• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1125-1136
• /
• 2010

Lately there exist increasing demands for online abnormality monitoring over trajectory stream, which are obtained from moving object tracking devices. This problem is challenging due to the requirement of high speed data processing within limited space cost. In this paper, we present a FADA (Fuzzy Anomaly Detection Algorithm) which constructs normal profile by computing mobility feature information from the GPS (Global Positioning System) logs of mobile devices in MANETs (Mobile Ad-hoc Networks), computes a fuzzy dissimilarity between the current mobility feature information of the mobile device and the mobility feature information in the normal profile, and detects effectively the anomaly behaviors of mobile devices on the basis of the computed fuzzy dissimilarity. The performance of proposed FADA is evaluated through simulation.

• The Journal of Society for e-Business Studies
• /
• v.5 no.2
• /
• pp.101-112
• /
• 2000

Costs and times, resources was better decreased than former times because it had been introduced EDI(Electronic Data Interchange) system. Nevertheless, many problems has been raised as before, that is high costs and data re-using, the rapidly changing environment, etc. To solve these problems, it was attempted to introduce XML technology at traditional EDI System. From this point to view, 1 designed and implemented XML/EDI System based on Internet(Internet Messaging System) in this paper. And I selected some services as basic service among many services which is provided at XML/EDI System, that is message sending and message receiving, message retrieval. Other service of client system was composed of MapIn and MapOut module. MapIn Module is to parse the received XML Message and to store XML Data to RDB system. And MapOut module is to generate XML Message after extracting data from RDB system and to transfer XML Message to recipient. Hereby, XML/EDI System(XEDI System) provide document re-using, the various result(output) generation f3r various requirement and directly interface with DB. Therefore, This System(XEDI System) is more various and more flexible than the existing Messaging System that just provide transfer and retrieval service

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.10
• /
• pp.579-585
• /
• 2003

Recently most of 3D graphics rendering Processors have the pixel cache storing depth data and color data to reduce the memory latency and the bandwidth requirement. In this paper, we propose the effective pixel cache for improving the performance of a rendering processor. The proposed cache system stores the depth data selectively based on the result of Z-test and the color data are stored into the auxiliary buffer. Simulation results show that the 16Kbyte proposed cache system provides better performance than the 32Kbyte conventional cache.

• Journal of the Korean Solar Energy Society
• /
• v.30 no.2
• /
• pp.54-64
• /
• 2010

Interest in new and renewable energies like solar energy and wind energy is increasing throughout the world due to the rapidly expanding energy consumption and environmental reasons. An essential requirement for wind force power generation is estimating the size of wind energy accurately. Wind energy is estimated usually using meteorological data or field measurement. This study attempted to estimate wind energy density using meteorological data on daily mean wind speed and the Weibull parameters in Seoul, a representative inland city where over 60% of 15 story or higher apartments in Korea are situated, and Busan, Incheon, Ulsan and Jeju that are major coastal cities in Korea. According to the results of analysis, the monthly mean probability density distribution based on the daily mean wind speed agreed well with the monthly mean probability density distribution based on the Weibull parameters. This finding suggests that the Weibull parameters, which is highly applicable and convenient, can be utilized to estimate the wind energy density distribution of each area. Another finding was that wind energy density was higher in coastal cities Busan and Incheon than in inland city Seoul.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Journal of Astronomy and Space Sciences
• /
• v.35 no.4
• /
• pp.243-252
• /
• 2018

In a satellite gravimetry mission similar to GRACE, the precision of inter-satellite ranging is one of the key factors affecting the quality of gravity field recovery. In this paper, the impact of ranging precision on the accuracy of recovered geopotential coefficients is analyzed. Simulated precise orbit determination (POD) data and inter-satellite range data of formation-flying satellites containing white noise were generated, and geopotential coefficients were recovered from these simulated data sets using the crude acceleration approach. The accuracy of the recovered coefficients was quantitatively compared between data sets encompassing different ranging precisions. From this analysis, a rough prediction of the accuracy of geopotential coefficients could be obtained from the hypothetical mission. For a given POD precision, a ranging measurement precision that matches the POD precision was determined. Since the purpose of adopting inter-satellite ranging in a gravimetry mission is to overcome the imprecision of determining orbits, ranging measurements should be more precise than POD. For that reason, it can be concluded that this critical ranging precision matching the POD precision can serve as the minimum precision requirement for an on-board ranging device. Although the result obtained herein is about a very particular case, this methodology can also be applied in cases where different parameters are used.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.644-652
• /
• 2022

During the pyroprocessing operation, various signals can be collected by process monitoring (PM). These signals are utilized to diagnose process states. In this study, feasibility of using PM for nuclear safeguards of electrorefining operation was examined based on the use of machine learning for detecting off-normal operations. The off-normal operation, in this study, is defined as co-deposition of key elements through reduction on cathode. The monitored process signal selected for PM was cathode potential. The necessary data were produced through electrodeposition experiments in a laboratory molten salt system. Model-based cathodic surface area data were also generated and used to support model development. Computer models for classification were developed using a series of recurrent neural network architectures. The concept of transfer learning was also employed by combining pre-training and fine-tuning to minimize data requirement for training. The resulting models were found to classify the normal and the off-normal operation states with a 95% accuracy. With the availability of more process data, the approach is expected to have higher reliability.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.199-203
• /
• 2023

In recent decades, the growth of communication technology has resulted in an explosion of data-related information. Ontology perception is being used as a growing requirement to integrate data and unique functionalities. Ontologies are not only critical for transforming the traditional web into the semantic web but also for the development of intelligent applications that use semantic enrichment and machine learning to transform data into smart data. To address these unclear facts, several researchers have been focused on expanding ontologies and semantic web technologies. Due to the lack of clear-cut limitations, ontologies would not suffice to deliver uncertain information among domain ideas, conceptual formalism supplied by traditional. To deal with this ambiguity, it is suggested that fuzzy ontologies should be used. It employs Ontology to introduce fuzzy logical policies for ambiguous area concepts such as darkness, heat, thickness, creaminess, and so on in a device-readable and compatible format. This survey efforts to provide a brief and conveniently understandable study of the research directions taken in the domain of ontology to deal with fuzzy information; reconcile various definitions observed in scientific literature, and identify some of the domain's future research-challenging scenarios. This work is hoping that this evaluation can be treasured by fuzzy ontology scholars. This paper concludes by the way of reviewing present research and stating research gaps for buddy researchers.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.205-212
• /
• 2018

With the development of high performance CPU / GPU, artificial intelligence algorithms such as deep neural networks, and a large amount of data, machine learning has been extended to various applications. In particular, a large amount of data collected from the Internet of Things, social network services, web pages, and public data is accelerating the use of machine learning. Learning data sets for machine learning exist in various formats according to application fields and data types, and thus it is difficult to effectively process data and apply them to machine learning. Therefore, this paper studied a method for building a learning data set for machine learning in accordance with standardized procedures. This paper first analyzes the requirement of learning data set according to problem types and data types. Based on the analysis, this paper presents the reference model to build learning data set for machine learning applications. This paper presents the target standardization organization and a standard development strategy for building learning data set.