• Journal of Biomedical Engineering Research
• /
• v.36 no.4
• /
• pp.79-85
• /
• 2015

The purpose of this study is to develop an automatic algorithm for vessel segmentation in X-Ray angiogram using Random Forest (RF). The proposed algorithm is composed of the following steps: First, the multiscale hessian-based filtering is performed in order to enhance the vessel structure. Second, eigenvalues and eigenvectors of hessian matrix are used to learn the RF classifier as feature vectors. Finally, we can get the result through the trained RF. We evaluated the similarity between the result of proposed algorithm and the manual segmentation using 349 frames, and compared with the results of the following two methods: Frangi et al. and Krissian et al. According to the experimental results, the proposed algorithm showed high similarity compared to other two methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.576-599
• /
• 2013

Protocol reverse engineering is useful for many security applications, including intelligent fuzzing, intrusion detection and fingerprint generation. Since manual reverse engineering is a time-consuming and tedious process, a number of automatic techniques have been proposed. However, the accuracy of these techniques is limited due to the complexity of binary instructions, and the derived formats have missed constraints that are critical for security applications. In this paper, we propose a new approach for protocol format extraction. Our approach reasons about only the evaluation behavior of a program on the input message from concolic execution, and enables field identification and constraint inference with high accuracy. Moreover, it performs binary analysis with low complexity by reducing modern instruction sets to BIL, a small, well-specified and architecture-independent language. We have implemented our approach into a system called Icefex and evaluated it over real-world implementations of DNS, eDonkey, FTP, HTTP and McAfee ePO protocols. Experimental results show that our approach is more accurate and effective at extracting protocol formats than other approaches.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.6
• /
• pp.889-897
• /
• 1986

The purpose of this study is to describe the strategy of machining process suitable for developing adaptive control with constraint of NC-machine tool. The algorithm that controls machining process parameters of every sampling time is established for the constraint of torque in machinig center. To prove this AC algorithm, manual AC-unit control test is used for simulating the on-line AC strategy control. Also machining tests are carried out on a CNC-machining center fitted with the ACC system and compared with the simulated results. The practical effectiveness of the ACC systems so discussed and the reduction of machining time are demonstrated with reference to typical models of cutting workpieces. As a typical model, taper and step geometry model are selected. The computer simulation results have a good agreement with the experimental observation and make it possible to develope a NC-machine tool with an on-line ACC system.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.1
• /
• pp.174-183
• /
• 2005

A train driving requires to n the fixed distance within given time, and it is desirable to consume low energy if necessary. Reducing energy consumption depends on the train operation modes by either manual or automatic operation. In this article, an operation to reduce energy consumption by changing modes of train operation by a driver without changing the train operation requirement is investigated. The powering model, braking model and consumed energy calculation model are developed, then simulated by using a Matlab software. The accuracy of the train dynamic model established by the simulations is verified by comparing with the real experimental data. Several simulations by various operations in the real track are executed, then the desirable pattern of train driving is found.

• Journal of Biosystems Engineering
• /
• v.18 no.1
• /
• pp.60-70
• /
• 1993

In this study, the environment variations and distributions in different types of greenhouses were measured and analyzed. The elements of environment analyzed were temperature, relative humidity, illumination, carbon dioxide and wind velocity. The analyzed greenhouse types were auto-multi type which has an automatic environment control system and multiple continuous arches, regular-multi type which has an temperature control system and multiple continuous arches, and single arch type which has no environment control system without manual temperature keeping method. The results of this study can be used for the greenhouse building and managements.

• Proceedings of the KWS Conference
• /
• 2001.05a
• /
• pp.65-68
• /
• 2001

The application of a feedback control system in robotic arc welding is becoming more and more demanding than ever before. This requirement arises from the fact that robotic arc welding process needs no manual operator to monitor and manipulate the process parameters and hence a means of controlling the quality of the robotic arc welding process becomes apparent. Arc force sensor employed in this research to monitor the bead geometry of the arc welding process, A relationship between the bead dimension and the arc force distributions was established. Experimental configuration for measurement of arc force was used to quantify the changes in the arc force distributions of the plate being welded. Arc force sensor mounted at the end of the robot wrist was employed to measure the arc force applied to the weld. The sensor information was the used to establish a relationship between welding current and arc force. Arc force sensor have shown to be on of the most sophisticated technique to monitor perturbations that occurred during arc welding process.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.4
• /
• pp.103-110
• /
• 2019

A patent contains detailed information of the developed technology and is published to the public. Thus, patents can be used to overcome the limitations of traditional technology trend research and prediction techniques. Recently, due to the advantages of patented analytical methodology, IP R&D is carried out worldwide. The patent is big data and has a huge amount, various domains, and structured and unstructured data characteristics. For this reason, there are many difficulties in collecting and researching patent information. Patent research generally writes the Search formula to collect patent documents from DB. The collected patent documents contain some noise patents that are irrelevant to the purpose of analysis, so they are removed. However, eliminating noise patents is a manual task of reading and classifying technology, which is time consuming and expensive. In this study, we propose a model that automatically classifies The Noise patent for efficient patent information research. The proposed method performs Patent Embedding using Word2Vec and generates Noise seed label. In addition, noise patent classification is performed using the Random forest. The experimental data is published and registered with the USPTO among the patents related to Ocean Surveillance & Tracking Network technology. As a result of experimenting with the proposed model, it showed 73% accuracy with the label actually given by experts.

• Asian Oncology Nursing
• /
• v.9 no.1
• /
• pp.67-75
• /
• 2009

Purpose: The purpose of this study was to analyze nursing research trends on the complementary and alternative therapies (CAT) for the cancer patients in Korea. Method: Thirty eight articles published in 17 nursing-related journal from 1987 to 2008 were analyzed. Results: Nursing Researches on CAT for the cancer patients have increased since 2000. Among the 38 studies, 34 studies used Quasi-experimental design and 13 studies (33%) were conducted for the breast cancer patients. Mind-body therapy (53%), manual healing therapy (42%), and pharmacologic and biological therapy (5%) were the often used CAT types. Nausea, vomiting, vital signs, immune cell, pain, and fatigue were measured as physiologic outcome variables; anxiety, depression, and hope as psychological outcome variables; and quality of life as social outcome variables. Conclusion: More CAM studies are needed targeting the patients with various cancer types and home-based cancer patients.

• Journal of Drive and Control
• /
• v.11 no.4
• /
• pp.61-67
• /
• 2014

When a manual transmission equipped car stops on an incline where the nose of the car is higher than the rear, hill-start control or hill-holder could prevent the vehicle from rolling backward as the car moves forward. The easy-hill assist valve consists of a check valve and a needle type ON/OFF solenoid valve connected in parallel; it is a hydraulic actuator that can maintain brake pressure using an electrical signal from the ECU. As the EHA valve is a safety-related component of the brake system, high reliability as well as superior dynamic performance is required for it to be applied in commercial vehicles. This paper presents the design of the EHA valve as a piece of equipment that can simulate the brake actuation pressure with a pressurizing piston. Following specific test standards, the experimental results validate the implemented functions of the test equipment, proving the test stand to be effective for the performance and endurance of the EHA valve.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.1
• /
• pp.145-152
• /
• 2016

The usage of LED(Light Emitting Diode) has been rapidly increased and energy efficient management of LED light system is regarded as an important technology to enhance the energy efficiency. In this paper, we design and implementation of LED lighting controller which can control the LED lighting by using the wire and wireless communication technology based on the LAN(Local Area Network) and PAN(Personal Area Network). The implemented system can reduce the cost of LED lighting installing and avoids complicated wiring problem. And it is possible to minimize power consumption through automatic or manual LED control that they wished. In experimental results, the implemented LED lighting controller was satisfactory for all of the desired functions.