• 제목/요약/키워드: long-memory process

검색결과 161건 처리시간 0.029초

정확도 향상을 위한 CNN-LSTM 기반 풍력발전 예측 시스템 (CNN-LSTM based Wind Power Prediction System to Improve Accuracy)

  • 박래진;강성우;이재형;정승민
    • 신재생에너지
    • /
    • 제18권2호
    • /
    • pp.18-25
    • /
    • 2022
  • In this study, we propose a wind power generation prediction system that applies machine learning and data mining to predict wind power generation. This system increases the utilization rate of new and renewable energy sources. For time-series data, the data set was established by measuring wind speed, wind generation, and environmental factors influencing the wind speed. The data set was pre-processed so that it could be applied appropriately to the model. The prediction system applied the CNN (Convolutional Neural Network) to the data mining process and then used the LSTM (Long Short-Term Memory) to learn and make predictions. The preciseness of the proposed system is verified by comparing the prediction data with the actual data, according to the presence or absence of data mining in the model of the prediction system.

STUDY OF DYNAMICAL MODEL FOR PIEZOELECTRIC CYLINDER IN FRICTIONAL ANTIPLANE CONTACT PROBLEM

  • S. MEDJERAB;A. AISSAOUI;M. DALAH
    • Journal of applied mathematics & informatics
    • /
    • 제41권3호
    • /
    • pp.487-510
    • /
    • 2023
  • We propose a mathematical model which describes the frictional contact between a piezoelectric body and an electrically conductive foundation. The behavior of the material is described with a linearly electro-viscoelastic constitutive law with long term memory. The mechanical process is dynamic and the electrical conductivity coefficient depends on the total slip rate, the friction is modeled with Tresca's law which the friction bound depends on the total slip rate with taking into account the electrical conductivity of the foundation both. The main results of this paper concern the existence and uniqueness of the weak solution of the model; the proof is based on results for second order evolution variational inequalities with a time-dependent hemivariational inequality in Banach spaces.

생물전공 대학생과 비전공 대학생의 생명과학 학습에서 자기조절 과정의 두뇌 활성 분석 (Analysis of Brain Activation on the Self-Regulation Process in College Life Science Learning between Biology Major and Non-Major Students)

  • 이수민;박상희;권승혁;권용주
    • 과학교육연구지
    • /
    • 제46권3호
    • /
    • pp.255-265
    • /
    • 2022
  • 본 연구의 목적은 생명과학 학습에서 생물학 전공자와 비전공 대학생의 자기조절 과정에서 나타나는 뇌 활성을 분석하고 비교하는 것이다. 자기조절과제는 생물분류 개념으로 생명과학 학습상황을 구현하였다. 대학생들의 뇌 활성은 fNIRS에 의해 측정되고 분석되었다. 동화 과정에서 양측 FP와 좌 DLPFC는 유의미한 활성이 나타났으며, 두 그룹은 동기부여 및 보상과 관련된 좌측 OFC 활성에서 차이를 보였다. 갈등 과정에서 왼쪽 DLPFC는 공통적으로 활성이 현저히 낮았으며, 두 그룹은 최근 메모리와 관련된 BA46과 장기 메모리와 관련된 BA47의 활성에서 차이를 보였다. 동화 과정에서 우측 DLPFC에서 유의하게 높은 활성이 공통적으로 발견되었으며, 두 그룹은 우측 DLPFC와 우측 FP의 활성의 차이를 보였다. 이 영역들은 오른쪽 전두엽 영역에 있으며 생명과학 지식의 이해와 관련이 있다. 본 연구 결과 생물학 전공 대학생과 비전공 대학생의 뇌 활성 패턴은 자기조절 과정에서 차이가 있음을 알 수 있었다. 또한 자기조절에 대한 신경학적 연구를 추가로 제안하고 학교 환경에서 구성할 수 있는 시스템과 학습전략을 제시할 수 있을 것이다.

An Efficient Complex Event Processing Algorithm based on INFA-HTS for Out-of-order RFID Event Streams

  • Wang, Jianhua;Wang, Tao;Cheng, Lianglun;Lu, Shilei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제10권9호
    • /
    • pp.4307-4325
    • /
    • 2016
  • With the aim of solving the problems of long processing times, high memory consumption and low event throughput in the current processing approaches in out-of-order RFID event streams, an efficient complex event processing method based on INFA-HTS (Improved Nondeterministic Finite Automaton-Hash Table Structure) is presented in this paper. The contribution of this paper lies in the fact that we use INFA and HTS to successfully realize the detection of complex events for out-of-order RFID event streams. Specifically, in our scheme, to detect the disorder of out-of-order event streams, we expand the traditional NFA model into a new INFA model to capture the related RFID primitive events from the out-of-order event stream. To high-efficiently manage the large intermediate capturing results, we use the HTS to store and process them. As a result, these problems in the existing methods can be effectively solved by our scheme. The simulation results of our experiments show that our proposed method in this paper outperforms some of the current general processing approaches used to process out-of-order RFID event streams.

Variations of Interface Potential Barrier Height and Leakage Current of (Ba, Sr)$TiO_3$ Thin Films Deposited by Sputtering Process

  • Hwang, Cheol-Seong;Lee, Byoung-Taek
    • The Korean Journal of Ceramics
    • /
    • 제2권2호
    • /
    • pp.95-101
    • /
    • 1996
  • Variations of the leakage current behaviors and interface potential barrier $({\Phi}_B)$ of rf-sputter deposited (Ba, Sr)$TiO_3$ (BST) thin films with thicknesses ranging from 20 nm to 150nm are investigated as a function of the thickness and bias voltages. The top and bottom electrodes are dc-sputter-deposited Pt films. ${\Phi}_B$ critically depends on the BST film deposition temperature, postannealing atmosphere and time after the annealing. The postannealing under $N_2$ atmosphere results in a high interface potential barrier height and low leakage current. Maintaining the BST capacitor in air for a long time reduces the ${\Phi}_B$ from about 2.4 eV to 1.6 eV due to the oxidation. ${\Phi}_B$ is not so dependent on the film thickness in this experimental range. The leakage conduction mechanism is very dependent on the BST film thickness; the 20 nm thick film shows tunneling current, 30 and 40 nm thick films show Shottky emission current.

  • PDF

Application of Correlation-Aided DSA(CDSA) Technique to Fast Cell Search in IMT-2000 W-CDMA Systems.

  • Kim, Byoung-Hoon;Jeong, Byeong-Kook;Lee, Byeong-Gi
    • Journal of Communications and Networks
    • /
    • 제2권1호
    • /
    • pp.58-68
    • /
    • 2000
  • In this paper we introduce the correlation-aided distributed sample acquisition (CDSA) scheme for fast cell search in IMT-2000 W-CDMA cellular system. The proposed scheme incorporates the state symbol correlation process into the comparison-correction based synchronization process of the original DSA scheme to enable fast acquisition even under very poor channel environment. for its realization, each mobile station (MS) has to store in its memory a set of state sample sequences. which are determined by the long-period scrambling sequences used in the system and the sampling interval of the state samples. CDSA based cell search is carried out in two stages : First, the MS first acquires the slot timing by using the primary synch code (PSC) and then identifies the igniter code which conveys the state samples of the current cell . Secondly. the MS identifies the scrambling code and frame timing by taking the comparison-correction based synchronization approach and, if the identification is not done satisfactorily within preset time. it initiates the state symbol correlation process which correlates the received symbol sequence with the pre-stored state sample sequences for a successful identification. As the state symbol SNR is relatively high. the state symbol correlation process enables reliable synchronization even in very low chip-SNR environment. Simulation results show that the proposed CDSA scheme outperforms the 3GPP 3-step approach, requiring the signal power of about 7 dB less for achieving the same acquisition time performance in low-SNR environments. Furthermore, it turns out very robust in the typical synchronization environment where large frequency offset exists.

  • PDF

PLC 디지털 제어 신호를 통한 LSTM기반의 이산 생산 공정의 실시간 고장 상태 감지 (Real-Time Fault Detection in Discrete Manufacturing Systems Via LSTM Model based on PLC Digital Control Signals)

  • 송용욱;백수정
    • 산업경영시스템학회지
    • /
    • 제44권2호
    • /
    • pp.115-123
    • /
    • 2021
  • A lot of sensor and control signals is generated by an industrial controller and related internet-of-things in discrete manufacturing system. The acquired signals are such records indicating whether several process operations have been correctly conducted or not in the system, therefore they are usually composed of binary numbers. For example, once a certain sensor turns on, the corresponding value is changed from 0 to 1, and it means the process is finished the previous operation and ready to conduct next operation. If an actuator starts to move, the corresponding value is changed from 0 to 1 and it indicates the corresponding operation is been conducting. Because traditional fault detection approaches are generally conducted with analog sensor signals and the signals show stationary during normal operation states, it is not simple to identify whether the manufacturing process works properly via conventional fault detection methods. However, digital control signals collected from a programmable logic controller continuously vary during normal process operation in order to show inherent sequence information which indicates the conducting operation tasks. Therefore, in this research, it is proposed to a recurrent neural network-based fault detection approach for considering sequential patterns in normal states of the manufacturing process. Using the constructed long short-term memory based fault detection, it is possible to predict the next control signals and detect faulty states by compared the predicted and real control signals in real-time. We validated and verified the proposed fault detection methods using digital control signals which are collected from a laser marking process, and the method provide good detection performance only using binary values.

병렬 연산을 이용한 방출 단층 영상의 재구성 속도향상 기초연구 (Preliminary Study on the Enhancement of Reconstruction Speed for Emission Computed Tomography Using Parallel Processing)

  • 박민재;이재성;김수미;강지연;이동수;박광석
    • Nuclear Medicine and Molecular Imaging
    • /
    • 제43권5호
    • /
    • pp.443-450
    • /
    • 2009
  • 목적: 기존의 영상 재구성은 간소화된 투사 물리 모델을 사용하고 있다. 하지만 3D 재구성과 같은 실제적인 물리 모델은 시간이 많이 걸려서 임상에서 모든 데이터에 적용하기 힘들고, 복잡한 물리모델을 설명하기 위해 큰 메모리를 사용하면 한대의 일반적인 재구성 머신으로는 불가능하다. 개인 컴퓨터들에서도 큰 규모의 기술을 가능하게 하기위해, 병렬 연산을 이용한 빠른 재구성의 현실적인 분산메모리 모델을 제시한다. 대상 및 방법: 실제로 구현하는 가능성을 보기 위해 가상 컴퓨터들을 이용하여 선행 연구를 진행하였고, 다양한 가능성을 테스트하기 위해 상용서비스를 하고 있는 슈퍼컴퓨터(Tachyon)에서 성능 테스트를 하였다. 가장 많이 사용되는 2D 투사 영상과 실제적인 물리 모델인 3D 응답라인을 이용한 기댓값 최대화 알고리즘을 테스트하였다. 스터디 중 특정 반복횟수 이후에 속도가 최대 6배까지 느려지는 현상이 발견되어 컴파일러 최적화를 통해 병렬 효율의 극대화를 꾀하였다. 결과: Linux에서 MPICH와 NFS를 이용하여, 여러 컴퓨터에서 하나의 프로그램으로 분산 연산이 가능하였다. 병렬 연산을 했을 때 동일한 반복 연산에서 재구성된 영상간의 차이가 실수의 유효숫자(6bit) 정도임을 확인하였다. 2배의 연상장치를 사용했을 때 1.96배의 좋은 병렬화 효율을 보여주었다. 반복 연산 횟수가 증가함에 따라 느려지는 현상은 SSE를 이용한 Vectorization 방법을 사용했을 때 해결할 수 있었다. 결론: 이번 연구를 통해 일반 컴퓨터들을 이용한 현실적인 병렬 컴퓨터 시스템을 구성하여, 작은 메모리의 단일 일반 컴퓨터로는 불가능한 간단화 할 수 없는 복잡한 물리 과정도 영상 재구성 방법에 사용 가능하게 되었다.

동기식 256-bit OTP 메모리 설계 (Design of Synchronous 256-bit OTP Memory)

  • 이용진;김태훈;심외용;박무훈;하판봉;김영희
    • 한국정보통신학회논문지
    • /
    • 제12권7호
    • /
    • pp.1227-1234
    • /
    • 2008
  • 본 논문에서는 자동차 전장용 Power IC, 디스플레이 구동 칩, CMOS 이미지 센서 등의 응용분야에서 필요로 하는 동기식 256-bit OTP(one-time programmable) 메모리를 설계하였다. 동기식 256-bit OTP 메모리의 셀은 고전압 차단 트랜지스터 없이 안티퓨즈인 NMOS 커패시터와 액세스 트랜지스터로 구성되어 있다. 기존의 3종류의 전원 전압을 사용하는 대신 로직 전원 전압인 VDD(=1.5V)와 외부 프로그램 전압인 VPPE(=5.5V)를 사용하므로 부가적인 차단 트랜지스터의 게이트 바이어스 전압 회로를 제거하였다. 그리고 프로그램시 전류 제한 없이 전압 구동을 하는 경우 안티퓨즈의 ON 저항 값과 공정 변동에 따라 프로그램 할 셀의 부하 전류가 증가한다. 그러므로 프로그램 전압은 VPP 전원 선에서의 저항성 전압 감소로 인해 상대적으로 증가하는 문제가 있다. 그래서 본 논문에서는 전압 구동 대신 전류 구동방식을 사용하여 OTP 셀을 프로그램 할 때 일정한 부하전류가 흐르게 한다. 그래서 웨이퍼 측정 결과 VPPE 전압은 5.9V에서 5.5V로 0.4V 정도 낮출 수 있도록 하였다. 또한 기존의 전류 감지 증폭기 대신 Clocked 인버터를 사용한 감지 증폭기를 사용하여 회로를 단순화시켰다. 동기식 256-bit OTP IP는 매그나칩 반도체 $0.13{\mu}m$ 공정을 이용하여 설계하였으며, 레이아웃 면적은 $298.4{\times}3.14{\mu}m2$이다.

분위기 소결공정에 의한 Bi3.75La0.25Ti3O12세라믹의 강유전특성 (Ferroelectric Properly of Bi3.75La0.25Ti3O12 Ceramic Sintered in the Ambient)

  • 김응권;박춘배;박기엽;송준태
    • 한국전기전자재료학회논문지
    • /
    • 제15권9호
    • /
    • pp.783-787
    • /
    • 2002
  • In recent year, B $i_{4-}$x L $a_{x}$ $Ti_3$ $O_{12(BLT)}$ is one of promising substitute materials for the ferroelectric random access memory(FRAM) applications. But the systematic composition is still insufficient, so this experiment was carried out in ceramic ambient sintering process which has the very excellent ferroelectric property. Samples were prepared by a bulk and the purpose which was estimated with a suitability of thin films applications. The density of B $i_{3.75}$ L $a_{0.25}$ $Ti_3$ $O_{12}$ was high and the XRD pattern showed that the intensity of main peak (117) was increased at the argon ambient sintering. Controlling the quantity of oxygen, crystallization showed a thin, long plate like type, and we obtained the excellent dielectric and polarization properties at the argon atmosphere sintering. Also this sintering process was effective at the bulk sample. Argon ambient sintered sample produced higher permittivity of 154, the remanent polarization(2Pr) of 6.8 uC/$\textrm{cm}^2$ compared with that sintered in air and oxygen ambient. And this sintering process showed a possibility which could be applied to thin films process..