Categories Of Features Research Articles

CLIP-FSSC: A Transferable Visual Model for Fish and Shrimp Species Classification Based on Natural Language Supervision

Fish and shrimp species classification is a practical need in the field of aquaculture. Traditional classification method includes extracting modal features of the single image and training them on downstream datasets. However, this method has the disadvantage of requiring manual annotated image data and significant training time. To address these issues, this paper introduces a method named CLIP-FSSC (Contrastive Language–Image Pre-training for Fish and Shrimp Species Classification) for zero-shot prediction using a pre-trained model. The proposed method aims to classify fish and shrimp species in the field of aquaculture using a multimodal pre-trained model that utilizes semantic text description as an image supervision signal for transfer learning. In the downstream fish dataset, we use natural language labels for three types of fish - grass carp, common carp, and silver carp. We extract text category features using a transformer and compare the results obtained from three different CLIP-based backbones for the image modality - vision transformer, Resnet50, and Resnet101. We compare the performance of these models with previous methods that performed well. After performing zero-shot predictions on samples of the three types of fish, we achieve similar or even better classification accuracy than models trained on downstream fish datasets. Our experiment results show an accuracy of 98.77%, and no new training process is required. This proves that using the semantic text modality as the label for the image modality can effectively classify fish species. To demonstrate the effectiveness of this method on other species in the field of aquaculture, we collected two sets of shrimp data - prawn and cambarus. Through zero-shot prediction, we achieve the highest classification accuracy of 92.00% for these two types of shrimp datasets. Overall, our results demonstrate that using a multimodal pre-trained model with semantic text description as an image supervision signal for transfer learning can effectively classify fish and shrimp species with high accuracy, while reducing the need for manual annotation and training time.

Inter-Reader Agreement for Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System Major Features and Final Categorization: A Subanalysis From a Prospective Multicenter Study.

Contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) is used to definitively diagnose hepatocellular carcinoma (HCC) in patients at risk. However, the user variability associated with CEUS LI-RADS has not been validated in North American and European patients. This study aims to evaluate the inter-reader agreements of CEUS LI-RADS features for, and final categorization of, HCC in patients at risk. This retrospective multicenter clinical study used the database of a previous prospective multinational study, evaluating the accuracy of CEUS LI-RADS for HCC diagnosis in patients at risk. All cases were first evaluated by a site physician performing/supervising the CEUS examination. Randomly selected cases were re-evaluated by a blinded central reader. Final diagnosis was confirmed with the reference standard, which was a composite of imaging tests and histology. Cohen's kappa test was used to evaluate inter-reader agreement. This study included 150 liver nodules and 58.0% (87/150) were confirmed as HCC, 4.7% (7/150) non-HCC malignancies, 22.7% (34/150) had no confirmed final diagnosis, and 14.7% (22/150) were nonmalignant. Inter-reader agreements were substantial for CEUS LI-RADS categorization (κ = 0.61; 95% confidence interval [CI]: 0.51-0.71) and major features assessment (ranged κ = 0.64-0.78), LR-5 (κ = 0.65; 95% CI: 0.52-0.77), and LR-M (κ = 0.67; 95% CI: 0.44-0.90), while for LR-1 and LR-2 categorization was almost perfect (κ = 0.85; 95% CI: 0.65-1.00). Our study reported a substantial inter-reader agreement for overall CEUS LI-RADS categorization, especially for LR-5 and LR-M, and major imaging features of HCC, further confirming CEUS LI-RADS as a valuable and reliable tool for diagnosis of HCC.

Predicting Online Gaming Behavior: A Comparative Analysis of Random Forest and Gaussian Naive Bayes Models

With the rising impact and economic benefits of the online gaming industry, online gaming companies need to understand players’ behavior to evaluate their products better and adjust their developing strategy. This paper uses machine learning models to predict players’ online gaming behaviors. The study utilizes the dataset from Kaggle, which contains 40,034 samples with 13 features related to player demographics, game preferences, and gameplay behaviors. The primary objective is to classify two target variables: ‘EngagementLevel’ and ‘InGamePurchases.’ Data preprocessing steps included handling missing values, encoding categorical features, normalizing numerical data, and addressing class imbalances using the Synthetic Minority Over-sampling Technique (SMOTE). The Random Forests (RF) and Gaussian Naïve Bayes (GNB) models were employed to predict the target variables. The RF model significantly outperformed the GNB model in both classification tasks, especially when predicting the in-game purchases. The RF model’s robustness is attributed to its ability to handle complex, non-linear relationships and interactions between features, while the GNB model’s performance was limited by its assumptions of feature independence and normally distributed data. The findings suggest that RF is a more effective tool for predicting online gaming behaviors, particularly in scenarios with complex feature interactions. Future research could incorporate additional machine learning models and more diverse datasets to further enhance predictive accuracy and offer a more comprehensive understanding of online gaming behaviors.

Optimizing Heart Disease Diagnosis: Feature Selection Techniques for Enhanced Machine Learning Model Performance

Heart disease is a growing global concern, affecting people across various age groups and genders. Detecting heart failure early is crucial, and ongoing research leverages advancements in healthcare technology, machine learning, imaging techniques, and data science to analyze vast datasets for this purpose. However, not all data attributes contribute equally to diagnosing heart disease, and the inclusion of irrelevant features can increase resource demands and potentially lead to inaccurate predictions with fatal consequences. This study focuses on feature extraction and reduction techniques to identify the most critical attributes for heart disease diagnosis, balancing resource efficiency with diagnostic accuracy. Using a dataset from the UCI repository, which includes both continuous and categorical features, we standardize the data and split it into training and testing sets in an 80:20 ratio. We then apply feature selection techniques to machine learning models such as K-nearest neighbor, decision tree classifier, SVM, logistic regression, and random forest. The models' predictive performance is evaluated using confusion matrices and ROC curves, demonstrating the impact of feature selection on diagnostic accuracy.

Interpretable multi-step hybrid deep learning model for karst spring discharge prediction: Integrating temporal fusion transformers with ensemble empirical mode decomposition

Karst groundwater is a critical freshwater resource for numerous regions worldwide. Monitoring and predicting karst spring discharge is essential for effective groundwater management and the preservation of karst ecosystems. However, the high heterogeneity and karstification pose significant challenges to physics-based models in providing robust predictions of karst spring discharge. In this study, an interpretable multi-step hybrid deep learning model called selective EEMD-TFT is proposed, which adaptively integrates temporal fusion transformers (TFT) with ensemble empirical mode decomposition (EEMD) for predicting karst spring discharge. The selective EEMD-TFT hybrid model leverages the strengths of both EEMD and TFT techniques to learn inherent patterns and temporal dynamics from nonlinear and nonstationary signals, eliminate redundant components, and emphasize useful characteristics of input variables, leading to the improvement of prediction performance and efficiency. It consists of two stages: in the first stage, the daily precipitation data is decomposed into multiple intrinsic mode functions using EEMD to extract valuable information from nonlinear and nonstationary signals. All decomposed components, temperature and categorical date features are then fed into the TFT model, which is an attention-based deep learning model that combines high-performance multi-horizon prediction and interpretable insights into temporal dynamics. The importance of input variables will be quantified and ranked. In the second stage, the decomposed precipitation components with high importance are selected to serve as the TFT model’s input features along with temperature and categorical date variables for the final prediction. Results indicate that the selective EEMD-TFT model outperforms other sequence-to-sequence deep learning models, such as LSTM and single TFT models, delivering reliable and robust prediction performance. Notably, it maintains more consistent prediction performance at longer forecast horizons compared to other sequence-to-sequence models, highlighting its capacity to learn complex patterns from the input data and efficiently extract valuable information for karst spring prediction. An interpretable analysis of the selective EEMD-TFT model is conducted to gain insights into relationships among various hydrological processes and analyze temporal patterns.

Leveraging Machine Learning for Sophisticated Rental Value Predictions: A Case Study from Munich, Germany

There has been very limited research conducted to predict rental prices in the German real estate market using an AI-based approach. From a general perspective, conventional approaches struggle to handle large amounts of data and fail to consider the numerous elements that affect rental prices. The absence of sophisticated, data-driven analytical tools further complicates this situation, impeding stakeholders, such as tenants, landlords, real estate agents, and the government, from obtaining the accurate insights necessary for making well-informed decisions in this area. This paper applies novel machine learning (ML) approaches, including ensemble techniques, neural networks, linear regression (LR), and tree-based algorithms, specifically designed for forecasting rental prices in Munich. To ensure accuracy and reliability, the performance of these models is evaluated using the R2 score and root mean squared error (RMSE). The study provides two feature sets for model comparison, selected by particle swarm optimisation (PSO) and CatBoost. These two feature selection methods identify significant variables based on different mechanisms, such as seeking the optimal solution with an objective function and converting categorical features into target statistics (TSs) to address high-dimensional issues. These methods are ideal for this German dataset, which contains 49 features. Testing the performance of 10 ML algorithms on two sets helps validate the robustness and efficacy of the AI-based approach utilising the PyTorch framework. The findings illustrate that ML models combined with PyTorch-based neural networks (PNNs) demonstrate high accuracy compared to standalone ML models, regardless of feature changes. The improved performance indicates that utilising the PyTorch framework for predictive tasks is advantageous, as evidenced by a statistical significance test in terms of both R2 and RMSE (p-values < 0.001). The integration results display outstanding accuracy, averaging 90% across both feature sets. Particularly, the XGB model, which exhibited the lowest performance among all models in both sets, significantly improved from 0.8903 to 0.9097 in set 1 and from 0.8717 to 0.9022 in set 2 after being combined with the PNN. These results showcase the efficacy of using the PyTorch framework, enhancing the precision and reliability of the ML models in predicting the dynamic real estate market. Given that this study applies two feature sets and demonstrates consistent performance across sets with varying characteristics, the methodology may be applied to other locations. By offering accurate projections, it aids investors, renters, property managers, and regulators in facilitating better decision-making in the real estate sector.

DDoS Attack Detection with Machine Learning

Nowadays, Distributed Denial of Service (DDoS) attacks are a major issue in internet security. These attacks target servers or network infrastructure. Similar to an unanticipated traffic jam on highway (lagging/crash) that prevent normal traffic reach to destination. DDoS may prevent users to access any system services. Researchers and scientists have developed numerous methods and algorithms to improve the performance of DDoS detection. In this paper, a DDoS detection method utilizing machine learning is proposed. There are three type of supervised machine learning classification methods which are K-Nearest Neighbor, Multilayer Perceptron and Random Forest, are applied in the proposed work to assess the accuracy of the model in training and testing processes. RF classification provides robustness and interpretability, MLP offers deep learning capabilities for complex patterns, and K-NN delivers simplicity and adaptability for instance-based learning. Together, these methods can contribute to a comprehensive DDoS attack detection system using machine learning. There are two types of classification setups: binary and multi-class classification. Binary classification involves identifying traffic as either a DDoS attack or normal using the NSL-KDD dataset. Multi-class classification, on the other hand, distinguishes between various types of DDoS attacks (such as DoS, Probe, U2R, and Sybil) and normal traffic using the NSL-KDD dataset. Feature engineering is also involved in this experiment to convert the categorical features into numerical values for detecting DDoS attack. Our model's performance was effective compared to other machine learning methods. RF achieved the highest accuracy rates: 99.35% in binary classification and 97.71% in multi-class classification. K-NN followed with 99.15% in binary and 97.35% in multi-class classification, while MLP achieved 90.63% in binary and 84.33% in multi-class classification.

Determining the Influence of Real Estate Features on Prices with Partial Dependence Plots: A Case Study in Szczecin, Poland

Abstract The study explores the application of Partial Dependence Plots (PDP) in the analysis of real estate features. The study centers on a selected real estate market in Szczecin, Poland, aiming to highlight the efficacy of PDP in understanding and interpreting the complex relationships between various features and property prices. The primary objective is to showcase the potential of PDP in capturing the nuanced interactions between real estate attributes and their impact on market prices. The CatBoost model, known for its robust handling of categorical features and strong predictive capabilities, is employed as the machine learning algorithm for this analysis. The performance of this model will be compared against a traditional multiple linear regression model, providing insights into the advantages of leveraging advanced machine learning techniques in real estate analysis. Results obtained from the analysis will be presented and discussed, shedding light on the interpretability and accuracy of the CatBoost model compared to the traditional linear regression approach. The presentation will conclude with implications for real estate practitioners and researchers, emphasizing the potential for PDP to enhance the transparency and understanding of complex models in the real estate domain. This research contributes to the growing body of knowledge on the application of advanced machine learning techniques in real estate analysis.

Research on Evaluation and Prediction Methods of Cognitive Intentions for Product Morphological Features

The morphological characteristics of a product serve as essential carriers for conveying design intentions. These characteristics directly affect users’ comprehension of the product’s functions and proper usage, which are critical to the safety of product utilization and the overall comfort of the user experience. Incorporating prior experience to predict users’ cognitive intentions regarding product form characteristics can provide valuable evaluation and decision-making references for design. This approach effectively reduces product development risks and contributes to enhancing user acceptance and experience. The study established intention discrimination indicators for form characteristics, covering six dimensions: functional orientation, behavioral intention, recognizability, cognitive load, attention distribution, and experiential feeling. Combining multidimensional scaling (MDS) and systematic clustering, samples were screened, and the morphological decomposition method was used to categorize and extract form characteristic categories and feature factors. The entropy weight method was applied to assign weights to the feature categories, and a feedforward neural network (FNN) was employed to construct a prediction model for cognitive intentions regarding product form characteristics. The model was tested using leave-one-out cross-validation, yielding a mean squared error (MSE) of 0.0089 and an R correlation coefficient of 0.9998, indicating high reliability. Finally, the feasibility and effectiveness of this method were validated through a case study on earthquake science experience facilities.

Dynamic Multi-Factor Correlation Analysis for Prediction of Provincial Carbon Emissions in China’s Bohai Rim Region

This study presents a dynamic multi-factor correlation analysis method designed to predict provincial carbon dioxide emissions (CDE) within China’s Bohai Rim region, including Tianjin, Hebei, Shandong, and Liaoning. By employing the sliding window technique, dynamic correlation curves are computed between various influencing factors and CDE at different time intervals, thereby facilitating the identification of key feature attributes. A novel metric, the Consistency Index of Influencing Factors (CIIF), is introduced to evaluate the consistency of these factors across regions. Furthermore, the Accurate Predictive Capability Indicator (APCI) is defined to measure the impact of different feature categories on the prediction accuracy. The findings reveal that models relying on a single influencing factor exhibit limited accuracy, whereas combining multiple factors with diverse correlation features significantly improves the prediction accuracy. This study introduces a refined analytical framework and a comprehensive indicator system for CDE prediction. It enhances the understanding of the complex factors that influence CDE and provides a scientific rationale for implementing effective emission reduction strategies.

Solo music performance assessment criteria: a systematic review.

Assessment is a crucial aspect of music performance. In pedagogical contexts, an effective assessment process can measure student achievement and inform instructional decisions that contribute to improving teaching and learning. However, music performance assessment is particularly challenging due to its inherent subjectivity, involving personal expression and interpretation, which can lead to divergent opinions. In this PRISMA systematic review (registration DOI: 10.17605/OSF.IO/CSM8Q), we aimed to delimit and analyze solo music performance assessment systems found in the literature to date, including their corresponding evaluation categories and descriptive criteria, rating methodology, and target audience. A search in three main scientific databases (Web of Science, Scopus, ERIC) was conducted using keywords associated with the topic of assessment in the field of solo music performance. Ultimately, 20 papers were selected and examined, resulting in 26 original assessment systems for analysis. Regarding sample characteristics, we found that studies mainly focused on evaluating high school and university students, with music teachers and faculty members serving as primary evaluators. Many assessment systems were designed to be applicable across various instruments, although some were tailored to specific instruments (e.g., piano, voice) and families (e.g., brass, woodwind). Systems typically structured evaluation around technical, interpretative/expressive, and various musical feature categories (e.g., pitch, rhythm, intonation), further elaborated with descriptive items. While five-point Likert scales were commonly used, recent studies indicated a shift towards rubrics for detailed feedback, which aids examiners' understanding and supports student progress. No differentiation was found in assessment criteria based on students' learning stages, suggesting an area for improvement in refining these assessment methods. This study identifies gaps and proposes improvements in existing assessment systems, providing a foundation for educators and policymakers to enhance curriculum design and instructional practices in music education.

Research on an identification model for mine water inrush sources based on the HBA-CatBoost algorithm

Accurate and efficient identification of water inrush sources, as one of the three critical elements of mine water hazards, is crucial for mine water management. To identify the sources of mine water inrush effectively, a model named HBA-CatBoost is introduced. This model is established on the hybrid bat algorithm (HBA)-optimized category feature gradient boosting tree (CatBoost), and the shapley additive explanation (SHAP) method is employed to elucidate the model’s decision-making process. Given the prevalent occurrence of water hazards in coal seam roofs and floors in the northern Guizhou coalfield, coupled with the challenges in pinpointing water inrush sources in mines, the HBA-CatBoost model is tested at the Longfeng Coal Mine in northern Guizhou to validate its practicality. Comparative analysis with the HBA-RF, HBA-XGBoost, CatBoost, RF, and XGBoost models demonstrates that the hybrid bat algorithm significantly enhances the classification performance of the CatBoost model, resulting in improved convergence speed and classification accuracy. The HBA-CatBoost model outperforms the aforementioned models in terms of classification effectiveness, achieving accuracy, recall, precision, and F1 scores of 96.43%, 97.22%, 96.43%, and 96.61%, respectively. The SHAP method elucidates the decision mechanism of the optimal HBA-CatBoost model, highlighting the significance of sample features and bolstering the model’s credibility. These outcomes underscore the superior performance of the HBA-CatBoost model and its potential for effectively identifying water inrush sources in mines.

Application of SHAP and Multi-Agent Approach for Short-Term Forecast of Power Consumption of Gas Industry Enterprises

Currently, machine learning methods are widely applied in the power industry to solve various tasks, including short-term power consumption forecasting. However, the lack of interpretability of machine learning methods can lead to their incorrect use, potentially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of the tasks of enhancing the energy efficiency of gas industry enterprises. In order to reduce the risks of making incorrect decisions based on the results of short-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a multi-agent approach for the decomposition of production processes using self-generation agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjusting the operation modes of self-generation units and energy-storage systems, optimizing the power consumption schedule, and reducing electricity and power costs. A comparative analysis of various algorithms for constructing decision tree ensembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features. The experiments demonstrated that using the developed method and production process factors reduced the MAE from 105.00 kWh (MAPE of 16.81%), obtained through expert forecasting, to 15.52 kWh (3.44%). Examples were provided of how the use of SHapley Additive exPlanation can increase the safety of the electrical system management of gas industry enterprises by improving experts’ confidence in the results of the information system.

Comparison of diagnostic accuracy of radiomics parameter maps and standard reconstruction for the detection of liver lesions in computed tomography.

The liver is a frequent location of metastatic disease in various malignant tumor entities. Computed tomography (CT) is the most frequently employed modality for initial diagnosis. However, liver metastases may only be delineated vaguely on CT. Calculating radiomics features in feature maps can unravel textures not visible to the human eye on a standard CT reconstruction (SCTR). This study aimed to investigate the comparative diagnostic accuracy of radiomics feature maps and SCTR for liver metastases. Forty-seven patients with hepatic metastatic colorectal cancer were retrospectively enrolled. Whole-liver maps of original radiomics features were generated. A representative feature was selected for each feature class based on the visualization of example lesions from five patients. These maps and the conventional CT image data were viewed and evaluated by four readers in terms of liver parenchyma, number of lesions, visual contrast of lesions and diagnostic confidence. T-tests and chi²-tests were performed with a significance cut off of p<0.05 to compare the feature maps with SCRT, and the data were visualized as boxplots. Regarding the number of lesions detected, SCTR showed superior performance compared to radiomics maps. However, the feature map for firstorder RootMeanSquared was ranked superior in terms of very high visual contrast in 57.4% of cases, compared to 41.0% in standard reconstructions (p < 0.001). All other radiomics maps ranked significantly lower in visual contrast when compared to SCTR. For diagnostic confidence, firstorder RootMeanSquared reached very high ratings in 47.9% of cases, compared to 62.8% for SCTR (p < 0.001). The conventional CT images showed superior results in all categories for the other features investigated. The application of firstorder RootMeanSquared feature maps may help visualize faintly demarcated liver lesions by increasing visual contrast. However, reading of SCTR remains necessary for diagnostic confidence.

Exploring Feature Relationships in Brain Stroke Data Using Polynomial Feature Transformation and Linear Regression Modeling

A Cerebral vascular accident, commonly known as a stroke, is a pathological condition that impacts the brain due to the rupture of capillaries. It occurs when there is a disturbance in the typical blood circulation and essential physiological processes of the brain. Stroke prediction plays a crucial role in early diagnosis and intervention, potentially improving patient outcomes. This paper proposes a machine learning model that leverages polynomial feature transformation and linear regression modeling for stroke prediction. The model addresses the challenge of capturing non-linear relationships between features and the target variable while maintaining interpretability. The proposed approach involves preprocessing data by separating categorical and numerical features, applying one-hot encoding to categorical features, and generating polynomial features up to the second degree for numerical features. This tailored preprocessing is facilitated by a Column Transformer. For model development, a machine learning pipeline is constructed, splitting the data into training and testing sets. Despite utilizing polynomial features, linear regression is employed as the final model, allowing for the capture of both linear and non-linear relationships while maintaining interpretability. This work contributes to stroke prediction by offering a balanced approach that considers model complexity and interpretability, showcasing the potential of linear regression with polynomial features for accurate predictions and insights into feature-target relationships. The proposed model exhibited superior performance compared to other existing models, achieving a remarkable testing accuracy of 99.2%.

Mixed fuzzy C-means clustering

Clustering analysis becomes challenging when the dataset has mixed data types comprising categorical (nominal or ordinal scale) and numerical (interval scale) features. Mainstream distance metrics cannot handle the information in categorical data about the similarity between the observations and cluster centers, leading to performance loss. Various methods are introduced in the literature to handle the mixed data types in clustering. However, each method has disadvantages in capturing categorical information about similarity, adjusting the contribution of categorical information to clustering, and computational or implementation inefficiency. This study proposes a mixed fuzzy C-means clustering method for mixed data types. Two new distance metrics are developed to handle binary and multi-class nominal features. The scaled entropy of each data type is used to adjust the weight of each data type in the overall similarity metric, providing a lower bias since no user-specified weight is required. A comparative numerical study is conducted with twenty real datasets and seven benchmark methods using five cluster validation statistics. The mixed fuzzy C-means clustering performs better than the benchmark methods and is computationally efficient in practice. Since all the computer codes for implementing mixed fuzzy C-means clustering are given, the proposed method is readily applicable to practical problems.

Computed tomography-based radiomics nomogram for prediction of lympho-vascular and perineural invasion in esophageal squamous cell cancer patients: a retrospective cohort study

PurposeLympho-vascular invasion (LVI) and perineural invasion (PNI) have been established as prognostic factors in various types of cancers. The preoperative prediction of LVI and PNI has the potential to guide personalized medicine strategies for patients with esophageal squamous cell cancer (ESCC). This study investigates whether radiomics features derived from preoperative contrast-enhanced CT could predict LVI and PNI in ESCC patients.Methods and materialsA retrospective cohort of 544 ESCC patients who underwent esophagectomy were included in this study. Preoperative contrast-enhanced CT images, pathological results of PNI and LVI, and clinical characteristics were collected. For each patient, the gross tumor volume (GTV-T) and lymph nodes volume (GTV-N) were delineated and four categories of radiomics features (first-order, shape, textural and wavelet) were extracted from GTV-T and GTV-N. The Mann–Whitney U test was used to select significant features associated with LVI and PNI in turn. Subsequently, radiomics signatures for LVI and PNI were constructed using LASSO regression with ten-fold cross-validation. Significant clinical characteristics were combined with radiomics signature to develop two nomogram models for predicting LVI and PNI, respectively. The area under the curve (AUC) and calibration curve were used to evaluate the predictive performance of the models.ResultsThe radiomics signature for LVI prediction consisted of 28 features, while the PNI radiomics signature comprised 14 features. The AUCs of the LVI radiomics signature were 0.77 and 0.74 in the training and validation groups, respectively, while the AUCs of the PNI radiomics signature were 0.69 and 0.68 in the training and validation groups. The nomograms incorporating radiomics signatures and significant clinical characteristics such as age, gender, thrombin time and D-Dimer showed improved predictive performance for both LVI (AUC: 0.82 and 0.80 in the training and validation group) and PNI (AUC: 0.75 and 0.72 in the training and validation groups) compared to the radiomics signature alone.ConclusionThe radiomics features extracted from preoperative contrast-enhanced CT of gross tumor and lymph nodes have demonstrated their potential in predicting LVI and PNI in ESCC patients. Furthermore, the incorporation of clinical characteristics has shown additional value, resulting in improved predictive performance.

NSEMBLE FINE TUNED MULTI LAYER PERCEPTRON FOR PREDICTIVE ANALYSIS OF WEATHER PATTERNS AND RAINFALL FORECASTING FROM SATELLITE DATA

The accurate prediction of weather patterns and rainfall forecasting is critical for various sectors, including agriculture, disaster management, and water resource planning. Traditional models often struggle to capture the complex interactions between atmospheric variables, particularly when integrating diverse types of satellite data (binary, categorical, and numerical). To address this challenge, an ensemble fine-tuned multi-layer perceptron (MLP) model is developed, combining the strengths of multiple machine learning techniques for more robust predictions. The primary problem is the difficulty in handling mixed data types while maintaining high prediction accuracy. Satellite data, including binary indicators (e.g., cloud presence), categorical features (e.g., cloud types), and numerical variables (e.g., temperature, humidity, and wind speed), provide rich information but require specialized processing for effective forecasting. The proposed method involves fine-tuning an ensemble of MLP models with backpropagation, dropout regularization, and batch normalization to reduce overfitting and enhance generalization. The ensemble integrates predictions from individual MLP models, each trained on different subsets of features (binary, categorical, numerical). This technique allows the model to leverage complementary strengths and produce more accurate rainfall forecasts. Satellite data is preprocessed and normalized before training, and categorical variables are one-hot encoded to ensure compatibility with the MLP architecture. Results from testing on historical satellite weather datasets demonstrate significant improvements in forecast accuracy. The ensemble MLP achieved an accuracy of 91.3%, with a precision of 90.7%, recall of 89.5%, and an F1-score of 90.1%. The model performed exceptionally well in identifying critical rainfall events, reducing false positives by 12% compared to traditional models.

Construction and comparative analysis of an early screening prediction model for fatty liver in elderly patients based on machine learning

Objective: To construct a prediction model for fatty liver disease (FLD) among elderly residents in community using machine learning (ML) algorithms and evaluate its effectiveness. Methods: The physical examination data of 4989 elderly people (aged over 60 years) in a street of Shanghai from 2019 to 2023 were collected. The subjects were divided into a training set and a testing set in a 7:3 ratio. Using feature selection and importance sorting methods, eight indicators were selected, including high-density lipoprotein cholesterol, body mass index, uric acid, triglycerides, albumin, red blood cell, white blood cell, and alanine aminotransferase. Six ML models, including Categorical Features Gradient Boosting, eXtreme Gradient Boosting, Light Gradient Boosting Machine, Random Forest, Decision Tree, and Logistic Regression, were constricted, and their predictive performances were compared via accuracy, precision, recall, F1 score, and Area Under Receiver Operating Characteristic Curve. Results: Among the six ML models, the Categorical Features Gradient Boosting model demonstrated the highest prediction accuracy of 0.74 for FLD in elderly community population, along with a precision of 0.70, a recall of 0.73, a F1 score of 0.71, and an area under the curve of 0.74. Conclusions: In the context of rapid development of artificial intelligence, a community-based elderly FLD prediction model constructed using ML algorithms aid family general practitioners in the early diagnosis, early treatment, and health management of local FLD patients.

Android malware defense through a hybrid multi-modal approach

The rapid proliferation of Android apps has given rise to a dark side, where increasingly sophisticated malware poses a formidable challenge for detection. To combat this evolving threat, we present an explainable hybrid multi-modal framework. This framework leverages the power of deep learning, with a novel model fusion technique, to illuminate the hidden characteristics of malicious apps. Our approach combines models (leveraging late fusion approach) trained on attributes derived from static and dynamic analysis, hence utilizing the unique strengths of each model. We thoroughly analyze individual feature categories, feature ensembles, and model fusion using traditional machine learning classifiers and deep neural networks across diverse datasets. Our hybrid fused model outperforms others, achieving an F1-score of 99.97% on CICMaldroid2020. We use SHAP (SHapley Additive exPlanations) and t-SNE (t-distributed Stochastic Neighbor Embedding) to further analyze and interpret the best-performing model. We highlight the efficacy of our architectural design through an ablation study, revealing that our approach consistently achieves over 99% detection accuracy across multiple deep learning models. This paves the way groundwork for substantial advancements in security and risk mitigation within interconnected Android OS environments.