• Genomics & Informatics
• /
• 제18권2호
• /
• pp.20.1-20.4
• /
• 2020

Accessible negative results are relevant for researchers and clinicians not only to limit their search space but also to prevent the costly re-exploration of research hypotheses. However, most biomedical relation extraction datasets do not seek to distinguish between a false and a negative relation among two biomedical entities. Furthermore, datasets created using distant supervision techniques also have some false negative relations that constitute undocumented/ unknown relations (missing from a knowledge base). We propose to improve the distinction between these concepts, by revising a subset of the relations marked as false on the phenotype-gene relations corpus and give the first steps to automatically distinguish between the false (F), negative (N), and unknown (U) results. Our work resulted in a sample of 127 manually annotated FNU relations and a weighted-F1 of 0.5609 for their automatic distinction. This work was developed during the 6th Biomedical Linked Annotation Hackathon (BLAH6).

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.716-718
• /
• 2004

The false alarm data in intrusion detection systems are divided into false positive and false negative. The false positive makes bad effects on the performance of intrusion detection system. And the false negative makes bad effects on the efficiency of intrusion detection system. Recently, the most of works have been studied the data mining technique for analysis of alert data. However, the false alarm data not only increase data volume but also change patterns of alert data along the time line. Therefore, we need a tool that can analyze patterns that change characteristics when we look for new patterns. In this paper, we focus on the false positives and present a framework for analysis of false alarm pattern from the alert data. In this work, we also apply incremental data mining techniques to analyze patterns of false alarms among alert data that are incremental over the time. Finally, we achieved flexibility by using dynamic support threshold, because the volume of alert data as well as included false alarms increases irregular.

• 전자공학회논문지
• /
• 제51권1호
• /
• pp.37-41
• /
• 2014

최근 전력 스펙트럼의 형태적 특징을 사용하여 스펙트럼 감지를 수행하는 방식에 대한 연구가 활발하게 진행 중이다. 그 중에서 수신 신호의 전력 스펙트럼 최대값을 시험 통계량으로 사용하는 방안이 제시된 바가 있으며, 이때 시험 통계량을 가우시안 분포로 근사화하고, 해당 방식의 오경보 확률을 나타낸 바 있다. 본 논문에서는 가우시안이라는 가정을 사용하지 않는 정확한 오경보 확률을 제시하고, 이전 분석 결과와 비교하고자 한다.

• ETRI Journal
• /
• 제41권4호
• /
• pp.437-451
• /
• 2019

Outlier detection techniques play an important role in enhancing the reliability of data communication in wireless sensor networks (WSNs). Considering the importance of outlier detection in WSNs, many outlier detection techniques have been proposed. Unfortunately, most of these techniques still have some potential limitations, that is, (a) high rate of false positives, (b) high time complexity, and (c) failure to detect outliers online. Moreover, these approaches mainly focus on either temporal outliers or spatial outliers. Therefore, this paper aims to introduce novel algorithms that successfully detect both temporal outliers and spatial outliers. Our contributions are twofold: (i) modifying the Hampel Identifier (HI) algorithm to achieve high accuracy identification rate in temporal outlier detection, (ii) combining the Gaussian process (GP) model and graph-based outlier detection technique to improve the performance of the algorithm in spatial outlier detection. The results demonstrate that our techniques outperform the state-of-the-art methods in terms of accuracy and work well with various data types.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.107-118
• /
• 2024

With the seamless growth of the technology, network usage requirements are expanding day by day. The majority of electronic devices are capable of communication, which strongly requires a secure and reliable network. Network-based intrusion detection systems (NIDS) is a new method for preventing and alerting computers and networks from attacks. Machine Learning is an emerging field that provides a variety of ways to implement effective network intrusion detection systems (NIDS). Bagging and Boosting are two ensemble ML techniques, renowned for better performance in the learning and classification process. In this paper, the study provides a detailed literature review of the past work done and proposed a novel ensemble approach to develop a NIDS system based on the voting method using bagging and boosting ensemble techniques. The test results demonstrate that the ensemble of bagging and boosting through voting exhibits the highest classification accuracy of 99.98% and a minimum false positive rate (FPR) on both datasets. Although the model building time is average which can be a tradeoff by processor speed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.

• 헤리티지:역사와 과학
• /
• 제45권4호
• /
• pp.92-103
• /
• 2012

본 연구는 고건축 기술사적 관점에서 첨성대 축조당시 가설공법을 규명하고자 하였다. 독특한 구조와 형태로 이루어진 첨성대는 그동안 많은 관심을 끌며 연구되어왔으나 고건축 기술사적 측면에서 접근한 사례를 보기 어렵다. 더욱이 첨성대 축조기술에 관한 연구는 고건축 기술사적 고찰기반이 취약한 추론으로 전개되어 있으므로 많은 의문점을 남기고 있다. 여러 가지 의문점 가운데 가설공법에 대한 논의는 고건축시공 규준방식과 드잡이에 관한 기술사적(技術史的) 고찰을 결여한 추론으로 전개되어 있으므로 신빙성 있는 역사적 사실규명으로 보기 어렵게 한다. 연구결과 첨성대축조 가설공법에 대한 규명은 실제유구가 남아있지 않아 직접 고찰에 한계가 있었으나, 그간의 오류 폭을 좁히고 기초자료 제공에 의한 기술사(技術史) 연구 활성화를 기대할 수 있게 되었다. 주요 연구결과는 세 가지로 정리되었다. 1. 원통형 구조로 이루어진 첨성대축조 규준방식은 또한 +자먹 규구법과 다림추를 이용한 준승방식에 기초한 중심축 규준을 적용하였음으로 고찰되었다. 2. 첨성대 축석공사는 규구준승에 기초한 규준방식과 부합하는 드잡이공사 방법으로 녹로사용 가능성이 고찰 검토되었다. 3. 첨성대축조 규준과 드잡이기술에 대한 고찰 결과 규구준승에 의한 규준방식과 녹로(??)를 이용한 드잡이공사는 축석공사에 별도로 운반을 위한 비계가설을 요하지 않는 고건축 시공기술로 고찰되었다.

• 한국수자원학회논문집
• /
• 제54권12호
• /
• pp.1255-1263
• /
• 2021

안개는 대체수자원이 될 수 있으나 교통사고 위험을 높이고 공항 운영에 제약을 가하는 사회적 영향이 큰 기상현상이다. 본 연구에서는 1 km 미만 가시거리(시정)로 정의되는 안개 발생을 기상자료로 예측하는 지역 기계학습모형을 개발하고 그 예측력을 평가하였다. 전라북도 지역의 10개 기상청 지상관측소의 2017-2019년 시정 및 기상관측자료로 앙상블 분류기법인 Extreme Gradient Boosting (XGB), Light Gradient Boosting(LGB), Random Forests (RF)를 학습시켜 지역 안개 모형을 개발하였고 독립적인 2020년 자료로 모형의 사용성을 평가하였다. 그 결과, 학습·검증기간(2017-2019)에는 True Skill Score를 기준으로 가장 높은 예측력을 보인 방법은 LGB 기법이었지만 다른 두 모형에 비해 False Alarm Ratio가 컸다. RF 모형과 XGB 방법 역시 기존 연구에 상응하는 예측성능을 보이는 것으로 확인되었다. 2020년 자료를 입력해 안개 발생을 모의했을 때 세 모형의 예측성능은 2017-2019년 기간보다 떨어졌지만 모두 관측 안개일수의 공간분포와 일관되는 안개 위험을 예측했다. 세 기계학습모형은 안개위험이 상대적으로 높은 지역을 추출하는 기법으로 사용이 가능할 것으로 보인다.