• Title, Summary, Keyword: 기계학습

Search Result 1,929, Processing Time 0.288 seconds

Study on High-speed Cyber Penetration Attack Analysis Technology based on Static Feature Base Applicable to Endpoints (Endpoint에 적용 가능한 정적 feature 기반 고속의 사이버 침투공격 분석기술 연구)

  • Hwang, Jun-ho;Hwang, Seon-bin;Kim, Su-jeong;Lee, Tae-jin
    • Journal of Internet Computing and Services
    • /
    • v.19 no.5
    • /
    • pp.21-31
    • /
    • 2018
  • Cyber penetration attacks can not only damage cyber space but can attack entire infrastructure such as electricity, gas, water, and nuclear power, which can cause enormous damage to the lives of the people. Also, cyber space has already been defined as the fifth battlefield, and strategic responses are very important. Most of recent cyber attacks are caused by malicious code, and since the number is more than 1.6 million per day, automated analysis technology to cope with a large amount of malicious code is very important. However, it is difficult to deal with malicious code encryption, obfuscation and packing, and the dynamic analysis technique is not limited to the performance requirements of dynamic analysis but also to the virtual There is a limit in coping with environment avoiding technology. In this paper, we propose a machine learning based malicious code analysis technique which improve the weakness of the detection performance of existing analysis technology while maintaining the light and high-speed analysis performance applicable to commercial endpoints. The results of this study show that 99.13% accuracy, 99.26% precision and 99.09% recall analysis performance of 71,000 normal file and malicious code in commercial environment and analysis time in PC environment can be analyzed more than 5 per second, and it can be operated independently in the endpoint environment and it is considered that it works in complementary form in operation in conjunction with existing antivirus technology and static and dynamic analysis technology. It is also expected to be used as a core element of EDR technology and malware variant analysis.

A Method of Detecting the Aggressive Driving of Elderly Driver (노인 운전자의 공격적인 운전 상태 검출 기법)

  • Koh, Dong-Woo;Kang, Hang-Bong
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.6 no.11
    • /
    • pp.537-542
    • /
    • 2017
  • Aggressive driving is a major cause of car accidents. Previous studies have mainly analyzed young driver's aggressive driving tendency, yet they were only done through pure clustering or classification technique of machine learning. However, since elderly people have different driving habits due to their fragile physical conditions, it is necessary to develop a new method such as enhancing the characteristics of driving data to properly analyze aggressive driving of elderly drivers. In this study, acceleration data collected from a smartphone of a driving vehicle is analyzed by a newly proposed ECA(Enhanced Clustering method for Acceleration data) technique, coupled with a conventional clustering technique (K-means Clustering, Expectation-maximization algorithm). ECA selects high-intensity data among the data of the cluster group detected through K-means and EM in all of the subjects' data and models the characteristic data through the scaled value. Using this method, the aggressive driving data of all youth and elderly experiment participants were collected, unlike the pure clustering method. We further found that the K-means clustering has higher detection efficiency than EM method. Also, the results of K-means clustering demonstrate that a young driver has a driving strength 1.29 times higher than that of an elderly driver. In conclusion, the proposed method of our research is able to detect aggressive driving maneuvers from data of the elderly having low operating intensity. The proposed method is able to construct a customized safe driving system for the elderly driver. In the future, it will be possible to detect abnormal driving conditions and to use the collected data for early warning to drivers.

An Automated Topic Specific Web Crawler Calculating Degree of Relevance (연관도를 계산하는 자동화된 주제 기반 웹 수집기)

  • Seo Hae-Sung;Choi Young-Soo;Choi Kyung-Hee;Jung Gi-Hyun;Noh Sang-Uk
    • Journal of Internet Computing and Services
    • /
    • v.7 no.3
    • /
    • pp.155-167
    • /
    • 2006
  • It is desirable if users surfing on the Internet could find Web pages related to their interests as closely as possible. Toward this ends, this paper presents a topic specific Web crawler computing the degree of relevance. collecting a cluster of pages given a specific topic, and refining the preliminary set of related web pages using term frequency/document frequency, entropy, and compiled rules. In the experiments, we tested our topic specific crawler in terms of the accuracy of its classification, crawling efficiency, and crawling consistency. First, the classification accuracy using the set of rules compiled by CN2 was the best, among those of C4.5 and back propagation learning algorithms. Second, we measured the classification efficiency to determine the best threshold value affecting the degree of relevance. In the third experiment, the consistency of our topic specific crawler was measured in terms of the number of the resulting URLs overlapped with different starting URLs. The experimental results imply that our topic specific crawler was fairly consistent, regardless of the starting URLs randomly chosen.

  • PDF

A Study on Abalone Young Shells Counting System using Machine Vision (머신비전을 이용한 전복 치패 계수에 관한 연구)

  • Park, Kyung-min;Ahn, Byeong-Won;Park, Young-San;Bae, Cherl-O
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.23 no.4
    • /
    • pp.415-420
    • /
    • 2017
  • In this paper, an algorithm for object counting via a conveyor system using machine vision is suggested. Object counting systems using image processing have been applied in a variety of industries for such purposes as measuring floating populations and traffic volume, etc. The methods of object counting mainly used involve template matching and machine learning for detecting and tracking. However, operational time for these methods should be short for detecting objects on quickly moving conveyor belts. To provide this characteristic, this algorithm for image processing is a region-based method. In this experiment, we counted young abalone shells that are similar in shape, size and color. We applied a characteristic conveyor system that operated in one direction. It obtained information on objects in the region of interest by comparing a second frame that continuously changed according to the information obtained with reference to objects in the first region. Objects were counted if the information between the first and second images matched. This count was exact when young shells were evenly spaced without overlap and missed objects were calculated using size information when objects moved without extra space. The proposed algorithm can be applied for various object counting controls on conveyor systems.

The Effect of regularization and identity mapping on the performance of activation functions (정규화 및 항등사상이 활성함수 성능에 미치는 영향)

  • Ryu, Seo-Hyeon;Yoon, Jae-Bok
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.10
    • /
    • pp.75-80
    • /
    • 2017
  • In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.

Smart Exercise Prescription of Elderly Users using Visual Path Map (비쥬얼패스맵을 이용한 고령자 대상의 스마트 운동처방)

  • Jeong, Chan-Soon;Ham, Jun-Seok;Ko, Il-Ju;Hur, Jun-Soo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.10
    • /
    • pp.185-196
    • /
    • 2011
  • Exercise programs for elderly users are operated by each department and facility, but it is not enough to visualize exercise prescription and effect followed by elderly users physical conditions. The purpose of this study is to suggest exercise prescription for elderly users with a visual path map. A visual path map is to visually present types of users classified according to physical strength conditions, the process of exercise prescription, and effects of exercise. Exercise prescription is divided into four stages: analysis of physical conditions, exercise prescription by the visual path map, smart exercise prescription, and exercise for elderly users. The first stage, analysis of physical conditions is to classify physical conditions by each type by mechanically learning elderly users' physical test values. The second stage, exercise prescription by the visual path map, is to present exercise prescription suitable for elderly users' physical conditions. The third stage, smart exercise prescription, is to offer exercise prescription of the day when exercise is carried out using elderly users' smart phones in consideration of their situations. The fourth stage, exercise for elderly users, is to provide information by their smart phones when they exercise. In conclusion, this study will be able to induce elderly users to do continuous exercise by motivating them.

Designing mobile personal assistant agent based on users' experience and their position information (위치정보 및 사용자 경험을 반영하는 모바일 PA에이전트의 설계)

  • Kang, Shin-Bong;Noh, Sang-Uk
    • Journal of Internet Computing and Services
    • /
    • v.12 no.1
    • /
    • pp.99-110
    • /
    • 2011
  • Mobile environments rapidly changing and digital convergence widely employed, mobile devices including smart phones have been playing a critical role that changes users' lifestyle in the areas of entertainments, businesses and information services. The various services using mobile devices are developing to meet the personal needs of users in the mobile environments. Especially, an LBS (Location-Based Service) is combined with other services and contents such as augmented reality, mobile SNS (Social Network Service), games, and searching, which can provide convenient and useful services to mobile users. In this paper, we design and implement the prototype of mobile personal assistant (PA) agents. Our personal assistant agent helps users do some tasks by hiding the complexity of difficult tasks, performing tasks on behalf of the users, and reflecting the preferences of users. To identify user's preferences and provide personalized services, clustering and classification algorithms of data mining are applied. The clusters of the log data using clustering algorithms are made by measuring the dissimilarity between two objects based on usage patterns. The classification algorithms produce user profiles within each cluster, which make it possible for PA agents to provide users with personalized services and contents. In the experiment, we measured the classification accuracy of user model clustered using clustering algorithms. It turned out that the classification accuracy using our method was increased by 17.42%, compared with that using other clustering algorithms.

Class prediction of an independent sample using a set of gene modules consisting of gene-pairs which were condition(Tumor, Normal) specific (조건(암, 정상)에 따라 특이적 관계를 나타내는 유전자 쌍으로 구성된 유전자 모듈을 이용한 독립샘플의 클래스예측)

  • Jeong, Hyeon-Iee;Yoon, Young-Mi
    • Journal of the Korea Society of Computer and Information
    • /
    • v.15 no.12
    • /
    • pp.197-207
    • /
    • 2010
  • Using a variety of data-mining methods on high-throughput cDNA microarray data, the level of gene expression in two different tissues can be compared, and DEG(Differentially Expressed Gene) genes in between normal cell and tumor cell can be detected. Diagnosis can be made with these genes, and also treatment strategy can be determined according to the cancer stages. Existing cancer classification methods using machine learning select the marker genes which are differential expressed in normal and tumor samples, and build a classifier using those marker genes. However, in addition to the differences in gene expression levels, the difference in gene-gene correlations between two conditions could be a good marker in disease diagnosis. In this study, we identify gene pairs with a big correlation difference in two sets of samples, build gene classification modules using these gene pairs. This cancer classification method using gene modules achieves higher accuracy than current methods. The implementing clinical kit can be considered since the number of genes in classification module is small. For future study, Authors plan to identify novel cancer-related genes with functionality analysis on the genes in a classification module through GO(Gene Ontology) enrichment validation, and to extend the classification module into gene regulatory networks.

Motor Imagery Brain Signal Analysis for EEG-based Mouse Control (뇌전도 기반 마우스 제어를 위한 동작 상상 뇌 신호 분석)

  • Lee, Kyeong-Yeon;Lee, Tae-Hoon;Lee, Sang-Yoon
    • Korean Journal of Cognitive Science
    • /
    • v.21 no.2
    • /
    • pp.309-338
    • /
    • 2010
  • In this paper, we studied the brain-computer interface (BCI). BCIs help severely disabled people to control external devices by analyzing their brain signals evoked from motor imageries. The findings in the field of neurophysiology revealed that the power of $\beta$(14-26 Hz) and $\mu$(8-12 Hz) rhythms decreases or increases in synchrony of the underlying neuronal populations in the sensorymotor cortex when people imagine the movement of their body parts. These are called Event-Related Desynchronization / Synchronization (ERD/ERS), respectively. We implemented a BCI-based mouse interface system which enabled subjects to control a computer mouse cursor into four different directions (e.g., up, down, left, and right) by analyzing brain signal patterns online. Tongue, foot, left-hand, and right-hand motor imageries were utilized to stimulate a human brain. We used a non-invasive EEG which records brain's spontaneous electrical activity over a short period of time by placing electrodes on the scalp. Because of the nature of the EEG signals, i.e., low amplitude and vulnerability to artifacts and noise, it is hard to analyze and classify brain signals measured by EEG directly. In order to overcome these obstacles, we applied statistical machine-learning techniques. We could achieve high performance in the classification of four motor imageries by employing Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) which transformed input EEG signals into a new coordinate system making the variances among different motor imagery signals maximized for easy classification. From the inspection of the topographies of the results, we could also confirm ERD/ERS appeared at different brain areas for different motor imageries showing the correspondence with the anatomical and neurophysiological knowledge.

  • PDF

A Study on Spatial Downscaling of Satellite-based Soil Moisture Data (토양수분 위성자료의 공간상세화에 관한 연구)

  • Shin, Dae Yun;Lee, Yang Won;Park, Mun Sung
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • /
    • pp.414-414
    • /
    • 2017
  • 토양수분은 지면환경에서 일어나는 수문 및 에너지 순환을 이해하는 데 있어 중요한 기상인자이다. 토양수분 현장관측은 땅속에 매설된 센서에 의해 상당히 정확하게 이루어지만, 관측점 수가 충분치 않아 공간적 연속성을 확보하지 못하는 어려움이 존재한다. 이에 광역적 및 연속적 관측이 가능한 마이크로파 위성센서가 토양수분 정보 획득을 위한 보조수단으로서 그 중요성이 부각되고 있다. 마이크로파 위성센서는 구름 등 기상조건의 제약을 받지 않으며, 1978년 이래 현재까지 여러 위성에 의해 25 km 및 10 km 해상도의 전지구 토양수분자료가 생산되어 왔다. 마이크로파 센서를 이용한 토양수분자료는 동일지점에 대하여 하루 2회 정도 산출되므로 적절한 시간분해능을 가지지만, 공간해상도가 최고 10 km로서 지역규모의 수문분석에 적용하기에는 충분치 않다. 이러한 토양수분자료의 공간해상도 문제 해결을 위하여 다양한 지면환경요소를 활용한 통계적 다운스케일링이 대안으로 제시되었다. 최근의 선행연구들은 대부분 방정식을 이용한 결합모형을 통해 통계적 다운스케일링을 수행하였는데, 회귀식과 같은 선형결합뿐 아니라 신경망이나 기계학습 등의 비선형결합에서도, 불가피하게 발생할 수밖에 없는 잔차(residual)로 인하여 다운스케일링 전후의 공간분포 패턴이 달라져버리는 문제를 안고 있었다. 회귀분석에 잔차의 공간내삽을 결합시킨 회귀크리깅(regression kriging)은 잔차보정을 통해 이러한 문제를 해결함으로써 다운스케일링 전후의 공간분포 일관성을 보장하는 기법이다. 이 연구에서는 회귀크리깅을 이용하여 일자별 AMSR2(Advanced Microwave Scanning Radiometer 2) 토양수분 자료를 10 km에서 1 km 해상도로 다운스케일링하고, 다운스케일링 전후의 자료패턴 일관성을 평가한다. 지면온도(LST), 지면온도상승률(RR), 식생온도건조지수(TVDI)는 일자별로 DB를 구축하였고, 식생지수(NDVI), 수분지수(NDWI), 지면알베도(SA)는 8일 간격으로 DB를 구축하였다. 이러한 8일 간격의 자료를 일자별로 변환하기 위하여 큐빅스플라인(cubic spline)을 이용하여 시계열내삽을 수행하였다. 또한 상이한 공간해상도의 자료는 최근린법을 이용하여 다운스케일링 목표해상도인 1 km에 맞도록 변환하였다. 우선 저해상도 스케일에서 추정치를 산출하기 위해서는 저해상도 픽셀별로 이에 해당하는 복수의 고해상도 픽셀을 평균화하여 대응시켜야 하며, 이를 통해 6개의 설명변수(LST, RR, TVDI, NDVI, NDWI, SA)와 AMSR2 토양수분을 반응변수로 하는 다중회귀식을 도출하였다. 이식을 고해상도 스케일의 설명변수들에 적용하면 고해상도 토양수분 추정치가 산출되는데, 이때 추정치와 원자료의 차이에 해당하는 잔차에 대한 보정이 필요하다. 저해상도 스케일로 존재하는 잔차를 크리깅 공간내삽을 통해 고해상도로 변환한 후 이를 고해상도 추정치에 부가해주는 방식으로 잔차보정이 이루어짐으로써, 다운스케일링 전후의 자료패턴 일관성이 유지되는(r>0.95) 공간상세화된 토양수분 자료를 생산할 수 있다.

  • PDF