Evaluation of Various Error Metrics in K-NN Image Classification: A Case Study on Egg Image Processing

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.

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.

Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series

The road infrastructure serves as a linchpin for both developed and developing nations, requiring efficient management strategies to uphold this vital mode of transportation. Long-term pavement management agencies are tasked with continuously monitoring and maintaining road pavements, relying on databases to secure critical data. Pavement condition index (PCI) is a pivotal metric for assessing pavement health, quantifying distress severity and structural integrity. Manual PCI assessment is laborious and error-prone, especially for extensive road networks. Recent technological advancements, particularly in Artificial Intelligence (AI), have revolutionised pavement management through predictive modelling. In this study, supervised machine learning algorithms are leveraged, including Random Forest Regressor, M5 Prime Model Tree Algorithm, Decision Tree, Multiple Linear Regression (MLR), Gradient Boosting Regressor, K-Nearest Neighbours (KNN) and Support Vector Machine Regressor (SVMR) to predict PCI, optimise rehabilitation strategies and prioritise maintenance efforts. The dataset utilised in this study comprises 237 roads with 9576 sample units covering various distress types, extents and severity levels crucial for PCI determination. The data undergoes rigorous training, testing and validation across all the selected algorithms. Model performance is evaluated using key metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Coefficient of Determination (R 2) and Mean Absolute Percentage Error (MAPE). Additionally, the Kruskal–Wallis test and t-test are employed to assess the statistical significance of the results. Our findings highlight the superior performance of the Random Forest Regressor and M5P models, with R 2 values of 0.96 and 0.95, respectively. These models outshine others, showcasing their effectiveness in PCI prediction. Conversely, the results of Gradient Boosting Regressor, KNN and SVMR models exhibit inconsistency and unreliability in PCI prediction. This study underscores the transformative potential of machine learning algorithms in pavement management, emphasising strategies to mitigate the limitations of manual methods in PCI determination.

Investing in the Malaysian stock market can be overwhelming due to the abundance of options, which necessitates informed decision-making to navigate the volatile market. This study addresses a common problem faced by investors venturing into the stock market, where instability and fluctuations pose significant risks, leading to financial losses stemming from inadequate knowledge about suitable stocks for investment. Unlike many studies that focus on long-term forecasting methods, this research adopts the Geometric Brownian Motion (GBM) model for short-term investment analysis. The study aims to identify the most effective volatility measurement model, develop a forecasting model using GBM based on the chosen volatility model, and evaluate the accuracy of the GBM model using Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Deviation (MAD). Four volatility models, which include simple, log, high-low, and high-low-closed volatility are analysed to determine the most effective volatility measurement model. Four months of daily stock data were collected to ensure accuracy excluding factors such as seasonality, politics, natural disasters, and wars. Findings indicate that the simple volatility model is the most suitable for forecasting stock market trends using the GBM model, demonstrating high accuracy based on MSE, MAPE and MAD. These results suggest that employing the simple volatility model within GBM model can offer a practical and accurate approach for short-term market analysis in Malaysia, potentially aiding investors in mitigating risks and optimizing their trading strategies.

The purpose of this study is to apply technical analysis e.g. Sutte Indicator in Stock Market that will assist in the investment decision-making process to buy or sell of stocks. This study took data from Apple Inc. which listed in the NasdaqGS in the period of 1 January 2008 to 26 September 2016. Performance of the Sutte Indicator can be see with comparison with other technical analysis e.g. Simple Moving Average (SMA) and Moving Average Convergence/Divergence (MACD). Comparasion of reliability of prediction from Sutte Indicator, SMA, and MACD using the mean of square error (MSE), mean absolute deviation (MAD), and mean absolute percentage error (MAPE).

Stock is one of the investment instruments that many investors choose, both short and long term. Meanwhile, the stock price index is an essential indicator for investors deciding whether to buy, sell, or hold the stock. This study aims to determine what methods are suitable for predicting the Stock Price Index of Construction Companies Listed on the Indonesia Stock Exchange in 2015-2019. By selecting a model that matches the existing time series data, to evaluate the results of the forecasting, the researcher uses a measure of accuracy with Mean Absolute Percentage Error (MAPE), Mean Absolute Deviation (MAD), and Mean Squared Deviation (MSD). This type of research is a quantitative study with a research population of 16 companies listed on the Indonesia Stock Exchange. Only four samples were used that fit the specified criteria, and only five years of research were conducted, namely in 2015 to 2019. data can be seen from historical data or actual data and tested using Minitab software version 19. The results showed that Double Exponential Smoothing (Holt's) and Double Moving Average Method could be used to forecast the Construction Company Stock Price Index. Obtaining the smallest error value of the four construction companies, namely WSKT company with MAPE = 7.3, MAD = 148.8, and MSD = 40506.0 for the Holt'sand MAPE method = 5.3, MAD = 110.1, and MSD = 22006.9 for the Double Moving Average method.

The prediction and modeling of stock price movements have been shown to possess considerable economic significance within the finance sector. Recently, a range of artificial intelligence methodologies, encompassing both traditional machine learning and deep learning approaches, have been introduced for the purpose of forecasting stock price fluctuations, yielding numerous successful outcomes. Nonetheless, the identification of effective features for predicting stock movements is considered a complex challenge, primarily due to the non-linear characteristics, volatility, and inherent noise present in financial data. This study introduces an innovative Deep Convolutional Transformer (DCT) model that amalgamates convolutional neural networks, Transformers, and a multi-head attention mechanism. It features an inception convolutional token embedding architecture alongside separable fully connected layers. Experiments conducted on the NASDAQ, Hang Seng Index (HSI), and Shanghai Stock Exchange Composite (SSEC) employ Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), accuracy, and Matthews Correlation Coefficient (MCC) as evaluation metrics. The findings reveal that the DCT model achieves the highest accuracy of 58.85% on the NASDAQ dataset with a sliding window width of 30 days. In terms of error metrics, it surpasses other models, demonstrating the lowest average prediction error across all datasets for MAE, MSE, and MAPE. Furthermore, the DCT model attains the highest MCC values across all three datasets. These results suggest a promising capability for classifying stock price trends and affirming the DCT model’s superiority in predicting closing prices.

Stock price forecasting provide valuable insight to the investor to facilitate well-informed investment decision making. The aim of this study is to examine the calendar anomalies i.e. DOW in Pakistan stock exchange though Artificial intelligence techniques. For this purpose, Support vector machine (SVM), Decision Tree (DT) and Artificial Neural Network is used to forecast the daily stock prices. The daily stock prices data of KSE100 index ranges from May,1994 to August 2023 is used as out variable while stock open, close, high and low prices are used as features/input variables. The training and testing ratio was 80:20 means 80% of the data was used in training and the 20% values were utilized for forecasting. To evaluate the accuracy of predictions, mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE)/mean absolute deviation (MAD), mean absolute percent error (MAPE), and R-squared (R^2) are taken as decision criteria. The daily forecasted stock prices show the almost zero error on Tuesday, Wednesday and Thursday in SVM. Decision tree show very low error in actual and forecasted stock prices. Therefore, it is concluded that, the DOW anomalies exist in KSE100 index of PSX. Results show that, SVM can better predict the stock prices than DT and ANN. These results conclude that the forecasted stock prices are much closer to actual daily stock price means the daily stock prices can be forecast in KSE100 index. These finding contradicts the Efficient market hypothesis and conclude that the Pakistan stock exchange (PSX) is weak-form inefficient market.

Silicoaluminophosphates (SAPOs) are structurally diverse materials widely used in separation, catalysis, and environmental applications. In this study, a simple post-synthetic method is used to create a hybrid porous material by immobilizing a copper(II) complex onto base-functionalized SAPO molecular sieves. The copper complex, synthesized using 2,9-dimethyl-1,10-phenanthroline and copper nitrate, is structurally confirmed through single-crystal X-ray diffraction. The effective activity in ring-opening reaction of epoxide is achieved when this complex is anchored on amine-functionalized SAPO materials. Characterization techniques such as powder X-ray diffraction, N2 adsorption-desorption, Fourier transform infrared spectroscopy, nuclear magnetic resonance, scanning electron microscope, and thermogravimetric analysis confirm the structural integrity, surface properties, and thermal stability of the materials. High conversion efficiencies of 90% and 88% are achieved using copper-complex-immobilized SAPO-34 and SAPO-5, respectively. To enhance industrial applicability, machine learning techniques are applied to predict product conversion and selectivity. Methods such as linear regression, support vector machine (SVM), and k-nearest neighbors (kNN) are evaluated, with SVM and kNN showing strong predictive performance. Error metrics like mean-squared error, mean absolute percentage error, and R score validate the model accuracy. This work highlights the effective integration of functionalized SAPOs with ML tools for catalytic optimization and industrial-scale applications.

Non-invasive glucose prediction and classification using NIR technology with machine learning

Road inconsistency may cause dangerous driving experience that leads to carelessness while handling the vehicle. To determine the road inconsistency, development of models which are based on the 85th percentile of speed is adopted. The models which are taken into consideration are other geometric road characteristics such as superelevation, radius of curve, width of curve, tangent length, and road gradient that can help to minimize the risk of accidents at curve. To further analyze the effectiveness of these developed models, validation of the models using new set of data and comparing it with other established models is crucial. The validation process is conducted by calculating the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). MSE value will indicate the differences between the empirical results with the predicted results, while MAE calculates the absolute difference between the empirical results and predicted results. MAPE evaluates the percentage errors between the empirical results with the predicted results. Small values of MSE, MAE, and MAPE is a proof that the models can predict good results.

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

MSMEs (Micro, Small and Medium Enterprises) in Indonesia have a major influence in terms of economic growth. NN MSMEs are MSMEs engaged in culinary. One type of NN MSME product is ready-to-eat emping. Often during the Eid al-Fitr holiday experience overwhelmed in terms of meeting the demand for ready-to-eat emping. This study aims to assist NN MSMEs in estimating the amount of consumer demand for ready-to-eat emping, as well as to find out the best results and methods in calculating forecasting in trend projection methods. The trend projection method used in forecasting calculations in this case is linear regression and least squares. Meanwhile, to calculate the error value from the forecasting results using the Mean Absolute Deviation (MAD), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE) methods. The best method from the results of this study is to use a linear regression method with demand values for 2024, 2025 and 2026 during Eid al-Fitr are 1771.23 kg, 1914.24 kg, and 2057.25 kg respectively with error values of MAD, MSE and MAPE respectively are 612.0781, 525807.4 and 48.83%.
 
 Keywords: Forecasting, Trend Projections, MSMEs, Consumer Demand

Stock market volatility is important for investment, option pricing and financial market regulation. In recent years, stock market analysis and prediction have the greatest significance for many professionals in the fields of finance and stock exchange. There are many methods available in the literature to solve the problem of future prediction. The present study provides a detailed comparison of Single Exponential Smoothing (SES) model and Autoregressive Integrated Moving Average (ARIMA) model. Future values are forecasting using SES and ARIMA model. Forecasted values for different iś values are calculated from SES method and ARIMA (0, 2, 3). Also, Mean Square Error (MSE), Mean Absolute Deviation (MAD), Root Mean Square (RMSE) and Mean Absolute Percentage Error (MAPE) are calculated individually for both methods.