Bayesian Classifier Research Articles

Design and Development of Artificial Intelligence Based Applications Using Classification Algorithms in Datamining to Predict Early Diabetes

Diabetes is a chronic disease characterized by high blood sugar levels. High blood sugar levels can cause various serious complications, such as heart disease, stroke and kidney failure. Early detection of diabetes is essential to prevent this complication. This research is using experimental method. The experimental method is a research method carried out by deliberately manipulating the independent variable to see its effect on the dependent variable. In this case, the independent variable being manipulated is the machine learning algorithm used to predict diabetes. The dependent variable observed was the accuracy of the diabetes prediction model. From the research results, it was found that the Naive Bayes model had the highest accuracy, namely 81.5%. This model is better than the Decision Tree C.45 (72.7%), Random Forest (73.8%), and K-Nearest Neighbor (71.5%) models. Based on the research results, it can be concluded that the Naive Bayes model is the best model for predicting diabetes. The appropriate system development method for this research is the Rapid Application Development (RAD) method. Further research can be carried out to improve the accuracy of diabetes prediction models by using optimization models, such as Particle Swarm Optimization or Colony Optimization. In addition, further research can be carried out to develop diabetes prediction applications that can predict diseases that may be caused by diabetes, such as heart disease, stroke, kidney disease and blindness.

PCOS Risk Prediction: Integrated Algorithm Approach

Abstract: A significant challenge in women’s health is posed by Polycystic Ovary Syndrome (PCOS) because it is a difficult disorder to comprehend and exhibits various symptoms. Thisresearch project suggests the creation of a computerized prediction scheme for PCOS using machine learning algorithms and bioinformatics tools. The aim of this system is to give personalized risk assessment to women thus enabling early detection, and proactive management of PCOS. It combines other intelligible probabilities about PCOS with the use of user provided health data with Machine Learning models such as Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, Radial SVM, Linear SVM and KNeighbours Classifier. Additionally, it provides intuitive predictions regarding PCOS likelihood through ML models, which are based on Random Forest, Logistic Regression, Support Vector Machine (SVM), Naive Bayes (NB), Radial SVM (RSVM), Linear SVM (LSVM) and KNeighbours Classifier (KNC). By way of thorough assessment as well as comparison within these models the system intends to improve precision together with reliability during prediction of PCOS. The major objective is therefore to enable timely intervention along with individualized healthcare strategies that will promote better health outcomes for all women.

Performance evaluation and clinical application of the UA-5600 automatic dry chemistry urine analyzer in renal diseases.

Urine testing as a routine screening programme, abnormal test results can be suggestive to clinicians but can sometimes be overlooked, and the establishment of a diagnostic model can better assist clinicians in identifying potential problems. BLD (blood), LEU (leukocyte), PRO (protein) and GLU (glucose) are the four most important parameters in urine testing, and the accuracy of their results is a key concern for clinicians, so it is essential to verify the accuracy of their results. In this study, we evaluated the analytical and clinical performance of Mindray's automatic urine dry chemistry analyzer, the UA-5600 (Hereinafter referred to as the (UA-5600), and the test strips configured with the instrument, and developed a machine-learning (ML) model for kidney disease screening from the results of 11 parameters output from the UA-5600 with the aim of detecting abnormal urine test results. Urine samples from outpatients and inpatients at The First Affiliated Hospital of Sun Yat-sen University were collected from August to September 2022 to evaluate the performance of the Mindray UA-5600 dry chemistry analyzer and test strips. The evaluation of the UA-5600 and its test strips focused on the agreement of the urine BLD and LEU readings with the RBC (red blood cell) and WBC (white blood cell) counts obtained by the Mindray EH-2090 urine formed element analyzer. We also compared the PRO and GLU readings with the results of the Mindray BS-2800M biochemistry analyzer. Urine samples from outpatients and inpatients were retrospectively analysed and grouped according to LIS diagnosis. Additionally, eight ML models for kidney disease screening were developed using 11 parameters measured by the UA-5600. And the model was validated by the validation set. The UA-5600 had an 89.55% concordance rate for BLD and a 91.04% concordance rate for LEU compared to the EH-2090 analyzer. When benchmarked against the BS-2800M, the concordance rates for PRO and GLU were 94.14% and 95.20%, respectively. A total of 1,691 samples were used for the construction of the ML models, of which 346 patients (135 males and 211 females, age range: 18 to 98 years) diagnosed with renal disease, and 1,345 patients (397 males and 948 females, age range: 18 to 92 years) with non-renal disease diagnosed with other conditions. Notably, the Naïve Bayes (NB) model, which was built from the UA-5600 parameters, demonstrated superior predictive capabilities for renal disease, with an area under the receiver operating characteristic curve of 0.9470, a sensitivity of 0.7767, and a specificity of 0.9457. The Mindray UA-5600 demonstrates robust detection abilities for both BLD and LEU, and its results for PRO and GLU align closely with those obtained from the chemistry analyzer. The NB model has a good screening ability and shows promise as an effective screening tool.

Identification of biomarkers related to tryptophan metabolism in osteoarthritis

BackgroundOA (osteoarthritis) is a common joint disease characterized by damage to the articular cartilage and affects the entire joint tissue, with its main manifestations being joint pain, stiffness, and limited movement.Currently,we know that OA is a complex process composed of inflammatory and metabolic factors.It is reported that the occurrence and development of OA is related to the change of tryptophan metabolism.Therefore, the study of tryptophan metabolism and OA related genes is hopeful to find a new therapeutic target for OA. MethodsDifferentially expressed genes (DEGs) in GSE55235 were gained via differential expression analysis (OA samples vs normal samples). The tryptophan metabolic related DEGs (TMR-DEGs) were obtained by overlapping tryptophan metabolism related genes (TMRGs) and DEGs. Further, biomarkers were screening via Least absolute shrinkage and selection operator (LASSO), naive bayes (NB) and supportvector machine-recursive feature elimination (SVM-RFE) algorithm to establish a diagnostic model. Afterward, Gene Set Enrichment Analysis (GSEA) and drug prediction were performed based on diagnostic biomarkers by multiple software and databases. Eventually, expression level of biomarker public databases was verified using real-time quantitative polymerase chain reaction (RT-qPCR). ResultsThree tryptophan metabolism related biomarkers (TDO2, AOX1 and SLC3A2) were identified in OA. GSEA analysis demonstrated that biomarkers were associated with the function of ‘FoxO signaling pathway’, ‘spliceosome’ and ‘ribosome’. There were seven drugs with therapeutic potential on TDO2 and AOX1. Ultimately, compared with normal group, expression of AOX1 and SLC3A2 in OA group remarkable lower. ConclusionOverall, three tryptophan metabolic related diagnostic biomarkers that associated with OA were obtained, which provided a original direction for the diagnosis and treatment of OA.

Efficient Generalized Electroencephalography-Based Drowsiness Detection Approach with Minimal Electrodes.

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an electroencephalography (EEG)-based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM), the K nearest neighbor (KNN), the Naive Bayes (NB), the Decision Tree (DT), and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake and drowsy). Segmentation into 10 s intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries.

Predicting Student Academic Performance Using Neural Networks: Analyzing the Impact of Transfer Functions, Momentum and Learning Rate

Artificial Neural Networks (ANN) demonstrate a compelling application of AI in predicting student performance, a critical aspect for both students and educators. Accurate forecasting of student achievements enables educators to monitor progress effectively, allowing educational institutions to optimize outcomes and improve student results. This study focuses on leveraging ANN for predictive analytics in student performance. Through a detailed evaluation of transfer functions, optimizers, learning rates, and momentum values, the model achieves an impressive 98% accuracy with specific configurations: a learning rate of 0.005, momentum of 0.7, Sigmoid transfer function, and SGD optimizer. Additionally, the study performs a comparative analysis of various Machine Learning Algorithms, including ANN, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Decision Trees (DT), Naive Bayes (NB), and Logistic Regression (LR). Using data from 689 B.Tech students at IP University, the analysis reveals that ANN outperforms other algorithms with an accuracy of 97%. This high accuracy demonstrates the potential of ANN in educational settings, providing a valuable tool for educators to enhance student performance and outcomes.

Ensemble Learning with Pre-Trained Transformers for Crash Severity Classification: A Deep NLP Approach

Transfer learning has gained significant traction in natural language processing due to the emergence of state-of-the-art pre-trained language models (PLMs). Unlike traditional word embedding methods such as TF-IDF and Word2Vec, PLMs are context-dependent and outperform conventional techniques when fine-tuned for specific tasks. This paper proposes an innovative hard voting classifier to enhance crash severity classification by combining machine learning and deep learning models with various word embedding techniques, including BERT, RoBERTa, Word2Vec, and TF-IDF. Our study involves two comprehensive experiments using motorists’ crash data from the Missouri State Highway Patrol. The first experiment evaluates the performance of three machine learning models—XGBoost (XGB), random forest (RF), and naive Bayes (NB)—paired with TF-IDF, Word2Vec, and BERT feature extraction techniques. Additionally, BERT and RoBERTa are fine-tuned with a Bidirectional Long Short-Term Memory (Bi-LSTM) classification model. All models are initially evaluated on the original dataset. The second experiment repeats the evaluation using an augmented dataset to address the severe data imbalance. The results from the original dataset show strong performance for all models in the “Fatal” and “Personal Injury” classes but a poor classification of the minority “Property Damage” class. In the augmented dataset, while the models continued to excel with the majority classes, only XGB/TFIDF and BERT-LSTM showed improved performance for the minority class. The ensemble model outperformed individual models in both datasets, achieving an F1 score of 99% for “Fatal” and “Personal Injury” and 62% for “Property Damage” on the augmented dataset. These findings suggest that ensemble models, combined with data augmentation, are highly effective for crash severity classification and potentially other textual classification tasks.

Sample-by-sample Power Quality Disturbance classification based on Sliding Window Recursive Discrete Fourier Transform

Power Quality Disturbances (PQDs) are caused by large-scale grid connections of nonlinear loads and Distributed Generations (DG). They affect the electrical and electronics equipment performance and may cause serious accidents and economic losses. The classification of PQDs becomes a key issue for end-users in order to enhance the Power Quality (PQ) and comprises an important step in monitoring the Electric Power System (EPS). Accurate PQDs classification is crucial for improving the quality of power supply, monitoring the condition of power equipment, and mitigating power grid issues. In the literature, several methods for detecting and classifying PQDs have been proposed. However, these methods consume a significant amount of processing time due to the detection and sample storage steps required to classify each disturbance class. In this work, we propose a method for classifying PQDs on a sample-by-sample basis. The innovation of this method lies in its ability to classify PQDs for each individual sample, thereby eliminating the need for window-based (batch) processing. To do so, it is applied the Sliding Window Recursive Discrete Fourier Transform (SWRDFT) to real-time estimation of PQ parameters. For the classification stage, decision tree, Artificial Neural Networks (ANN), Ensemble and the Naive Bayes classifiers were employed. The proposed method using Ensemble achieved the most satisfactory results for six different types of PQDs (oscillatory transients, harmonics, notches, sags, spikes and swells), in which oscillatory transients and spikes were identified in the first monitored samples (sample 2 and 11 respectively), sags were identified in the 14th sample counting from the beginning of the disturbance, notches were captured from the 35th sample, and harmonics and swells were identified after the 113th sample.

Machine learning algorithms for predicting COVID-19 mortality in Ethiopia

BackgroundCoronavirus disease 2019 (COVID-19), a global public health crisis, continues to pose challenges despite preventive measures. The daily rise in COVID-19 cases is concerning, and the testing process is both time-consuming and costly. While several models have been created to predict mortality in COVID-19 patients, only a few have shown sufficient accuracy. Machine learning algorithms offer a promising approach to data-driven prediction of clinical outcomes, surpassing traditional statistical modeling. Leveraging machine learning (ML) algorithms could potentially provide a solution for predicting mortality in hospitalized COVID-19 patients in Ethiopia. Therefore, the aim of this study is to develop and validate machine-learning models for accurately predicting mortality in COVID-19 hospitalized patients in Ethiopia.MethodsOur study involved analyzing electronic medical records of COVID-19 patients who were admitted to public hospitals in Ethiopia. Specifically, we developed seven different machine learning models to predict COVID-19 patient mortality. These models included J48 decision tree, random forest (RF), k-nearest neighborhood (k-NN), multi-layer perceptron (MLP), Naïve Bayes (NB), eXtreme gradient boosting (XGBoost), and logistic regression (LR). We then compared the performance of these models using data from a cohort of 696 patients through statistical analysis. To evaluate the effectiveness of the models, we utilized metrics derived from the confusion matrix such as sensitivity, specificity, precision, and receiver operating characteristic (ROC).ResultsThe study included a total of 696 patients, with a higher number of females (440 patients, accounting for 63.2%) compared to males. The median age of the participants was 35.0 years old, with an interquartile range of 18–79. After conducting different feature selection procedures, 23 features were examined, and identified as predictors of mortality, and it was determined that gender, Intensive care unit (ICU) admission, and alcohol drinking/addiction were the top three predictors of COVID-19 mortality. On the other hand, loss of smell, loss of taste, and hypertension were identified as the three lowest predictors of COVID-19 mortality. The experimental results revealed that the k-nearest neighbor (k-NN) algorithm outperformed than other machine learning algorithms, achieving an accuracy of 95.25%, sensitivity of 95.30%, precision of 92.7%, specificity of 93.30%, F1 score 93.98% and a receiver operating characteristic (ROC) score of 96.90%. These findings highlight the effectiveness of the k-NN algorithm in predicting COVID-19 outcomes based on the selected features.ConclusionOur study has developed an innovative model that utilizes hospital data to accurately predict the mortality risk of COVID-19 patients. The main objective of this model is to prioritize early treatment for high-risk patients and optimize strained healthcare systems during the ongoing pandemic. By integrating machine learning with comprehensive hospital databases, our model effectively classifies patients' mortality risk, enabling targeted medical interventions and improved resource management.Among the various methods tested, the K-nearest neighbors (KNN) algorithm demonstrated the highest accuracy, allowing for early identification of high-risk patients. Through KNN feature identification, we identified 23 predictors that significantly contribute to predicting COVID-19 mortality. The top five predictors are gender (female), intensive care unit (ICU) admission, alcohol drinking, smoking, and symptoms of headache and chills.This advancement holds great promise in enhancing healthcare outcomes and decision-making during the pandemic. By providing services and prioritizing patients based on the identified predictors, healthcare facilities and providers can improve the chances of survival for individuals. This model provides valuable insights that can guide healthcare professionals in allocating resources and delivering appropriate care to those at highest risk.

Tongue Disease Prediction Based on Machine Learning Algorithms

The diagnosis of tongue disease is based on the observation of various tongue characteristics, including color, shape, texture, and moisture, which indicate the patient’s health status. Tongue color is one such characteristic that plays a vital function in identifying diseases and the levels of progression of the ailment. With the development of computer vision systems, especially in the field of artificial intelligence, there has been important progress in acquiring, processing, and classifying tongue images. This study proposes a new imaging system to analyze and extract tongue color features at different color saturations and under different light conditions from five color space models (RGB, YcbCr, HSV, LAB, and YIQ). The proposed imaging system trained 5260 images classified with seven classes (red, yellow, green, blue, gray, white, and pink) using six machine learning algorithms, namely, the naïve Bayes (NB), support vector machine (SVM), k-nearest neighbors (KNN), decision trees (DTs), random forest (RF), and Extreme Gradient Boost (XGBoost) methods, to predict tongue color under any lighting conditions. The obtained results from the machine learning algorithms illustrated that XGBoost had the highest accuracy at 98.71%, while the NB algorithm had the lowest accuracy, with 91.43%. Based on these obtained results, the XGBoost algorithm was chosen as the classifier of the proposed imaging system and linked with a graphical user interface to predict tongue color and its related diseases in real time. Thus, this proposed imaging system opens the door for expanded tongue diagnosis within future point-of-care health systems.

Analysis of the possibility of increasing the level of reliability of fire alarms systems through integration with video-based flame detection system

Classic Fire Alarm Systems (FAS) are characterized by a high level of false alarms in relation to the number of confirmed reports. To increase the level of reliability of operation of this type of system, it was proposed to integrate it with a Video-Based Flame Detection System (VBFDS). For this purpose, a video-based fire detection algorithm was designed. In addition, methods popular in the literature for increasing the reliability of such systems, such as color filtering, the Tracking Growth Object (TGO) factor, and the use of the Naive-Bayes (NB) classifier, were tested. The purpose of the article is to analyze these methods in comparison with the basic version of the algorithm, as well as the possibility of integrating Video-Based Flame Detection System (VBFDS) with classic FAS.

Ransomware Early Detection using Machine Learning Approach and Pre-Encryption Boundary Identification

The escalating ransomware threat has catalysed the formation of a sophisticated network of cybercriminal enterprises. Addressing this issue, our research provides a detailed exploration of the ransomware menace and an evaluation of contemporary detection methodologies. A successful ransomware attack leverages many factors: robust encryption methods that defy decryption, the anonymity of cyber currencies, and the widespread availability of ransomware kits that enable even inexperienced actors to launch attacks. Such dynamics have cultivated a niche for cybercriminal specialists in the digital underworld. In response to these challenges, our study proposes a detection framework based on machine learning, a domain where regression algorithms have gained popularity without yielding a definitive protective model. We employ API call analysis as the foundation to assess various machine learning classifiers' efficiency in identifying ransomware. The evaluation demonstrates that the Naive Bayes classifier underperforms due to suboptimal accuracy, making it unsuitable for this application. Conversely, Logistic Regression, with an AUC of 0.951, minimal training time, and substantial efficacy gains, emerges as a strong contender. The Decision Tree and Random Forest classifiers exhibit comparable proficiency; however, the Decision Tree's interpretability and Random Forest's computational swiftness present unique advantages. Superior still, SVM and Gradient Boosted Trees command the highest AUC and gains, albeit at the cost of increased training duration. Our findings affirm the pivotal role of API call analysis in ransomware detection and the potency of machine learning approaches in learning from extensive datasets to identify novel malware strains. Given the continual evolution of malware, detection methodologies must adapt correspondingly. This study's comparative analysis elucidates the trade-offs between accuracy, computational speed, and training time, guiding the selection of the optimal machine learning algorithm for robust ransomware detection.

On Entropic Learning from Noisy Time Series in the Small Data Regime.

In this work, we present a novel methodology for performing the supervised classification of time-ordered noisy data; we call this methodology Entropic Sparse Probabilistic Approximation with Markov regularization (eSPA-Markov). It is an extension of entropic learning methodologies, allowing the simultaneous learning of segmentation patterns, entropy-optimal feature space discretizations, and Bayesian classification rules. We prove the conditions for the existence and uniqueness of the learning problem solution and propose a one-shot numerical learning algorithm that-in the leading order-scales linearly in dimension. We show how this technique can be used for the computationally scalable identification of persistent (metastable) regime affiliations and regime switches from high-dimensional non-stationary and noisy time series, i.e., when the size of the data statistics is small compared to their dimensionality and when the noise variance is larger than the variance in the signal. We demonstrate its performance on a set of toy learning problems, comparing eSPA-Markov to state-of-the-art techniques, including deep learning and random forests. We show how this technique can be used for the analysis of noisy time series from DNA and RNA Nanopore sequencing.

Forecasting Sustainability Reports with Financial Performance Indicators using Random Forest for Feature Selection and Gradient Boosting for Learning

Problems such as excessive population growth, climate change, loss of biodiversity and resource scarcity in the world have led to an increase in global awareness in companies over the years. Lately companies have started to prefer sustainable models instead of existing economy models. As a result, they have started to prepare a sustainability report that includes social and environmental reports instead of just preparing an economic report. In recent years, the data of the circular economy model, which is a new approach for sustainable development to reach its goals, can also be followed through sustainability reports. Research shows that companies that attach importance to sustainability are seen as valuable by investors and sustainability indices are created in the stock markets of countries. This situation has increased the number of studies examining the impact of sustainability reporting or circular economy on financial performance. Firms want to be included in the sustainability indices in order to attract the attention of the potential investor. In this study, time series data of financial performance of companies in XUSRD are used. On the other hand, contrary to the statistical analyses in the literature, to predict whether companies will take part in XUSRD, a combination of two machine learning methods, namely random forest for feature selection and gradient boosting for learning, is used. In addition, to overcome the problem of data scarcity, the column-wise random shuffling method, which is a proven data augmentation technique in predicting stock market indices, has been used. The results show that the combination of random forest and gradient boosting reaches a test accuracy of 94.74% and outperforms state-of-the art models, namely, k-nearest neighbor, random forest, decision tree, support vector, naive Bayes classifiers that have been used in this study for comparison.

Ship Trajectory Classification Prediction at Waterway Confluences: An Improved KNN Approach

This study presents a method to support ship trajectory prediction at waterway confluences using historical Automatic Identification System (AIS) data. The method is meant to improve the recognition accuracy of ship behavior trajectory, assist in the proactive avoidance of collisions, and clarify ship collision responsibility, to ensure the safety of waterway transportation systems in the event of ship encounters induced by waterway confluence or channel limitation. In this study, the ship trajectory based on AIS data is considered from five aspects: time, location, heading, speed, and trajectory by using the piecewise cubic Hermite interpolation method and then quickly clustered by regional navigation rules. Then, an improved K-Nearest Neighbor Algorithm considering the sensitivity of data characteristics (SKNN) is proposed to predict the trajectory of ships, which considers the influence weights of various parameters on ship trajectory prediction. The method is trained and verified using the AIS data of the Yangtze River and Han River intersection in Wuhan. The results show that the accuracy of SKNN is better than that of conventional KNN and Naive Bayes (NB) in the same test case. The accuracy of the ship trajectory prediction method is above 99% and the performance metrics of the SKNN surpass those of both the conventional KNN and NB classifiers, which is helpful for early warning of collision encounters to ensure avoidance.

Prediction of Histological Grade of Oral Squamous Cell Carcinoma Using Machine Learning Models Applied to 18F-FDG-PET Radiomics.

The histological grade of oral squamous cell carcinoma affects the prognosis. In the present study, we performed a radiomics analysis to extract features from 18F-FDG PET image data, created machine learning models from the features, and verified the accuracy of the prediction of the histological grade of oral squamous cell carcinoma. The subjects were 191 patients in whom an 18F-FDG-PET examination was performed preoperatively and a histopathological grade was confirmed after surgery, and their tumor sizes were sufficient for a radiomics analysis. These patients were split in a 70%/30% ratio for use as training data and testing data, respectively. We extracted 2993 radiomics features from the PET images of each patient. Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) machine learning models were created. The areas under the curve obtained from receiver operating characteristic curves for the prediction of the histological grade of oral squamous cell carcinoma were 0.72, 0.71, 0.84, 0.74, and 0.73 for LR, SVM, RF, NB, and KNN, respectively. We confirmed that a PET radiomics analysis is useful for the preoperative prediction of the histological grade of oral squamous cell carcinoma.

Construction and validation of risk prediction models for pulmonary embolism in hospitalized patients based on different machine learning methods.

This study aims to apply different machine learning (ML) methods to construct risk prediction models for pulmonary embolism (PE) in hospitalized patients, and to evaluate and compare the predictive efficacy and clinical benefit of each model. We conducted a retrospective study involving 332 participants (172 PE positive cases and 160 PE negative cases) recruited from Guangdong Medical University. Participants were randomly divided into a training group (70%) and a validation group (30%). Baseline data were analyzed using univariate analysis, and potential independent risk factors associated with PE were further identified through univariate and multivariate logistic regression analysis. Six ML models, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost were developed. The predictive efficacy of each model was compared using the receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). Clinical benefit was assessed using decision curve analysis (DCA). Logistic regression analysis identified lower extremity deep venous thrombosis, elevated D-dimer, shortened activated partial prothrombin time, and increased red blood cell distribution width as potential independent risk factors for PE. Among the six ML models, the RF model achieved the highest AUC of 0.778. Additionally, DCA consistently indicated that the RF model offered the greatest clinical benefit. This study developed six ML models, with the RF model exhibiting the highest predictive efficacy and clinical benefit in the identification and prediction of PE occurrence in hospitalized patients.

Duration and resource constraint prediction models for construction projects using regression machine learning method

PurposeThe construction projects are highly subjected to uncertainties, which result in overruns in time and cost. Realistic estimates of workforce and duration are imperative for construction projects to attain their intended objectives. The aim of this study is to provide accurate labor and duration estimates for the construction projects, considering actual uncertainties.Design/methodology/approachThe dataset was formulated from the information collected from 186 construction projects through direct interviews, group discussions and questionnaire methods. The actual uncertainties and exposure conditions of construction activities were recorded. The data were verified with the standard guideline to remove the outliers. The prediction model was developed using support vector regression (SVR), a machine learning (ML) method. The performance was evaluated using the widely adopted regression metrics. Further, the cross validation was made with the visualization of residuals and predicted errors, ridge regression with transformed target distribution and a Gaussian Naive Bayes (NB) regressor.FindingsThe prediction models predicted the duration and labor requirements with the consideration of actual uncertainties. The residual plot indicated the appropriate use of SVR to develop the prediction model. The duration (DC) and resource constraint (RC) prediction models obtained 80 and 82% accuracy, respectively. Besides, the developed model obtained better accuracy for the training and test scores than the Gaussian NB regressor. Further, the range of the explained variance score and R2 was from 0.95 to 0.97, indicating better efficiency compared with other prediction models.Research limitations/implicationsThe researchers will utilize the research findings to estimate the duration and labor requirements under uncertain conditions and further improve the construction project management practices.Practical implicationsThe research findings will enable industry practitioners to accurately estimate the duration and labor requirements, considering historical uncertain conditions. A precise estimation of resources will ensure the attainment of the intended project outcomes.Social implicationsDelays in construction projects will be reduced by implementing the research findings, which significantly ensures the effective utilization of resources and attainment of other economic benefits. The policymakers will develop a guideline to develop a database to collect the uncertainties of the construction projects and relatively estimate the resource requirements.Originality/valueThis is the first study to consider the actual uncertainties of construction projects to develop RC and DC prediction models. The developed prediction models accurately estimate the duration and labor requirements with minimal computational time. The industry practitioners will be able to accurately estimate the duration and labor requirements using the developed models.

Generalisable sensor-free frustration detection in online learning environments using machine learning

Learning can generally be categorised into three domains, which include cognitive (thinking), affective (emotions or feeling) and psychomotor (physical or kinesthetic). In the learner model, acknowledging the affective aspects of learning is important for a range of learner outcomes, including motivation, persistence, and engagement. Learners’ affective states can be detected using physical (e.g. cameras) and physiological sensors (e.g., EEG) in online learning. Although these detectors demonstrate high accuracy, they raise privacy concerns for learners and present challenges in deploying them on a large scale to larger groups of students or in classroom settings. Consequently, researchers have designed an alternative method that can recognise students’ affective states at any point during online learning from their interaction with a computer-based learning platform (i.e. intelligent tutoring systems) without using any sensors. Existing sensor-free affect detectors however, are less accurate and not directly generalisable to other domains and systems. This research focuses on developing generalisable sensor-free affect detectors to identify students’ frustration during online learning using machine learning classifiers. The detectors were built by identifying minimal optimal features associated with frustration from the high-dimensional feature space through a series of experiments on a real-world students’ affective dataset, which are generalisable across various learning platforms and domains. To evaluate their accuracy and generalisability, the detectors’ performance was validated on two independent datasets collected from different educational institutions. The experimental results show that cost-sensitive Bayesian classifiers can achieve higher affect detection accuracies with a small number of generalisable features compared to other classifiers.

An approach-based machine learning and automated thermal images to predict the dark-cutting incidence in cattle management of healthcare supply chain

The healthcare supply chain is a network made up of various systems, processes, and elements that function and interact seamlessly to offer healthcare services and products. Food safety is an essential component of the healthcare supply chain. In the cattle industry, the healthcare supply chain contributes positively to the global economy through providing high-quality products such as milk and meat. Stress in cattle is one of main factor that cause low quality meat called “dark meat”. Numerous studies have been conducted on the development of different non-invasive methods based on Infrared Thermography Technology (IRT) to enhance the meat quality by detecting stress in cattle pre-slaughtering. These studies have the following issues: lack of automating in detecting body temperature of cattle and ignoring detecting stress with prediction dark meat incidence. The present study endeavors a new fully automated system for detecting stress, and dark meat incidence, incorporating the following new approaches: Multiview face detecting, Automatic eye localisation for detecting body temperature automatically employing computer vision and image processing, respectively. Furthermore, machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), Naïve Bayes (NB), and Decision Tree (DT) have been developed specifically for stress detection and the prediction of dark meat. To develop automated system, two forms of data were collected: statistical temperature and infrared thermal images. Infrared thermal images are used to develop Multiview face detection and Automatic eye localisation. Temperature data used to develop the machine learning model. Results reveal that Multiview face detection better than the current methods in term of Precision 0.99, Recall 0.91, F-score 0.95 with high True positive rate 0.90 and zero False-positive rate. Automatic eye localisation has high accuracy, with the following values: sensitivity 0.9780, precision 0.7212, F measure of 0.8024, and misclassification 0.0455. Lastly, results elaborate that the decision tree model can attain a notable level of accuracy in terms of specificity, recall, F-measure, and Area Under the Curve (AUC), all at an optimal rate of 98%.