Risk Level Prediction Research Articles

Hidden in Plain Sight: A Data-Driven Approach to Safety Risk Management for Highway Traffic Officers

Highway traffic officers (HTOs) are often exposed to life-threatening workplace incidents while performing their duties. However, scant research has been undertaken to address these safety concerns. This research explores case study data from highway incident reports (held by National Highways, a UK government company) and employs deep neural network (DNN) in unearthing patterns which inform safety decision makers on pertinent safety challenges confronting HTOs. A mixed philosophical stance of positivism and interpretivism was adopted to synthesise the findings made. A four-phase sequential method was implemented to evaluate the validity of the research viz.: (i) architectural design; (ii) data exploration; (iii) predictive modelling; and (iv) performance evaluation. The DNN model’s predictive performance is benchmarked against three other machine learning models, namely Support Vector Machines (SVM), Random Forest (RF), and Naïve Bayes (NB). The DNN model outperformed the other three models. Findings from the data exploration also show that most work operations undertaken by HTOs have a medium risk level with night shifts posing the greatest risk challenges. Carriageways and traffic management enclosures had the highest incident occurrence. This is the first study to uncover such hidden patterns and predict risk levels using a database specifically for HTOs. This study presents evidence-based information for proactive risk management for HTOs.

Prediction of aviation safety incident risk level based on ECSDNN

Prediction of aviation safety incident risk level is an important means of active risk management. Considering the high-dimensional complexity and class imbalance of massive aviation safety incident data, a prediction method for aviation safety incident risk level based on integrated cost-sensitive deep neural network (ECSDNN) is proposed. The feature representation of aviation safety incident data is realized by using the method of embedded coding of categorical attributes and splicing of numerical attributes; the cost-sensitive matrix and cost-sensitive loss function are designed by comprehensively considering the misclassification ratio and fixed cost, and the base classifier model based on cost-sensitive deep neural network (CSDNN) is constructed; the hard voting method is used to integrate multiple base classifiers with different parameters and performances to construct the integrated prediction model ECSDNN for aviation safety incident risk level. The experimental results on the Aviation Safety Incident Reporting System (ASRS) dataset show that compared with the optimal prediction ability of the baseline algorithm, the prediction accuracy of the ECSDNN model is improved 4.51%; compared with the single CSDNN base classifier, the prediction accuracy is improved 3.17%.

Climate, altitude, yield, and varieties drive lodging in sugarcane: A random forest approach to predict risk levels on a tropical island

Lodging is a critical factor in reducing sugarcane yields worldwide, mainly due to the selection of highly productive varieties. Understanding the response of yield and lodging to the combined effects of climate, sugarcane traits, and varieties has become a priority under climate change. The aim of this study was to better understand the influence of plant characteristics, climate, and soil conditions on the trade-off between sugarcane yield and lodging on the tropical Reunion Island. Data from a 14-year experimental network run by the eRcane breeding institute were used to build random-forest models to predict sugarcane yield and lodging classes, i.e. <10 %, 10–50 %, >50 % of lodging. Yield and lodging probability were then predicted across the island using climate change projections from 2015 to 2035. Both yield and lodging were highly influenced by the variety and characteristics (height and tillering) and climatic conditions. Areas on the island at high altitudes were subject to high probability of lodging (>50 %), while in areas with high wind speed, the risk of moderate lodging (10–50 %) increased. Overall, conditions or plant characteristics that favor higher yields increased lodging probability. Nevertheless, the correlation between yield and lodging probability varied considerably depending on the variety, highlighting the importance of sugarcane characteristics in resistance to lodging. This study highlights the fact that promoting more productive varieties in recent decades has led to an increase in lodging and identified critical environments on the island prone to increased risk of lodging.

An Ensemble Learning Algorithm with Hyperparameter Optimization (ELAHO) Model for Early Detection of Maternal Health Risk (MHR) Level Using Machine Learning

Despite the advancement in the healthcare system, maternal health risk remains high, which is the most challenging aspect nowadays. There is a need to develop an effective model for early detection, monitoring, and prediction of maternal health risk levels during pregnancy. The machine learning intelligence model has proven its effectiveness and robustness in providing accurate and reliable prediction, analysis, and interpretation of medical data, reducing several risk factors for early diagnosis in healthcare. In this research work, we proposed an ensemble learning algorithm with a hyperparameter optimization (ELAHO) model using machine learning algorithms to improve its robustness, effectiveness, and model performance. The proposed method uses a hybrid model of logistic regression and support vector machines (LG-SVM) to predict maternal health risk levels during pregnancy. The method utilized Python software for training, testing, and validation. We evaluated the performance of our proposed model using accuracy, precision, sensitivity, f1-score, and ROC-AUC score. The proposed models outperformed the conventional models and achieved 100% predictive accuracy. The proposed approach has the potential to be adapted as an intelligence-monitoring system for early medical diagnosis during pregnancy. The proposed techniques will help medical professionals make quick decisions accurately and enhance monitoring to improve the level of care offered to pregnant mothers and their unborn children.

A novel adaptive weight bi-directional long short-term memory (AWBi-LSTM) classifier model for heart stroke risk level prediction in IoT.

Stroke prediction has become one of the significant research areas due to the increasing fatality rate. Hence, this article proposes a novel Adaptive Weight Bi-Directional Long Short-Term Memory (AWBi-LSTM) classifier model for stroke risk level prediction for IoT data. To efficiently train the classifier, Hybrid Genetic removes the missing data with Kmeans Algorithm (HKGA), and the data are aggregated. Then, the features are reduced with independent component analysis (ICA) to reduce the dataset size. After the correlated features are identified using the T-test-based uniform distribution-gradient search rule-based elephant herding optimization for cluster analysis (GSRBEHO) (T-test-UD-GSRBEHO). Next, the fuzzy rule-based decisions are created with the T-test-UDEHOA correlated features to classify the risk levels accurately. The feature values obtained from the fuzzy logic are given to the AWBi-LSTM classifier, which predicts and classifies the risk level of heart disease and diabetes. After the risk level is predicted, the data is securely stored in the database. Here, the MD5-Elliptic Curve Cryptography (MD5-ECC) technique is utilized for secure storage. Testing the suggested risk prediction model on the Stroke prediction dataset reveals potential efficacy. By obtaining an accuracy of 99.6%, the research outcomes demonstrated that the proposed model outperforms the existing techniques.

Regional Disaster Risk Assessment Based on ARIMA Prediction and Comprehensive Evaluation Model

The occurrence of extreme weather events affects the natural economic and social security, and has a serious impact on some industries, so the prediction and evaluation of disaster risk level is particularly important. This paper collected data on nine indicators from 25 regions and divided them into four areas: extreme weather, natural, social, and economic. the ARIMA prediction model is used to predict the probability and intensity of extreme weather in the future. The combined weights of each index were calculated by Composite Weighting Method, including principal component analysis, entropy weight method and coefficient of variation method, and the Risk Assessment Index (RAI) formula was constructed, and then the WNSE prediction and evaluation model was constructed. It is divided into four risk levels by fuzzy cluster analysis. We use WNSE prediction and evaluation model to calculate New York City and Switzerland’s RAI and coverage levels. Using this prediction, we can assess the severity of the consequences of natural disasters and prevent or remedy them. The assessment of regional disaster risk levels can give relevant reference to the government, and the government can make reasonable resource allocation.

Prediction of Accident Risk Levels in Traffic Accidents Using Deep Learning and Radial Basis Function Neural Networks Applied to a Dataset with Information on Driving Events

A complex AI system must be worked offline because the training and execution phases are processed separately. This process often requires different computer resources due to the high model requirements. A limitation of this approach is the convoluted training process that needs to be repeated to obtain models with new data continuously incorporated into the knowledge base. Although the environment may be not static, it is crucial to dynamically train models by integrating new information during execution. In this article, artificial neural networks (ANNs) are developed to predict risk levels in traffic accidents with relatively simpler configurations than a deep learning (DL) model, which is more computationally intensive. The objective is to demonstrate that efficient, fast, and comparable results can be obtained using simple architectures such as that offered by the Radial Basis Function neural network (RBFNN). This work led to the generation of a driving dataset, which was subsequently validated for testing ANN models. The driving dataset simulated the dynamic approach by adding new data to the training on-the-fly, given the constant changes in the drivers’ data, vehicle information, environmental conditions, and traffic accidents. This study compares the processing time and performance of a Convolutional Neural Network (CNN), Random Forest (RF), Radial Basis Function (RBF), and Multilayer Perceptron (MLP), using evaluation metrics of accuracy, Specificity, and Sensitivity-recall to recommend an appropriate, simple, and fast ANN architecture that can be implemented in a secure alert traffic system that uses encrypted data.

Prediction of maternal health risk levels based on multiple machine learning algorithms

With the development and popularisation of the Internet of Things (IoT) technology, more and more medical devices have begun to connect with the Internet, forming IoT medical devices. Among them, for pregnant women's health risk monitoring, IoT devices can achieve remote monitoring, data transmission, intelligent analysis and other functions to provide more comprehensive health management services for pregnant women. To evaluate the model's effectiveness in predicting the health risk level of pregnant women, we use four metrics: precision, accuracy, recall, and F1 score. Where precision indicates the proportion of correctly predicted samples to the total number of samples; accuracy indicates the proportion of true cases to the number of all samples predicted to be positive; recall indicates the proportion of true cases to the number of all samples that are actually positive; and F1 score is the reconciled average of precision and recall. By using these metrics, we can more fully assess the predictive effectiveness of the model. In this paper, we use three models, decision tree, random forest and logistic regression, for training and testing. All three models are common machine learning algorithms, but they each have different strengths and weaknesses. By training and testing the three models, we found that the random forest model performed the best, with a prediction accuracy of 80%. In conclusion, this paper describes an IoT-based health risk monitoring system for pregnant women, trained and tested using three models: decision tree, random forest and logistic regression, it can provide more comprehensive health management services for pregnant women.

Accurate prediction of drug combination risk levels based on relational graph convolutional network and multi-head attention

BackgroundAccurately identifying the risk level of drug combinations is of great significance in investigating the mechanisms of combination medication and adverse reactions. Most existing methods can only predict whether there is an interaction between two drugs, but cannot directly determine their accurate risk level.MethodsIn this study, we propose a multi-class drug combination risk prediction model named AERGCN-DDI, utilizing a relational graph convolutional network with a multi-head attention mechanism. Drug-drug interaction events with varying risk levels are modeled as a heterogeneous information graph. Attribute features of drug nodes and links are learned based on compound chemical structure information. Finally, the AERGCN-DDI model is proposed to predict drug combination risk level based on heterogenous graph neural network and multi-head attention modules.ResultsTo evaluate the effectiveness of the proposed method, five-fold cross-validation and ablation study were conducted. Furthermore, we compared its predictive performance with baseline models and other state-of-the-art methods on two benchmark datasets. Empirical studies demonstrated the superior performances of AERGCN-DDI.ConclusionsAERGCN-DDI emerges as a valuable tool for predicting the risk levels of drug combinations, thereby aiding in clinical medication decision-making, mitigating severe drug side effects, and enhancing patient clinical prognosis.

Machine learning-driven predictions and interventions for cardiovascular occlusions.

Cardiovascular diseases remain a leading cause of global morbidity and mortality, with heart attacks and strokes representing significant health challenges. The accurate, early diagnosis and management of these conditions are paramount in improving patient outcomes. The specific disease, cardiovascular occlusions, has been chosen for the study due to the significant impact it has on public health. Cardiovascular diseases are a leading cause of mortality globally, and occlusions, which are blockages in the blood vessels, are a critical factor contributing to these conditions. By focusing on cardiovascular occlusions, the study aims to leverage machine learning to improve the prediction and management of these events, potentially helping to reduce the incidence of heart attacks, strokes, and other related health issues. The use of machine learning in this context offers the promise of developing more accurate and timely interventions, thus improving patient outcomes. We analyze diverse datasets to assess the efficacy of various machine learning algorithms in predicting heart attacks and strokes, comparing their performance to pinpoint the most accurate and reliable models. Additionally, we classify individuals by their predicted risk levels and examine key features that correlate with the incidence of cardiovascular events. The PyCaret machine learning library's Classification Module was key in developing predictive models which were evaluated with stratified cross-validation for reliable performance estimates. Our findings suggest that machine learning can significantly improve the prediction accuracy for heart attacks and strokes, facilitating earlier and more precise interventions. We also discuss the integration of machine learning models into clinical practice, addressing potential challenges and the need for healthcare professionals to interpret and apply these predictions effectively. The use of machine learning for risk stratification and the identification of modifiable factors may empower preemptive approaches to cardiovascular care, ultimately aiming to reduce the occurrence of life-threatening events and improve long-term patient health trajectories.

MathEagle: Accurate prediction of drug-drug interaction events via multi-head attention and heterogeneous attribute graph learning

BackgroundDrug-drug interaction events influence the effectiveness of drug combinations and can lead to unexpected side effects or exacerbate underlying diseases, jeopardizing patient prognosis. Most existing methods are restricted to predicting whether two drugs interact or the type of drug-drug interactions, while very few studies endeavor to predict the specific risk levels of side effects of drug combinations. MethodsIn this study, we propose MathEagle, a novel approach to predict accurate risk levels of drug combinations based on multi-head attention and heterogeneous attribute graph learning. Initially, we model drugs and three distinct risk levels between drugs as a heterogeneous information graph. Subsequently, behavioral and chemical structure features of drugs are utilized by message passing neural networks and graph embedding algorithms, respectively. Ultimately, MathEagle employs heterogeneous graph convolution and multi-head attention mechanisms to learn efficient latent representations of drug nodes and estimates the risk levels of pairwise drugs in an end-to-end manner. ResultsTo assess the effectiveness and robustness of the model, five-fold cross-validation, ablation experiments, and case studies were conducted. MathEagle achieved an accuracy of 85.85 % and an AUC of 0.9701 on the drug risk level prediction task and is superior to all comparative models. The MathEagle predictor is freely accessible at http://120.77.11.78/MathEagle/. ConclusionsThe experimental results indicate that MathEagle can function as an effective tool for predicting accurate risk of drug combinations, aiding in guiding clinical medication, and enhancing patient outcomes.

Diabetic prediction and classification of risk level using ODDTADC method in big data analytics

Diabetic prediction and classification of risk level using ODDTADC method in big data analytics

Intelligent salivary biosensors for periodontitis: in vitro simulation of oral oxidative stress conditions.

One of the most common oral diseases affecting millions of people worldwide is periodontitis. Usually, proteins in body fluids are used as biomarkers of diseases. This study focused on hydrogen peroxide, lipopolysaccharide (LPS), and lactic acid as salivary non-protein biomarkers for oxidative stress conditions of periodontitis. Electrochemical analysis of artificial saliva was done using Gamry with increasing hydrogen peroxide, bLPS, and lactic acid concentrations. Electrochemical impedance spectroscopy (EIS) and cyclic voltammetry (CV) were conducted. From EIS data, change in capacitance and CV plot area were calculated for each test condition. Hydrogen peroxide groups had a decrease in CV area and an increase in percentage change in capacitance, lipopolysaccharide groups had a decrease in CV area and a decrease in percentage change in capacitance, and lactic acid groups had an increase of CV area and an increase in percentage change in capacitance with increasing concentrations. These data showed a unique combination of electrochemical properties for the three biomarkers. Scanning electron microscopy (SEM) with energy dispersive spectroscopy (EDS) employed to observe the change in the electrode surface and elemental composition data present on the sensor surface also showed a unique trend of elemental weight percentages. Machine learning models using hydrogen peroxide, LPS, and lactic acid electrochemical data were applied for the prediction of risk levels of periodontitis. The detection of hydrogen peroxide, LPS, and lactic acid by electrochemical biosensors indicates the potential to use these molecules as electrochemical biomarkers and use the data for ML-driven prediction tool for the periodontitis risk levels.

A two-stage clustering ensemble algorithm applicable to risk assessment of railway signaling faults

Knowledge graph (KG) modeling constructs a connected network of hazard/fault events by drawing on historical reports, helping extract risk factors and propagation features in railway signaling safety. For the huge graph structure of the knowledge system, efficiently and accurately transforming the event information with text for risk level prediction is the crucial topic of this paper. To establish a quantitative risk assessment method based on KG modeling, we innovatively introduce text clustering technology to intelligently divide the entity short text data set in the KG, assign standardized entity names to the cluster partitions, and then complete the calculation and analysis according to the characteristic parameter formula, greatly reducing the labor and time consumption of data annotation and approximate text repetitive processing. Significantly, a two-stage clustering ensemble algorithm (TSCEA) integrating base clusterer optimization and hierarchical clustering prediction is proposed, whose innovative approach lies in describing sample similarity by the co-association matrix, while considering the contribution discrepancy of samples for decision-making. Specifically, Stage One selects and optimizes various base clusterers with different method kernels, while Stage Two emphasizes the contribution discrepancy of the cluster core and the cluster halo to make the final clustering decision, with the ensemble strategy serving as the bridge between these two. The KG established on field investigation is used to complete the experiment and analysis of the novel algorithm. Another clustering ensemble algorithm (based on a direct weighting strategy) and each base clusterer are applied to verify clustering performance, while the evaluation depends on external indicators. The results indicate that the proposed clustering ensemble algorithm outperforms others in various indicators, significantly improving clustering accuracy and robustness.

Personalized Infant Risk Prediction for Severe Respiratory Syncytial Virus Lower Respiratory Tract Infection Requiring Intensive Care Unit Admission.

Currently, there are no available tools to identify infants at the highest risk of significant morbidity and mortality from respiratory syncytial virus (RSV) lower respiratory tract infection (LRTI) who would benefit most from RSV prevention products. The objective was to develop and internally validate a personalized risk prediction tool for use among all newborns that uses readily available birth/postnatal data to predict RSV LRTI requiring intensive care unit (ICU) admission. We conducted a population-based birth cohort study of infants born from 1995 to 2007, insured by the Tennessee Medicaid Program, and who did not receive RSV immunoprophylaxis during the first year of life. The primary outcome was severe RSV LRTI requiring ICU admission during the first year of life. We built a multivariable logistic regression model including demographic and clinical variables available at or shortly after birth to predict the primary outcome. In a population-based sample of 429 365 infants, 713 (0.2%) had severe RSV LRTI requiring ICU admission. The median age of admission was 66 days (interquartile range, 37-120). Our tool, including 19 variables, demonstrated good predictive accuracy (area under the curve, 0.78; 95% confidence interval, 0.77-0.80) and identified infants who did not qualify for palivizumab, based on American Academy of Pediatrics guidelines, but had higher predicted risk levels than infants who qualified (27% of noneligible infants with >0.16% predicted probabilities [lower quartile for eligible infants]). We developed a personalized tool that identified infants at increased risk for severe RSV LRTI requiring ICU admission, expected to benefit most from immunoprophylaxis.

Fuzzy-Ontology based knowledge driven disease risk level prediction with optimization assisted ensemble classifier

Modern medicinal analysis is a complex procedure, requiring precise patient data, scientific knowledge obtained over numerous years and a theoretical understanding of related medical literature. To improve the accuracy and to reduce the time for diagnosis, clinical decision support systems (DSS) were introduced, which incorporate data mining schemes for enhancing the disease diagnosing accuracy. This work proposes a new disease-predicting model that involves 3 stages. Initially, “improved stemming and tokenization” are carried out in the pre-processing stage. Then, the “Fuzzy ontology, improved mutual information (MI), and correlation features” are extracted. Then, prediction is carried out via ensemble classifiers that include “improved Fuzzy logic, Long Short Term Memory (LSTM), Deep Convolution Neural Network (DCNN), and Bidirectional Gated Recurrent Unit (Bi-GRU)”.The outcomes from improved fuzzy logic, LSTM, and DCNN are further classified via Bi-GRU which offers the results. Specifically, Bi-GRU weights are optimally tuned using Deer Hunting Update Explored Arithmetic Optimization (DHUEAO). Finally, the efficiency of the proposed work is determined concerning a variety of metrics.

Deep Learning for Holistic Mental Illness Diagnosis with Multimodal Imaging

Detecting and diagnosing mental illnesses is a complex task due to the heterogeneous nature of these conditions, which encompass various types and subtypes. Timely identification and diagnosis are essential for advancing mental health research, improving early intervention, and developing effective therapies. However, existing methods have primarily focused on categorizing and diagnosing single mental illness types, often prioritizing patient survival over comprehensive treatment. This research introduces a deep learning-based approach to establish a universal framework for the detection, diagnosis, symptom-based prediction, and screening of diverse mental illnesses, their subtypes, and associated factors using a diverse dataset comprising images and clinical scans. The proposed architecture leverages a VGG-19-based 3D-convolutional neural network for robust feature extraction and employs a random forest algorithm for regression tasks. To create a comprehensive dataset, we incorporate results from the DAIC-WOZ laboratory dataset, imaging studies, and biopsy reports, moving beyond sole reliance on clinical images. The initial step involves distinguishing between healthy and unhealthy depression, sleep disorder, Alzheimer's, schizophrenia, and epilepsy conditions and subsequently classifying depression, sleep disorder, Alzheimer's, schizophrenia, and epilepsy cases into their specific subtypes while assessing their severity and growth patterns. Our model is designed to predict risk levels at various time intervals, utilizing the available pertinent factors consistently across different diagnostic tools. Our results demonstrate promising accuracy, with a 98.80% success rate in classifying them into their respective subtypes, a sensitivity of 98.24%, and a specificity of 98.49%. This research represents a significant step toward a more holistic and precise approach to mental illness detection, diagnosis, and management, performing 4.74% better than other state-of-the-art AI models and offering potential benefits for individuals and mental health professionals alike.

Graph-based two-level indicator system construction method for smart city information security risk assessment

&lt;p&gt;The rapid development of urban informatization has led to a deep integration of advanced information technology into urban life. Many decision-makers are starting to alleviate the adverse effects of this informatization process through risk assessment. However, existing methods cannot effectively analyze internal and hierarchical relationships because of the excessive number of indicators. Thus, it is necessary to construct an indicator's dependency graph and conduct a comprehensive hierarchical analysis to solve this problem. In this study, we proposed a graph-based two-level indicator system construction method. First, a random forest was used to extract the indicators' dependency graph from missing data. Then, spectral clustering was used to separate the graph and form a functional subgraph. Finally, PageRank was used to calculate the prioritization for each subgraph's indicator, and the two-level indicator system was established. To verify the performance, we took China's 25 smart cities as examples. For the simulation of risk level prediction, we compared our method with some machine learning algorithms, such as ridge regression, Lasso regression, support vector regression, decision trees, and multi-layer perceptron. Results showed that the two-level indicator system is superior to the general indicator system for risk assessment.&lt;/p&gt;

Deep Bi-LSTM with Binary Harris Hawkes Algorithm-Based Heart Risk Level Prediction

Deep Bi-LSTM with Binary Harris Hawkes Algorithm-Based Heart Risk Level Prediction

Correlated feature-based diabetes and heart disease risk-level classification in IoT environment using PLD-SSL-RBM

The survival of patients’ deaths owing to Heart Disease (HD) could be improved with the assistance of an enhanced approach for predicting the risk of diabetes and HD. Nevertheless, such schemes are developed rarely. Thus, this paper proposes a new Power Lognormal Distribution-Semi-Supervised Learning-centric Restricted Boltzmann Machine (PLD-SSL-RBM) diabetes and HD risk level prediction model for IoT data. The missing data are removed by partial Derivation of the Hamilton-Cluster Centered-K-means Clustering (DH-CC-KC) to efficiently train the classifier and then, the data are aggregated. Next, to reduce the dataset size, the features are reduced with Shell Sort-Principal Component Analysis (SS-PCA). Then, the fuzzy rule-based decisions are created with the T-test-centric Uniform Distribution-Elephant Herd Optimization Algorithm (T-test-UDEHOA) Correlated Features (CF) to classify the risk levels accurately. Lastly, the risk levels of HD and diabetes are predicted; in addition, by employing the Elliptic Curve Cryptography (ECC)7encryption technique, the data is securely stored on the medical database. The proposed risk prediction model’s performance is analyzed on the Framingham dataset. As per the experimental outcomes, when analogized to the prevailing methodologies, the proposed technique attained a higher accuracy of 99.55%.