Modelling the Hatching Success of Sea Turtle Eggs Using Long Short-Term Memory (LSTM) for Conservation Oriented Ecotourism

Forecasting daily PM2.5 concentrations in Wuhan with a spatial-autocorrelation-based long short-term memory model

River stage prediction is indispensably a challenging task in flood-prone river basins to disseminate accurate early warning in advance. In this study, multivariate wavelet-based long short-term memory (WLSTM) models have been developed to predict river stage at six gauging stations of the Teesta River basin in India for 1, 3, and 5-day lead time, the comparison of which has been done with long short-term memory (LSTM) models. Various combinations of wavelet decomposed components were utilized to form different sub-series that were fed as input in WLSTM models. In terms of statistical indicators, both the models yielded exceptionally good results, but the root-mean-square error values of the WLSTM model for 1- and 3-day lead time were minimal compared to the LSTM model. However, the accuracy of the LSTM model in longer lead time prediction is noticeable. Specifically, the WLSTM model predicted the peak stage values more precisely compared to the LSTM model, indicating the potential of wavelet analysis to capture the variations and periodicities of the data by removing the noise. Though the WLSTM model marginally outperformed the LSTM model in prediction accuracy, the results highlight both models as feasible alternatives for longer lead time water level prediction.

This paper proposes two novel vector decomposed neural network models for behavioral modeling and digital predistortion (DPD) of radio-frequency (RF) power amplifiers (PAs): vector decomposed long short-term memory (VDLSTM) model and simplified vector decomposed long short-term memory (SVDLSTM) model. The proposed VDLSTM model is a variant of the classic long short-term memory (LSTM) model that can model long-term memory effects. To comply with the physical mechanism of RF PAs, VDLSTM model only conducts nonlinear operations on the magnitudes of the input signals, while the phase information is recovered by linear weighting operations on the output of the LSTM cell. Furthermore, this study modifies the LSTM cell by adding phase recovery operations inside the cell and replacing the original hidden state with the output magnitudes that are recovered with phase information. With the modified LSTM cell, a low-complexity SVDLSTM model is proposed. The experiment results show that the proposed VDLSTM model can achieve better linearization performance compared with the state-of-the-art models when linearizing PAs with wideband inputs. Besides, in wideband scenarios, SVDLSTM model with much fewer parameters can present comparable linearzation performance compared to VDLSTM model.

In recent years, the air quality in China has become a matter of serious concern. Among the available indicators for evaluating air quality, PM2.5 is one of the most important. It comprises a complex mixture of extremely small particles and liquid droplets emitted into the air, whose diameters are no more than 2.5 μm. Environments with a high PM2.5 index are extremely harmful to human health. Once inhaled, these particles can affect the heart and lungs and cause serious health problems. Air pollution is closely related to meteorological conditions such as wind speed, wind direction, atmospheric stability, temperature, and air humidity. With the development of various machine learning methods, deep learning models based on neural networks are increasingly applied in air pollution research. In this study, the temperature, humidity, wind velocity data at different pressure altitudes from 8 locations around Beijing and average of PM2.5 data in Beijing were analyzed and normalized. Multi-dimensional data was ideal for research applications using machine learning methods. and three neural network models were built, including the back propagation (BP), convolutional neural network (CNN), and long short-term memory (LSTM) models, and trained them using the meteorological and PM2.5 data.The results indicate that the accuracies of the back propagation and convolutional neural network models in predicting the PM2.5 pollution level in the next hour is much lower than that of the long short-term memory model. The PM2.5 pollution index predicted for the next hour by the long short-term memory model is very close to the actual value. This result reveals the strong relationship between the PM2.5 pollution index of Beijing and the local meteorological conditions. The long short-term memory model is trained using meteorological data from different pressure altitudes, and found it to be more accurate in predicting pollution levels when using near-surface meteorological data than that obtained from multiple altitudes.

A multiscale long short-term memory model with attention mechanism for improving monthly precipitation prediction

Air pollution remains one of the environmental issues affecting some countries, which leads to health issues globally. Though several machine learning and deep learning models are used to analyze air pollutants, model interpretability is a challenge. Also, the dynamic and time-varying nature of air pollutants often creates noise in measurements, making air pollutant prediction (e.g., Sulfur Dioxide (SO2) concentration) inaccurate, which influences a model’s performance. Recent advancements in artificial intelligence (AI), particularly explainable AI, offer transparency and trust in the deep learning models. In this regard, organizations using traditional machine and deep learning models are confronted with how to integrate explainable AI into air pollutant prediction systems. In this paper, we propose a novel approach that integrates explainable AI (xAI) into long short-term memory (LSTM) models and attempts to address the noise by Adaptive Kalman Filters (AKFs) and also includes causal inference analysis. By utilizing the LSTM, the long-term dependencies in daily air pollutant concentration and meteorological datasets (between 2008 and 2024) for the City of Kimberley, South Africa, are captured and analyzed in multi-time steps. The proposed model (AKF_LSTM_xAI) was compared with LSTM, the Gate Recurrent Unit (GRU), and LSTM-multilayer perceptron (LSTM-MLP) at different time steps. The performance evaluation results based on the root mean square error (RMSE) for the one-day time step suggest that AKF_LSTM_xAI guaranteed 0.382, LSTM (2.122), LSTM_MLP (3.602), and GRU (2.309). The SHapley Additive exPlanations (SHAP) value reveals “Relative_humidity_t0” as the most influential variable in predicting the SO2 concentration, whereas LIME values suggest that high “wind_speed_t0” reduces the predicted SO2 concentration.

In the financial world, the forecasting of stock price gains significant attraction. For the growth of shareholders in a company's stock, stock price prediction has a great consideration to increase the interest of speculators for investing money to the company. The successful prediction of a stock's future cost could return noteworthy benefit. Different types of approaches are taken in forecasting stock trend in the previous years. In this research, a new stock price prediction framework is proposed utilizing two popular models; Recurrent Neural Network (RNN) model i.e. Long Short Term Memory (LSTM) model, and Bi-Directional Long Short Term Memory (BI-LSTM) model. From the simulation results, it can be noted that using these RNN models i.e. LSTM, and BI-LSTM with proper hyper-parameter tuning, our proposed scheme can forecast future stock trend with high accuracy. The RMSE for both LSTM and BI-LSTM model was measured by varying the number of epochs, hidden layers, dense layers, and different units used in hidden layers to find a better model that can be used to forecast future stock prices precisely. The assessments are conducted by utilizing a freely accessible dataset for stock markets having open, high, low, and closing prices.

Customer reviews are important information that can be used by providers of goods or services to maintain customer loyalty, understand customer feelings and analyze the business competition. Users use customer feedback on social media or e-commerce as material for consideration before using or buying products. This study aims to conduct a sentiment analysis for user satisfaction of the Video on Demand application in Indonesia with the Long Short-Term Memory (LSTM) model. LSTM, which is a deep learning method that is widely implemented in natural language processing research. Sentiment analysis is applied to find out how customers feel about products on the market. The study results indicate that the LSTM model's implementation for sentiment analysis using two positive and negative labels obtained the value of precision 73.81%, recall 73.81%, f1 score 73.81%. In addition, the accuracy value obtained is 73.90% can be used as a consideration for the company in knowing user sentiment to meet the expectations and desires of customers and keep customers using the service.

Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction

A data-driven strategy using long short term memory models and reinforcement learning to predict building electricity consumption

Traditional Long Short Term Memory (LSTM) model can effectively improve the price prediction problem, but the LSTM model only accepts a single element input, and the power equipment price prediction involves multiple factors. Based on this, this paper proposes a multi-factor input-based LSTM model for transformer purchase price prediction, firstly, by changing the mapping structure of input layer, loop layer and output layer in the LSTM model, and then reasonably introducing the loop dropout restriction mechanism to ensure that the model structure is efficiently adapted to multi-factor input and low data training time. Finally, experimental simulations are conducted on a real price data set, and the validation results show that this algorithm can efficiently improve the price prediction accuracy and model robustness compared with traditional models.

The aim of study is building new program for processing MRI images using MATLAB and to investigate different breast MRI detection algorithms that inform normal and abnormal scans of MRI. In this research an algorithm is proposed to extract texture feature and inform normal and abnormal scans of MRI. First, the MRI scans are pre- processed by image enhancement, intensity normalization, background segmentation and detection of mirror symmetry of breast. Second, the proposed gray level co- occurrence matrix (GLCM) and gray level run length matrix (GLRLM) methods are used to extract texture features from MRI T2-weighted and STIR images. Finally, these features are classified into normal and abnormal by using long short term memory (LSTM) model. The research will be validated using 326 datasets that downloaded from cancer imaging archive (TCIA). The achieved classification accuracy was 98.80%.

Sign language is the primary communication tool used by the deaf community and people with speaking difficulties, especially during emergencies. Numerous deep learning models have been proposed to solve the sign language recognition problem. Recently. Bidirectional LSTM (BLSTM) has been proposed and used in replacement of Long Short-Term Memory (LSTM) as it may improve learning long-team dependencies as well as increase the accuracy of the model. However, there needs to be more comparison for the performance of LSTM and BLSTM in LRCN model architecture in sign language interpretation applications. Therefore, this study focused on the dense analysis of the LRCN model, including 1) training the CNN from scratch and 2) modeling with pre-trained CNN, VGG-19, and ResNet50. Other than that, the ConvLSTM model, a special variant of LSTM designed for video input, has also been modeled and compared with the LRCN in representing emergency sign language recognition. Within LRCN variants, the performance of a small CNN network was compared with pre-trained VGG-19 and ResNet50V2. A dataset of emergency Indian Sign Language with eight classes is used to train the models. The model with the best performance is the VGG-19 + LSTM model, with a testing accuracy of 96.39%. Small LRCN networks, which are 5 CNN subunits + LSTM and 4 CNN subunits + BLSTM, have 95.18% testing accuracy. This performance is on par with our best-proposed model, VGG + LSTM. By incorporating bidirectional LSTM (BLSTM) into deep learning models, the ability to understand long-term dependencies can be improved. This can enhance accuracy in reading sign language, leading to more effective communication during emergencies.

Background: Despite technological advancements, accurate weather forecasting remains a complex and challenging task. This looks at climate forecasts in Mosul City, Iraq, using a deep getting-to-know-you model that uses Long Short-Term Memory (LSTM) networks. More than a century's worth of historical weather records, including temperature, humidity, and precipitation, was used to teach and validate the model. The results demonstrate the effectiveness of LSTM in enhancing the dependability of climate forecasting, with an accuracy charge of above 88%. This takes a look at offers a strong basis for similar studies and operational forecasting structures while demonstrating the innovative capability of deep mastering in meteorological packages. Aims: The study presents an intensive teaching model using a long short-term memory (LSTM) network to predict weather conditions in Mosul City, Iraq, with an accuracy rate of more than 88%. The research examines deep learning ability in meteorological and weather applications and suggests future research on LSTM variants and network architecture. Study Design: The study takes a look at outlines and the procedure of constructing a Long Short-Term Memory (LSTM) model using Pandas. The dataset is loaded, preprocessed, and normalized using MinMaxScaler. Sequence creation is carried out through the use of Keras's Sequential API. The version is compiled using the Adam optimizer and MSE loss function for regression duties. The version is trained on the dataset, making predictions for the next day's climate in Mosul. Place and Duration of Study: Departments: Administrative Institute at Northern Technical University, Institution: Northern Technical University, Location: Mosul, Iraq, Duration: April 23 – May 2, 2024. Methodology: The method for predicting destiny climate entails loading a weather dataset, preprocessing it, creating sequences, building an LSTM version with MSE and MAE metrics, compiling the model with the usage of the Adam optimizer, and using mean squared mistakes for regression tasks. The LSTM version is educated on the dataset through the use of the match () technique, and the model predicts the next day's climate using inverse transformation and information manipulation. The predictions are displayed and stored in a brand-new CSV file for efficient time series analysis and preservation of ancient climate information. Results: A weather forecasting version becomes advanced through the use of Long Short-Term Memory (LSTM) neural networks and weather facts for Mosul. The model produced correct predictions for destiny climate parameters like humidity, temperature extremes, rainfall, and UV index. The model finished with an 88% average accuracy throughout all variables, with the lowest accuracy (60%) occurring on April 29 because of combined errors in humidity and MAX temperature. The version has proven reliable performance for temperature and humidity but calls for refinement for rainfall prediction, mainly throughout high-variability periods. The 88% common accuracy offers actionable insights for agricultural and disaster control planning. Conclusion: A weather forecasting model that uses Long Short-Term Memory (LSTM) neural networks and Mosul metropolis weather records completed 88% common accuracy for destiny weather parameters like humidity, temperature extremes, rainfall, and UV index. The version offers actionable insights for agricultural and catastrophe control planning; however, it calls for refinement for rainfall prediction. The findings should improve weather forecasts, useful resource groups in choice-making, and observe industries like catastrophe alleviation, transportation, and agriculture.

Machine learning (ML) is increasingly being used in the healthcare domain for time-series predictions. However, the development of multi-headed ML architectures for multivariate time-series predictions has been less explored in the literature concerning healthcare domain. Multi-headed neural network architectures work on the idea that each independent variable (input series) can be handled by a separate neural network model (head) and the output of each of these models (heads) can be combined before a prediction is made about a dependent variable. In this paper, we develop three multi-headed ML architectures and their ensemble to predict patients’ weekly average expenditures on two pain medications. A multi-headed long short-term memory (LSTM) model, a multi-headed convolutional neural network long short-term memory (CNN-LSTM) model, a multi-headed convolutional long short-term memory (ConvLSTM) model, and an ensemble model combining predictions of the three multi-headed models were calibrated to predict patients’ weekly average expenditures on two pain medications. The ensemble model combined the predictions of different multi-headed models using an exponential weight algorithm. Results revealed that the ensemble model outperformed the multi-headed models for both pain medications. Furthermore, the multi-headed CNN-LSTM model outperformed the multi-headed LSTM and ConvLSTM models for one medication; however, the multi-headed LSTM model outperformed the multi-headed CNN-LSTM and ConvLSTM models for the other medication. We highlight the utility of developing multi-headed ML architectures and their ensembles for prediction of patient-related expenditures in the healthcare domain.