Smart Count System Based on Object Detection Using Deep Learning

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

BackgroundMore than 79.2 million confirmed COVID-19 cases and 1.7 million deaths were caused by SARS-CoV-2; the disease was named COVID-19 by the World Health Organization. Control of the COVID-19 epidemic has become a crucial issue around the globe, but there are limited studies that investigate the global trend of the COVID-19 pandemic together with each country’s policy measures.ObjectiveWe aimed to develop an online artificial intelligence (AI) system to analyze the dynamic trend of the COVID-19 pandemic, facilitate forecasting and predictive modeling, and produce a heat map visualization of policy measures in 171 countries.MethodsThe COVID-19 Pandemic AI System (CPAIS) integrated two data sets: the data set from the Oxford COVID-19 Government Response Tracker from the Blavatnik School of Government, which is maintained by the University of Oxford, and the data set from the COVID-19 Data Repository, which was established by the Johns Hopkins University Center for Systems Science and Engineering. This study utilized four statistical and deep learning techniques for forecasting: autoregressive integrated moving average (ARIMA), feedforward neural network (FNN), multilayer perceptron (MLP) neural network, and long short-term memory (LSTM). With regard to 1-year records (ie, whole time series data), records from the last 14 days served as the validation set to evaluate the performance of the forecast, whereas earlier records served as the training set.ResultsA total of 171 countries that featured in both databases were included in the online system. The CPAIS was developed to explore variations, trends, and forecasts related to the COVID-19 pandemic across several counties. For instance, the number of confirmed monthly cases in the United States reached a local peak in July 2020 and another peak of 6,368,591 in December 2020. A dynamic heat map with policy measures depicts changes in COVID-19 measures for each country. A total of 19 measures were embedded within the three sections presented on the website, and only 4 of the 19 measures were continuous measures related to financial support or investment. Deep learning models were used to enable COVID-19 forecasting; the performances of ARIMA, FNN, and the MLP neural network were not stable because their forecast accuracy was only better than LSTM for a few countries. LSTM demonstrated the best forecast accuracy for Canada, as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 2272.551, 1501.248, and 0.2723075, respectively. ARIMA (RMSE=317.53169; MAPE=0.4641688) and FNN (RMSE=181.29894; MAPE=0.2708482) demonstrated better performance for South Korea.ConclusionsThe CPAIS collects and summarizes information about the COVID-19 pandemic and offers data visualization and deep learning–based prediction. It might be a useful reference for predicting a serious outbreak or epidemic. Moreover, the system undergoes daily updates and includes the latest information on vaccination, which may change the dynamics of the pandemic.

Object detection is a technology that deals with recognizing classes of objects and their location. It is used in many different areas, such as in face-detecting systems [16, 34, 37], surveillance tools [9], human-machine interfaces [17], and self-driving cars [18, 23, 25, 26, 30]. These days, deep learning object detection approaches have achieved significantly better performance than the classical feature-based algorithms. Darknet [31] is a deep learning object detection framework, which is well known for its fast speed and simple structure. Unfortunately, Darknet can only work with Nvidia CUDA [6] for accelerating its deep learning calculations. For this reason, users have only limited options of selecting appropriate graphic cards. Open computing language (OpenCL) [35], an open standard for cross-platform, parallel programming of heterogeneous systems, is available for the general hardware accelerators. However, many deep learning frameworks including Darknet have no support for OpenCL. In our previous paper, we presented OpenCL-Darknet [19], which transformed the CUDA-based Darknet into an open standard OpenCL backend. The original OpenCL-Darknet successfully showed its ability for the general graphics processing unit (GPU) hardware. However, it could not achieve competitive performance compared with the CUDA version, and it only supported a limited platform. In this study, we improved the performance of OpenCL-Darknet with several optimization techniques and added support for various architectures. We also evaluated OpenCL-Darknet not only in AMD R7 accelerated processing unit (APU) with OpenCL 2.0, but also in Nvidia GPU and ARM Mali embedded GPU with OpenCL 1.2 Profile. The evaluation using the standard object detection datasets showed that our advanced OpenCL-Darknet reduced the processing time by at most 50% on average for various deep learning object detection networks compared with our original implementation. We also showed that our OpenCL deep learning framework has competitiveness compared with the CUDA-based one.

Vegetation cover classification using mixed or low-resolution scalar images is challenging. Fortunately, recently deep learning object detection methods have emerged as a replacement to the conventional machine learning methods for the detection and classification of land use and land cover. This paper presents a deep learning object detection approach for land use and land cover detection using low/mixed resolution satellite images acquired from Google Earth satellite images. Google Earth images are accessible freely using the Google Earth Pro desktop application. Our dataset consists of two (02) classes (vegetation and non-vegetation) with a total of 450 labeled images captured from different parts of Pakistan. We present a comparison of the recent anchor-free object detection model YOLOX with the anchor-based object detection model YOLOR for solving real-time problems. The end-to-end differentiability, efficient GPU utilization, and absence of hand-crafted parameters make anchor-free models a compelling choice in object detection, and yet not been explored on Land cover classification using satellite images. Our experimental study shows that YOLOX delivers an overall accuracy of 83.50% on Vegetation and 86% on Non-Vegetation classes, which outperformed YOLOR by 30% on Vegetation classes and 34% on non-Vegetation classes for our dataset. We also show how an object detection system can be used for Vegetation and Non-Vegetation classification tasks, which can then be used for change monitoring and assisting in developing geographical maps using low/mixed resolution freely available satellite images.

Fractional-order models (FOMs) have been recognized as superior tools for capturing the complex electrochemical dynamics of lithium-ion batteries, outperforming integer-order models in accuracy, robustness, and adaptability. Parameter identification (PI) is essential for FOMs, as its accuracy directly affects the model’s ability to predict battery behavior and estimate critical states such as state of charge (SOC) and state of health (SOH). In this study, a hybrid deep learning approach has been introduced for FOM PI, representing the first application of deep learning in this domain. A simulation platform was developed to generate datasets using Sobol and Monte Carlo sampling methods. Five deep learning models were constructed: long short-term memory (LSTM), gated recurrent unit (GRU), one-dimensional convolutional neural network (1DCNN), and hybrid models combining 1DCNN with LSTM and GRU. Hyperparameters were optimized using Optuna, and enhancements such as Huber loss for robustness to outliers, stochastic weight averaging, and exponential moving average for training stability were incorporated. The primary contribution lies in the hybrid architectures, which integrate convolutional feature extraction with recurrent temporal modeling, outperforming standalone models. On a test set of 1000 samples, the improved 1DCNN + GRU model achieved an overall root mean square error (RMSE) of 0.2223 and a mean absolute percentage error (MAPE) of 0.27%, representing nearly a 50% reduction in RMSE compared to its baseline. This performance surpasses that of the improved LSTM model, which yielded a MAPE of 9.50%, as evidenced by tighter scatter plot alignments along the diagonal and reduced error dispersion in box plots. Terminal voltage prediction was validated with an average RMSE of 0.002059 and mean absolute error (MAE) of 0.001387, demonstrating high-fidelity dynamic reconstruction. By advancing data-driven PI, this framework is well-positioned to enable real-time integration into battery management systems.

This article uses machine learning techniques as fuzzy and neuro-fuzzy ANFISs, to develop and compare prediction models capable of relating pregnant women’s exposure to air pollutants, such as Nitrogen Dioxide and Particulate Matter, the mother’s age, and the number of prenatal consultations to the incidence of premature birth. In the current literature, studies can be found that relate prematurity to the exposure of pregnant women to NO2, O3, and PM10; to Toluene and benzene, mainly in the window 5 to 10 days before birth; and to PM10 in the week before birth. Both models used logistic regression to quantify the effects of pollutants as a result of premature birth. Datasets from Brazil—Departamento de Informatica do Sistema Único de Saúde (DATASUS) and Companhia Ambiental do Estado de São Paulo (CETESB)—were used, covering the period from 2016 to 2018 and comprising women living in the city of São José dos Campos (SP), Brazil. In order to evaluate and compare the different techniques used, evaluation metrics were calculated, such as correlation (r), coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and Mean Absolute Error (MAE). These metrics are widely used in the literature due to their ability to evaluate the robustness and efficiency of prediction models. For the RMSE, MAPE, MSE, and MAE metrics, lower values indicate that prediction errors are smaller, demonstrating better model accuracy and confidence. In the case of (r) and R2, a positive and strong result indicates alignment and better performance between the real and predicted data. The neuro-fuzzy ANFIS model showed superior performance, with a correlation (r) of 0.59, R2 = 0.35, RMSE = 2.83, MAPE = 5.35%, MSE = 8.00, and MAE = 1.70, while the fuzzy model returned results of r = 0.20, R2 = 0.04, RMSE = 3.29, MSE = 10.81, MAPE = 6.67%, and MAE = 2.01. Therefore, the results from the ANFIS neuro-fuzzy system indicate greater prediction capacity and precision in relation to the fuzzy system. This superiority can be explained by integration with neural networks, allowing data learning and, consequently, more efficient modeling. In addition, the findings obtained in this study have potential for the formulation of public health policies aimed at reducing the number of premature births and promoting improvements in maternal and neonatal health.

Drought is a complex and frequently occurring natural hazard in many parts of the world. Therefore, accurate drought forecasting is essential to mitigate its adverse impacts. This research has inferred the implication and the appropriateness of the extreme learning machine (ELM) algorithm for drought forecasting. For numerical evaluation, time series data of the Standardized Precipitating Temperature Index (SPTI) are used for nine meteorological stations located in various climatological zones of Pakistan. To assess the performance of ELM, this research includes parallel inferences of multilayer perceptron (MLP) and autoregressive integrated moving average (ARIMA) models. The performance of each model is assessed using root mean square error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), Kling‐Gupta efficiency (KGE), Willmott index (WI), and Karl Pearson’s correlation coefficient. Generally, graphical results illustrated an excellent performance of the ELM algorithm over MLP and ARIMA models. For training data of SPTI‐1, ELM’s best performance has observed at Chitral station (RMSE = 0.374, KGE = 0.838, WI = 0.960, MAE = 0.272, MAPE = 259.59, R = 0.93). For SPTI‐1 at Astore station, the numerical results are (RMSE = 0.688, KGE = 0.988, WI = 0.997, MAE = 0.798, MAPE = 247.35). The overall results indicate that the ELM outperformed by producing the smallest RMSE, MAE, and MAPE values and maximum values for KGE, WI, and correlation coefficient values at almost all the selected meteorological stations for (1, 3, 6, 9, and 12) month time scales. In summary, this research endorses the use of ELM for accurate drought forecasting.

Object detection and counting in video surveillance is a crucial task with various applications, yet it faces significant challenges due to dynamic environmental conditions such as varying illumination, occlusions, and noise. This research evaluates and compares the performance of two prominent background subtraction techniques: Gaussian Mixture Model (GMM) and Fuzzy Logic, for moving object segmentation and counting. The methodology involves image preprocessing (grayscale conversion, Gaussian blur, normalization), background model generation using the median of initial frames, object segmentation with both GMM and Fuzzy Logic enhanced by Region of Interest (ROI) and morphological operations, and object tracking using a simple Centroid Tracker. Performance was evaluated using segmentation metrics (Precision, Recall, F1-score, Percentage of Wrong Classifications (PWC)) and counting accuracy metrics (Mean Absolute Error (MAE), Accuracy). Results indicate that GMM achieved a slightly better F1-score (0.23 vs 0.18) for segmentation, while Fuzzy Logic demonstrated marginally higher Precision (0.37 vs 0.33). For object counting, both methods yielded an identical average MAE of 0.94, with Fuzzy Logic showing a slightly higher average accuracy (9.88% vs 9.41%). The study highlights that both GMM and Fuzzy Logic are viable for moving object detection and counting, each with distinct strengths and weaknesses, but performance remains sensitive to dynamic scene conditions. The dataset utilized, CDnet's "night videos" category, specifically the "busyBoulvard" sequence, presented unique challenges due to low light and dense traffic, which were central to the evaluation.

Analysis of load plays an important role in the operation of modern power systems due to its highly intermittent nature. This manuscript proposes the best approach by comparing results of Hold out, Cross and Re-Substitution validation from hyperparameter tuned Short Term Load Forecasting (STLF). Tree, Neural Network and GPR (Gaussian Process Regression) are three stochastic regression methods used. Each validation procedure is compared with every considered regression method, leading to 9 such combinations. Each combination is analysed with statistical parameters like RMSE (Root Mean Square Error), R Squared, MSE(Mean Square Error), MAE (Mean Absolute Error) and training time. The best approach is further optimised by modifying hyper parameters using Bayesian, Grid Search, and Random Search and most suitable method is proposed. The simulations are performed in Python and MATLAB platforms. The best combination for computation of STLF is K-fold validation with Tree Regression The statistical parameters obtained from the combination are RMSE, R Squared, MSE, MAE and training time of 0.077, 0.88, 0.0059, 0.046, 1.2 respectively. The best method for hyper-parameter tuning is found out to be Grid search with a reduced MSE of 0.0023.

The rapid development of the aviation industry has increased the need for accurate airline ticket price prediction, benefiting both airlines and consumers. This study evaluates the performance of the Random Forest model before and after Bayesian Optimization to enhance predictive accuracy. Using a dataset from "Ease My Trip," the model is assessed with Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared Score (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>). Hyperparameter Tuning is performed using Bayesian Optimization to optimize model parameters. Results indicate that tuning improves the model’s ability to capture data patterns, enhancing predictive performance. The untuned model achieved an MSE of 4,910,040.02, RMSE of 2,215.86, MAE of 829.00, and an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Score of 0.9903918. After tuning, optimal parameters (max_depth: None, min_samples_leaf: 1, min_samples_split: 5, n_estimators: 100) improved MSE to 4,815,187.66, RMSE to 2,194.35, and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Score to 0.9905774, though MAE slightly declined to 850.42. This study highlights the effectiveness of Hyperparameter Tuning in refining model performance, offering valuable insights for airline pricing strategies and consumer decision-making. The findings suggest that optimized models can enhance revenue management for airlines and improve fare forecasting for passengers. Future research could explore alternative methods for more efficient tuning, such as Early Stopping method with Bayesian Optimization.

Maize is a strategic commodity in Indonesia’s national food system, yet traditional yield-prediction methods based on statistical or survey approaches often fail to capture the nonlinear and dynamic relationships among agronomic, climatic, and socio-economic variables. Accurate forecasting remains essential for supporting food self-sufficiency and climate-resilient agricultural planning. To address these challenges, this study proposes SMART-JAGUNG, a machine learning–based maize yield prediction system employing three ensemble and regression models: Random Forest (RF), Support Vector Regression (SVR), and eXtreme Gradient Boosting (XGBoost). The dataset comprises five years of maize production data from the Indonesian Central Bureau of Statistics (BPS), along with auxiliary variables including rainfall, temperature, NDVI, seed type, and fertilizer use. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination before and after hyperparameter tuning with GridSearchCV. Results indicate that RF achieved the best performance before tuning (MAE = 36,310.53; RMSE = 95,343.05; = 0.9758), followed closely by XGBoost, while SVR consistently underperformed. Although post-tuning performance slightly decreased, the predicted-versus-actual visualization confirmed the robustness of RF and XGBoost for non-extreme data. Overall, SMART-JAGUNG demonstrates strong potential as a reliable, data-driven decision-support tool for precise maize yield estimation, contributing to sustainable food security and national self-sufficiency policies.

With the in-depth implementation of China’s “National Strategy for Building a Strong Transportation Network,” the scale of expressway construction has continued to expand. As a result, the number of high-fill and deep-cut subgrade projects under complex geological conditions has increased significantly, leading to a surge in landslide-related issues. Consequently, accurate prediction of slope displacement is of critical importance for early warning and prevention of landslide disasters. This study proposes a hybrid prediction model, VMD-MPA-LSSVM-LSTM (VMLL), which integrates Variational Mode Decomposition (VMD), Marine Predators Algorithm (MPA), Least Squares Support Vector Machine (LSSVM), and Long Short-Term Memory (LSTM) networks. Using monitoring data from the high-fill embankment slope at Hongtuyao as the research subject, the VMLL model is employed to predict slope displacement based on small-sample data. The objective is to provide a more accurate method for early warning of slope displacement. Firstly, the original monitoring data are decomposed into trend displacement components and fluctuation displacement components using Variational Mode Decomposition (VMD). Subsequently, the trend component and the fluctuation component are predicted using Least Squares Support Vector Machine (LSSVM) and Long Short-Term Memory (LSTM) networks, respectively. Finally, the Marine Predators Algorithm (MPA) is employed to optimize the hyperparameters of the predictive models. Based on this framework, a VMLL-based slope displacement prediction model is constructed. To verify the superiority of the VMLL model, a comparative analysis was conducted against LSSVM, LSTM, and the VMD-LSSVM-LSTM models. The results demonstrate that the VMLL model achieves the highest prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.4022%, a Mean Absolute Error (MAE) of 0.016 mm, a Root Mean Square Error (RMSE) of 0.0206 mm, a coefficient of determination (R²) of 94.08%, and a Variance Accounted For (VAF) of 96.5%. Compared with the other three models, the VMLL model reduces the MAPE, MAE, and RMSE by 30.41–67.62%, 30.38–67.40%, and 27.32–71.00%, respectively. Meanwhile, it improves the R² and VAF by 5.95–217.51% and 0.38–11.48%, respectively. These improvements clearly demonstrate that the VMLL model outperforms the other models, indicating its significant advantage over single prediction models. Furthermore, three additional datasets were used to evaluate the model’s performance. The average values of the performance evaluation metrics for these datasets were 0.6207% (MAPE), 0.0238 mm(MAE), 0.0273 mm(RMSE), 90.33%(R²), and 96.81%(VAF), respectively. These results demonstrate the high accuracy and strong robustness of the proposed model in predicting both horizontal displacement and vertical settlement of slopes, providing a reliable methodological framework for slope stability assessment and landslide disaster early warning.

Evaluation of artificial neurocomputing algorithms and their metacognitive robustness in predictive modeling of fuel consumption rates during tillage

Advances in industrial digital technologies have led to an increasing volume of data generated from industrial bioprocesses, which can be utilised within data-driven models (DDM). However, data volume and variability complications make developing models that captures the underlying biological nature of the bioprocesses challenging. In this study, a framework for developing data-driven models of bioprocesses is proposed and evaluated by modelling an industrial bioprocess, which treats industrial or agrifood wastewaters whilst simultaneously generating bioenergy. Six models were developed to predict the reduction in chemical oxygen demand from the wastewater by the bioprocess and statistically evaluated using both testing data (randomly partitioned data from the model development) and unseen data (new data not used during the model development). The statistical error metrics employed were the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The stacked neural network model was best able to model the bioprocess, having the highest accuracy on the testing data (R2: 0.98; RMSE: 1.29; MAE: 2.27; MAPE: 4.08) and the unseen data (R2: 0.82; RMSE: 2.57; MAE: 1.75; MAPE: 3.68). Data visualisation is used to observe (or confirm) whether new data points are within the model boundaries, helping to increase confidence in the model’s predictions on future data.

Tomatoes are among the world’s most significant vegetables, both in terms of production and consumption. Harvesting takes place in tomato production when the important quality attribute of total soluble solids content reaches its maximum possible level. Tomato total soluble solids content (TSS) is among the most crucial attribute parameters for assessing tomato quality and for tomato commercialization. Determination of total soluble solids content by conventional measurement methods is both destructive and time-consuming. Therefore, the tomato processing industry needs a rapid identification method to measure total soluble solids content (TSS). In this study, we aimed to estimate how much soluble solids there are in beef tomato fruit by Artificial Neural Networks (ANN) and Multiple Linear Regression (MLR) methods. The models were assessed using the Coefficient of Determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics. The training data set results of the MLR model established to estimate the amount of brix in tomato fruit, calculated as MAE: 0.2349, RMSE: 0.3048, R2: 0.8441, and MAPE: 5.5368, while, according to the ANN model, MAE: 0.0250, RMSE: 0.031, R2: 0.9982 and MAPE: 0.5814. According to the metric outcomes, the ANN-based model performed better in both the training and testing parts.