data as well as included false alarms increases irregular.

• Structural Monitoring and Maintenance
• /
• v.7 no.4
• /
• pp.345-365
• /
• 2020

At present, many machine leaning and data mining methods are used for analyzing and predicting structural response characteristics. However, the platform that combines big data analysis methods with online and offline analysis modules has not been used in actual projects. This work is dedicated to developing a multifunctional Hadoop-Spark big data platform for bridges to monitor and evaluate the serviceability based on structural health monitoring system. It realizes rapid processing, analysis and storage of collected health monitoring data. The platform contains offline computing and online analysis modules, using Hadoop-Spark environment. Hadoop provides the overall framework and storage subsystem for big data platform, while Spark is used for online computing. Finally, the big data Hadoop-Spark platform computational performance is verified through several actual analysis tasks. Experiments show the Hadoop-Spark big data platform has good fault tolerance, scalability and online analysis performance. It can meet the daily analysis requirements of 5s/time for one bridge and 40s/time for 100 bridges.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.159-177
• /
• 2018

Participatory sensing is becoming popular and has shown its great potential in data acquisition for ambient assisted living. In this paper, we propose an incentive mechanism in participatory sensing for ambient assisted living, which benefits both the platform and the mobile devices that participated in the sensing task. Firstly, we analyze the profit of participant and platform, and a Stackelberg game model is formulated. The model takes privacy, reputation, power state and quality of data into consideration, and aims at maximizing the profit for both participant and publisher. The discussion of properties of the game show that there exists an unique Stackelberg equilibrium. Secondly, two algorithms are given: one describes how to reach the Stackelberg equilibrium and the other presents the procedures of employing the incentive strategy. Finally, we conduct simulations to evaluate the properties and effectiveness of the proposed mechanism. Simulation results show that the proposed incentive mechanism works well, and the participants and the publisher will be benefitted from it. With the mechanism, the total amount of sensory data can be maximized and the quality of the data can be guaranteed effectively.