Using NLP for Functional Size Measurement of IoT Devices
Salma Salem, Hassan Soubra · 2023
The Internet of Things (IoT) was born when embedded systems represented in edge devices were able to send and receive data back and forth via the Internet and process these data in real-time near the same physical environments they are deployed. Hence, enabling the existence of numerous smart applications and devices used in daily life. The ubiquity of IoT applications required means to measure software-provided functionality. Functional size measurement is a tool used for this purpose in addition to obtaining technical indicators early in the design phase. The Common Software Measurement International Consortium (COSMIC) method is an international standard for functional size measurement of a software. A study [?] has represented a tool to automatically retrieve source codes of IoT edge devices and measure their COSMIC functional size through analysing the code. Nevertheless, the tool was limited to certain Arduino libraries. In this paper, Natural language processing (NLP), a sub-field of Artificial intelligence that enables computers to process human language is integrated with the tool presented to analyse the source code. Hence, enabling the tool to measure the COSMIC functional size of any source code retrieved automatically. This paper presents an approach to modify the tool presented in [1] by using NLP to automatically analyse and measure the COSMIC functional size of source codes without being limited to a certain number of libraries.