Crop Yield Prediction of Indian Districts Using Deep Learning

Effective prediction of electric power consumption is vital for accurate energy management systems, particularly in growing urban regions. Conventional statistical techniques usually fail to capture the complicated patterns and non-linear tendencies in time-series energy data. The development of deep learning models has demonstrated encouraging findings in a variety of prediction tasks. Therefore, this paper concentrates on the application of diverse deep learning models, comprising One-dimensional Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional LSTM, and a hybrid model for power consumption prediction based on a dataset gathered from January 1, 2017, until January 1, 2018, in Tetouan, Morocco. These applied models were assessed utilizing diverse robust assessment metrics, and the findings demonstrated that the hybrid model (One-dimensional CNN with LSTM) reached superior performance with a Mean Squared Error (MSE) of 0.42548, Root-MSE of 0.65228, Mean Absolute Error (MAE) of 0.54395, and Median-AE of 0.51401, surpassing the other standalone and relevant models. The attained findings emphasize the merits of incorporating recurrent and convolutional structures to obtain more effective and accurate predictions of energy consumption time series

This study evaluates the performance of traditional statistical methods, specifically the Seasonal Autoregressive Integrated Moving Average (SARIMA), in comparison to advanced deep learning models—Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN)—for wind speed forecasting across various regions in Saudi Arabia: Al-Jouf, Abha, Al-Ahsa, and Al-Dawadami. The historical wind speed dataset covering the year 2018 was utilized, with data preprocessing conducted using the Exploratory Data Analysis (EDA) method to ensure consistency and quality. The models were assessed based on three primary error metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Square Error (RMSE). Results show that CNN consistently outperforms SARIMA and the other deep learning models, particularly when forecasting stable wind speed patterns. LSTM demonstrates an ability to handle fluctuating wind speeds effectively, while BiLSTM offers advantages in capturing complex bidirectional temporal dependencies. On the other hand, SARIMA generally exhibits lower performance compared to deep learning approaches. The superior performance of CNN is likely attributed to its strength in local feature extraction and handling spatial patterns effectively, which are beneficial for short-term forecasting. These findings provide valuable insights into model selection for wind energy forecasting and can contribute to optimizing renewable energy integration and planning strategies. Future work may explore hybrid model approaches to further enhance forecasting accuracy.

Industrial robots are widely used in critical tasks such as assembly, welding, and material handling as core components of modern manufacturing systems. For the reliable operation of these systems, early and accurate detection of execution failures is crucial. In this study, a comprehensive comparison of machine learning and deep learning methods is conducted for the classification of robot execution failures using data acquired from force-torque sensors. Three different feature engineering approaches are proposed. The first is a Baseline approach that includes 90 raw time-series features. The second is the Domain-6 approach, which consists of 6 basic statistical features per sensor (36 in total). The third is the Domain-12 approach, which comprises 12 comprehensive statistical features per sensor (72 in total). The domain features include the mean, standard deviation, minimum, maximum, range, slope, median, skewness, kurtosis, RMS, energy, and IQR. In total, ten classification algorithms are evaluated, including eight machine learning methods and two deep learning models: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (KNN), Artificial Neural Network (ANN), Naive Bayes (NB), Decision Trees (DT), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM-LGBM), as well as a One-Dimensional Convolutional Neural Network (CNN-1D) and Long Short-Term Memory (LSTM). For traditional machine learning algorithms, 5 × 5 nested cross-validation is used, whereas for deep learning models, 5-fold cross-validation with a 20% validation split is employed. To ensure statistical reliability, all experiments are repeated over 30 independent runs. The experimental results demonstrate that feature engineering has a decisive impact on classification performance. In addition, regardless of the feature set, the highest accuracy (93.85% ± 0.90) is achieved by the Naive Bayes classifier using the Baseline features. The Domain-12 feature set provides consistent improvements across many algorithms, with substantial performance gains. The results are reported using accuracy, precision, recall, and F1-score metrics and are supported by confusion matrices. Finally, permutation feature importance analysis indicates that the skewness features of the Fx and Fy sensors are the most critical variables for failure detection. Overall, these findings show that time-domain statistical features offer an effective approach for robot failure classification.

This study introduces a deep learning-based framework for portfolio optimization tailored to different investor risk preferences. We combine two prediction models, Long Short-Term Memory (LSTM) and One-Dimensional Convolutional Neural Network (1D-CNN), with three portfolio frameworks: Mean-Variance with Forecasting (MVF), Risk Parity Portfolio (RPP), and Maximum Drawdown Portfolio (MDP). Each framework represents a distinct risk profile: return-seeking, moderate-risk and conservative. The dataset is constructed from daily returns of VN-100 stocks in Vietnam, covering the period from 2017 to 2024. Forecasts from the deep learning models are integrated into each optimization approach. Results from the 2023–2024 test period showed that LSTM outperforms 1D-CNN in both accuracy and stability. Portfolios using LSTM achieved better performance. LSTM+MVF delivers the best risk-adjusted returns, while LSTM+MDP achieves the highest total return. The study highlights the value of aligning predictive models with appropriate optimization strategies for improved investment outcomes. Future work may include other asset classes, transaction cost modeling, and dynamic rebalancing. Combining deep learning with macroeconomic or alternative data could also improve forecasting and portfolio outcomes.

The Internet of Things (IoT) holds transformative potential in fields such as power grid optimization, defense networks, and healthcare. However, the constrained processing capacities and resource limitations of IoT networks make them especially susceptible to cyber threats. This study addresses the problem of detecting intrusions in IoT environments by evaluating the performance of deep learning (DL) models under different data and algorithmic conditions. We conducted a comparative analysis of three widely used DL models—Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Bidirectional LSTM (biLSTM)—across four benchmark IoT intrusion detection datasets: BoTIoT, CiCIoT, ToNIoT, and WUSTL-IIoT-2021. Each model was assessed under balanced and imbalanced dataset configurations and evaluated using three loss functions (cross-entropy, focal loss, and dual focal loss). By analyzing model efficacy across these datasets, we highlight the importance of generalizability and adaptability to varied data characteristics that are essential for real-world applications. The results demonstrate that the CNN trained using the cross-entropy loss function consistently outperforms the other models, particularly on balanced datasets. On the other hand, LSTM and biLSTM show strong potential in temporal modeling, but their performance is highly dependent on the characteristics of the dataset. By analyzing the performance of multiple DL models under diverse datasets, this research provides actionable insights for developing secure, interpretable IoT systems that can meet the challenges of designing a secure IoT system.

Water quality prediction (WQP) plays an essential role in water quality management for aquaculture to make aquaculture production profitable and sustainable. In this work, we propose hybrid deep learning (DL) models, convolutional neural network (CNN) with the long short-term memory (LSTM) and gated recurrent unit (GRU) for aquaculture WQP. CNN can effectively fetch the aquaculture water quality characteristics, whereas GRU and LSTM can learn long-term dependencies in the time series data. We conduct experiments using the two different water quality datasets and present an extensive study on the impact of hyperparameters on the performance of the proposed hybrid DL models. Furthermore, the performance of hybrid CNN-LSTM and CNN-GRU models are compared with different baseline LSTM, GRU and CNN DL models and also with attention-based LSTM and attention-based GRU DL models. The results show that the hybrid CNN-LSTM outperformed all other models in terms of prediction accuracy and computation time.

Renewable energy (RE) plays a critical role in mitigating climate change and ensuring energy security globally. As the adoption of RE technologies continues to grow, accurate forecasting of renewable energy consumption has become increasingly important for grid planning and integration. This paper provides a comprehensive review of the key factors influencing renewable energy consumption and the application of machine learning and deep learning models for forecasting RE consumption. The study examines various socioeconomic, demographic, and environmental variables that have been found to impact the demand and usage of renewable energy sources such as solar, wind, and hydropower. Factors like GDP, population, energy prices, government policies, and weather conditions are discussed in detail for their influence on RE consumption patterns. The paper also analyzes how technological advancements, consumer behavior, and energy efficiency measures can shape renewable energy demand. Furthermore, the paper evaluates the performance of various machine learning techniques, which have been done in various research from 2020 to 2024, including artificial neural networks, support vector machines, random forests, gradient boosting, and deep learning models such as long short-term memory (LSTMs) and convolutional neural networks (CNNs), in forecasting renewable energy consumption. The study analyzes the strengths, limitations, and accuracy of these models based on case studies across residential, commercial, and industrial sectors. The findings indicate that deep learning models, particularly LSTMs and CNNs, have outperformed traditional machine learning techniques in renewable energy consumption forecasting. These deep learning models are able to capture the complex nonlinear relationships and temporal dependencies inherent in RE consumption data, leading to higher accuracy and better generalization performance.

Small and Medium-sized Enterprises (SMEs) in Sri Lanka are increasingly turning to social media to gain insights into consumer preferences; however, they frequently lack sophisticated analytical tools to derive actionable insights. This research introduces a hybrid deep learning framework aimed at sentiment and emotion analysis specifically for the Sri Lankan cake sector. Customer reviews and social media comments were gathered and processed through various methods including text cleaning, emoji translation, stopword elimination, tokenization, and sequence padding. Several deep learning models— Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Units (GRU) were assessed, along with hybrid models that combined CNN and BiLSTM with GPT-2 embeddings. The CNN+GPT-2 model achieved the highest accuracy in sentiment classification at 96.14%, while BiLSTM performed best in emotion classification with an accuracy of 91.57%. In terms of trend forecasting, Long Short-Term Memory (LSTM) outshone both SARIMA and Prophet, yielding the lowest error metrics and the most reliable sentiment predictions. These results underscore the potential of hybrid deep learning and transformer-based models to effectively capture complex consumer sentiments and provide SMEs with practical, AI-driven insights. This study is among the first to implement such hybrid NLP models within a localized Sri Lankan context, presenting a scalable approach for business intelligence and informed decision-making.

In recent years, Deep Learning (DL) models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM), have been widely used for Human Activities Recognition (HAR). They have achieved considerable performance improvements over classical Machine Learning (ML) approaches due to their excellent feature representation capabilities. Simple human activities are performed in sequential order with no overlaps or concurrent actions. The paucity of labeled training activity samples, high computational cost, and system resource requirements of deep learning architectures compared to lightweight models are some of the research challenges confronting the HAR community. We framed the lightweight DL-based CNNs, RNNs, and LSTM model for HAR to tackle these research challenges. The RNNs and LSTM have single layers with softmax activation functions, whereas the one-dimensional CNNs have two convolutional and single max-pooling layers. To evaluate the performance of our models, we used the publicly available benchmark WISDM experimental dataset, which includes the reading of six activities (walking, jogging, upstairs, downstairs, sitting, and standing) performed by 36 participants using a single accelerometer sensor. The experimental result illustrates the efficacy of our models in activity recognition, demonstrating that they attain higher accuracy while being computationally efficient.

The stock market may be unpredictable; understanding when to purchase and sell can greatly assist businesses and individuals in maximizing profits and minimizing losses. Many companies have previously modified time-series analysis, a data mining technique, to forecast stock price movement. The idea of textual data mining has recently come up in debates about stock market forecasts. In this study, five of the largest firms’ historical stock prices were used to train two deep learning models—long short-term memory (LSTM) and one-dimensional convolutional neural network (1D CNN), then the results of all the models were compared. To connect price value fluctuations with the general public, sentiment scores were offered in addition to stock price values by employing natural language processing techniques (TextBlob) to tweets.

A CNN encoder decoder LSTM model for sustainable wind power predictive analytics

BackgroundTimely and non‐invasive prediction of amyloid status are pivotal in Alzheimer’s disease (AD) diagnostics. This research leverages T1 MRI images to predict amyloid positivity or negativity, offering an economical and less invasive alternative to amyloid PET scans. Using the comprehensive TRAID dataset from McGill University, the study evaluates a spectrum of cognitive conditions including AD, atypical AD, Cognitively Normal (CN), Mild Cognitive Impairment (MCI), MCI not due to AD, Suspected Non‐Alzheimer’s Pathophysiology (SNAP), and Vascular MCI (VMCI).MethodThe study involved 588 subjects, representing a cross‐section of cognitive states. A VGG16‐based feature extraction process was meticulously applied to T1 MRI images to capture complex biomarkers of AD. These high‐dimensional features, alongside demographic data, were harnessed to train two deep learning models: a Long Short‐Term Memory (LSTM) model and a Convolutional Neural Network (CNN) ensemble model. To prevent overfitting and data leakage, the models employ 10‐fold StratifiedKFold validation and early stopping, alongside regularization techniques like dropout and batch normalization. Data preprocessing is contained within StratifiedKFolds, and an independent test set is used for unbiased evaluation. The predictive accuracy was scrutinized using a range of metrics, including accuracy, F1‐score, recall, precision, and ROC AUC on the validation sets.ResultThe LSTM model reported average validation metrics with an accuracy of 70.88%, F1‐score of 70.64%, recall of 78.07%, precision of 70.88%, and a ROC AUC of 71.86%. The CNN ensemble model showed a marked improvement, particularly in its recall of 88.00% and ROC AUC of 82.47%, alongside an accuracy of 76.27% and F1‐score of 75.86% (Figure 1 and 2). However, in another model, it was the CNN ensemble model that demonstrated remarkable predictive power, achieving an ROC AUC of 88% within the AD spectrum (CN, MCI, and AD subjects), indicating a high degree of predictive power in classifying amyloid status.ConclusionThis study underscores the CNN ensemble model’s robustness in predicting amyloid status across a broad spectrum of cognitive conditions, with particular emphasis on its application in high‐sensitivity clinical settings. These findings represent a significant advancement in the field of AD diagnostics, contributing to the development of more accessible and cost‐effective prognostic techniques.

Tracking structural behavior is critically important to reduce maintenance and repair costs. Structural Health Monitoring (SHM) aims to evaluate the structural integrity, detect damage or abnormalities, and estimate overall safety. The integration of Machine Learning techniques has significantly advanced SHM by enabling the identification of deterioration patterns through sensor data analysis. This study focuses on classifying different vibration patterns recorded under various excitation scenarios (ambient, transient, and forced) using sensors installed directly on a 3-DoF structure. The proposed approach used a two-dimensional convolutional neural network (2D-CNN) trained on vibration image patterns generated from vibration signal scalogram images. To address dataset imbalance, stratified 5 × 3 Nested cross-validation and multiple performance metrics were computed to ensure robust evaluation. The proposed method was compared with single-sensor scalogram approaches and baseline models, including Support Vector Machines (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), One-Dimensional Convolutional Neural Network (1D-CNN), and Long Short-Term Memory (LSTM) models, incorporating class-weighting strategies. Additionally, the contribution of the Total Energy Delivered by Sensor (TES) feature was evaluated for SVM, RF, and XGBoost models. The 2D-CNN model achieved superior performance in identifying excitation types associated with structural dynamic behavior, highlighting its effectiveness for structural vibration pattern recognition in SHM applications.

The purpose of the study was to train and compare machine learning (ML) and deep learning (DL) models for long-term forecasting of minimum daily temperatures (frosts) - a key agrometeorological risk affecting crop productivity. The study was based on data from weather stations in St. Petersburg and the Leningrad region. To predict the year ahead, which aligns with the needs of operational agricultural production planning (sowing dates, harvest timing, protective measures), 8 methods were used: ForecasterAutoreg, Random Forest, Support Vector Regression (SVR), XGBoost, Convolutional Neural Network (CNN), SimpleRNN, Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM). The analysis was carried out on two datasets: for the periods 1936-2024 and 1881-1995. The quality of the models was assessed using the metrics MAE, MSE, RMSE, R2 and adjusted R2. The LSTM model showed the most accurate results on the main dataset (1936-2024): MAE 2.9, MSE 14.661, R2 0.789. The SVR method (MAE 3.461, R2 0.775) demonstrated the best metrics based on archived data (1881-1995). It has been established that DL models (LSTM, GRU, CNN) generally outperform classical ML methods based on modern data. The LSTM method is recognized as the most effective for integration into precision farming systems and agricultural monitoring in the region for the advance planning of agrotechnological measures to protect crops from frost, optimization of crop rotation systems, and minimization of crop loss risks.

This paper presents an innovative approach for enhancing power output forecasting of Photovoltaic (PV) power plants in dynamic environmental conditions using a Hybrid Deep Learning Model (DLM). The hybrid DLM employs a synergy of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Bidirectional LSTM (Bi-LSTM), effectively capturing spatial and temporal dependencies within weather data crucial for accurate predictions. To optimize the DLM’s performance efficiently, a unique Kepler Optimization Algorithm (KOA) is introduced for hyperparameter tuning, drawing inspiration from Kepler’s laws of planetary motion. By leveraging KOA, the DLM attains optimal hyperparameter configurations, elevating power output prediction precision. Additionally, this study integrates Transductive Transfer Learning (TTL) with the deep learning models to enhance resource efficiency. By leveraging knowledge gained from previously learned tasks, TTL enables the DLM to improve its forecasting capabilities while minimizing resource utilization. Datasets encompassing environmental parameters and PV plant-generated power across diverse sites are employed for DLM training and testing. Three hybrid models, amalgamating KOA, CNN, LSTM, and Bi-LSTM techniques, are introduced and evaluated. Comparative assessment of these models across distinct PV sites yields insightful observations. Performance evaluation, focused on short-term PV power forecasting, underscores the hybrid DLM’s superiority over individual CNN and LSTM models. This hybrid approach achieves remarkable accuracy and resilience in predicting power output under varying weather conditions, showcasing its potential for efficient PV power plant management.