• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.10A
• /
• pp.1159-1166
• /
• 2004

This paper follows up the previous work on the linearly constrained, modified minimum mean-squared error(MMSE) detection for direct-sequence code-division multiple-access DS-CDMA) systems in fading channels. We find a condition to avoid the breakdown of joint modified MMSE detection and pilot symbol-aided channel estimation (PSACE). The linearly constrained, modified MMSE solution is theoretically shown to be robust against time variations in Rayleigh fading channels. This fact is consistent with the simulation results. We also show that under some conditions the linearly constrained, modified MMSE detection maximizes the output signal-to-interference-plus-noise ratio.(SINR)

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.5
• /
• pp.380-388
• /
• 2004

This study proposed an improved spike detection algorithm which automatically detects suitable spike threshold on the amplitude of surface electromyography(SEMG) signal during isometric contraction. The EMG data from the low back muscles was obtained in six channels and the proposed signal processing algorithm is compared with the median frequency and Gabriel's spike parameter. As a result, the reliability of spike parameter was inferior to the median frequency. This fact indicates that a spike parameter is inadequate for analysis of multi-channel EMG signal. Because of uncertainty of fixed spike threshold, the improved spike detection algorithm was proposed. It automatically detects suitable spike threshold depending on the amplitude of the EMG signal, and the proposed algorithm was able to detect optimal threshold based on mCFAR(modified Constant False Alarm Rate) in the every EMG channel. In conclusion, from the reliability points of view, neither median frequency nor existing spike detection algorithm was superior to the proposed method.

• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.604-615
• /
• 2019

Single-user spectrum sensing is susceptible to multipath effects, shadow effects, hidden terminals and other unfavorable factors, leading to misjudgment of perceived results. In order to increase the detection accuracy and reduce spectrum sensing cost, we propose an adaptive cooperative sensing strategy based on an estimated signal-to-noise ratio (SNR). Which can adaptive select different sensing strategy during the local sensing phase. When the estimated SNR is higher than the selection threshold, adaptive double threshold energy detector (ED) is implemented, otherwise cyclostationary feature detector is performed. Due to the fact that only a better sensing strategy is implemented in a period, the detection accuracy is improved under the condition of low SNR with low complexity. The local sensing node transmits the perceived results through the control channel to the fusion center (FC), and uses voting rule to make the hard decision. Thus the transmission bandwidth is effectively saved. Simulation results show that the proposed scheme can effectively improve the system detection probability, shorten the average sensing time, and has better robustness without largely increasing the costs of sensing system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.461-464
• /
• 2023

최근 GPT-3 와 LLaMa 같은 생성형 거대 언어모델을 활용한 서비스가 공개되었고, 실제로 많은 사람들이 사용하고 있다. 해당 모델들은 사용자들의 다양한 질문에 대해 유창한 답변을 한다는 이유로 주목받고 있다. 하지만 LLMs 의 답변에는 종종 Inconsistent content 와 non-factual statement 가 존재하며, 이는 사용자들로 하여금 잘못된 정보의 전파 등의 문제를 야기할 수 있다. 이에 논문에서는 동일한 질문에 대한 LLM 의 답변 샘플과 외부 지식을 활용한 Hallucination Detection 방법을 제안한다. 제안한 방법은 동일한 질문에 대한 LLM 의 답변들을 이용해 일관성 점수(Consistency score)를 계산한다. 거기에 외부 지식을 이용한 사실검증을 통해 사실성 점수(Factuality score)를 계산한다. 계산된 일관성 점수와 사실성 점수를 활용하여 문장 수준의 Hallucination Detection 을 가능하게 했다. 실험에는 GPT-3 를 이용하여 WikiBio dataset 에 있는 인물에 대한 passage 를 생성한 데이터셋을 사용하였으며, 우리는 해당 방법을 통해 문장 수준에서의 Hallucination Detection 성능이 baseline 보다 AUC-PR scores 에서 향상됨을 보였다.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.780-789
• /
• 2018

Nowadays, gun crimes occur very frequently not only in public places but in alleyways around the world. In particular, it is essential to detect a person armed by a pistol to prevent those crimes since small guns, such as pistols, are often used for those crimes. Because conventional works for armed person detection have treated an armed person as a single object in an input image, their accuracy is very low. The reason for the low accuracy comes from the fact that the gunman is treated as a single object although the pistol is a relatively much smaller object than the person. To solve this problem, we propose a novel algorithm called APDA(Armed Person Detection Algorithm). APDA detects the armed person using in a post-processing the positions of both wrists and the pistol achieved by the CNN-based human body feature detection model and the pistol detection model, respectively. We show that APDA can provide both 46.3% better recall and 14.04% better precision than SSD-MobileNet.

• Journal of Veterinary Clinics
• /
• v.14 no.2
• /
• pp.301-307
• /
• 1997

These studies were performed to provide some basic informations for developing an automatic system in dairy farming cattle in order that the farmers may easily and automatically detect the maintenance of pregnancy and the fact of abortion of the pregnant cows and also to find out the diseased animals with fever. As a method of automatical detection of the maintenance of pregnancy or the fact of abortion, weighing the pregnant cows was conducted from one month-pregnancy to the term using a digital balance. From the first to the 3rd month of pregnancy the body weight of dairy cows was slowly increased (less than 2% per month), then, relatively high increase (3.4% -4.3% per month) from the fourth to the seventh month followed by decrease (3.3%) in the 8th month and very low increase (0.8-0.9%) from the 9th month to the term were shown, resulting in increase of 128.8 kg (25.05%) of body weight to be compared with the first weight. More than 107, increase of body weight to be compared with the first month-weight was denoted from the 61th month of pregnancy and more than 20% increase from the 7th or the 8th month of pregnancy as wells consequently it was presumed that detection of the maintenance of pregnancy is possible from the 4th or the 5th month of pregnancy. It was possible to diagnose a cow aborted at the 6th month by continual weighing the cow from the 1st month of pregnancy. The calved cows showed considerably higher decrease of body weight even in the third week after parturition (p<0.01)to be compared with the body weight near to the term (81.8-102.0 kg, 14-16% decrease). During the same period of 8months, the pregnant cows gained 127.4 kg (24.78% increase), whereas the non-pregnant cows gained 33.0 kg (0.71% increase) to be compared with the first weight showing considerably higher increase of body weight gain in the pregnant cows than the non-pregnant cows (p<0.01). The statistics of body temperatures of dairy cattle were collected from three clinics including the Teaching Hospital of Chonbuk University and the diseases were classified simply by the major symptoms manifested, denoting the highest temperature in respiratory disease ($39.8{\circ}C$) and the lowest in alimentary disease ($39.6{\circ} C$). These informations of body temperatures were expected to be of value for early and automatical detection of the diseased animals with fever when automatic machinery would be established. The results of periodic weighing the body weight of pregnant cows while milking were also expected to be of great use for the farmers to detect the maintenance of pregnancy and the fact of abortion when the automatic system is established in the near future.

• Journal of the Korea Convergence Society
• /
• v.10 no.7
• /
• pp.15-21
• /
• 2019

Research in detecting fake information gained a lot of interest after the US presidential election in 2016. Information from unknown sources are produced in the shape of news, and its rapid spread is fueled by the interest of public drawn to stimulating and interesting issues. In addition, the wide use of mass communication platforms such as social network services makes this phenomenon worse. Poynter Institute created the International Fact Checking Network (IFCN) to provide guidelines for judging the facts of skilled professionals and releasing "Code of Ethics" for fact check agencies. However, this type of approach is costly because of the large number of experts required to test authenticity of each article. Therefore, research in automated fake news detection technology that can efficiently identify it is gaining more attention. In this paper, we investigate fake news detection systems and researches that are rapidly developing, mainly thanks to recent advances in deep learning technology. In addition, we also organize shared tasks and training corpus that are released in various forms, so that researchers can easily participate in this field, which deserves a lot of research effort.

• Journal of The Korean Association of Information Education
• /
• v.12 no.2
• /
• pp.183-194
• /
• 2008

This research was conducted from the perspective of student management focusing on such central topic as realization of research ethics on the basis of research ethics case study model. In this study, improvement method for research ethics education through means of application of DEVAC System, which is a paper plagiarism detection system, and survey on current status of research ethics in college education and degree of consciousness thereof were explored. Through these investigations, a topic relating to establishment of the foundation in order to foster consciousness of research ethics in the college education was established as the primary purpose of this study. To accomplish the purpose of this study, firstly, actual situation of paper plagiarism committed by the college students and their consciousness were surveyed. Secondly, the research ethics education was examined through means of applying DEVAC paper plagiarism detection system. The results from investigations revealed the followings: First, 424 students (65.43%) who participated in this research and survey on the fact of paper plagiarism had experience of report plagiarism, and the result of investigation showed that 49.3% of students among those who had experience of paper plagiarism committed report plagiarism more than three times in a semester. And, 34.1% of participants showed a positive response to the use of a paper plagiarism detection system in the college, and results from the investigation displayed that the creative education (39.0%) marked the highest scores as in the educational method to reinforce the research ethics. Second, the results from examination of paper plagiarism having applied DEVAC system indicated that use of this system can be an alternative to prevent paper plagiarism from students. It is realized through this study that there is a necessity in various respects to build up the foundation which will enable individual students to improve their consciousness to such a degree so as to make them clearly recognize the fact that plagiarism is criminal act.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.176-178
• /
• 2005

In the images of a video camera employed for surveillance, detecting targets by extracting foreground image is of great importance. The foreground regions detected, however, include not only moving targets but also their shadows. This paper presents a novel technique to detect shadow pixels in the foreground image of a video camera. The image characteristics of video cameras employed, a web-cam and a CCD, are first analysed in the HSV color space and a pixel-level shadow detection technique is proposed based on the analysis. Compared with existing techniques where unified criteria are used to all pixels, the proposed technique determines shadow pixels utilizing a fact that the effect of shadowing to each pixel is different depending on its brightness in background image. Such an approach can accommodate local features in an image and hold consistent performance even in changing environment. In experiments targeting pedestrians, the proposed technique showed better results compared with an existing technique.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.7
• /
• pp.679-688
• /
• 2008

This paper presents an algorithm capable of detecting leading vehicles using a forward-looking camera. In fact, the accurate measurements of the contact locations of vehicles with road surface are prerequisites for the intelligent vehicle technologies based on a monocular vision. Relying on multistage processing of relevant edge features to the hypothesis generation of a vehicle, the proposed algorithm creates candidate positions being the left and right boundaries of vehicles, and searches for pairs to be vehicle boundaries from the potential positions by evaluating horizontal symmetry. The proposed algorithm is proven to be successful by experiments performed on images acquired by a moving vehicle.