• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.4
• /
• pp.71-83
• /
• 1989

The optimization in the machining process has been a long-standing goal of the manufacturing community. The optimization is composed of two main subjects;one is to select an optimum cutting condition, and the other is to detect the emergency situation and take necessary actions in real-time base. This paper proposes a reliable and practical guide system whose purpose is the optimization of cutting conditions, and the detection of tool failure in the machining process. The optimal cutting conditions are determined through the estimation of tool wear rate and the establishment of access- ible field from the measured cutting temperature and force. Tool breakage is detected by the normal force component acting on minor flank face extracted from on-line sensed feed force and radial force. In experiments, the proposed guide system has proved availability for the decision of reliable cutting conditions for the given tool-work system and the detection of tool breakage in ordinary cutting environments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.139-144
• /
• 1987

The problem of process(Sensor) fault management in Observer Based Control System are considered and structures of Fault Tolerant Observer based Control Systems (FMCS) that function well in the face of the faults are proposed. The FTOCSs include detection logic unit and an additional observer driven by residuals of primary observer and estimate estimation errors of primary observer and fault variables. Since the FTOCSs have the ability to detect and accomodate the faults the original control objectives can be accomplished without considerable control performance deterioration even in the faulty environments. Therefore, the Proposed FMCSs can effectively be used for enhancing the functional reliability of the Observer Based Control Systems.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1960-1963
• /
• 2003

For applications such as video surveillance and human computer interface, we propose an efficiently integrated method to detect and track faces. Various visual cues are combined to the algorithm: motion, skin color, global appearance and facial pattern detection. The ICA (Independent Component Analysis)-SVM (Support Vector Machine based pattern detection is performed on the candidate region extracted by motion, color and global appearance information. Simultaneous execution of detection and short-term tracking also increases the rate and accuracy of detection. Experimental results show that our detection rate is 91％ with very few false alarms running at about 4 frames per second for 640 by 480 pixel images on a Pentium IV 1㎓.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2003.07a
• /
• pp.121-125
• /
• 2003

In this paper, we propose a framework of Transmission Control Protocol with Software Rejuvenation methodology, which is applicable for network system survivability. This method is utilized to improve the survivability because it can limit the damage caused by successful attacks. The main objectives are to detect intrusions in real time, to characterize attacks, and to survive in face of attacks. To counter act the attacks' attempts or intrusions, we perform the Software Rejuvenation methods such as killing the intruders' processes in their tracks, halting abuse before it happens, shutting down unauthorized connection, and responding and restarting in real time. These slogans will really frustrate and deter the attacks, as the attacker can't make their progress. This is the way of survivability to maximize the deterrence against an attack in the target environment. We address a framework to model and analyze the critical intrusion tolerance problems ahead of intrusion detection on Transmission Control Protocol (TCP).

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.2
• /
• pp.199-207
• /
• 2010

Recently, large amount of information in IDS(Intrusion Detection System) can be un manageable and also be mixed with false prediction error. In this paper, we propose a data mining methodology for IDS, which contains uncertainty based on training process and post-processing analysis additionally. Our system is trained to classify the existing attack for misuse detection, to detect the new attack pattern for anomaly detection, and to define border patter between attack and normal pattern. In experimental results show that our approach improve the performance against existing attacks and new attacks, from 0.62 to 0.84 about 35%.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1515-1518
• /
• 2002

This paper proposes an active contour model to detect facial regions in a given image. Accordingly we use the color information human faces which is represented by a skin color model. We evolve the active contour using the level set method which allows for cusps, corners, and automatic topological changes. Experimental results show the effectiveness of the proposed method.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2003.12a
• /
• pp.141-145
• /
• 2003

We propose the model of Software Rejuvenation methodology, which is applicable for survivability. Software rejuvenation is a proactive fault management technique and being used in fault tolerant systems as a cost effective technique for dealing with software faults. Survivability focuses on delivery of essential services and preservation of essential assets, even systems are penetrated and compromised. Thus, our objective is to detect the intrusions in a real time and survive in face of such attacks. As we deterrent against an attack in a system level, the Intrusion tolerance could be maximized at the target environment. We address the optimal time to execute ad hoc software rejuvenation and we compute it by using the semi Markov process. This is one way that could be really frustrated and deterred the attacks, as the attacker can't make their progress. This Software Rejuvenation method can be very effective under the assumption of unknown attacks. In this paper, we compute the optimum time to perform an ad hoc Software Rejuvenation through intrusions.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.787-795
• /
• 2008

Human recognition on camera is an interesting topic in computer vision. While fingerprint and face recognition have been become common, gait is considered as a new biometric feature for distance recognition. In this paper, we propose a gait recognition algorithm based on the knee angle, 2 feet distance, walking velocity and head direction of a person who appear in camera view on one gait cycle. The background subtraction method firstly use for binary moving object extraction and then base on it we continue detect the leg region, head region and get gait features (leg angle, leg swing amplitude). Another feature, walking speed, also can be detected after a gait cycle finished. And then, we compute the errors between calculated features and stored features for recognition. This method gives good results when we performed testing using indoor and outdoor landscape in both lateral, oblique view.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.119-128
• /
• 2020

Object detection is an important field of computer vision and is applied to applications such as security, autonomous driving, and face recognition. Recently, as the application of artificial intelligence technology including deep learning has been applied in various fields, it has become a more powerful tool that can learn meaningful high-level, deeper features, solving difficult problems that have not been solved. Therefore, deep learning techniques are also being studied in the field of object detection, and algorithms with excellent performance are being introduced. In this paper, a deep learning-based object detection algorithm used to detect multiple objects in an image is investigated, and future development directions are presented.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.85-94
• /
• 2024

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.