Search Results (544)

Ovarian cancer stands out as one of the most formidable adversaries in women’s health, largely due to its typically subtle and nonspecific early symptoms, which pose significant challenges to early detection and diagnosis. Although existing diagnostic methods, such as biomarker testing and imaging, can help with early diagnosis to some extent, these methods still have limitations in sensitivity and accuracy, often leading to misdiagnosis or missed diagnosis. Ovarian cancer’s high heterogeneity and complexity increase diagnostic challenges, especially in disease progression prediction and patient classification. Machine learning (ML) has outperformed traditional methods in cancer detection by processing large datasets to identify patterns missed by conventional techniques. However, existing AI models still struggle with accuracy in handling imbalanced and high-dimensional data, and their “black-box” nature limits clinical interpretability. To address these issues, this study proposes SHAP-GAN, an innovative diagnostic model for ovarian cancer that integrates Shapley Additive exPlanations (SHAP) with Generative Adversarial Networks (GANs). The SHAP module quantifies each biomarker’s contribution to the diagnosis, while the GAN component optimizes medical data generation. This approach tackles three key challenges in medical diagnosis: data scarcity, model interpretability, and diagnostic accuracy. Results show that SHAP-GAN outperforms traditional methods in sensitivity, accuracy, and interpretability, particularly with high-dimensional and imbalanced ovarian cancer datasets. The top three influential features identified are PRR11, CIAO1, and SMPD3, which exhibit wide SHAP value distributions, highlighting their significant impact on model predictions. The SHAP-GAN network has demonstrated an impressive accuracy rate of 99.34% on the ovarian cancer dataset, significantly outperforming baseline algorithms, including Support Vector Machines (SVM), Logistic Regression (LR), and XGBoost. Specifically, SVM achieved an accuracy of 72.78%, LR achieved 86.09%, and XGBoost achieved 96.69%. These results highlight the superior performance of SHAP-GAN in handling high-dimensional and imbalanced datasets. Furthermore, SHAP-GAN significantly alleviates the challenges associated with intricate genetic data analysis, empowering medical professionals to tailor personalized treatment strategies for individual patients. Full article

This work explores the effectiveness of explainable artificial intelligence in mapping solar photovoltaic power outputs based on weather data, focusing on short-term mappings. We analyzed the impact values provided by the Shapley additive explanation method when applied to two algorithms designed for tabular data—XGBoost and TabNet—and conducted a comprehensive evaluation of the overall model and across seasons. Our findings revealed that the impact of selected features remained relatively consistent throughout the year, underscoring their uniformity across seasons. Additionally, we propose a feature selection methodology utilizing the explanation values to produce more efficient models, by reducing data requirements while maintaining performance within a threshold of the original model. The effectiveness of the proposed methodology was demonstrated through its application to a residential dataset in Madeira, Portugal, augmented with weather data sourced from SolCast. Full article

With the increasing application of federated learning to medical and image data, the challenges of class distribution imbalances and Non-IID heterogeneity across clients have become critical factors affecting the generalization ability of global models. In the medical domain, the phenomenon of data silos is particularly pronounced, leading to significant differences in data distributions across hospitals, which in turn hinder the performance of global model training. To address these challenges, this paper proposes FedCon, a federated learning method capable of dynamically adjusting aggregation weights, while accurately evaluating client contributions. Specifically, FedCon initializes aggregation weights based on client data volume and class distribution and employs Monte Carlo sampling to effectively simplify the computation of Shapley values. Subsequently, it further optimizes the aggregation weights by comprehensively considering the historical contributions of clients and the similarity between clients and the global model. This approach significantly enhances the ability to generalize and update the stability of the global model. Experimental results demonstrate that, compared to existing methods, FedCon achieved a superior generalization performance on public datasets and significantly accelerated the convergence of the global model. Full article

Hydroxyl-terminated polyether (HTPE) propellants are attractive in the weapons materials and equipment industry for their insensitive properties. Storage, combustion, and explosion of solid propellants are affected by their mechanical properties, so accurate mechanical modeling is vital. In this study, deep neural networks are applied to model composite solid-propellant mechanical behavior for the first time. A data-driven framework incorporating a novel training–testing splitting strategy is proposed. By building Neural Networks (FFNNs), Kolmogorov–Arnold Networks (KANs) and Long Short-Term Memory (LSTM) networks and optimizing the model framework and parameters using a Bayesian optimization algorithm, the results show that the LSTM model predicts the stress–strain curve of HTPE propellant with an RMSE of 0.053 MPa, which is 62.7% and 48.5% higher than the FFNNs and the KANs, respectively. The R² values of the LSTM model for the testing set exceed 0.99, which can effectively capture the effects of tensile rate and temperature changes on tensile strength, and accurately predict the yield point and the slope change of the stress–strain curve. Using the interpretable Shapley Additive Explanations (SHAP) method, fine-grained ammonium perchlorate (AP) can increase its tensile strength, and plasticizers can increase their elongation at break; this method provides an effective approach for HTPE propellant formulation. Full article

The paper demonstrates the nonsense of using Bitcoin in financial investments. By using mean-variance financial analysis, stochastic dominance, CVaR, and the Shapley value theory as analytical statistical models, I show how Bitcoin performs poorly by comparing it against other traded assets. The conclusion is reached by analyzing daily freely available market data for the period 2018–2023. Full article

The traditional non-cooperative and cooperative game methods have limitations in solving the traffic problems of autonomous or assisted driving vehicles using vehicle-to-everything communication. In this paper, the biform game method is introduced to optimize the lane-changing behavior of autonomous or assisted driving vehicles in highway on-ramp areas based on vehicle-to-everything. Considering the lane-changing and speed adjustment needs of autonomous vehicles in high-speed scenarios, a forced lane-changing framework was constructed, and the speed gain allocation was determined based on the target vehicle lane-changing time, and a speed increase was regarded as a benefit. Through the constructed biform game model, research was carried out on conflicting and cooperative vehicles. A strategy combination is first constructed in the non-cooperative situation, and then the cooperative game competition stage begins. The Shapley value is used to deduce the distribution value of each participant in the cooperative game stage, which is the profit value in the non-cooperative stage, and then the pure-strategy Nash equilibrium solution is calculated. The interaction with other vehicles in the lane-change process is based on maximizing the benefit to all the vehicles participating in the lane change, and the optimal speed solution of the biform game model when changing lanes is obtained. Numerical examples were used to verify the validity and feasibility of the model and broaden the application range of the biform game method. In future research, this method will be applied to more complex traffic models, such as driving models in emergency situations and research from the perspective of road infrastructure designers, providing new ideas and directions for optimization strategies for autonomous vehicle lane changes in the Internet of Vehicles. Full article

Monitoring and forecasting air quality is essential for public health and environmental management. It details the air’s cleanliness, pollution levels, and any related health risks that the general public may find concerning. This research investigates how effective machine learning techniques and particle swarm optimization are in predicting air quality. An array of machine learning algorithms, including XGBoost, support vector regression, linear regression, and random forest, was selected to ensure effective modeling outcomes. The models were trained on an open access dataset and performed performance evaluation. The answers from an on-site gas multisensor device in an Italian city were included in the dataset. The findings from the dataset were shown to accurately model and predict environmental factors affecting air quality (e.g., air temperature, humidity, indium oxide, tin oxide, NO_x, NO₂, etc.) using real-world air quality data. The experiments were repeated by optimizing the relevant machine learning methods with PSO. PSO is a metaheuristic optimization method widely used in feature selection and feature extraction processes. The metrics MAE, MSE, RMSE, and R², commonly used to evaluate regression algorithms, were utilized to assess the models’ performances. Particle swarm optimization-based support vector regression performed best, with MAE, MSE, RMSE, and R² values of 0.071, 0.015, 0.122, and 0.999, respectively. In addition, Shapley additive explanations (SHAP) analysis was performed to show which feature of the PSO-based SVR model was practical and to what extent. The results show that the proposed model successfully predicts air quality. Full article

The skeletal muscle of cattle is the main component of their muscular system, responsible for supporting and movement functions. However, there are still many unknown areas regarding the ranking of the importance of different types of cell populations within it. This study conducted in-depth research and made a series of significant findings. First, we trained 15 bovine skeletal muscle models and selected the best-performing model as the initial model. Based on the SHAP (Shapley Additive exPlanations) analysis of this initial model, we obtained the SHAP values of 476 important genes. Using the contributions of these 476 genes, we reconstructed a 476-gene SHAP value matrix, and relying solely on the interactions among these 476 genes, successfully mapped the single-cell atlas of bovine skeletal muscle. After retraining the model and further interpretation, we found that Myofiber cells are the most representative cell type in bovine skeletal muscle, followed by neutrophils. By determining the key genes of each cell type through SHAP values, we conducted analyses on the correlations among key genes and between cells for Myofiber cells, revealing the critical role these genes play in muscle growth and development. Further, by using protein language models, we performed cross-species comparisons between cattle and pigs, deepening our understanding of Myofiber cells as key cells in skeletal muscle, and exploring the common regulatory mechanisms of muscle development across species. Full article

Laminated composites display exceptional weight-saving abilities that make them suited to advanced applications in aerospace, automobile, civil, and marine industries. However, the orthotropic nature of laminated composites means that they possess several damage modes that can lead to catastrophic failure. Therefore, machine learning-based Structural Health Monitoring (SHM) techniques have been used for damage detection. While Lamb waves have shown significant potential in the SHM of laminated composites, most of these techniques are focused on imaging-based methods and are limited to damage detection. Therefore, this study aims to localize the damage in laminated composites without the use of imaging methods, thus improving the computational efficiency of the proposed approach. Moreover, the machine learning models are generally black-box in nature, with no transparency of the reason for their decision making. Thus, this study also proposes the use of Shapley Additive Explanations (SHAP) to identify the important feature to localize the damage in laminated composites. The proposed approach is validated by the experimental simulation of the damage at nine different locations of a composite laminate. Multi-feature extraction is carried out by first applying the Hilbert transform on the envelope signal followed by statistical feature analysis. This study compares raw signal features, Hilbert transform features, and multi-feature extraction from the Hilbert transform to demonstrate the effectiveness of the proposed approach. The results demonstrate the effectiveness of an explainable K-Nearest Neighbor (KNN) model in locating the damage, with an $R^2$ value of 0.96, a Mean Square Error (MSE) value of 10.29, and a Mean Absolute Error (MAE) value of 0.5. Full article

Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of human activities and climate change. This study investigates the performance of deep learning models, particularly the Transformer model, as there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, a commonly used indicator of phytoplankton biomass and a proxy for HAB occurrences, is used as the target variable. We consider multiple influencing parameters—including physical, chemical, and biological water quality monitoring data from multiple stations located west of Lake Erie—and employ SHapley Additive exPlanations (SHAP) values as an explainable artificial intelligence (XAI) tool to identify key input features affecting HABs. Our findings highlight the superiority of deep learning models, especially the Transformer, in capturing the complex dynamics of water quality parameters and providing actionable insights for ecological management. The SHAP analysis identifies Particulate Organic Carbon, Particulate Organic Nitrogen, and total phosphorus as critical factors influencing HAB predictions. This study contributes to the development of advanced predictive models for HABs, aiding in early detection and proactive management strategies. Full article

The benefits of Patient Blood Management can vary depending on a patient’s risk profile for requiring a blood transfusion. The objective of this study is to develop and analyse machine learning models that can identify patients at risk of requiring red blood cell transfusion. This retrospective cohort study was conducted at a tertiary northern Portuguese hospital between 2018 and 2023. Two machine learning algorithms, extreme gradient boosting and neural networks, were employed due to their efficiency in handling complex feature interactions. Shapley additive explanations values were analysed to assess the contribution of each feature to the predictions generated by the models. The neural network achieved an accuracy of 0.735 and an area under the receiver operating characteristic curve of 0.798 (95% CI 0.747 to 0.849). The extreme gradient boosting model achieved an accuracy of 0.700 and an area under the receiver operating characteristic curve of 0.762 (95% CI 0.707 to 0.817). An analysis of Shapley additive explanations values revealed that the most important variable was preoperative haemoglobin levels, which can be optimised through the Patient Blood Management approach. These machine learning models demonstrate the potential to improve the accuracy of transfusion prediction at hospital admission, despite the absence of key variables such as surgeon identity and anaemia diagnosis. Full article

Landslide dams, formed by natural disasters or human activities, pose significant challenges for lifespan prediction, which is crucial for effective water conservancy management and disaster prevention. This study proposes a hybrid CNN–Transformer model optimized using the Improved Black-Winged Kite Algorithm (IBKA) aimed at improving the accuracy of landslide dam lifespan prediction by combining local feature extraction with global dependency modeling. The model integrates CNN’s local feature extraction with Transformer’s global modeling capabilities, effectively capturing the nonlinear dynamics of key parameters affecting landslide dam lifespan. The IBKA ensures optimal parameter tuning, which enhances the model’s adaptability and generalization, especially when dealing with small-sample datasets. Experiments utilizing multi-source heterogeneous datasets compare the proposed model with traditional machine learning and deep-learning approaches, including LightGBM, MLP, SVR, CNN–Transformer, and BKA–CNN–Transformer. The results show that the IBKA–CNN–Transformer achieves R² values of 0.99 on training data and 0.98 on testing data, surpassing the baseline methods. Moreover, SHapley Additive exPlanations analysis quantifies the influence of critical features such as dam length, reservoir capacity, and upstream catchment area on lifespan prediction, improving model interpretability. This approach not only provides scientific insights for risk assessment and decision making in landslide dam management but also demonstrates the potential of deep learning and optimization algorithms in broader geological disaster management applications. Full article

Flight Operations Quality Assurance (FOQA) is an internationally recognized solution to ensure the safety of civil aircraft flights based on Quick Access Recorder (QAR) data. The traditional approach to anomaly detection in civil aviation is to detect the over-limit values of monitoring parameters for each monitoring event based on the standards issued by civil aviation authorities. Usually, for each anomaly detection operation routine, this only works for one monitoring event. Furthermore, the causal analyses for the detected anomaly events are based on the relevant worker’s expertise. In order to improve the efficiency of FOQA, this paper proposes an automated anomaly detection and causal analysis method called $\mathsf{MAD}\text{-}\mathsf{XFP}$. Due to the unique industry characteristics of QAR data and the requirements of FOQA, feature engineering and hyper-parameter optimization techniques are utilized to enhance the machine learning model. The proposed method can monitor multiple events in one routine and provide a causal analysis. In the causal analysis process, the Shapley additive interpretation method is applied to produce analysis report for detected anomalies. Experimental evaluations are conducted on real civil aviation datasets. The experimental results show that the proposed method can efficiently and automatically detect different abnormal events with high precision in the approach phase and produce preliminary causal analysis. Full article

Large-scale and long-term landslide susceptibility assessments are crucial for revealing the patterns of landslide risk variation and for guiding the formulation of disaster prevention and mitigation policies at the national level. This study, through the establishment of a global dynamic landslide susceptibility model, uses the multi-dimensional analysis strategy and studies the development trend of China’s large-scale landslide susceptibility. First, a global landslide dataset consisting of 8023 large-scale landslide events triggered by rainfall and earthquakes between 2001 and 2020 was constructed based on the GEE (Google Earth Engine) platform. Secondly, a global dynamic landslide susceptibility model was developed using the ResNet18 (18-layer residual neural network) DL (deep learning) framework, incorporating both dynamic and static LCFs (landslide conditioning factors). The model was utilized to generate sequential large-scale landslide susceptibility maps for China from 2001 to 2022. Finally, the MK (Mann–Kendall) test was used to investigate the change trends in the large-scale landslide susceptibility of China. The results of the study are as follows. (1) The ResNet18 model outperformed SVMs (support vector machines) and CNNs (convolutional neural networks), with an AUC value of 0.9362. (2) SHAP (Shapley Additive Explanations) analyses revealed that precipitation played an important factor in the occurrence of landslides in China. In addition, profile curvature, NDVI, and distance to faults are thought to have a significant impact on landslide susceptibility. (3) The large-scale landslide susceptibility trends in China are complex and varied. Particular emphasis should be placed on Southwest China, including Chongqing, Guizhou, and Sichuan, which exhibit high landslide susceptibility and notable upward trends, and also consider Northwest China, including Shaanxi and Shanxi, which have high susceptibility but decreasing trends. These results provide valuable insights for disaster prevention and mitigation in China. Full article

This study introduces an innovative machine learning method to model the spatial variation of land surface temperature (LST) with a focus on the urban center of Da Nang, Vietnam. Light Gradient Boosting Machine (LightGBM), support vector machine, random forest, and Deep Neural Network are employed to establish functional relationships between urban LST and its influencing factors. The machine learning approaches are trained and validated using remote sensing data from 2014, 2019, and 2024. Various explanatory variables representing topographical and spatial characteristics, as well as urban landscapes, are used. Experimental results show that LightGBM outperforms other benchmark methods. In addition, Shapley Additive Explanations are utilized to clarify the impact of the factors affecting LST. The analysis outcomes indicate that while the importance of these variables changes over time, urban density and greenspace density consistently emerge as the most influential factors. LightGBM attained R² values of 0.85, 0.92, and 0.91 for the years 2014, 2019, and 2024, respectively. The findings of this work can be helpful for deeper understanding of urban heat stress dynamics and facilitate urban planning. Full article