1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Tracking of Hardware Development Schedule based on Software Effort Estimation
作者 張宏慶
Jang, Hung-Chin;Wu, Sin-Chun
貢獻者 資訊系
關鍵詞 software effort estimation; hardware development schedule tracking; project time management; machine learning; deep learning
日期 2022-10
上傳時間 16-Feb-2024 15:36:49 (UTC+8)
摘要 Accurately predicting the time required for tasks in the development process can effectively manage resources and costs, which is crucial in project management. In 1960, Farr [3] and Nelson [6] proposed the concept of software effort estimation. Early research focused on building standardized estimation models to estimate the number of hours worked to complete tasks through statistical regression analysis or expert rules of thumb. Later, machine learning and deep learning were used to train models to estimate working hours to replace traditional estimation methods. This study proposes that software effort estimation can be extended to the hardware development industry. We use machine learning and deep learning to estimate the time required for tasks in the hardware development process and then accurately manage the product development time. This research uses semantic analysis to extract the keywords of the problems in the development process through NLP and use them as features for afterward analysis. We compare the accuracy, MMRE, and PRED(25) of the four models of machine learning's decision tree, random forest, XGBoost, and deep learning's RNN model in estimating the time required for tasks. The experimental results show that the decision tree has higher accuracy than the other three models. This study proves that the software effort estimation technique can be applied to task tracking in the hardware development process.
關聯 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), IEEE Vancouver section, SMART Society, IEM, UEM
資料類型 conference
DOI https://doi.org/10.1109/IEMCON56893.2022.9946524
dc.contributor 資訊系
dc.creator (作者) 張宏慶
dc.creator (作者) Jang, Hung-Chin;Wu, Sin-Chun
dc.date (日期) 2022-10
dc.date.accessioned 16-Feb-2024 15:36:49 (UTC+8)-
dc.date.available 16-Feb-2024 15:36:49 (UTC+8)-
dc.date.issued (上傳時間) 16-Feb-2024 15:36:49 (UTC+8)-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/149879-
dc.description.abstract (摘要) Accurately predicting the time required for tasks in the development process can effectively manage resources and costs, which is crucial in project management. In 1960, Farr [3] and Nelson [6] proposed the concept of software effort estimation. Early research focused on building standardized estimation models to estimate the number of hours worked to complete tasks through statistical regression analysis or expert rules of thumb. Later, machine learning and deep learning were used to train models to estimate working hours to replace traditional estimation methods. This study proposes that software effort estimation can be extended to the hardware development industry. We use machine learning and deep learning to estimate the time required for tasks in the hardware development process and then accurately manage the product development time. This research uses semantic analysis to extract the keywords of the problems in the development process through NLP and use them as features for afterward analysis. We compare the accuracy, MMRE, and PRED(25) of the four models of machine learning's decision tree, random forest, XGBoost, and deep learning's RNN model in estimating the time required for tasks. The experimental results show that the decision tree has higher accuracy than the other three models. This study proves that the software effort estimation technique can be applied to task tracking in the hardware development process.
dc.format.extent 112 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), IEEE Vancouver section, SMART Society, IEM, UEM
dc.subject (關鍵詞) software effort estimation; hardware development schedule tracking; project time management; machine learning; deep learning
dc.title (題名) Tracking of Hardware Development Schedule based on Software Effort Estimation
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/IEMCON56893.2022.9946524
dc.doi.uri (DOI) https://doi.org/10.1109/IEMCON56893.2022.9946524