• Journal of Internet Computing and Services
• /
• v.7 no.2
• /
• pp.23-35
• /
• 2006

This work presents o novel method which extract facial region und features from motion picture automatically and controls the 3D facial expression in real time. To txtract facial region and facial feature points from each color frame of motion pictures a new nonparametric skin color model is proposed rather than using parametric skin color model. Conventionally used parametric skin color models, which presents facial distribution as gaussian-type, have lack of robustness for varying lighting conditions. Thus it needs additional work to extract exact facial region from face images. To resolve the limitation of current skin color model, we exploit the Hue-Tint chrominance components and represent the skin chrominance distribution as a linear function, which can reduce error for detecting facial region. Moreover, the minimal facial feature positions detected by the proposed skin model are adjusted by using edge information of the detected facial region along with the proportions of the face. To produce the realistic facial expression, we adopt Water's linear muscle model and apply the extended version of Water's muscles to variation of the facial features of the 3D face. The experiments show that the proposed approach efficiently detects facial feature points and naturally controls the facial expression of the 3D face model.

• Journal of Internet Computing and Services
• /
• v.17 no.6
• /
• pp.123-131
• /
• 2016

Process mining in big data environment utilize a number of data were generated from the business process. It generates lots of knowledge and insights regarding implementation and improvement of the process through the event log of the company's enterprise resource planning (ERP) system. In recent years, various research activities engaged with the audit work of company organizations are trying actively by using the maximum strength of the mining process. However, domestic studies on applicable sales auditing system for the process mining are insufficient under big data environment. Therefore, we propose process-mining methods that can be optimally applied to online and traditional auditing system. In advance, we propose continuous monitoring information system that can early detect and prevent the risk under the big data environment by monitoring risk factors in the organizations of enterprise. The scope of the research of this paper is to design a pre-verification system for risk factor via practical examples in sales auditing. Furthermore, realizations of preventive audit, continuous monitoring for high risk, reduction of fraud, and timely action for violation of rules are enhanced by proposed sales auditing system. According to the simulation results, avoidance of financial risks, reduction of audit period, and improvement of audit quality are represented.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.4
• /
• pp.273-287
• /
• 2001

In this paper, we introduce our experience for designing and implementing a media manager in the Integrated Streaming Service Architecture (ISSA) developed by the authors. The media manager is regarded as a necessary module in the ISSA framework for the following reasons. It realizes that from which locations of the media source devices, the media streams are coming. Once it knows where the origin is, the media manager should recognizes what types of stream are. After that, it performs how to chose an appropriate CODEC to handle the recognized input streams efficiently, and what type of media playback device should be selected. In order to do such a job efficiently, the proposed media manager consists of two modules source module and sink module. The major role of a media source module is to make an abstraction for the media streams that are coming from various types of media device. This, in consequence, enables a media manager to consistently handle tlle media streams without considering wherever they come from. On the other hand, the media sink module distributes the input streams to an appropriate media device to playback. One of the remarkable virtues of the proposed media manager is an ability to supporting high value-added database services since it provides an interface between the ISSA and real-time multimedia database. Also, it provides the RTP!RTSP source filter and Winamp gateway modules which allow the flexibility to the system. Moreover, the media manager can adopt any types of new media which in fact will provide scalability to the ISSA.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.115-119
• /
• 2010

As the subjects of education has been changed from the instructors to learners, a web-based self-directed learning which can accelerate the initiative of learners and can be free from the restriction of time and space has been received attention. In this paper, the web-based self-directed learning system was designed. For the design, to make the learners build their own lecture plan, the service was designed to provide three kinds of lectures of video clip, slide lecture, and e-text lecture that were focused on various lecture contents. In addition, a learner and an assistant was man to man matched to enable the on-line mentoring for mutual communication between learners and assistants. Implementation was carried out by three sets of module - Manager, Learner and Assistant - that were applied to the real educational activities. The survey on satisfaction for the education, efficiency of ability improvement, and educational intelligibility for the attendants on the education showed more than 67.2% of satisfaction in satisfaction for the education. Furthermore, more than 86.9% of attendants replied that their ability were improved after the education of this system. The educational system realized in this paper shows effectiveness for the self-directed learning.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.589-599
• /
• 2021

Purpose: A reliable indicator of congested traffic speed is essential in providing the information of traffic flow states about motorway sections. The aim of this study is to propose an adaptive indicator of congested speed which is employed for deciding the traffic flow states for individual motorway sections using disaggregated section-based speed data. Method: Typically, the state of traffic flow is categorized into the three: uncongested, mixed, congested states. A method, presented in this study, was developed for identifying boundary speed values of road sections through categorizing the three traffic flow states with individual vehicular speed values. The boundary speed state of each road segment is determined using the speed distributions of mixed and congested traffic states. Result: Analysis results revealed that boundary speed values between mixed and congested states for road sections were similar to those of US and EU criteria (i.e., 48.28~66.0 kph). This indicates that boundary speed values could be different according to road sections. Conclusion: It is expected that the method and indicator, proposed in this study, could be efficaciously used for providing ad-hoc real-time traffic states and computing traffic congestion costs for motorway sections in the era of big data.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.17-26
• /
• 2021

This paper is about a physical layer frame security technique using OFB-style encryption/decryption with AES algorithms on Gigabit Ethernet network. We propose a data security technique at the physical layer that performs OFB-style encryption/decryption with AES algorithm with strong security strength when sending and receiving data over Gigabit Ethernet network. Generally, when operating Gigabit Ethernet network, there is no security features, but data security is required, additional devices that apply this technique can be installed to perform security functions. In the case of data transmission over Gigabit Ethernet network, the Ethernet frames conform to IEEE 802.3 specification, which includes several fields to ensure proper reception of data at the receiving node in addition to the data field. When encrypting, only the data field should be encrypted and transmitted in real time. In this paper, we show that only the data field of the IEEE802.3 frame is encrypted and transmitted on the sending node, and only the data field is decrypted to show the plain text on the receiving node, which shows that the encryption/decryption is carried out correctly. Therefore, additional installation of devices that apply this technique can increase the reliability of the system when security for data is required in Ethernet network operating without security features.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.268-279
• /
• 2021

The geospatial schemes based on topo-climatology have been developed to produce digital climate maps at a site-specific scale. Their development processes are reviewed here to derive the needs for new schemes in the future. Agricultural and forestry villages in Korea are characterized by complexity and diversity in topography, which results in considerably large spatial variations in weather and climate over a small area. Hence, the data collected at a mesoscale through the Automated Synoptic Observing System (ASOS) operated by the Korea Meteorological Administration (KMA) are of limited use. The geospatial schemes have been developed to estimate climate conditions at a local scale, e.g., 30 m, lowering the barriers to deal with the processes associated with production in agricultural and forestry industries. Rapid enhancement of computing technologies allows for near real-time production of climate information at a high-resolution even in small catchment areas and the application to future climate change scenarios. Recent establishment of the early warning service for agricultural weather disasters can provide growth progress and disaster forecasts for cultivated crops on a farm basis. The early warning system is being expanded worldwide, requiring further advancement in geospatial schemes and digital climate mapping.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.77-86
• /
• 2022

The Republic of Korea is a country in which coastal surveillance is an imperative national task as it is surrounded by seas on three sides under the confrontation between South and North Korea. However, due to Defense Reform 2.0, the number of R/D (Radar) operating personnel has decreased, and the period of service has also been shortened. Moreover, there is always a possibility that a human error will occur. This paper presents specific guidelines for developing an AI learning model for the intelligent coastal surveillance system. We present a three-step strategy to realize the guidelines. The first stage is a typical stage of building an AI learning model, including data collection, storage, filtering, purification, and data transformation. In the second stage, R/D signal analysis is first performed. Subsequently, AI learning model development for classifying real and false images, coastal area analysis, and vulnerable area/time analysis are performed. In the final stage, validation, visualization, and demonstration of the AI learning model are performed. Through this research, the first achievement of making the existing weapon system intelligent by applying the application of AI technology was achieved.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.33-40
• /
• 2021

Automatic Speech Recognition(ASR) is a technology that analyzes human speech sound into speech signals and then automatically converts them into character strings that can be understandable by human. Speech recognition technology has evolved from the basic level of recognizing a single word to the advanced level of recognizing sentences consisting of multiple words. In real-time voice conversation, the high recognition rate improves the convenience of natural information delivery and expands the scope of voice-based applications. On the other hand, with the active application of speech recognition technology, concerns about related cyber attacks and threats are also increasing. According to the existing studies, researches on the technology development itself, such as the design of the Automatic Speaker Verification(ASV) technique and improvement of accuracy, are being actively conducted. However, there are not many analysis studies of attacks and threats in depth and variety. In this study, we propose a cyber attack model that bypasses voice authentication by simply manipulating voice frequency and voice speed for AI voice recognition service equipped with automated identification technology and analyze cyber threats by conducting extensive experiments on the automated identification system of commercial smartphones. Through this, we intend to inform the seriousness of the related cyber threats and raise interests in research on effective countermeasures.