AdaBoost Algorithm Research Articles

Accurate identification of oxygen desaturation status in COPD by using classifier ensemble.

The accurate identification of oxygen desaturation (OD) status plays critical role in the clinic diagnosis of chronic obstructive pulmonary disease (COPD), which is a common disease related to the lungs and respiratory tract of the human body. This paper focuses on a specific type of OD status, i.e., exercise-induced oxygen desaturation (EIOD) status in COPD, and try to further improve the performance of EIOD status identification. We propose a new and effective EIOD status identification method by using classifier ensemble strategy. In the proposed method, five different features of each data point from the time series of SpO2 and pulse are extracted and then combined to form the discriminative feature of the corresponding data point; then, multiple base classifiers with different balanced training subsets are trained and then integrated by using AdaBoost Algorithm. The comparative computational results on the 6-min walk test (6MWT) of the recruited participants show that the proposed method achieved the best global performance with AUC (Area Under Curve) value of 0.8532, indicating that the proposed method can be effectively used for the identification of EIOD and could assist the clinic diagnosis of COPD.

DETECTION OF KERATOCONUS DISEASE DEPENDING ON CORNEAL TOPOGRAPHY USING DEEP LEARNING

Keratoconus is a disease that ML has contributed much in its diagnosis and management. It is not a widely prevalent disease, with a research gap caused by the absence of standardized datasets for model training and evaluation. This work presents a novel dataset, which strengthens the CNN model's resilience and creates standards for assessing keratoconus diagnostic techniques. The research depends on data of patients examined at Jenna Ophthalmic Center in Baghdad. The proposed system works on three stages: pre-processing, feature extraction, and classification with machine learning algorithms including NB, KNN, ADA, DT, and CNN deep learning. The pre-processing stage involves cropping images to retain the relevant maps, which were subjected to contrast enhancement to improve image quality. The pre-processed data is then fed into Machine Learning(ML) algorithms and Convolutional Neural Network(CNN) models, by which the four corneal maps were analyzed. The precision of the ML method was quantified, yielding a precision score of 0.79 for the AdaBoost algorithm and an impressive score of 0.99 for the suggested CNN model exemplifying its high accuracy and ability to surpass all machine learning approaches. Applying PCA for feature extraction before utilizing tradition ML algorithms and CNN helps in achieving high-accuracy results.

A Motion Capture Framework for Table Tennis Using Optimized SVM and AdaBoost Algorithms

A Motion Capture Framework for Table Tennis Using Optimized SVM and AdaBoost Algorithms

Dynamic Ensemble Algorithm for Context-Aware Diabetes Prediction: Integrating Local and Global Data for Real-World Applications

- This research proposes a novel decision support system utilizing dynamic ensemble algorithms for the accurate prediction of diabetes. This system mitigates the issues of regional disparities and unrecorded information in diabetes-related datasets by integrating global datasets and the medical data that are gathered locally. This technique utilizes the Adaptive Boosting (AdaBoost) algorithm blended with decision stumps and support vector machines to improve classification accuracy. The validation was carried out on the Pima Indian Diabetes Dataset and a locally curated dataset from multiple regions. The system that was suggested obtaining an accuracy of 84.5% was higher than the regular approaches. The article ends up with such suggestions as increasing the ensemble methods through the hybrid way. Key Words: Diabetes Prediction, Ensemble Methods, Machine Learning, Local-Global Integration, AdaBoost, Decision Stump.

Predicting the risk of a high proportion of three/multiple pronuclei (3PN/MPN) zygotes in individual IVF cycles using comparative machine learning algorithms.

The majority of machine learning applications in assisted reproduction have been focused on predicting the likelihood of pregnancy. In the present study, we aim to investigate which machine learning models are most effective in predicting the occurrence of a high proportion (>30%) of 3PN/MPN zygotes in individual IVF cycles. Eight machine learning algorithms were trained and compared, including the AdaBoost and Gaussian NB. Data from IVF cycles carried out from September 2015 to September 2019 were used as a training set. Cycle data from October 2019 to June 2020 were used as a validation set to verify the training model. Cycles with a 3PN/MPN zygote proportion higher than 30% were classified as high 3PN/MPN zygote proportion cycles. The AdaBoost algorithm was the best model for model construction and external validation. In both the training and validation sets, age, basal FSH, FSH and E2 level on the day of Gonadotrophin (GN) stimulation, and FSH and LH levels on the day of HCG were statistically higher in patients with 3PN/MPN>30% than in patients with 3PN/MPN≤30%; AFC, AMH, E2 level on HCG day and total number of oocytes were lower in patients with 3PN/MPN>30% than in patients with 3PN/MPN≤30%. The top five predictors were the number of oocytes retrieved, age, male factor infertility, AFC, and total days of GN stimulation. By applying a suitable machine learning algorithm, we can potentially predict the risk of a high proportion of 3PN/MPN zygotes in individual IVF cycles before insemination and avoid polyspermy fertilization by ICSI fertilization method.

Feature optimized hybrid model for prediction of myocardial infarction

Background Cardiovascular disease is rampant worldwide and has become the leading factor in increasing the global mortality rates. According to the World Heart Federation, death toll due to CVD has increased from 12.1 million in 1990 to around 19 million in 2019. Myocardial Infarction (MI) is a condition where the heart muscle dies due to reduced or inhibited flow of oxygenated blood. It has affected approximately 3 million people worldwide, with more than 1 million deaths in the United States annually. Such unusual proliferation in global death toll due to CVD can be reduced to a great extent by predicting the risk of CVD at an early stage. Method In this paper, several feature selection techniques including Variance-based, Mutual Information (MI), Maximum Relevance Minimum Redundancy (MRMR), Boruta, and Recursive Feature Elimination (RFE) algorithms are used feature optimization. For class prediction, the Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Adaboost algorithms were implemented in their ordinary, One-vs-Rest (OVR) and One-vs-One (OVO) methods. Result The performance of Adaboost model has significantly improved by using feature selection techniques, that is, the accuracy of 74% (without any feature selection taking 5.3 seconds) is increased to 85% (with Boruta feature selection taking only 2.17 seconds training time) and 88% (with MRMR feature selection taking 1.6 seconds training time). Similarly, the DT-OVO model’s performance has improved from 84% (without any feature selection taking 1.48 seconds training time) to 86% (with Boruta feature selection taking 0.58 training time). For other models, the performance is maintained with reduced model training times. Conclusion This research paper prioritizes on feature selection in developing machine learning models for CVD prediction. This conclusion is justified by demonstrating the significant reduction in model training times for the 72 models generated while maintaining or even improving the model’s predictive performance.

Integrating machine learning and nano-QSAR models to predict the oxidative stress potential caused by single and mixed carbon nanomaterials in algal cells.

In silico methods are increasingly important in predicting the ecotoxicity of engineered nanomaterials (ENMs), encompassing both individual and mixture toxicity predictions. It is widely recognized that ENMs trigger oxidative stress effects by generating intracellular reactive oxygen species (ROS), serving as a key mechanism in their cytotoxicity studies. However, existing in silico methods still face significant challenges in predicting the oxidative stress effects induced by ENMs. Herein, we utilized laboratory-derived toxicity data and machine learning methods to develop quantitative nanostructure-activity relationship (nano-QSAR) classification and regression models, aiming to predict the oxidative stress effects of five carbon nanomaterials (fullerene, graphene, graphene oxide, single-walled carbon nanotubes, and multi-walled carbon nanotubes) and their binary mixtures on Scenedesmus obliquus cells. We constructed five nano-QSAR classification models by combining zeta potential (ζP) with the C4.5 decision tree, support vector machine, artificial neural network, naive Bayes, and K-nearest neighbor algorithms. Moreover, we constructed three classification models by integrating the features including ζP, hydrodynamic diameter (DH), and specific surface area (SSA) with the logistic regression, random forest, and Adaboost algorithms. The Accuracy, Recall, Precision and harmonic mean of Precision and Recall (F1-score) values of these models were all higher than 0.600, indicating an excellent performance in distinguishing whether CNMs have the potential to generate ROS. In addition, using the ζP, DH, and SSA descriptors, we combined decision tree regression, random forest regression, gradient boosting, and the Adaboost algorithm, and successfully constructed four nano-QSAR regression models with applicable application domains (all training and testing data points lie within 95% confidence intervals), goodness-of-fit (Rtrain2 ≥ 0.850), and robustness (cross-validation R2 ≥ 0.650) as well as predictive power (Rtest2 ≥ 0.610). The method developed would establish a fundamental basis for more precise evaluations of ecological risks posed by these materials from a mechanistic standpoint.

Optimized Deep Learning Techniques to Identify Rumors and Fake News in Online Social Networks

The swift expansion of networking platforms has led to a significant proliferation of fake news on social media in recent years, posing a serious risk to public safety. This phenomenon carries various potential negative effects on society, including the erosion of public confidence in journalists and governmental institutions. Consequently, the identification of fake news has attracted considerable attention from researchers across various fields. As online and social media platforms have grown, it has become easier for false information to mix in with real or verified information. People who spread false information usually have some kind of political or social goal in mind when they spread their hoaxes. Because of this, it is of the utmost importance to come up with a trustworthy way to spot false information. This article describes a way to use deep learning to spot fake news. Methodology is made up of a set of input data. The information in this dataset comes from the social networking site Twitter. First, the raw data that is being used are preprocessed. Stop word removal, stemming, and tokenization are the main parts of data preprocessing. The NTLK library is used to get rid of stop words. Porter's Algorithm is used to do stemming. N-gram model is used to do tokenization. LSTM, CNN, and AdaBoost algorithms are used to build the model. Results have shown that LSTM is better than CNN and AdaBoost in terms of accuracy, specificity, and sensitivity. LSTM has achieved an accuracy of 99.24% for fake news detection. Specificity of LSTM is 99.2%. LSTM's sensitivity is 98.67%. LSTM has achieved an accuracy of 99.24% for fake news detection. Specificity of LSTM is 99.2% and sensitivity is 98.67%. Received: 1 May 2024 | Revised: 4 September 2024 | Accepted: 19 October 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The Twitter Sentiment Analysis datasets that support the findings of this study are openly available at https://www.kaggle.com/competitions/tweet-sentiment-extraction/discussion/142142. The glove Twitter data that support the findings of this study are openly available at https://www.kaggle.com/datasets/bertcarremans/glovetwitter27b100dtxt. Author Contribution Statement Abu Sarwar Zamani: Conceptualization, Writing – original draft, Project administration, Funding acquisition. Aisha Hassan Abdalla Hashim: Writing – review & editing, Supervision. Sara Saadeldeen Ibrahim Mohamed: Investigation, Visualization. Md. Nasre Alam: Software, Writing – review & editing, Data curation.

Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning.

Machine learning exhibits excellent performance in terms of predictive power. We aimed to construct an interpretable machine learning model utilizing National Health and Nutrition Examination Survey data to investigate the relationship between heavy metal exposure and cardiovascular disease (CVD). A total of 4600 adults were included in the analysis. The Least Absolute Shrinkage and Selection Operator regression method was employed to select relevant feature variables. Subsequently, six machine learning models were constructed, including random forest, decision tree, gradient boosting decision tree, k-nearest neighbor, support vector machine, and AdaBoost algorithms. Feature importance analysis, partial dependence plot, and shapley additive explanations were integrated to enhance the interpretability of the CVD prediction model. Among all models, the random forest exhibited the best performance, with an accuracy of 90 %, an area under the curve of 0.85, and an F1 score of 0.86. Urine cadmium (Cd), blood lead (Pb), urine thallium (Tl), and urine tungsten (W) were identified as the most significant predictors of CVD, with importance scores of 0.062, 0.057, 0.051, and 0.050, respectively. At the overall level, higher levels of urine Cd, blood Pb, and urine W were associated with an increased risk of CVD, whereas a lower level of urine Tl was linked to a reduced CVD risk. Additionally, the analysis of synergistic effects revealed that Cd was the predominant determinant of CVD risk. The random forest-based CVD prediction model demonstrated excellent predictive power and provided valuable insights for personalized patient care and optimal resource allocation in populations exposed to heavy metals.

Prediction of Persistent Tumor Status in Nasopharyngeal Carcinoma Post-Radiotherapy-Related Treatment: A Machine Learning Approach.

Background/Objectives: The duration of the response to radiotherapy-related treatment is a critical prognostic indicator for patients with nasopharyngeal carcinoma (NPC). Persistent tumor status, including residual tumor presence and early recurrence, is associated with poorer survival outcomes. To address this, we developed a prediction model to identify patients at a high risk of persistent tumor status prior to initiating treatment. Methods: This retrospective study included 104 patients with NPC receiving radiotherapy-related treatment who had completed a 3-year follow-up period; 29 were classified into the persistent tumor status group and 75 into the disease-free group. Radiomic features were extracted from pretreatment positron emission tomography (PET) images and used to construct a prediction model by employing machine learning algorithms. The model's diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUC), whereas SHapley Additive exPlanations (SHAP) analysis was conducted to determine the contribution of individual features to the model. Results: The prediction model developed using the AdaBoost algorithm and validated through five-fold cross-validation achieved the highest AUC of 0.934. Its sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 89.66%, 86.67%, 72.22%, 95.59%, and 87.5%, respectively. SHAP analysis revealed that the feature of high dependence low metabolic uptake emphasis50 had the greatest impact on model predictions. Furthermore, patients classified as disease-free exhibited markedly higher overall survival rates compared with those with persistent tumor status. Conclusions: In conclusion, the proposed prediction model efficiently identified patients with NPC at a high risk of persistent tumor status by using radiomic features extracted from pretreatment PET images.

Maritime safety through multi-source data fusion: an AdaBoost-based approach for predictive ship detention by port state control

ABSTRACT In global maritime safety, the efficiency of Port State Control (PSC) is paramount in ensuring the safety of sea. Facing the challenge of effectively identifying high-risk vessels, this study innovatively enhances PSC inspection efficiency. This study aims to reduce maritime accidents by significantly improving the efficiency and accuracy of detained vessels prediction through multi-source data fusion technology and the enhanced AdaBoost algorithm. AdaBoost, improves model accuracy by combining multiple weak classifiers. By comprehensively analyzing ship inspection records from 2015 to 2022 across various Chinese ports, combined with additional vessel information, this research constructs a developed predictive model to forecast the likelihood of ships being detained by PSC in Chinese ports. The proposed model successfully identified numerous non-detained and detained ships and achieved highly satisfactory predictive results on the training dataset. Through in-depth analysis of crucial evaluation metrics such as precision, recall, F1 score, and ROC, this study provides strong technical support for accurately identifying high-risk vessels that play a vital role in enhancing maritime safety. Moreover, our findings offer valuable insights for port managers to optimize ship selection processes and for shipping companies to improve operational efficiency, having a profound impact on the safety and development of the maritime transportation industry.

Mobile Robot Positioning with Wireless Fidelity Fingerprinting and Explainable Artificial Intelligence.

Wireless Fidelity (Wi-Fi) based positioning has gained popularity for accurate indoor robot positioning in indoor navigation. In daily life, it is a low-cost solution because Wi-Fi infrastructure is already installed in many indoor areas. In addition, unlike the Global Navigation Satellite System (GNSS), Wi-Fi is more suitable for use indoors because signal blocking, attenuation, and reflection restrictions create a unique pattern in places with many Wi-Fi transmitters, and more precise positioning can be performed than GNSS. This paper proposes a machine learning-based method for Wi-Fi-enabled robot positioning in indoor environments. The contributions of this research include comprehensive 3D position estimation, utilization of existing Wi-Fi infrastructure, and a carefully collected dataset for evaluation. The results indicate that the AdaBoost algorithm attains a notable level of accuracy, utilizing the dBm signal strengths from Wi-Fi access points distributed throughout a four-floor building. The mean average error (MAE) values obtained in three axes with the Adaptive Boosting algorithm are 0.044 on the x-axis, 0.063 on the y-axis, and 0.003 m on the z-axis, respectively. In this study, the importance of various Wi-Fi access points was examined with explainable artificial intelligence methods, and the positioning performances obtained by using data from a smaller number of access points were examined. As a result, even when positioning was conducted with only seven selected Wi-Fi access points, the MAE value was found to be 0.811 for the x-axis, 0.492 for the y-axis, and 0.134 for the Z-axis, respectively.

Acdim: A Cardiovascular Disease Risk Prediction Model Based on TabNet and AdaBoost for Smart Aging

Cardiovascular disease is a typical chronic disease. The incidence of cardiovascular disease in the elderly population has grown to exceed 50%. The further aging of the current population has brought additional pressure on public health services. Therefore, to reduce the service pressure of medical institutions, accurate prediction of cardiovascular disease risk has become an essential task in intelligent elderly care. In order to achieve accurate prediction of cardiovascular disease risk, we propose a cardiovascular disease risk prediction model Acdim (a cardiovascular disease risk prediction model) based on ResNet (Residual Network), zebra optimization algorithm (ZOA), TabNet (Attentive Interpretable Tabular Learning), and AdaBoost (Adaptive Boosting) algorithms. In training the Acdim model, we used the dat set of the World Health Organization (WHO) Behavioral Risk Factor Monitoring System records. In the experiment, the Acdim model achieved an accuracy of 96%, a precision of 94%, a recall of 93%, a specificity of 95%, an F1 score of 91%, and an AUC of 95%. The experimental results show that the proposed Acdim model can enable elderly care institutions to accurately predict the risk of cardiovascular disease in the absence of doctors.

Identification of Transformer Anomalies Utilizing the AdaBoost Machine Learning Algorithm

Electrical energy is one of the most important needs in the local area, concerning the provision of electrical power a transformer is needed to distribute electrical power to each house. The use of transformers in each area requires testing the oil content in them to assess the state of the transformer. The Duval Pentagon Method (DPM) and the Duval Triangle Method (DTM) can be used in tests to identify transformer interference. Owing to the vast quantity of transformers utilized in public energy distribution, the Adaboost machine learning method was applied to identify transformer disruptions. By categorizing test data on a dataset derived from tests conducted with the earlier DTM and DPM techniques, the AdaBoost algorithm predicts transformer disruptions. According to the findings of tests conducted using the best dataset, the division used 80% of the data for training and reserved 20% for testing, using a learning rate of 1 and an estimator of 400 for DTM. This resulted in an accuracy level of 91.1%, which is an excellent classification. In contrast, the DPM approach divides the dataset into 80% training and 20% testing, employs an estimator of 500, and has a learning rate of 0.5. This leads to an excellent classification accuracy rate of 84.9%.

A Genetic algorithm aided hyper parameter optimization based ensemble model for respiratory disease prediction with Explainable AI.

In the current era, a lot of research is being done in the domain of disease diagnosis using machine learning. In recent times, one of the deadliest respiratory diseases, COVID-19, which causes serious damage to the lungs has claimed a lot of lives globally. Machine learning-based systems can assist clinicians in the early diagnosis of the disease, which can reduce the deadly effects of the disease. For the successful deployment of these machine learning-based systems, hyperparameter-based optimization and feature selection are important issues. Motivated by the above, in this proposal, we design an improved model to predict the existence of respiratory disease among patients by incorporating hyperparameter optimization and feature selection. To optimize the parameters of the machine learning algorithms, hyperparameter optimization with a genetic algorithm is proposed and to reduce the size of the feature set, feature selection is performed using binary grey wolf optimization algorithm. Moreover, to enhance the efficacy of the predictions made by hyperparameter-optimized machine learning models, an ensemble model is proposed using a stacking classifier. Also, explainable AI was incorporated to define the feature importance by making use of Shapely adaptive explanations (SHAP) values. For the experimentation, the publicly accessible Mexico clinical dataset of COVID-19 was used. The results obtained show that the proposed model has superior prediction accuracy in comparison to its counterparts. Moreover, among all the hyperparameter-optimized algorithms, adaboost algorithm outperformed all the other hyperparameter-optimized algorithms. The various performance assessment metrics, including accuracy, precision, recall, AUC, and F1-score, were used to assess the results.

Performance Comparasion of Adaboost and PSO Algorithms for Cervical Cancer Classification Using KNN Algorithm

Abstract. Cervical cancer impacts the female reproductive organs and stands as the second most common cancer among women worldwide. The World Health Organization (WHO) reports that annually, approximately 500,000 women are diagnosed with cervical cancer, and about 300,000 die from it. Many of these deaths result from insufficient early detection and preventive measures. There are four primary screening techniques for detecting cervical cancer cells: Hinselmann, Schiller, Cytology, and Biopsy. In this study, patient health history data is analyzed using the KNN algorithm, which is further optimized with Adaboost and PSO techniques. These optimization strategies are evaluated to identify the most precise model for detecting patterns in cervical cancer patients and predicting their screening outcomes. This study employs the RapidMiner tool. Findings reveal that the KNN algorithm effectively performs multilabel classification, and when optimized with PSO, there is a slight improvement in accuracy.Purpose: The aim of this research is to assess the performance of the K-Nearest Neighbor (KNN) algorithm in multilabel classification of cervical cancer and to optimize it using Adaboost and Particle Swarm Optimization (PSO) techniques. This research is significant as it offers a potentially more accurate diagnostic method for detecting cervical cancer using medical records.Methods/Study design/approach: The Cervical Cancer Risk Classification dataset from Kaggle was used in this study. Data preprocessing was conducted before applying the KNN algorithm. The KNN algorithm's performance was evaluated using a 10-fold cross-validation method, and results were measured using the Confusion Matrix. Additionally, the KNN algorithm was optimized using Adaboost and PSO to assess improvements in accuracy.Result/Findings: Experimental results indicated that the KNN algorithm achieved optimal accuracy with k=5, reaching 95.81%, 91.26%, 94.64%, and 93.01% for Hinselmann, Schiller, Cytology, and Biopsy targets, respectively. Adaboost did not significantly improve accuracy, while PSO slightly enhanced the Hinselmann target accuracy from 95.81% to 95.92%. The average training time for this experiment was around two minutes. These results demonstrate the effectiveness of the KNN algorithm in conducting multilabel classification for cervical cancer diagnosis.Novelty/Originality/Value: This research demonstrates that optimizing the KNN algorithm with PSO can enhance accuracy, though not significantly. This suggests potential for further development to improve cervical cancer diagnostic accuracy. Testing the model with the latest data and optimizing parameters may lead to better models and useful tools for early cervical cancer diagnosis.

Optimizing Performance of AdaBoost Algorithm through Undersampling and Hyperparameter Tuning on CICIoT 2023 Dataset

Optimizing Performance of AdaBoost Algorithm through Undersampling and Hyperparameter Tuning on CICIoT 2023 Dataset

An innovative combination of extra trees within adaboost for accurate prediction of agricultural water quality indices

The management of water quality plays a pivotal role in fostering sustainable development, especially in areas where groundwater serves as a vital resource for agricultural purposes. This study investigates methods to predict water quality indicators like potential salinity (PS) and sodium adsorption ratio (SAR) using data-driven techniques. It explores the AdaBoost algorithm and a hybrid model that combines AdaBoost with Extra Trees (ET). The research centers on the Sarayan region in southern Khorasan, Iran, involving the collection and analysis of groundwater quality data, which includes both physical and chemical parameters, spanning a period of four years. Pearson correlation analysis is utilized in this study to determine the critical input variables for predicting Sodium Adsorption Ratio (SAR) and Potential Salinity (PS). Significant performance improvements are demonstrated through the optimization of AdaBoost and the hybrid AdaBoost-Extra Trees (ET) models, achieved via grid search and Bayesian optimization. The results indicate that the hybrid model surpasses AdaBoost in performance. Specifically, the optimized AdaBoost model achieves a Test MSE of 3.57 and a Test R² of 0.87 for SAR prediction, whereas the hybrid model obtains a significantly better Test MSE of 0.87 and Test R² of 0.97. For the prediction of PS, the optimized AdaBoost model yields a Test MSE of 0.223 and a Test R² of 0.976, while the hybrid model delivers a significantly improved Test MSE of 0.018 and Test R² of 0.998. Feature importance analysis identifies critical patterns in the relevance of input parameters. This study underscores the efficacy of hybrid data-driven models in water quality prediction, showcasing their superior accuracy.

Prediction of Concrete Compressive Strength Based on ISSA-BPNN-AdaBoost.

Strength testing of concrete mainly relies on physical experiments, which are not only time-consuming but also costly. To solve this problem, machine learning has proven to be a promising technological tool in concrete strength prediction. In order to improve the accuracy of the model in predicting the compressive strength of concrete, this paper chooses to optimize the base learner of the ensemble learning model. The position update formula in the search phase of the sparrow search algorithm (SSA) is improved, and piecewise chaotic mapping and adaptive t-distribution variation are added, which enhances the diversity of the population and improves the algorithm's global search and convergence abilities. Subsequently, the effectiveness of the improvement strategy was demonstrated by comparing improved sparrow search algorithm (ISSA) with some commonly used intelligent optimization algorithms on 10 test functions. A back propagation neural network (BPNN) optimized with ISSA was used as the base learner, and the adaptive boosting (AdaBoost) algorithm was used to train and integrate multiple base learners, thus establishing an adaptive boosting algorithm based on back propagation neural network improved by the improved sparrow search algorithm (ISSA-BPNN-AdaBoost) concrete compressive strength prediction model. Then comparison experiments were conducted with other ensemble models and single models on two strength prediction datasets. The experimental results show that the ISSA-BPNN-AdaBoost model exhibits excellent results on both datasets and can accurately perform the prediction of concrete compressive strength, demonstrating the superiority of ensemble learning in predicting concrete compressive strength.

Forecasting Raw Material Yield in the Tanning Industry: A Machine Learning Approach

This study presents an innovative machine learning (ML) approach to predicting raw material yield in the leather tanning industry, addressing a critical challenge in production efficiency. Conducted at a tannery in southern Brazil, the research leverages historical production data to develop a predictive model. The methodology encompasses four key stages: data collection, processing, prediction, and evaluation. After rigorous analysis and refinement, the dataset was reduced from 16,046 to 555 high-quality records. Eight ML models were implemented and evaluated using Orange Data Mining software, version 3.38.0, including advanced algorithms such as Random Forest, Gradient Boosting, and neural networks. Model performance was assessed through cross-validation and comprehensive metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Coefficient of Determination (R2). The AdaBoost algorithm emerged as the most accurate predictor, achieving impressive results with an MAE of 0.042, MSE of 0.003, RMSE of 0.057, and R2 of 0.331. This research demonstrates the significant potential of ML techniques in enhancing raw material yield forecasting within the tanning industry. The findings contribute to more efficient forecasting processes, aligning with Industry 4.0 principles and paving the way for data-driven decision-making in manufacturing.