LSTM Technique Research Articles

Predictive Modeling of Crop Yield Using Deep Learning Based Transformer with Climate Change Effects

Climate change is a significant global challenge concerning agriculture and food security. The understanding of climate change effects on crop production is necessary for developing an effective adaptation strategies and predicting a crop yield accurately. This paper suggests the combined Clustering Long Short Term Memory Transformer (CLSTMT) model for crop yield prediction. CLSTMT is a hybrid model that integrates clustering, deep learning based LSTM and Transformer techniques. The outliers from the historical crop and climate data are removed using k-means clustering. Followed by, the crop yield is predicted using Transformer-based neural network with LSTM layers and feed-forward neural network (FNN) components. The model design effectively captures climate-influenced patterns, enhances the precision and comprehensiveness of crop yield prediction. The experiment is conducted using the dataset with crop yield, climate, and pesticide details over 101 countries collected from 1990 to 2013. The comparative analysis reveals that the CLSTMT model outperforms other regression models such as SGDRegressor (SGDR), Lasso Regression (LR), Support Vector Regression (SVR), ElasticNet (EN) and Ridge Regression (RR). The proposed design effectively captures climate-influenced patterns, enhancing the precision and comprehensiveness of crop yield predictions. The findings indicate that the proposed model provides an accurate prediction of crop yield with high R2 of 0.951 and lesser Mean Absolute Percentage Error (MAPE) of 0.195. This value suggests a minimal average percentage deviation between the actual and predicted yields. The findings indicate that the CLSTMT model provides more accurate crop yield prediction compared to others.

Intelligent Reflecting Surface-Assisted Wireless Communication Using RNNs: Comprehensive Insights

By adjusting the propagation environment using reconfigurable reflecting elements, intelligent reflecting surfaces (IRSs) have become potential techniques used to improve the efficiency of wireless communication networks. In IRS-assisted communication systems, accurate channel estimation is crucial for optimizing signal transmission and achieving high spectral efficiency. As mobile data traffic continues to surge and the demand for high-capacity and low-latency wireless connectivity grows, IRSs are becoming pivotal technologies in the development of next-generation communication networks. IRSs offer the potential to revolutionize wireless propagation environments, improving network capacity and coverage, particularly in high-frequency wave scenarios where traditional signals encounter obstacles. Amidst this evolving landscape, machine learning (ML) emerges as a powerful tool to harness the full potential of IRS-assisted communication systems, particularly given the escalating computational complexity associated with deploying and operating IRSs in dynamic environments. This paper presents an overview of preliminary results for IRS-assisted communication using recurrent neural networks (RNNs). We first implement single- and double-layer LSTM, BiLSTM, and GRU techniques for an IRS-based communication system. In the next phase, we explore a hybrid approach, combining different RNN techniques, including LSTM-BiLSTM, LSTM-GRU, and BiLSTM-GRU, as well as their reverse configurations. These RNN algorithms were evaluated with respect to bit error rate (BER) and symbol error rate (SER) for IRS-enhanced communication. According to the experimental results, the BiLSTM double-layer model and the BiLSTM-GRU combination demonstrated the highest BER and SER accuracy compared to other approaches.

Integrating machine and deep learning technologies in green buildings for enhanced energy efficiency and environmental sustainability

A green building (GB) is a design idea that integrates environmentally conscious technology and sustainable procedures throughout the building’s life cycle. However, because different green requirements and performances are integrated into the building design, the GB design procedure typically takes longer than conventional structures. Machine learning (ML) and other advanced artificial intelligence (AI), such as DL techniques, are frequently utilized to assist designers in completing their work more quickly and precisely. Therefore, this study aims to develop a GB design predictive model utilizing ML and DL techniques to optimize resource consumption, improve occupant comfort, and lessen the environmental effect of the built environment of the GB design process. A dataset ASHARE-884 is applied to the suggested models. An Exploratory Data Analysis (EDA) is applied, which involves cleaning, sorting, and converting the category data into numerical values utilizing label encoding. In data preprocessing, the Z-Score normalization technique is applied to normalize the data. After data analysis and preprocessing, preprocessed data is used as input for Machine learning (ML) such as RF, DT, and Extreme GB, and Stacking and Deep Learning (DL) such as GNN, LSTM, and RNN techniques for green building design to enhance environmental sustainability by addressing different criteria of the GB design process. The performance of the proposed models is assessed using different evaluation metrics such as accuracy, precision, recall and F1-score. The experiment results indicate that the proposed GNN and LSTM models function more accurately and efficiently than conventional DL techniques for environmental sustainability in green buildings.

Arctic and Antarctic Sea Ice Extent Forecasting using Hybrid LSTM Technique

Arctic and Antarctic Sea Ice Extent Forecasting using Hybrid LSTM Technique

Electric vehicle supply equipment monitoring and early fault detection through autoencoders

This paper presents a novel approach to detecting anomalies in Electric Vehicle charging unit power profiles using a combination of Autoencoders with LSTM techniques. This study presents a robust methodology, combining the two Machine Learning techniques, for early fault estimation in a real-world case study. The proposed methodology offers significant advantages over existing methods by providing a more comprehensive analysis of anomalous trends. To validate the effectiveness of the proposed methodology, the authors tested it on real Electric Vehicles charging power curves provided by an Italian Distribution System Operator recorded on a historical database and compared the performances with the ones of a traditional anomaly detection technique. The results of the study, tested on Electric Vehicles Supply Equipment or charging stations, demonstrate that the proposed approach is highly effective in detecting anomalous trends in Electric Vehicles charging profiles.

Improved rank-based recursive feature elimination method based ovarian cancer detection model via customized deep architecture

BackgroundOvarian cancer is often considered the most lethal gynecological cancer because it tends to be diagnosed at an advanced stage, leading to limited treatment options and poorer outcomes. Several factors contribute to the challenges in managing ovarian cancer, namely rapid metastasis, genetic factors, reproductive history, etc. This necessitates the prompt and precise diagnosis of ovarian cancer in order to carry out efficient treatment plans and give patients who are all impacted by OC the care and support they need. MethodsThis CCLSTM model is suggested under four essential stages including preprocessing, feature extraction, feature selection and detection. Initially, the input data is preprocessed using Improved Two-step Data Normalization. Subsequently, features such as statistical, modified entropy, raw features and mutual information are extracted from the normalized data. Next, obtained features undergo the Improved Rank-based Recursive Feature Elimination method (IR-RFE) to select the most suitable features. Finally, the proposed CCLSTM model takes the selected features as input and provides a final detection outcome. ResultsFurthermore, the performance of the proposed CCLSTM technique is examined through a thorough assessment using diverse analyses Additionally, the CCLSTM schemes show a sensitivity value of 0.948, whereas the sensitivity ratings for ALO-LSTM + ALOCNN, Bi-GRU, LSTM, RNN, KNN, CNN, and DCNN are 0.808, 0.893, 0.829, 0.851, 0.765, 0.872, and 0.893, respectively. ConclusionIn the end, the development of CNN and the addition of LSTM technique have produced an ovarian cancer detection technique that is more accurate and consistent compared to other existing strategies.

A comprehensive analysis of LSTM techniques for predicting financial market

The “Financial Engineering” has revolutionized the financial industry by integrating mathematics, finance, economics, statistics, and computational tools to solve complex problems like risk management and portfolio optimization. This interdisciplinary approach has given rise to “AI in Finance”, merging the quantitative techniques of financial engineering with AI’s data-driven capabilities. In this survey, we explore concrete examples of their real-world impact. One such example involves a leading investment firm using machine learning algorithms to analyze market sentiments for informed trading decisions, resulting in significant returns. Additionally, AI-driven credit scoring models are expanding financial access by accurately assessing creditworthiness, especially for underserved populations. Natural language processing algorithms are also employed to parse financial news and social media data, providing investors with timely insights to navigate volatile markets effectively. These advancements highlight the transformative potential of financial engineering and AI in finance. By optimizing investment strategies and mitigating risks, they drive innovation and resilience in today’s dynamic financial landscape. From algorithmic trading to credit risk assessment and market sentiment analysis, the fusion of these disciplines is reshaping traditional paradigms and shaping the future of finance.

PV ENERGY FORECASTING USING DEEP LEARNING ALGORITHM

Solar energy has vast potential in India which is a rapidly growing economy with diverse geographical features. Solar energy has intermittent behaviour and depends on geographical and weather conditions. Therefore, the reliability of the solar depends on the seamless operation of solar plants with the latest technologies. The main objective of power operator is to facilitate the renewable power sources intergeration for maintaining an uninterrupted power supply. To achieve this objective, researchers have employed various Deep Learning methods of machine learning, such as RNN, LSTM, CNN and SVM for accurate solar power forecasting with higher relibaility. In this paper, a GA-CNN deep learning algorithm is employed with an optimized hyperparameters technique for PV energy forecasting. This technique outperforms when compared with the other methods such as LSTM, KNN-SVM, and CNN-RNN techniques in terms of RMSE, MAE, MSE and R-Square performance indices. This method provides a better and more robust method of deep learning for solar PV energy forecasting.

Stock Prediction using LSTM Technique

Abstract: We attempt to use a machine learning approach to anticipate stock prices in this project. Whenit comes to stock price predictions, machine learning works well. The goal is to forecast future stock prices. make more accurate and better investment decisions We propose incorporating mathematical functions into stock prices. To arrive at an acceptable timescale, examine the prediction system, machine learning, and other external factors. delivers accurate stock predictions and lucrative trades There are some There are two types of stocks. Day trading is another name forintraday trading. The phrase "day trading"was thrown around. Interday traders invest in a diverse range ofassets. at least one day after another, and frequently forseveral days or weeks, LSTMs are quite effective in solving sequence prediction problems.because they maystore information from the past.

Spatiotemporal Flood Hazard Map Prediction Using Machine Learning for a Flood Early Warning Case Study: Chiang Mai Province, Thailand

Floods cause disastrous damage to the environment, economy, and humanity. Flood losses can be reduced if adequate management is implemented in the pre-disaster period. Flood hazard maps comprise disaster risk information displayed on geo-location maps and the potential flood events that occur in an area. This paper proposes a spatiotemporal flood hazard map framework to generate a flood hazard map using spatiotemporal data. The framework has three processes: (1) temporal prediction, which uses the LSTM technique to predict water levels and rainfall for the next time; (2) spatial interpolation, which uses the IDW technique to estimate values; and (3) map generation, which uses the CNN technique to predict flood events and generate flood hazard maps. The study area is Chiang Mai Province, Thailand. The generated hazard map covers 20,107 km2. There are 14 water-level telemetry stations and 16 rain gauge stations. The proposed model accurately predicts water level and rainfall, as demonstrated by the evaluation results (RMSE, MAE, and R2). The generated map has a 95.25% mean accuracy and a 97.25% mean F1-score when compared to the actual flood event. The framework enhances the accuracy and responsiveness of flood hazard maps to reduce potential losses before floods occur.

The supply chain demand forecasting model based on LSTM and multiple clustering techniques

The supply chain demand forecasting model based on LSTM and multiple clustering techniques

Environmental Sustainability in the Age of Deep Learning: Balancing Technological Advancement with Ecological Responsibility

The convergence of technological innovation, particularly deep learning (DL), with the importance of responsibility for the environment in achieving environmental sustainability. Deep learning (DL) offers to improve sustainability in different areas. This paper discusses DL breakthroughs and their applications in accomplishing SDGs, renewable energy, and environmental health. This discovers problems in reconciling technological innovation with caring for the environment by investigating the uses of deep learning in diverse areas and measuring their environmental implications. Furthermore, it explores CNN and LSTM techniques in Deep learning for incorporating environmental factors into the development, application, benefits and challenges of DL technologies to promote sustainability. This study aims to provide insights and recommendations for creating a harmonious link between technical advancement and ecological responsibility in the pursuit of environmental sustainability by conducting a comprehensive review of existing literature. There are three indicators: MAPE, RMSE, and MAE. The MAPE, RMSE, and MAE results are provided based on 7.5, 15, and 30 minutes, indicating low forecast accuracy.

FORECASTING THE FUTURE: A COMPARATIVE ANALYSIS OF ML AND DL MODELS IN SUPPLY CHAIN DEMAND PREDICTION

Supply chain demand forecasting is a strategic process aimed at predicting future customer demand for products within the broader framework of a supply chain. This involves forecasting the anticipated quantity of goods or services that customers will purchase and seamlessly integrating this insight into the overall supply chain management. The primary goal is to synchronize production, procurement, and distribution activities with expected demand, thereby optimizing inventory costs, minimizing instances of under stocking or overstocking, reducing waste, and ultimately enhancing overall supply chain efficiency. The emphasis is on leveraging advanced technologies, including deep learning techniques such as CNN, LSTM, CNN+LSTM, GRU, and machine learning techniques like Linear Regression and XGBoost, to achieve accurate predictions. By implementing these algorithms, businesses can construct a robust forecasting system capable of monitoring changes in demand and aligning supply accordingly. This proactive approach empowers retailers to enhance their inventory and planning efficiency, ultimately contributing to increased customer satisfaction. KEY WORDS: Machine Learning, Deep Learning, XG Boost, Linear Regression, CNN, LSTM, CNN+LSTM, GRU

Spatiotemporal Landsat-Sentinel-2 satellite imagery-based Hybrid Deep Neural network for paddy crop prediction using Google Earth engine

Rice is one of the predominant food sources to fulfill the dietary requirements of well-being in India. Therefore, accurate and timely paddy crop yield prediction is crucial to ensure the food security of the country. In this direction, the present study proposed a hybrid deep-learning method based on Conv-1D and LSTM layers using the classification-derived phenological with meteorological parameters for paddy crop yield prediction. The paddy crop classification has been conducted using high-resolution (10 m) multispectral imagery based on GPS coordinates collected during the paddy field visits to extract the phenological parameters for input to the prediction model. In this context, the efficiency of Random Forest, Naïve Bayes, SVM, and Gradient Tree boost classifiers was assessed. Furthermore, we have also analyzed the accuracy of Landsat-8, Sentinel-1 GRD, and Sentinel-2 satellite imagery in paddy crop classification based on area estimation. The Statistical Abstract of Haryana was utilized to validate the paddy crop area estimation and yield prediction. The classification outcomes showed that the Random Forest method attained the highest accuracy of 96.6 % compared to other GEE-based classifiers. The proposed Hybrid Deep learning approach achieved an RMSE value of 0.219 t/ha compared to CNN, LSTM, CNN-Bi-LSTM, and Regression techniques for crop yield prediction. The study conclusion highlighted that the sentinel-2 satellite imagery performed well and found that the proposed hybrid approach provided an alternative for paddy crop yield prediction.

Mechanical Framework for Geopolymer Gels Construction: An Optimized LSTM Technique to Predict Compressive Strength of Fly Ash-Based Geopolymer Gels Concrete.

As an environmentally responsible alternative to conventional concrete, geopolymer concrete recycles previously used resources to prepare the cementitious component of the product. The challenging issue with employing geopolymer concrete in the building business is the absence of a standard mix design. According to the chemical composition of its components, this work proposes a thorough system or framework for estimating the compressive strength of fly ash-based geopolymer concrete (FAGC). It could be possible to construct a system for predicting the compressive strength of FAGC using soft computing methods, thereby avoiding the requirement for time-consuming and expensive experimental tests. A complete database of 162 compressive strength datasets was gathered from the research papers that were published between the years 2000 and 2020 and prepared to develop proposed models. To address the relationships between inputs and output variables, long short-term memory networks were deployed. Notably, the proposed model was examined using several soft computing methods. The modeling process incorporated 17 variables that affect the CSFAG, such as percentage of SiO2 (SiO2), percentage of Na2O (Na2O), percentage of CaO (CaO), percentage of Al2O3 (Al2O3), percentage of Fe2O3 (Fe2O3), fly ash (FA), coarse aggregate (CAgg), fine aggregate (FAgg), Sodium Hydroxide solution (SH), Sodium Silicate solution (SS), extra water (EW), superplasticizer (SP), SH concentration, percentage of SiO2 in SS, percentage of Na2O in SS, curing time, curing temperature that the proposed model was examined to several soft computing methods such as multi-layer perception neural network (MLPNN), Bayesian regularized neural network (BRNN), generalized feed-forward neural networks (GFNN), support vector regression (SVR), decision tree (DT), random forest (RF), and LSTM. Three main innovations of this study are using the LSTM model for predicting FAGC, optimizing the LSTM model by a new evolutionary algorithm called the marine predators algorithm (MPA), and considering the six new inputs in the modeling process, such as aggregate to total mass ratio, fine aggregate to total aggregate mass ratio, FASiO2:Al2O3 molar ratio, FA SiO2:Fe2O3 molar ratio, AA Na2O:SiO2 molar ratio, and the sum of SiO2, Al2O3, and Fe2O3 percent in FA. The performance capacity of LSTM-MPA was evaluated with other artificial intelligence models. The results indicate that the R2 and RMSE values for the proposed LSTM-MPA model were as follows: MLPNN (R2 = 0.896, RMSE = 3.745), BRNN (R2 = 0.931, RMSE = 2.785), GFFNN (R2 = 0.926, RMSE = 2.926), SVR-L (R2 = 0.921, RMSE = 3.017), SVR-P (R2 = 0.920, RMSE = 3.291), SVR-S (R2 = 0.934, RMSE = 2.823), SVR-RBF (R2 = 0.916, RMSE = 3.114), DT (R2 = 0.934, RMSE = 2.711), RF (R2 = 0.938, RMSE = 2.892), LSTM (R2 = 0.9725, RMSE = 1.7816), LSTM-MPA (R2 = 0.9940, RMSE = 0.8332), and LSTM-PSO (R2 = 0.9804, RMSE = 1.5221). Therefore, the proposed LSTM-MPA model can be employed as a reliable and accurate model for predicting CSFAG. Noteworthy, the results demonstrated the significance and influence of fly ash and sodium silicate solution chemical compositions on the compressive strength of FAGC. These variables could adequately present variations in the best mix designs discovered in earlier investigations. The suggested approach may also save time and money by accurately estimating the compressive strength of FAGC with low calcium content.

Google Stocks Prediction by Machine Learning of RNN and LSTM Techniques

The objective of this study is to utilize a combined model of two algorithms, namely Long Short-Term Memory network and Recurrent Neural Network, to forecast the stock price of Google. Using Google stock price data from 2010 to 2022 as the training set and performed data preprocessing and feature engineering. This then build a deep neural network model consisting of multiple LSTM and RNN layers and train it by the backpropagation algorithm. During training, this paper employs an appropriate loss function and optimizer to minimize the prediction error. In conclusion, the performance of the model was assessed by employing Google stock price data from 2023 as a test set. By comparing the error between the actual stock price and the predicted value of the model, it can evaluate the accuracy and stability of the model. The experimental results show that the superposition model using LSTM and RNN algorithms can effectively predict the Google stock price with high accuracy and stability. This research presents a practical approach that can enhance the predictive capabilities of investors, financial institutions, and other related domains, enabling them to make well-informed investment decisions in the stock market.

Classification and Comparative Evaluation of Text and Emoji‐Based Tweets With Deep Neural Network Models

Emojis have become increasingly prevalent in today’s digital world, allowing individuals to convey a wide range of emotions, from uncomplicated to intricate, to a greater extent than previously. Consequently, emojis are being utilized in sentiment analysis and tailored marketing strategies. The ongoing research on conducting emotion detection on both tweets and a symbolic expression dataset sourced from Kaggle. Given that tweets are largely commentaries, we utilized two end‐to‐end sentence embedding models, the DistilBERT, USE‐Large3, and RoBERTa, which generate embeddings. These embeddings are further utilized for training with dense neural networks (NNs) and LSTM techniques. Remarkably, it was perceived that the text classification accuracy for both models was consistently high, hovering around 98%. However, when the validation set is constructed with that of symbolic expression or emojis not included in the training dataset, a significant drop in accuracy for both models, plummeting to 75%, had been observed. Additionally, a distributed training methodology is utilized as a substitute for the conventional single‐threaded model to enhance scalability. This approach resulted in a roughly 17% reduction in the runtime while maintaining accuracy. Lastly, in pursuit of explainable AI, the SHAP and LIME algorithms are employed to elucidate the model’s behavior and assess any potential biases in the dataset. The creative use of advanced deep NN techniques customized for the delicate complexities of hybrid‐data sentiment analysis indicates a significant leap forward. Our proposed work provides the critical gap in existing sentiment analysis methods, which primarily aimed at either text or emojis in isolation, thereby exploring more holistic understanding of sentiment in digital communications. Moreover, the application of explainable AI techniques, SHAP and LIME, to demystify model decisions emphasizes commitment to advancing transparent and trustworthy deep learning technologies in sentiment analysis.

A predictive model based on the LSTM technique for the maintenance of railway track system

A predictive model based on the LSTM technique for the maintenance of railway track system

Markov enhanced I-LSTM approach for effective anomaly detection for time series sensor data

Users could engage and interact with their immediate surroundings without effort in smart settings. The emergence of intelligent technologies along with software-based services has made this possible. It is clear that technical advancements have ushered in a new era for both computer processing and sensor technology, facilitating the concept of smart surroundings. Even though their implementation faces a number of obstacles, numerous expansive projects are working to advance their adoption. The problem of anomalies in the sensor data could result inappropriate decisions and could lead unamicable situations to the users. Many such algorithms are already there, which does not provide satisfactory predictions for the sensor data for the time series data. Time series anomaly detection problems are typically stated as finding outlier data points in comparison to some norm or typical signal. Better anomaly detection in time series data is provided by the proposed Markov and enhanced LSTM technique. The Markov model and the enhanced LSTM offer accurate predictions for extra- and short-term data, which is highly useful in situations involving intelligent environments. When compared to the KNN algorithm, the technique offers reduced MAE, RMSE, MSE and MAPE errors. The algorithm also performs better than other LSTM and RNN methods. The proposed algorithm provides 0.00047 reduced error in humidity data, 0.00416 reduced error in temperature and 0.01771 reduced MAE value in case of light intensity when comparing with the KNN algorithm.

Constructing the Public Opinion Crisis Prediction Model Using CNN and LSTM Techniques Based on Social Network Mining

Constructing the Public Opinion Crisis Prediction Model Using CNN and LSTM Techniques Based on Social Network Mining