• Journal of Internet of Things and Convergence
• /
• v.6 no.4
• /
• pp.65-72
• /
• 2020

In this paper, we developed a web-based DApp system based on a private blockchain by applying machine learning techniques to automatically identify Android malicious apps that are continuously increasing rapidly. The optimal machine learning model that provides 96.2587% accuracy for Android malicious app identification was selected to the authorized experimental data, and automatic identification results for Android malicious apps were recorded/managed in the Hyperledger Fabric blockchain system. In addition, a web-based DApp system was developed so that users who have been granted the proper authority can use the blockchain system. Therefore, it is possible to further improve the security in the Android mobile app usage environment through the development of the machine learning-based Android malicious app identification block chain DApp system presented. In the future, it is expected to be able to develop enhanced security services that combine machine learning and blockchain for general-purpose data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.12
• /
• pp.1253-1259
• /
• 2008

This paper presents a landing controller and guidance law for net-recovery of fixed-wing unmanned aerial vehicles. A linear quadratic controller was designed using the system identification result of the unmanned aerial vehicle. A pursuit guidance law is applied to guide the vehicle to a recovery net with imaginary landing points on the desired approach path. The landing performance of a pure pursuit guidance, a constant pseudo pursuit guidance, and a variable pseudo pursuit guidance is compared. Numerical simulation using an unmanned aerial vehicle model was performed to verify the performance of the proposed landing guidance law.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• The Journal of the Korea Contents Association
• /
• v.17 no.5
• /
• pp.624-632
• /
• 2017

Automatic butterfly identification using images is one of the interesting research fields because it helps the related researchers studying species diversity and evolutionary and development process a lot in this field. The performance of the butterfly species identification system is dependent heavily on the quality of selected features. In this paper, we propose color intensity (CI) entropy by using the distribution of color intensities in a butterfly image. We show color intensity entropy can increase the recognition rate by 10% if it is used together with previously suggested branch length similarity entropy. In addition, the performance comparison with other features such as Eigenface, 2D Fourier transform, and 2D wavelet transform is conducted against several well known machine learning methods.

• Korean Journal of Clinical Laboratory Science
• /
• v.45 no.4
• /
• pp.144-148
• /
• 2013

Candida spp. are yeast form fungi, which cause an opportunistic infections in a immune suppressed patients however it is a normal flora of the respiratory system, the gastrointestinal system, and the urogenital system of healthy person. It is investigated that the distribution of Candida spp. cause an oral disease from oral cavity of healthy people and also identified Candia dubliniensis. Distribution and identification of the yeast form fungi in oral cavities of healthy people was investigated by an automatic identifier, VITEK2 system. We found 21 strains of Candida albicans, 3 strains of Candida famata, one strain of Candida tropicalis, Candida haemulonii, Candida krusei, and Candida dubliniensis. In addition, one strain of Cryptococcus spp., Saccharomyces spp., and two unknown strains were isolated. Candida dubliniensis which forms a mass by more than 2 chlamydospores was isolated from a healthy person for the first time. Candida dubliniensis was not grown at $42^{\circ}C$ whereas Candida albicans was grown well. It is known that Candida dubliniencis was isolated in AIDS while it is found in healthy people from this study, which will be helpful to investigate the distribution of Candida spp.

• Journal of information and communication convergence engineering
• /
• v.5 no.4
• /
• pp.389-393
• /
• 2007

The distribution of donated blood for medical purpose is an area that presents many challenges. In order to establish a comprehensive solution, the current patterns of distribution must be reviewed and problems related to it need to be clearly understood. This paper introduces 'Radio Frequency Identification (RFID) System', as a potential solution to some of the problems which arise in the process of blood supply distribution, and a way to systematically manage the blood supply. For the various possible RFID systems, the reader and tag must be suitable for the purpose of blood distribution. A database has been designed that can recognize tags and objects in a ubiquitous RFID blood distribution system. In this paper, we design the real-time software to control the RFID reader system and transponder, using the EEPROM memory by RFID. The experimental results confirm that the transmission rate of 3.9kbps for RF is 125 KHz. The electric power usage of transponder chip is $100{\mu}W$, with the recognition distance is about 7cm range.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.5
• /
• pp.468-481
• /
• 2011

This research presents a strategy and information system to manage the logistics of delivery ready mixed concrete (RMC) under the integrated environment of PMIS+RFID. PMIS is system tool and technique used in construction sectors to delivery information. Information that can be extracted electronically in real time is more valuable than data gathered and maintained manually. RFID technology can help to improve data accuracy through supply chains and by identifying products and objects at specific points through automatic identification. The objectives of these two implementations can be able to improve the efficiency of logistics management for RMC truck process, and to verify the technical and practical feasibility of PMIS+RFID application in construction industry. This may be realistic given the dynamics of daily activities on construction sites. This research is focused on examples on real world case study, applications and research theme related and connected to PMIS+RFID technology. It demonstrated that PMIS+RFID technology has been automatically implemented and has shown process information about the RMC truck and the overall status information about it, both quickly and accurately. As a result, the construction site where needs 300 $m^3$ pouring (50 RMC trucks) per day can be reduced total 250 minutes. Moreover, this time saving is related to the labour cost saving. From the case studies, RFID+PMIS system was proven in terms of effectiveness rather than current method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.1 s.15
• /
• pp.97-103
• /
• 2000

The main purpose of 1-1-9 Caller Location Information System is to identify and display the precise location of emergency incidents such as natural or man - made fires, medical emergencies and accidents. The state - of- the - art technologies such as Am (Automatic Number Identification), GIS(Geographical Information System) and GPS (Global Positioning System) were applied and integrated in the system for efficient and effective location identification. It displays a radius of 25M, 50M and 100M on the map after location identification. The system can also provide the shortest path to an incident location from a fire station or a fire engine. In case of a fire breakout in or near a building, the attribute information of the building, called a building attribute card, is displayed along with the map location. The system then matches the information with the fire situation and sends an alert to a responsible fire station by phone or fax in order to help promptly react to the problem. An attribute card includes the critical information of a premise such as building's location, number of stories, floor plans, capacity, construction history, indoor fire detection and Prevention facilities, etc.

• 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.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.181-186
• /
• 2006

Estimation based on current data of construction performances have become one of the critical subjects which many researchers have been interested in for the past decades. In order to accomplish accurate measurement and estimation of construction performances, the method of data collection stands the highest priority. However, there are many difficulties in data collection from construction jobsite due to the characteristics of the construction industry. With developments of new technologies in other industries, several technologies has recently initiated to be applied to construction field. Electronic tags based on the identification technology, automatic volume measurement based on laser scanning technology, and Global Positioning System (GPS) have been represented the technologies which show the high opportunity for being used in construction. This study reviews specific aspects of these technologies focused on the utilization in construction jobsite. Also, the challenges which these technologies need to overcome are discussed.