Explore the vast range of titles available.

Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community’s behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency–inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques.

Currently, complex scene classification strategies are limited to high-definition image scene sets, and low-quality scene sets are overlooked. Although a few studies have focused on artificially noisy images or specific image sets, none have involved actual low-resolution scene images. Therefore, designing classification models around practicality is of paramount importance. To solve the above problems, this paper proposes a two-stage classification optimization algorithm model based on MPSO, thus achieving high-precision classification of low-quality scene images. Firstly, to verify the rationality of the proposed model, three groups of internationally recognized scene datasets were used to conduct comparative experiments with the proposed model and 21 existing methods. It was found that the proposed model performs better, especially in the 15-scene dataset, with 1.54% higher accuracy than the best existing method ResNet-ELM. Secondly, to prove the necessity of the pre-reconstruction stage of the proposed model, the same classification architecture was used to conduct comparative experiments between the proposed reconstruction method and six existing preprocessing methods on the seven self-built low-quality news scene frames. The results show that the proposed model has a higher improvement rate for outdoor scenes. Finally, to test the application potential of the proposed model in outdoor environments, an adaptive test experiment was conducted on the two self-built scene sets affected by lighting and weather. The results indicate that the proposed model is suitable for weather-affected scene classification, with an average accuracy improvement of 1.42%.

Data imbalance is one of the most difficult problems in machine learning. The improved ensemble learning model is a promising solution to mitigate this challenge. In this paper, an improved multi-class imbalanced data classification framework is proposed by combining the Focal Loss with Boosting model (FL-Boosting). By addressing the confusion of the second-order derivation of Focal Loss in the traditional ensemble learning model, the proposed model achieves a more efficient and accurate classification of the imbalanced data. More specifically, a Highly Adaptive Focal Loss (HAFL) is proposed to ensure that the model maintains lasting attention to the minority samples, which could be combined with boosting model to build HAFL-Boosting to achieve better performance. The framework has the scalability to adapt to different situations according to typical ensemble learning algorithms such as LightGBM, XGBoost and CatBoost. In addition, to implement the application of the proposed framework on deep models, a two-stage classification method combining ConvNeXt with the improved boosting model is proposed, which could improve the recognition ability to high-dimensional imbalanced data. We evaluate the HAFL-Boosting and the two-stage class imbalance classification method by ablation experiments and benchmark experiments, which demonstrated that the proposed methods obviously improved the scores on several evaluation indexes. The comparative experiments with the latest classification models show that the proposed methods could achieve leading performance from multiple perspectives.

Background: Skin cancer is the most common cancer worldwide, with melanoma being the deadliest type, though it accounts for less than 5% of cases. Traditional skin cancer detection methods are effective but are often costly and time-consuming. Recent advances in artificial intelligence have improved skin cancer diagnosis by helping dermatologists identify suspicious lesions. Methods: The study used datasets from two ethnic groups, sourced from the ISIC platform and CSMU Hospital, to develop an AI diagnostic model. Eight pre-trained models, including convolutional neural networks and vision transformers, were fine-tuned. The three best-performing models were combined into an ensemble model, which underwent multiple random experiments to ensure stability. To improve diagnostic accuracy and reduce false negatives, a two-stage classification strategy was employed: a three-class model for initial classification, followed by a binary model for secondary prediction of benign cases. Results: In the ISIC dataset, the false negative rate for malignant lesions was significantly reduced, and the number of malignant cases misclassified as benign dropped from 124 to 45. In the CSMUH dataset, false negatives for malignant cases were completely eliminated, reducing the number of misclassified malignant cases to zero, resulting in a notable improvement in diagnostic precision and a reduction in the false negative rate. Conclusions: Through the proposed method, the study demonstrated clear success in both datasets. First, a three-class AI model can assist doctors in distinguishing between melanoma patients who require urgent treatment, non-melanoma skin cancer patients who can be treated later, and benign cases that do not require intervention. Subsequently, a two-stage classification strategy effectively reduces false negatives in malignant lesions. These findings highlight the potential of AI technology in skin cancer diagnosis, particularly in resource-limited medical settings, where it could become a valuable clinical tool to improve diagnostic accuracy, reduce skin cancer mortality, and reduce healthcare costs.

Predictive maintenance (PdM) is vital for ensuring the reliability, safety, and cost efficiency of heavy-duty vehicle fleets. However, real-world sensor data are often highly imbalanced, noisy, and temporally irregular, posing significant challenges to model robustness and deployment. Using multivariate time-series data from Scania trucks, this study proposes a novel PdM framework that integrates efficient feature summarization with cost-sensitive hierarchical classification. First, the proposed last_k_summary method transforms recent operational records into compact statistical and trend-based descriptors while preserving missingness, allowing LightGBM to leverage its inherent split rules without ad-hoc imputation. Then, a two-stage LightGBM framework is developed for fault detection and severity classification: Stage A performs safety-prioritized fault screening (normal vs. fault) with a false-negative-weighted objective, and Stage B refines the detected faults into four severity levels through a cascaded hierarchy of binary classifiers. Under the official cost matrix of the IDA Industrial Challenge, the framework achieves total misclassification costs of 36,113 (validation) and 36,314 (test), outperforming XGBoost and Bi-LSTM by 3.8%–13.5% while maintaining high recall for the safety-critical class (0.83 validation, 0.77 test). These results demonstrate that the proposed approach not only improves predictive accuracy but also provides a practical and deployable PdM solution that reduces maintenance cost, enhances fleet safety, and supports data-driven decision-making in industrial environments.

Credit risk assessment plays a crucial role in financial decision-making, but imbalanced datasets present significant challenges, leading to biased predictions and poor classification of defaulters. Traditional techniques such as under-sampling, over-sampling, and SMOTE aim to address this imbalance but suffer from issues like information loss, lack of diversity, and duplicated patterns. To address these issues, we propose a novel two-stage classification framework that integrates a Voting Classifier with Meta-Dynamic Ensemble Selection (Meta-DES). The first stage employs a voting classifier to make confident predictions while isolating ambiguous instances. The second stage applies Meta-DES to dynamically select the most competent classifiers based on meta-features and the region of competence. This approach enhances classification performance by refining uncertain predictions through meta-learning and leveraging ensemble techniques to improve robustness. Extensive experimentation on a real-world loan application dataset demonstrates that our approach significantly outperforms traditional machine learning models. Our method maintains reliable predictions as demonstrated by comprehensive performance evaluations. The proposed model achieves superior precision and recall, outperforming traditional classifiers. Experimental results highlight its balanced performance in distinguishing defaulters and non-defaulters, achieving an accuracy of 0.8332, with significantly improved F1 scores. Additionally, statistical validation using the McNemar test confirms the superiority of our approach over baseline models, with overwhelmingly significant results. By effectively reducing Type I and Type II errors, our approach enhances financial risk assessment and supports more reliable credit decision-making. The proposed methodology not only improves classification outcomes but also contributes to minimizing financial losses and optimizing lending strategies.

One of the challenges that arise when utilizing real-time reaction services, such as constructing deep learning models within the Internet of Medical Things (IoMT) infrastructure, is effectively balancing the computation load between the cloud and fog computing layers. This paper proposes a unified framework of offline training and online response to the healthcare professional. The framework gathers medical images from various heterogeneous IoMT devices and then arranges them into homogeneous locations in the cloud, using a stage-one classification stage (or offline training). Furthermore, the stage-two classification (or online response) is employed to detect the type of cancer for each homogeneous location containing the same image type within the cloud. To evaluate the framework, we conducted extensive experiments on six well-known cancer datasets of multiple types. The stage-one classification shows superior results of the error rates for the InceptionResNetV2 and DenseNet201 pre-trained transfer learning models of 0.33% and 0.43% with accuracy values of 99.67% and 99.57% respectively. In the stage-two classification, the results show different performances on each dataset. The point is that each dataset is organized separately which helps in studying the influence of pre-trained transfer learning models and improving their performance in the absence of intervention and bias in datasets.

Introduction: Sperm morphology is a fundamental parameter in the evaluation of male infertility, offering critical insights into reproductive health. However, traditional manual assessments under microscopy are limited by operator dependency and subjective interpretation caused by biological variation. To overcome these limitations, there is a need for accurate and fully automated classification systems. Objectives: This study aims to develop a two-stage, fully automated sperm morphology classification framework that can accurately identify a wide spectrum of abnormalities. The framework is designed to reduce subjectivity, minimize misclassification between visually similar categories, and provide more reliable diagnostic support in reproductive healthcare. Methods: A novel two-stage deep learning-based framework is proposed utilizing images from three staining-specific versions of a comprehensive 18-class dataset. In the first stage, sperm images are categorized into two principal groups: (1) head and neck region abnormalities, and (2) normal morphology together with tail-related abnormalities. In the second stage, a customized ensemble model—integrating four distinct deep learning architectures, including DeepMind’s NFNet-F4 and vision transformer (ViT) variants—is employed for detailed abnormality classification. Unlike conventional majority voting, a structured multi-stage voting strategy is introduced to enhance decision reliability. Results: The proposed framework consistently outperforms single-model baselines, achieving accuracies of 69.43%, 71.34%, and 68.41% across the three staining protocols. These results correspond to a statistically significant 4.38% improvement over prior approaches in the literature. Moreover, the two-stage system substantially reduces misclassification among visually similar categories, demonstrating enhanced ability to detect subtle morphological variations. Conclusions: The proposed two-stage, ensemble-based framework provides a robust and accurate solution for automated sperm morphology classification. By combining hierarchical classification with structured decision fusion, the method advances beyond traditional and single-model approaches, offering a reliable and scalable tool for clinical decision-making in male fertility assessment.

Algorithms are proposed to address the radar target detection problem of compressed sensing (CS) under the conditions of a low signal-to-noise ratio (SNR) and a low signal-to-clutter ratio (SCR) echo signal. The algorithms include a two-stage classification for radar targets based on compressive detection (CD) without signal reconstruction and a support vector data description (SVDD) one-class classifier. First, we present the sparsity of the echo signal in the distance dimension to design a measurement matrix for CD of the echo signal. Constant false alarm rate (CFAR) detection is performed directly on the CD echo signal to complete the first-order target classification. In simulations, the detection performance is similar to that of the traditional matched filtering algorithm, but the data rate is lower, and the necessary data storage space is reduced. Then, the power spectrum features are extracted from the data after the first-order classification and converted to the feature domain. The SVDD one-class classifier is introduced to train and classify the characteristic signals to complete the separation of the targets and the false alarms. Finally, the performance of the algorithm is verified by simulation. The number of false alarms is reduced, and the detection probability of the targets is improved.

This paper aims to identify the most effective strategy for incorporating feature selection (FS) into credit risk classification, employing three classifiers: Logistic regression (Logreg), Random Forests (RF), and Support Vector Machine (SVM) with the linear kernel through various embedded and wrapper strategies existing in the literature. We performed a comparative analysis on the German Credit dataset using three criteria: classification error rate, stability of selection, and calculation time. According to the Welsh t-test, RFE-RF (Recursive Feature Elimination for RF) outperformed RFE-SVM and penalized Logistic regression, with no significant difference in F1-score for RFE-SVM and suffers from the long-running computation. Conversely, RFE-SVM offers the best stability of 71% with a significantly shorter computation time. Furthermore, the paper intends to introduce a new classification of feature selection strategies in credit risk assessment in light of recent developments. Based on this new classification, a comparison with related literature reveals that the one-stage FS (RFE-RF and RFE-SVM) provides roughly the same accuracy as the two-stage FS and the two-stage classification model and, in some cases, outperforms.