CNN-BPSO approach to Select Optimal Values of CNN Parameters for Software Requirements Classification

• Published in: 2020 IEEE 17th India Council International Conference (INDICON) pp. 1 - 6
• Main Authors: Bisi, Manjubala, Keskar, Kirti
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10-12-2020
• Subjects: binary particle swarm optimization; convolutional neural network; Data models; Encyclopedias; Internet; Numerical models; Particle swarm optimization; Predictive models; Software; Software requirements classification
• ISSN: 2325-9418
• DOI: 10.1109/INDICON49873.2020.9342381

Software requirement analysis plays a vital role in Software Development Life Cycle (SDLC). Users requests are transformed into structured software requirements. It is required to know the class of requirements that each request belongs to. Manual classification of these requirements is time consuming . In this work, Convolutional Neural Network (CNN) model is proposed to classify software requirements into functional and non functional. The performance of CNN is affected by model architecture, embedding input word vectors, filter region size and number of filters. In this work, Binary particle swarm optimization (BPSO) is used to optimize the above parameters of CNN (CNN-BPSO) to improve the performance of CNN for software requirements classification. The proposed model is evaluated on PROMISE corpus data set which contains a set of functional and non-functional requirements. The experimental results of proposed CNN-BPSO model is able to provide better prediction accuracy than CNN model.