Mutual Information Method Research Articles

The Parameter Optimization of Support Vector Machine with Genetic Algorithm in Risk Early Warning Models

Machine Learning algorithms are widely used by lenders in risk early warning models. With Machine Learning, the risk levels of individual and corporate customers are determined at the account and customer level. Lenders want to manage risk by evaluating the payment performance of customer or account with the help of Machine Learning algorithms. Banks, which have an important place among lenders, develop risk early warning models with the help of learning algorithms using customer information. In the development process of risk early warning models, while banks generally use customer information and credit bureau information for the individual segment, they use financial, non-financial and behaviour-based information for the corporate segment. In this study, it is planned to develop a risk early model for customers in corporate service segment. For the customers of corporate service segment, Balance Sheet and Income Statement items were used and the financial ratios were calculated for risk early warning models. In the development of risk early warning models, Mutual Information method was used as a novel feature selection approach and Support Vector Machine method (linear function, radial basis function and sigmoid function) was used as a supervised learning approach. By changing the neighbourhood metric (k), important patterns were discovered with the Mutual Information method in feature selection process. The optimal C and gamma parameters for Support Vector Machine models have been tried to be determined with the Genetic Algorithm, which is among the Meta-Heuristic algorithms. In order to find the optimal metrics in this study, the metric values for all parameters of the SVM model (function specific) have been kept quite wide. In this dataset of corporate service customers, the small neighbourhood metric has been found to have a significant impact on model learning and performance.

A proposed technique for predicting heart disease using machine learning algorithms and an explainable AI method

One of the critical issues in medical data analysis is accurately predicting a patient’s risk of heart disease, which is vital for early intervention and reducing mortality rates. Early detection allows for timely treatment and continuous monitoring by healthcare providers, which is essential but often limited by the inability of medical professionals to provide constant patient supervision. Early detection of cardiac problems and continuous patient monitoring by physicians can help reduce death rates. Doctors cannot constantly have contact with patients, and heart disease detection is not always accurate. By offering a more solid foundation for prediction and decision-making based on data provided by healthcare sectors worldwide, machine learning (ML) could help physicians with the prediction and detection of HD. This study aims to use different feature selection strategies to produce an accurate ML algorithm for early heart disease prediction. We have chosen features using chi-square, ANOVA, and mutual information methods. The three feature groups chosen were SF-1, SF-2, and SF-3. The study employed ten machine learning algorithms to determine the most accurate technique and feature subset fit. The classification algorithms used include support vector machines (SVM), XGBoost, bagging, decision trees (DT), and random forests (RF). We evaluated the proposed heart disease prediction technique using a private dataset, a public dataset, and different cross-validation methods. We used the Synthetic Minority Oversampling Technique (SMOTE) to eliminate inconsistent data and discover the machine learning algorithm that achieves the most accurate heart disease predictions. Healthcare providers might identify early-stage heart disease quickly and cheaply with the proposed method. We have used the most effective ML algorithm to create a mobile app that instantly predicts heart disease based on the input symptoms. The experimental results demonstrated that the XGBoost algorithm performed optimally when applied to the combined datasets and the SF-2 feature subset. It had 97.57% accuracy, 96.61% sensitivity, 90.48% specificity, 95.00% precision, a 92.68% F1 score, and a 98% AUC. We have developed an explainable AI method based on SHAP approaches to understand how the system makes its final predictions.

Prediction on seismic performance levels of reinforced concrete beams by considering crack development

The plastic rotation angle or deflection is typically used as the indicator to evaluate the earthquake-induced damage and classify the seismic performance levels of reinforced concrete (RC) beams. Herein, one of the most important issues is to determine the seismic performance level limits of RC beams. Whereas, different countries provided their specific method to determine the limit values by considering the loading-carrying capacity of RC beams, which could not be used to describe the earthquake-induced seepage of structures, especially for underground structures. Therefore, in this study, the seismic performance level limits of RC beams were predicted by using the machine learning methods and considering the development of cracks. Firstly, the seismic performance level limits of RC beams were presented after discussing the methods in different codes and the development of cracks. Then an earthquake performance test database of RC beams was established after collecting 452 test results of RC beams, and Pearson correlation analysis was conducted for feature selection to determine the input mechanical parameters and dimensional parameters for machine learning. Meanwhile, the correlation between the inputs and limit values was analyzed using the mutual information method. Regression models of seven machine learning methods were then established to predict the performance level limits of RC beams, and the hyperparameters of the machine learning models were optimized with the TPE optimization algorithm and cross-validation. The generalization ability of the prediction models was evaluated and the accuracy of predicted results by different methods was analyzed. Finally, the predicted seismic performance level limits of RC beams could be used to evaluate the earthquake-induced damage of RC beams by combining them with the seismic behavior of RC beams.

SmartScanPCOS: A feature-driven approach to cutting-edge prediction of Polycystic Ovary Syndrome using Machine Learning and Explainable Artificial Intelligence

PolyCystic Ovarian Syndrome (PCOS) poses significant challenges to women's reproductive health due to its diagnostic complexity arising from a variety of symptoms, including hirsutism, anovulation, pain, obesity, hyperandrogenism, and oligomenorrhea, necessitating multiple clinical tests. Leveraging Artificial Intelligence (AI) in healthcare offers several benefits that can significantly impact patient care, streamline operations, and improve medical outcomes overall. This study presents an Explainable Artificial Intelligence (XAI)-driven PCOS smart predictor, structured as a hierarchical ensemble consisting of two tiers of Random Forest classifiers following extensive analysis of seven conventional classifiers and two additional stacking ensemble classifiers. An open-source data set comprising numerical parametric features linked to PCOS for classifier training was used. Moreover, to identify essential features for PCOS prediction three feature selection methods: Threshold-driven Optimized Principal Component Analysis (TOPCA), Optimized Salp Swarm (OSSM), and Threshold-driven Optimized Mutual Information Method (TOMIM) were fine-tuned through thresholding and improvisation to detect diverse attribute sets with varying numbers and combinations. Notably, the two-level Random Forest classifier model outperformed others with a remarkable 99.31 % accuracy by employing the top 17 features selected through the Threshold-driven Optimized Mutual Information Method (TOMIM) along with anoverallaccuracy of 99.32 % with 8 fold cross validation for 25 runs. The Smart predictor, constructed using Shapash - a Python library for Explainable Artificial Intelligence - was utilized to deploy the two-level Random Forest classifier model. Ensuring transparency and result reliability, visualizations from robust Explainable AI libraries were employed at different prediction stages for all considered classifiers in this study.

Prediction of typical gas components in cigarette smoke based on transformer

Abstract Harm reduction of cigarette products has become one of the primary objectives of the entire tobacco industry. The prediction of typical gas components (TGC) and dynamic adjustment of process parameters are crucial for cigarette coke reduction and harm reduction. In this study, a deep learning (DL)-assisted TGC prediction framework is proposed to predict CO and NI simultaneously. Firstly, a large number of experimental and simulation parameters of cigarette process are collected as the data base for subsequent model construction. Then, the feature importance analysis of the process parameters was carried out by combining the mechanism of the combustion process through the mutual information method. Finally, DL models based on Multilayer Perceptron, One-Dimension Convolutional Neural Network and Transformer (TF) was developed as data-driven surrogate models to establish the mapping relationship between process parameters and TGC. The results show that TF model generalizes best and can predict TGC quickly and accurately with R2 over 0.99. This work will provide a valuable predictive and decision-making tool for cigarette harm reduction.

The time lag in local field potential signals for the development of its Bayesian belief network

PurposeThe objective is to suggest time as an important variable to consider in the network model, specifically when discussing causality.MethodsThere is a consideration of the context of functional connectivity because of the time importance of observing the feature inside the neuroscience context. A network model was constructed using the Bayesian network method, utilizing a dataset consisting of three rats’ local field potentials. The model took into consideration the time delay of communication among brain areas, as recorded in this study. In pursuit of this objective, the delayed mutual information method was employed to ascertain the temporal delay between local field potentials and K2 score for the purpose of model comparison.ResultsBayesian network depicted the probabilistic relationship among rat’s brain areas. Delayed mutual information captured the lag among brain areas, and after its appliance on the Bayesian network model, posed better results.ConclusionThe primary novelty of this research lies in its integration of minor delays within the Bayesian network approach, accomplished through the utilization of the delayed mutual information technique prior to its implementation. The suggested methodology incorporates an essential feature that supports the analysis of functional connectivity among brain areas, thereby providing support for the dynamics of neurophysiology.

Reconstructing and assessing global maritime transport network: based on the Port Cargo Composite Transport index

ABSTRACT Solution to the problem of limited explanatory power of transport economics due to the homogenisation of existing the Global Maritime Transport Network (GMTN) construction indicators. By integrating the Port Cargo Composite Transport (PCCT) index and considering the volume-value mismatch relationship and the type and flow of cargo transported in ports, the GMTN can be reconstructed through a bottom-up logic. Combining the complex network, natural breaks, and point mutual information method with the Leiden and PageRank algorithm, the characteristics of the GMTN were derived from three aspects, i.e. network topology, node characteristics, and inter-node dependency. The GMTN presents the characteristics as follows. Community division presents typical geographical aggregation and industrial complementarity. Node characteristics show the classic phenomenon of rich people’s clubs, with obvious heavy-tailed distribution. Maritime transport linkage preferences present a phenomenon of geographical proximity, and their expansion can clarify the direction of the main links. Enhancing their maritime links will be more targeted to support the transport of trade cargoes. These findings help us to understand the characteristics of the international maritime trade pattern, and provide decision references for industry stakeholders to provide a strategic layout of maritime transport.

A comparative analysis of mutual information methods for pairwise relationship detection in metagenomic data

BackgroundConstruction of co-occurrence networks in metagenomic data often employs correlation to infer pairwise relationships between microbes. However, biological systems are complex and often display qualities non-linear in nature. Therefore, the reliance on correlation alone may overlook important relationships and fail to capture the full breadth of intricacies presented in underlying interaction networks. It is of interest to incorporate metrics that are not only robust in detecting linear relationships, but non-linear ones as well.ResultsIn this paper, we explore the use of various mutual information (MI) estimation approaches for quantifying pairwise relationships in biological data and compare their performances against two traditional measures–Pearson’s correlation coefficient, r, and Spearman’s rank correlation coefficient, ρ. Metrics are tested on both simulated data designed to mimic pairwise relationships that may be found in ecological systems and real data from a previous study on C. diff infection. The results demonstrate that, in the case of asymmetric relationships, mutual information estimators can provide better detection ability than Pearson’s or Spearman’s correlation coefficients. Specifically, we find that these estimators have elevated performances in the detection of exploitative relationships, demonstrating the potential benefit of including them in future metagenomic studies.ConclusionsMutual information (MI) can uncover complex pairwise relationships in biological data that may be missed by traditional measures of association. The inclusion of such relationships when constructing co-occurrence networks can result in a more comprehensive analysis than the use of correlation alone.

A new approximate belief mutual information derived from the developed fuzzy mutual information considering belief negation

The Dempster combination rule relies on fundamental assumption that evidences are mutually independent. However, this idealized prerequisite is frequently challenging to fulfill in real-world scenarios. How to measure belief mutual information to investigate dependence among evidence sources is a critical and significant issue. Inspired by fuzzy mutual information based on D–S evidence theory, a method of approximate belief mutual information (BMI) is developed to partially represent the dependence among the sources of evidence. In the BMI model, an interval correlation method considering the basic probability assignment (BPA) and its negation are proposed. Several examples are used to illustrate the availability of the BMI, which shows the developed BMI has better fault tolerance. Finally, the proposed method obtains higher recognition accuracy in pattern recognition tasks. The proposed method can maintain stable and reliable recognition results even when the data is disturbed, verifying the effectiveness of the proposed method.

Estimation of complete mutual information exploiting nonlinear magnitude-phase dependence: Application to spatial FNC for complex-valued fMRI data

BackgroundReal-valued mutual information (MI) has been used in spatial functional network connectivity (FNC) to measure high-order and nonlinear dependence between spatial maps extracted from magnitude-only functional magnetic resonance imaging (fMRI). However, real-valued MI cannot fully capture the group differences in spatial FNC from complex-valued fMRI data with magnitude and phase dependence. MethodsWe propose a complete complex-valued MI method according to the chain rule of MI. We fully exploit the dependence among magnitudes and phases of two complex-valued signals using second and fourth-order joint entropies, and propose to use a Gaussian copula transformation with a lower bound property to avoid inaccurate estimation of joint probability density function when computing the joint entropies. ResultsThe proposed method achieves more accurate MI estimates than the two histogram-based (normal and symbolic approaches) and kernel density estimation methods for simulated signals, and enhances group differences in spatial functional network connectivity for experimental complex-valued fMRI data. Comparison with existing methodsCompared with the simplified complex-valued MI and real-valued MI, the proposed method yields higher MI estimation accuracy, leading to 17.4 % and 145.5 % wider MI ranges, and more significant connectivity differences between healthy controls and schizophrenia patients. A unique connection between executive control network (EC) and right frontal parietal areas, and three additional connections mainly related to EC are detected than the simplified complex-valued MI. ConclusionsWith capability in quantifying MI fully and accurately, the proposed complex-valued MI is promising in providing qualified FNC biomarkers for identifying mental disorders such as schizophrenia.

Influence of Time-Lag Effects between Winter-Wheat Canopy Temperature and Atmospheric Temperature on the Accuracy of CWSI Inversion of Photosynthetic Parameters.

When calculating the CWSI, previous researchers usually used canopy temperature and atmospheric temperature at the same time. However, it takes some time for the canopy temperature (Tc) to respond to atmospheric temperature (Ta), suggesting the time-lag effects between Ta and Tc. In order to investigate time-lag effects between Ta and Tc on the accuracy of the CWSI inversion of photosynthetic parameters in winter wheat, we conducted an experiment. In this study, four moisture treatments were set up: T1 (95% of field water holding capacity), T2 (80% of field water holding capacity), T3 (65% of field water holding capacity), and T4 (50% of field water holding capacity). We quantified the time-lag parameter in winter wheat using time-lag peak-seeking, time-lag cross-correlation, time-lag mutual information, and gray time-lag correlation analysis. Based on the time-lag parameter, we modified the CWSI theoretical and empirical models and assessed the impact of time-lag effects on the accuracy of the CWSI inversion of photosynthesis parameters. Finally, we applied several machine learning algorithms to predict the daily variation in the CWSI after time-lag correction. The results show that: (1) The time-lag parameter calculated using time-lag peak-seeking, time-lag cross-correlation, time-lag mutual information, and gray time-lag correlation analysis are 44-70, 32-44, 42-58, and 76-97 min, respectively. (2) The CWSI empirical model corrected by the time-lag mutual information method has the highest correlation with photosynthetic parameters. (3) GA-SVM has the highest prediction accuracy for the CWSI empirical model corrected by the time-lag mutual information method. Considering time lag effects between Ta and Tc effectively enhanced the correlation between CWSI and photosynthetic parameters, which can provide theoretical support for thermal infrared remote sensing to diagnose crop water stress conditions.

Differential learning model for carbon emission allowance prices prediction based on adaptive decomposition and joint feature contribution

Currently, how to effectively control carbon emissions is a global concern. Accurate carbon price prediction can help us more effectively control carbon emissions and reduce environmental pollution. Due to the complexity of carbon valence, this study proposes an improved decomposition ensemble prediction model. Firstly, a novel signal decomposition algorithm is designed to adaptively determine the number of decomposition modes for carbon price sequences, obtaining a set of intrinsic mode functions (IMFs). Secondly, a creative method for assessing the contribution of feature components is developed. It utilizes a genetic algorithm-based mutual-information method to calculate the contribution of each IMFs to the original sequence, classifying all feature components into high and low contribution components. Then, this study developed a differential learning method that partitions the contribution of feature components and applies targeted learning and integration using temporal convolutional network with different structures. Compared to traditional forecasting frameworks, this framework improves prediction performance while reducing structural complexity and computational costs. Empirical results demonstrate the superiority and robustness of the proposed model with the outcomes of this study present the performances that the proposed model outperforms the others with Guangzhou's mean absolute percentage error of 3.30313%, which are beneficial for governments and enterprises to predict adverse signals in the carbon market in a more timely manner, and to take measures in advance to maintain the stability of carbon emissions.

CPMI: comprehensive neighborhood-based perturbed mutual information for identifying critical states of complex biological processes

BackgroundThere exists a critical transition or tipping point during the complex biological process. Such critical transition is usually accompanied by the catastrophic consequences. Therefore, hunting for the tipping point or critical state is of significant importance to prevent or delay the occurrence of catastrophic consequences. However, predicting critical state based on the high-dimensional small sample data is a difficult problem, especially for single-cell expression data.ResultsIn this study, we propose the comprehensive neighbourhood-based perturbed mutual information (CPMI) method to detect the critical states of complex biological processes. The CPMI method takes into account the relationship between genes and neighbours, so as to reduce the noise and enhance the robustness. This method is applied to a simulated dataset and six real datasets, including an influenza dataset, two single-cell expression datasets and three bulk datasets. The method can not only successfully detect the tipping points, but also identify their dynamic network biomarkers (DNBs). In addition, the discovery of transcription factors (TFs) which can regulate DNB genes and nondifferential ‘dark genes’ validates the effectiveness of our method. The numerical simulation verifies that the CPMI method is robust under different noise strengths and is superior to the existing methods on identifying the critical states.ConclusionsIn conclusion, we propose a robust computational method, i.e., CPMI, which is applicable in both the bulk and single cell datasets. The CPMI method holds great potential in providing the early warning signals for complex biological processes and enabling early disease diagnosis.

Early screening and staging of melanoma using blood based on laser-induced breakdown spectroscopy

For melanoma, early screening could increase the cure rate, while staging helps to make treatment strategies. Blood sampling has advantages of little damage, convenient operation and low cost, which combined with laser-induced breakdown spectroscopy (LIBS) has been utilized for tumor diagnoses. Here, we proposed to accurately attain early screening and staging of melanoma blood using LIBS. The serum was collected from 25 melanoma mice and 10 healthy controls on the 7th, 14th, 21st and 28th days. Compared with k nearest neighbor (kNN), support vector machine (SVM) and back propagation neural network (BPNN) models, the adaptive boosting of BPNN (BP_AdaBoost) models had the best accuracies of 83.37 % for early screening and 96.18 % for staging, respectively. Using mutual information (MI) method to select features, the accuracies of BP_AdaBoost models were improved to 86.11 % for early screening and 96.91 % for staging, respectively. Besides, the difference significance of elements and molecular bands in the serum was examined by the Kruskal-Wallis (K-W) test. The test results showed that obvious differences of Ca and Na existed in both early screening and staging, while K and Mg made significant differences in staging, consistent with roles of Ca and Na in the whole process of tumor development and roles of K and Mg in tumor proliferation and metastasis. Overall, all results demonstrated that early screening and staging of melanoma could be accurately realized using blood based on LIBS.

Comparative Study of sEMG Feature Evaluation Methods Based on the Hand Gesture Classification Performance.

Effective feature extraction and selection are crucial for the accurate classification and prediction of hand gestures based on electromyographic signals. In this paper, we systematically compare six filter and wrapper feature evaluation methods and investigate their respective impacts on the accuracy of gesture recognition. The investigation is based on several benchmark datasets and one real hand gesture dataset, including 15 hand force exercises collected from 14 healthy subjects using eight commercial sEMG sensors. A total of 37 time- and frequency-domain features were extracted from each sEMG channel. The benchmark dataset revealed that the minimum Redundancy Maximum Relevance (mRMR) feature evaluation method had the poorest performance, resulting in a decrease in classification accuracy. However, the RFE method demonstrated the potential to enhance classification accuracy across most of the datasets. It selected a feature subset comprising 65 features, which led to an accuracy of 97.14%. The Mutual Information (MI) method selected 200 features to reach an accuracy of 97.38%. The Feature Importance (FI) method reached a higher accuracy of 97.62% but selected 140 features. Further investigations have shown that selecting 65 and 75 features with the RFE methods led to an identical accuracy of 97.14%. A thorough examination of the selected features revealed the potential for three additional features from three specific sensors to enhance the classification accuracy to 97.38%. These results highlight the significance of employing an appropriate feature selection method to significantly reduce the number of necessary features while maintaining classification accuracy. They also underscore the necessity for further analysis and refinement to achieve optimal solutions.

An in-depth investigation of global sea surface temperature behavior utilizing chaotic modeling.

Sea surface temperature (SST), with its complex and dynamic behavior, is a major driver of ocean-atmosphere interactions. The purpose of this study is to investigate the behavior of SST and its prediction using a chaotic approach. Average mutual information (AMI) and Cao methods were used to reconstruct the phase space. The Lyapunov exponent and correlation dimension were used to investigate chaos. The Lyapunov exponent index was used to predict SST with a 5-year average prediction horizon using the local prediction method between 2023 and 2027. The results showed a 3-month delay time for the Pacific and Antarctic Oceans, and a 2-month delay time for the Atlantic, Indian, and Arctic Oceans. The optimal embedding dimension for all oceans is between 6 and 7. Our analysis reveals that the dynamics of SST in all oceans exhibit varying degrees of chaos, as indicated by the correlation dimension. The local prediction method achieves relatively accurate short-term SST predictions due to the clustering of SST points around specific attractors in the phase space. However, in the long term, the accuracy of this method decreases as the points in the phase space of SST can spread randomly. The model performance ranking with a Percent Mean Relative Absolute Error shows that the Indian Ocean has the best performance compared to other oceans, while the Atlantic, Pacific, and Antarctic and Arctic Oceans are in the next ranks. This study contributes to understanding the dynamics of SST and has practical value for use in the development of climate models.

Expanding the clinical application of OPM-MEG using an effective automatic suppression method for the dental brace metal artifact

Optically pumped magnetometer magnetoencephalography (OPM-MEG) holds significant promise for clinical functional brain imaging due to its superior spatiotemporal resolution. However, effectively suppressing metallic artifacts, particularly from devices such as orthodontic braces and vagal nerve stimulators remains a major challenge, hindering the wider clinical application of wearable OPM-MEG devices.A comprehensive analysis of metal artifact characteristics from time, frequency, and time–frequency perspectives was conducted for the first time using an OPM-MEG device in clinical medicine. This study focused on patients with metal orthodontics, examining the modulation of metal artifacts by breath and head movement, the incomplete regular sub-Gaussian distribution, and the high absolute power ratio in the 0.5–8 Hz band. The existing metal artifact suppression algorithms applied to SQUID-MEG, such as fast independent component analysis (FastICA), information maximization (Infomax), and algorithms for multiple unknown signal extraction (AMUSE), exhibit limited efficacy. Consequently, this study introduced the second-order blind identification (SOBI) algorithm, which utilized multiple time delays for the component separation of OPM-MEG measurement signals. We modified the time delays of the SOBI method to improve its efficacy in separating artifact components, particularly those in the ultralow frequency range. This approach employs the frequency-domain absolute power ratio, root mean square (RMS) value, and mutual information methods to automate the artifact component screening process.The effectiveness of this method was validated through simulation experiments involving four subjects in both resting and evoked experiments. In addition, the proposed method was also validated by the actual OPM-MEG evoked experiments of three subjects. Comparative analyses were conducted against the FastICA, Infomax, and AMUSE algorithms. Evaluation metrics included normalized mean square error, normalized delta band power error, RMS error, and signal-to-noise ratio, demonstrating that the proposed method provides optimal suppression of metal artifacts. This advancement holds promise for enhancing data quality and expanding the clinical applications of OPM-MEG.

Study on the relationship between draft tube pressure pulsation and unit vibration based on mutual information method

Abstract Draft tube pressure pulsation, as a long-term phenomenon, affects the key to stable unit operation. Based on data from actual power plants, this study qualitatively analyses the relationship between unit vibration parameters and draft tube pressure pulsation under variable load. Then the nonlinear correlation coefficient of mutual information (MI) between draft tube pressure pulsation and external vibration factors is obtained by quantitative calculation from data analysis and probability statistics. The feasibility of this method is demonstrated, and it provides a basis for the subsequent prediction of draft tube pressure pulsation based on the external vibration factors screened by mutual information.

Preoperative prediction of lymph node metastasis in colorectal cancer using 18F-FDG PET/CT peritumoral radiomics analysis.

Radiomics has been used in the diagnosis of tumor lymph node metastasis (LNM). However, to date, most studies have been based on intratumoral radiomics. Few studies have focused on the use of 18F-fluorodeoxyglucose positron emission computed tomography (18F-FDG PET/CT) peritumoral radiomics for the diagnosis of LNM in colorectal cancer (CRC). Determining the value of radiomics features extracted from 18F-FDG PET/CT images of the peritumoral region in predicting LNM in patients with CRC. The clinical data and preoperative 18F-FDG PET/CT images of 244 CRC patients were retrospectively analyzed. Intratumoral and peritumoral radiomics features were screened using the mutual information method, and least absolute shrinkage and selection operator regression. Based on the selected radiomics features, a radiomics score (Rad-score) was calculated, and independent risk factors obtained from univariate and multivariate logistic regression analyses were used to construct clinical and combined (Radiomics + Clinical) models. The performance of these models was evaluated using the DeLong test, while their clinical utility was assessed by decision curve analysis. Finally, a nomogram was constructed to visualize the predictive model. The most optimal set of features retained by the feature filtering process were all peritumoral radiomic features. Carcinoembryonic antigen levels, PET/CT-reported lymph node status and Rad-score were found to be independent risk factors for LNM. All three LNM risk assessment models exhibited good predictive performance, with the combined model showing the best classification results, with areas under the curve of 0.85 and 0.76 in the training and validation groups, respectively. The DeLong test revealed that the performance of the combined model was superior to that of the clinical and radiomics models in both the training and validation groups, although this difference was only statistically significant in the training group. DCA indicated that the combined model displayed better clinical utility. 18F-FDG PET/CT peritumoral radiomics is uniquely suited to predict the presence of LNM in patients with CRC. In particular, the predictive efficacy of LNM for precision therapy and individualized patient management can be improved by using a combination of clinical risk factors.

Accurate Satellite Operation Predictions Using Attention-BiLSTM Model with Telemetry Correlation

In satellite health management, anomalies are mostly resolved after an event and are rarely predicted in advance. Thus, trend prediction is critical for avoiding satellite faults, which may affect the accuracy and quality of satellite data and even greatly impact safety. However, it is difficult to predict satellite operation using a simple model because satellite systems are complex and telemetry data are copious, coupled, and intermittent. Therefore, this study proposes a model that combines an attention mechanism and bidirectional long short-term memory (attention-BiLSTM) with telemetry correlation to predict satellite behaviour. First, a high-dimensional K-nearest neighbour mutual information method is used to select the related telemetry variables from multiple variables of satellite telemetry data. Next, we propose a new BiLSTM model with an attention mechanism for telemetry prediction. The dataset used in this study was generated and transmitted from the FY3E meteorological satellite power system. The proposed method was compared with other methods using the same dataset used in the experiment to verify its superiority. The results confirmed that the proposed method outperformed the other methods owing to its prediction precision and superior accuracy, indicating its potential for application in intelligent satellite health management systems.