Confusion Matrix Research Articles

Advancing aquifer vulnerability mapping through integrated deep learning approaches

Groundwater vulnerability maps are crucial for safeguarding groundwater quality. A research gap exists in using advanced data fusion techniques to identify areas subject to seawater intrusion. To address this gap, this research enhances the GALDIT method and applies diverse deep learning models, combined with machine learning techniques, to improve the precision of aquifer vulnerability mapping. The new GALDITMW model incorporates the seawater mixing index and the parameters related to the production well density and aquifer porous medium. For the first time, supervised and unsupervised deep learning models, such as deep neural networks, deep belief networks, deep stacked autoencoders, and convolutional neural networks, are used for vulnerability mapping. In the second stage, the results of various machine learning models are fused to improve performance. The models' effectiveness is evaluated using a vulnerability index based on total dissolved solids (TDS) in an aquifer hydraulically connected with Salt Lake in central Iran, which faces groundwater depletion and salinization. The evaluation of the models based on performance metrics and the confusion matrix demonstrates that initial deep-learning models perform well. Significant improvements were observed in the second stage involving machine learning models, confirming their strong correlation (R2 > 0.985) with observed chloride values. The GPR model achieved an F1 score of 86.92%, an NSE of 0.911, and an RMSE reduction of 0.026 mg/L compared to the first-stage models. The proposed method offers a novel and accurate method for identifying vulnerable areas and provides helpful information for groundwater resource management.

Detection and classification of surface defects on hot-rolled steel using vision transformers

This study proposes a vision transformer to detect visual defects on steel surfaces. The proposed approach utilizes an open-source image dataset to classify steel surface conditions into six fault categories namely, crazing, inclusion, rolled in, pitted surface, scratches and patches. The defect images are first subject to resizing and then fed into a vision transformer subject to different hyperparameter configurations to determine the most optimal setting to render highest classification performance. The performance of the model is evaluated for different hyperparameter configurations, and the most optimal configuration is examined using the associated confusion matrices. It was observed that the proposed model presents a high overall accuracy of 96.39 % for detection and classification of steel surface faults. The study presents a descriptive insight into the vision transformer architecture and in addition, compares the performance of the current model with the results of other approaches suggested for application in literature. Vision transformers can serve as standalone approaches and suitable alternatives to the widely used convolution neural networks (CNNs) by actuating complex defect detection and classification tasks in real-time, enabling efficient and robust condition monitoring of a wide range of defects.

Machine Learning Techniques for Predication of Heart Diseases

Heart disease, or cardiovascular illness, encompasses a wide range of disorders affecting the cardiovascular system. One of the trickiest things to do in medicine is to make predictions about cardiovascular disease. Nowadays, heart disease claims the life of almost one person every minute. Heart disease has several causes, but one of the most pressing issues is the lack of sensitive, precise methods for early identification, which makes proper management of the condition impossible. Automating the prediction process is necessary to prevent the hazards connected with cardiac disease diagnosis and to inform the patient at an early stage due to the intricacy of the condition. Data mining is extensively utilized in healthcare to forecast the occurrence of cardiovascular illness by analyzing massive and intricate medical records. To forecast cardiac problems, researchers conduct in-depth analyses of massive amounts of medical data using a wide range of data mining and machine learning algorithms. Here, we provide several heart disease characteristics and build a model using supervised learning methods like random forest and support vector machine (SVM). The Kaggle repository contains the cardiac condition dataset that is used in this research. Predicting patients' risk of heart disease is the main objective of this investigation. Confusion matrices were used for proposed system evaluation .The findings demonstrate that Random Forest achieves the highest level of accuracy, reaching 98.54 percent.

Research on Prediction Model of Benign and Malignant Breast Cancer Based on Machine Learning

This study uses three machine learning models to perform classification analysis on breast cancer data, aiming to improve diagnostic accuracy. After data preprocessing and standardization, the performance of each model was comprehensively evaluated using classification and regression metrics. The results showed that the logistic regression model performed the best, with an accuracy of 0.9825, while SVM and random forest also showed good performance. The classification effects of each model were visualized through ROC curves and confusion matrices, demonstrating that logistic regression has high application value in breast cancer diagnosis.

Comparative Analysis of K-Nearest Neighbors and Decision Tree Methods in Determining Students’ Purchase Interest in MacBook Laptops

In the context of increasingly competitive technology markets, companies need to know consumer preferences accurately to optimize product offerings and increase sales. Two classification methods that are often used in data mining, namely K-Nearest Neighbors and Decision Tree, have their own advantages and disadvantages. This study proposes a solution that involves processing student data using both classification methods to identify the most accurate and effective method for identifying purchase intentions. This study aims to compare the performance of the two methods in determining student purchase intentions for MacBook laptops. The research methodology includes collecting data from 100 students covering various factors such as user experience, design and portability, technical specifications, price, and security. This data is then classified using the K-Nearest Neighbors and Decision Tree methods. Furthermore, a confusion matrix is used to provide a more detailed picture of the performance of the two methods. The results of the study show that the Decision Tree method has a higher accuracy (91%) compared to K-Nearest Neighbors (88%). In addition, Decision Tree excels in other metrics such as precision (87.18% vs. 85.71%), recall (89.47% vs. 85.71%), specificity (91.94% vs. 89.66%), and F1-Score (88.31% vs. 85.71%). The decision tree also has a higher NPV value and lower FPR and FNR rates than K-Nearest Neighbors, indicating that it is superior in avoiding misclassification. The study's conclusion is that the Decision Tree method is more effective and accurate than K-Nearest Neighbors in determining students' purchase intentions for MacBook laptops. The decision tree shows better performance in almost all evaluation metrics, making it a more reliable method to use in consumer data analysis. The results of this study are expected to help companies choose a more appropriate and effective analysis method for their marketing strategies, as well as provide a basis for further research in the field of consumer purchase intention classification.

Comparison of YOLOv8 Models for Aircraft Detection in Airport Apron Using Digital Image Processing

Airport safety can be improved by efficient air traffic management, which monitors aircraft parking spots and controls their movement into them more efficiently. In addition to emergency situations, it can assist in accurately inspecting airport areas. Management costs can be reduced by reducing the workload of personnel in controlling and helping manage air and ground traffic. This research focuses on comparing the performance of various YOLOv8 models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8nl, and YOLOv8nx) in an automated aircraft detection system using digital image processing techniques. The methodology involves collecting a dataset of 1,000 airport apron images with parked aircraft, dividing them into 900 training images and 100 testing images. The YOLOv8 models are trained on the training dataset, and their performance is evaluated on the testing dataset using confusion matrices. Experimental results reveal that YOLOv8nx achieves the highest average aircraft detection performance, with a precision of 0.94, recall of 0.74, and f1-score of 0.83. Additionally, YOLOv8n demonstrates the highest processing speed at 0.95 milliseconds. Consequently, YOLOv8n is suitable for applications requiring high-speed processing, while YOLOv8nx is ideal for tasks demanding the utmost performance efficiency.

Programming and Setting Up the Object Detection Algorithm YOLO to Determine Feeding Activities of Beef Cattle: A Comparison between YOLOv8m and YOLOv10m.

This study highlights the importance of monitoring cattle feeding behavior using the YOLO algorithm for object detection. Videos of six Charolais bulls were recorded on a French farm, and three feeding behaviors (biting, chewing, visiting) were identified and labeled using Roboflow. YOLOv8 and YOLOv10 were compared for their performance in detecting these behaviors. YOLOv10 outperformed YOLOv8 with slightly higher precision, recall, mAP50, and mAP50-95 scores. Although both algorithms demonstrated similar overall accuracy (around 90%), YOLOv8 reached optimal training faster and exhibited less overfitting. Confusion matrices indicated similar patterns of prediction errors for both versions, but YOLOv10 showed better consistency. This study concludes that while both YOLOv8 and YOLOv10 are effective in detecting cattle feeding behaviors, YOLOv10 exhibited superior average performance, learning rate, and speed, making it more suitable for practical field applications.

Implementation of Raita Algorithm in Manado-Indonesia Translation Application with Text Suggestion Using Levenshtein Distance Algorithm

Abstract. Manado City is one of the multidimensional and multicultural cities, possessing assets that are considered highly potential for development into tourism and development attractions. The current tourism assets being developed by the Manado City government are cultural tourism, as they hold a charm and allure for tourists. Hence, a communication tool in the form of a translation application is necessary for facilitating communication between visiting tourists and the native community of North Sulawesi, even for newcomers who intend to reside in North Sulawesi, given that the Manado language serves as the primary communication tool within the community. This research employs a combination of the Raita algorithm and the Levenshtein distance algorithm in its creation process, along with the confusion matrix method to calculate the accuracy of translation results using the Levenshtein distance algorithm with a text suggestion feature. The research begins by collecting a dataset consisting of Manado language vocabulary and their translations in Indonesia language, sourced from literature studies and original respondents from North Sulawesi, which have been validated by a validator to prevent translation data errors. The subsequent stage involves preprocessing the dataset, converting the entire content of the dataset to lowercase using the case folding process, and removing spaces at the start and end of texts using the trim function. Next, both algorithms are implemented, with the Raita algorithm serving for translation and the Levenshtein distance algorithm providing text suggestions for typing errors during the translation process. The accuracy results derived from the confusion matrix calculations during the translation process of 100 vocabulary words, accounting for typing errors, indicate that the Levenshtein distance algorithm is capable of effectively translating vocabulary accurately and correctly, even in the presence of typing errors, resulting in a high accuracy rate of 94,17%. Purpose: To determine the implementation of the Levenshtein distance and Raita algorithms in the process of using the Manado-Indonesian translation application, as well as the resulting accuracy level. Methods/Study design/approach: In this study, a combination of the Raita and Levenshtein distance algorithms is utilized in the translation application system, along with the confusion matrix method to calculate accuracy. Result/Findings: The accuracy achieved in the translation process using text suggestions from the Levenshtein distance algorithm is 94.17%. Novelty/Originality/Value: This research demonstrates that the combination of the Raita and Levenshtein distance algorithms yields optimal results in the vocabulary translation process and provides accurate outcomes from the use of effective text suggestions. This is attributed to the fact that nearly all the data used was successfully translated by the system, even in the presence of typographical errors.

Implementasi Deteksi Objek Real-Time Sebagai Media Edukasi dengan Algoritma YOLOv8 pada Objek Sampah

Waste is one of the complex global issues and is one of the points of the SDGs indicators related to municipal waste, food waste, hazardous waste and recycling systems that cannot be resolved. According to data from SIPSN in 2022, waste generation in Indonesia will reach 35,289,535.55 tons/year while about 47.32% of waste handling is done, which is 16,697,790.76 tons/year. The National Research and Innovation Agency said that currently there are still few Indonesians who have the awareness to start sorting waste from their own homes. As many as 80% of Indonesians do not sort their waste. To overcome these problems, everyone needs to make changes early on by making waste management a habit so as to change people's skeptical attitude towards waste management. Thus, research was conducted to identify the type of waste using the YOLOv8 algorithm, with a dataset of 17,617 data which was then analyzed by creating a yolov8 model. The best accuracy results were obtained by using the yolov8l variant as well as 16 batch sizes and the SGD optimizer with a learning rate value of 0.001 as a parameter. The model training process was then evaluated using confusion matrix with a percentage reaching 86.5%.

Analysis of Public Interest in Smartfren SIM Cards using the K-Nearest Neighbors Method

The use of Smartfren SIM cards is increasing along with the public's need for fast and stable internet services. However, a deep understanding of public interest in the SIM card is necessary to optimize marketing strategies and increase sales. Proper analysis can help companies identify potential target markets and develop effective marketing strategies. We chose the K-Nearest Neighbors method to analyze public interest in using Smartfren SIM cards. This study aims to develop and evaluate the K-Nearest Neighbors model in predicting public interest in using Smartfren SIM cards. This study uses a dataset containing information about Smartfren SIM card users. We divide the data into two sets: a training set for model building and a test set for evaluating model performance. We apply the K-Nearest Neighbors method to classify the data into two categories: interested and not interested. We evaluate the model performance using accuracy, precision, recall, and F1-score metrics. We present the evaluation results as a confusion matrix. The developed K-Nearest Neighbors model showed excellent performance with an accuracy of 94.29%, a precision of 94.20%, a recall of 100%, and an F1-score of 97.01%. These results indicate that the K-Nearest Neighbors model is effective in predicting people's interest in Smartfren SIM cards. The high recall value indicates that the model is able to identify all interested individuals without missing any, while the high precision value indicates that the model rarely makes false positive prediction errors. This study concludes that the K-Nearest Neighbors method is very effective for use in analyzing people's interest in using Smartfren SIM cards. We can rely on the developed model's strong performance for real-world applications in marketing strategies.

Analysis Of Public Interest In Smartfren SIM Cards Using The K-Nearest Neighbors Method

The use of Smartfren SIM cards is increasing along with the public's need for fast and stable internet services. However, a deep understanding of public interest in the SIM card is necessary to optimize marketing strategies and increase sales. Proper analysis can help companies identify potential target markets and develop effective marketing strategies. We chose the K-Nearest Neighbors method to analyze public interest in using Smartfren SIM cards. This study aims to develop and evaluate the K-Nearest Neighbors model in predicting public interest in using Smartfren SIM cards. This study uses a dataset containing information about Smartfren SIM card users. We divide the data into two sets: a training set for model building and a test set for evaluating model performance. We apply the K-Nearest Neighbors method to classify the data into two categories: interested and not interested. We evaluate the model performance using accuracy, precision, recall, and F1-score metrics. We present the evaluation results as a confusion matrix. The developed K-Nearest Neighbors model showed excellent performance with an accuracy of 94.29%, a precision of 94.20%, a recall of 100%, and an F1-score of 97.01%. These results indicate that the K-Nearest Neighbors model is effective in predicting people's interest in Smartfren SIM cards. The high recall value indicates that the model is able to identify all interested individuals without missing any, while the high precision value indicates that the model rarely makes false positive prediction errors. This study concludes that the K-Nearest Neighbors method is very effective for use in analyzing people's interest in using Smartfren SIM cards. We can rely on the developed model's strong performance for real-world applications in marketing strategies.

Prediction of Sand Production from Poorly Consolidated Formations Using Artificial Neural Network: A Case Study, Nahr Umr Formation in Subba Oil Field

Sand production in poorly consolidated formations is a significant challenge to the oil and gas industry, resulting in reduced production and compromised equipment integrity. The oil and gas industry has recently become interested in data analytics because it has significantly simplified, accelerated, and reduced the cost of data visualization. The intriguing new approaches in artificial intelligence development promise to offer long-term solutions to the increasing problems affecting the petroleum industry's operations. Any completion operation in sandstone formations is based on determining whether or not a well will produce sand. It is economically unfavorable to the Nahr Umr Formation to install sand control equipment for wells that don't produce sand. This study aims to create an efficient and precise artificial neural network that can predict sanding in sandstone formations. To achieve this, we developed a two-layered ANN with a back-propagation algorithm using JMP software. The model formulation included various geological and mechanical factors that could impact sand detachment, such as Young’s modulus (YME), Poisson’s ratio, minimum and maximum horizontal stresses (SHMIN and SHMAX), pore pressure, shale volume, and formation strength. The study acquired data from both local fields, specifically the Amarah oilfield, and non-local fields from the literature. Two sets were created from the data: a training set comprising 75% of the data, and a test set comprising 25% of the data, both of which were classified. The speed and accuracy of a learning process in an Artificial Neural Network depends on the size of the data set, the number of hidden layers, and the input parameters. The statistical measures such as accuracy, confusion matrix, root mean square error, and generalized RSquare demonstrate the strong efficacy of the created Artificial Neural Network model. The results indicate a significant likelihood of sand production occurring over the perforation intervals across Su-4 and Su-5 wells. The method's unique feature is its ability to isolate shale areas and identify weak areas capable of producing sand in sandstone formations. In conclusion, it is determined that an Artificial Neural Network employing the back-propagation algorithm is a simple, reliable, and easy-to-use method for accurately predicting sand production.

Implementing K-Nearest Neighbors (k-NN) Algorithm and Backward Elimination on Cardiotocography Datasets

Having a healthy baby is a dream for mothers. Unfortunately, high maternal and fetal mortality has become a vital problem that requires early risk detection for pregnant women. A cardiotocograph examination is necessary to maintain maternal and fetal health. One method that can solve this problem is classification. This research analyzes the optimal use of k values and distance measurements in the k-NN method. This research expects to become the primary reference for other studies examining the same dataset or developing k-NN. A selection feature is needed to optimize the classification method, particularly for improving accuracy results. This study used the cardiotocography dataset from cardiotocograph examinations related to fetal conditions. The cardiotocography dataset consisted of 2,126 records with 22 features and variables. It also had three classification classes, normal, suspect, and pathological, from the Universal Child Immunization Machine Learning Repository website. It employed the K-Nearest Neighbor (k-NN) method and the backward elimination feature with ordinary least squares regression. The test in this research applied the scenarios of three distance calculations, i.e., Euclidean distance, Manhattan distance, and Minkowski distance, as well as four variations of k values. Evaluation of each scenario indicated the accuracy of the confusion matrix and execution time. This study compared K-Nearest Neighbor (k-NN) and Backward Elimination methods with K-nearest neighbor (k-NN) without selection features. The best accuracy of the Backward Elimination and K-Nearest Neighbor (K-NN) methods was 91%, as was the K-Nearest Neighbor (k-NN) method without selection features. Both had similar k values (k = 3) and Manhattan distance. The backward elimination method reduced the number of features from 22 to 14. Meanwhile, the execution times of the Backward Elimination and K-Nearest Neighbor (k-NN) methods got better results as each distance averaged 26.54, 19.23, and 68.09 seconds. K-Nearest Neighbor (k-NN) execution times without selection features were 26.83, 19.39, and 68.84, respectively. In conclusion, backward elimination did not increase accuracy because it yielded the same accuracy. However, backward elimination and K-nearest Neighbor (k-NN) produced faster results, with differences of 29%, 16%, and 75%, respectively.

Analysis Of The Use Of Nazief-Adriani Stemming And Porter Stemming In Covid-19 Twitter Sentiment Analysis With Term Frequency-Inverse Document Frequency Weighting Based On K-Nearest Neighbor Algorithm

Abstract. This system was developed to determine the accuracy of sentiment analysis on Twitter regarding the COVID-19 issue using the Nazief-Adriani and Porter stemmers with TF-IDF weighting, along with a classification process using K-Nearest Neighbor (KNN) that resulted in a comparison of 48.24% for Nazief-Adriani and 48.24% for Porter. Purpose: This research aims to determine the accuracy of the Nazief-Adriani and Porter stemmer algorithms in performing text preprocessing using a dataset from Indonesian-language Twitter. This research involves word weighting using TF-IDF and classification using the K-Nearest Neighbor (KNN) algorithm. Methods/Study design/approach: The experimentation was conducted by applying the Nazief-Adriani and Porter stemmer algorithm methods, utilizing data sourced from Twitter related to COVID-19. Subsequently, the data underwent text preprocessing, stemming, TF-IDF weighting, accuracy testing of training and testing data using K-Nearest Neighbor (KNN) algorithm, and the accuracy of both stemmers was calculated employing a confusion matrix table. Result/Findings: This study obtained reasonably accurate results in testing the Nazief-Adriani stemmer with an accuracy of 50.98%, applied to sentiment analysis of COVID-19-related Twitter data using the Indonesian language. As for the accuracy of the Porter stemmer, it achieved an accuracy rate of 48.24%. Novelty/Originality/Value: Feature selection is crucial in stemmer accuracy testing. Therefore, in this study, feature selection is carried out using the Nazief-Adriani and Porter stemmers for testing purposes, and the accuracy data classification is conducted using the K-Nearest Neighbor (KNN) algorithm

Using random forest and biomarkers for differentiating COVID-19 and Mycoplasma pneumoniaeinfections.

The COVID-19 pandemic has underscored the critical need for precise diagnostic methods to distinguish between similar respiratory infections, such as COVID-19 and Mycoplasma pneumoniae (MP). Identifying key biomarkers and utilizing machine learning techniques, such as random forest analysis, can significantly improve diagnostic accuracy. We conducted a retrospective analysis of clinical and laboratory data from 214 patients with acute respiratory infections, collected between October 2022 and October 2023 at the Second Hospital of Nanping. The study population was categorized into three groups: COVID-19 positive (n = 52), MP positive (n = 140), and co-infected (n = 22). Key biomarkers, including C-reactive protein (CRP), procalcitonin (PCT), interleukin- 6 (IL-6), and white blood cell (WBC) counts, were evaluated. Correlation analyses were conducted to assess relationships between biomarkers within each group. The random forest analysis was applied to evaluate the discriminative power of these biomarkers. The random forest model demonstrated high classification performance, with area under the ROC curve (AUC) scores of 0.86 (95% CI: 0.70-0.97) for COVID-19, 0.79 (95% CI: 0.64-0.92) for MP, 0.69 (95% CI: 0.50-0.87) for co-infections, and 0.90 (95% CI: 0.83-0.95) for the micro-average ROC. Additionally, the precision-recall curve for the random forest classifier showed a micro-average AUC of 0.80 (95% CI: 0.69-0.91). Confusion matrices highlighted the model's accuracy (0.77) and biomarker relationships. The SHAP feature importance analysis indicated that age (0.27), CRP (0.25), IL6 (0.14), and PCT (0.14) were the most significant predictors. The integration of computational methods, particularly random forest analysis, in evaluating clinical and biomarker data presents a promising approach for enhancing diagnostic processes for infectious diseases. Our findings support the use of specific biomarkers in differentiating between COVID-19 and MP, potentially leading to more targeted and effective diagnostic strategies. This study underscores the potential of machine learning techniques in improving disease classification in the era of precision medicine.

Implementation of K-Nearest Neighbors Algorithm in Analyzing Public Interest in Shoping at Supermarkets

People's shopping patterns and behaviors continue to develop along with technological advances and lifestyle changes, thus requiring retail business actors, especially supermarkets, to better understand their customers' interests and preferences. In this context, accurate analysis of customer shopping interests is very important to improve customer satisfaction and optimize marketing strategies. One solution that can be implemented to analyze people's shopping interests is the application of the K-Nearest Neighbors algorithm, a simple yet effective nearest neighbor-based classification method for recognizing patterns from existing data. This study aims to apply the K-Nearest Neighbors algorithm to classify people's interest in shopping at supermarkets. This study also evaluates the effectiveness and performance of the algorithm in the context of business decision-making in the retail sector. The research methodology includes collecting data on people's shopping interests, data pre-processing, implementing the K-Nearest Neighbors algorithm, and evaluating model performance using evaluation metrics such as accuracy, precision, recall, and F1-score. The results of this study indicate that the K-Nearest Neighbors algorithm is able to achieve an accuracy of 88%, with precision, recall, and F1-score all reaching 92.86%. These results indicate that the K-Nearest Neighbors model is very effective in classifying people's shopping interests, with a low error rate. The resulting confusion matrix also shows the model's ability to identify customers who are interested in shopping with little prediction error. This study concludes that we can rely on the K-Nearest Neighbors algorithm to analyze people's shopping interests in supermarkets. This model not only shows good performance in classification but also has great potential to be implemented in recommendation systems and customer segmentation in the real world. This study contributes to the development of consumer behavior analysis methods in the retail sector, as well as providing a basis for further research to explore other algorithms or combinations of techniques to improve the accuracy and effectiveness of classification models.

Sentiment Analysis Of Ijen Crater Reviews Using Naïve Bayes Classification And Oversampling Optimization

Sentiment analysis is a method that applies text mining concepts to provide classifications that have polarity that is positive, negative, or neutral from each sentence or document. In this context, the purpose of this research is to analyse the sentiment of user reviews related to the Ijen crater tourist attractions found on the Google Maps platform. This research is conducted in three main stages: first, Data Collection and Preprocessing by taking data samples obtained from Ijen Crater reviews contained on Google Maps; second Optimisation and Classification by changing the minority class samples to be almost equal to the majority class by randomly duplicating the minority class samples, third, classification performance measurement using confusion matrix. The test is conducted by comparing the performance between NBC classification without optimisation and NBC classification with SMOTE and ADASYN optimisation. The performance results show that SMOTE-optimised NBC classification provides the best improvement in accuracy by 6.74% compared to the performance of ordinary NBC and NBC added with ADASYN.

Artificial Intelligence Approaches for Predicting Diabetes in Egypt

One major public health concern in Egypt is the increasing incidence of diabetes mellitus. It is essential to recognize problems early and treat them effectively [1]. This work applies several machine learning methods to predict diabetes risk using a dataset from Egyptian diabetes and endocrinology clinics. Features including age, BMI, medical history, and other health markers are included in the dataset. Using performance criteria such as confusion matrix, F1-score, recall, accuracy, and precision, we assessed various models including K-Neighbors, Gaussian Naive Bayes, Bernoulli Naive Bayes, Extra Trees, SVC, and Logistic Regression. The findings indicate that diabetes can be accurately predicted using machine learning. Logistic Regression, with a cross-validated accuracy of 0.965, test accuracy of 0.957, precision of 0.94, recall of 0.90, and an F1-score of 0.92, proved to be the most effective model for this dataset.

Predictive models for heat stress assessment in Holstein dairy heifers using infrared thermography and machine learning.

Heat stress is a condition that impairs the animal's productive and reproductive performance, and can be monitored by physiological and environmental variables, including body surface temperature, through infrared thermography. The objective of this work is to develop computational models for classification of heat stress from respiratory rate variable in dairy cattle using infrared thermography. The database used for the construction of the models was obtained from 10 weaned heifers, housed in a climate chamber with temperature control, and submitted to thermal comfort and heat wave treatments. Physiological and environmental data were collected, as well as thermographic images. The machine learning modeling environment used was IBM Watson, IBM's cognitive computing services platform, which has several data processing and mining tools. Classifier models for heat stress were evaluated using the confusion matrix metrics and compared to the traditional method based on Temperature and Humidity Index. The best accuracy obtained for classification of the heat stress level was 86.8%, which is comparable to previous works. The authors conclude that it was possible to develop accurate and practical models for real-time monitoring of dairy cattle heat stress.

A U-Net Model for Urban Land Cover Classification Using VHR Satellite Images

Urban settings are dynamic, constantly changing, and presenting a wide range of surface materials with high diversity in both spatial and spectral variation. As a result, mapping urban growth, evaluating infrastructure, managing water resources, and monitoring natural land cover become more complex tasks. Urban applications have made considerable progress thanks to the abundance of VHR orbital data and the recent development of artificial intelligence strategies especially neural networks. Convolutional neural networks have the potential to significantly enhance the analysis of urban land cover by addressing the limitations of traditional techniques. U-Net is a popular neural network for land cover analysis in remote sensing images. The current research presents a CNN model employing U-Net for image semantic segmentation in urban study area using both spectral and spatial context of VHR satellite data. The proposed model is trained, validated, and tested for VHR satellite image classification into five urban classes: water, vegetation, bare soil, road, and building. The CNN semantic segmentation results are compared to maximum likelihood image classification outcomes for validation and stability evaluation. A confusion matrix is applied to the classified scenes to determine the overall accuracy, producer's and user's accuracy, and Kappa coefficient using 400 random points with their corresponding ground truth. The U-Net image semantic segmentation technique achieved an overall accuracy of 87.50% and Kappa coefficient of 0.8395 which outperforms the maximum likelihood classification method with an overall accuracy of 83.25% and Kappa coefficient of 0.7812.