Overfitting Reduction of Text Classification Based on AdaBELM

Stacked Ensemble with Machine Learning Regressors on Optimal Features (SMOF) of hyperspectral sensor PRISMA for inland water turbidity prediction

Leveraging hyperspectral data across various domains yields substantial benefits, yet managing many spectral bands and identifying the essential ones poses a formidable challenge. This study identifies the most relevant bands within a hyperspectral data cube for turbidity prediction in inland water. Nine machine learning regressors Cat Boost, Decision Trees, Extra Trees, Gradient Boost, Light Gradient Boost (LightGBM), Recursive Feature Elimination (RFE), Random Forest, Support Vector Regressor (SVR), and Xtreme Gradient Boost (XGBoost) have been used to compute the feature importance of the hyperspectral bands for predicting turbidity. Random Forest has outperformed the other models with a mean absolute percentage error (MAPE) of 1.61%, and the R2 of the linear fit is 0.96. Band 77, with a central wavelength of 1067.61 nm, is the most dominating band regarding feature importance. We have also developed a novel framework for turbidity prediction: Stacked Ensemble with Machine Learning Regressors on Optimal Features (SMOF). It employs a stacking ensemble of the nine regressors mentioned above with Random Forest as both base and meta-model, leveraging feature selection outputs. With this framework, the MAPE (%) reached 1.21, while the R2 stood at 0.95. The present study also presents a simple statistical algorithm to detect noisy bands in the Hyperspectral Precursor of the Application Mission (PRISMA) data cube. The approach assesses quadrat-wise intra-band spatial coherence using Renyi's entropy thresholding for noisy band segregation. Radiometric calibration error and absorption due to water vapour are the two primary sources of noise within the data cube. Moreover, this research implements the open-source Water Colour Simulator (WASI) to simulate inland water spectra with varied proportions of turbidity. Overall, the study presents an approach to identify noisy bands and integrates the potential wavelengths for turbidity prediction of inland waters.

Detection of ChatGPT fake science with the xFakeSci learning algorithm

Generative AI tools exemplified by ChatGPT are becoming a new reality. This study is motivated by the premise that "AI generated content may exhibit a distinctive behavior that can be separated from scientific articles". In this study, we show how articles can be generated using means of prompt engineering for various diseases and conditions. We then show how we tested this premise in two phases and prove its validity. Subsequently, we introduce xFakeSci, a novel learning algorithm, that is capable of distinguishing ChatGPT-generated articles from publications produced by scientists. The algorithm is trained using network models driven from both sources. To mitigate overfitting issues, we incorporated a calibration step that is built upon data-driven heuristics, including proximity and ratios. Specifically, from a total of a 3952 fake articles for three different medical conditions, the algorithm was trained using only 100 articles, but calibrated using folds of 100 articles. As for the classification step, it was performed using 300 articles per condition. The actual label steps took place against an equal mix of 50 generated articles and 50 authentic PubMed abstracts. The testing also spanned publication periods from 2010 to 2024 and encompassed research on three distinct diseases: cancer, depression, and Alzheimer's. Further, we evaluated the accuracy of the xFakeSci algorithm against some of the classical data mining algorithms (e.g., Support Vector Machines, Regression, and Naive Bayes). The xFakeSci algorithm achieved F1 scores ranging from 80 to 94%, outperforming common data mining algorithms, which scored F1 values between 38 and 52%. We attribute the noticeable difference to the introduction of calibration and a proximity distance heuristic, which underscores this promising performance. Indeed, the prediction of fake science generated by ChatGPT presents a considerable challenge. Nonetheless, the introduction of the xFakeSci algorithm is a significant step on the way to combating fake science.

Machine-learning-aided application of high-gravity technology to enhance ammonia recovery of fresh waste leachate

Stripping is widely applied for the removal of ammonia from fresh waste leachate. However, the development of air stripping technology is restricted by the requirements for large-scale equipment and long operation periods. This paper describes a high-gravity technology that improves ammonia stripping from actual fresh waste leachate and a machine learning approach that predicts the stripping performance under different operational parameters. The high-gravity field is implemented in a co-current-flow rotating packed bed in multi-stage cycle series mode. The eXtreme Gradient Boosting algorithm is applied to the experimental data to predict the liquid volumetric mass transfer coefficient (K_La) and removal efficiency (η) for various rotation speeds, numbers of stripping stages, gas flow rates, and liquid flow rates. Ammonia stripping under a high-gravity field achieves η = 82.73% and K_La = 5.551 × 10^-4 s^-1 at a pH value of 10 and ambient temperature. The results suggest that the eXtreme Gradient Boosting model provides good accuracy and predictive performance, with R² values of 0.9923 and 0.9783 for K_La and η, respectively. The machine learning models developed in this study are combined with experimental results to provide more comprehensive information on rotating packed bed operations and more accurate predictions of K_La and η. The information mining behind the model is an important reference for the rational design of high-gravity-field-coupled ammonia stripping projects.

UAV Multispectral Image-Based Urban River Water Quality Monitoring Using Stacked Ensemble Machine Learning Algorithms—A Case Study of the Zhanghe River, China

Timely monitoring of inland water quality using unmanned aerial vehicle (UAV) remote sensing is critical for water environmental conservation and management. In this study, two UAV flights were conducted (one in February and the other in December 2021) to acquire images of the Zhanghe River (China), and a total of 45 water samples were collected concurrently with the image acquisition. Machine learning (ML) methods comprising Multiple Linear Regression, the Least Absolute Shrinkage and Selection Operator, a Backpropagation Neural Network (BP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) were applied to retrieve four water quality parameters: chlorophyll-a (Chl-a), total nitrogen (TN), total phosphors (TP), and permanganate index (CODMn). Then, ML models based on the stacking approach were developed. Results show that stacked ML models could achieve higher accuracy than a single ML model; the optimal methods for Chl-a, TN, TP, and CODMn were RF-XGB, BP-RF, RF, and BP-RF, respectively. For the testing dataset, the R2 values of the best inversion models for Chl-a, TN, TP, and CODMn were 0.504, 0.839, 0.432, and 0.272, the root mean square errors were 1.770 μg L−1, 0.189 mg L−1, 0.053 mg L−1, and 0.767 mg L−1, and the mean absolute errors were 1.272 μg L−1, 0.632 mg L−1, 0.045 mg L−1, and 0.674 mg L−1, respectively. This study demonstrated the great potential of combined UAV remote sensing and stacked ML algorithms for water quality monitoring.

Discrimination of Methicillin-resistant Staphylococcus aureus by MALDI-TOF Mass Spectrometry with Machine Learning Techniques in Patients with Staphylococcus aureus Bacteremia

Early administration of proper antibiotics is considered to improve the clinical outcomes of Staphylococcus aureus bacteremia (SAB), but routine clinical antimicrobial susceptibility testing takes an additional 24 h after species identification. Recent studies elucidated matrix-assisted laser desorption/ionization time-of-flight mass spectra to discriminate methicillin-resistant strains (MRSA) or even incorporated with machine learning (ML) techniques. However, no universally applicable mass peaks were revealed, which means that the discrimination model might need to be established or calibrated by local strains' data. Here, a clinically feasible workflow was provided. We collected mass spectra from SAB patients over an 8-month duration and preprocessed by binning with reference peaks. Machine learning models were trained and tested by samples independently of the first six months and the following two months, respectively. The ML models were optimized by genetic algorithm (GA). The accuracy, sensitivity, specificity, and AUC of the independent testing of the best model, i.e., SVM, under the optimal parameters were 87%, 75%, 95%, and 87%, respectively. In summary, almost all resistant results were truly resistant, implying that physicians might escalate antibiotics for MRSA 24 h earlier. This report presents an attainable method for clinical laboratories to build an MRSA model and boost the performance using their local data.

Machine Learning in Causal Inference: Application in Pharmacovigilance

Monitoring adverse drug events or pharmacovigilance has been promoted by the World Health Organization to assure the safety of medicines through a timely and reliable information exchange regarding drug safety issues. We aim to discuss the application of machine learning methods as well as causal inference paradigms in pharmacovigilance. We first reviewed data sources for pharmacovigilance. Then, we examined traditional causal inference paradigms, their applications in pharmacovigilance, and how machine learning methods and causal inference paradigms were integrated to enhance the performance of traditional causal inference paradigms. Finally, we summarized issues with currently mainstream correlation-based machine learning models and how the machine learning community has tried to address these issues by incorporating causal inference paradigms. Our literature search revealed that most existing data sources and tasks for pharmacovigilance were not designed for causal inference. Additionally, pharmacovigilance was lagging in adopting machine learning-causal inference integrated models. We highlight several currently trending directions or gaps to integrate causal inference with machine learning in pharmacovigilance research. Finally, our literature search revealed that the adoption of causal paradigms can mitigate known issues with machine learning models. We foresee that the pharmacovigilance domain can benefit from the progress in the machine learning field.

A new neutrosophic TF-IDF term weighting for text mining tasks: text classification use case

Purpose

This paper aims to present a new term weighting approach for text classification as a text mining task. The original method, neutrosophic term frequency – inverse term frequency (NTF-IDF), is an extended version of the popular fuzzy TF-IDF (FTF-IDF) and uses the neutrosophic reasoning to analyze and generate weights for terms in natural languages. The paper also propose a comparative study between the popular FTF-IDF and NTF-IDF and their impacts on different machine learning (ML) classifiers for document categorization goals.

Design/methodology/approach

After preprocessing textual data, the original Neutrosophic TF-IDF applies the neutrosophic inference system (NIS) to produce weights for terms representing a document. Using the local frequency TF, global frequency IDF and text N's length as NIS inputs, this study generate two neutrosophic weights for a given term. The first measure provides information on the relevance degree for a word, and the second one represents their ambiguity degree. Next, the Zhang combination function is applied to combine neutrosophic weights outputs and present the final term weight, inserted in the document's representative vector. To analyze the NTF-IDF impact on the classification phase, this study uses a set of ML algorithms.

Findings

Practicing the neutrosophic logic (NL) characteristics, the authors have been able to study the ambiguity of the terms and their degree of relevance to represent a document. NL's choice has proven its effectiveness in defining significant text vectorization weights, especially for text classification tasks. The experimentation part demonstrates that the new method positively impacts the categorization. Moreover, the adopted system's recognition rate is higher than 91%, an accuracy score not attained using the FTF-IDF. Also, using benchmarked data sets, in different text mining fields, and many ML classifiers, i.e. SVM and Feed-Forward Network, and applying the proposed term scores NTF-IDF improves the accuracy by 10%.

Originality/value

The novelty of this paper lies in two aspects. First, a new term weighting method, which uses the term frequencies as components to define the relevance and the ambiguity of term; second, the application of NL to infer weights is considered as an original model in this paper, which also aims to correct the shortcomings of the FTF-IDF which uses fuzzy logic and its drawbacks. The introduced technique was combined with different ML models to improve the accuracy and relevance of the obtained feature vectors to fed the classification mechanism.

Entropy Weight Ensemble Framework for Yield Prediction of Winter Wheat Under Different Water Stress Treatments Using Unmanned Aerial Vehicle-Based Multispectral and Thermal Data

Crop breeding programs generally perform early field assessments of candidate selection based on primary traits such as grain yield (GY). The traditional methods of yield assessment are costly, inefficient, and considered a bottleneck in modern precision agriculture. Recent advances in an unmanned aerial vehicle (UAV) and development of sensors have opened a new avenue for data acquisition cost-effectively and rapidly. We evaluated UAV-based multispectral and thermal images for in-season GY prediction using 30 winter wheat genotypes under 3 water treatments. For this, multispectral vegetation indices (VIs) and normalized relative canopy temperature (NRCT) were calculated and selected by the gray relational analysis (GRA) at each growth stage, i.e., jointing, booting, heading, flowering, grain filling, and maturity to reduce the data dimension. The elastic net regression (ENR) was developed by using selected features as input variables for yield prediction, whereas the entropy weight fusion (EWF) method was used to combine the predicted GY values from multiple growth stages. In our results, the fusion of dual-sensor data showed high yield prediction accuracy [coefficient of determination (R ²) = 0.527-0.667] compared to using a single multispectral sensor (R ² = 0.130-0.461). Results showed that the grain filling stage was the optimal stage to predict GY with R ² = 0.667, root mean square error (RMSE) = 0.881 t ha^-1, relative root-mean-square error (RRMSE) = 15.2%, and mean absolute error (MAE) = 0.721 t ha^-1. The EWF model outperformed at all the individual growth stages with R ² varying from 0.677 to 0.729. The best prediction result (R ² = 0.729, RMSE = 0.831 t ha^-1, RRMSE = 14.3%, and MAE = 0.684 t ha^-1) was achieved through combining the predicted values of all growth stages. This study suggests that the fusion of UAV-based multispectral and thermal IR data within an ENR-EWF framework can provide a precise and robust prediction of wheat yield.

Universal Sample Size Invariant Measures for Uncertainty Quantification in Density Estimation

Previously, we developed a high throughput non-parametric maximum entropy method (PLOS ONE, 13(5): e0196937, 2018) that employs a log-likelihood scoring function to characterize uncertainty in trial probability density estimates through a scaled quantile residual (SQR). The SQR for the true probability density has universal sample size invariant properties equivalent to sampled uniform random data (SURD). Alternative scoring functions are considered that include the Anderson-Darling test. Scoring function effectiveness is evaluated using receiver operator characteristics to quantify efficacy in discriminating SURD from decoy-SURD, and by comparing overall performance characteristics during density estimation across a diverse test set of known probability distributions.