Advancements in digital technologies make it easy to modify the content of digital images. Hence, ensuring digital images' integrity and authenticity is necessary to protect them against various attacks that manip...
详细信息
Statistical models, enhanced by deep learning techniques, have become pivotal in various predictive tasks, including financial forecasting. This paper addresses the challenge of predicting cryptocurrency prices, utili...
详细信息
Cloud computing (CC) is a cost-effective platform for users to store their data on the internet rather than investing in additional devices for storage. Data deduplication (DD) defines a process of eliminating redunda...
详细信息
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detecti...
详细信息
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.
Artificial intelligence (AI) has emerged as a powerful tool in computational biology, where it is being used to analyze large datasets to detect difficult biological patterns. This has enabled the design of new drug m...
详细信息
Crop yield Prediction based on environmental, soil, water, and crop parameters has been an active area of research in agriculture. Many studies have shown that these parameters can have a significant impact on crop yi...
详细信息
Maternal health during pregnancy is influenced by various factors that significantly impact pregnancy outcomes. This paper aims to highlight these critical factors, promote awareness, and advocate proactive self-care ...
详细信息
Recognizing the emotional content of Natural Language sentences can improve the way humans communicate with a computer system by enabling them to recognize and imitate emotional expressions. In this paper, deep learni...
详细信息
Wireless sensor networks (WSN) have seen immense use in everyday life, like health, battle-field administration, and disaster administration. Nodes inside WSN are more vulnerable to safety attacks like data replay and...
详细信息
Wireless sensor networks (WSN) have seen immense use in everyday life, like health, battle-field administration, and disaster administration. Nodes inside WSN are more vulnerable to safety attacks like data replay and eavesdropping attacks. Node capture attacks function as destructive attacks that let attackers physically seize sensor nodes, reconfigure the structures, and deploy new nodes. An efficient architecture consists of a number of protocols for safe key creation and node capture attack revocation. A pairwise key establishment addresses arbitrary inputs from the pair of nodes implicated for the secure key establishment. Thus, the detailed exploration of various attack models to enhance key management security is a critical research direction in WSN security. Our model approaches the node capture attack problem from an attacker's viewpoint. The proposed model discovers the optimal collection of nodes likely to be attacked for node capturing. Based on the optimization algorithm i.e., fruit fly, the proposed model identifies multiple objectives like the set of dominating nodes, the vulnerability in paths, traveling cost, node contribution, and dominant rank and computes the optimal set of nodes with higher destructiveness. This indicates that the suggested node capture model has significant performance in the aspect of the least cost and lower attacking rounds. In this proposed model, we present an improved fruit fly optimization based attacking model consisting of several objectives as node strength, node and key participation rank, dominant rank and cost for capturing nodes in the system. Our approach outperforms existing attack models like RA, MLA, MTA, MKA, FGA, FFOA, and MA in terms of largest traffic compromised, lowest total attacking rounds, key captured, and least energy cost. The results demonstrated that the proposed method attained a path compromise probability up to 91% and reduced the cost by 60% in a network size of 100 nodes. The deduction in th
In the era of digital transformation and increasing concerns regarding data privacy, the concept of Self-Sovereign Identity (SSI) has attained substantial recognization. SSI offers individuals greater control over the...
详细信息
暂无评论