Wildfire Susceptibility Mapping Using Deep Learning Algorithms in Two Satellite Imagery Dataset

The suitability of using Moderate Resolution Imaging Spectroradiometer (MODIS) images for surface soil moisture estimation to investigate the importance of soil moisture in different applications, such as agriculture, hydrology, meteorology and natural disaster management, is evaluated in this study. Soil moisture field measurements and MODIS images of relevant dates have been acquired. Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and Normalized Difference Water Index (NDWI) are calculated from MODIS images. In addition, MODIS Land Surface Temperature (LST) data (MOD11A1) are used in this analysis. Four different soil moisture estimation models, which are based on NDVI–LST, EVI–LST, NDVI–LST–NDWI and EVI–LST–NDWI, are developed and their accuracies are assessed. Statistical analysis shows that replacing EVI with NDVI in the model that is based on LST and NDVI increases the accuracy of soil moisture estimation. Accuracy evaluation of soil moisture estimation using check points shows that the model based on LST, EVI and NDWI values gives a higher accuracy than that based on LST and EVI values. It is concluded that the model based on the three indices is a suitable model to estimate soil moisture through MODIS imagery.

Bitcoin's decentralized nature has made it a popular mode of payment for buyers and sellers, but its highly volatile nature poses a challenge for investors. This study aims to predict future Bitcoin prices using a combination of Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) algorithms. The non-stationary nature of Bitcoin prices is addressed using RNN, which is particularly useful for analyzing sequential data.The dataset used in this research is sourced from the Kraken exchange and includes various factors that are believed to influence Bitcoin prices, such as transaction volume, hash rate, and Google search trends. The data is preprocessed and cleaned to ensure accuracy, and then fed into the RNN and LSTM models for training and testing.The study's use of RNN and LSTM algorithms demonstrates the effectiveness of these methods in predicting Bitcoin prices, particularly in the context of sequential data. The results of the study, provide insights into potential future trends in Bitcoin prices and identify key indicators that significantly influence Bitcoin prices. The findings of this research have important implications for investors and traders looking to make informed decisions in the cryptocurrency market, as well as for researchers seeking to improve our understanding of Bitcoin's price dynamics. By predicting future prices, the study provides insights that can mitigate the risks associated with Bitcoin's volatility, making it a more viable investment option.

In today's digital world, app stores have become an essential part of software distribution, providing customers with a wide range of applications and opportunities for software developers to showcase their work. This study elaborates on the importance of end-user feedback for software evolution. However, in the literature, more emphasis has been given to high-rating & popular software apps while ignoring comparatively low-rating apps. Therefore, the proposed approach focuses on end-user reviews collected from 64 low-rated apps representing 14 categories in the Amazon App Store. We critically analyze feedback from low-rating apps and developed a grounded theory to identify various concepts important for software evolution and improving its quality including user interface (UI) and user experience (UX), functionality and features, compatibility and device-specific, performance and stability, customer support and responsiveness and security and privacy issues. Then, using a grounded theory and content analysis approach, a novel research dataset is curated to evaluate the performance of baseline machine learning (ML), and state-of-the-art deep learning (DL) algorithms in automatically classifying end-user feedback into frequently occurring issues. Various natural language processing and feature engineering techniques are utilized for improving and optimizing the performance of ML and DL classifiers. Also, an experimental study comparing various ML and DL algorithms, including multinomial naive Bayes (MNB), logistic regression (LR), random forest (RF), multi-layer perception (MLP), k-nearest neighbors (KNN), AdaBoost, Voting, convolutional neural network (CNN), long short-term memory (LSTM), bidirectional long short term memory (BiLSTM), gated recurrent unit (GRU), bidirectional gated recurrent unit (BiGRU), and recurrent neural network (RNN) classifiers, achieved satisfactory results in classifying end-user feedback to commonly occurring issues. Whereas, MLP, RF, BiGRU, GRU, CNN, LSTM, and Classifiers achieved average accuracies of 94%, 94%, 92%, 91%, 90%, 89%, and 89%, respectively. We employed the SHAP approach to identify the critical features associated with each issue type to enhance the explainability of the classifiers. This research sheds light on areas needing improvement in low-rated apps and opens up new avenues for developers to improve software quality based on user feedback.

Knowledge of the variation and regulation of the diffuse attenuation coefficient is important for management of lake water quality and ecological environments. Data were collected seven times (378 samples) from 2006 to 2011 in Lake Taihu to improve the existing semianalytical model of diffuse attenuation coefficient at 490 nm (Kd(490)) by measuring in situ Kd(490) and remote sensing reflectance (Rrs). This semianalytical model was applied to determine the long‐term variation of Kd(490) and its driving factors from Moderate Resolution Imaging Spectroradiometer (MODIS) images. Our semianalytical model of Kd(490) improves the retrieval accuracy of Kd(490) from 29.60% to 22.58% (root‐mean‐square percentage error) and 24.28 ± 18.54% (mean value ± standard deviation) to 19.29 ± 14.34% (mean absolute relative error). The Kd(490) from maps produced from MODIS images clearly present the temporal and spatial variations of Kd(490). This indicates the suitability of using the improved semianalytical model and MODIS to observe Kd(490) in turbid shallow inland waters. Long‐term MODIS observation of Kd(490) shows distinct seasonal and spatial variations. Temporally, the highest and the lowest Kd(490) were found in winter and in summer, respectively. Spatially, high Kd(490) values were primarily distributed in the southwestern and northwestern Lake Taihu, and relatively low Kd(490) values were distributed in Meiliang Bay and Gonghu Bay (the eastern part of the lake and East Bay were excluded in this study due to invalid retrieval results of Kd(490)). Many covarying points were found between Kd(490) and maximum wind speed from long‐term observations, suggesting that wind‐induced sediment resuspension is the principal driver of high Kd(490). Correlation was also observed between Kd(490) and heavy rainfall events, suggesting the regulating effect of heavy rainfall.

This paper presents a method of validating the MODIS (Moderate-Resolution Imaging Spectroradiometer) surface reflectance (MOD09) based on ground spectral measurements and high-resolution remote sensing images. Given that the spatial resolution of the MODIS image is too low to directly compare ground measurements with the MODIS pixels, registration is first made between MODIS and a high-resolution image. Afterwards, the same sizable sample area to one MODIS pixel is chosen in a high resolution image (a pixel in MODIS corresponds to many pixels in a high-resolution image), after which image classification is conducted in each sample area. Finally, reflectance is measured for each class in each area. Taking the ratio of every class area to each sample area as the weight, the weighted mean reflectance is then calculated for each sample area (a pixel for MODIS), which is treated as the measured reflectance of the corresponding pixel in the MODIS image. A contradistinctive analysis is carried out between measured reflectance and MODIS retrieval reflectance from the space in order to determine the accuracy of the MODIS land surface reflectance product and correct its error. The experiment indicates that a linear positive correlativity between the MODIS pixel retrieval reflectance from space and the measured (calculated) surface reflectance exists. From this, we can build an error correction model of the MODIS surface reflectance product by linear regression. The accuracy of the MODIS surface reflectance products after error correction is remarkably improved. Likewise, the relative error can be controlled by 10%, thereby satisfying the requirements of various remote sensing applications.

Data available on the internet is growing constantly. This huge amount of data makes it harder for the users to get useful information. Comments and reviews of movies are given by many users, and recommendation systems makes it easier to find useful content, which is fast and relevant for users. Movies with more positive reviews and comments are usually chosen by everyone. The sentiment behind user reviews is useful to know whether a movie is worth watching. This paper outlines an approach for a movie recommendation system that uses cosine similarity technique to recommend similar movies to users based on the movie title , genre, director, actor they choose or search . Deep learning algorithms, GRU (Gated Recurrent unit), LSTM (long short-term memory), RNN (Recurrent neural network) and BI-LSTM (bi-directional long short-term memory), are trained and tested to classify user comments taken from YouTube into positive, negative, and neutral sentiments. Accuracy, F1-score, precision, recall measures are utilized to assess the model from every perspective. After comparing four algorithms, as BI-LSTM outperformed other algorithms with an accuracy, recall, F1 score and precision, of 98.58%, 97.99% 98.26% and 98.54% respectively, Bi-LSTM (bi-directional long short-term memory) is used for performing sentiment analysis on the movie reviews dataset to understand users sentiment.

Prediction concept needs human-like thinking and ideas. ANN helps make a program for describing the solutions to the prediction problems. To gain accurate prediction, there is a need for deep thinking in the knowledge system discovered. Deep learning helps form such next-level type of ANN thinking. Deep learning models do not require humans for programming the problems. It can determine the prediction by itself by learning the dataset. This paper describes the prediction by considering sequential model for continuous accessing of data with the help of multi-layers. Deep learning is very helpful for predicting larger dataset. This paper proposes an algorithmic model known as a Comprehensive Deep Recurrent Artificial Neural Networks (CDRANN) by hybridizing LSTM (long short-term memory) with RNN (recurrent neural network) backtrack solver for better future stock prediction. This paper also explains the need for hybridizing evolutionary model CDRANN to create a novel change in future prediction.KeywordsCDRANN (Comprehensive Deep Recurrent Artificial Neural Networks)LSTM (long short-term memory)RNN (recurrent neural network)Stock marketPrediction

Understanding and exploiting feeding patterns in swine could allow a reduced feed waste and minimized sorting losses. The objectives of this study were to evaluate the ability to predict whether a pig reached a target weight at finishing by using several algorithms and to compare the prediction using varying amounts of data during the growing period. Data were collected on 655 pigs from 75 to 166 days of age. Pigs were housed with 8 to 15 pigs and a Feed Intake Recording Equipment in each pen. Feed consumption, occupation time, and body weight per visit were recorded when a pig visited the feeder. Lasso Regression (LS), a machine learning algorithm: Random Forest (RF), and a deep learning algorithm: Long-short Term Memory (LSTM) network, were used to forecast whether pigs can reach 129 kg at the finishing stage (159–166 d). Times of visits, a sum of feed consumption, a sum of occupation time in the feeder every day, and age were used as predictors. Data were split into 6 slices by 14 days and used to calibrate the models and their predictive ability was tested with data corresponding to the last 8 days of the study period. The greatest correlation coefficients were 0.799, 0.828, and 0.868 using slice 6 (145–158 d) to train the LS, RF, and LSTM, respectively. The LS and LSTM algorithms had a smaller root mean squared error, 0.863 and 0.895 compared to the RF with 1.375 in the prediction. Overall, LS and LSTM performed best. Predictions using data closest to the finishing stage proved better. This study connects the dynamics of feeding behavior and feed intake data to growth using prediction methods that will hopefully accelerate the mainstream application of electronic feeders in pig production systems.

We used publicly available digital spatial datasets to study the area extents and their horizontal variations of two water bodies within the Danjiangkou Reservoir, China. Between 2003 and 2005, the water levels varied from 140 to 149 m above mean sea level as measured by the Geoscience Laser Altimeter System (GLAS). Detailed procedures to derive the horizontal extents and variations from the Moderate Resolution Imaging Spectroradiometer (MODIS) and Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM) coupled with GLAS data and to verify the extents and variations spatially were provided. For the water bodies on the north and west, the surface water extents derived from four MODIS images varied between 174 and 218 km2 and from 96 to 135 km2, respectively. The extents by inundating the DEM using the GLAS data were 178–212 km2 for the water body on the north and 104–118 km2 for the water body on the west. The spatial verifications of surface water extents derived from the MODIS images versus DEM coupled with GLAS data agreed 83–93%. Within the ring areas between water/land boundaries at elevations of 140 and 147 m, and 140 and 149 m, the spatial agreement was 52–75%.

On extreme learning machines in sequential and time series prediction: A non-iterative and approximate training algorithm for recurrent neural networks

Protein lysine acetylation is an important post- translational modification (PTM) that takes an important part in many cellular processes, such as metabolism, differentiation and replication. However, the current lysine acetylation site identification mainly adopts experimental detection methods which are time-consuming and inefficient. Therefore, several shallow machine learning algorithms were applied for protein lysine acetylation site prediction. However, traditional machine learning algorithms are not as accurate as deep learning algorithms. As a special kind of recurrent neural network (RNN), long short-term memory (LSTM) can not only process sequence data but also solve the vanishing gradient problem. Therefore, this paper proposes a method based on LSTM to predict lysine acetylation sites. In addition, two traditional machine learning algorithms k-nearest neighbors (KNN) and support vector machine (SVM) were adopted for training as comparison. Through experimental verification, the prediction method based on LSTM is superior to the other two based on traditional machine learning algorithms, and the final prediction accuracy of LSTM model can reach up to 81.52%.

Wearable electroencephalography (EEG) devices for seizure detection accuracy and reliability are deep learning (DL) applications in the field of epilepsy diagnosis. In this study, we sought to increase the accuracy of seizure detection using advanced DL algorithms on the Children’s Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) EEG database. First, a fully convolutional network (FCN) was trained and assessed using accuracy and recall/precision metrics, and the early stopping technique was used to avoid overfitting. To assess the performance, the FCN was evaluated in terms of various metrics, including accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC)-area under the curve (AUC). In addition, two-dimensional (2D) convolutional neural networks (CNNs) and long short-term memory (LSTM) models were used to model the database, and their performance was thoroughly measured using different metrics, graphs, and confusion matrices. Using LSTM variants, such as standard LSTM, bidirectional LSTM, stacked LSTM, and LSTM attention mechanisms, hybrid convolutional LSTM (ConvLSTM) models were trained and compared. The comparison was conducted based on the training and validation accuracy and loss, as well as the graphs resulting from the precision–recall curves. Apart from DL approaches, EEG signal analysis using time–frequency techniques, such as wavelet transform and short-time Fourier transform, has also been investigated. These methods assisted in the analysis of the time–frequency features of EEG signals in combination with DL models. This study demonstrates that the performance of wearable EEG devices can be augmented using a combination of DL and seizure signal processing techniques. The FCN achieved an accuracy of 92%, with a recall for seizures of 33%, an F1-score of 0.03, and strong ROC-AUC results. The 2D CNN achieved 96% accuracy, a seizure recall of 70%, an F1-score of 0.12, and an ROC-AUC score of 78%. The baseline LSTM struggled with effectiveness at 53% accuracy with a seizure recall of 18%. In contrast, the LSTM model, which incorporated synthetic minority oversampling technique (SMOTE) balancing, was able to reach improvements of up to 89% accuracy, with a precision of 91%, a recall of 86%, an F1-score of 0.89, and a strong ROC curve performance. Among the models, the LSTM with SMOTE was the best performer, with 89% accuracy, 91% precision, 86% recall, and an F1-score of 0.89. These results provide evidence that applying techniques for data balancing in combination with certain DL network architectures significantly improves the detection of seizures using wearable EEG devices worn on the body. We believe that real-time monitoring and high-performance systems are feasible using optimized DL frameworks. The analysis of the performance of different models allows for the understanding of the possibilities of optimizing the architectures of DL algorithms for the modern diagnosis of epilepsy in real time. The source code used to carry out the experiments is publicly available at CHB-MIT EEG Dataset Python Scripts (https://www.kaggle.com/code/adnankust/adnaneeg1).

System or equipment prognosis and health management (PHM) has become more important than ever as modern industry develop. Normally PHM requires abundant prior information or statistic features to predict future system states, however an expert or accurate physical model is usually unavailable in practice. As an important trend of deep neural network algorithms, long short term memory (LSTM) recurrent neural network (RNN) has been proven significantly practical and accurate in machine learning problems such as natural language processing (NLP) and time serial prediction. In this paper a novel fault prognosis approach using LSTM based on vibration signal of rotating machinery is presented. It is proven that the capacity of machinery performance prediction with LSTM algorithm is improved with limited data available in a relatively short time period. The proposed LSTM approach, compared with other prognosis methods, gives a successful outcomes that may enhance the ability of health management and machine condition monitoring. It is proven that the proposed approach is superior and more practical for machine prognosis in complex bearing systems.

The nature of stock market movement has always been ambiguous for investors because of various influential factors. This study aims to significantly reduce the risk of trend prediction with machine learning and deep learning algorithms. Four stock market groups, namely diversified financials, petroleum, non-metallic minerals and basic metals from Tehran stock exchange, are chosen for experimental evaluations. This study compares nine machine learning models (Decision Tree, Random Forest, Adaptive Boosting (Adaboost), eXtreme Gradient Boosting (XGBoost), Support Vector Classifier (SVC), Naïve Bayes, K-Nearest Neighbors (KNN), Logistic Regression and Artificial Neural Network (ANN)) and two powerful deep learning methods (Recurrent Neural Network (RNN) and Long short-term memory (LSTM). Ten technical indicators from ten years of historical data are our input values, and two ways are supposed for employing them. Firstly, calculating the indicators by stock trading values as continues data, and secondly converting indicators to binary data before using. Each prediction model is evaluated by three metrics based on the input ways. The evaluation results indicate that for the continues data, RNN and LSTM outperform other prediction models with a considerable difference. Also, results show that in the binary data evaluation, those deep learning methods are the best; however, the difference becomes less because of the noticeable improvement of models’ performance in the second way.

The application of a deep learning algorithm (DL) can more accurately predict the initial flowering period of Platycladus orientalis (L.) Franco. In this research, we applied DL to establish a nationwide long-term prediction model of the initial flowering period of P. orientalis and analyzed the contribution rate of meteorological factors via Shapely Additive Explanation (SHAP). Based on the daily meteorological data of major meteorological stations in China from 1963–2015 and the observation of initial flowering data from 23 phenological stations, we established prediction models by using recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2) were used as training effect indicators to evaluate the prediction accuracy. The simulation results show that the three models are applicable to the prediction of the initial flowering of P. orientalis nationwide in China, with the average accuracy of the GRU being the highest, followed by LSTM and the RNN, which is significantly higher than the prediction accuracy of the regression model based on accumulated air temperature. In the interpretability analysis, the factor contribution rates of the three models are similar, the 46 temperature type factors have the highest contribution rate with 58.6% of temperature factors’ contribution rate being higher than 0 and average contribution rate being 5.48 × 10−4, and the stability of the contribution rate of the factors related to the daily minimum temperature factor has obvious fluctuations with an average standard deviation of 8.57 × 10−3, which might be related to the plants being sensitive to low temperature stress. The GRU model can accurately predict the change rule of the initial flowering, with an average accuracy greater than 98%, and the simulation effect is the best, indicating that the potential application of the GRU model is the prediction of initial flowering.