• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.224-227
• /
• 2020

엣지컴퓨팅 기반 유해조수 퇴치 Drone의 유해조수 추적 기술은 Doppler Sensor를 이용해 사유지에 침입한 유해조수를 인식 후 사용자에게 위험 요소에 대한 알림 서비스를 제공한다. 이후 사용자는 Drone의 Camera와 전용 애플리케이션을 이용해 경작지를 실시간으로 보며 Drone을 조종한다. Camera는 Tensor Flow Object Detection Deep Learning을 적용하여 유해조수를 학습 및 파악, 추적한다. 이후 Drone은 Speaker와 Neo Pixel LED Ring을 이용해 유해조수의 시각과 청각을 자극해 도망을 유도하며 퇴치한다. Tensor Flow object detection을 핵심으로 Drone에 접목했고 이를 위해 전용 애플리케이션을 개발했다.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.569-573
• /
• 2016

Background: A colorectal cancer screening program was piloted in two districts of Kedah in 2013. There is scarcity of information on colorectal cancer screening in Malaysia. Objective: Thus, this research was conducted to evaluate the colorectal cancer screening program in the districts to provide insights intop its efficacy. Materials and Methods: A cross sectional study was conducted using data on the colorectal cancer screening program in 2013 involving Kota Setar and Kuala Muda districts in Malaysia. We determined the response rate of immunochemical fecal occult blood test (iFOBT), colonoscopy compliance, and detection rates of neoplasia and carcinoma. We also compared the response of FOBT by demographic background. Results: The response rate of FOBT for first iFOBT screening was 94.7% while the second iFOBT screening was 90.7%. Participants from Kuala Muda district were 27 times more likely to default while Indians had a 3 times higher risk of default compared to Malays. The colonoscopy compliance was suboptimal among those with positive iFOBT. The most common finding from colonoscopy was hemorrhoids, followed by tubular adenoma. Detection rate of carcinoma and neoplasia for our program was 1.2%. Conclusions: In summary, the response rate of iFOBT was encouraging but the colonoscopy compliance was suboptimal which led to a considerably low detection rate.

• Smart Media Journal
• /
• v.1 no.2
• /
• pp.47-53
• /
• 2012

Wind energy is currently the fastest growing source of renewable energy used for electrical generation around world. Wind farms are adding a significant amount of electrical generation capacity. The increase in the number of wind farms has led to the need for more effective operation and maintenance procedures. Condition Monitoring System(CMS) can be used to aid plant owners in achieving these goals. In this work, systematic design procedure for artificial neural network based normal behavior model which can be applied for fault detection of various devices is proposed. Furthermore, to verify the design method SCADA(Supervisor Control and Data Acquisition) data from 850kW wind turbine system installed in Beaung port were utilized.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.245-261
• /
• 2024

The COVID-19 pandemic has led to the widespread adoption of contactless transactions, resulting in a noticeable increase in the trend towards fully unmanned stores. In such stores, all operational processes are automated, primarily using artificial intelligence (AI) technology. However, this AI technology has several security vulnerabilities, which can be critical in the environment of fully unmanned stores. This paper analyzes the security vulnerabilities that AI-based fully unmanned stores may face, focusing particularly on the object detection model YOLO, demonstrating that Hiding Attacks and Altering Attacks using adversarial patches are possible. It is confirmed that objects with adversarial patches attached may not be recognized by the detection model or may be incorrectly recognized as other objects. Furthermore, the paper analyzes how Data Augmentation techniques can mitigate security threats by providing a defensive effect against adversarial patch attacks. Based on these results, we emphasize the need for proactive research into defensive measures to address the inherent security threats in AI technology used in fully unmanned stores.

• Korean Journal of Food Science and Technology
• /
• v.36 no.4
• /
• pp.677-682
• /
• 2004

Debates on safety of genetically modified (GM) crops have led to mandatory-labeling legislation of GM foods in many countries including Korea. Effects of heat, pressure, and acid treatments on degradation of DNAs or proteins in GM soybean at levels below detection limits of qualitative PCR and lateral flow strip test (LFST) methods were examined. Results showed that genomic DNAs and proteins were degraded into fragment sizes no longer possible for detection of inserted gene depending on thermal, or thermal and pressure treatment period. Detectaability of LFST for toasted meal increased in weakly treated soybean. DNA and protein detection methods were barely effective for detection of GM ingredient after $121^{\circ}C$ and 1.5 atmospheric treatment for 20 min. These results will be useful in determining GM labeling requirements of processed foods.

• Journal of Korean Society of Transportation
• /
• v.35 no.6
• /
• pp.469-480
• /
• 2017

On April 1, 2004, KTX (Korea Train eXpress), the first HSR (High-Speed Rail) in Korea, was introduced to Gyeongbu Line. The introduction of the KTX service led to a change in the number of passengers for Gyeongbu Line. Previous studies have analyzed the pre and post-event changes of the intervening events by either simple statistics or intervention ARIMA analysis. However, the intervention ARIMA model has a limitation that several assumptions such as the occurrence time and the type of intervention events are necessary. To this end, this study analyzed the effects of intervention event on the number of passengers using the Gyeongbu line based on a time series outlier detection technique which can overcome limitations in the previous studies. The time series outlier detection technique can analyze the time, effect type and size of an intervention event without the assumption of the time and effect type of the intervention event. The data were collected from the Korea Transport Database (KTDB) for twelve years from 2003 to 2014 (144 months). The analysis results showed that the size of the influence type in the same intervention events was different across the major city routes, and the intervention event which could not be found by previous study methods was also found.

• Korean Journal of Veterinary Service
• /
• v.31 no.1
• /
• pp.43-55
• /
• 2008

Recently, the major viral diseases, Newcastle disease (ND), infectious bronchitis (IB), low pathogenic avian influenza (LPAI), avian pneumovirus infection (APV), Marek's disease (MD) and infectious bursal disease (IBD), have led to huge economic losses in chicken industry of Korea. To evaluate prevalence of the major viral disease infections in broiler breeder and broiler farms, epidemiological survey has been conducted in Jeonbuk province from 2005 to 2007 by serological ELISA test for APV, PCR for MD, and RT-PCR for ND, IB, LPAI and IBD, respectively. A total of 424 cases was submitted to our laboratory for diagnosis of the major viral disease from broiler breeder and broiler farms in the above period. The diagnosed results were analysed for the detection rate of infections on basis of years, seasons and ages, respectively. This study was showed that the detection rates of ND and APV were considerably high for every years regardless of seasons and ages in both broiler breeder and commercial broiler. In comparison with detection rates of ND and APV, IB and LPAI were lower but detected around 10% for every years. Especially, detection rate of IB was significantly high in commercial broiler than in broiler breeder. Therefore, to minimize economic losses for broiler breeder and broiler farms, it will need for effective countermeasures to decrease detection rate of the viral respiratory diseases. Although the detection rates of MD and IBD were gradually decreased from 2005 to 2007 in both broiler breeder and commercial broiler, it will continually make an effort about disease control for increasing productivity in chicken industry.

• Journal of Oral Medicine and Pain
• /
• v.42 no.3
• /
• pp.85-88
• /
• 2017

Burkitt's lymphoma is a malignant monoclonal proliferation of early B-lymphocyte. Since Burkitt's lymphoma is a highly aggressive disease, early detection is a crucial. This disease often involves jaw and mandibular mass or swelling may also be seen, but in the early phase of Burkitt's lymphoma these symptoms cannot be observed. A rare case of Burkitt's lymphoma without any mandibular mass and the general symptoms was present. The excruciating toothache led the patient to visit the dental clinic and misdiagnosis of chronic periodontal abscess was made initially. Dentists should consider the oral manifestations of systemic disease when the multiple periodontal ligament space widening is observed and the dental treatment for mimicking odontogenic pain has no effect.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.583-585
• /
• 2004

In this paper we will deal with a calibration method for low cost motion capture system using psd(position sensitive detection) optical sensor. To measure the incident direction of the light from LED emitted marker, the PSD is used the output current ratio on the electrode of PSD is proportional with the incident position of the light focused by lens. In order to defect the direction of the light, the current output is converted into digital voltage value by opamp circuits peak detector and AD converter with the digital value the incident position is measured. Unfortunately, due to the non-linearly problem of the circuit poor position accuracy is shown. To overcome such problems, we compensated the non-linearly by using least-square fitting method. After compensated the non-linearly in the circuit, the system showed more enhanced position accuracy.