LSTM Technique Research Articles

Improving wave height prediction accuracy with deep learning

A novel convolutional neural network-long short-term memory (CNN-LSTM) model is proposed for wave height prediction. The model effectively extracts relevant features such as wind speed, wind direction, wave height, latitude, and longitude. The proposed model outperforms traditional machine learning algorithms such as multi-layer perceptron (MLP), support vector machine (SVM), random forest and LSTM, especially for extreme values and fluctuations. The model has a significantly lower average root mean square error (RMSE) of 71.1%, 72.8%, 71.9% and 72.2% for MLP, SVM, random forest and LSTM, respectively. Our model is computationally more efficient than traditional numerical simulations, making it suitable for real-time applications. Moreover, it has better long-term robustness compared to traditional models. The integration of CNN and LSTM techniques improves wave height prediction accuracy while enhancing its efficiency and robustness. The proposed CNN-LSTM model provides a promising tool for effective wave height prediction, making a valuable contribution to coastal disaster prevention and mitigation. Future research should aim to improve long-term prediction accuracy, and we believe that the CNN-LSTM model plays a crucial role in developing real-time coastal disaster prevention and mitigation measures. Overall, our study represents a significant step towards achieving more accurate and efficient wave height prediction using machine learning techniques.

Automatic Approach for Brain Aneurysm Detection Using Convolutional Neural Networks

The paper introduces an approach for detecting brain aneurysms, a critical medical condition, by utilizing a combination of 3D convolutional neural networks (3DCNNs) and Convolutional Long Short-Term Memory (ConvLSTM). Brain aneurysms pose a significant health risk, and early detection is vital for effective treatment. Traditional methods for aneurysm detection often rely on complex and time-consuming procedures. A radiologist specialist annotates each aneurysm and supports our work with true-ground annotations. From the annotated data, we extract images to train proposed neural networks. The paper experiments with two different types of networks, specifically focusing on 2D convolutional neural networks (2DCNNs), 3D convolutional neural networks (3DCNNs), and Convolutional Long Short-Term Memory (ConvLSTM). Our goal is to create a virtual assistant to improve the search for aneurysm locations, with the aim of further realizing the virtual assistant. Subsequently, a radiologist specialist will confirm or reject the presence of an aneurysm, leading to a reduction in the time spent on the searching process and revealing hidden aneurysms. Our experimental results demonstrate the superior performance of the proposed approach compared to existing methods, showcasing its potential as a valuable tool in clinical settings for early and accurate brain aneurysm detection. This innovative fusion of 3DCNN and LSTM (3DCNN-ConvLSTM) techniques not only improves diagnostic precision but also holds promise for advancing the field of medical image analysis, particularly in the domain of neurovascular diseases. Overall, our research underscores the potential of neural networks for the machine detection of brain aneurysms.

A novel hybrid deep learning model for multi-step wind speed forecasting considering pairwise dependencies among multiple atmospheric variables

The reliable wind speed forecasting is critical for wind farms as it enables them to improve cost-effectiveness and optimize energy efficiency. In this study, a novel hybrid deep learning model is proposed for multi-step wind speed forecasting, which simultaneously captures pairwise dependencies and temporal features of multiple atmosphere variables. Initially, to extract intrinsic mode functions (IMFs) of nonstationary atmospheric variables, the Variational Mode Decomposition (VMD) is used. The decomposed atmospheric variables are then grouped according to similarity of mode and the pairwise dependencies are captured using the Graph Neural Network (GNN). Subsequently, the Temporal Convolutional Network (TCN) is applied for wind speed forecasting. The proposed model notably outperforms existing models with a Mean Absolute Error (MAE) of less than 0.1 m/s in one-hour ahead forecasting (1-h). Additionally, it improves wind speed forecasting accuracy by 79.22% at 1-h, 79.13% at 2-h, 80.00% at 3-h, 78.70% at 6-h, and 58.41% at 12-h, respectively, compared to the frequently used LSTM technique for wind speed forecasting. The outcomes of this study indicate that this novel approach to wind speed forecasting holds substantial potential for real-world wind farm operational contexts.

Unveiling the SALSTM-M5T model and its python implementation for precise solar radiation prediction

The world is increasingly embracing cleaner and more sustainable energy sources, with solar energy playing a crucial role in mitigating greenhouse gas emissions and addressing climate change. Accurate solar radiation predictions are vital for optimizing solar energy resource utilization and identifying suitable locations for solar power plants. Therefore, our study introduces a new model to advance solar and renewable energy systems. In this paper, we suggest a novel hybrid model, Self-attention (SA) mechanism-long short-term memory neural network (LSTM)-M5Tree (SALSTM5T) model, for predicting solar radiation. The SALSTM-M5T model combines the advantages of the Self-attention- LSTM (SALSTM) and M5Tree models. The LSTM component captures long-term solar radiation dependencies. SA improves the accuracy of LSTM and M5T models by focusing on relevant input features at different time steps. The study utilizes K-fold cross-validation to overcome the limitations of traditional methods for determining the size of training and testing data. By combining the advantages of the SALSTM and M5Tree models, our research presents a new framework for accurate solar radiation prediction. Existing techniques are developed by using SA and K-fold cross-validation. Furthermore, our paper emphasizes the practical applications of solar radiation prediction, such as identifying suitable areas for solar power plants and optimizing energy production. Our study concluded that the self-attention mechanism and LSTM model improved the efficiency of M5T models for analyzing solar time series data as these models can attend to important features. The centralized root mean square error (CRMSE) of the SALSTM-M5T, LSTM-M5T, LSTM, ANN, and M5T models was 0.04, 0.17, 0.25, 0.49, and 0.70, respectively. The SALSTM-M5T, LSTM-M5T, LSTM, ANN, and M5T models' correlation coefficients were 0.99, 0.98, 0.96, 0.89, and 0.82, respectively. Our SALSTM-M5T model contributes to advancing renewable energy planning and decision-making. The main innovation of the current article is the development of the M5T model using the capabilities of the SA and LSTM models. The SALSTM-M5T hybrid model, which combines self-attention, LSTM and M5Tree techniques, is proposed as an effective approach for solar radiation prediction. The results show its superiority over other models in terms of accuracy and suitability, which can be useful for practical applications in the field of renewable energy, such as site selection for solar power plants and optimization of energy production. Furthermore, this paper aligns with the advancement of digital sensors to enhance the accuracy of solar radiation prediction.

A Novel Method of Fraud Detection of Credit Cards by Fuzzy, LSTM, and PSO Optimization

Since online shopping has become so popular, credit card theft has skyrocketed. This makes it hard to spot fake charges on accounts. In this research, credit card fraud detection is performed using a fuzzy database. It has been considered a data mining challenge to reliably identify whether or not a transaction is legitimate. This paper discusses the LSTM method and fuzzy logic. The learning process was sped up and made more precise by using a technique called particle swarm optimization (PSO). Performance values have been compared with those of the LSTM and fuzzy logic techniques, and a PSO-based neural network has been intensively trained by increasing the number of iterations and the population, or number of swarms. It has been shown that the PSO-based algorithm yields the best result for detecting fraudulent transactions. The goal of this method is to lower the mean square error (MSE) rate of the system. PSO is a popular optimization technique that can be used to locate the optimal set of features for the credit card fraud detection system. The proposed method PSO shows less mean squared error compared with Fuzzy and LSTM techniques.

Fake News Detection Using Optimized CNN and LSTM Techniques

Fake News Detection Using Optimized CNN and LSTM Techniques

Intelligent irrigation scheduling scheme based on deep bi-directional LSTM technique

Intelligent irrigation scheduling scheme based on deep bi-directional LSTM technique

A multihead LSTM technique for prognostic prediction of soil moisture

Prognostic prediction of soil moisture is a critical step in various fields such as geotechnical engineering, agriculture, geology, hydrology, and climatology. For example, in agricultural applications, soil moisture prediction is needed one-day and one-week ahead of time to optimize crop planting quality and set irrigation schedule, respectively. In soil and environmental management applications, soil moisture prediction is usually needed one-month ahead of time. Therefore, a capability to accurately forecast soil moisture is of paramount importance. For this purpose, deep learning methods, especially the long short-term memory network (LSTM) method, have been used extensively. It is shown that such models can successfully forecast the soil moisture for a short time frame in future, but their accuracy sharply decreases for long time frames. To resolve this issue, in this study, we present a multihead LSTM model that learns a number of hypotheses and aggregates them for prognostic prediction tasks. The multihead LSTM model is comprised of four LSTM models that digest time series data of soil moisture aggregated at different scales as inputs. The outputs of these models, i.e., predicted soil moisture at a certain time in future, are then combined using a weighted averaging method to obtain the final prediction values. Different statistical measures, such as the root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R-squared are employed to assess the performance of the multihead LSTM model predictions against the ground truth. The results show that the proposed multihead LSTM method is effective to forecast the soil moisture up to one-month in future with a R-squared value of 95.04%.

Prediction of Cognitive Load from Electroencephalography Signals Using Long Short-Term Memory Network

In recent years, the development of adaptive models to tailor instructional content to learners by measuring their cognitive load has become a topic of active research. Brain fog, also known as confusion, is a common cause of poor performance, and real-time detection of confusion is a challenging and important task for applications in online education and driver fatigue detection. In this study, we propose a deep learning method for cognitive load recognition based on electroencephalography (EEG) signals using a long short-term memory network (LSTM) with an attention mechanism. We obtained EEG signal data from a database of brainwave information and associated data on mental load. We evaluated the performance of the proposed LSTM technique in comparison with random forest, Adaptive Boosting (AdaBoost), support vector machine, eXtreme Gradient Boosting (XGBoost), and artificial neural network models. The experimental results demonstrated that the proposed approach had the highest accuracy of 87.1% compared to those of other algorithms, including random forest (64%), AdaBoost (64.31%), support vector machine (60.9%), XGBoost (67.3%), and artificial neural network models (71.4%). The results of this study support the development of a personalized adaptive learning system designed to measure and actively respond to learners' cognitive load in real time using wireless portable EEG systems.

Comparison of Different Machine Learning Scenarios for Stock Price Prediction of Netflix

Buying stocks based on relatively accurate predictions to make a profit is what investors have been yearning for. However, due to the volatility and stochastic intrinsic of the stock, the price is also full of uncertainty, which is difficult to predict. With the improvement of computer performance and the popularization of machine learning methods nowadays, effective stock prediction methods emerge one after another. In this paper, random forest, XGBoost, and LSTM techniques are utilized for predicting the closing price of Netflix, which is one of the major stocks in Nasdaq and has been fluctuating this year. The closing price of the previous five days and the last day’s volume are used as inputs. The models are evaluated by MSE and R-square. According to the analysis, similar model evaluation results in random forest and LSTM indicate that the models are efficient. Furthermore, the prediction could be improved by considering the fluctuations of stocks simultaneously and introducing more variables in various dimensions. These results shed light on guiding further exploration of predicting stock price movements based on advanced machine learning methods.

Improvements of Stock Price Prediction Based on LSTM by Fama-French Five Factors on Market Capitalization

Stock price prediction refers to determining the trend of a budgetary trade's stock projection. The precise prognosis of offer value growth will urge greater profit for speculators. The research based on previously obtained massive data with the use of AI techniques is applicable to a variety of disciplines. The primary goal is to create an analysis for the purpose of producing well-quality information that will be beneficial for decision-making. There are several machine-learning approaches with varying degrees of accuracy. However, choosing of the optimal technique to attain the maximum level of precision is an important requirement. The LSTM techniques are supervised learning-based and will require training to increase accuracy. This paper adopts LSTM algorithms combining with the Fama-French five-factors (FF5F) daily to the daily close price prediction of 10 companies represent as large and small market capitalizations from October 31, 2012 till October 28, 2022. It determines the relationship of the proposed LSTM model and market capitalization of companies. The results reveal that the LSTM model combined with FF5F for the low market capitalization companies outperforms the large market capitalization on stock price prediction.

Hybrid LSTM technique for phonetic

Demographic Details is empirically obtained data depicting different elements of a population. Various phonetic-based retrieving strategies are utilized, yet they are useless when trying to appeal to Indian name lists. The purpose of this research is to find Indian names with identical accents but distinct spellings based on data entries acquired from demographic databases. This study document contains the phonetic-based pronunciation technique, Long Short Term Memory, and K-Mean method Hybrid LSTM approach to identify Indian names using databases. The suggested Hybrid LSTM method is compared to a recurrent unit GRU-based technique in order to assess the precision of name prediction for Indian names. The hybrid LSTM model is produced by combining the K-Mean technique and the LSTM technique. When obtaining entries of Indian Names from sources, the constructed LSTM approach provides improved precision. If, as is the case in this instance, the demographic data collected from Indian Names from demographic sources has inaccurate data due to misspelled names, the provided method can be utilized to decrease data redundancy and acquire accurate data.

Harnessing LSTM Classifier to Suggest Nutrition Diet for Cancer Patients

A customized nutrition-rich diet plan is of utmost importance for cancer patients to intake healthy and nutritious foods that help them to be strong enough to maintain their body weight and body tissues. Consuming nutrition-rich diet foods will prevent them from the side effects caused before and after treatment thereby minimizing it. This work is proposed here to provide them with an effective diet assessment plan using deep learning-based automated medical diet system. Hence, an Enhanced Long-Short Term Memory (E-LSTM) has been proposed in this paper, especially for cancer patients. This proposed method will be very useful for cancer patients as this would help them predict the foods which can be consumed by them based on the nutrition analysis of food images. The classification will be performed in E-LSTM by analyzing the two datasets, one with food images and another with cancer patients’ details. Following an in-depth analysis of the major research papers concerning deep learning strategies to identify the foods along with their nutrition composition, this method has been identified as one of the finest deep learning approaches that are used for classification especially. This work has been identified as the first work producing a new layer for feature extraction and providing nutrition suggestions, especially for cancer patients using the LSTM technique. The accuracy of prediction and classification will be improved by the dedicated layer for feature extraction in E-LSTM. Hence, it is proved that this proposed method outperforms all other existing techniques in terms of F1 Score, Precision, Recall, Classification accuracy, Training loss and Validation loss.

Cardiovascular disease prediction using hyperparameters-tuned LSTM considering COVID-19 with experimental validation

<abstract> <p>Heart disease, globally recognized as a leading cause of death, has seen its impact magnified by the emergence of COVID-19. The heightened demand for early detection and diagnosis of heart disease has forced the development of innovative, intelligent systems. This research offers a novel approach by leveraging extended short-term memory networks (LSTM) and including COVID-19 as a significant parameter in cardiac arrest analysis. A comparative study is conducted between LSTM and other prevalent techniques, such as support vector machines (SVM), linear regression (LR), and artificial neural networks (ANN), focusing on accuracy and other prognostic criteria for heart disease. We aim to develop an intelligent system powered by LSTM to predict heart disease, thereby assisting healthcare professionals in making well-informed decisions about heart disease management, stroke prevention, and patient monitoring. Additionally, hyperparameter tuning has been performed to optimize the LSTM model's performance in cardiac arrest prediction. The results underscore that LSTM, especially when trained with COVID-19 as an input parameter, surpasses other established techniques in prediction accuracy. The proposed model underwent experimental testing, showcasing its proficiency in predicting cardiovascular disease.</p> </abstract>

Performance Comparison of Deep Learning Algorithm for Speech Emotion Recognition

One of the problems in Speech emotion recognition is related to time series data, while the feedforward process in neural networks is unidirectional where the results from one layer are directly channeled to the next layer. This kind of feedforward process cannot store past data. Thus, if Deep Neural Network (DNN) is used for Speech emotion recognition, some problems arise, such as the speech rate of the speaker. DNN cannot analyze the existing acoustic patterns and so cannot map different levels of speech rate. Another method that can take input at once while retaining relevant data in the previous process is the Recurrent Neural Network (RNN). This paper presents the characteristics of the RNN method consisting of LSTM and GRU techniques for Speech emotion recognition using the Berlin EMODB dataset. The dataset is divided into 80% for training and 20% for testing. The feature extraction methods used are Zero crossing Rate (ZCR), Mel Frequency Cepstral Coefficients (MFCC), Root Mean Square Energy (RMSE), Mel Spectrogram, and Chroma. This study compares the CNN, LSTM, and GRU algorithms. The classification results show that the CNN algorithm gets better results, namely 79.13%. Meanwhile, LSTM and GRU only got an accuracy of 55.76% and 55.14%, respectively

Sentiment Classification of Financial Texts for Stock Forecasting using LSTM Technique

Sentiment Classification of Financial Texts for Stock Forecasting using LSTM Technique

A Survey Of Machine Learning Techniques OnSpeech Based Emotion Recognition And Post Traumatic Stress DisorderDetection

This paper reviews the literature on a wide array of methodologies utilizedfor emotion recognition from stressedspeech. These techniques include models for the detection of post-traumaticstress disorder (PTSD), neural networks, and long and short-term memory networks (LSTM). The relevance of selecting alternative classification models has also been emphasized. The crucial issues to consider for future emotion recognition research in general,specifically in theindian context, have been highlighted where applicable. Finally, possible future trends in stressed emotion recognition are discussed, including the use of region based convolutional neural network (RCNN), you look only once (YOLO),recurrent neural networks (RNN), and LSTM techniques to solve new challenges in this domain.

Sentiment Classification of Financial Texts for Stock Markets using LSTM Technique: A Survey

Sentiment Classification of Financial Texts for Stock Markets using LSTM Technique: A Survey

Deep learning models for detecting respiratory pathologies from raw lung auscultation sounds.

In recent years deep learning models improve the diagnosis performance of many diseases especially respiratory diseases. This paper will propose an evaluation for the performance of different deep learning models associated with the raw lung auscultation sounds in detecting respiratory pathologies to help in providing diagnostic of respiratory pathologies in digital recorded respiratory sounds. Also, we will find out the best deep learning model for this task. In this paper, three different deep learning models have been evaluated on non-augmented and augmented datasets, where two different datasets have been utilized to generate four different sub-datasets. The results show that all the proposed deep learning methods were successful and achieved high performance in classifying the raw lung sounds, the methods were applied on different datasets and used either augmentation or non-augmentation. Among all proposed deep learning models, the CNN–LSTM model was the best model in all datasets for both augmentation and non-augmentation cases. The accuracy of CNN–LSTM model using non-augmentation was 99.6%, 99.8%, 82.4%, and 99.4% for datasets 1, 2, 3, and 4, respectively, and using augmentation was 100%, 99.8%, 98.0%, and 99.5% for datasets 1, 2, 3, and 4, respectively. While the augmentation process successfully helps the deep learning models in enhancing their performance on the testing datasets with a notable value. Moreover, the hybrid model that combines both CNN and LSTM techniques performed better than models that are based only on one of these techniques, this mainly refers to the use of CNN for automatic deep features extraction from lung sound while LSTM is used for classification.

A Comparison of Sensitive Information Detection Framework using LSTM and RNN Techniques

Sensitive information is meant to be stored securely to avoid any data breach. Hence this research emphasized on whether or not Long Short Term Memory and Recurrent Neural Network is suitable for sensitive information detection framework since performance analysis on this method are not common. In this research, the objectives are to design Sensitive Information Detection Framework using Deep Learning techniques, to detect sensitive information using LSTM and RNN techniques and to test and validate the sensitive information detection framework performance. This research uses raw data set given from Book Hack Enterprise company and by using Weka Explorer software tool to go through 5 phases in the proposed framework, which are Dataset, Preprocessing, Feature Extraction, Classification Algorithm and Performance Evaluation. This research evaluates the model performance based on Accuracy, Precision, Recall and F1-score.