Many Machine Learning Research Articles

Machine Learning-based Prediction of African Swine Fever (ASF) in Pigs

African Swine Fever (ASF) is a contiguous viral disease of the pig with serious economic threats to the pork industry. Early identification of ASF infection is important to support sustainable developments in the ASF industry. There is also a need for a solution to identify the ASF infection as early as possible based on apparent symptoms of ASF to screen the infected animals, that are not targeted in the existing literature. Many machine learning (ML) solutions have been proposed in recent years for the prediction and identification of human, animal, and plant diseases. To deal with ASF in pigs ML-assisted model is proposed for the early identification of ASF infection without medical diagnosis and expert opinion. The data regarding apparent symptoms are collected from Chinese small pig farms. The loss of appetite, weakness, diarrhea, vomiting, coughing, skin redness, and breathing difficulty levels are taken as major apparent symptoms of ASF infection. Moreover, different ML models are also evaluated for their performance in the prediction of ASF infection based on selected apparent symptoms of ASF infection. In this regard, Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), Decision Tree (DT), Random Forests (RF), and Gaussian Naïve Bayes ML models are evaluated for ASF infection prediction. The implementation of the proposed solution reveals that the GNB model is more accurate as compared to the other evaluated models for the identification of ASF infection from the apparent ASF symptoms in infected pig animals, with 94.31\% accuracy. The proposed solution would be very effective in the early screening of ASF-infected pig animals without medical diagnosis and expert judgment.

Performance comparison of machine learning algorithms for the estimation of blood pressure using photoplethysmography

This paper deals with an in-depth performance analysis on the estimation of Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP) by using features from the photoplethysmography (PPG) signal enhanced using the Maximal Overlap Discrete Wavelet Transform (MODWT), to train many machine learning (ML) regression models, including eXtreme Gradient Boost (XGBoost). The impact of different features selections methods, ML methods and training set sizes has been analyzed. One result is on the achievable improvements using features extracted from MODWT enhanced PPG signals. The most significant features have been selected using three different algorithms, namely RReliefF, Minimum Redundancy Maximum Relevance (MRMR) and Correlation-based Feature Selection (CFS). This comparison has been critical to underline that the exploitation of the new features allows to improve SBP and DBP estimation. Moreover, the authors have trained several ML algorithms to provide a comparison of their accuracy and training time, showing the Pareto frontier. RReliefF and MRMR selections algorithms, and several ML algorithms such as XGBoost, Gaussian Process Regression(GPR) and Ensemble stood out for their performance, with a different compromise between prediction error and training time. In addition, a further result has been obtained by varying the dimension of the dataset to understand the impact on Root Mean Square Error (RMSE) for models that have shown better performance, giving an empirical relationship on achievable RMSE as a function of training set size. From that relationship it has been extrapolated an upper boundary of the set size over which no further RMSE improvements are expected.

Short-term vital parameter forecasting in the intensive care unit: A benchmark study leveraging data from patients after cardiothoracic surgery.

Patients in an Intensive Care Unit (ICU) are closely and continuously monitored, and many machine learning (ML) solutions have been proposed to predict specific outcomes like death, bleeding, or organ failure. Forecasting of vital parameters is a more general approach to ML-based patient monitoring, but the literature on its feasibility and robust benchmarks of achievable accuracy are scarce. We implemented five univariate statistical models (the naïve model, the Theta method, exponential smoothing, the autoregressive integrated moving average model, and an autoregressive single-layer neural network), two univariate neural networks (N-BEATS and N-HiTS), and two multivariate neural networks designed for sequential data (a recurrent neural network with gated recurrent unit, GRU, and a Transformer network) to produce forecasts for six vital parameters recorded at five-minute intervals during intensive care monitoring. Vital parameters were the diastolic, systolic, and mean arterial blood pressure, central venous pressure, peripheral oxygen saturation (measured by non-invasive pulse oximetry) and heart rate, and forecasts were made for 5 through 120 minutes into the future. Patients used in this study recovered from cardiothoracic surgery in an ICU. The patient cohort used for model development (n = 22,348) and internal testing (n = 2,483) originated from a heart center in Germany, while a patient sub-set from the eICU collaborative research database, an American multicenter ICU cohort, was used for external testing (n = 7,477). The GRU was the predominant method in this study. Uni- and multivariate neural network models proved to be superior to univariate statistical models across vital parameters and forecast horizons, and their advantage steadily became more pronounced for increasing forecast horizons. With this study, we established an extensive set of benchmarks for forecast performance in the ICU. Our findings suggest that supplying physicians with short-term forecasts of vital parameters in the ICU is feasible, and that multivariate neural networks are most suited for the task due to their ability to learn patterns across thousands of patients.

Molecular similarity: Theory, applications, and perspectives

Molecular similarity pervades much of our understanding and rationalization of chemistry. This has become particularly evident in the current data-intensive era of chemical research, with similarity measures serving as the backbone of many Machine Learning (ML) supervised and unsupervised procedures. Here, we present a discussion on the role of molecular similarity in drug design, chemical space exploration, chemical “art” generation, molecular representations, and many more. We also discuss more recent topics in molecular similarity, like the ability to efficiently compare large molecular libraries.

A comprehensive machine learning-based investigation for the index-value prediction of 2G HTS coated conductor tapes

Index-value, or so-called n-value prediction is of paramount importance for understanding the superconductors’ behaviour specially when modeling of superconductors is needed. This parameter is dependent on several physical quantities including temperature, the magnetic field’s density and orientation, and affects the behaviour of high-temperature superconducting devices made out of coated conductors in terms of losses and quench propagation. In this paper, a comprehensive analysis of many machine learning (ML) methods for estimating the n-value has been carried out. The results demonstrated that cascade forward neural network (CFNN) excels in this scope. Despite needing considerably higher training time when compared to the other attempted models, it performs at the highest accuracy, with 0.48 root mean squared error (RMSE) and 99.72% Pearson coefficient for goodness of fit (R-squared). In contrast, the rigid regression method had the worst predictions with 4.92 RMSE and 37.29% R-squared. Also, random forest, boosting methods, and simple feed forward neural network can be considered as a middle accuracy model with faster training time than CFNN. The findings of this study not only advance modeling of superconductors but also pave the way for applications and further research on ML plug-and-play codes for superconducting studies including modeling of superconducting devices.

An MCDM approach for Reverse vaccinology model to predict bacterial protective antigens

Reverse vaccinology (RV) is a significant step in sensible vaccine design. In recent years, many machine learning (ML) methods have been used to improve RV prediction accuracy. However, there are still issues with prediction accuracy and programme accessibility in ML-based RV. This paper presents a supervised ML-based method to classify bacterial protective antigens (BPAgs) and identify the model(s) that consistently perform well for the training dataset. Six ML classifiers are used for testing with physiochemical features extracted from a comprehensive training dataset. Selecting the best performing model from different performance metrics (accuracy, precision, recall, F1-score, and AUC-ROC) has not been easy, because all the metrics has the same importance to predict BPAgs. To fix this issue, we propose a soft and hard ranking model based on multi-criteria decision-making (MCDM) approach for selecting the best performing ML method that classifies BPAgs. First, our proposed model uses homologous proteins (positive and negative samples) from Protegen and Uniprot databases. Second, we applied four strategies of Synthetic Minority Oversampling Technique and Edited Nearest Neighbour (SMOTE-ENN) to handle the data imbalance problem and train the model using ML methods. Third, we consider MCDM-based technique for order preference by similarity to the ideal solution (TOPSIS) method integrated with soft and hard ranking model. The entropy is used to obtain weighted evaluation criteria for ranking the models. Our experimental evaluations show that the proposed method with best performing models (Random Forest and Extreme Gradient Boosting) outperforms compared to existing open-source RV methods using benchmark datasets.

PLANT LEAF DISEASE DETECTION

Plant diseases affect the growth of their respective species, therefore their early identification is very important. Many Machine Learning (ML) models have been employed for the detection and classification of plant diseases but, after the advancements in a subset of ML, that is, Deep Learning (DL), this area of research appears to have great potential in terms of increased accuracy. Many developed/modified DL architectures are implemented along with several visualization techniques to detect and classify the symptoms of plant diseases. Moreover, several performance metrics are used for the evaluation of these architectures/techniques. This review provides a comprehensive explanation of DL models used to visualize various plant diseases. In addition, some research gaps are identified from which to obtain greater transparency for detecting diseases in plants, even before their symptoms appear clearly Keywords: Plant leaf disease detection, leaf disease detection, convolutional neural network, deep learning

A novel electronic health record-based, machine-learning model to predict severe hypoglycemia leading to hospitalizations in older adults with diabetes: A territory-wide cohort and modeling study.

Older adults with diabetes are at high risk of severe hypoglycemia (SH). Many machine-learning (ML) models predict short-term hypoglycemia are not specific for older adults and show poor precision-recall. We aimed to develop a multidimensional, electronic health record (EHR)-based ML model to predict one-year risk of SH requiring hospitalization in older adults with diabetes. We adopted a case-control design for a retrospective territory-wide cohort of 1,456,618 records from 364,863 unique older adults (age ≥65 years) with diabetes and at least 1 Hong Kong Hospital Authority attendance from 2013 to 2018. We used 258 predictors including demographics, admissions, diagnoses, medications, and routine laboratory tests in a one-year period to predict SH events requiring hospitalization in the following 12 months. The cohort was randomly split into training, testing, and internal validation sets in a 7:2:1 ratio. Six ML algorithms were evaluated including logistic-regression, random forest, gradient boost machine, deep neural network (DNN), XGBoost, and Rulefit. We tested our model in a temporal validation cohort in the Hong Kong Diabetes Register with predictors defined in 2018 and outcome events defined in 2019. Predictive performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC) statistics, and positive predictive value (PPV). We identified 11,128 SH events requiring hospitalization during the observation periods. The XGBoost model yielded the best performance (AUROC = 0.978 [95% CI 0.972 to 0.984]; AUPRC = 0.670 [95% CI 0.652 to 0.688]; PPV = 0.721 [95% CI 0.703 to 0.739]). This was superior to an 11-variable conventional logistic-regression model comprised of age, sex, history of SH, hypertension, blood glucose, kidney function measurements, and use of oral glucose-lowering drugs (GLDs) (AUROC = 0.906; AUPRC = 0.085; PPV = 0.468). Top impactful predictors included non-use of lipid-regulating drugs, in-patient admission, urgent emergency triage, insulin use, and history of SH. External validation in the HKDR cohort yielded AUROC of 0.856 [95% CI 0.838 to 0.873]. Main limitations of this study included limited transportability of the model and lack of geographically independent validation. Our novel-ML model demonstrated good discrimination and high precision in predicting one-year risk of SH requiring hospitalization. This may be integrated into EHR decision support systems for preemptive intervention in older adults at highest risk.

Quick large-scale spatiotemporal flood inundation computation using integrated Encoder-Decoder LSTM with time distributed spatial output models

Accurate spatiotemporal flood simulations are essential for making informed decisions regarding flood release in affected regions, such as flood detention areas. Traditional spatiotemporal flood simulation approach uses partial differential equation (PDE) models (or physics-based models), which need high computational time. Although many machine learning (ML) models for inundation are increasingly being used to emulate the PDE models to address this issue, utilizing conventional ML models to achieve large-scale spatiotemporal flood prediction (i.e., simulation output in tens of thousands of grids and time steps over the whole flood event) remains a significant challenge. Therefore, we developed a new inundation model (IM) using encoder-decoder long short-term memory (ED-LSTM) with Time Distributed Spatial output model (ED-LSTM-TDS) that can acquire accurate spatially distributed flood information more rapidly. In the new IM framework, each ED-LSTM-TDS is built to simultaneously generate output for multiple (K) cell grids and multiple ED-LSTM-TDS models are built for prediction at all grids of entire PDE model. This study is the first of its kind to employ the ED-LSTM-TDS method to address spatiotemporal flood inundation simulation problems for flood detention areas. A 1994 km2 flood detention area in northeastern China was used as a case study. ED-LSTM-TDS exhibited better performance in predicting flood characteristics (e.g., water depth, velocity) than alternative methods, including ordinary LSTM, artificial neural network (ANN), and multiple linear regression (MLR). In addition, we investigated the trade-off relationship between the accuracy of flood characteristic prediction and the computation time of the proposed model by considering different numbers of K cell grids in each ED-LSTM-TDS model. The final proposed inundation model could accurately predict the spatiotemporal flood characteristics within 1.5 min to acquire the same information that required approximately 1 h by the PDE models. Such rapid and accurate prediction by the proposed model is important for evacuation planning, upstream flood control decisions and flood damage reduction.

Feature-Assisted Machine Learning for Predicting Band Gaps of Binary Semiconductors.

The band gap is a key parameter in semiconductor materials that is essential for advancing optoelectronic device development. Accurately predicting band gaps of materials at low cost is a significant challenge in materials science. Although many machine learning (ML) models for band gap prediction already exist, they often suffer from low interpretability and lack theoretical support from a physical perspective. In this study, we address these challenges by using a combination of traditional ML algorithms and the 'white-box' sure independence screening and sparsifying operator (SISSO) approach. Specifically, we enhance the interpretability and accuracy of band gap predictions for binary semiconductors by integrating the importance rankings of support vector regression (SVR), random forests (RF), and gradient boosting decision trees (GBDT) with SISSO models. Our model uses only the intrinsic features of the constituent elements and their band gaps calculated using the Perdew-Burke-Ernzerhof method, significantly reducing computational demands. We have applied our model to predict the band gaps of 1208 theoretically stable binary compounds. Importantly, the model highlights the critical role of electronegativity in determining material band gaps. This insight not only enriches our understanding of the physical principles underlying band gap prediction but also underscores the potential of our approach in guiding the synthesis of new and valuable semiconductor materials.

PulmoNet: a novel deep learning based pulmonary diseases detection model

Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model’s performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.

Impact of Elevation Angle on Cross Polarization Discrimination for Telecommunication Application in Warri, Delta State, Nigeria

This study explores the impact of elevation angle on Cross Polarization Discrimination (XPD) in telecommunication systems, as evidenced by data collected under varying rain conditions. The study examines XPD values at elevation angles of 400 and 600 degrees across different rain classifications and intensities. Analysis of the data reveals that increasing the elevation angle generally leads to improvements in XPD, indicating enhanced discrimination against cross-polarized interference and improved signal quality. Notably, significant improvements in XPD are observed in conditions of widespread rain at higher elevation angles. However, the effectiveness of elevating antennas in mitigating interference diminishes as rain intensity increases, particularly in extreme cloudburst scenarios. The findings underscore the importance of considering elevation angle in antenna placement and system design to optimize XPD and ensure reliable communication performance, especially in adverse weather conditions. This research contributes to a deeper understanding of the complex relationship between elevation angle and XPD, offering valuable insights for the design and optimization of telecommunication networks.

Explainable AI: motivations and connections with system identification

The results of many machine learning (ML) algorithms often yield very complicated black box models. While these models can have superb accuracy, their challenge lies in articulating the rationale behind specific outputs for given inputs, making verification and trust-building problematic in numerous applications or scenarios. In response to this challenge, ML researchers have started to devise methods that tackle this issue, creating a relatively heterogeneous set of tools which are often covered under the umbrella term of eXplainable AI, and abbreviated as XAI. Historically, system identification researchers have also faced similar problems with estimating meaningful parameters in order to obtain more interpretable models. Nevertheless, results from these fields currently seem to draw little from each other. This part of the tutorial, tailored as an introduction, aims at providing system identification researchers with a foundational overview of the motivations behind eXplainable AI (XAI) and the main connections with their field.

Fake review detection using transformer-based enhanced LSTM and RoBERTa

Internet reviews significantly influence consumer purchase decisions across all types of goods and services. However, fake reviews can mislead both customers and businesses. Many machine learning (ML) techniques have been proposed to detect fake reviews, but they often suffer from poor accuracy due to their focus on linguistic features rather than semantic content. This paper presents a novel semantic- and linguistic-aware model for fake review detection that improves accuracy by leveraging advanced transformer architecture. Our model integrates RoBERTa with an LSTM layer, enabling it to capture intricate patterns within fake reviews. Unlike previous methods, our approach enhances the robustness of fake review detection and authentic behavior profiling. Experimental results on semi-real benchmark datasets show that our model significantly outperforms state-of-the-art methods, achieving 96.03 % accuracy on the OpSpam dataset and 93.15 % on the Deception dataset. To further enhance transparency and credibility, we utilize Shapley Additive Explanations (SHAP) and attention techniques to clarify our model's classifications. The empirical findings indicate that our proposed model can offer rational explanations for classifying specific reviews as fake.

A Hardware Trojan Detection and Diagnosis Method for Gate-Level Netlists Based on Machine Learning and Graph Theory

The integrated circuit (IC) supply chain has become globalized, thereby inevitably introducing hardware Trojan (HT) threats during the design stage. To safeguard the integrity and security of ICs, many machine learning (ML)-based solutions have been proposed. However, most existing methods lack consideration of the integrity of HTs, thereby resulting in lower true negative rates (TNR) and true positive rate (TPRs). Therefore, to solve these problems, this paper presents a HT detection and diagnosis method for gate-level netlists (GLNs) based on ML and graph theory (GT). In this method, to address the issue of nonuniqueness in submodule partition schemes, the concept of “Maximum Single-Output Submodule (MSOS)” and a partition algorithm are introduced. In addition, to enhance the accuracy of HT diagnosis, we design an implant node search method named breadth-first comparison (BFC). With the support of the aforementioned techniques, we have completed experiments on HT detection and diagnosis. The HT implantation examples selected in this article are sourced from Trust-Hub. The experimental results demostrate the following: (1) The detection method proposed in this article, when detecting gate-level hardware trojans (GLHTs), achieves a TPR exceeding 95%, a TNR exceeding 37%, and F1 values exceeding 97%. Compared to existing methods, this method has improved the TNR for GLHTs by at least 25%. (2) The TPR for diagnosing GLHTs is consistently above 93%, and the TNR is 100%. Compared to existing methods, this method has achieved approximately a 4% improvement in the TPR and a 15% improvement in the TNR for GLHT diagnosis.

Gated graph neural networks for identifying contamination sources in water distribution systems

Contamination events in water distribution networks (WDN) pose significant threats to water supply and public health. Rapid and accurate contamination source identification (CSI) can facilitate the development of remedial measures to reduce impacts. Though many machine learning (ML) methods have been proposed for fast detection, there is a critical need for approaches capturing complex spatial dynamics in WDNs to enhance prediction accuracy. This study proposes a gated graph neural network (GGNN) for CSI in the WDN, incorporating both spatiotemporal water quality data and flow directionality between network nodes. Evaluated across various contamination scenarios, the GGNN demonstrates high prediction accuracy even with limited sensor coverage. Notably, directional connections significantly enhance the GGNN CSI accuracy, underscoring the importance of network topology and flow dynamics in ML-based WDN CSI approaches. Specifically, the method achieves a 92.27% accuracy in narrowing the contamination source to 5 points using just 2 h of sensor data. The GGNN showcases resilience under model and measurement uncertainties, reaffirming its potential for real-time implementation in practice. Moreover, our findings highlight the impact of sensor sampling frequency and measurement accuracy on CSI accuracy, offering practical insights for ML methods in water network applications.

COMPARISON AND EVALUATION OF MACHINE-LEARNING-BASED SPATIAL DOWNSCALING APPROACHES ON SATELLITE-DERIVED PRECIPITATION DATA

Abstract. Precipitation estimation with high accuracy and resolution is crucial for hydrological and meteorological applications, particularly in ungauged river basins and regions with scarce water resources. Many machine learning (ML) algorithms have been employed in the downscaling of precipitation, however, it remains unclear which algorithm can outperform others. To address this issue, this study evaluates the performance of four ML based downscaling methods to generate high-resolution precipitation estimates at an annual scale. The satellite-derived precipitation data, environmental variables, such as, latitude, longitude, normalized difference vegetation index (NDVI), digital elevation model (DEM), and land surface temperature (LST), as well as the observations from rainfall gauges were used to constructed the regression models. The performance of the four ML algorithms including the Support Vector Regression (SVR), Random Forest (RF), Spatial Random Forest (SRF), and Extreme Gradient Boosting (XGBoost) algorithms was compared with three conventional methods: Multiple Linear Regression (MLR), geographically weighted regression (GWR) and Kriging interpolation model. Results showed that ML-based method generally outperformed traditional interpolation methods in precipitation downscaling, as they had higher accuracy and were better at reproducing the spatial distribution of rainfall. Out of ML approaches, XGBoost received the best performance, followed by SRF, RF and SVR, indicating its robustness of capturing nonlinear relationships. After the XGBoost, better performance of SRF than RF and SVR was found. This might be because the SRF just introduced the spatial autocorrelation into the RF models, which illustrated the importance of capturing spatial variations in ML algorithms. These findings regarding the comparison and assessment provided a novel downscaling method for generating high-resolution precipitation data, which could benefit regional flood forecasting, drought monitoring, and irrigation planning.

A novel machine learning based hybrid approach for breast cancer relapse prediction

<span>The second leading cause of death for women is breast cancer, which is growing. Some cancer cells may remain in the body, so relapse is possible even if treatment begins soon after diagnosis. Since there are now many machine learning (ML) approaches to recurrence prediction in breast cancer, it is important to compare and contrast them to find the most effective one. Datasets with many features often lead to incorrect predictions because of this. In this study, correlation-based feature selection (CFS) and the flower pollination algorithm (FPA) are used to improve the quality of the wisconsin prognostic breast cancer (WPBC) and University Medical Centre, Institute of Oncology (UMCIO) breast cancer relapse datasets respectively. Data imputation, scaling, pre-process raw data. The second stage uses CFS to select discriminative features based on important feature correlations. The FPA chose the optimum attribute combination for the most precise answer. We tested the approach using 10-fold cross-validation stratification. Various trials show 84.85% and 83.92% accuracy on the WPBC and UMCIO breast cancer relapse datasets, respectively. The hybrid method performed well in feature selection, increasing the accuracy of the relapse classification for breast cancer.</span>

Reliability analysis of slope stability by neural network, principal component analysis, and transfer learning techniques

The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering. Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-demanding. To assess the slope stability problems with a more desirable computational effort, many machine learning (ML) algorithms have been proposed. However, most ML-based techniques require that the training data must be in the same feature space and have the same distribution, and the model may need to be rebuilt when the spatial distribution changes. This paper presents a new ML-based algorithm, which combines the principal component analysis (PCA)-based neural network (NN) and transfer learning (TL) techniques (i.e. PCA–NN–TL) to conduct the stability analysis of slopes with different spatial distributions. The Monte Carlo coupled with finite element simulation is first conducted for data acquisition considering the spatial variability of cohesive strength or friction angle of soils from eight slopes with the same geometry. The PCA method is incorporated into the neural network algorithm (i.e. PCA-NN) to increase the computational efficiency by reducing the input variables. It is found that the PCA-NN algorithm performs well in improving the prediction of slope stability for a given slope in terms of the computational accuracy and computational effort when compared with the other two algorithms (i.e. NN and decision trees, DT). Furthermore, the PCA–NN–TL algorithm shows great potential in assessing the stability of slope even with fewer training data.

AIBugHunter: A Practical tool for predicting, classifying and repairing software vulnerabilities

Many Machine Learning(ML)-based approaches have been proposed to automatically detect, localize, and repair software vulnerabilities. While ML-based methods are more effective than program analysis-based vulnerability analysis tools, few have been integrated into modern Integrated Development Environments (IDEs), hindering practical adoption. To bridge this critical gap, we propose in this article AIBugHunter, a novel Machine Learning-based software vulnerability analysis tool for C/C++ languages that is integrated into the Visual Studio Code (VS Code) IDE. AIBugHunter helps software developers to achieve real-time vulnerability detection, explanation, and repairs during programming. In particular, AIBugHunter scans through developers’ source code to (1) locate vulnerabilities, (2) identify vulnerability types, (3) estimate vulnerability severity, and (4) suggest vulnerability repairs. We integrate our previous works (i.e., LineVul and VulRepair) to achieve vulnerability localization and repairs. In this article, we propose a novel multi-objective optimization (MOO)-based vulnerability classification approach and a transformer-based estimation approach to help AIBugHunter accurately identify vulnerability types and estimate severity. Our empirical experiments on a large dataset consisting of 188K+ C/C++ functions confirm that our proposed approaches are more accurate than other state-of-the-art baseline methods for vulnerability classification and estimation. Furthermore, we conduct qualitative evaluations including a survey study and a user study to obtain software practitioners’ perceptions of our AIBugHunter tool and assess the impact that AIBugHunter may have on developers’ productivity in security aspects. Our survey study shows that our AIBugHunter is perceived as useful where 90% of the participants consider adopting our AIBugHunter during their software development. Last but not least, our user study shows that our AIBugHunter can enhance developers’ productivity in combating cybersecurity issues during software development. AIBugHunter is now publicly available in the Visual Studio Code marketplace.