Supervised Machine Learning Techniques Research Articles

Increasing load factor in logistics and evaluating shipment performance with machine learning methods: A case from the automotive industry

The insufficient loading of vehicles, which leads to a low logistics load factor is a common problem in the logistics industry. This study addresses this issue by utilizing actual shipment data from an automotive company. An effective method has been proposed to improve the company’s logistics efficiency through a scenario-based approach. Two real- world scenarios were developed to enhance vehicle loading performance. Machine learning algorithms were employed to evaluate the shipment performance of these scenarios. For the study, a dataset was generated from the company’s ERP system and real-world shipment data. Since this is a real-world problem, the dataset consisted of unlabeled data. To solve this problem, both supervised and unsupervised learning algorithms were applied. First, unsupervised clustering algorithms were used to group the shipment performance based on similarities. Then, supervised learning algorithms were utilized to classify the data within each group. The average cost was used to evaluate the clusters obtained through the unsupervised methods, while classification performance was measured using supervised machine learning techniques. The scenario-based approach has significantly improved the performance of the shipments as it shows the changes in load factor more clearly. In the actual case, only %25.7 of shipments were high performing, while this percentage gradually increased to %98.4 in the scenarios. The results show that optimizing the load factor makes the transports more efficient and balanced.

Artificial intelligence to predict treatment response in rheumatoid arthritis and spondyloarthritis: a scoping review

To analyse the types and applications of artificial intelligence (AI) technologies to predict treatment response in rheumatoid arthritis (RA) and spondyloarthritis (SpA). A comprehensive search in Medline, Embase, and Cochrane databases (up to August 2024) identified studies using AI to predict treatment response in RA and SpA. Data on study design, AI methodologies, data sources, and outcomes were extracted and synthesized. Findings were summarized descriptively. Of the 4257 articles identified, 89 studies met the inclusion criteria (74 on RA, 7 on SpA, 4 on Psoriatic Arthritis and 4 a mix of them). AI models primarily employed supervised machine learning techniques (e.g., random forests, support vector machines), unsupervised clustering, and deep learning. Data sources included electronic medical records, clinical biomarkers, genetic and proteomic data, and imaging. Predictive performance varied by methodology, with accuracy ranging from 60 to 70% and AUC values between 0.63 and 0.92. Multi-omics approaches and imaging-based models showed promising results in predicting responses to biologic DMARDs and JAK inhibitors but methodological heterogeneity limited generalizability. AI technologies exhibit substantial potential in predicting treatment responses in RA and SpA, enhancing personalized medicine. However, challenges such as methodological variability, data integration, and external validation remain. Future research should focus on refining AI models, ensuring their robustness across diverse patient populations, and facilitating their integration into clinical practice to optimize therapeutic decision-making in rheumatology.

Crime Data Analysis Against Women and Girls in India

Crime is a critical issue that poses a serious threat to public safety and national development. As crime rates increase across various regions, the need for intelligent systems to detect patterns and predict potential threats becomes essential. This project focuses on the analysis and prediction of crime using Python and machine learning algorithms. The dataset provides comprehensive crime records across different states, genders, and time periods. The project involves multiple stages, including data preprocessing, exploratory data analysis (EDA), visualization, and the application of supervised machine learning techniques. Random Forest and Support Vector Machine (SVM) algorithms are implemented to classify and predict crime occurrences based on selected features. In addition, Python libraries such as Pandas, Seaborn, Matplotlib, and Scikit-learn are utilized for data handling, statistical analysis, and graphical representation. The results provide deep insights into crime trends and help identify hotspots and recurring patterns. The machine learning models enhance the project’s practical utility by enabling crime prediction with a high degree of accuracy, thus supporting law enforcement agencies in proactive crime prevention and decision-making.

Implementation of a Face Detection Surveillance Security System in a Rice Farm Using Supervised Machine Learning Techniques

Implementation of a Face Detection Surveillance Security System in a Rice Farm Using Supervised Machine Learning Techniques

Relationships of Personality Traits With the Taxonomic Composition of the Gut Microbiome Among Psychiatric Inpatients.

Through the brain-gut-microbiome axis, myriad psychological functions that affect behavior share a dynamic, bidirectional relationship with the intestinal microbiome. Little is known about the relationship between personality-a stable construct that influences social- and health-related behaviors-and the bacterial ecosystem. The authors of this exploratory study examined the relationship between general and maladaptive personality traits and the composition of the gut microbiome. In total, 105 psychiatric inpatients provided clinical data and fecal samples. Personality traits were measured with the five-factor model of personality, the Structured Clinical Interview for DSM-IV Axis II Personality Disorders, and the Personality Inventory for DSM-5; 16S ribosomal DNA sequencing and whole-genome shotgun sequencing methods were used on fecal samples. Machine learning (ML) was used to identify personality traits associated with bacterial variability and specific taxa. Supervised ML techniques were used to classify traits of social detachment (maximum area under the receiver operating characteristic curve [AUROC]=0.944, R2>0.20), perceptual disturbance (maximum AUROC=0.763, R2=0.301), and hoarding behaviors (maximum AUROC=0.722) by using limited sets of discriminant bacterial species or genera. Established bacterial genera associated with psychosis (e.g., Peptococcus and Coprococcus) were associated with traits of perceptual disturbance. Hoarding behaviors were associated with a defined gut microbial composition that included Streptococcus, a known contributor to the development of pediatric autoimmune neuropsychiatric disorders. Observations from this study are consistent with recent findings demonstrating person-to-person interactions as a mode of gut microbiome transmission. This study adds to the emerging literature on the intricate connections between brain and gut function, expanding the interdisciplinary field of psychiatric microbiology.

412 Quantitative air trapping analysis in lung transplant recipients

Objectives/Goals: Bronchiolitis obliterans syndrome (BOS), a form of chronic lung allograft dysfunction (CLAD) that primarily affects the small airways, is often diagnosed too late using standard pulmonary function tests. This project aims to evaluate whether quantitative air trapping analysis can serve as an early diagnostic tool for BOS. Methods/Study Population: We performed a retrospective analysis of 134 computed tomography scans with inspiratory and expiratory protocols from 73 lung transplant recipients (48 male, 25 female). Quantitative air trapping analysis was performed by VIDA Diagnostics using a supervised machine learning technique called disease probability measure (DPM). Results/Anticipated Results: We found that lung transplant recipients exhibit significantly more air trapping compared to healthy controls and other small airway diseases, such as long COVID and cystic fibrosis. Notably, lung transplant recipients showed increased air trapping in the upper lobes. However, when separating participants into CLAD and non-CLAD groups, those meeting criteria for CLAD had significantly more air trapping in the left lower lobe. Additionally, only 2 out of 16 participants meeting CLAD criteria had less than 20% air trapping in their lungs, suggesting early involvement of the small airways. Discussion/Significance of Impact: Quantitative air trapping analysis seems to be an important diagnostic modality in the early detection of lung transplant-related small airway disease. Prospective longitudinal studies are needed to evaluate the spatial pathophysiology in these patients and to determine whether early air trapping can predict the development of CLAD.

Predicting rock mass strength from drilling data using synergistic unsupervised and supervised machine learning approaches

Extracting rock mass strength properties from existing data like Measurement While Drilling (MWD) is important to reduce the cost of additional geological and geotechnical surveys. This study presents an approach that combines clustering (unsupervised learning) and classification algorithms to identify similar rock groups for their prediction. The dataset comprises 272,272 MWD from 2,790 drill holes, split into 215,401 data points (2,332 drill holes) for cross-validation, and another 215,401 data points, from 558 previously unseen drill holes for testing. Principal component analysis (PCA) and clustering algorithms such as K-means, Gaussian mixture, C Fuzy, and hierarchical clustering were employed to group rocks with similar MWD parameters. The combination of PCA and k-means clustering provides good cluster quality which best describes the different rock strength characteristics (clusters), as revealed by geological investigation and coring data. After identifying the rock categories, Extra Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) approaches were used to develop classification models for rock strength prediction. The XGBoost model achieved the best and most reliable performance with accuracy, precision, recall, and F1 score exceeding 98% on the test set. This study highlights the synergetic benefits of combining unsupervised and supervised machine learning techniques to predict rock mass conditions, especially in scenarios with limited geological information or unavailable labeled data.

Identifying Financial Fraud Transactions Using Decision Tree Classifier Algorithm

Fraud in financial transactions is a critical issue for businesses, governments, and consumers, causing substantial financial losses and eroding trust in financial systems. Rule-based systems and other conventional fraud detection techniques have trouble identifying complex fraudulent activity. This research applies various machine learning (ML) algorithms to detect fraud in financial transactions. The research compares the performance of supervised ML techniques, such as random forest, logistic regression, and decision tree classifier, using a publicly available Kaggle dataset. It evaluates the models based on accuracy, precision, recall, and F1 scores. To address data imbalance in both undersampling and oversampling techniques, with a focus on oversampling techniques such as Synthetic Minority Over-Sampling Method (SMOTE) to enhance model performance. Results show that the Decision Tree Classifier, when used with oversampling, outperforms other models, achieving a 99% accuracy in detecting fraudulent transactions. This highlights the effectiveness of using ensemble and hybrid models in combination with oversampling to enhance the identification of fraud. The findings emphasize the importance of using advanced ML techniques and robust data preprocessing for detection of financial fraud.

Optimizing sample size for supervised machine learning with bulk transcriptomic sequencing: a learning curve approach.

Accurate sample classification using transcriptomics data is crucial for advancing personalized medicine. Achieving this goal necessitates determining a suitable sample size that ensures adequate classification accuracy without undue resource allocation. Current sample size calculation methods rely on assumptions and algorithms that may not align with supervised machine learning techniques for sample classification. Addressing this critical methodological gap, we present a novel computational approach that establishes the accuracy-versus-sample size relationship by employing a data augmentation strategy followed by fitting a learning curve. We comprehensively evaluated its performance for microRNA and RNA sequencing data, considering diverse data characteristics and algorithm configurations, based on a spectrum of evaluation metrics. To foster accessibility and reproducibility, the Python and R code for implementing our approach is available on GitHub. Its deployment will significantly facilitate the adoption of machine learning in transcriptomics studies and accelerate their translation into clinically useful classifiers for personalized treatment.

Wind energy forecasts with supervised machine learning techniques

Wind energy forecasts with supervised machine learning techniques

Knowledge Integration in Steel Microstructure Analysis Using Unsupervised Image Segmentation and Supervised Machine Learning Techniques

This study presents a methodology for analyzing bainitic microstructures in steel using image segmentation techniques and machine learning methods. Images of steel microstructures were processed using a superpixel segmentation algorithm, which generated image segments based on grayscale intensity. The histograms of values in grayscale of those segments served as input for classification models such as decision trees, random forests, and the KNN algorithm. Experimental results demonstrated that this method enables effective microstructure classification, including the identification of segments containing bainite. A comparison of algorithms revealed the superiority of random forests in terms of stability and accuracy. Results also show that small segments provide better final results. The obtained results indicate the potential for further development of this method using more advanced neural networks for automated steel microstructure analysis.

Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning.

To predict palatally impacted maxillary canines based on maxilla measurements through supervised machine learning techniques. The maxilla images from 138 patients were analysed to investigate intermolar width, interpremolar width, interpterygoid width, maxillary length, maxillary width, nasal cavity width and nostril width, obtained through cone beam computed tomography scans. The predictive models were built using the following machine learning algorithms: Adaboost Classifier, Decision Tree, Gradient Boosting Classifier, K-Nearest Neighbours (KNN), Logistic Regression, Multilayer Perceptron Classifier (MLP), Random Forest Classifier and Support Vector Machine (SVM). A 5-fold cross-validation approach was employed to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision and F1 Score were calculated for each model, and ROC curves were constructed. The predictive model included four variables (two dental and two skeletal measurements). The interpterygoid width and nostril width showed the largest effect sizes. The Gradient Boosting Classifier algorithm exhibited the best metrics, with AUC values ranging from 0.91 [CI95% = 0.74-0.98] for test data to 0.89 [CI95% = 0.86-0.94] for crossvalidation. The nostril width variable demonstrated the highest importance across all tested algorithms. The use of maxillary measurements, through supervised machine learning techniques, is a promising method for predicting palatally impacted maxillary canines. Among the models evaluated, both the Gradient Boosting Classifier and the Random Forest Classifier demonstrated the best performance metrics, with accuracy and AUC values exceeding 0.8, indicating strong predictive capability.

A Comparative Analysis Machine Learning Techniques for LULC Classification Using Landsat-8 Satellite Imagery

This study compares various categorization methods to assign land use and land cover (LULC) classes. Using Geographic Information Systems (GIS) and Remote Sensing (RS) to leverage the dynamic and complex area of LULC, this study examines the potential of different machine learning classification methods. Precise differentiation and classification of various land cover categories, such as green vegetation, urban areas, water bodies, dark green vegetation, and bare terrain, are made possible by the great spatial and spectral resolution of Landsat imagery. For efficient land management and planning, the integration of Landsat data with GIS and RS approaches provides insightful information about the distribution and temporal changes in LULC. This study uses four classifiers to explore the principles of supervised machine learning techniques and identify their drawbacks and advantages. Testing results show that the Support Vector Machine with four kernel linear-99.17%, radial basis (RBF)-99.11%, Sigmoid-99.11% and Polynomial-99.11% is a reliable option for LULC classification, outperforming than other classifiers in terms of accuracy, including the Minimum Distance Classifier (MD-93.47%), Maximum Likelihood Classifier (MLC- 98.98%), and Mahalanobis Distance Classifier (MH-97.83%). Among the tested classifiers, SVM with four kernels notably shows the highest accuracy. With their essential insights for well-informed decision-making towards sustainable development and resource utilization, our findings add to a thorough understanding of LULC dynamics. For accurate mapping and long-term monitoring of deviations in land cover (LC), the study emphasizes the value of using front-line classification systems in remote sensing applications

A COMPARATIVE EVALUATION OF SOME MACHINE LEARNING TECHNIQUES FOR PREDICTING BREAST CANCER

With over 2 million new cases in 2020, breast cancer (BC) is the most common cancer diagnosed in women worldwide. Breast cancer is becoming more common every year, so early identification and diagnosis are crucial for reducing mortality rate. Machine learning algorithms can uncover hidden patterns and insights by analyzing massive datasets, enabling scientists to make data-driven decisions and more successfully address health concerns. In this paper, a performance comparison between four supervised machine learning techniques, namely Decision tree (DT), K-nearest neighbors (KNN), Extreme gradient Boost (XGB) and logistic regression (LR) is conducted. The primary objective is to evaluate the performance in classifying data with respect to efficiency and effectiveness of each algorithm in terms of classification test accuracy, precision, and recall. XGB outperformed the other algorithms in all the metrics used for evaluation.

Developing A Machine Learning Model to Predict Medication Adherence in Chronic Disease Management

In the healthcare industry, chronic disease prediction is crucial. It is crucial to diagnose the illness early. Large amounts of data are generated in computer science as a result of significant technological advancements. Many medical databases are created as clinical information networks advance. Data mining, the process of managing vast amounts of diverse data and extracting insights from it, has emerged as a crucial area of study. Early illness detection, patient treatment, and community services from huge data creation in the biomedical and healthcare communities are all benefited by the accurate analysis of medical data. Nowadays, one of the main areas of research is the management and extraction of knowledge from vast amounts of diverse data. Accurate processing of health data helps the biomedical and healthcare communities by improving patient care, early illness detection, and community services. However, analytical precision is reduced if medical data is not sufficiently consistent. For the domains of biomedical pattern recognition and master learning, the perception and diagnosis of chronic disease are guaranteed to be consistent. Additionally, the decision-making approach's goal is pushed. The study of high-dimensional, multi-modal biomedical data can be effectively addressed by machine learning. In computer science, chronic disease prediction is crucial. Early detection and prediction of chronic disease is crucial. The dataset for chronic obstructive pulmonary disease is used for analysis by the suggested model. Using supervised machine learning techniques such as Random Forest, Multiplayer Perceptron, Logistic Regression, Stochastic Gradient Descent, and XG boost, we provide a chronic obstructive pulmonary disease prediction system. Next, we examine classification techniques for predicting chronic diseases using a variety of criteria, such as accuracy, precision, sensitivity, ROC, and AUC.

The Application of Machine Learning Algorithms to Predict HIV Testing in Repeated Adult Population-Based Surveys in South Africa: Protocol for a Multiwave Cross-Sectional Analysis.

HIV testing is the cornerstone of HIV prevention and a pivotal step in realizing the Joint United Nations Program on HIV/AIDS (UNAIDS) goal of ending AIDS by 2030. Despite the availability of relevant survey data, there exists a research gap in using machine learning (ML) to analyze and predict HIV testing among adults in South Africa. Further investigation is needed to bridge this knowledge gap and inform evidence-based interventions to improve HIV testing. This study aims to determine consistent predictors of HIV testing by applying supervised ML algorithms in repeated adult population-based surveys in South Africa. A retrospective analysis of multiwave cross-sectional survey data will be conducted to determine the predictors of HIV testing among South African adults aged 18 years and older. A supervised ML technique will be applied across the five cycles of the South African National HIV Prevalence, Incidence, Behavior, and Communication Survey (SABSSM) surveys. The Human Science Research Council (HSRC) conducted the SABSSM surveys in 2002, 2005, 2008, 2012, and 2017. The available SABSSM datasets will be imported to RStudio (version 4.3.2; Posit Software, PBC) to clean and remove outliers. A chi-square test will be conducted to select important predictors of HIV testing. Each dataset will be split into 80% training and 20% test samples. Logistic regression, support vector machines, random forests, and decision trees will be used. A cross-validation technique will be used to divide the training sample into k-folds, including a validation set, and models will be trained on each fold. The models' performance will be evaluated on the validation set using evaluation metrics such as accuracy, precision, recall, F1-score, area under curve-receiver operating characteristics, and confusion matrix. The SABSSM datasets are open access datasets available on the HSRC database. Ethics approval for this study was obtained from the University of Johannesburg Research and Ethics Committee on April 23, 2024 (REC-2725-2024). The authors were given access to all five SABSSM datasets by the HSRC on August 20, 2024. The datasets were explored to identify the independent variables likely influencing HIV testing uptake. The findings of this study will determine consistent variables predicting HIV testing uptake among the South African adult population over the course of 20 years. Furthermore, this study will evaluate and compare the performance metrics of the 4 different ML algorithms, and the best model will be used to develop an HIV testing predictive model. This study will contribute to existing knowledge and deepen understanding of factors linked to HIV testing beyond traditional methods. Consequently, the findings would inform evidence-based policy recommendations that can guide policy makers to formulate more effective and targeted public health approaches toward strengthening HIV testing. DERR1-10.2196/59916.

A machine learning framework for short-term prediction of chronic obstructive pulmonary disease exacerbations using personal air quality monitors and lifestyle data

Chronic Obstructive Pulmonary Disease (COPD) is a heterogeneous disease with a variety of symptoms including, persistent coughing and mucus production, shortness of breath, wheezing, and chest tightness. As the disease advances, exacerbations, i.e. acute worsening of respiratory symptoms, may increase in frequency, leading to potentially life-threatening complications. Exposure to air pollutants may trigger COPD exacerbations. Literature predictive models for COPD exacerbations, while promising, may be constrained by their reliance on fixed air quality sensor data that may not fully capture individuals’ dynamic exposure to air pollution. To address this, we designed a machine learning (ML) framework that leverages data from personal air quality monitors, health records, lifestyle, and living condition information to build models that perform short-term prediction of COPD exacerbations. The framework employs (i) k-means clustering to uncover potentially distinct patient sub-types, (ii) supervised ML techniques (Logistic Regression, Random Forest, and eXtreme Gradient Boosting) to train and test predictive models for each patient sub-type and (iii) an explainable artificial intelligence technique (SHAP) to interpret the final models. The framework was tested on data collected in 101 COPD patients monitored for up to 6 months with occurrence of exacerbation in 10.7% of total samples. Two different patient sub-types have been identified, characterised by different disease severity. The best performing models were Random Forest in cluster 1, with area under the receiver operating characteristic curve (AUC) of 0.90, and area under the precision/recall curve (AUPRC) of 0.7; and Random Forest model in cluster 2, with AUC of 0.82 and AUPRC of 0.56. The model interpretability analysis identified previous symptoms and cumulative pollutant exposure as key predictors of exacerbations. The results of our study set a premise for a predictive framework in COPD exacerbations, particularly investigating the potential influence of environmental features. The SHAP analysis revealed that the contribution of environmental features is not uniform across all subjects. For instance, cumulative exposure to pollutants demonstrated greater predictive power in cluster 1. The SHAP analysis also shown that overall clinical factors and individual symptomatology play the most significant role in this setup to determine exacerbation risk.

Machine learning-based technique for gain prediction of mm-wave miniaturized 5G MIMO slotted antenna array with high isolation characteristics

This study presents the design and analysis of a compact 28 GHz MIMO antenna for 5G wireless networks, incorporating simulations, measurements, and machine learning (ML) techniques to optimize its performance. With dimensions of 3.19 λ₀ × 3.19 λ₀, the antenna offers a bandwidth of 5.1 GHz, a peak gain of 9.43 dBi, high isolation of 31.37 dB, and an efficiency of 99.6%. Simulations conducted in CST Studio were validated through prototype measurements, showing strong agreement between the measured and simulated results. To further validate the design, an equivalent RLC circuit model was developed and analyzed using ADS, with the reflection coefficient results closely matching those from CST. Additionally, supervised ML techniques were employed to predict the antenna’s gain, evaluating nine models using metrics such as R-squared, variance score, mean absolute error, and root mean squared error. Among the models, Random Forest Regression achieved the highest accuracy, delivering approximately 99% reliability in gain prediction. This integration of machine learning with antenna design underscores its potential to optimize performance and enhance design efficiency. With its compact size, high isolation, and exceptional efficiency, the proposed antenna is a promising candidate for 28 GHz 5G applications, offering innovative solutions for next-generation wireless communication.

Exploring the process—structure–property relationship of nylon aramid 3D printed composites and parameter optimization using supervised machine learning techniques

The main goals of this research are to identify the significant input parameters using supervised machine learning methods and investigate the relationship between the process, structure, and properties of components created using fused deposition modeling utilizing nylon aramid composite filaments. To develop an experimental layout using Taguchi’s L18 orthogonal array, six different FDM parameters such as infill pattern, infill density, layer thickness, component orientation, print temperature, and raster angle have been taken into consideration.Using an Ultimaker FDM printer, rectangular samples were created, and the values of face hardness, thickness regions, printing time, and component weight were assessed. ANOVA and the signal to noise ratio method are two techniques that have been used to find the significant influencing parameter and the ideal combination of parameters. When comparing thickly layered samples with a suitable increase in time and weight, thin-layered samples are shown to have greater hardness values at both tested areas. With a 50.09% contribution to face hardness and a 30.11% contribution to hardness at the thickness area, raster angle is found to be significant over hardness.Layer thickness is an important element that contributes 81.95% to printing time and 42.09% to part weight, respectively. In an 80:20 train-test split, the decision tree approach outperformed the k-nearest neighbor algorithm for all four output responses, with classification accuracy ranging from 83.33% to 100%. Infill density is recommended by the decision tree method to be extremely significant over face hardness and component weight, and layer thickness is similarly recommended to be highly significant over printing time and hardness at the thickness region. The presence of surface pores, interior voids, and layer abnormalities is confirmed by FESEM images.

DiffuSeg: Domain-driven Diffusion for Medical Image Segmentation.

In recent years, the deployment of supervised machine learning techniques for segmentation tasks has significantly increased. Nonetheless, the annotation process for extensive datasets remains costly, labor-intensive, and error-prone. While acquiring sufficiently large datasets to train deep learning models is feasible, these datasets often experience a distribution shift relative to the actual test data. This problem is particularly critical in the domain of medical imaging, where it adversely affects the efficacy of automatic segmentation models. In this work, we introduce DiffuSeg, a novel conditional diffusion model developed for medical image data, that exploits any labels to synthesize new images in the target domain. This allows a number of new research directions, including the segmentation task that motivates this work. Our method only requires label maps from any existing datasets and unlabelled images from the target domain for image diffusion. To learn the target domain knowledge, a feature factorization variational autoencoder is proposed to provide conditional information for the diffusion model. Consequently, the segmentation network can be trained with the given labels and the synthetic images, thus avoiding human annotations. Initially, we apply our method to the MNIST dataset and subsequently adapt it for use with medical image segmentation datasets, such as retinal fundus images for vessel segmentation and MRI images for heart segmentation. Our approach exhibits significant improvements over relevant baselines in both image generation and segmentation accuracy, especially in scenarios where annotations for the target dataset are unavailable during training. An open-source implementation of our approach can be released after reviewing.