Purpose: This research paper proposes an automated approach for categorizing bug reports as security-related bugs (SRBs) or non-security-related bug reports (NSBRs) using machine learning techniques and software vulnerability information. The purpose of this paper is to address the challenges associated with identifying SRBs manually and provide an effective automated solution to ensure that potential security risks are identified and addressed promptly. Methods: The proposed approach leverages software vulnerability information from authorized sources such as Common Weakness Enumeration (CWE) and manually collected security-related keywords to generate a list of security keywords. The authors use machine learning techniques and performance measures such as F1, false positive rate (FPR), and area under the curve (AUC), Balance, Accuracy to evaluate the effectiveness of the proposed approach. Statistical non-parametric tests, namely, Friedman test and the Kruskal–Wallis test, are conducted to compare the performance of different classifiers. Results: The results of the paper indicate that XGBoost outperformed other classifiers in building bug prediction models. The proposed approach offers significant benefits over the traditional manual extraction of SRBs from large datasets using security-related keywords. Conclusion: The paper concludes that automating the process of identifying SRBs is essential to ensure that potential security risks are identified and addressed promptly. The proposed approach provides an effective solution to the problem of identifying SRBs using machine learning techniques and software vulnerability information. The results of the paper highlight the importance of automating the process of identifying SRBs to ensure the security of software systems.

The field of Library Information Systems (LIS) has transformed with the rise of Artificial Intelligence (AI), enhancing library operations, services, and user experiences. AI improves user satisfaction by streamlining access to resources and providing librarians with tools for collection management, information retrieval, and data-driven decision-making. It enables analysis of user behavior and trends, optimizing resource allocation and collection development. By leveraging AI to assess circulation data and usage patterns, librarians can better anticipate user needs and future trends. This study examines recent advancements in AI integration within LIS over the past five years, focusing on the methodologies, tools, and algorithms used. Through a systematic literature review, the study identifies key trends, challenges, and examples of AI applications in LIS, providing insights and recommendations for future research and implementation.

In this paper, we address the task of solving proportional analogies between sentences in a generative manner. To this end, we use pre-trained word or sentence embedding models or fine-tune several pre-trained language models. Experiments on analogies between short sentences show that fine-tuning GPT-2 achieves the best performance, while combining a word embedding model with its vector-to-sequence decoder delivers competitive accuracy. However, the increased sizes of large-scale language models might not be worth the slight increase in performance observed when compared with lightweight models to simple analogy tasks. To extend this, we develop a data pipeline for collecting semantico-formal analogies between long sentences, spotting parallel associations beyond individual words. We create a complex set of analogies, each validated with evidence of relational matches on underlying concepts. Comparative analyses of three language models demonstrate that the autoregressive framework is particularly effective at learning analogy structures when sequences are long.

Graph Edit Distance (GED) computation is a fundamental yet NP-hard problem in graph theory that quantifies the structural dissimilarity between graphs through a series of edit operations. Despite its significance in fields like bioinformatics, cheminformatics, and social network analysis, the computational complexity of exact GED calculation has driven the development of heuristic and approximate methods. This paper proposes a novel approach leveraging Graph Neural Networks to predict GED efficiently. By capturing both local and global graph features through advanced embedding techniques and integrating the Weisfeiler–Lehman graph kernel, our method achieves high accuracy in estimating GED values. Extensive experiments on datasets such as AIDS, Linux, and IMDB demonstrate that our approach outperforms existing methods in terms of mean absolute error (MAE) and computational feasibility. The proposed framework not only enhances the scalability and precision of GED computation, but also provides a robust tool for graph dissimilarity assessments in various application domains.

This study presents a comparative analysis of transformer models for text classification, utilizing a hybrid approach that integrates rule-based regular expressions with fine-tuned neural network models. Initially, regular expressions are employed to annotate sentences in a cost-effective manner, providing an efficient alternative to manual labeling. The annotated dataset, comprising around 33,000 instances across three classes (Reminder, Scheduled Activity, General) and also restructured into two classes (Reminder and General) by merging “Scheduled Activity” with “Reminder”, is then used to fine-tune various transformer models, including DistilBERT, BERT, RoBERTa, ALBERT, Electra, Ernie 2.0, XLNet, and GPT-2. Our methodology involves freezing all layers except the final one during fine-tuning, allowing the models to learn nuanced linguistic patterns while mitigating overfitting. Results reveal that DistilBERT, despite its smaller size (66 million parameters), outperforms larger models such as BERT and GPT-2 in terms of accuracy, precision, recall, and F1-score. Likewise, we demonstrated that the proposed method can work better than generative AI large language models for both zero-shot and one-shot learning, namely GPT-3.5, GPT-4, GPT-4o and LLaMA-3 70B. This efficiency is attributed to the distillation process that retains essential features while reducing computational demands. Notably, DistilBERT achieved an overall accuracy of 0.86, significantly surpassing BERT’s 0.55, GPT-2’s 0.36, XLNet’s 0.51, Ernie 2.0’s 0.72, Electra’s 0.74, ALBERT’s 0.72, and RoBERTa’s 0.71. The study highlights the importance of model size and architecture in achieving optimal performance, especially in resource-constrained scenarios. This investigation underscores the efficacy of combining rule-based methods with advanced transformer models for text annotation, demonstrating that a balanced approach leveraging both handcrafted rules and learned representations can generalize better than relying solely on one technique. The proposed hybrid method offers a robust and adaptable solution for sentence annotation pipelines, enhancing performance in diverse natural language processing applications with limited labeled data. Code is available at https://github.com/arafet/Text-annotation-using-rule-based-method-and-Transformers .

Today, due to the problem of environmental pollution, water, and other factors have caused many dangerous diseases, including cancer. According to recent statistics, breast cancer is one of the leading diseases in women, and this disease tends to increase more and more. To detect and diagnose the disease, doctors perform many examinations: self-examination, clinical examination, X-ray, ultrasound screening, etc., in which X-ray is a highly effective method. This study proposes an approach to detecting and classifying breast cancer on an X-ray dataset using a refined Vision Transformer (ViT), ViT-B32. The considered dataset contains about 7000 X-ray images from patients aged 27 to 90, labeled as malignant, benign, or normal. As presented in scenarios, the study yielded positive results, with 91% to 94% in ACC and F1-score metrics. Furthermore, it has shown that the results obtained for breast cancer detection on X-ray images using the fine-tuned ViT architecture outperformed CNN models such as VGG16, MobileNet, Xception, ResNet50, and some state-of-the-art approaches.

Mental health (MH) assessment and prediction have become critical areas of focus in healthcare, leveraging developments in natural language processing (NLP). Recent advancements in machine learning have facilitated the exploration of predictive models for MH based on user-generated comments that overlooked the integration of emotional attention mechanisms. The methods often struggle with contextual nuances and emotional subtleties, leading to suboptimal predictions. The prevailing challenge lies in accurately understanding the emotional context embedded within textual comments, which is crucial for effective prediction and intervention. In this research, we introduce a novel approach employing contextual emotional transformer-based models (CETM) for comment analysis in MH case prediction. CETM leverages state-of-the-art transformer architectures enhanced with contextual embedding layers and emotional attention mechanisms for MH case prediction. By incorporating contextual information and emotional cues, CETM captures the underlying emotional states and MH indicators expressed in user comments. Through extensive experimentation and evaluation, both Roberta and bidirectional encoder representations from transformers (BERT) models exhibited enhanced accuracy, precision, recall, and F1 scores compared to their counterparts lacking emotional attention. Notably, the Roberta model attained a greater accuracy of 94.5% when matched to BERT’s 87.6% when emotional attention was employed. Hence, by incorporating emotional context into the predictive model, we achieved significant improvements, which offers promising avenues for more precise and personalized MH interventions.

Medical imaging is considered the first step in the examination for diagnosing kidney disease. However, the recent increase in kidney stone cases has put a remarkable burden on the whole medical diagnosis system. This problem causes a demand of an automatic kidney stone detection model to decrease the weight for medical imaging phase. Moreover, X-ray imaging, which is the current most popular medical imaging technique, is struggling with false positives, which is caused by low quality, making the diagnosis more challenging. Due to the two main problems above, this study is carried out with two contributions. First, fusing different attention modules to YOLOv7 architecture that shall bring higher performance of kidney stone detection task. Second, proposing the use of super resolution (SR) models that shall address the problem of low quality in X-ray image. As a result, the proposed YOLOv7 with attention modules easily outperforms the YOLOv7 baseline in detection performance, the highest accuracy model belongs to convolution block attention module attached with YOLOv7, which reaches 91.2% mAP50. When SR models are applied to upsample X-ray images, these SR X-ray images enable the proposed attention-based models to improve the precision and sensitivity considerably, with the highest precision reaching 97.3% and highest sensitivity hitting a peak at 91.7%. Consequently, our methods are proposed to address current issues of kidney stone diagnosis and contribute another aspect of X-ray image enhancement.

This paper studies a classification model dedicated to dispersed data, employing the k-nearest neighbors method as a base classifier and a Radial Basis Function (RBF) network as a fusion method. Focusing on classifying objects described by different attributes, the study systematically reduces common objects in local tables to assess the robustness of the model. Surprisingly, the proposed approach shows resilience in reducing common objects without significantly affecting key metrics such as F-measure, balanced accuracy and overall accuracy. Moreover, the studied model performs better on balanced data. This research contributes valuable insights into dispersed data classification, demonstrating the model’s effectiveness in handling diverse objects and attributes. The findings have implications for fields reliant on dispersed data storage, such as healthcare, banking, and surveillance, showcasing the model’s potential for real-world applications.