• 제목/요약/키워드: Long Short-Term Memory (LSTM) Network

검색결과 274건 처리시간 0.024초

Time Series Crime Prediction Using a Federated Machine Learning Model

  • Salam, Mustafa Abdul;Taha, Sanaa;Ramadan, Mohamed
    • International Journal of Computer Science & Network Security
    • /
    • 제22권4호
    • /
    • pp.119-130
    • /
    • 2022
  • Crime is a common social problem that affects the quality of life. As the number of crimes increases, it is necessary to build a model to predict the number of crimes that may occur in a given period, identify the characteristics of a person who may commit a particular crime, and identify places where a particular crime may occur. Data privacy is the main challenge that organizations face when building this type of predictive models. Federated learning (FL) is a promising approach that overcomes data security and privacy challenges, as it enables organizations to build a machine learning model based on distributed datasets without sharing raw data or violating data privacy. In this paper, a federated long short- term memory (LSTM) model is proposed and compared with a traditional LSTM model. Proposed model is developed using TensorFlow Federated (TFF) and the Keras API to predict the number of crimes. The proposed model is applied on the Boston crime dataset. The proposed model's parameters are fine tuned to obtain minimum loss and maximum accuracy. The proposed federated LSTM model is compared with the traditional LSTM model and found that the federated LSTM model achieved lower loss, better accuracy, and higher training time than the traditional LSTM model.

Two-stream Convolutional Long- and Short-term Memory 모델의 2001-2021년 9월 북극 해빙 예측 성능 평가 (Performance Assessment of Two-stream Convolutional Long- and Short-term Memory Model for September Arctic Sea Ice Prediction from 2001 to 2021)

  • 지준화
    • 대한원격탐사학회지
    • /
    • 제38권6_1호
    • /
    • pp.1047-1056
    • /
    • 2022
  • 지구 온난화의 중요한 지시자인 북극의 바다 얼음인 해빙은 기후 시스템, 선박의 항로 안내, 어업 활동 등에서의 중요성으로 인해 다양한 학문 분야에서 관심을 받고 있다. 최근 자동화와 효율적인 미래 예측에 대한 요구가 커지면서 인공지능을 이용한 새로운 해빙 예측 모델들이 전통적인 수치 및 통계 예측 모델을 대체하기 위해 개발되고 있다. 본 연구에서는 북극 해빙의 전역적, 지역적 특징을 학습할 수 있는 two-stream convolutional long- and short-term memory (TS-ConvLSTM) 인공지능 모델의 북극 해빙 면적이 최저를 보이는 9월에 대해 2001년부터 2021년까지 장기적인 성능 검증을 통해 향후 운용 가능한 시스템으로써의 가능성을 살펴보고자 한다. 장기 자료를 통한 검증 결과 TS-ConvLSTM 모델이 훈련자료의 양이 증가하면서 향상된 예측 성능을 보여주고 있지만, 최근 지구 온난화로 인한 단년생 해빙의 감소로 인해 해빙 농도 5-50% 구간에서는 예측력이 저하되고 있음을 보여주었다. 반면 TS-ConvLSTM에 의해 예측된 해빙 면적과 달리 Sea Ice Prediction Network에 제출된 Sea Ice Outlook (SIO)들의 해빙 면적 중간값의 경우 훈련자료가 늘어나더라도 눈에 띄는 향상을 보이지 않았다. 본 연구를 통해 TS-ConvLSTM 모델의 향후 북극 해빙 예측 시스템의 운용 가능 잠재성을 확인하였으나, 향후 연구에서는 예측이 어려운 자연 환경에서 더욱 안정성 있는 예측 시스템 개발을 위해 더 많은 시공간 변화 패턴을 학습할 수 있는 방안을 고려해야 할 것이다.

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.

어텐션 메커니즘 기반 Long-Short Term Memory Network를 이용한 EEG 신호 기반의 감정 분류 기법 (Emotion Classification based on EEG signals with LSTM deep learning method)

  • 김유민;최아영
    • 한국산업정보학회논문지
    • /
    • 제26권1호
    • /
    • pp.1-10
    • /
    • 2021
  • 본 연구에서는 EEG 신호를 기반으로 감정 인식에 유용한 딥러닝 기법을 제안한다. 감정이 시간에 따라 변화하는 특성을 반영하기 위해 Long-Short Term Memory 네트워크를 사용하였다. 또한, 특정 시점의 감정적 상태가 전체 감정 상태에 영향을 미친다는 이론을 기반으로 특정 순간의 감정 상태에 가중치를 주기 위해 어텐션 메커니즘을 적용했다. EEG 신호는 DEAP 데이터베이스를 사용하였으며, 감정은 긍정과 부정의 정도를 나타내는 정서가(Valence)와 감정의 정도를 나타내는 각성(Arousal) 모델을 사용하였다. 실험 결과 정서가(Valence)와 각성(Arousal)을 2단계(낮음, 높음)로 나누었을 때 분석 정확도는 정서가(Valence)의 경우 90.1%, 각성(Arousal)의 경우 88.1%이다. 낮음, 중간, 높음의 3단계로 감정을 구분한 경우 정서가(Valence)는 83.5%, 각성(Arousal)은 82.5%의 정확도를 보였다.

딥러닝 기반의 다범주 감성분석 모델 개발 (Development of Deep Learning Models for Multi-class Sentiment Analysis)

  • 알렉스 샤이코니;서상현;권영식
    • 한국IT서비스학회지
    • /
    • 제16권4호
    • /
    • pp.149-160
    • /
    • 2017
  • Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

Dynamic deflection monitoring method for long-span cable-stayed bridge based on bi-directional long short-term memory neural network

  • Yi-Fan Li;Wen-Yu He;Wei-Xin Ren;Gang Liu;Hai-Peng Sun
    • Smart Structures and Systems
    • /
    • 제32권5호
    • /
    • pp.297-308
    • /
    • 2023
  • Dynamic deflection is important for evaluating the performance of a long-span cable-stayed bridge, and its continuous measurement is still cumbersome. This study proposes a dynamic deflection monitoring method for cable-stayed bridge based on Bi-directional Long Short-term Memory (BiLSTM) neural network taking advantages of the characteristics of spatial variation of cable acceleration response (CAR) and main girder deflection response (MGDR). Firstly, the relationship between the spatial and temporal variation of the CAR and the MGDR is described based on the geometric deformation of the bridge. Then a data-driven relational model based on BiLSTM neural network is established using CAR and MGDR data, and it is further used to monitor the MGDR via measuring the CAR. Finally, numerical simulations and field test are conducted to verify the proposed method. The root mean squared error (RMSE) of the numerical simulations are less than 4 while the RMSE of the field test is 1.5782, which indicate that it provides a cost-effective and convenient method for real-time deflection monitoring of cable-stayed bridges.

A Novel RGB Channel Assimilation for Hyperspectral Image Classification using 3D-Convolutional Neural Network with Bi-Long Short-Term Memory

  • M. Preethi;C. Velayutham;S. Arumugaperumal
    • International Journal of Computer Science & Network Security
    • /
    • 제23권3호
    • /
    • pp.177-186
    • /
    • 2023
  • Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

Traffic-based reinforcement learning with neural network algorithm in fog computing environment

  • Jung, Tae-Won;Lee, Jong-Yong;Jung, Kye-Dong
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제12권1호
    • /
    • pp.144-150
    • /
    • 2020
  • Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

LSTM과 GRU 딥러닝 IoT 파워미터 기반의 단기 전력사용량 예측 (Short-term Power Consumption Forecasting Based on IoT Power Meter with LSTM and GRU Deep Learning)

  • 이선민;선영규;이지영;이동구;조은일;박대현;김용범;심이삭;김진영
    • 한국인터넷방송통신학회논문지
    • /
    • 제19권5호
    • /
    • pp.79-85
    • /
    • 2019
  • 본 연구에서는 Long Short Term Memory (LSTM) 신경망과 Gated Recurrent Unit(GRU) 신경망을 Internet of Things (IoT) 파워미터에 적용하여 단기 전력사용량 예측방법을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 성능평가 지표로써 Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Percentage Error (MPE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE)를 이용한다. 실험 결과는 GRU 기반의 모델이 LSTM 기반의 모델에 비해 MAPE 기준으로 4.52%, MPE 기준으로 5.59%만큼의 성능개선을 보였다.

순서 정보 기반 악성코드 분류 가능성 (Malware Classification Possibility based on Sequence Information)

  • 윤태욱;박찬수;황태규;김성권
    • 정보과학회 논문지
    • /
    • 제44권11호
    • /
    • pp.1125-1129
    • /
    • 2017
  • LSTM(Long Short-term Memory)은 이전 상태의 정보를 기억하여 현재 상태에 반영해 학습하는 순환신경망(Recurrent Neural Network) 모델이다. 악성코드에서 선형적 순서 정보는 각 시점에서 호출되는 함수로서 정의 가능하다. 본 논문에서는 LSTM 모델의 이전 상태를 기억하는 특성을 이용하며, 시간 순서에 따른 악성코드의 함수 호출 정보를 입력으로 사용한다. 그리고 실험으로서 우리가 제시한 방법이 악성코드 분류가 가능함을 보이고 순서 정보의 길이 변화에 따른 정확률을 측정한다.