Spam SMS Text Classification Using a Scalable Quantum Convolutional Neural Network

Description

SMSTSQCNN is an efficient deep learning framework for automatic classification of spam and legitimate SMS messages. The model employs a Scalable Quantum Convolutional Neural Network (SQCNN) to capture semantic patterns and contextual dependencies within short text messages. By leveraging quantum-inspired convolutional feature extraction, SMSTSQCNN improves discrimination between spam and ham messages, even in the presence of noisy or overlapping textual cues. This framework provides a reliable AI-driven solution for intelligent SMS filtering and communication security.

Input

The input to the proposed SMSTSQCNN model consists of raw SMS text messages:

1. SMS message content (text)

Output

·Predicted SMS Label

oNot Spam (0) – Legitimate message

oSpam (1) – Spam message

Tags

#SMSTSQCNN #SpamDetection #SMSClassification #QuantumCNN #TextClassification #NLP #DeepLearning #MachineLearning #AIinSecurity #CyberSecurity #IntelligentSystems #MessageFiltering #NaturalLanguageProcessing #DataScience #TechInnovation #AIModels #DigitalCommunication

References:

1,Cong, I., Choi, S. and Lukin, M.D., 2019. Quantum convolutional neural networks. Nature Physics, 15(12), pp.1273-1278.

2,Almeida, T.A., Hidalgo, J.M.G. and Yamakami, A., 2011, September. Contributions to the study of SMS spam filtering: new collection and results. In Proceedings of the 11th ACM symposium on Document engineering (pp. 259-262).

3,Kim, Y., 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.