Effective Machine Learning Algorithm Research Articles

Enhancing Loan Prediction Accuracy: A Comparative Analysis of Machine Learning Algorithms with XAI Integration

The contemporary financial landscape necessitates loan recommendation systems that offer both accuracy and transparency. Conventional assessment methodologies often suffer from limitations in efficiency and transparency, leading to potential risks for both lenders and borrowers. This research proposes the development of a novel loan recommendation system that leverages the power of machine learning (ML) and Explainable Artificial Intelligence (XAI). The paper delves into the processes of data collection, preprocessing, model training, evaluation, and subsequent integration into a web application using the Flask framework. The employed datasets encompass a variety of loan types, with the study aiming to identify the most effective ML algorithms from a selection that includes XGBoost, CatBoost, Random Forest, Gradient Boosting, and Logistic Regression. To enhance the system's transparency, Explainable AI methods, such as LIME, are incorporated. The culmination of this research is a web application that facilitates personalized predictions regarding loan eligibility, accompanied by clear explanations. Index terms - Loan Recommendation System, Machine Learning, Explainable AI, XGBoost, CatBoost, Random Forest, Gradient Boost, Logistic Regression,LIME.

High-efficiency scattering field modeling in metallic components: a machine-learning-inspired approach

We present a highly efficient method for characterizing the scattering field distribution of surface plasmon polaritons in metallic components by combining the eXtended Pseudospectral Frequency-Domain (X-PSFD) method with an iterative, machine-learning-inspired procedure. Shifting away from traditional matrix operations, we utilize the “Adam” optimizer—an effective and swift machine learning algorithm—to solve the scattering field distribution. Our method encompasses the derivation of the associated cost function and gradient differentiation of the field, leveraging spectral accuracy at Legendre collocation points in the Helmholtz equation. We refine the total-field/scattered-field (TF/SF) formulation within the X-PSFD framework for optimized incident field management and employ Chebyshev–Lagrange interpolation polynomials for rapid, accurate computation of broad-band results. To ensure global accuracy, we introduce unique physical boundary conditions at subdomain interfaces. Demonstrating our method’s robustness and computational efficiency, we model perfect electric conductors (PECs) and silver nanocylinders, and we apply our approach to analyze the excited electric field on subtly distorted metallic surfaces, particularly plasmonic structures, thereby validating its wide-ranging effectiveness.

DEPRESSION DETECTION BY ANALYZING SOCIAL MEDIA POST OF USER: A REVIEW

In contemporary times, identifying depression at an early stage has become a critical issue within the field of psychology. Mental health problems, notably depression, afflict a significant portion of the global population, with an estimated 300 million individuals currently affected. Leveraging the vast amount of user-generated content on social media platforms, researchers are exploring ways to utilize this data to identify potential mental health issues in users. Depression remains a pressing concern in society and a topic of ongoing research globally. Despite numerous studies attempting to understand various mood disorders such as depression, anxiety, and stress using activity logs from devices like smartphones, accurately predicting depressive episodes remains challenging. Social media analysis has emerged as a popular approach to tackle this challenge. In this paper, we propose a system for assessing depression and detecting suicidal ideation by predicting suicidal tendencies based on the severity of depression. Our study aims to develop effective machine learning algorithms for identifying potential signs of depression in individuals through their social media posts. To achieve this, we trained and tested classifiers to discern whether a person exhibits signs of depression using features extracted from their social media activities. Various machine learning algorithms were employed to train and classify users into different levels of depression on a scale ranging from 0 to 100%. Data in the form of posts were collected and categorized into depressed or non-depressed using machine learning algorithms. Our primary contribution lies in exploring a range of features and their effectiveness in detecting the degree of depression. We aim to build a deep learning model capable of categorizing users with depression by learning from individual-level labels to infer post-level labels. By amalgamating the probabilities of post label categories, we can create temporal posting profiles to classify users with depression. Our findings reveal distinct variations in posting behaviors between depressed and non-depressed users, as indicated by the combined probabilities of post label categories. In our study, we utilized natural language processing (NLP) techniques, employing the BERT algorithm, to efficiently identify potential depression indicators in social media content. This approach offers a more accessible and effective means of detecting depression. Keywords— Machine Learning, NLP, BERT Algorithm, Depression, Classification, Social Media Post.

A Two-stage Method for Damage Detection in Z24 Bridge Based on K-nearest Neighbor and Artificial Neural Network

In this paper, we propose an effective approach for identifying damages in the Z24 bridge, a large-scale bridge in Switzerland. The dataset of the Z24 bridge is evaluated as a benchmark, reflecting the behavior of a real structure that has been used for numerous studies. However, most of the previous studies have only addressed the issues of updating the model or estimating the location and severity of damages. The core idea behind our proposed approach is to leverage the strengths of two effective Machine Learning (ML) algorithms: K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN), to assess both the location and severity of damages in the Z24 bridge. First, we employ KNN, an unsupervised learning algorithm, for pinpointing the damage location. This strategy proves highly efficient, significantly reducing computation time by circumventing the need for a loss function during KNN training. By adopting this approach, KNN effectively mitigates the risk of encountering local minima in the ANN optimization process. Subsequently, we deploy ANN to determine the damage severity. When compared to previous studies on the Z24 bridge, our proposed method (KNN-ANN) exhibits promising results. Furthermore, our results illustrate that KNN-ANN consistently outperforms traditional ANN methodologies.

P066 Predictive Modeling of Infection Risk in Lupus Nephritis using Multiple Machine Learning Algorithms

Abstract Background/Aims The incidence of infections is considerably higher among patients with lupus nephritis (LN), and these infections significantly contribute to mortality rates. This study analysed the characteristics of peripheral blood lymphocyte subsets in LN patients, aiming at using machine learning (ML) methods to explore the risk factors of infection and establish a most effective ML algorithm to predict the occurrence of co-infection in LN. Methods This retrospective study encompassed LN patients, consisting of 111 non-infected individuals and 72 infected individuals. Additionally, 206 healthy controls (HCs) matched age and sex were recruited. The patient’s basic information, infection site, pathogen type, clinical manifestation, patient medication, and auxiliary laboratory indexes were recorded. Eight ML methods were compared to establish a corresponding model through a training group, and then verify the results in a test group. We trained the ML models, including Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Random Forest (RF), Ada boost (Ada), Extreme Gradient Boosting (XGB), after selecting variables for LN infection prediction in the training set, and further evaluated potential predictors of infection. Results The levels of T, B, helper T, suppressor T, Natural killer cells in the infected patients were significantly decreased when compared with both non-infected LN patients and HCs. The number of regulatory T cells in LN was significantly lower than HCs, and the infected patients had the fewest regulatory T cells among all these groups. Regarding localization of infection, the respiratory tract was most frequently involved (69.4%), followed by gastrointestinal (20.8%) and urinary tract infection (12.5%). Concerning pathogens, bacterial infection was more common. Viral included Epstein Barr virus, cytomegalovirus, and respiratory syncytial virus. In training group, the AUC values, accuracy and precision of DT, RF, Ada, and XGB were 1, 100%, and 100%, respectively. As for the modeled effects of predicting LN co-infection in test groups by the eight algorithms, the three algorithms with the highest AUC values were SVM, RF and XGB, with values of 0.85, 0.81 and 0.76, respectively. Among the algorithms, XGB algorithm has the highest accuracy (80%) and precision (84.62%), thus it is recommended to be used for prediction in clinical practice. In addition, the top four weighting factors for infection identified of LN by the XGB in ML were T, red blood cell, hospital length of stay, and lymphocyte%. Conclusion Both innate and adaptive immune systems in LN patients are disturbed, and monitoring the lymphocyte subsets may provide a reference for the prevention and treatment of infection. Our research found that the XGB algorithm performs better than other models with the most accuracy in prediction, which may be one of the preferred algorithms in LN patients with co-infection for future research. Disclosure J. Zhang: None. P. Cai: None. J. Liu: None. Q. Xie: None.

Using Artificial Intelligence Algorithms to Detect Hate Speech in Social Media Posts

Detecting hate speech on social media is of great importance to prevent negative impacts on people and communities and to remove such content. However, detecting hate speech is a complex and challenging process due to linguistic and cultural diversity. Therefore, it is important to develop powerful and effective machine learning algorithms. Since detecting such content using traditional methods can be time-consuming and costly, it is stated that artificial intelligence-based machine learning algorithms have great potential in this regard. The aim of this study is to evaluate the performance of artificial intelligence-based machine learning algorithms used in detecting posts containing hate speech on social media. The study focuses on the problem of detecting and managing hate speech on social media platforms. In this study, we will compare the performances of different algorithms and determine the most suitable methods. Additionally, the effects of the dataset and feature extraction methods on algorithm performance will be analyzed. Algorithms are often based on natural language processing techniques and try to detect hate speech by learning features in texts. The performance of these algorithms can vary depending on factors such as language, culture, the attributes they use, and the training dataset, so a comprehensive analysis is required. In the research, the performance of the algorithms used in detecting hate speech was compared with the dataset and feature extraction methods. In this process, the algorithms' linguistic and cross-cultural effectiveness, feature selection and representation, false positive and false negative rates, and overall accuracy will be analyzed.

Optimization of Using Multiple Machine Learning Approaches in Atrial Fibrillation Detection Based on a Large-Scale Data Set of 12-Lead Electrocardiograms: Cross-Sectional Study.

Atrial fibrillation (AF) represents a hazardous cardiac arrhythmia that significantly elevates the risk of stroke and heart failure. Despite its severity, its diagnosis largely relies on the proficiency of health care professionals. At present, the real-time identification of paroxysmal AF is hindered by the lack of automated techniques. Consequently, a highly effective machine learning algorithm specifically designed for AF detection could offer substantial clinical benefits. We hypothesized that machine learning algorithms have the potential to identify and extract features of AF with a high degree of accuracy, given the intricate and distinctive patterns present in electrocardiogram (ECG) recordings of AF. This study aims to develop a clinically valuable machine learning algorithm that can accurately detect AF and compare different leads' performances of AF detection. We used 12-lead ECG recordings sourced from the 2020 PhysioNet Challenge data sets. The Welch method was used to extract power spectral features of the 12-lead ECGs within a frequency range of 0.083 to 24.92 Hz. Subsequently, various machine learning techniques were evaluated and optimized to classify sinus rhythm (SR) and AF based on these power spectral features. Furthermore, we compared the effects of different frequency subbands and different lead selections on machine learning performances. The light gradient boosting machine (LightGBM) was found to be the most effective in classifying AF and SR, achieving an average F1-score of 0.988 across all ECG leads. Among the frequency subbands, the 0.083 to 4.92 Hz range yielded the highest F1-score of 0.985. In interlead comparisons, aVR had the highest performance (F1=0.993), with minimal differences observed between leads. In conclusion, this study successfully used machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs. The performance marked by an average F1-score of 0.988 and minimal interlead variation underscores the potential of machine learning algorithms to bolster real-time AF detection. This advancement could significantly improve patient care in intensive care units as well as facilitate remote monitoring through wearable devices, ultimately enhancing clinical outcomes.

Predicting political attitudes from web tracking data: a machine learning approach

ABSTRACT Anecdotal evidence suggests that the surge of populism and subsequent political polarization might make voters’ political preferences more detectable from digital trace data. This potential scenario could expose voters to the risk of being targeted and easily influenced by political actors. This study investigates the linkage between over 19,000,000 website visits, tracked from 1,003 users in Germany, and their survey responses to explore whether website choices can accurately predict political attitudes across five dimensions: Immigration, democracy, issues (such as climate and the European Union), populism, and trust. Our findings indicate a limited ability to identify political attitudes from individuals’ website visits. Our most effective machine learning algorithm predicted interest in politics and attitudes toward democracy but with dependency on model parameters. Although website categories exhibited suggestive patterns, they only marginally distinguished between individuals with anti- or pro-immigration attitudes, as well as those with populist or mainstream attitudes. This further confirm the reliability of surveys in measuring attitudes compared to digital trace data and, from a normative perspective, suggests that the potential to extract sensitive political information from online behavioral data, which could be utilized for microtargeting, remains limited.

Combining machine learning and remote sensing-integrated crop modeling for rice and soybean crop simulation.

Machine learning (ML) techniques offer a promising avenue for improving the integration of remote sensing data into mathematical crop models, thereby enhancing crop growth prediction accuracy. A critical variable for this integration is the leaf area index (LAI), which can be accurately assessed using proximal or remote sensing data based on plant canopies. This study aimed to (1) develop a machine learning-based method for estimating the LAI in rice and soybean crops using proximal sensing data and (2) evaluate the performance of a Remote Sensing-Integrated Crop Model (RSCM) when integrated with the ML algorithms. To achieve these objectives, we analyzed rice and soybean datasets to identify the most effective ML algorithms for modeling the relationship between LAI and vegetation indices derived from canopy reflectance measurements. Our analyses employed a variety of ML regression models, including ridge, lasso, support vector machine, random forest, and extra trees. Among these, the extra trees regression model demonstrated the best performance, achieving test scores of 0.86 and 0.89 for rice and soybean crops, respectively. This model closely replicated observed LAI values under different nitrogen treatments, achieving Nash-Sutcliffe efficiencies of 0.93 for rice and 0.97 for soybean. Our findings show that incorporating ML techniques into RSCM effectively captures seasonal LAI variations across diverse field management practices, offering significant potential for improving crop growth and productivity monitoring.

Carpal tunnel syndrome prediction with machine learning algorithms using anthropometric and strength-based measurement.

Carpal tunnel syndrome (CTS) stands as the most prevalent upper extremity entrapment neuropathy, with a multifaceted etiology encompassing various risk factors. This study aimed to investigate whether anthropometric measurements of the hand, grip strength, and pinch strength could serve as predictive indicators for CTS through machine learning techniques. Enrollment encompassed patients exhibiting CTS symptoms (n = 56) and asymptomatic healthy controls (n = 56), with confirmation via electrophysiological assessments. Anthropometric measurements of the hand were obtained using a digital caliper, grip strength was gauged via a digital handgrip dynamometer, and pinch strengths were assessed using a pinchmeter. A comprehensive analysis was conducted employing four most common and effective machine learning algorithms, integrating thorough parameter tuning and cross-validation procedures. Additionally, the outcomes of variable importance were presented. Among the diverse algorithms, Random Forests (accuracy of 89.474%, F1-score of 0.905, and kappa value of 0.789) and XGBoost (accuracy of 86.842%, F1-score of 0.878, and kappa value of 0.736) emerged as the top-performing choices based on distinct classification metrics. In addition, using variable importance calculations specific to these models, the most important variables were found to be wrist circumference, hand width, hand grip strength, tip pinch, key pinch, and middle finger length. The findings of this study demonstrated that wrist circumference, hand width, hand grip strength, tip pinch, key pinch, and middle finger length can be utilized as reliable indicators of CTS. Also, the model developed herein, along with the identified crucial variables, could serve as an informative guide for healthcare professionals, enhancing precision and efficacy in CTS prediction.

Efficient machine learning models for the detection of coconut milk adulteration

Coconut milk adulteration detection involves the use of analytical methods, including machine learning, to detect the presence of impurities or additives in coconut milk. Adulteration can occur when substances such as water or other cheaper ingredients are added to coconut milk, compromising its quality, nutritional value, and authenticity. Identifying adulteration is crucial for ensuring consumer safety, maintaining product quality, and upholding industry standards. The aim of this study was to propose a machine learning model to detect adulteration in coconut milk. To implement the proposed work, a coconut milk adulteration dataset is collected from a standard source. The amount of available data is limited; hence, synthetic data is generated by applying the CTGAN algorithm. The proposed framework employs three different Feature Extraction (FE) strategies, i.e., Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Autoencoder (AE). Then, the feature-extracted dataset is classified through four effective machine learning algorithms, such as Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The machine learning algorithms outcomes are evaluated using four performance metrics, i.e., Accuracy, Precision, Recall, and F1-score. RF provides the highest accuracy of 99.17%, precision value of 97.29%, recall value of 96.71%, and F1 Score of 97% for the LDA techniques.

Prediction of Coronary Artery Disease using Machine Learning – A Comparative study of Algorithms

Purpose: Heart illness is one of the major killers of humans worldwide. Heart illness and the possibility of experiencing a heart attack have both increased in recent years. Medical professionals face significant difficulties when attempting to forecast heart disease. One of the medical field's virtuosi is early prediction, and this is particularly true in cardiology. The early prediction model-building studies illuminated the most up-to-date methods for locating variations in medical imaging. The study of computer-assisted diagnosis is a dynamic and quickly developing field. Since wrong medical diagnoses can lead to dangerous treatments, a lot of work has been done recently to enhance computer programs that help doctors make diagnoses. Computer-assisted diagnosis relies heavily on machine learning. The basic aspect of pattern recognition is the capability to learn from precedents. Pattern identification and artificial intelligence have a lot of promise to improve the accuracy with which biomedical professionals perceive and diagnose illness. They also help make decisions more objectively. Machine learning is a promising method for developing elegant and automatic algorithms for the study of high-dimensional and multimodal bio-medical data. Two heart disease-related datasets were considered for the purpose of this research. The study implements several machine learning algorithms and compares their prediction accuracy and a handful of other performance metrics to determine which one is the most effective. Objective: The primary goal of the research is to evaluate the performance of several machine learning algorithms using different evaluation criteria such as f1 score, roc, and auc values. The aim is to discover the most effective machine learning algorithm for the datasets obtained for the study. Design/Methodology/Approach: The research utilizes datasets from Kaggle heart information. Python, Skilearn, Pandas, and Jupyter Notebook have been used to build various machine learning prediction models and the outcomes have been compared. Findings/Results: Both datasets comprise of different parameters, therefore pre-processing had to be customized. Applying machine learning algorithms to the training dataset and comparing the trained models to the testing dataset yielded varied results for each dataset. Model performance was measured by accuracy and AUC. Both datasets gave good results with boosting algorithms, however the Cleveland dataset did better with decision trees. Originality/Value: The research included an examination of two Kaggle heart databases. It has been seen how data is distributed, how various features depend on each other, and how all the features influence the target feature of heart disease prediction. Models have been constructed and trained using different machine learning methods, each with its own set of hyper-tuning parameters. To learn which machine learning model is most effective for a given collection of data, the study has looked into both the prediction results using the trained models and the performance parameters of the individual models. Through this study, we now know more about how different machine learning methods work. To determine the most effective algorithm, it is necessary to conduct additional research of the datasets using Deep Learning techniques. Paper Type: Comparative Study

APPLICATION OF NAÏVE BAYES CLASSIFIER ALGORITHM IN DETERMINING THE LEVEL OF CUSTOMER SATISFACTION WITH RUMBAI POST OFFICE SERVICES

Technological advances make service and delivery of goods grow rapidly. Coupled with people's changing shopping habits by shopping online, shipping companies are increasingly needed. PT. POS Indonesia is the first expedition company in Indonesia. Currently PT. POS Indonesia has opened many POS Office branches in every region in Indonesia, one of which is the Rumbai POS Office located in Pekanbaru City. To continue to maintain the company while competing with other expeditions, the Rumbai POS Office must continue to maintain its customers by improving the quality of service. Survey analysis can be done to determine the extent of customer satisfaction with the services provided. To find out the level of customer satisfaction, you can use the classification method. Naive Bayes is a popular and effective machine learning algorithm for classification problems. The study used datasets sourced from the results of questionnaire distribution to customers of the Rumbai POS Office. The questionnaire used 14 indicators derived from the Community Satisfaction Index set by the Ministry of Agriculturein 2004. The classification resulted in a Satisfied class of 16 data with a percentage of 84.2% and a Dissatisfied class of 3 data with a percentage of 15.8%, it can be concluded that the service at the Rumbai POS Office is good. From the classification results, it is proven that the Naïve Bayes algorithm is able to predict well the level of customer satisfaction with an accuracy value of 94.74%, precision of 100%, and recall of 94.12%. The results of this research can later be used as information for the Rumbai POS Office to be able to improve service quality.

A multi-factor quantitative model based on weighted SIR-SAVE and model averaging

In financial quantitative research, there are many kinds of predictors that are closely related to stock prices, so how to design effective machine learning algorithms for such high-dimensional prediction problems is a hot issue. Based on this, this paper proposes a stock factor quantization and prediction model based on the idea of sufficient dimensionality reduction and model averaging. The proposed method is based on the principle of conditional independence, which can greatly retain the validity of the predictors on the stock price while solving the dimensionality catastrophe problem. In addition, the method adaptively learns the link function between the quantized factors and stock prices by using the model averaging method to effectively weigh the variance and bias of the prediction model. In the actual data analysis, this paper chooses the weighted SIR-SAVE as the adequate dimensionality reduction method, the mutual information criterion as the assignment rule of model averaging, and some classical high-dimensional regression techniques as the comparison method, and the empirical results show that the proposed method has a higher accuracy under the evaluation indexes of mean squared error and absolute error, and possesses a certain degree of robustness. Finally, since the sub-models in the model averaging are free, the proposed method is also applicable to the problem of classifying the prediction of stock ups and downs.

MACHINE LEARNING APPROACH FOR SCIENTIFIC AND TECHNICAL EXPERTISE

When conducting scientific and technical expertise, it is necessary to analyze the texts of reports on scientific research work. The analysis is carried out in order to determine whether the research being conducted belongs to the class of scientific research and development work in the field of IT. The main purpose of this study is to improve algorithms for analyzing text documents during scientific and technical expertise. To achieve this goal, the tasks of binary classification of documents provided by companies using machine learning technologies are considered. As a result of the study, a comparative analysis was carried out and the most effective machine learning algorithms were identified. The proposed algorithms will be used in a system that automates the process of checking documents submitted to taxpayers by the tax office.

Effective Machine Learning Algorithm to Predict House Price

Effective Machine Learning Algorithm to Predict House Price

Constructing a Deep Learning Radiomics Model Based on X-ray Images and Clinical Data for Predicting and Distinguishing Acute and Chronic Osteoporotic Vertebral Fractures: A Multicenter Study

To construct and validate a deep learning radiomics (DLR) model based on X-ray images for predicting and distinguishing acute and chronic osteoporotic vertebral fractures (OVFs). A total of 942 cases (1076 vertebral bodies) with both vertebral X-ray examination and MRI scans were included in this study from three hospitals. They were divided into a training cohort (n=712), an internal validation cohort (n=178), an external validation cohort (n=111), and a prospective validation cohort (n=75). The ResNet-50 model architecture was used for deep transfer learning (DTL), with pre-training performed on RadImageNet and ImageNet datasets. DTL features and radiomics features were extracted from lateral X-ray images of OVFs patients and fused together. A logistic regression model with the least absolute shrinkage and selection operator was established, with MRI showing bone marrow edema as the gold standard for acute OVFs. The performance of the model was evaluated using receiver operating characteristic curves. Eight machine learning classification models were evaluated for their ability to distinguish between acute and chronic OVFs. The Nomogram was constructed by combining clinical baseline data to achieve visualized classification assessment. The predictive performance of the best RadImageNet model and ImageNet model was compared using the Delong test. The clinical value of the Nomogram was evaluated using decision curve analysis (DCA). Pre-training resulted in 34 and 39 fused features after feature selection and fusion. The most effective machine learning algorithm in both DLR models was Light Gradient Boosting Machine. Using the Delong test, the area under the curve (AUC) for distinguishing between acute and chronic OVFs in the training cohort was 0.979 and 0.972 for the RadImageNet and ImageNet models, respectively, with no statistically significant difference between them (P=0.235). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.629, 0.886 vs 0.817, and 0.933 vs 0.661, respectively, with statistically significant differences in all comparisons (P<0.05). The deep learning radiomics nomogram (DLRN) was constructed by combining the predictive model of RadImageNet with clinical baseline features, resulting in AUCs of 0.981, 0.974, 0.895, and 0.902 in the training cohort, internal validation cohort, external validation cohort, and prospective validation cohort, respectively. Using the Delong test, the AUCs for the fused feature model and the DLRN in the training cohort were 0.979 and 0.981, respectively, with no statistically significant difference between them (P=0.169). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.974, 0.886 vs 0.895, and 0.933 vs 0.902, respectively, with statistically significant differences in all comparisons (P<0.05). The Nomogram showed a slight improvement in predictive performance in the internal and external validation cohort, but a slight decrease in the prospective validation cohort (0.933 vs 0.902). DCA showed that the Nomogram provided more benefits to patients compared to the DLR models. Compared to the ImageNet model, the RadImageNet model has higher diagnostic value in distinguishing between acute and chronic OVFs. Furthermore, the diagnostic performance of the model is further improved when combined with clinical baseline features to construct the Nomogram.

Artificial Intelligence for Surface Water Quality Evaluation, Monitoring and Assessment

The study utilizes a dataset with seven critical constraints and creates models that are estimated based on various metrics. The goal is to categorize and properly predict the water quality index (WQI) using the suggested models. The outcomes show that the implied models can accurately assess water quality and forecast WQI with high rates of success. Temperature, pH, dissolved oxygen (DO), conductivity, total dissolved solids (TDS), turbidity, and chlorides (Cl-) are some of the six crucial factors used in the study’s dataset. The mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2) are some of the metrics used to develop and assess the Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) models. The study also makes use of heat maps and correlation graphs to shed further light on the connections between various water quality measures. The color-coded values of the seven parameters, which represent the water quality level of the sample, are displayed on the heat map. The link between the two parameters is shown by the correlation graph between TDS and turbidity, which depicts their correlation coefficient. The study’s results show how effective machine learning algorithms may be as a tool for observing surface water quality. Himachal Pradesh is the tourist hub, so with the rapid increase in the volume of surface water contamination, the application of artificial intelligence will give a better view of data analytics and help with prediction and modeling. It was obtained from the study that the mean square error and root mean square error of ANN and LSTM lie between 0.52–6.0 and 0.04–0.21, respectively. However, the LSTM model’s accuracy is 95%, which is higher than the ANN model. The study highlights the importance of leveraging machine learning techniques in water quality monitoring to ensure the protection and management of water resources. With advancements in machine learning, artificial intelligence (AI) techniques have emerged as a promising tool for surface water quality monitoring. The major goal of the study is to explore the potential of two types of machine learning algorithms, namely artificial neural networks (ANNs) and long short-term memory (LSTM) models, for surface water quality monitoring.

Machine learning and DFT-based combined framework for predicting transmission spectra of quantum-confined bio-molecular nanotube.

The Adenine-based nanotube is theoretically designed, and its transmission spectra are investigated. The quantum-confined Adenine nanotube shows electronic transmission of the carrier at minimum stress. In this paper, the prediction of transmission spectra of the quantum-confined bio-molecular nanotube is investigated and deeply studied. Molecular level structure prediction and their electronic characterization can be possible with ab initio accuracy using a machine learning algorithmic approach. At the molecular level, it is difficult to predict quantum transmission spectra as these results are always hampered by the carrier backscattering effect. However, mostly these predictive models are available for intrinsic semi-conducting materials and other inorganic structures. Machine learning algorithms are designed to predict the electronic properties of the nano-scale structure. This task is even more difficult when quantum-confined molecular arrangements are considered, whose transmission spectra are sensitive to the confinements applied. This paper presents an effective machine learning algorithms framework for predicting transmission spectra of quantum-confined nanotubes from their geometries. In this paper, we consider regression machine learning algorithms to find maximum accuracy with varying configurations and geometries to excerpt their atoms' local environment information. The Hamiltonian components are then used to enable the utilization of the information to predict the electronic structure at any arbitrary sampling point or k-point. The theoretical basics introduced in this process help to capture and incorporate minor changes in quantum confinements into transmission spectra and provide the framework algorithm with more accuracy. This paper shows the ability to predict the accurate algorithmic models of the Adenine nanotube. In this framework, we have considered a tiny data set to achieve a rapid and reliable method for electronic structure determination and also propose the best algorithm for predictive model analysis.

Rapid Diagnosis of Urinary Tract Cancers on a LEGO-Inspired Detection Platform via Chemiresistive Profiling of Volatile Metabolites.

Rapid and in situ profiling of volatile metabolites from body fluids represents a new trend in cancer diagnosis and classification in the early stages. We report herein an on-chip strategy that combines an array of conductive nanosensors with a chaotic gas micromixer for real-time monitoring of volatiles from urine and for accurate diagnosis and classification of urinary tract cancers. By integrating a class of LEGO-inspired microchambers immobilized with MXene-based sensing nanofilms and zigzag microfluidic gas channels, it enables the intensive intermingling of volatile organic chemicals with sensor elements that tremendously facilitate their ion-dipole interactions for molecular recognition. Aided with an all-in-one, point-of-care platform and an effective machine-learning algorithm, healthy or diseased samples from subpopulations (i.e., tumor subtypes, staging, lymph node metastasis, and distant metastasis) of urinary tract cancers can be reliably fingerprinted in a few minutes with high sensitivity and specificity. The developed detection platform has proven to be a noninvasive supplement to the liquid biopsies available for facile screening of urinary tract cancers, which holds great potential for large-scale personalized healthcare in low-resource areas.