The rapid growth of data has led to a significant increase in unstructured data, such as text, audio, and images, which dominate modern information processing. However, the complexity of unstructured data presents cha...
详细信息
The perception of offensive language varies based on cultural, social, and individual perspectives. With the spread of social media, there has been an increase in offensive content online, necessitating advanced solut...
详细信息
Requirements engineering focuses on eliciting, specifying, transforming and validating user and system requirements correctly and efficiently. Transforming user requirements to system requirements is a critical step i...
详细信息
Requirements engineering focuses on eliciting, specifying, transforming and validating user and system requirements correctly and efficiently. Transforming user requirements to system requirements is a critical step in this process. It is a challenging because the high-level intentions of users often lack the detailed information to help specify system requirements. In practice, the successful transformation from user requirements to system requirements is labor-intensive, which requires the sophisticated human efforts of domain experts and developers for information processing and supplementation. It is desirable to have a method for automatically transforming user requirements into system requirements. In this paper, we propose an approach iStar2UML that can automatically transform the user requirements of iStar into the system requirements specified by UML models. iStar is a well-known goal-oriented model for eliciting and specifying user requirements;it concentrates on analyzing intentions and social dependencies of stakeholders. Unified Modeling Language (UML) is a de facto standard for object-oriented system requirements modeling and design. We evaluate the proposed approach through five case studies. The results indicate that 82.9% of UML models were successfully generated from iStar models and confirmed by domain experts. Additionally, the proposed transformation approach reduced transformation errors by an average of 11.7% and time costs by 21.4% compared to a fully manual approach. Overall, the results suggest the approach is effective, though further validation is necessary. The proposed approach can be extended and applied for the requirements engineering processes in the software industry.
This study aims to revolutionize software defect prediction by leveraging deep learning (DL) techniques, specifically focusing on Convolutional Neural Networks (CNN) and Stack Sparse Autoencoders (SSAE). The research ...
详细信息
Can artists be recognized from the way they render certain materials, such as fabric, skin, or hair? In this paper, we study this problem with a focus on recognizing works by Rembrandt, Van Dyck, and other Dutch and F...
详细信息
作者：
Ma, XutongYan, JiweiYan, JunZhang, JianChinese Acad Sci
Key Lab Syst Software CAS Ins Software Beijing Peoples R China Chinese Acad Sci
State Key Lab Comp Sci Ins Software Beijing Peoples R China Chinese Acad Sci
Tech Ctr Software Engn Ins Software Beijing Peoples R China Chinese Acad Sci
Univ Chinese Acad Sci Key Lab Syst Software CAS Inst Software Beijing Peoples R China Chinese Acad Sci
Univ Chinese Acad Sci State Key Lab Comp Sci Inst Software Beijing Peoples R China
The widely-used Compiler-Based Tools CRT), such as static analyzers, process input source code using data structures inside a compiler. CBTs can he invoked together with compilers by injecting the compilation process....
详细信息
ISBN:
(纸本)9798400706127
The widely-used Compiler-Based Tools CRT), such as static analyzers, process input source code using data structures inside a compiler. CBTs can he invoked together with compilers by injecting the compilation process. However, it is seldom the best practice for the inconvenience of running various CBTs, the unexpected failures due to interference with compilers, and the efficiency degradation under compilation dependencies. To fill this gap, we propose Panda, an efficient scheduler for C/C++ CBTs. It executes various CBTs in a compilation-independent manner to avoid mutual interference with the build system, and parallelizes the process based on an estimated makespan to improve the execution efficiency. 'the assessment indicates that Panda can reduce the total execution time by 19%-47;'t, compared with compilation-coupled execution, with an average 39.03x-52.15x speedup with 64 parallel workers.
Training convolutional neural networks (CNNs) for semi-semantic segmentation in remote sensing images is difficult due to the substantial amount of labelled data required. The scarcity of dense pixel-level annotations...
详细信息
Recent research highlights the advantages of leveraging complementary strengths of both human expert and model in decision-making processes. Learning to Defer(L2D) is proposed to build a system consisting of both and ...
详细信息
Opinion dynamics (OD) models simulate the evolution of personal opinions using computer science, social dynamics, physics, and complexity science tools on social networks. However, current opinion dynamics models main...
详细信息
Opinion dynamics (OD) models simulate the evolution of personal opinions using computer science, social dynamics, physics, and complexity science tools on social networks. However, current opinion dynamics models mainly utilize agent -based models to simulate user interactions but still need to leverage large-scale data fully. Social networks typically involve a vast number of users and information, making it difficult for models to capture the complex interactions in real social networks. Additionally, many models overlook the specific mechanisms of user interactions, such as how network individuals influence and interact with one another, resulting in inaccuracies in modeling individual opinion evolution. This paper proposes a novel approach that integrates the probabilistic bounded confidence model (PBC) with deep learning, i.e., Neural Probabilistic Bounded Confidence (NPBC), to tackle these challenges. The NPBC model adopts an attention network, a long short-term memory (LSTM) network, and a feedforward neural network to approximate the evolution of individual opinions within networks. It satisfies the data approximation and the users' opinion update rule that conforms to the PBC model. This model enhances the understanding of opinion dynamics, helping to develop effective strategies for opinion guidance in social networks. Finally, the proposed NPBC model is evaluated on three synthetic and Twitter datasets. The results demonstrate that the proposed NPBC model performs better than the six baseline methods in predicting user opinions. Compared to baseline models, the model's accuracy (ACC) and comprehensive evaluation (F1) scores improve by up to 18% and 7%, respectively.
This paper proposes an innovative decision support system based on sentiment analysis, specifically designed for the transportation sector. The system employs an aspect-based sentiment analysis approach, which accurat...
详细信息
暂无评论