Stock price forecasting remains a persistent challenge in time series analysis due to complex inter-stock relationships and dynamic textual signals such as financial news. While Graph Neural Networks (GNNs) can model relational structures, they often struggle with capturing higher-order dependencies and are sensitive to noise. Moreover, sentiment signals are typically aggregated using fixed time windows, which may introduce temporal bias. To address these issues, we propose DASF-Net (Diffusion-Aware Sentiment Fusion Network), a multimodal framework that integrates structural and textual information for robust prediction. DASF-Net leverages diffusion processes over two complementary financial graphs—one based on industry relationships, the other on fundamental indicators—to learn richer stock representations. Simultaneously, sentiment embeddings extracted from financial news using FinBERT are aggregated over an empirically optimized window to preserve temporal relevance. These modalities are fused via a multi-head attention mechanism and passed to a temporal forecasting module. DASF-Net integrates daily stock prices and news sentiment, using a 3-day sentiment aggregation window, to forecast stock prices over daily horizons (1–3 days). Experiments on 12 large-cap S&P 500 stocks over four years demonstrate that DASF-Net outperforms competitive baselines, achieving up to 91.6% relative reduction in Mean Squared Error (MSE). Results highlight the effectiveness of combining graph diffusion and sentiment-aware features for improved financial forecasting.
Software defect prediction aims to automatically determine the most likely location of defective program elements (i.e., statement, method, class, module etc.). Previous studies for software defect prediction mainly focus on exploring designing features such as source code complexity, object oriented design metrics etc. to classify program elements into two categories: (i) defective and (ii) non-defective. Although these approaches have obtained promising results, there exists two significant challenges in this research field: (i) removing irrelevant and redundant information from designing structures ; (ii) reducing the impact of skewed data distribution on learning models. In this paper, we aim to address these two issues by firstly applying kernel PCA to extract essential information from designing features and secondly proposing a deep neural network model which investigates the non-linear relationship among features. In order to mitigate the class imbalance, we apply a weighted loss function combined with a bootstrapping method to handle batch training mechanism of our model. We conducted some experiments to assess the performance of our proposed approach over NASA (with 10 projects) and PROMISE (with 34 projects) datasets. In order to leverage the efficiency of kernel PCA technique in software defect prediction, we compared it to some traditional feature selection approaches over a high-dimensional dataset ECLIPSE. The empirical results showed that our proposed method has outperformed these other state-of-the-art models by effectively predicting defective source files.
Automated software defect prediction aims to identify and estimate the likelihood of defects in software source code elements, seeking to enhance software quality while reducing testing costs. Previous research on software defect prediction primarily concentrated on investigating design-related features such as source code complexity and object-oriented design metrics for the purpose of classifying program elements into two categories: (i) defective and (ii) non-detective. Nevertheless, the majority of these studies have relied solely on hand-crafted software metrics, neglecting the valuable asset of source code instruction, which can play a pivotal role in detecting bugs. This study leverages the use of source code embedding techniques to extract essential information from program elements through a convolutional neural network. The likelihood of a source file element (e.g., class or method) being defective is established through the utilization of a fully connected network that incorporates both source code features and design-related attributes. Additionally, we explore specific imbalanced learning strategies to address the skewed defect data distribution issue. To assess the effectiveness of our proposed approach, we conducted experiments on the publicly available dataset, namely PROMISE. The empirical results consistently showcase the superior performance of our method, as it effectively predicts defective source files, outperforming other state-of-the-art models.
1 October 2024 in Journal of Science and Technology on Information security
Our world is becoming increasingly automated due to the application of deep learning/machine learning models to systems, but these systems are vulnerable to adversarial attacks, which create deceptive data to trick them. Without proper defenses, attackers can exploit deep learning systems in facial recognition, self-driving cars, and social media filters. Research on adversarial image generation and methods to against attacks is important. This paper proposes employing the ResNet architecture with adversarial training to against adversarial images. The model is tested on a Hybrid CIFAR-10 dataset, which is designed to improve robustness and accuracy by incorporating GAN-generated images. The proposed model achieves an accuracy of over 95%, which is better than three other state-of-the-art architectures VGG19_bn, ShuffleNetV2, and RepVGG_a2.