Universities across China have made great progress in the construction of smart campus with the rapid deployment of Internet of Things (IoT). But at the same time, it also exposed some problems, such as the lack of theoretical guidance, the lack of smart campus function design, the lack of overall planning and design. Based on the six domain model of IoT, this paper designs an architecture with the overall construction of smart campus as the core. The smart campus is divided into six functional domains. The information and function description of each domain are given. It provides reference for the structure design of smart campus system and intelligent solutions for the management of the school.
Requirements classification is a significant task for requirements engineering, which is timeconsuming and challenging. The traditional requirements classification models usually rely on manual preprocessing and have poor generalization capability. Moreover, these traditional models ignore the sentence structure and syntactic information in requirements. To address these problems, we propose an automatic requirements classification based BERT and graph attention network (GAT), called DBGAT. We construct dependency parse trees and then utilize the GAT for mining the implicit structure feature and syntactic feature of requirements. In addition, we introduce BERT to improve the generalization ability of the model. Experimental results of the PROMISE datasets demonstrate that our proposed DBGAT significantly outperforms existing state-of-the-art methods. Moreover, we investigate the impact of graph construction methods on non-functional requirements classification. DBGAT achieved the best classification results on both seen (F1-scores of up to 91%) and unseen projects (F1-scores of up to 88%), further demonstrating the strong generalization ability.
Software size is a significant input for software cost estimation, and the implementation of software size estimation dramatically affects the results and efficiency of cost estimation. Traditionally, the software size estimation is implemented by strictly trained experts and is more labor-intensive for large software projects, which is relatively expensive and inefficient. Function Point Analysis is a widely used method for software size estimation, supported by several international standards. We propose a structured and automated function point extraction method based on event extraction in natural language processing to address the problem of complex and inefficient manual recognition for function point recognition. This approach has been validated in 10 industrial cases. Experimental results show that our method can identify more than 70% of the function points, which significantly improves the efficiency of Function Point Analysis implementation. This paper could be a guide on the application of artificial intelligence techniques to software cost estimation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.