Minimum Redundancy Maximum Relevance Research Articles

Genetic Algorithm-based Machine Learning Approach for Epileptic Seizure Identification and Classification

Background: Epileptic Seizure (ES) is a neural disorder that generates an uncontrolled brain signal impulse. The disorder is seen in young children and adults with a positive medical history. Method: In this paper, a novel approach to epileptic seizure detection and prediction is proposed and evaluated. The seizure is retrained from Electroencephalography (EEG) high-dimension datasets. The EEG datasets further segment features of interdependent EEG into a matrix. This matrix is linked to providing a validation occurrence of similar feature events with a minimum redundancy maximum relevance (MRMR) approach for ES feature optimization. Result & Discussion: The uncertainty-based genetic algorithm for parametric evaluation and validation (GAPEr) is used for predictive analysis and decision support via a dedicated neural networking model. The sizer detection and prediction are supported and validated via a series of interactions from trained datasets. Conclusion: The proposed setup has achieved higher accuracy and dependency in decision support of Epileptic Seizure identification and classification based on predictive evaluation.

Automated radiomics model for preoperative pancreatic neuroendocrine tumor grade prediction.

655 Background: Pancreatic neuroendocrine tumors (PNETs) have varying biologic behavior based on factors including tumor grade. Many prognostic factors can only be determined post-pancreatectomy; thus, are unable to guide clinical decision making preoperatively. This is particularly relevant in small, non-functional (NF)-PNETs. Imaging analysis with radiomics may be able to elucidate biologic data such as tumor grade, without the need for tissue sampling. Our study aims to create an automatic pipeline from segmentation to radiomics-signature building to preoperatively predict tumor grade. Methods: Patients that underwent resection between 2003-21 with adequate preoperative arterial phase CT scans were divided into training and validation cohorts. In the training cohort, the pancreas and tumor region were manually segmented and used to train an auto-segmentation model. The validation cohort then underwent automatic segmentation. A total of 255 radiomics features were extracted from the tumor region. Correlated features were removed, and the minimum redundancy maximum relevance (mRMR) method was used to select the final feature set. These features were used to train a Support Vector Machine (SVM)-based classifier through the training cohort to predict grade, which was dichotomized into grade I versus II/III. The radiomic based prediction model was then evaluated in the automatically segmented validation cohort. Results: A total of 186 patients were identified and divided into training (n = 140) and validation (n = 46) cohorts. Median age was 57 (27, 85) and 52% were male. 113 (62%) and 70 (38%) patients were grades I and II/III, respectively. Median tumor size was 24 mm (6, 200) and 43 (26%) patients had positive nodal disease. The auto-segmentation model was able to accurately segment the tumor region in 33 (72%) patients of the validation cohort. In the training cohort (n = 140), the radiomics-signature produced an area under the curve (AUC) of 0.87 (0.81, 0.93). Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 0.94 (0.9, 0.98), 0.74 (0.66, 0.81), 0.72 (0.65, 0.80) and 0.97 (0.94, 1.00) respectively. In the auto-segmented validation cohort (n = 33), the radiomics model produced an AUC of 0.75 (0.61, 0.90). Sensitivity, specificity, PPV and NPV were 0.88 (0.77, 0.99), 0.62 (0.46, 0.79), 0.71 (0.56, 0.87) and 0.83 (0.71, 0.96), respectively. Conclusions: The proposed auto-segmentation model was able to automatically identify tumor regions with a high degree of accuracy. Similarly, the subsequent radiomics-signature was also able to strongly discern PNET grade. This automatic pipeline bypasses manual segmentation and could help incorporate a radiomics-signature into preoperative clinical decision-making for PNETs.

Computed tomography-based absolute delta radiomics nomogram for predicting perineural invasion in hypopharyngeal squamous cell carcinoma.

To assess the efficacy of computed tomography (CT)-based radiomics nomogram in predicting perineural invasion (PNI) in patients with hypopharyngeal squamous cell carcinoma (HPSCC). Overall, 146 patients were retrospectively recruited and divided into training and test cohorts at a 7:3 ratio. Radiomics features were extracted and delta and absolute delta radiomics features were calculated. Feature selection was performed using maximum relevance minimum redundancy and least absolute shrinkage and selection operator methods. Preliminary models were built using logistic regression, and the optimal one was selected as the radiomics signature. A nomogram was constructed by combining independent clinical factors and the radiomics signature. Its performance was evaluated using the area under the curve (AUC) values of receiver operating characteristic curves, decision curve analysis (DCA), and calibration curves. The radiomics signature comprised 14 absolute delta radiomics features. The nomogram, incorporating tumor thickness and radiomics signature, outperformed the other models (AUC=0.79 and 0.78, training and test cohorts, respectively). The Delong test demonstrated that the nomogram's predictive performance was significantly higher than that of the clinical model (p<0.05) in both cohorts. Calibration curves indicated good calibration, and the Hosmer-Lemeshow test confirmed a good fit (p=0.969 and 0.429, training and test cohorts, respectively). DCA highlighted the nomogram's considerable clinical usefulness. The CT-based absolute delta radiomics nomogram can noninvasively and preoperatively predict PNI status in patients with HPSCC, providing a valuable tool for clinical decision making and individualized treatment plans.

Enhancing Prediction of Electron Affinity and Ionization Energy in Liquid Organic Electrolytes for Lithium-Ion Batteries Using Machine Learning

The electron affinity (EA) and ionization energy (IE) of battery electrolyte molecules are pivotal in determining the electrochemical properties of electrode materials, significantly impacting the performance and safety of batteries. In this study, we employed a suite of machine learning algorithms, including linear regression, gradient boosting, CatBoost, XGBoost, and random forest regression, to predict these properties. Our analysis leveraged a comprehensive dataset of 24432 electrolyte molecules extracted from the Joint Center for Energy Storage Research (JCESR) Molecules database, and used RDKit and Mordred tools to generate a series of molecular descriptors. Through meticulous feature engineering and selection using the maximum relevance minimum redundancy (mRMR) algorithm, we identified the most influential molecular features for predicting EA and IE. The CatBoost model emerged as the most accurate, outperforming other models with its ability to handle complex nonlinear relationships and provide robust predictions with lower errors. The model's predictions were further validated through 10-fold cross-validation, demonstrating its generalization capability and resistance to overfitting. The CatBoost model achieved a root mean squared error (RMSE) of 0.239 eV for IE and 0.427 eV for EA, with R-squared (R2) values of 0.944 and 0.879, respectively. SHapley Additive exPlanations (SHAP) value analysis elucidated the contribution of each feature to the model's predictions, highlighting the molecular characteristics that significantly influence EA and IE. Our findings offer valuable insights for the design of novel electrolyte materials with tailored electronic properties, advancing the development of high-performance battery technologies.

Age group classification based on optical measurement of brain pulsation using machine learning

Optical techniques, such as functional near-infrared spectroscopy (fNIRS), contain high potential for the development of non-invasive wearable systems for evaluating cerebral vascular condition in aging, due to their portability and ability to monitor real-time changes in cerebral hemodynamics. In this study, thirty-six healthy adults were measured by single channel fNIRS to explore differences between two age groups using machine learning (ML). The subjects, measured during functional magnetic resonance imaging (fMRI) at Oulu University Hospital, were divided into young (age ≤ 32) and elderly (age ≥ 57) groups. Brain pulses were extracted from fNIRS using a single 830 nm wavelength. Four feature sets were derived from log-normal parameters estimated by pulse decomposition algorithm. ML experiments utilized support vector machines and random forest learners, along with maximum relevance minimum redundancy and principal component analysis for feature selection. Performance with increasing sample size was estimated using learning curve method. The best mean balanced accuracies for each feature set were over 75% (75.9%, 76.4%, 79.3%, 76.9%), indicating the pulse features containing age related information. Learning curves indicated stable classification performance with increasing sample size. The results demonstrate the potential of using single channel fNIRS in the analysis of aging.

An Intelligent Prediction Model for the Synthesis Conditions of Metal-Organic Frameworks Utilizing Artificial Neural Networks Enhanced by Genetic Algorithm Optimization.

In the field of emerging materials, metal-organic frameworks (MOFs) have gained prominence due to their unique porous structures, showing versatility in gas adsorption, storage, separation, and liquid processes. However, their decomposition, collapse tendencies, and complex synthesis make large-scale production costly and challenging with no accurate method for predicting synthesis conditions. This work proposes an intelligent prediction model based on the structural characteristics of MOFs to forecast synthesis conditions. A genetic algorithm-optimized back-propagation (BP) neural network was developed, starting with feature selection via the minimum redundancy maximum relevance algorithm to rank feature importance. The optimal number of inputs and outputs was determined on the basis of performance, followed by genetic algorithm optimization of the BP neural network. The best initial population size and number of hidden nodes were identified. The study compared 10 models, including a genetic algorithm-optimized BP neural network and a simple BP neural network. The results revealed that the R coefficient of the optimized model reached 96.2%, surpassing that of conventional methods with all R values of approximately 85%. This approach allows for accurate prediction of MOF synthesis conditions, aiding material manufacturing in precise control over synthesis processes, improving material quality, and reducing raw material waste.

A predictive clinical-radiomics nomogram for early diagnosis of mesenteric arterial embolism based on non-contrast CT and biomarkers.

Mesenteric artery embolism (MAE) is a relatively uncommon abdominal surgical emergency, but it can lead to catastrophic clinical outcomes if the diagnosis is delayed. This study aims to build a prediction model of clinical-radiomics nomogram for early diagnosis of MAE based on non-contrast computed tomography (CT) and biomarkers. In this retrospective study, a total of 364 patients confirmed as MAE (n = 131) or non-MAE (n = 233) who were randomly divided into a training cohort (70%) and a validation cohort (30%). In the training cohort, the minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) algorithms were used to select optimal radiomics features from non-contrast CT images for calculating Radscore which was utilized to establish the radiomics model. Logistic regression analysis was performed to screen clinical factors, and then generate the clinical model. A predictive nomogram model was built using Radscore and the selected clinical risk factors, which was evaluated through the receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA). Thirteen radiomics features were chosen to calculate Radscore. Age, white blood cell (WBC) count, creatine kinase (CK) and D-dimer were determined as the independent clinical factors. The clinical-radiomics nomogram model showed the best performance in training cohort. The nomogram model was with higher area under curve (AUC) value of 0.93, compared to radiomics model with AUC value of 0.90 or clinical model with AUC value of 0.78 in the validation cohort. The calibration curve showed that nomogram model achieved a good fit in both cohorts (P = 0.59 and 0.92, respectively). The DCA indicated that nomogram model was significantly favorable for clinical usefulness of MAE diagnosis. The nomogram provides an effective tool for the early diagnosis of MAE, which may play a crucial role in shortening the time for therapeutic decision-making, thereby reducing the risk of intestinal necrosis and death.

Detection of Acromion Types in Shoulder Magnetic Resonance Image Examination with Developed Convolutional Neural Network and Textural-Based Content-Based Image Retrieval System.

Background: The morphological type of the acromion may play a role in the etiopathogenesis of various pathologies, such as shoulder impingement syndrome and rotator cuff disorders. Therefore, it is important to determine the acromion's morphological types accurately and quickly. In this study, it was aimed to detect the acromion shape, which is one of the etiological causes of chronic shoulder disorders that may cause a decrease in work capacity and quality of life, on shoulder MR images by developing a new model for image retrieval in Content-Based Image Retrieval (CBIR) systems. Methods: Image retrieval was performed in CBIR systems using Convolutional Neural Network (CNN) architectures and textural-based methods as the basis. Feature maps of the images were extracted to measure image similarities in the developed CBIR system. For feature map extraction, feature extraction was performed with Histogram of Gradient (HOG), Local Binary Pattern (LBP), Darknet53, and Densenet201 architectures, and the Minimum Redundancy Maximum Relevance (mRMR) feature selection method was used for feature selection. The feature maps obtained after the dimensionality reduction process were combined. The Euclidean distance and Peak Signal-to-Noise Ratio (PSNR) were used as similarity measurement methods. Image retrieval was performed using features obtained from CNN architectures and textural-based models to compare the performance of the proposed method. Results: The highest Average Precision (AP) value was reached in the PSNR similarity measurement method with 0.76 in the proposed model. Conclusions: The proposed model is promising for accurately and rapidly determining morphological types of the acromion, thus aiding in the diagnosis and understanding of chronic shoulder disorders.

Feature optimized hybrid model for prediction of myocardial infarction

Background Cardiovascular disease is rampant worldwide and has become the leading factor in increasing the global mortality rates. According to the World Heart Federation, death toll due to CVD has increased from 12.1 million in 1990 to around 19 million in 2019. Myocardial Infarction (MI) is a condition where the heart muscle dies due to reduced or inhibited flow of oxygenated blood. It has affected approximately 3 million people worldwide, with more than 1 million deaths in the United States annually. Such unusual proliferation in global death toll due to CVD can be reduced to a great extent by predicting the risk of CVD at an early stage. Method In this paper, several feature selection techniques including Variance-based, Mutual Information (MI), Maximum Relevance Minimum Redundancy (MRMR), Boruta, and Recursive Feature Elimination (RFE) algorithms are used feature optimization. For class prediction, the Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Adaboost algorithms were implemented in their ordinary, One-vs-Rest (OVR) and One-vs-One (OVO) methods. Result The performance of Adaboost model has significantly improved by using feature selection techniques, that is, the accuracy of 74% (without any feature selection taking 5.3 seconds) is increased to 85% (with Boruta feature selection taking only 2.17 seconds training time) and 88% (with MRMR feature selection taking 1.6 seconds training time). Similarly, the DT-OVO model’s performance has improved from 84% (without any feature selection taking 1.48 seconds training time) to 86% (with Boruta feature selection taking 0.58 training time). For other models, the performance is maintained with reduced model training times. Conclusion This research paper prioritizes on feature selection in developing machine learning models for CVD prediction. This conclusion is justified by demonstrating the significant reduction in model training times for the 72 models generated while maintaining or even improving the model’s predictive performance.

Application of Developing Artificial Intelligence (AI) Techniques to Model Pan Evaporation Trends in Slovak River Sub-Basins

The modeling of pan evaporation (Ep) trends in Slovak river sub-basins was conducted using advanced artificial intelligence (AI) techniques algorithms to accurately calculate evaporation rates based on daily climate data from 2010 to 2023 across eight sub-basins in the Slovak Republic. The AI modeling results reveal that the Bodrog, Hornád, Ipeľ, Morava, Slaná, and Váh river basins are experiencing increases in evaporation, while the Dunaj and Hron rivers show declining trends. This divergence may indicate varying ecological factors influencing the evaporation dynamics of each river. A comprehensive set of 28 machine learning (ML) and deep learning (DL) models was employed, including ML techniques such as linear regression, tree-based, support vector machines (both with and without kernels), ensemble, and Gaussian process methods; as well as DL approaches like neural networks (narrow, medium, wide, bilayered, and trilayered). Among these, stepwise linear regression provided the most optimal fit. The minimum redundancy maximum relevance (mRMR) method was utilized for feature selection to balance relevance and redundancy effectively. The results suggest that emphasizing relative humidity (RH) and minimum temperature (tmin) significantly enhances accuracy, highlighting the critical roles of these factors in modeling pan evaporation trends. The results offer precise evaporation analyses to improve water management and lessen scarcity.

Detection of Woody Breast Condition in Broiler Breast Fillets Using Light Scattering Imaging

HighlightsBroadband light scattering images were acquired from broiler breast fillets affected with woody breast (WB).Both deep-learning-based and hand-crafted features were extracted from scattering images for model development.The hand-crafted scattering image features performed better in differentiating normal from WB-affected samples.An overall accuracy of 92.3% was achieved by the model based on selected hand-crafted scattering features.Abstract. Muscular myopathies such as woody or wooden breast, which impair the eating quality and marketability of poultry products, are threatening the profitability of poultry industries worldwide, with an estimated annual loss exceeding $500 million for the United States (U.S.) poultry industry. WB-affected fillets are characterized by abnormal tissue hardness and muscle rigidity with varying degrees of severity. The assessment of WB conditions at processing facilities currently relies on tactile palpation combined with a visual examination by trained personnel. This approach is subjective, labor-intensive, costly, and may induce contamination due to physical contact. Optical imaging technology offers a promising alternative for objective and non-invasive quality assessment of broiler meat. This study presents a novel investigation of light scattering imaging (LSI) that captures light-scattering characteristics of meat tissues for the detection of WB conditions in broiler breast fillets. Broadband scattering images, induced under the illumination of a highly focused broadband light beam, were acquired from broiler meat samples. Two types of image features, i.e., (1) deep-learning-based and (2) hand-crafted scattering features, were extracted for building classification models using regularized linear discriminant analysis to differentiate samples into two categories, i.e., “Normal” (no WB) and “Defective” (WB-affected). Deep-learning-based features yielded an overall classification accuracy of 80.4%, while an accuracy of 91.7% was obtained by hand-crafted scattering features, representing a significant improvement of 11.3% (P &amp;lt; 0.01). Furthermore, feature reduction approaches, including MRMR (minimum redundancy maximum relevance) and PCA (principal component analysis), were conducted to reduce the model complexity, leading to a further accuracy improvement to 92.3% with the top-ranked 65 features identified by MRMR and 25 principal components (PCs), respectively. This study has demonstrated the LSI technique is promising for WB assessment of broiler breast meat. Keywords: Light scattering, Machine learning, Optical imaging, Poultry, Woody breast.

Fluid volume status detection model for patients with heart failure based on machine learning methods.

Fluid volume abnormalities are a major cause of exacerbations in heart failure patients. However, there is few efficient, rapid, or cost-effective clinical approach for determining volume status, resulting in inadequate or unsatisfactory treatment. The aim was to develop an early fluid volume detection model for heart failure patients utilizing a machine learning stratification. The training set data collected by Tianjin Chest Hospital on heart failure patients from December 2016 to December 2021, included 2056 samples and 97 medical characteristics. The minimum Redundancy Maximum Relevance(mRMR) feature selection method was utilized to filter features that were strongly related to the patient's fluid volume status. Four machine learning classification models were used to predict patients' fluid volume status, and their effectiveness was measured using the receiver operating characteristic (ROC) area under the curve (AUC), calibration curve, accuracy, precision, recall, F1 score, specificity, and sensitivity. Data from 186 heart failure patients collected between January 2022 and July 2022 were employed as an external validation set to investigate the effects of model training. SHapley Additive exPlanations (SHAP) were used to interpret the ML models. Thirty features were selected for model development, and the area under the ROC curve AUC (95% CI) for the four machine learning models in the testing set was 0.75 (0.73-0.77), 0.77 (0.74-0.79), 0.70 (0.67-0.73), and 0.76 (0.73-0.78), and the AUC (95% CI) in the external validation set was 0.74 (0.71-0.76), 0.70 (0.67-0.73), 0.64 (0.59-0.68), and 0.67 (0.63-0.71). Logistic regression models were globally interpreted using SHAP-based summary plots. Machine learning methods are effective in detecting fluid volume status in heart failure patients and can assist physicians with assisted diagnosis, thus helping clinicians to tailor precise management.

Dynamic Prediction of Physical Exertion: Leveraging AI Models and Wearable Sensor Data During Cycling Exercise.

Background/Objectives: This study aimed to explore machine learning approaches for predicting physical exertion using physiological signals collected from wearable devices. Methods: Both traditional machine learning and deep learning methods for classification and regression were assessed. The research involved 27 healthy participants engaged in controlled cycling exercises. Physiological data, including ECG, heart rate, oxygen saturation, and pedal speed (RPM), were collected during these sessions, which were divided into eight two-minute segments. Heart rate variability (HRV) was also calculated to serve as a predictive indicator. We employed two feature selection algorithms to identify the most relevant features for model training: Minimum Redundancy Maximum Relevance (MRMR) for both classification and regression, and Univariate Feature Ranking for Classification. A total of 34 traditional models were developed using MATLAB's Classification Learner App, utilizing 20% of the data for testing. In addition, Long Short-Term Memory (LSTM) networks were trained on the top features selected by the MRMR and Univariate Feature Ranking algorithms to enhance model performance. Finally, the MRMR-selected features were used for regression to train the LSTM model for predicting continuous outcomes. Results: The LSTM model for regression demonstrated robust predictive capabilities, achieving a mean squared error (MSE) of 0.8493 and an R-squared value of 0.7757. The classification models also showed promising results, with the highest testing accuracy reaching 89.2% and an F1 score of 91.7%. Conclusions: These results underscore the effectiveness of combining feature selection algorithms with advanced machine learning (ML) and deep learning techniques for predicting physical exertion levels using wearable sensor data.

Rocking Spectrum for Cylindrical Structures Subjected to Bidirectional Pulse‐Like Ground Motions

ABSTRACTIn recent years, cylindrical structures free to rock have been exploited in practical engineering. However, their seismic response in three dimensions (3D), greatly sensitive to the parameters that define it, is difficult and time‐consuming to predict. To this end, this study focuses on developing a rocking spectrum, an efficient graphical tool linking seismic rocking response to structural parameters, for seismic response prediction and performance‐based seismic design of cylindrical structures. The development of the rocking spectrum is based on the numerical rocking response of 2500 idealized rigid cylinders excited by 100 sets of synthetic bidirectional pulse‐like ground motions. The minimum Redundancy Maximum Relevance (mRMR) algorithm is first employed to reveal that the rocking response is more related to ground acceleration, ground velocity, and ground displacement when the response is small (close to uplift), intermediate, and large (close to overturning), respectively. Following these relations, the support vector machine (SVM) algorithm is employed to develop the rocking spectrum. The obtained rocking spectrum can reliably predict the rocking response of cylinders subjected to the synthetic pulse‐like ground motions. The applicability of the spectrum is also discussed for as‐recorded pulse‐like ground motions.

Development and validation of a radiomics-based nomogram for predicting pathological grade of upper urinary tract urothelial carcinoma

BackgroundUpper urinary tract urothelial carcinoma (UTUC) is a rare and highly aggressive malignancy characterized by poor prognosis, making the accurate identification of high-grade (HG) UTUC essential for subsequent treatment strategies. This study aims to develop and validate a nomogram model using computed tomography urography (CTU) images to predict HG UTUC.MethodsA retrospective cohort study was conducted to include patients with UTUC who underwent radical nephroureterectomy and received a CTU examination prior to surgery. In the CTU images, tumor lesions located in the renal calyces, renal pelvis and ureter were segmented, and radiomics features from the unenhanced, medullary, and excretory phases were extracted. The maximum relevance minimum redundancy algorithm, least absolute shrinkage and selection operator, and various machine learning (ML) algorithms—including random forest, support vector machine, and eXtreme gradient boosting—were employed to select radiomics features and calculate radiomics scores. Logistic regression (LR) analysis was performed to identify the independent influencing factors of clinical baseline characteristics. Multiple datasets of radiomics features were constructed by integrating single-phase radiomics features with the most significant independent factor. Both LR and ML algorithms were utilized to develop predictive models. The area under the receiver operating characteristic curve (AUC values), accuracy, sensitivity, and specificity were assessed for model performance evaluation. Decision curve analysis was conducted to evaluate the clinical net benefits.ResultsA total of 167 patients were enrolled in this study. Among them, 56 were diagnosed with low-grade UTUC (including papillary urothelial neoplasms with low malignant potential and low-grade urothelial carcinoma) as confirmed by postoperative pathological examination results, and 111 were of HG. These patients were randomly allocated to the training set and the validation set at a ratio of 7:3. The training set comprised 116 patients with a mean age of 63.5 ± 9.38 years and 38 males. The validation set comprised 51 patients with a mean age of 65.6 ± 11.1 years and 18 males. Hydronephrosis was identified as the most significant independent factor in the clinical baseline features. Models that include mixed-phase development achieve better performance compared to models that rely simply on single-phase development. The nomogram model had excellent predictive ability for HG UTUC, with AUC values of 0.844 and an accuracy of 0.793 in the validation sets. The nomogram model can enhance accuracy by 14.1% (79.3% vs. 65.2%) and sensitivity by 32.8% (93.2% vs. 60.4%) compared to urinary cytology.ConclusionsThis study developed a nomogram model, which significantly improved the diagnostic ability for HG UTUC compared to urinary cytology. Furthermore, the results of the decision curve analysis showed that the model had a net benefit and could provide a non-invasive and potentially diagnostic reference tool for HG UTUC.

A Mutual Information Based Multifeature Pattern Recognition Criterion for Identification and Optimization of Thermally Safe Operating Conditions for Single Diffusion‐Controlled Reactions Occurring in Isoperibolic Liquid–Liquid Semibatch Reactors

ABSTRACTPrevention of thermal runaway and establishment of safe‐economic operating conditions are crucial for the practical operation of single diffusion‐controlled liquid–liquid reactions occurring in isoperibolic semibatch reactors. Hence, in this study, a mutual information‐based multiple feature recognition criterion (MI‐MFR) was innovatively proposed, for which the maximum relevance minimum redundancy approach was introduced in feature screening; in combination with the support vector machine algorithm, various thermal behaviors can be effectively recognized. On this basis, a series of boundary diagrams were established accordingly, the impact of the variation in model parameters on which was systematically explored. Subsequently, an improved generalized thermal safety region was developed by introducing the upper thresholds in normal and cooling failure scenarios. Meanwhile, the robustness and progressiveness of the established MI‐MFR criterion were confirmed by comparison with other conventional criteria. Finally, MI‐MFR‐based procedures were constructed to identify thermal behaviors and optimize safe‐economic operating conditions in practices, based on which the optimum operating conditions of toluene mononitration were obtained.

Prediction of arsenic (III) adsorption from aqueous solution using non-neural network algorithms

Heavy metals such as arsenic can be effectively removed through adsorption. Through material property evaluation and adsorption parameter optimization, machine learning (ML) modeling provides an alternative to lengthy laboratory experimentation. In this work, adsorption data from an earlier study employing a waste-material composite were used. To create prediction models, four non-neural network algorithms - support vector machines (SVM), Gaussian process regression (GPR), linear regression, and ensemble approaches - were used and contrasted with neural network algorithms. Nine predictors were utilized, ranging from adsorbent composition alterations to experimental circumstances. Using principal component analysis (PCA) and feature selection, together with the F-test and minimum redundancy maximum relevance (MRMR) algorithms for feature reduction, optimization was accomplished. With an R-squared of 0.939, mean absolute error (MAE) of 5.778, and root mean squared error (RMSE) of 7.119 for training and an R-squared of 0.942, MAE of 5.450, and RMSE of 6.870 for testing, the optimized GPR method offered the best predictive performance. The best R-squared values found for other algorithms were: SVM (0.922), linear regression (0.925), and ensemble (0.927). The most important variables influencing adsorption efficiency were initial arsenic concentration, time, and the iron salt content. Local interpretable model-agnostic explanations (LIME), partial dependence plot (PDP), and Shapley additive explanations (SHAP) plots were used to explain these results. This work shows that, based on model-derived parameters, non-neural network algorithms may efficiently simulate and optimize arsenic adsorption tests, providing a trustworthy substitute for neural network techniques and markedly increasing adsorption efficiency.

Enhanced Sequence-to-Sequence Attention-Based PM2.5 Concentration Forecasting Using Spatiotemporal Data

Severe air pollution problems continue to increase because of accelerated industrialization and urbanization. Specifically, fine particulate matter (PM2.5) causes respiratory and cardiovascular diseases, and according to the World Health Organization (WHO), millions of premature deaths and significant health burdens annually. Therefore, PM2.5 concentration forecasting is essential. This study proposed a method to forecast PM2.5 concentrations one hour after using Sequence-to-Sequence Attention (Seq2Seq-attention). The proposed method selects neighboring stations using minimum redundancy maximum relevance (mRMR) and integrates their data using a convolutional neural network (CNN). The proposed attention score and Seq2Seq are used on the integrated data to forecast PM2.5 concentration after one hour. The performance of the proposed method is validated through two case studies. The first comparison evaluated the performance of the conventional attention score against the proposed attention scores. The second comparison evaluated the forecasting results with and without considering neighboring stations. The first study showed that the proposed attention score improved the performance index (Root Mean Square Error (RMSE): 3.48%p, Mean Absolute Error (MAE): 8.60%p, R2: 0.49%p, relative Root Mean Square Error (rRMSE): 3.64%p, Percent Bias (PBIAS): 59.29%p). The second case study showed that considering neighboring stations’ data can be more effective in forecasting than considering that of a standalone station (RMSE: 5.49%p, MAE: 0.51%p, R2: 0.67%p, rRMSE: 5.44%p, PBIAS: 46.56%p). This confirmed that the proposed method can effectively forecast the PM2.5 concentration after one hour.

Robust audio copy-move detection and localisation based on Smoothed Pseudo Wigner-Ville Distribution and adaptive processing

Audio Copy-Move forgery is a copy and paste operation within the same audio source that alters the original audio content in order to deceive or mislead listeners. Existing audio copy-move forgery detection algorithms show good robustness against audio that has undergone a single post-processing (noise addition, compression, median filtering, etc.), but perform poorly in detecting copy-move that have undergone a mixed post-processing attack, where multiple post-processes are present in the audio simultaneously. To overcome this problem, we propose a new adaptive processing method based on Variational Modal Decomposition and Minimum Redundancy Maximum Relevance. First, the forged audio is decomposed into multiple Intrinsic Mode Functions located in different frequency domains. Scores are then computed based on correlation and redundancy. The calculated scores are used as weights and reconstructed by weighting to obtain the final audio signal. Through feature selection and weighted reconstruction, the new audio signal is provided with adaptive attributes. We chose the Smoothed Pseudo Wigner-Weil Distribution as the feature for performing the final copy-move detection. For the experimental part, we created hybrid post-processing datasets and applied adaptive processing to existing representative copy-move detection methods, all of which have improved detection results. Finally, we tested the robustness of the proposed method and the performance is optimal in comparison with other methods. The experimental results show that the proposed method is robust to both single and hybrid post-processing attacks.

Enhanced Intrusion Detection in Software-Defined Networking using Advanced Feature Selection: The EMRMR Approach

Most traditional IP networks face serious security and management challenges due to their rapid increase in complexity. SDN resolves these issues by the separation of control and data planes, hence enabling programmability for centralized management with flexibility. On the other hand, its centralized architecture makes SDN very prone to DDoS attacks, hence necessitating the use of advanced and efficient IDSs. This study focuses on improving IDS performance in SDN environments through the integration of deep learning techniques and novel feature selection methods. This study presents an Enhanced Maximum Relevance Minimum Redundancy (EMRMR) approach that incorporates a Mutual Information Feature Selection (MIFS) strategy and a new Contextual Redundancy Coefficient Upweighting (CRCU) strategy to optimize feature selection for early attack detection. Experiments on the inSDN dataset showed that EMRMR achieved better precision, recall, F1-score, and accuracy compared to the state-of-the-art approaches, especially when fewer features are selected. These results highlight the efficiency of the proposed EMRMR approach in the selection of relevant features with minimal computational overhead, which enhances the real-time capability for IDS in SDN environments.