• 제목/요약/키워드: short- and long-term memory

검색결과 589건 처리시간 0.026초

Prediction Oil and Gas Throughput Using Deep Learning

  • Sangseop Lim
    • 한국컴퓨터정보학회논문지
    • /
    • 제28권5호
    • /
    • pp.155-161
    • /
    • 2023
  • 우리나라 수출의 97.5%, 수입의 87.2%가 해상운송으로 이뤄지며 항만이 한국 경제의 중요한 구성요소이다. 이러한 항만의 효율적인 운영을 위해서는 항만 물동량의 단기 예측을 통해 개선시킬 수가 있으며 과학적인 연구방법이 필요하다. 이전 연구는 주로 장기예측을 기반으로 대규모 인프라투자를 위한 연구에 중점을 두었으며 컨테이너 항만물동량에만 집중한 측면이 크다. 본 연구는 국내 대표적인 석유항만인 울산항의 석유 및 가스화물 물동량에 대한 단기 예측을 수행하였으며 딥러닝 모델인 LSTM(Long Short Term Memory) 모델을 사용하여 RMSE기준으로 예측성능을 확인하였다. 본 연구의 결과는 석유 및 가스화물 물동량 수요 예측의 정확도를 높여 항만 운영의 효율성을 개선하는 근거가 될 수 있을 것으로 기대된다. 또한 기존 연구의 한계로 컨테이너 항만 물동량뿐만 아니라 석유 및 가스화물 물동량 예측에도 LSTM의 활용할 수 있다는 가능성을 확인할 수 있으며 향후 추가 연구를 통해 일반화가 가능할 것으로 기대된다.

Deep learning-based LSTM model for prediction of long-term piezoresistive sensing performance of cement-based sensors incorporating multi-walled carbon nanotube

  • Jang, Daeik;Bang, Jinho;Yoon, H.N.;Seo, Joonho;Jung, Jongwon;Jang, Jeong Gook;Yang, Beomjoo
    • Computers and Concrete
    • /
    • 제30권5호
    • /
    • pp.301-310
    • /
    • 2022
  • Cement-based sensors have been widely used as structural health monitoring systems, however, their long-term sensing performance have not actively investigated. In this study, a deep learning-based methodology is adopted to predict the long-term piezoresistive properties of cement-based sensors. Samples with different multi-walled carbon nanotube contents (0.1, 0.3, and 0.5 wt.%) are fabricated, and piezoresistive tests are conducted over 10,000 loading cycles to obtain the training data. Time-dependent degradation is predicted using a modified long short-term memory (LSTM) model. The effects of different model variables including the amount of training data, number of epochs, and dropout ratio on the accuracy of predictions are analyzed. Finally, the effectiveness of the proposed approach is evaluated by comparing the predictions for long-term piezoresistive sensing performance with untrained experimental data. A sensitivity of 6% is experimentally examined in the sample containing 0.1 wt.% of MWCNTs, and predictions with accuracy up to 98% are found using the proposed LSTM model. Based on the experimental results, the proposed model is expected to be applied in the structural health monitoring systems to predict their long-term piezoresistice sensing performances during their service life.

LSTM-based Sales Forecasting Model

  • Hong, Jun-Ki
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권4호
    • /
    • pp.1232-1245
    • /
    • 2021
  • In this study, prediction of product sales as they relate to changes in temperature is proposed. This model uses long short-term memory (LSTM), which has shown excellent performance for time series predictions. For verification of the proposed sales prediction model, the sales of short pants, flip-flop sandals, and winter outerwear are predicted based on changes in temperature and time series sales data for clothing products collected from 2015 to 2019 (a total of 1,865 days). The sales predictions using the proposed model show increases in the sale of shorts and flip-flops as the temperature rises (a pattern similar to actual sales), while the sale of winter outerwear increases as the temperature decreases.

네트워크 침입탐지를 위한 세션관리 기반의 LSTM 모델 (LSTM Model based on Session Management for Network Intrusion Detection)

  • 이민욱
    • 한국인터넷방송통신학회논문지
    • /
    • 제20권3호
    • /
    • pp.1-7
    • /
    • 2020
  • 증가하는 사이버공격에 대응하기 위하여 머신러닝을 적용한 자동화된 침입탐지기술이 연구되고 있다. 최근 연구결과에 따르면, 순환형 학습모델을 적용한 침입탐지기술이 높은 탐지성능을 보여주는 것으로 확인되었다. 하지만 단순한 순환형 모델을 적용하는 것은 통신이 중첩된 환경일수록 연관된 통신의 특성을 반영하기 어려워 탐지성능이 저하될 수 있다. 본 논문에서는 이 같은 문제점을 해결하고자 세션관리모듈을 설계하여 LSTM(Long Short-Term Memory) 순환형 모델에 적용하였다. 실험을 위하여 CSE-CIC-IDS 2018 데이터 셋을 사용하였으며, 정상통신비율을 증가시켜 악성통신의 연관성을 낮추었다. 실험결과 통신연관성을 파악하기 힘든 환경에서도 제안하는 모델은 높은 탐지성능을 유지할 수 있음을 확인하였다.

TV뉴스의 카메라워크와 수용자의 관여도가 뉴스 기억에 미치는 영향 (Effect of TV news camerawork and viewers' involvement on memory of news)

  • 박덕춘
    • 디지털융복합연구
    • /
    • 제11권7호
    • /
    • pp.297-304
    • /
    • 2013
  • 본 연구는 텔레비전 뉴스의 카메라워크와 수용자의 관여도가 뉴스에 대한 장단기 기억에 어떠한 영향을 미치는지 실험을 통해 살펴보았다. 본 연구를 위해 카메라워크의 유무에 따라 2가지 종류의 TV뉴스를 제작하여 관여도를 조작한 2개의 대학생 집단에게 시청하게 하고, 이들의 장단기 기억을 측정, 분석하였다. 분석결과 TV뉴스 영상의 카메라워크는 수용자의 단기기억에는 영향을 미치지 못하지만, 장기기억에는 영향을 미치는 것으로 나타났다. 또한 관여도가 높은 수용자들은 뉴스 내용에 대한 장단기 기억이 높은 것으로 나타났다. 그러나 카메라워크는 주변단서로서 고관여도 수용자보다 저관여도 수용자의 기억에 더 큰 영향을 미칠 것으로 예측한 가설은 지지되지 못하였다.

기억의 신경심리학 (Neuropsychology of Memory)

  • 이민규
    • 수면정신생리
    • /
    • 제4권1호
    • /
    • pp.1-14
    • /
    • 1997
  • This paper reviewed models to explain memory and neuropsychological tests to assess memory. Memory was explained in cognitive and neuroanatomical perspectives, Cognitive model describes memory as structure and process. In structure model, memory is divided into three systems: sensory memory, short-term memory(working memory), and long-term memory. In process model, there are broadly three categories of memory process: encoding, storage, and retrieval. Memory process work in memory structure. There are two prominent models of the neuroanatomy of memory, derived from the work of Mishkin and Appenzeller and that of Squire and Zola-Morgan. These two models are the most useful for the clinician in part because they take into account the connections between the limbic and frontal cortical regions. The major difference between the two models concerns the role of the amygdala in memory processess. Mishkin and his colleagues believe that the amygdala plays a significant role while Squire and his colleagues do not. The most popular and widely used tests of memory ability such as WMS-R, AVLT, CVLT, HVLT. RBMT, CFT, and BVRT-R, were reviewed.

  • PDF

메모리 요소를 활용한 신경망 연구 동향 (A Survey on Neural Networks Using Memory Component)

  • 이지환;박진욱;김재형;김재인;노홍찬;박상현
    • 정보처리학회논문지:소프트웨어 및 데이터공학
    • /
    • 제7권8호
    • /
    • pp.307-324
    • /
    • 2018
  • 최근 순환 신경 망(Recurrent Neural Networks)은 시간에 대한 의존성을 고려한 구조를 통해 순차 데이터(Sequential data)의 예측 문제 해결에서 각광받고 있다. 하지만 순차 데이터의 시간 스텝이 늘어남에 따라 발생하는 그라디언트 소실(Gradients vanishing)이 문제로 대두되었다. 이를 해결하기 위해 장단기 기억 모델(Long Short-Term Memory)이 제안되었지만, 많은 데이터를 저장하고 장기간 보존하는 데에 한계가 있다. 따라서 순환 신경망과 메모리 요소(Memory component)를 활용한 학습 모델인 메모리-증대 신경망(Memory-Augmented Neural Networks)에 대한 연구가 최근 활발히 진행되고 있다. 본 논문에서는 딥 러닝(Deep Learning) 분야의 화두로 떠오른 메모리-증대 신경망 주요 모델들의 구조와 특징을 열거하고, 이를 활용한 최신 기법들과 향후 연구 방향을 제시한다.

Integrate-and-Fire Neuron Circuit and Synaptic Device using Floating Body MOSFET with Spike Timing-Dependent Plasticity

  • Kwon, Min-Woo;Kim, Hyungjin;Park, Jungjin;Park, Byung-Gook
    • JSTS:Journal of Semiconductor Technology and Science
    • /
    • 제15권6호
    • /
    • pp.658-663
    • /
    • 2015
  • In the previous work, we have proposed an integrate-and-fire neuron circuit and synaptic device based on the floating body MOSFET [1-3]. Integrate-and-Fire(I&F) neuron circuit emulates the biological neuron characteristics such as integration, threshold triggering, output generation, refractory period using floating body MOSFET. The synaptic device has short-term and long-term memory in a single silicon device. In this paper, we connect the neuron circuit and the synaptic device using current mirror circuit for summation of post synaptic pulses. We emulate spike-timing-dependent-plasticity (STDP) characteristics of the synapse using feedback voltage without controller or clock. Using memory device in the logic circuit, we can emulate biological synapse and neuron with a small number of devices.

A robust collision prediction and detection method based on neural network for autonomous delivery robots

  • Seonghun Seo;Hoon Jung
    • ETRI Journal
    • /
    • 제45권2호
    • /
    • pp.329-337
    • /
    • 2023
  • For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

Supervised learning-based DDoS attacks detection: Tuning hyperparameters

  • Kim, Meejoung
    • ETRI Journal
    • /
    • 제41권5호
    • /
    • pp.560-573
    • /
    • 2019
  • Two supervised learning algorithms, a basic neural network and a long short-term memory recurrent neural network, are applied to traffic including DDoS attacks. The joint effects of preprocessing methods and hyperparameters for machine learning on performance are investigated. Values representing attack characteristics are extracted from datasets and preprocessed by two methods. Binary classification and two optimizers are used. Some hyperparameters are obtained exhaustively for fast and accurate detection, while others are fixed with constants to account for performance and data characteristics. An experiment is performed via TensorFlow on three traffic datasets. Three scenarios are considered to investigate the effects of learning former traffic on sequential traffic analysis and the effects of learning one dataset on application to another dataset, and determine whether the algorithms can be used for recent attack traffic. Experimental results show that the used preprocessing methods, neural network architectures and hyperparameters, and the optimizers are appropriate for DDoS attack detection. The obtained results provide a criterion for the detection accuracy of attacks.