Deep LSTM Model Research Articles

워드 임베딩 방법에 따른 가짜뉴스 판별 모델에 관한 연구

Status of information technology and mediaization Fake news is emerging as a permanent problem in our society. By developing a model to detect fake news, we aim to deliver reliable information about the impact of the current coverage of fake news. Among natural language processing methods, we would like to introduce various embedding methods to share fake news and share the performance of the model through a deep learning model based on the word embedding method. The push embedding method is a method of extracting meaningful features from news text data and identifying meaning and consistency between words. This method is used to identify information that does not match the actual content of the news article and place importance on fake news. After generating the embedding matrix of each word embedding method, TF-IDF, Word2Vec, and FastTextt, and combining the embedding layer with the deep learning-based LSTM model, which is a model with fake news, the power (accuracy) of the model is compared to see which is superior. An embedding method was presented. Comparing the cooperation of the models across participants in this study, we show that the Word2Vec method outperforms TF-IDF and FastText.

Prediction of Solar Radiation using Deep LSTM-based Machine Learning Algorithm

Solar radiation, a critical parameter for various applications such as solar energy systems and weather forecasting, exhibits complex temporal patterns influenced by numerous environmental factors. In the quest to enhance the accuracy of solar radiation predictions, this study introduces a novel approach utilizing Deep Long Short-Term Memory (Deep LSTM) networks, a type of recurrent neural network (RNN) known for its capability to model sequential data. Traditional prediction methods often struggle to capture these intricacies, leading to sub-optimal performance. This investigation is based on a Deep LSTM-based machine learning algorithm designed to predict solar radiation with elevated exactitude. The model is meticulously trained on copious datasets encompassing historical meteorological data, including temperature, humidity, wind velocity, and antecedent solar radiation metrics. Pivotal stages encompass data preprocessing, judicious feature selection, and hyperparameter optimization to enhance the model’s predictive efficacy. Empirical results clearly illustrate that the Deep LSTM model surpasses traditional methodologies, attaining superior accuracy and resilience across diverse meteorological scenarios. The ramifications of this endeavor portend significant advancements in the strategic planning and administration of solar energy resources, thereby contributing to more dependable and efficacious renewable energy systems.

Bitcoin returns and YouTube news: a behavioural time series analysis

ABSTRACT This study investigates whether investor’s sentiment and attention information collected via YouTube can improve bitcoin return forecasts. Accordingly, we collected daily data over the period 2017–2023, covering calm and turbulent periods marked by different types and episodes of emotions. Unlike previous studies, we used YouTube videos to propose two sentiment proxies: investor attention to YouTube (daily number of YouTube video views) and investor sentiment on YouTube (number of positive and negative videos on YouTube). Interestingly, we break down both attention and sentiment per subject. Econometrically, we assess lead-lag effects between sentiment/attention and bitcoin return using causality tests and Vector Auto-regressive (VAR) model. We also evaluate the forecasting power of YouTube attention/sentiment data using a deep learning LSTM model. Our study shows two main results. First, we find lead-lag effects between bitcoin returns and per subject investor’s attention and sentiment proxies. Second, we show that our deep learning LSTM model relying on the information provided by attention and sentiment supplants benchmark Buy and Hold Strategy to forecast future bitcoin returns.

Covid-19 Analysis Using Deep Learning LSTM Model

Covid-19 Analysis Using Deep Learning LSTM Model

Testing Of Deep Learning-Based LSTM Model For Number Of Road Accidents Predicting

Many have used the prediction of the number of road accidents, but it is still rare to find those who use and test prediction models that are not suitable. Predictive models that have been used to predict road accidents have proven successful, but have not provided model testing with data that is different from the deep learning approach. The LSTM model test is proposed to be tested with 5 different datasets from Kaggle and 3 hidden layer variations. The test results of the LSTM model are that with variations of 4 hidden layers it can achieve higher accuracy results than those without hidden layers and 2 hidden layers. The results are obtained from stability with the lowest average MSLE value and relatively balanced average time. Deep learning-based LSTM model testing was carried out to ensure and prove the stability of the model for predicting the number of road accidents in the future. Stakeholders can predict the number of road accidents using the resulting prediction model.

Deep learning approaches to identify order status in a complex supply chain

Deep learning approaches to identify order status in a complex supply chain

An Optimized Deep LSTM Model for Human Action Recognition

An Optimized Deep LSTM Model for Human Action Recognition

Artificial intelligence-based forecasting model for incinerator in sulfur recovery units to predict SO2 emissions

Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term networks (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset.

Optimizing Deep LSTM Model through Hyperparameter Tuning for Sensor-Based Human Activity Recognition in Smart Home

Optimizing Deep LSTM Model through Hyperparameter Tuning for Sensor-Based Human Activity Recognition in Smart Home

A Deep Bidirectional LSTM Model Enhanced by Transfer-Learning-Based Feature Extraction for Dynamic Human Activity Recognition

Dynamic human activity recognition (HAR) is a domain of study that is currently receiving considerable attention within the fields of computer vision and pattern recognition. The growing need for artificial-intelligence (AI)-driven systems to evaluate human behaviour and bolster security underscores the timeliness of this research. Despite the strides made by numerous researchers in developing dynamic HAR frameworks utilizing diverse pre-trained architectures for feature extraction and classification, persisting challenges include suboptimal performance accuracy and the computational intricacies inherent in existing systems. These challenges arise due to the vast video-based datasets and the inherent similarity in the data. To address these challenges, we propose an innovative, dynamic HAR technique employing a deep-learning-based, deep bidirectional long short-term memory (Deep BiLSTM) model facilitated by a pre-trained transfer-learning-based feature-extraction approach. Our approach begins with the utilization of Convolutional Neural Network (CNN) models, specifically MobileNetV2, for extracting deep-level features from video frames. Subsequently, these features are fed into an optimized deep bidirectional long short-term memory (Deep BiLSTM) network to discern dependencies and process data, enabling optimal predictions. During the testing phase, an iterative fine-tuning procedure is introduced to update the high parameters of the trained model, ensuring adaptability to varying scenarios. The proposed model’s efficacy was rigorously evaluated using three benchmark datasets, namely UCF11, UCF Sport, and JHMDB, achieving notable accuracies of 99.20%, 93.3%, and 76.30%, respectively. This high-performance accuracy substantiates the superiority of our proposed model, signaling a promising advancement in the domain of activity recognition.

Deep LSTM model exploiting optical sensors for soil nutrient prediction

Deep LSTM model exploiting optical sensors for soil nutrient prediction

Ultra-short-term PV power prediction based on Informer with multi-head probability sparse self-attentiveness mechanism

As a clean energy source, solar power plays an important role in reducing the high carbon emissions of China’s electricity system. However, the intermittent nature of the system limits the effective use of photovoltaic power generation. This paper addresses the problem of low accuracy of ultra-short-term prediction of distributed PV power, compares various deep learning models, and innovatively selects the Informer model with multi-head probability sparse self-attention mechanism for prediction. The results show that the CEEMDAN-Informer model proposed in this paper has better prediction accuracy, and the error index is improved by 30.88% on average compared with the single Informer model; the Informer model is superior to other deep learning models LSTM and RNN models in medium series prediction, and its prediction accuracy is significantly better than the two. The power prediction model proposed in this study improves the accuracy of PV ultra-short-term power prediction and proves the feasibility and superiority of the deep learning model in PV power prediction. Meanwhile, the results of this study can provide some reference for the power prediction of other renewable energy sources, such as wind power.

Predicting Future Incidences of Cardiac Arrhythmias Using Discrete Heartbeats from Normal Sinus Rhythm ECG Signals via Deep Learning Methods.

This study aims to compare the effectiveness of using discrete heartbeats versus an entire 12-lead electrocardiogram (ECG) as the input for predicting future occurrences of arrhythmia and atrial fibrillation using deep learning models. Experiments were conducted using two types of inputs: a combination of discrete heartbeats extracted from 12-lead ECG and an entire 12-lead ECG signal of 10 s. This study utilized 326,904 ECG signals from 134,447 patients and categorized them into three groups: true-normal sinus rhythm (T-NSR), atrial fibrillation-normal sinus rhythm (AF-NSR), and clinically important arrhythmia-normal sinus rhythm (CIA-NSR). The T-NSR group comprised patients with at least three normal rhythms in a year and no atrial fibrillation or arrhythmias history. Clinically important arrhythmia included atrial fibrillation, atrial flutter, atrial premature contraction, atrial tachycardia, ventricular premature contraction, ventricular tachycardia, right and left bundle branch block, and atrioventricular block over the second degree. The AF-NSR group included normal sinus rhythm paired with atrial fibrillation or atrial flutter within 14 days, and the CIA-NSR group comprised normal sinus rhythm paired with CIA occurring within 14 days. Three deep learning models, ResNet-18, LSTM, and Transformer-based models, were utilized to distinguish T-NSR from AF-NSR and T-NSR from CIA-NSR. The experiments demonstrated the potential of using discrete heartbeats in predicting future arrhythmia and atrial fibrillation incidences extracted from 12-lead electrocardiogram (ECG) signals alone, without any additional patient information. The analysis reveals that these discrete heartbeats contain subtle patterns that deep learning models can identify. Focusing on discrete heartbeats may lead to more timely and accurate diagnoses of these conditions, improving patient outcomes and enabling automated diagnosis using ECG signals as a biomarker.

Dual-dimension Time-GGAN data augmentation method for improving the performance of deep learning models for PV power forecasting

Solar energy has intermittency and volatility, which poses a serious challenge to the stable and safe operation of the power grid. Accurate photovoltaic power prediction is one of the key technologies to solve this problem. Due to the larger volume of data collected by photovoltaic systems, deep learning methods are more in-depth in the field of photovoltaic power prediction. However, photovoltaic power generation data also has more diversity and lower value density, which brings more severe challenges to the feature extraction ability of prediction models. Photovoltaic power prediction methods with deep data mining capabilities are urgently needed to address these issues. This paper proposes a dual-dimensional time series adversarial neural network based on gated recurrent neural network (Dd_Time_GGAN) to enhance low-value-density photovoltaic data by two dimensions (time dimension and feature dimension) and obtain high-value-density feature data. by replacing the generator and optimizer to improve the performance of network-enhanced data, the training time of the network was reduced by 26% by adjusting the iteration times of each stage of the network. Then, combining the two mainstream deep neural networks LSTM and CNN models in the current photovoltaic forecast field to achieve ultra-short-term photovoltaic power prediction. The experimental data is two-year operation data of a photovoltaic station in China. The experimental results show that compared with only using raw sample data, using enhanced data proposed by the data augmentation method combined with raw sample data as input, both types of deep learning prediction models have higher prediction accuracy. The accuracy of the LSTM prediction model improved by 3.1%, and the CNN prediction model improved by 2.3%. It proves that through data enhancement, the prediction accuracy of the photovoltaic power prediction model can be improved.

WiFi-based indoor passive fall detection for medical Internet of Things

There are currently numerous automated fall detection devices available, but most require the deployment of additional specialized equipment, which can create inconvenience for elderly individuals in their daily lives. This paper proposes a solution that reuses existing smartphone and WiFi infrastructure, eliminating the need for extra equipment and greatly simplifying the implementation of fall event detection. Due to the lower quality of data collected by smartphones, we have developed an adaptive DBSCAN clustering algorithm to process and extract useful data. We then train a deep convolutional LSTM model to classify the collected data in real-time. When a fall is detected, the smartphone can transmit an alert via the internet to notify relatives or medical staff of the incident. Our experimental results demonstrate that utilizing smartphones for fall detection is both feasible and accurate.

AACO: Aquila Anti-Coronavirus Optimization-Based Deep LSTM Network for Road Accident and Severity Detection

Globally, traffic accidents are of main concern because of more death rates and economic losses every year. Thus, road accident severity is the most important issue of concern, mainly in the undeveloped countries. Generally, traffic accidents result in severe human fatalities and large economic losses in real-world circumstances. Moreover, appropriate, precise prediction of traffic accidents has a high probability with regard to safeguarding public security as well as decreasing economic losses. Hence, the conventional accident prediction techniques are usually devised with statistical evaluations, which identify and evaluate the fundamental relationships among human variability, environmental aspects, traffic accidents and road geometry. However, the conventional approaches have major restrictions based on the assumptions regarding function kind and data distribution. In this paper, Aquila Anti-Coronavirus Optimization-based Deep Long Short-Term Memory (AACO-based Deep LSTM) is developed for road accident severity detection. Spearman’s rank correlation coefficient and Deep Recurrent Neural Network (DRNN) are utilized for the feature fusion process. Data augmentation method is carried out to improve the detection performance. Deep LSTM detects the road accident and its severity, where Deep LSTM is trained by the designed AACO algorithm for better performance. The developed AACO-based Deep LSTM model outperformed other existing methods with the Mean Square Error (MSE), Root-Mean-Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) of 0.0145, 0.1204 and 0.075%, respectively.

Forecasting Particulate Matter Emissions Using Time Series Models

Environmental pollution is a serious concern nowadays with its disastrous impact on living organisms. In several types of pollution, Air pollution takes on a crucial role by directly affecting the respiratory system and causing fatal diseases in humans. Air pollution is a mixture of gaseous and particulate matter interweaved by different sources and emanating into the atmosphere. In particular, particle pollutants are critical in growing air pollution in India’s main cities. Forecasting the particulate matter could mitigate the complications caused by it. The employment of a model to predict future values based on previously observed values is known as time series forecasting. In this paper, the PM2.5 pollutant emission data recorded at the Kodungaiyur region of Chennai city were forecasted using three-time series models. The standard ARIMA model is compared with the deep learning-based LSTM model and Facebook’s developed Prophet algorithm. This comparison helps to identify an appropriate forecasting model for PM2.5 pollutant emission. The Root Mean Squared Error (RMSE) acquired from experimental findings is used to compare model performances.

Enhanced security using video summarization for surveillance system using deep LSTM model with K-means clustering technique

For the security of the Society, Video surveillance systems have become an important tool that can help in preventing crime in public or private establishments, leading to more safe and secure environment. With the rise of technology that can handle high volune video data and the need for continuous monitoring for security to citizens, the analysis of the video footages, during security breach attempts has become more challenging. Video summarization can play a crucial role in secure surveillance systems by optimizing the analysis time of the security breach. This research attempts to summarise the important aspects of the original video without losing its context and also optimizes the storage requirement. To achieve the same a unique KM-LSTM based technique has been developed that utilizes deep learning methods to understand links among highlight as well as non-highlight video segments through the use of pairwise distance calculations. A new Deep LSTM model has been used to extract the features from all segments of frames. These extracted features are clustered using k-means clustering. Then, such features are trained using a pairwise deep learning model to get highlight scores as well as leverage the comparative similarity among pairs of the highlight as well as non-highlight segments. At last, video summarization takes place to generate the video summary from the highlight segments only. From the results of these experiments discovering the moments of the user’s major or special interest (namely, highlights) in a video, to generating summarization of videos. The above technique can help in increasing the analysis of Video content and thus achieving a more vigilant and secure society.

Deep LSTM model exploiting optical sensors for soil nutrient prediction

Deep LSTM model exploiting optical sensors for soil nutrient prediction

Application of Deep Learning LSTM and ARIMA Models in Time Series Forecasting: A Methods Case Study analyzing Canadian and Swedish Indoor Air Pollution Data

Application of Deep Learning LSTM and ARIMA Models in Time Series Forecasting: A Methods Case Study analyzing Canadian and Swedish Indoor Air Pollution Data