• 한국정보시스템학회지:정보시스템연구
• /
• 제32권2호
• /
• pp.87-108
• /
• 2023

Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

• 지역사회간호학회지
• /
• 제13권2호
• /
• pp.363-375
• /
• 2002

Objectives: The aim of this study was to analyze the trend of research on cancer prevention and early detection in Korea, in order to suggest a future direction of research on cancer prevention and early detection for Koreans. Methods: A total of 97 studies published from 1980 to 2001 were analyzed according to the year of publication, research design, journal type, cancer type, major study concepts, and findings. Results: 1) The number of studies related to cancer prevention and early detection had increased rapidly since the year 1995. 2) The most frequently used research design in the studies was the descriptive study design (55.7%). 3) There were 10 master's theses on cancer prevention and early detection, and 10 studies published in the Korean Epidemiology Journal. 4) When classified by the published field, 47 studies (48.5%) were published in nursing journals, 46 studies (47.4%) were published in medical journals, and 4 studies (4.1%) were published in public health journals. 5) The major topics of the studies were cancer prevention (51.5%), early detection (44.4%), and cancer prevention and early detection (4.1%). 6) Breast cancer was the most largely addressed issue in the studies (N=25; 25.7%), followed by lung cancer (N=23; 23.7%), hepatoma (N=17; 17.5%), gastric cancer (N=16; 16.5%), other general type of cancer (N=6; 6.2%), colorectal cancer (N=5; 5.2%) and cervical cancer (N=5; 5.2%). Conclusion: It is suggested that there should be more studies on cancer prevention and early detection in the future, and, particularly, experimental studies to exam the effects of intervention on cancer prevention and early detection are considered necessary.

• 한국정보통신학회논문지
• /
• 제25권8호
• /
• pp.1117-1123
• /
• 2021

객체 인식이란 하나의 특정 이미지를 입력했을 때, 주어진 이미지를 분석하여 특정한 객체(object)의 위치(location)와 종류(class)를 파악하는 것이다. 최근 객체 인식 기술이 적극적으로 접목되는 분야 중 하나는 자율주행 차량이라 할 수 있고, 본 논문에서는 자율주행 차량에서 영상 기반의 객체 인식 인공지능 기술에 대해 기술한다. 영상 기반 객체 검출 알고리즘은 최근 두 가지 방법(단일 단계 검출 방법 및 두 단계 검출 방법)으로 좁혀지고 있는데, 이를 중심으로 분석 정리하고자 한다. 두 가지 검출 방법의 장단점을 분석 제시하고, 단일 단계 검출 방법에 속하는 YOLO/SSD 알고리즘과 두 단계 검출 방법에 속하는 R-CNN/Faster R-CNN 알고리즘에 대해 분석 기술한다. 이를 통해 자율주행에 필요한 각 객체 인식 응용에 적합한 알고리즘이 선별적으로 선택되어 연구개발 되어질 수 있기를 기대한다.

• 융합보안논문지
• /
• 제4권2호
• /
• pp.1-7
• /
• 2004

정보통신망의 빠른 발달과 이로 인한 인터넷 사용의 급증으로 인하여 해킹, 바이러스 등의 정보통신 역기능 또한 빠르게 발전하고 있다 이를 방지하기 위해 F/W, IDS, VPN 등의 보안 제품이 많이 사용되고 있다. 그러나, 1.25 인터넷 대란에서 알 수 있듯이 현 상황은 관리자가 보안 제품들에서 발생하는 경고 메시지를 확인하고 해당 내용을 대응할 수 없을 정도로 빠른 시간에 확산된다. 따라서, IDS와 더불어 자동 대응 기능을 갖추고 있는 침입방지시스템(IPS)이 절실히 요구되어지고 있고, 널리 사용되어지고 있다. 본 논문에서는 linux 운영 체제 환경에서의 공개된 도구인 snort와 iptables를 이용하여 시스템 구축 비용이 최소화될 수 있는 방향으로 설계되었다. 또한, snort에서 발생시킨 경보 메시지를 iptables와 연계하여 자동 대응을 수행하도록 구성되었으며, 이를 통하여 관리자 개입을 최소화하고 해킹사고에 대한 피해를 최소화 할 수 있도록 제안되었다.

• 대한의용생체공학회:의공학회지
• /
• 제27권3호
• /
• pp.131-141
• /
• 2006

A visual decision by clinical experts like physical therapists is a best way to detect onset and offset time of muscle activation. The current computer-based algorithms are being researched toward similar results of clinical experts. The new algorithm in this paper has an ability to extract a trend from noisy input data. Kalman smoother is used to recognize the trend to be revealed from disorderly signals. Histogram of smoothed signals by Kalman smoother has a clear boundary to separate muscle contractions from relaxations. To verify that the Kalman smoother algorithm is reliable way to detect onset and offset time of muscle contractions, the algorithm of Robert P. Di Fabio (published in 1987) is compared with Kalman smoother. For 31 templates of subjects, an average and a standard deviation are compared. The average of errors between Di Fabio's algorithm and experts is 109 milliseconds in onset detection and 142 milliseconds in offset detection. But the average between Kalman smoother and experts is 90 and 137 milliseconds in each case. Moreover, the standard deviations of errors are 133 (onset) and 210 (offset) milliseconds in Di Fabio's one, but 48 (onset) and 55 (offset) milliseconds in Kalman smoother. As a result, the Kalman smoother is much closer to determinations of clinical experts and more reliable than Di Fabio's one.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권11호
• /
• pp.4377-4384
• /
• 2014

According to the World Health Organization (WHO), 1.37 million people died of lung cancer all around the world in 2008, occupying the first place in all cancer-related deaths. However, this number might be decreased if patients were detected earlier and treated appropriately. Unfortunately, traditional imaging techniques are not sufficiently satisfactory for early detection of lung cancer because of limitations. As one alternative, breath volatile organic compounds (VOCs) may reflect the biochemical status of the body and provide clues to some diseases including lung cancer at early stage. Early detection of lung cancer based on breath analysis is becoming more and more valued because it is non-invasive, sensitive, inexpensive and simple. In this review article, we analyze the limitations of traditional imaging techniques in the early detection of lung cancer, illustrate possible mechanisms of the production of VOCs in cancerous cells, present evidence that supports the detection of such disease using breath analysis, and summarize the advances in the study of E-noses based on gas sensitive sensors. In conclusion, the analysis of breath VOCs is a better choice for the early detection of lung cancer compared to imaging techniques. We recommend a more comprehensive technique that integrates the analysis of VOCs and non-VOCs in breath. In addition, VOCs in urine may also be a trend in research on the early detection of lung cancer.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.240-242
• /
• 2005

It is well known that the PD (Partial Discharge) signals are generated if insulators have some defects such as voids in electrical facility and various PD detection methods are developed for preventing electrical troubles. So, an interest for the PD signals is higher and higher according to the high concern for the defects detection method of the aging electrical facility. When the equipment to detect PD signals installed at site and it works, a lot of noises flow in the equipment from surrounding situation and it will be mixed with original PD waveform. So we can not get the desired PD waveform. Therefore, there are many trial to reject or suppress the noise from the PD signals from long times ago. The greater of them used the hardware such as bridge circuits and frequency filters to suppress the noise. This paper proposed a novel noise rejection method in acquired data from PD detection equipment. The noise has the irregular phase and higher signal level than real PD, and noise decision is performed after inspection of pulse distribution in ${\Phi}$-q-n graph of acquired data from PD detection equipments. By experimental results on high voltage electric equipments, it is shown that proposed method has good performance. It is expected that this noise rejection technology is useful in numeric calculation and trend management of PD level.

• 한국산업보건학회지
• /
• 제28권1호
• /
• pp.100-107
• /
• 2018

Objectives: This study examines exposure to hazardous substances in the working environment caused by exposure to toxic substances produced in the aluminum die casting process in the automobile manufacturing industry. Materials and Methods: The exposure concentration levels, detection rates and time-trend of 15 hazardous factors in the aluminum die casting process over 10 years(from 2006 to 2016) were used as a database. Results: The study found that hazardous factors in the aluminum die casting process were mostly metals. The rate for detected samples was 70.6%(405 samples), and that for not detected samples was 29.4%. The noise for an eight-hour work shift showed a 49.7% exceedance rate for TLV-TWA. Average noise exposure was 89.0 dB. The maximum exposure level was 105.1 dB. Conclusion: The high numbers of no-detection rates for hazardous substance exposure shows that there is no need to do a work environment measurement. Therefore, alternatives are necessary for improving the efficiency and reliability of the work environment measurement. Moreover, to prevent noise damage, reducing noise sources from automation, shielding, or sound absorbents are necessary.

• 정보보호학회논문지
• /
• 제6권4호
• /
• pp.39-52
• /
• 1996

네트워크의 발달로 시공간을 초월하여 자료 및 자원의 공유, 분산처리, 컴퓨터 통신이 가능하게 되는 순기능도 있으나, 반면에 전세계 어디에서든지 컴퓨터를 통하여 컴퓨터 시스템의 무단 이용과 시스템의 파괴, 저장된 자료의 유출 등의 수단으로도 이용되고 있다. 최근의 동향은 국내뿐만아니라 외국에서도 한국으로의 해킹사례가 늘고 있어 그 심각성이 날로 증대되고 있다. 따라서 국방 전산자원을 보호해 줄 수 있는 시스템의 개발 및 적용이 시급하다. 본 논문에서는 예상되는 각종 침입에 대해 전산망 보안 요구사항을 도출하고 감사데이타를 활용하는 통계적 침입 탐지 및 규칙기반 침입 탐지 기법 분석을 통해 침입 탐지 시스템을 설계하고자 한다.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.688-701
• /
• 2023

The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.