• 한국인터넷방송통신학회논문지
• /
• 제22권6호
• /
• pp.165-171
• /
• 2022

사람의 심박수는 운동 강도 측정의 기준으로 사용되는 중요한 지표이다. 만약 심박수를 예측한다면 운동 중 운동 강도를 미리 조절하여 효율적으로 운동할 수 있다. 본 논문에서는 FitRec 기반 달리기 운동을 수행하는 사용자의 심박수를 예측하는 모델을 제안한다. 학습을 위해 Endomondo의 데이터를 사용하여 예측 모델에 적용한다. 성능 비교를 위해 시계열 데이터 처리 알고리즘 LSTM(long short term memory)과 GRU(gated recurrent unit)를 사용하였다. FitRec에 유산소 운동 중 달리기 데이터만 학습한 결과 여러 유산소 운동 데이터를 모두 학습한 모델보다 MAE(mean absolute error)와 RMSE(root mean squared error) 둘 다 성능이 향상됨을 확인하였다.

• 스마트미디어저널
• /
• 제9권2호
• /
• pp.92-98
• /
• 2020

본 논문은 고성능의 서버 없이 안드로이드 스마트폰 단독으로 동작할 수 있도록 경량화 딥러닝 모델을 사용하여 구현한 자동차 번호판 인식 시스템을 제안한다. 자동차 번호판 인식시스템은 [번호판검출]-[문자영역 분할]-[문자인식]으로 3단계의 과정으로 구성되며, 번호판검출은 SSD-Mobilenet, 문자영역 분할은 ResNet에 localization을 추가하여 사용하였고 문자인식은 ResNet을 이용하여 구현하였다. 테스트한 기기는 삼성 갤럭시 S7, LG Q9이며 정확도는 약 85.3%, 실행속도는 약 1.1초가 소요된다.

• 정보보호학회논문지
• /
• 제29권6호
• /
• pp.1393-1401
• /
• 2019

최근 시스템에 음성 인증 기능이 탑재됨에 따라 화자(Speaker)를 정확하게 인증하는 중요성이 높아지고 있다. 이에 따라 다양한 방법으로 화자를 인증하는 모델이 제시되어 왔다. 본 논문에서는 Short-time Fourier transform(STFT)를 적용한 새로운 화자 인증 모델을 제안한다. 이 모델은 기존의 Mel-Frequency Cepstrum Coefficients(MFCC) 추출 방법과 달리 윈도우 함수를 약 66.1% 오버랩하여 화자 인증 시 정확도를 높일 수 있다. 새로운 화자 인증 모델을 제안한다. 이 때, LSTM 셀을 적용한 Recurrent Neural Network(RNN)라는 딥러닝 모델을 사용하여 시변적 특징을 가지는 화자의 음성 특징을 학습하고, 정확도가 92.8%로 기존의 화자 인증 모델보다 5.5% 정확도가 높게 측정되었다.

• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.213-218
• /
• 2021

This paper proposes a technique for detecting a significant threat that attempts to get sensitive and confidential information such as usernames, passwords, credit card information, and more to target an individual or organization. By definition, a phishing attack happens when malicious people pose as trusted entities to fraudulently obtain user data. Phishing is classified as a type of social engineering attack. For a phishing attack to happen, a victim must be convinced to open an email or a direct message [1]. The email or direct message will contain a link that the victim will be required to click on. The aim of the attack is usually to install malicious software or to freeze a system. In other instances, the attackers will threaten to reveal sensitive information obtained from the victim. Phishing attacks can have devastating effects on the victim. Sensitive and confidential information can find its way into the hands of malicious people. Another devastating effect of phishing attacks is identity theft [1]. Attackers may impersonate the victim to make unauthorized purchases. Victims also complain of loss of funds when attackers access their credit card information. The proposed method has two major subsystems: (1) Data collection: different websites have been collected as a big data corresponding to normal and phishing dataset, and (2) distributed detection system: different artificial algorithms are used: a neural network algorithm and machine learning. The Amazon cloud was used for running the cluster with different cores of machines. The experiment results of the proposed system achieved very good accuracy and detection rate as well.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• Genomics & Informatics
• /
• 제17권2호
• /
• pp.15.1-15.7
• /
• 2019

Automatically detecting mentions of pharmaceutical drugs and chemical substances is key for the subsequent extraction of relations of chemicals with other biomedical entities such as genes, proteins, diseases, adverse reactions or symptoms. The identification of drug mentions is also a prior step for complex event types such as drug dosage recognition, duration of medical treatments or drug repurposing. Formally, this task is known as named entity recognition (NER), meaning automatically identifying mentions of predefined entities of interest in running text. In the domain of medical texts, for chemical entity recognition (CER), techniques based on hand-crafted rules and graph-based models can provide adequate performance. In the recent years, the field of natural language processing has mainly pivoted to deep learning and state-of-the-art results for most tasks involving natural language are usually obtained with artificial neural networks. Competitive resources for drug name recognition in English medical texts are already available and heavily used, while for other languages such as Spanish these tools, although clearly needed were missing. In this work, we adapt an existing neural NER system, NeuroNER, to the particular domain of Spanish clinical case texts, and extend the neural network to be able to take into account additional features apart from the plain text. NeuroNER can be considered a competitive baseline system for Spanish drug and CER promoted by the Spanish national plan for the advancement of language technologies (Plan TL).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

• 한국해양공학회지
• /
• 제36권1호
• /
• pp.50-60
• /
• 2022

The deep ocean engineering basin (DOEB) of the Korea Research Institute of Ship and Ocean Engineering (KRISO) is equipped with an extreme-environment reproduction facility that can analyze the motion characteristics of offshore structures and ships. In recent years, there have been requirements for a wide range of six-degree-of-freedom (6-DOF) motion measurements for performing maneuvering tests and free-running tests of target objects (offshore structures or ships). This study introduces the process of developing a wide-area motion measurement technology by incorporating the auto-tracking technology of the towing carriage system to overcome the existing 6-DOF motion measurement limitation. To realize a wide range of motion measurements, the automatic tracking control system of the towing carriage in the DOEB was designed as a speed control method. To verify the control performance, the characteristics of the towing carriage according to the variation in control gain were analyzed. Finally, a wide range of motions was tested using a model test object (a remotely operated vehicle (ROV)), and the wide-area motion measurement technology was implemented using an automatic tracking control system for a towing carriage.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.929-938
• /
• 2023

모바일 장치에서 사용되는 ARM 프로세서는 하드웨어 기반의 격리 실행 환경인 TrustZone 개념을 도입하여 신뢰 실행 환경인 Secure World와 비신뢰 실행 환경인 Normal World를 구현하였다. 악성 소프트웨어의 종류 중 루트킷은 관리자 권한을 획득하고 자신의 존재를 숨기면서 백도어를 만든다. Secure World에서 동작하는 프로세스는 메모리 접근에 제한이 없고, 격리되어 있어 Secure World에서 루트킷이 실행되었을 때 탐지하기 어렵다. 본 논문에서는 하드웨어 기반의 성능 측정 모니터인 Performance Monitoring Unit을 활용하여 Secure World 루트킷의 이벤트를 측정하고 딥러닝 기반으로 루트킷을 탐지하는 기법을 제시한다.

• 콘크리트학회논문집
• /
• 제15권5호
• /
• pp.689-696
• /
• 2003

최근 ACI 318-02기준 부록 A에 깊은 보의 전단설계에 있어 스트럿-타이 모델을 적용 가능하도록 소개하고 있다. STM은 깊은 보, 개구부가 있는 깊은 보, 코벨, 턱이진 보와 같이 부재의 변형률 분포가 상당히 비선형인 콘크리트 부재의 설계에 광범위하게 사용되고 있다. 본 연구는 고강도콘크리트를 적용한 깊은 보의 각국의 전단강도규준과 전단거동을 평가하고자 실험적 연구로 2점 단순 집중하중을 받는 고강도 RC 깊은 보 5개를 제작하여 파괴 실험을 실시하였다. 또한, 국내 B사의 기계적 정착철물을 사용하여 주인장철근의 양단부에 기계적정착을 적용하였다. 파괴 시 모든 시험체는 가력점과 지지점을 연결하는 주 경사균열이 나타났고, 주인장철근을 기계적 정착한 시험체가 90도 표준갈고리 시험체보다 파괴 시 하중 수행능력이 우수한 것으로 나타났다. 실험결과를 기초로 ACI 318-99 기준, ACI 318-02 부록 A STM, CSA 23.3-94 기준 및 CIRIA Guide-2의 전단설계기준을 비교 평가하였다. ACI 318-99 기준과 ACI 318-02 기준의 스트럿-타이 모델, CIRIA Guide-2는 단순스팬 깊은 보의 극한전단강도 예측 있어 10∼36%정도 낮게 안정적으로 평가하는 것으로 나타났다. ACI 318-99 기준에 의한 전단강도예측값이 표준편차가 가장 낮은 것으로 조사되었다.