Auto Machine Learning Research Articles

Current and Future Probability of Occurrence of the Floodwater Mosquito Aedes vexans (Meigen, 1830) in the Netherlands

ABSTRACTAedes vexans (Meigen, 1830) is a floodwater mosquito species that may cause significant nuisance and can serve as a vector for multiple arboviruses. Its distribution is expected to shift in the future as a result of changes in climate and land use. Understanding these shifts is important for estimating future disease risk. This study aims to identify habitat suitability and probability of occurrence of A. vexans. Using the Netherlands as a case study, we utilised an occurrence dataset generated by the Netherlands Centre for Monitoring of Vectors. We employed an auto machine learning approach to model generation, using a variety of modelling methodologies, determining the optimal ratio of presence: Absence datapoints in the training data and ultimately creating a 10‐model ensemble. We selected predictor variables relating to weather, land use, soil properties, flood risk and salinity. The probability of A. vexans presence was predicted on a 1 km grid for both the current Dutch situation and for four scenarios for 2050. Our analysis identified temperature, soil type and land cover as the primary determinants influencing the probability of A. vexans occurrence. Future projections reveal an increase in the likelihood of A. vexans occurrence in the study area, particularly along major river corridors and in regions with increasing amounts of artificial and natural areas. Additionally, the mosquito season is predicted to become longer under all future scenarios. Insights provided in our study can also be applied to other similar areas, such as other north‐western European countries or other urban deltas. This study shows for the first time detailed future occurrence predictions and also future seasonal predictions for this mosquito species. Seasonal predictions allow researchers to study how disease risk changes throughout the year, something which is particularly valuable given the predicted lengthening of the mosquito (and thus disease transmission) season.

Classification of salivary gland biopsies in Sjögren's syndrome by a convolutional neural network using an auto-machine learning platform.

The histopathological analysis of minor salivary gland biopsies, particularly through the quantification of the Focus Score (FS), is pivotal in the diagnostic workflow for Sjögren's Syndrome (SS). AI-based image recognition using deep learning models has demonstrated potential in enhancing diagnostic accuracy and efficiency in preclinical research. The primary aim of this investigation was to utilize an auto-machine learning (autoML) platform for the automated segmentation and quantification of FS on histopathological slides, aiming to augment diagnostic precision and speed in SS. A cohort comprising 86 patients with sicca syndrome (37 diagnosed with SS based on the 2016 ACR/EULAR Classification Criteria and 49 non-SS) was selected for an in-depth histological examination. A repository of 172 slides (two per patient) was assembled, encompassing 74 slides meeting the classificatory thresholds for SS (FS ≥ 1, indicative of lymphocytic infiltration) and 98 slides showcasing normal salivary gland histology. The autoML platform utilized (Giotto, L2F, Lausanne Switzerland) employed a Convolutional Neural Network (CNN) architecture (ResNet-152) for the training and validation phases, using a dataset of 172 slides. The developed model exhibited a reliability score of 0.88, proficiently distinguishing SS cases, with a sensitivity of 89.47% (95% CI: 66.86% to 98.70%) and a specificity of 88.24% (95% CI: 63.56% to 98.54%). The model found histological slides of suboptimal quality (e.g., those compromised during fixation or staining processes) to be the most challenging for accurate classification. AutoML platforms offer a rapid and flexible approach to developing machine learning models, even with smaller datasets, as demonstrated in this study for SS. These platforms hold significant potential for enhancing diagnostic precision and efficiency in both clinical and research settings. Multicentric studies with larger patient cohorts are essential for thorough evaluation and validation of this innovative diagnostic approach.

Auto machine learning tools to distinguish between two killer whale ecotypes

Auto machine learning tools to distinguish between two killer whale ecotypes

Auto-machine learning for opportunistic thyroid nodule detection in lung cancer screening chest CT.

e13639 Background: Automated Machine Learning (Auto-ML) in medical imaging is a process that allows non-experts to utilize machine learning techniques, opening the door for non-coder physician-driven exploitation of the technology. Auto-ML was applied for opportunistic detection of thyroid nodules in the context of low-dose lung cancer screening chest CT, facilitated by an innovative platform integration. By leveraging scans originally intended for lung cancer screening, suspicious appearing asymptomatic thyroid nodules can also be screened for where technically feasible. Methods: CT scans from the National Lung Screening Trial (NLST) dataset were utilized. This dataset contains low-dose chest CT examinations initially used for lung cancer screening. Annotation was carried out within a no-code web-based platform, Gesund.ai. A board-certified diagnostic radiologist annotated 100 CT examinations. A case was labeled "suspicious" if it presented a thyroid nodule of 1 cm or greater in diameter, while cases with no such nodules were deemed "not suspicious." The Auto-ML feature was then engaged within the software platform for parameter adjustments to refine the model without the need for manual coding. This phase was characterized by an iterative exploration of model performance, facilitated by the platform’s robust validation tools. Results: Upon training and validation, the Auto-ML model, cultivated from 100 annotated cases and assessed against a separate set of 130 cases, demonstrated a discernment accuracy of 0.51 in identifying "suspicious" thyroid nodules with a sensitivity and precision of 0.51 and 0.62 respectively. The AUC for this class stands at 0.69, indicating a moderate ability to distinguish between the presence and absence of thyroid nodules. This metric, while foundational, offers insight into the model's potential efficacy in real-world diagnostic scenarios, reflecting the initial capabilities of the platform's Auto-ML integration in enhancing diagnostic processes. Conclusions: The findings from this study highlight the potential of Auto-ML in revolutionizing opportunistic screening for thyroid nodules via lung cancer CT. The initial accuracy rate underscores the necessity for further refinement and validation of the model, but also demonstrates the promising potential of Auto-ML. Institutional Auto-ML would include extraction of appropriate studies through the no-code software platform integrated directly within the PACS framework. This process would ensure data immobility and foster a secure environment for dataset creation. Annotation would be carried out by multiple physician imagers within the same facility, enhancing the data’s accuracy and comprehensiveness specific for the institution’s patient population. This exploration highlights the strategic role of Auto-ML in advancing cancer patient care through innovative technological integration.

Aqpet — An R package for air quality policy evaluation

Evaluating the effectiveness of clean air policies is important in the cycle of air quality management, ensuring policy accountability and informing future policy-making processes. However, such evaluations are challenging due to complex confounding factors such as varying weather conditions or seasonal or annual changes in air quality unrelated to the policy implementation. To address this challenge, we developed 'aqpet', a R package designed to streamline the quantification of policy effects on air quality using observational data. The package 'aqpet' includes: (1) automated-machine learning to predict air pollutants under average weather conditions – a process term as "weather normalisation"; (2) augmented synthetic control method (ASCM) to quantify the actual policy impact on air pollution. 'aqpet' offers functions for data collection and preparation, building auto-machine learning models, conducting weather normalisation, model performance evaluation and explanation, and causal impact analysis using ASCM. 'aqpet' enables fast, efficient, and interactive policy analysis for air quality management.

A Deep Analysis of Printed Image Forensics with Auto Machine Learning

This research undertakes an exhaustive exploration of the Auto Machine Learning-based approach (AutoML) to ascertain the source printer for microscopic printed image forensics. The primary focus is on enhancing precision and efficacy in a scenario with limited sample data, achieved by integrating traditional image processing methods with diverse AutoML representatives. The investigation involves a meticulous evaluation and comparative analysis of classical Machine Learning (ML) models and AutoML models in microscopic printed image forensics. Through extensive experiments, we highlight the inherent limitations of traditional models and underscore the compelling advantages offered by AutoML. Notably, we recognize AutoML’s unique capability to discern varying degrees of uncertainty within printed patterns. The outcomes emphasize the prowess of Auto Machine Learning in improving the accuracy of printed image forensics, making it particularly promising for future research, especially given the tabular nature of the data and the imperative for a lightweight model suitable for embedded systems.

Combining Multi-View UAV Photogrammetry, Thermal Imaging, and Computer Vision Can Derive Cost-Effective Ecological Indicators for Habitat Assessment

Recent developments in Unmanned Aircraft Vehicles (UAVs), thermal imaging, and Auto-machine learning (AutoML) have shown high potential for precise wildlife surveys but have rarely been studied for habitat assessment. Here, we propose a framework that leverages these advanced techniques to achieve cost-effective habitat quality assessment from the perspective of actual wildlife community usage. The framework exploits vision intelligence hidden in the UAV thermal images and AutoML methods to achieve cost-effective wildlife distribution mapping, and then derives wildlife use indicators to imply habitat quality variance. We conducted UAV-based thermal wildlife surveys at three wetlands in the Rainwater Basin, Nebraska. Experiments were set to examine the optimal protocols, including various flight designs (61 and 122 m), feature types, and AutoML. The results showed that UAV images collected at 61 m with a spatial resolution of 7.5 cm, combined with Faster R-CNN, returned the optimal wildlife mapping (more than 90% accuracy). Results also indicated that the vision intelligence exploited can effectively transfer the redundant AutoML adaptation cycles into a fully automatic process (with around 33 times efficiency improvement for data labeling), facilitating cost-effective AutoML adaptation. Eventually, the derived ecological indicators can explain the wildlife use status well, reflecting potential within- and between-habitat quality variance.

Analysis of Diabetes Prediction using Decision Tree Classifier

Diabetes is a serious complaint that affects the maturity of the population. Now a days its play a major role on human life. Imbalance in insulin processing by the body which leads to varieties of disorder. The main aim of this work is to make an early prediction of diabetes more precisely by using Auto Machine Learning Tools. Auto Machine learning Tools provide better results in diabetes detection by constructing models from patient datasets. This model automates the training, tuning, and deploying machine learning models. Recent developments in Machine learning show that Automatic Diabetic detection using Random Forest Algorithm models can be very beneficial in such problems. The proposed Random forest model predicts the diabetes at early stage. We use Decision tree classifier to predict whether a patient has diabetes based on diagnostic measurements. Performance and accuracy of the applied algorithm is discusses and compared.

Novel machine learning insights into the QM7b and QM9 quantum mechanics datasets.

This paper (i) explores the internal structure of two quantum mechanics datasets (QM7b, QM9), composed of several thousands of organic molecules and described in terms of electronic properties, and (ii) further explores an inverse design approach to molecular design consisting of using machine learning methods to approximate the atomic composition of molecules, using QM9 data. Understanding the structure and characteristics of this kind of data is important when predicting the atomic composition from physical-chemical properties in inverse molecular designs. Intrinsic dimension analysis, clustering, and outlier detection methods were used in the study. They revealed that for both datasets the intrinsic dimensionality is several times smaller than the descriptive dimensions. The QM7b data is composed of well-defined clusters related to atomic composition. The QM9 data consists of an outer region predominantly composed of outliers, and an inner, core region that concentrates clustered inliner objects. A significant relationship exists between the number of atoms in the molecule and its outlier/inliner nature. The spatial structure exhibits a relationship with molecular weight. Despite the structural differences between the two datasets, the predictability of variables of interest for inverse molecular design is high. This is exemplified by models estimating the number of atoms of the molecule from both the original properties and from lower dimensional embedding spaces. In the generative approach the input is given by a set of desired properties of the molecule and the output is an approximation of the atomic composition in terms of its constituent chemical elements. This could serve as the starting region for further search in the huge space determined by the set of possible chemical compounds. The quantum mechanic's dataset QM9 is used in the study, composed of 133,885 small organic molecules and 19 electronic properties. Different multi-target regression approaches were considered for predicting the atomic composition from the properties, including feature engineering techniques in an auto-machine learning framework. High-quality models were found that predict the atomic composition of the molecules from their electronic properties, as well as from a subset of only 52.6% size. Feature selection worked better than feature generation. The results validate the generative approach to inverse molecular design.

An autonomous mixed data oversampling method for AIOT-based churn recognition and personalized recommendations using behavioral segmentation.

The telecom sector is currently undergoing a digital transformation by integrating artificial intelligence (AI) and Internet of Things (IoT) technologies. Customer retention in this context relies on the application of autonomous AI methods for analyzing IoT device data patterns in relation to the offered service packages. One significant challenge in existing studies is treating churn recognition and customer segmentation as separate tasks, which diminishes overall system accuracy. This study introduces an innovative approach by leveraging a unified customer analytics platform that treats churn recognition and segmentation as a bi-level optimization problem. The proposed framework includes an Auto Machine Learning (AutoML) oversampling method, effectively handling three mixed datasets of customer churn features while addressing imbalanced-class distribution issues. To enhance performance, the study utilizes the strength of oversampling methods like synthetic minority oversampling technique for nominal and continuous features (SMOTE-NC) and synthetic minority oversampling with encoded nominal and continuous features (SMOTE-ENC). Performance evaluation, using 10-fold cross-validation, measures accuracy and F1-score. Simulation results demonstrate that the proposed strategy, particularly Random Forest (RF) with SMOTE-NC, outperforms standard methods with SMOTE. It achieves accuracy rates of 79.24%, 94.54%, and 69.57%, and F1-scores of 65.25%, 81.87%, and 45.62% for the IBM, Kaggle Telco and Cell2Cell datasets, respectively. The proposed method autonomously determines the number and density of clusters. Factor analysis employing Bayesian logistic regression identifies influential factors for accurate customer segmentation. Furthermore, the study segments consumers behaviorally and generates targeted recommendations for personalized service packages, benefiting decision-makers.

Exploring the Utility of Auto-machine Learning in Predicting Traffic Accident Severity in Jordan

The World Health Organization (WHO) estimates that approximately 1.35 million annual fatalities are caused by road traffic accidents, representing a significant global challenge. This study focuses on creating a machine-learning model to forecast traffic accident severity in Jordan. The objective of this study is to help reduce fatalities and economic losses caused by accidents, which can achieve using various machinelearning classifiers, like Decision Trees, Random Forests, Light Gradient Boosting Machines, Extra Trees, Bagging Classifiers, and Gradient Boosting. These models were assessed before and after down-sampling to deal with imbalance in accuracy, balanced accuracy, recall, precision, and F1-score metrics with and without hyper parameter tuning. The study emphasized the importance of advanced analytics in improving road safety measures and reducing accident severity. The researchers analyzed a dataset of 115,148 accidents. Factors considered included traffic volume, environmental conditions, and road geometry features. The data was segmented into urban and rural categories for customized modeling. Down-sampling improved the models' ability to detect injuries and deaths in both urban and rural areas. Hyper parameter tuning offered an additional improvement in balanced recall and F1-score, particularly after down-sampling. In urban areas, the LGBM and Gradient Boosting classifiers showed the most significant gains in recall for minority classes, while in rural areas the Random Forest, Bagging, and Extra Trees classifiers maintained a better balance between precision and recall. All classifiers achieved high accuracy (above 0.97) in both urban and rural areas, so that these models can accurately forecast the severity of accidents, including property damage, fatalities, and injuries. The authors have also recommended incorporating variables of temporal patterns, driver behavior, demographic data, and geographic location into the models of accident prediction to make them more efficient and stronger. Keywords: Accident severity prediction, Auto-machine learning, Accident classifiers, Python, Jordan.

Mapping changes of grassland to arable land using automatic machine learning of stacked ensembles and H2O library

ABSTRACT Permanent grasslands play a very important role in the landscape. The loss of permanent grasslands and their subsequent conversion into arable land create erosion-prone agricultural areas in the landscape and have a negative impact on the biodiversity. From this point of view, there is a need for the accurate and effective monitoring of changes in the agricultural landscape along with an assessment of the influence of the agricultural policies on the landscape. Sentinel-2 from the Copernicus programme has improved options for the implementation of remote sensing data into the monitoring of agricultural land. The aim of this study was to evaluate the potential of H2O library and within implemented Automachine learning function (AutoML) and its stacked ensembles for mapping changes from grasslands to arable lands. All results show high overall accuracy from 93.5% to 96.6% and high values of area under the ROC curve (0.94–0.98). Stacked ensembles appear to be the most accurate machine learning models for mapping changes from grasslands to arable lands. The importance of several biological predictors has been tested (FAPAR, FCOVER, LAI, NDVI, etc.) with the help of a heatmap that is part of AutoML function of H2O library.

Building Information Modeling and Artificial Intelligence Based Smart Construction Management: Materials and Electrical

With the development of society and technological progress, the requirements of government regulatory departments for engineering construction efficiency, quality, and safety are constantly increasing. The traditional extensive construction process can no longer meet the requirements of modern construction industry development. Based on the shortcomings of traditional construction processes, the concept of intelligent construction has been introduced. The construction of new smart and digital twin (DT) cities is entering an explosive period. The application of building rapid modeling technology based on artificial intelligence (AI) and building information modeling (BIM) integration in smart cities has gradually begun new explorations and attempts, and its application value is becoming increasingly prominent. A brand-new auto-machine learning (auto-ML) integrated algorithm technology platform for 3D building modeling is being developed and improved over time by combining AI and BIM technology in a deep way. This allows for fast and accurate modeling as well as high-value scenarios in the smart city industry, including architecture, municipal engineering, roads, and bridges.

Lung diseases classification based on auto-machine learning

The escalating incidence of lung diseases and the substantial costs associated with their diagnosis underscore the significance of developing approaches that can enhance the effectiveness and precision of detection. In this regard, this study employs an auto-machine learning platform called Edge Impulse to train a greyscale dataset of lung diseases. Specifically, the study compares two classification models and two transfer learning models generated by edge impulse and BrainChip, respectively, and employs accuracy as a metric to assess the efficacy of these models. The research analyzes the potential causes behind the differing performances of the two authors and the two types of models and selects the optimal model for implementation in real-world devices. Additionally, the study takes into account the accuracy in detecting individual types of diseases to evaluate the model's performance in detailed classification. The findings reveal that the most effective model, the transfer learning model developed by Edge Impulse, performs exceptionally well in detecting abnormal lungs, particularly in diagnosing COVID-19. However, its classification capabilities with respect to identifying the specific type of disease remain limited.

Multi-Objective Considered Process Parameter Optimization of Welding Robots Based on Small Sample Size Dataset

The welding process is characterized by its high energy density, making it imperative to optimize the energy consumption of welding robots without compromising the quality and efficiency of the welding process for their sustainable development. The above evaluation objectives in a particular welding situation are mostly influenced by the welding process parameters. Although numerical analysis and simulation methods have demonstrated their viability in optimizing process parameters, there are still limitations in terms of modeling accuracy and efficiency. This paper presented a framework for optimizing process parameters of welding robots in industry settings, where data augmentation was applied to expand sample size, auto machine learning theory was incorporated to quantify reflections from process parameters to evaluation objectives, and the enhanced non-dominated sorting algorithm was employed to identify an optimal solution by balancing these objectives. Additionally, an experiment using Q235 as welding plates was designed and conducted on a welding platform, and the findings indicated that the prediction accuracy on different objectives obtained by the enlarged dataset through ensembled models all exceeded 95%. It is proven that the proposed methods enabled the efficient and optimal determination of parameter instructions for welding scenarios and exhibited superior performance compared with other optimization methods in terms of model correctness, modeling efficiency, and method applicability.

Predictive Modeling for Highway Pavement Rutting: A Comparative Analysis of Auto-Machine Learning and Structural Equation Models

Highway pavements deteriorate over time as successive wheel loads cause rutting, cracking, texture loss, and so forth. Design standards and pavement performance models account for some of the known contributory factors, such as levels of traffic and vehicle composition. However, such models are limited in their predictive power, and highway authorities must conduct regular pavement condition surveys rather than relying on the standard deterioration models alone. The ways in which multiple factors affect pavement deterioration, including rutting, are complex and are believed to include feedback loops where rutting then influences driving position, exacerbating the rutting levels. Standard regression models are not well suited to representing such complex causal mechanisms. This paper compares two alternative modeling approaches, structural equation models and auto-machine learning, and evaluates the predictive ability and practicalities of each. The findings indicate that auto-machine learning (AutoML) may be superior in its predictive ability. However, the “black box” nature of AutoML results makes them potentially less useful to practitioners. A process of using machine learning to help inform a structural equation model is proposed.

Optimal Machine-Learning-Based Controller for Shunt Active Power Filter by Auto Machine Learning

This paper proposes a Machine Learning (ML) based controller for shunt active power filter (SAPF). ML design had always been sub-optimal as human experts designed them, even though ML models are computationally simpler than traditional methods. This drawback is also addressed by optimizing all the design processes, including data preprocessing, model selection and model hyperparameters. Automated Machine Learning (AutoML) algorithms are used to find the optimum pipeline for ML model from a search space of 110 hyperparameters (more than 15 ML models, 14 feature preprocessing methods and 4 data preprocessing methods). It has both classical ML methods and deep learning models in their pool, such as decision tree, support vector machine, ADALINE, Multilayer perceptron (MLP), recurrent neural network, convolutional neural network, Gaussian process, etc. Optimization is done with Bayesian Optimization and network morphism based neural architecture search. This work proposes a method to develop a general ANN model independent of system parameters. This universal ML controller produces accurate current reference generation and faster estimation results compared to the conventional control scheme. The proposed techniques are simulated with MATLAB and Python. The proposed system was also verified using an experimental prototype developed in the laboratory.

A Survey on Recent Advancements in Auto-Machine Learning with a Focus on Feature Engineering

A study on the recent trends and progress in the area of Automated Machine Learning (AutoML) is done in detail in this paper. AutoML deals with the end-to-end automation of various steps in a machine-learning pipeline. Some of the steps include feature selection, feature engineering, neural architecture search, hyperparameter optimization, and model selection. The time and the specialized skill set required to perform these tasks may be reduced to some extent with the help of automating all or some of these steps. Thus, a lot of research is going on in the area of AutoML and the recent research articles add justice to the same. A review of existing literature on AutoML with a focus on feature engineering is presented in this paper to assist scientists in building better machine learning models "off the shelf" without extensive data science experience. The use of AutoML in different sectors will also be discussed, as will existing applications of AutoML. A review of published papers, accompanied by describing work in AutoML from a computer science perspective was conducted.

Distributed denial of service attack defense system-based auto machine learning algorithm

The use of network-connected gadgets is rising quickly in the internet age, which is escalating the number of cyberattacks. The detection of distributed denial of service (DDoS) attacks is a tedious task that has necessitated the development of a number of models for its identification recently. Nonetheless, because of major fluctuations in subscriptions and traffic rates, it continues to be a difficult challenge. A novel automatic detection technique was created to address this issue in this work, which reduces the feature space and consequently minimizes the computational time and model overfitting. Data preprocessing is done first to increase the model's generalizability; then, a feature selection method is used to choose the most pertinent features to increase the accuracy of the classification process. Additionally, hyperparameter tuning-choosing the proper parameters for the learning approach-improved model performance. Finally, the support vector machine (SVM) is compatible with the optimization and the hyperparameters offered by supervised learning methods. The CICDDoS2019 dataset was used to evaluate each of these assays, and the experimental findings demonstrated that, with an accuracy of 99.95%, the suggested model performs well when compared to more modern techniques.

Identifying the predictors of severe psychological distress by auto-machine learning methods

Social stress in daily life and the COVID-19 pandemic have greatly impacted the mental health of the population. Early detection of a predisposition to severe psychological distress is essential for timely interventions. This paper analyzed 4036 samples participating in the 2019–2020 National Health Information Trends Survey (HINTS) and identified 57 candidate predictors of severe psychological distress based on univariate chi-square and t-test analyses. Five machine learning methods, namely logistic regression (LR), automatic generalized linear models (Auto-GLM), automatic random forests (Auto-Random Forests), automatic deep neural networks (Auto-Deep learning) and automatic gradient boosting machines (Auto-GBM), were employed to model synthetic minority oversampling technique-based (SMOTE) resampled data and identify predictors of severe psychological distress. Predictors were evaluated by odds ratios in logistic models and variable importance in the other models. Forty-seven variables were identified as significant predictors of severe psychological distress, including 13 sociodemographic variables and 34 variables related to individual lifestyle and behavioral habits. Among them, new potentially relevant variables related to an individual's level of concern and trust in cancer information, exposure to health care providers, and cancer screening and awareness are included. The performance of each model was evaluated using five-fold cross-validation. The optimal model performance-wise was Auto-GBM with an accuracy of 89.75%, a precision of 89.68%, a recall of 89.31%, an F1-score of 89.48% and an AUC of 95.57%. Significant predictors of severe psychological distress were identified in this study and the value of machine learning methods in predicting severe psychological distress is demonstrated, thereby enhancing pre-prediction and clinical decision-making of severe psychological distress problems.