• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.209-213
• /
• 2023

In recent years, the image processing mechanisms are used widely in several medical areas for improving earlier detection and treatment stages, in which the time factor is very important to discover the disease in the patient as possible as fast, especially in various cancer tumors such as the liver cancer. Liver cancer has been attracting the attention of medical and sciatic communities in the latest years because of its high prevalence allied with the difficult treatment. Statistics indicate that liver cancer, throughout world, is the one that attacks the greatest number of people. Over the time, study of MR images related to cancer detection in the liver or abdominal area has been difficult. Early detection of liver cancer is very important for successful treatment. There are few methods available to detect cancerous cells. In this paper, an automatic approach that integrates the intensity-based segmentation and k-means clustering approach for detection of cancer region in MRI scan images of liver.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.144-147
• /
• 2004

Two different sensors (here, KOMPSAT and RADARSAT) are considered for ship detection, and are used to delineate the detection performance for their data. The experiments are set for coastal regions of Mokpo Port and Ulsan Port and field experiments on board pilot boat are conducted to collect in situ ship validation information such as ship type and length. This paper introduce mainly the experiment result of ship detection by both RADARSAT SAR imagery and landbased RADAR data, operated by the local Authority of South Korea, so called vessel traffic system (VTS) radar. Fine imagery of Ulsan Port was acquired on June 19, 2004 and in-situ data such as wind speed and direction, taking pictures of ships and natural features were obtained aboard a pilot ship. North winds, with a maximum speed of 3.1 m/s were recorded. Ship's position, size and shape and natural features of breakwaters, oil pipeline and alongside ship were compared using SAR and VTS. It is shown that KOMPSAT/EOC has a good performance in the detection of a moving ship at a speed of 7 kts or more an hour that ship and its wake can be imaged. The detection capability of RADARSAT doesn't matter how fast ship is running and depends on a ship itself, e.g. its material, length and type. Our results indicate that SAR can be applicable to automated ship detection for a VTS and SAR combination service.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2001.11a
• /
• pp.42-71
• /
• 2001

Leakage detection system can possibly locate leak point without laboratory analysis. Several different types of sensors provide these benefits. But the use of these technologies is not widespread, mainly because of cost. Each of the leakage detection systems available has different advantages and disadvantages. The ideal system would be affordable, durable enough to last through the life of the landfill, automated, and applicable to all types of landfills. The laboratory tests were performed to investigate the relationship between electrical resistivity and the unsaturated subsurface condition and to evaluate the contamination due to leachate based on measuring electrical resistivity. The results of experiment show that the electrical resistivity of soil decreases as moisture density increases. The electrical resistivity of soil decreases as the concentration of leachate in pore fluid increases. These facts indicate that electrical resistivity method can be a promising tool in detecting of leachate. Also, the field model tests were conducted to verify that detection of leachate leak point on detection system using electrical characteristics is accurate. Field model test results of leakage detection system imply that the leakage detection system using electrical characteristics have the great potential of detecting exactly the leak point of leachate.

• Fire Science and Engineering
• /
• v.34 no.2
• /
• pp.30-40
• /
• 2020

In the event of a fire and a disaster, prompt and accurate alarms inside and outside the building are directly related to the minimization of damage and the success of life evacuation. However, due to unwanted fire alarms in automated fire detection systems, the number of dispatches by misunderstanding in the 119 service is increasing. This causes the insensitivity to the safety of building managers and the waste of the fire-fighting power. Therefore, in this study, the statistical databases and literature on unwanted fire alarms in Korea and abroad (USA, UK) were identified and the management systems for unwanted fire alarms were compared and analyzed to identify problems of statistics in the management systems for unwanted fire alarms.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1013-1017
• /
• 2014

A variety of applications that are accessible through app markets provide useful features and functions. However, those applications can present many GUI bugs due to the deficiency of testing processes. Even though various approaches have been developed for mobile app testing, GUI bugs in applications are still difficult to be identified due to the absence of efficiency, lack of automation, and necessity of access to the source code. In this paper, we propose an automated black-box testing method for efficient GUI bug detection. Our experimental results show that the proposed method achieves better code coverage and uncovers GUI bugs when compared with existing black-box testing called Monkey.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.37 no.2
• /
• pp.106-114
• /
• 2017

This paper presents an automated subsurface micro void detection technique based on pulsed infrared thermography for inspecting epoxy molding compounds (EMC) used in electronic device packaging. Subsurface micro voids are first detected and visualized by extracting a lock-in amplitude image from raw thermal images. Binary imaging follows to achieve better visualization of subsurface micro voids. A median filter is then applied for removing sparse noise components. The performance of the proposed technique is tested using 36 EMC samples, which have subsurface (below $150{\mu}m{\sim}300{\mu}m$ from the inspection surface) micro voids ($150{\mu}m{\sim}300{\mu}m$ in diameter). The experimental results show that the subsurface micro voids can be successfully detected without causing any damage to the EMC samples, making it suitable for automated online inspection.

• Imaging Science in Dentistry
• /
• v.32 no.4
• /
• pp.187-194
• /
• 2002

Purpose: To evaluate the performance of the LOGICON Caries Detector using RVG-4 and RVG-ui sensors, by comparing results of each detector to the results of clinical and histological examinations. Materials and Methods : Pairs of extracted teeth were radiographed, and a total of 57 proximal surfaces, which included both carious and non-carious situations, were analyzed. The RVG-4 produced 8-bit images, while the RVG-ui unit produced 12-bit images, which were taken in the high sensitivity mode. The images produced by the LOGICON were evaluated by a trained observer using both automated and manual caries detection software modes. Ground sections of the teeth established the actual absence or existence of caries. Results: LOGIC ON-aided caries detection and depth discrimination of the RVG-4 and RVG-ui sensors were equally inconsistent irrespective of whether the LOGIC ON software was set to the automated or manual mode. Sensitivity ranged from 50% to 57% for caries penetration of the enamel-dentin junction. Conclusion: Care needs to be taken when using LOGIC ON in conjunction with RVG images as an adjunct for treatment planning dental caries. Even when applied by a trained observer, substantial discrepancies exist between the results of the LOGIC ON software-guided evalutations using RVG images and histologic examination.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.249-257
• /
• 2005

In this paper proposed automated attack reaction tool based on IPv6. Currently, much researches are performing focused on application program and standardization for IPv6. But, It is not enough for future IPv6 security. The proposed method detect attacks on IPv6 and conventional IPv4, therefore it is possible to protect personal information using automated reaction method. Usually, IDS just perform detection, therefore damages may be repeated. However, this paper considered the problems described above, and suggested solution for this problems. The proposed algorithm suggested in this paper is simulated on IPv6 network based on Linux. As a simulation result, it is proved that proposed algorithm can detect attacks efficiently.

• The Korean Journal of Physiology and Pharmacology
• /
• v.23 no.2
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.