• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.237-245
• /
• 2022

The prominence of IoTs (Internet of Things) and exponential advancement of computer networks has resulted in massive essential applications. Recognizing various cyber-attacks or anomalies in networks and establishing effective intrusion recognition systems are becoming increasingly vital to current security. MLTs (Machine Learning Techniques) can be developed for such data-driven intelligent recognition systems. Researchers have employed a TFDNNs (Tensor Flow Deep Neural Networks) and DCNNs (Deep Convolution Neural Networks) to recognize pirated software and malwares efficiently. However, tuning the amount of neurons in multiple layers with activation functions leads to learning error rates, degrading classifier's reliability. HTFDNNs ( Hybrid tensor flow DNNs) and MRNs (Modified Residual Networks) or Resnet CNNs were presented to recognize software piracy and malwares. This study proposes HTFDNNs to identify stolen software starting with plagiarized source codes. This work uses Tokens and weights for filtering noises while focusing on token's for identifying source code thefts. DLTs (Deep learning techniques) are then used to detect plagiarized sources. Data from Google Code Jam is used for finding software piracy. MRNs visualize colour images for identifying harms in networks using IoTs. Malware samples of Maling dataset is used for tests in this work.

• 데이타베이스연구회지:데이타베이스연구
• /
• 제34권3호
• /
• pp.137-147
• /
• 2018

기계 학습을 통한 인간 동작 인지 (human activity recognition) 시스템에서 중요한 요소는 충분한 양의 라벨 데이터 (labeled data)를 확보하는 것이다. 그러나 라벨 데이터를 확보하는 일은 많은 비용과 시간을 필요로 한다. 매우 적은 수의 라벨 데이터를 가지고 있는 새로운 환경 (타겟 도메인)에서 동작 인지 시스템을 구축하는 경우, 기존의 환경 (소스 도메인)의 데이터나 이 환경에서 학습된 분류기(classifier)를 사용하는 것은 도메인이 서로 다르기 때문에 바람직하지 않다. 기존의 기계 학습 방법들이 이러한 문제를 해결할 수 없으므로 전이 학습 (transfer learning) 방법이 제시되었으며, 이 방법에서는 소스 도메인에서 확보한 지식을 활용하여 타겟 도메인에서의 분류기 성능을 높이도록 하고 있다. 본 논문에서는 다중 태스크 신경망 (multitask neural network)을 사용하여 매우 제한된 수의 데이터만으로 정확도가 높은 동작 인지 분류기를 생성하는 전이 학습방법을 제안한다. 이 방법에서는 소스 및 타겟 도메인 분류기의 손실 함수 최소화가 별개의 태스크로 간주된다. 즉, 하나의 신경망을 사용하여 두 태스크의 손실 함수를 동시에 최소화하는 방식으로 지식 전이(knowledge transfer)가 일어나게 된다. 또한, 제안한 방법에서는 모델 학습을 위하여 비지도 방식(unsupervised manner)으로 라벨이 부여되지 않은 데이터를 활용한다. 실험 결과, 제안한 방법은 기존의 방법에 비하여 일관적으로 우수한 성능을 보여주고 있다.

• 동아시아식생활학회지
• /
• 제14권1호
• /
• pp.54-63
• /
• 2004

This study was accomplished to investigate the recognition and the using practices about food-nutrition labeling system of 20's consumers. Two hundred and fifty-four man and women were examined using the questionnaire. The results were as follows. 1. The degree of recognition of subjects about food-nutrition labeling system was low (43.3％) and the using practices were even lower (18.1％). 2. The items considered as important were in the order of shelf life, manufactured date and cost. 3. The confidence score to the food-nutrition labeling system of consumers was 3.2 and was higher in the females compared to males. 4. The preferred method of food-nutrition labeling was in the order of picture and graphic type method, table type method and descriptive type method. 5. The expected effects of the current food-nutrition labeling system were easy to select foods for the prevention of the adult diseases and diet therapy. From these results, we might propose the conclusion as follows: Food-nutrition labeling system might be a good source of nutrition information and the consumers'demand for disease-prevention and dietary purpose. Therefore, the agencies concerned should make an every effort for the successful implementation of food-nutrition labeling system.

• 디지털산업정보학회논문지
• /
• 제11권3호
• /
• pp.1-9
• /
• 2015

In this paper, we implemented the computer vision platform design with MEAN Stack through Raspberry PI 2 model which is an open source platform. we experimented the face recognition, temperature and humidity sensor data logging with WiFi communication under Raspberry Pi 2 model. Especially we directly made the shape of platform with 3D printing design. In this paper, we used the face recognition algorithm with OpenCV software through haarcascade feature extraction machine learning algorithm, and extended the functionality of wireless communication function ability with Bluetooth technology for the purpose of making Android Mobile devices interface. And therefore we implemented the functions of the vision platform for identifying the face recognition characteristics of scanning with PI camera with gathering the temperature and humidity sensor data under IoT environment. and made the vision platform with 3D printing technology. Especially we used MongoDB for developing the performance of vision platform because the MongoDB is more akin to working with objects in a programming language than what we know of as a database. Afterwards, we would enhance the performance of vision platform for clouding functionalities.

• 정보처리학회논문지B
• /
• 제17B권2호
• /
• pp.107-114
• /
• 2010

사용자가 직접 연주하여 제작한 콘텐츠에서 많이 사용되는 악기는 기타, 피아노, 그리고 바이올린 이다. 이중 기타와 피아노가 만들어 내는 오디오 신호의 특성이 비슷하여 구분하기가 어렵다. 하지만 시간에 따른 신호의 에너지 변화가 피크(Peak)들을 중심으로 서로 다른 패턴을 보이는 것으로 분석되었다. 누적 히스토그램을 이용하여 피크 존재 가능성의 확률적 분포를 구한 후, 피크를 중심으로 그 주변의 주파수 대역 별에너지 변화 패턴을 통계적 방법으로 모델링하여 실험한 결과 피아노와 기타의 구분 성공률이 최고 14% 정도의 향상을 보였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권2호
• /
• pp.63-68
• /
• 2018

얼굴인식 분야의 관심은 다양한 신흥분야의 응용에 의해 증강되고 있다. 2-차원적인 인식 알고리즘의 필요성이 어떤 변화무쌍한 환경들, 예를 들어서, 얼굴의 방향이나 조명도, 안경의 유무, 혹은 웃음과 울음 같은 다양한 표정변화의 처리에 적합할 수 있게 고찰 되어 지고 있다. 형상 기억이나 일반화 과정, 유사성 인식, 오류수정 등에 장점을 가지고 있는 홉 필드 네트워크의 기능을 바탕으로 하여 본 연구에서는 새로운 방법의 병렬적인 다중 홉 필드 네트워크를 구성하여 변화에 강한 얼굴표정 인식의 실험을 2-차원 알고리즘으로 실시하였고 결과가 실제적인 얼굴 형상 환경 변화에서 강한 적응성을 가지고 있음을 확인하였다.

• 한국전기전자재료학회논문지
• /
• 제19권10호
• /
• pp.942-946
• /
• 2006

We simulated insulation defects of stator winding wire on high voltage generator by 5 types. 4 types have one discharge source and other one has multi discharge source by simulation. For accurate decision, measurements used to PRPD pattern to occurred partial discharge source of various types. In this research, when PRPD pattern carried out or analyzed pattern recognition of discharge source, it used to powerful tools. In this result, PRPD Pattern defined to have single discharge source of 4 types by insulation defect. When insulation defect simulated, all the defected winding have not the same result. Errors for a little different can make mistakes from a subtle distinction. The difference between internal and void discharge have magnitude of pulse amplitude of inner discharge bigger than void discharge and have a shape of bisymmetry. But void discharge has a shape of bisymmetry against maximum value on polarity respectively. In cases of slot and surface discharge, we confirmed to show similar results those other researchers. In case of multi-discharge, as a result of we could classify not perfect match with occurred patterns in single discharge eachother. In the future, we will have to recognize and classify with results of multi-discharge.

• 제어로봇시스템학회논문지
• /
• 제18권2호
• /
• pp.126-132
• /
• 2012

The technique for estimation of sound source direction is one of the important methods necessary for various engineering fields such as monitoring system, military services and so on. As a new approach for estimation of sound source direction, this paper propose the bio-mimetic localization sensor based on mechanically coupling structure motivated by hearing structure of fly, Ormia Ochracea. This creature is known for its outstanding recognition ability to the sound which has large wavelength compared to its own size. ITTF (Inter-Tympanal Transfer Function) which is the transfer function between displacements of the tympanal membranes on each side has the all inter-tympanal information dependent on sound direction. The peak and notch features of desired ITTF can be generated by using the appropriate mechanical properties. A example of estimation of sound source direction using generated ITTF with monotonically changing notch and peak patterns is shown.

• 동아시아식생활학회지
• /
• 제7권4호
• /
• pp.475-483
• /
• 1997

The main purpose of this research is to provide Information regarding the preference and intake of calcium of middle school students in the Daegu area. The results were summarized as follows: The recognition score of calcium of the subjects was male 12.85 and female 12.45, respectively. Also the preference scores of calcium source foods of the subjects were male 3.60 and female 3.49. They preferred ice cream, laver, yoghurt and steamed fish cakes in that order, but they disliked cheese and loach soup. The daily calcium intake was 483.78mg(53.8% of RDA) for males and 545.91mg (68.2% of RDA) for females.

• 한국전기전자재료학회논문지
• /
• 제17권9호
• /
• pp.1006-1012
• /
• 2004

In this paper, neural networks is studied to apply as a PD source classification in XLPE power cable specimen. Two learning schemes are used to classification; BP(Back propagation algorithm), SOM(self organized map - kohonen network). As a PD source, using treeing discharge sources in the specimen, three defected models are made. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And a]so these distribution characteristics are applied to classify PD sources by two scheme of the neural networks. In conclusion, recognition efficiency of BP is superior to SOM.