Ensemble Machine Learning Model Research Articles

Прогнозирование результатов кинопроката с помощью машинного обучения

The subject of the research is the results of distribution of Russian national films. The purpose of the study is to classify projects according to the principle of their success/failure at the box office and predict the characteristics of the box office. The objectives of the study are to create algorithms for selecting (classifying) potentially successful projects into an investment portfolio and predicting (regression) rental characteristics: the number of views, payback, viewer rating. The technique is based on the application of ensemble machine learning models. The empirical base of the study is the entire set of Russian national films in distribution from 2004 to April 2022 (N=1469) and from May 2022 to April 2023 (N=194). Achieved accuracy of 0.95 and 0.89 for two and four class classification and high performance ROC_AUC = 0.97 for two class model and 0.94 – 0.98 for four class model. More complex metamodels (superensembles) can achieve an accuracy of 0.97-0.98 for a two-class classification and 0.96 for a four-class one. Complex regression metamodels predict the absolute values of payback, fees, views with a coefficient of determination (R2) in the range of 0.97-0.98 using synthetic data. As a result, it became possible to form investment portfolios of film projects with an annual historical return of up to 139%. The scope of application is to ensure the selection of films for investment "portfolios of film projects" of state (Ministry of Culture, Cinema Fund) and private investors. Machine learning models can be adapted to the conditions of global and foreign markets by increasing the number of model features, expanding the arsenal of machine learning methods, including the analysis of texts, images, videos, and user data of social networks.

Performance of Path Loss Models over Mid-Band and High-Band Channels for 5G Communication Networks: A Review

The rapid development of 5G communication networks has ushered in a new era of high-speed, low-latency wireless connectivity, as well as the enabling of transformative technologies. However, a crucial aspect of ensuring reliable communication is the accurate modeling of path loss, as it directly impacts signal coverage, interference, and overall network efficiency. This review paper critically assesses the performance of path loss models in mid-band and high-band frequencies and examines their effectiveness in addressing the challenges of 5G deployment. In this paper, we first present the summary of the background, highlighting the increasing demand for high-quality wireless connectivity and the unique characteristics of mid-band (1–6 GHz) and high-band (>6 GHz) frequencies in the 5G spectrum. The methodology comprehensively reviews some of the existing path loss models, considering both empirical and machine learning approaches. We analyze the strengths and weaknesses of these models, considering factors such as urban and suburban environments and indoor scenarios. The results highlight the significant advancements in path loss modeling for mid-band and high-band 5G channels. In terms of prediction accuracy and computing effectiveness, machine learning models performed better than empirical models in both mid-band and high-band frequency spectra. As a result, they might be suggested as an alternative yet promising approach to predicting path loss in these bands. We consider the results of this review to be promising, as they provide network operators and researchers with valuable insights into the state-of-the-art path loss models for mid-band and high-band 5G channels. Future work suggests tuning an ensemble machine learning model to enhance a stable empirical model with multiple parameters to develop a hybrid path loss model for the mid-band frequency spectrum.

Fairness of Machine Learning Algorithms for Predicting Foregone Preventive Dental Care for Adults

Access to routine dental care prevents advanced dental disease and improves oral and overall health. Identifying individuals at risk of foregoing preventive dental care can direct prevention efforts toward high-risk populations. To predict foregone preventive dental care among adults overall and in sociodemographic subgroups and to assess the algorithmic fairness. This prognostic study was a secondary analyses of longitudinal data from the US Medical Expenditure Panel Survey (MEPS) from 2016 to 2019, each with 2 years of follow-up. Participants included adults aged 18 years and older. Data analysis was performed from December 2022 to June 2023. A total of 50 predictors, including demographic and socioeconomic characteristics, health conditions, behaviors, and health services use, were assessed. The outcome of interest was foregoing preventive dental care, defined as either cleaning, general examination, or an appointment with the dental hygienist, in the past year. Among 32 234 participants, the mean (SD) age was 48.5 (18.2) years and 17 386 participants (53.9%) were female; 1935 participants (6.0%) were Asian, 5138 participants (15.9%) were Black, 7681 participants (23.8%) were Hispanic, 16 503 participants (51.2%) were White, and 977 participants (3.0%) identified as other (eg, American Indian and Alaska Native) or multiple racial or ethnic groups. There were 21 083 (65.4%) individuals who missed preventive dental care in the past year. The algorithms demonstrated high performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.84 (95% CI, 0.84-0.85) in the overall population. While the full sample model performed similarly when applied to White individuals and older adults (AUC, 0.88; 95% CI, 0.87-0.90), there was a loss of performance for other subgroups. Removing the subgroup-sensitive predictors (ie, race and ethnicity, age, and income) did not impact model performance. Models stratified by race and ethnicity performed similarly or worse than the full model for all groups, with the lowest performance for individuals who identified as other or multiple racial groups (AUC, 0.76; 95% CI, 0.70-0.81). Previous pattern of dental visits, health care utilization, dental benefits, and sociodemographic characteristics were the highest contributing predictors to the models' performance. Findings of this prognostic study using cohort data suggest that tree-based ensemble machine learning models could accurately predict adults at risk of foregoing preventive dental care and demonstrated bias against underrepresented sociodemographic groups. These results highlight the importance of evaluating model fairness during development and testing to avoid exacerbating existing biases.

Influence of chemical constituents of binder and activator in predicting compressive strength of fly ash-based geopolymer concrete using firefly-optimized hybrid ensemble machine learning model

This study focuses on investigating the impact of chemical constituents in binders and activators on the prediction of strength, particularly proposing a novel hybrid ensemble model that synergizes the strengths of three base models optimized using the Firefly Algorithm. The primary objective is to enhance the accuracy of predicting the compressive strength (CS) of fly ash-based (FA) geopolymer concrete (GPC). The dataset employed encompasses comprehensive material and chemical information, facilitating a predictive approach linking factors to strength. Rigorous preprocessing techniques are employed to eliminate outliers and ensure data integrity. Multivariate analyses are executed to visually represent the dataset's structure. The development of the hybrid ensemble model is realized through a stacking strategy, integrating the predictive capabilities of individual models. Thorough evaluation using diverse statistical metrics validates the superiority of the hybrid model compared to standalone base models, underscoring its enhanced precision in CS prediction for FA-based GPC. Sobol and FAST global sensitivity analysis was also employed to find the influence of input parameters on strength. Extra water content and curing temperature with Sobol indices of 67.2% and 42.5%, and FAST indices of 65.2% and 45% were found to be the most sensitive parameters of the studied database. Among the chemical constituents of binders and activators, the SiO2 content and CaO content of FA exhibited greater sensitivity, impacting the CS. On the other hand, the Na2O, Al2O3, and Fe2O3 content of fly ash and the SiO2 and Na2O percentage of sodium silicate were found to have a relatively lower impact.

Towards white box modeling of compressive strength of sustainable ternary cement concrete using explainable artificial intelligence (XAI)

Since the production of sustainable ternary cement concrete (TCC) involves a large range of constituents which can affect the compressive strength (CS) of TCC in different ways, the evaluation of CS in a unified manner is necessary. Unlike the black box machine learning (ML) models, the predictions of CS of TCC using local explanations to global understanding with explainable artificial intelligence (XAI) models have been investigated in a systematic approach by means of SHapley Additive exPlanations (SHAP). For this, two conventional ML and three ensemble ML models were used. Hyper-parameter tuning was also carried out. The ensemble ML models had a higher accuracy than the conventional ML models. Taylor diagram, model evaluation parameters and the SHAP values were used to interpret machine learning model predictivity. From insights obtained through local explanations, it can be concluded that predictions made by black box models should be used carefully.

Combining clinical notes with structured electronic health records enhances the prediction of mental health crises

An automatic prediction of mental health crises can improve caseload prioritization and enable preventative interventions, improving patient outcomes and reducing costs. We combine structured electronic health records (EHRs) with clinical notes from 59,750 de-identified patients to predict the risk of mental health crisis relapse within the next 28days. The results suggest that an ensemble machine learning model that relies on structured EHRs and clinical notes when available, and relying solely on structured data when the notes are unavailable, offers superior performance over models trained with either of the two data streams alone. Furthermore, the study provides key takeaways related to the required amount of clinical notes to add value in predictive analytics. This study sheds light on the untapped potential of clinical notes in the prediction of mental health crises and highlights the importance of choosing an appropriate machine learning method to combine structured and unstructured EHRs.

A Novel Approach for Detection of DoS / DDoS Attack in Network Environment using Ensemble Machine Learning Model

One of the most serious threat to network security is Denial of service (DOS) attacks. Internet and computer networks are now important parts of our businesses and daily lives. Malicious actions have become more common as our reliance on computers and communication networks has grown. Network threats are a big problem in the way people communicate today. To make sure that the networks work well and that users' information is safe, the network data must be watched and analysed to find malicious activities and attacks. Flooding may be the simplest DDoS assault. Computer networks and services are vulnerable to DoS and DDoS attacks. These assaults flood target systems with malicious traffic, making them unreachable to genuine users. The work aims to enhance the resilience of network infrastructures against these attacks and ensure uninterrupted service delivery. This research develops and evaluates enhanced DoS/DDoS detection methods. DoS attacks usually stop or slow down legal computer or network use. Denial-of-service (DoS) attacks prevent genuine users from accessing and using information systems and resources. The OSI model's layers make up the computer network. Different types of DDoS strikes target different layers. The Network Layer can be broken by using ICMP Floods or Smurf Attacks. The Transport layer can be attacked using UDP Floods, TCP Connection Exhaustion, and SYN Floods. HTTP-encrypted attacks can be used to get through to the application layer. DoS/DDoS attacks are malicious attacks. Protect network data from harm. Computer network services are increasingly threatened by DoS/DDoS attacks. Machine learning may detect prior DoS/DDoS attacks. DoS/DDoS attacks proliferate online and via social media. Network security is IT's top priority. DoS and DDoS assaults include ICMP, UDP, and the more prevalent TCP flood attacks. These strikes must be identified and stopped immediately. In this work, a stacking ensemble method is suggested for detecting DoS/DDoS attacks so that our networked data doesn't get any worse. This paper used a method called "Ensemble of classifiers," in which each class uses a different way to learn. In proposed methodology Experiment#1 , I used the Home Wifi Network Traffic Collected and generated own Dataset named it as MywifiNetwork.csv, whereas in proposed methodology Experiment#2, I used the kaggle repository “NSL-KDD benchmark dataset” to perform experiments in order to find detection accuracy of dos attack detection using python language in jupyter notebook. The system detects attack-type or legitimate-type of network traffic during detection ML classification methods are used to compare how well the suggested system works. The results show that when the ensembled stacking learning model is used, 99% of the time it is able to find the problem. In proposed methodology two Experiments are implemented for comparing detection accuracy with the existing techniques. Compared to other measuring methods, we get a big step forward in finding attacks. So, our model gives a lot of faith in securing these networks. This paper will analyse the behaviour of network traffics.

A neuroimaging biomarker for Individual Brain-Related Abnormalities In Neurodegeneration (IBRAIN): a cross-sectional study

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder that poses a worldwide public health challenge. A neuroimaging biomarker would significantly improve early diagnosis and intervention, ultimately enhancing the quality of life for affected individuals and reducing the burden on healthcare systems. Cross-sectional and longitudinal data (10,099 participants with 13,380 scans) from 12 independent datasets were used in the present study (this study was performed between September 1, 2021 and February 15, 2023). The Individual Brain-Related Abnormalities In Neurodegeneration (IBRAIN) score was developed via integrated regional- and network-based measures under an ensemble machine learning model based on structural MRI data. We systematically assessed whether IBRAIN could be a neuroimaging biomarker for AD. IBRAIN accurately differentiated individuals with AD from NCs (AUC=0.92) and other neurodegenerative diseases, including Frontotemporal dementia (FTD), Parkinson's disease (PD), Vascular dementia (VaD) and Amyotrophic Lateral Sclerosis (ALS) (AUC=0.92). IBRAIN was significantly correlated to clinical measures and gene expression, enriched in immune process and protein metabolism. The IBRAIN score exhibited a significant ability to reveal the distinct progression of prodromal AD (i.e., Mild cognitive impairment, MCI) (Hazard Ratio (HR)=6.52 [95% CI: 4.42∼9.62], p<1×10-16), which offers similar powerful performance with Cerebrospinal Fluid (CSF) Aβ (HR=3.78 [95% CI: 2.63∼5.43], p=2.13×10-14) and CSF Tau (HR=3.77 [95% CI: 2.64∼5.39], p=9.53×10-15) based on the COX and Log-rank test. Notably, the IBRAIN shows comparable sensitivity (beta=-0.70, p<1×10-16) in capturing longitudinal changes in individuals with conversion to AD than CSF Aβ (beta=-0.26, p=4.40×10-9) and CSF Tau (beta=0.12, p=1.02×10-5). Our findings suggested that IBRAIN is a biologically relevant, specific, and sensitive neuroimaging biomarker that can serve as a clinical measure to uncover prodromal AD progression. It has strong potential for application in future clinical practice and treatment trials. Science and Technology Innovation 2030 Major Projects, the National Natural Science Foundation of China, Beijing Natural Science Funds, the Fundamental Research Funds for the CentralUniversity, and the Startup Funds for Talents at Beijing Normal University.

Integrated radiogenomics models predict response to neoadjuvant chemotherapy in high grade serous ovarian cancer

High grade serous ovarian carcinoma (HGSOC) is a highly heterogeneous disease that typically presents at an advanced, metastatic state. The multi-scale complexity of HGSOC is a major obstacle to predicting response to neoadjuvant chemotherapy (NACT) and understanding critical determinants of response. Here we present a framework to predict the response of HGSOC patients to NACT integrating baseline clinical, blood-based, and radiomic biomarkers extracted from all primary and metastatic lesions. We use an ensemble machine learning model trained to predict the change in total disease volume using data obtained at diagnosis (n = 72). The model is validated in an internal hold-out cohort (n = 20) and an independent external patient cohort (n = 42). In the external cohort the integrated radiomics model reduces the prediction error by 8% with respect to the clinical model, achieving an AUC of 0.78 for RECIST 1.1 classification compared to 0.47 for the clinical model. Our results emphasize the value of including radiomics data in integrative models of treatment response and provide methods for developing new biomarker-based clinical trials of NACT in HGSOC.

Ensemble learning model identifies adaptation classification and turning points of river microbial communities in response to heatwaves.

Heatwaves are a global issue that threaten microbial populations and deteriorate ecosystems. However, how river microbial communities respond to heatwaves and whether and how high temperatures exceed microbial adaptation remain unclear. In this study, we proposed four types of pulse temperature-induced microbial responses and predicted the possibility of microbial adaptation to high temperature in global rivers using ensemble machine learning models. Our findings suggest that microbial communities in parts of South American (e.g., Brazil and Chile) and Southeast Asian (e.g., Vietnam) countries are likely to change due to heatwave disturbance from 25 to 37°C for consecutive days. Furthermore, the microbial communities in approximately 48.4% of the global river gauge stations are prone to fast stress inadaptation, with approximately 76.9% of these stations expected to exceed microbial adaptation after heatwave disturbances. If emissions of particulate matter with sizes not more than 2.5 μm (PM2.5, an indicator of human activities) increase by twofold, the number of global rivers associated with the fast stress adaptation type will decrease by ~13.7% after heatwave disturbances. Understanding microbial responses is crucially important for effective ecosystem management, especially for fragile and sensitive rivers facing heatwave events.

Accurately predicting the mechanical behavior of deteriorated reinforced concrete components using natural intelligence-integrated Machine learners

Corrosion in reinforced concrete components promotes the degradation of structural durability during the service life of buildings. In this paper, the performance of several advanced prediction and ensemble machine learning models is compared in terms of their respective abilities to predict the strength of deteriorated reinforced concrete components. The models compared include three single models, namely least square support vector regression (LSSVR), radial basic function neural network (RBFNN), and multivariate adaptive regression splines (MARS), and two ensemble models, namely logit boosting (LogitBoost) and the extreme gradient boosting technique (XGBoost). All machine learning models were trained using an equilibrium optimizer (EO). A dataset consisting of 140 data samples collected from residential buildings in southern Vietnam was used to establish, validate, and test the machine learning methods using a cross-validation method. The experimental results, supported by statistical tests, demonstrate that the hybrid EO-LSSVR achieved the best prediction performance in terms of root mean square error (110.98), mean absolute percentage error (2.66%), mean absolute error (44.38), and coefficient of determination (0.958). The new machine learning models proposed in this study effectively overcome limitations inherent in theoretical and experimental studies and help increase prediction accuracy. Therefore, these models offer a promising tool for obtaining early and accurate estimates of structural durability, which are critical to scheduling and performing effective building maintenance.

Does noise affect housing prices? A case study in the urban area of Thessaloniki

Real estate markets depend on various methods to predict housing prices, including models that have been trained on datasets of residential or commercial properties. Most studies endeavor to create more accurate machine learning models by utilizing data such as basic property characteristics as well as urban features like distances from amenities and road accessibility. Even though environmental factors like noise pollution can potentially affect prices, the research around this topic is limited. One of the reasons is the lack of data. In this paper, we reconstruct and make publicly available a general purpose noise pollution dataset based on published studies conducted by the Hellenic Ministry of Environment and Energy for the city of Thessaloniki, Greece. Then, we train ensemble machine learning models, like XGBoost, on property data for different areas of Thessaloniki to investigate the way noise influences prices through interpretability evaluation techniques. Our study provides a new noise pollution dataset that not only demonstrates the impact noise has on housing prices, but also indicates that the influence of noise on prices significantly varies among different areas of the same city.

Smart reference evapotranspiration using Internet of Things and hybrid ensemble machine learning approach

Reference Evapotranspiration (ETo) is the cornerstone of efficient water utilization for sustainability in agriculture. The standard Penman–Montieth (PM) approach of Reference Evapotranspiration (ETo), is complex due to the involvement of an extensive set of climatic conditions. The existing solutions of simplification of ETo predictions are not in accordance with the Penman–Montieth approach. A hybrid ensemble machine learning approach for simplification of ETo prediction is proposed using the Internet of Things(IoT) based crop field sensed climatic data. The proposed hybrid ensemble model is implemented with an Artificial Neural Network (ANN) and regression models. The proposed solution is unique for its utilization of flexible climatic conditions and in accordance with the standard Penman–Montieth (PM) approach. The proposed solution is able to predict daily ETo from only temperature and also can adjust ETo according to wind speed, humidity, and sunshine duration. The assessment of the proposed model exhibits a high coefficient of determination (R2) of 0.94 compared to 0.91 from the basic ANN model. The proposed hybrid ensemble model also exhibits a low RMSE of 0.86, MAE of 0.75 mm day−1, and MAPE of 15.05%, compared to 0.91, 0.75 mm day−1, and 20.40% from the basic ANN model. The ETo predictions by the proposed hybrid ensemble model also exhibit a higher Pearson correlation coefficient of 0.917 with the ETo by the Penman–Montieth (PM) approach, compared to 0.778 by the basic ANN model. The statistics reveal the accuracy and goodness of fit of the proposed hybrid ensemble machine learning model.

Using machine learning to predict the efficiency of biochar in pesticide remediation

Pesticides have remarkably contributed to protecting crop production and increase food production. Despite the improved food availability, the unavoidable ubiquity of pesticides in the aqueous media has significantly threatened human microbiomes and biodiversity. The use of biochar to remediate pesticides in soil water offers a sustainable waste management option for agriculture. The optimal conditions for efficient pesticide treatment via biochar are aqueous-matrix specific and differ amongst studies. Here, we use a literature database on biochar applications for aqueous environments contaminated with pesticides and employ ensemble machine learning models (i.e., CatBoost, LightGBM, and RF) to predict the adsorption behavior of pesticides. The results reveal that the textural properties of biochar, pesticide concentration, and dosage were the significant parameters affecting pesticide removal from water. The data-driven modeling intervention offers an empirical perspective toward the balanced design and optimized usage of biochar for capturing emerging micro-pollutants from water in agricultural systems.

Assessing eligibility for lung cancer screening using parsimonious ensemble machine learning models: A development and validation study.

Risk-based screening for lung cancer is currently being considered in several countries; however, the optimal approach to determine eligibility remains unclear. Ensemble machine learning could support the development of highly parsimonious prediction models that maintain the performance of more complex models while maximising simplicity and generalisability, supporting the widespread adoption of personalised screening. In this work, we aimed to develop and validate ensemble machine learning models to determine eligibility for risk-based lung cancer screening. For model development, we used data from 216,714 ever-smokers recruited between 2006 and 2010 to the UK Biobank prospective cohort and 26,616 high-risk ever-smokers recruited between 2002 and 2004 to the control arm of the US National Lung Screening (NLST) randomised controlled trial. The NLST trial randomised high-risk smokers from 33 US centres with at least a 30 pack-year smoking history and fewer than 15 quit-years to annual CT or chest radiography screening for lung cancer. We externally validated our models among 49,593 participants in the chest radiography arm and all 80,659 ever-smoking participants in the US Prostate, Lung, Colorectal and Ovarian (PLCO) Screening Trial. The PLCO trial, recruiting from 1993 to 2001, analysed the impact of chest radiography or no chest radiography for lung cancer screening. We primarily validated in the PLCO chest radiography arm such that we could benchmark against comparator models developed within the PLCO control arm. Models were developed to predict the risk of 2 outcomes within 5 years from baseline: diagnosis of lung cancer and death from lung cancer. We assessed model discrimination (area under the receiver operating curve, AUC), calibration (calibration curves and expected/observed ratio), overall performance (Brier scores), and net benefit with decision curve analysis. Models predicting lung cancer death (UCL-D) and incidence (UCL-I) using 3 variables-age, smoking duration, and pack-years-achieved or exceeded parity in discrimination, overall performance, and net benefit with comparators currently in use, despite requiring only one-quarter of the predictors. In external validation in the PLCO trial, UCL-D had an AUC of 0.803 (95% CI: 0.783, 0.824) and was well calibrated with an expected/observed (E/O) ratio of 1.05 (95% CI: 0.95, 1.19). UCL-I had an AUC of 0.787 (95% CI: 0.771, 0.802), an E/O ratio of 1.0 (95% CI: 0.92, 1.07). The sensitivity of UCL-D was 85.5% and UCL-I was 83.9%, at 5-year risk thresholds of 0.68% and 1.17%, respectively, 7.9% and 6.2% higher than the USPSTF-2021 criteria at the same specificity. The main limitation of this study is that the models have not been validated outside of UK and US cohorts. We present parsimonious ensemble machine learning models to predict the risk of lung cancer in ever-smokers, demonstrating a novel approach that could simplify the implementation of risk-based lung cancer screening in multiple settings.

Performance analysis of machine learning algorithms: Single Model VS Ensemble Model

Machine Learning is a branch of Artificial Intelligence that predicts several naturally occurring events by training a model with some data and then using unseen data to test it. This paper seeks to analyze the performances of single and ensemble machine learning algorithms on the Cleveland Heart disease data set. Experimental study proves that the accuracy score and area under the ROC curve in the ensemble machine learning model is higher than the single machine learning model in predicting non-CVD and CVD patients.

A High-Generalizability Machine Learning Framework for Analyzing the Homogenized Properties of Short Fiber-Reinforced Polymer Composites.

This study aims to develop a high-generalizability machine learning framework for predicting the homogenized mechanical properties of short fiber-reinforced polymer composites. The ensemble machine learning model (EML) employs a stacking algorithm using three base models of Extra Trees (ET), eXtreme Gradient Boosting machine (XGBoost), and Light Gradient Boosting machine (LGBM). A micromechanical model of a two-step homogenization algorithm is adopted and verified as an effective approach to composite modeling with randomly distributed fibers, which is integrated with finite element simulations for providing a high-quality ground-truth dataset. The model performance is thoroughly assessed for its accuracy, efficiency, interpretability, and generalizability. The results suggest that: (1) the EML model outperforms the base members on prediction accuracy, achieving R2 values of 0.988 and 0.952 on the train and test datasets, respectively; (2) the SHapley Additive exPlanations (SHAP) analysis identifies the Young's modulus of matrix, fiber, and fiber content as the top three factors influencing the homogenized properties, whereas the anisotropy is predominantly determined by the fiber orientations; (3) the EML model showcases good generalization capability on experimental data, and it has been shown to be more effective than high-fidelity computational models by significantly lowering computational costs while maintaining high accuracy.

Moth–Flame Optimization based ensemble classification for intrusion detection in intelligent transport system for smart cities

The number of vehicles travelling on the road has increased tremendously over the past few decades throughout the globe. The advent of Intelligent Transport System (ITS) enabled the vehicles to be managed intelligently. However, the ITS network can be intruded by malicious users to access the sensitive information. So a strong Intrusion Detection System (IDS) is required to safeguard the ITS network. Due to the huge volume of data generated by the sensors in the vehicles in ITS, there is a dire need to extract the most important features from the ITS data for classification phase in IDS. Even though, many researchers have worked on building an IDS system in ITS, not much work is done on addressing the aforementioned issue. To address this problem, we have utilized the Moth–Flame Optimization (MFO) in this work. In the proposed work, a MFO based ensemble machine learning model is proposed to classify the IDS dataset in ITS. Firstly the IDS dataset is normalized using the standard-scaler method. Then optimal features from the IDS dataset are chosen by MFO. These optimal features are trained by an ensemble classifier comprising of linear regression, random forest and XGBoost classification algorithms for intelligent decision making. The performance of the proposed model is compared against several state of the art meta-heuristic algorithms based on ensemble models which achieved a superior accuracy and recall of 100%, and precision of 99.5% on shellcode attacks.

Advancing ocean subsurface thermal structure estimation in the Pacific Ocean: A multi-model ensemble machine learning approach

Estimation of the ocean subsurface thermal structure (OSTS) is important for understanding thermodynamic processes and climate variability. In the present study, a novel multi-model ensemble machine learning (Ensemble-ML) model is developed to retrieve subsurface thermal structure in the Pacific Ocean by integrating sea surface data with Argo observations. The Ensemble-ML model integrates four individual machine learning models to enhance estimation accuracy and reliability. Our results exhibit good agreement between the satellite sea surface temperature (SST) and sea surface salinity (SSS) data and Argo observations, providing validation for the utilization of these datasets in the Ensemble-ML model. The Ensemble-ML model exhibits better performance compared to individual machine learning models, with an average root mean square error (RMSE) of 0.3273 °C and an average coefficient of determination (R²) of 0.9905. Notably, incorporating geographical information as input variables enhance model performance, emphasizing the importance of considering spatial context in OSTS estimation. The Ensemble-ML model accurately captures the spatial distribution of OSTS across depths and seasons in the Pacific Ocean, effectively reproducing critical temperature features while maintaining strong agreement with Argo observations. Nevertheless, its performance shows relative weakness within the thermocline layer and the equatorial Pacific region (spanning from 10°S to 10°N latitude), which are characterized by complex circulation systems. Despite these challenges, the Ensemble-ML model effectively reproduces the spatial distribution of OSTS of the Pacific Ocean. This indicates the potential of machine learning models, particularly ensemble models, for enhancing OSTS estimation in the Pacific Ocean and other regions, offering valuable insights for future research and applications in physical oceanography.

Bi-Model Engagement Emotion Recognition Based on Facial and Upper-Body Landmarks and Machine Learning Approaches

Customer satisfaction can be measured using facial expression recognition. The current generation of artificial intelligence systems heavily depends on facial features such as eyebrows, eyes, and foreheads. This dependence introduces a limitation as people generally prefer to conceal their genuine emotions. As body gestures are difficult to conceal and can convey a more detailed and accurate emotional state, the authors incorporate upper-body gestures as an additional feature that improves the predicted emotion's accuracy. This work uses an ensemble machine-learning model that integrates support vector machines, random forest classifiers, and logistic regression classifiers. The proposed method detects emotions from facial expressions and upper-body movements and is experimentally evaluated and has been found to be effective, with an accuracy rate of 97% on the EMOTIC dataset and 99% accuracy on MELD dataset.