STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Mobile Computing, Communications & Mobile Networks Review Article

Design And Implementation Of A Multi-Modal Mobile Application Safety Analytics Utilizing Nlp

  1. Km Sandhya Marathwada Institute of Technology, Bulandshahr
  2. Navin Kumar Tyagi Marathwada Institute of Technology, Bulandshahr
  3. R. Prasad Hindustan College of Science & Technology, Mathura

Abstract

This study suggests a multi-modal mobile app safety analytics platform that uses natural language processing (NLP) to handle voice, text, and SOS messages. For effective intent recognition and decision-making, the platform processes all messages in a standard text or SOS flag format. Tokenization and normalization are used to process text communications, whereas noise reduction and text conversion are used to handle voice messages. For a quicker response, the SOS messages are processed without any intermediary processing. The platform's performance evaluation reveals a high accuracy rate of (>90%) for intent detection, 85–90% for speech recognition, 98% for text processing, and 92% for the entire system. It is appropriate for real-time mobile app operation due to its low response time (~1.2 s) for efficient operation. The platform works well to increase user safety. Future research can focus on enhancing performance in noisy settings and including an effective intent detection method for increased effectiveness.

Keywords

References (18)

  1. ABRO AA, TALPUR MSH, JUMANİ AK. Natural Language Processing Challenges and Issues: A Literature Review. Gazi University Journal of Science. 2023;36(4):1522-1536. doi:10.35378/gujs.1032517
  2. K. Sharifani, M. Amini, Y. Akbari, and J. A. Godarzi, “Operating machine learning across natural language processing techniques for improvement of fabricated news model,” International Journal of Science and Information System Research, vol. 12, no. 9, Oct. 2022.
  3. Shankar K, Prajwal SC, Kumar VG, Anusha P, Kameswar RCS, Prakashn SB. Women Safety App to Detect Danger And Prevent Automatically Using Machine Learning. Advances in Computer Science Research. 2024:1443-1452. doi:10.2991/978-94-6463-471-6_140
  4. Ganesan V. Machine Learning in Mobile Applications. International Journal of Computer Science and Mobile Computing. 2022;11(2):110-118. doi:10.47760/ijcsmc.2022.v11i02.013
  5. Reddy Bhimanapati VB, Jain S, Gopalakrishna Pandian PK. Security Testing for Mobile Applications Using AI and ML Algorithms. Journal of Quantum Science and Technology. 2024;1(2):44-58. doi:10.36676/jqst.v1.i2.15
  6. X. Meng, S. Li, M. M. Malik, and Q. Umer, “Machine-learning-based suitability prediction for mobile applications for kids,” Sustainability, vol. 14, no. 19, p. 12400, 2022, DOI: https://doi.org/10.3390/ su141912400
  7. Begum MA, Rajkumar BP, Labhade-Kumar N, Sankaradass V, Sathya C, Bhaskar B. AI and IoT based Mobile Application for Women Safety. 2025 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI). 2025:1-6. doi:10.1109/icdsaai65575.2025.11011614
  8. Islam MR, Oliullah K, Kabir M, Rahman A, Mridha MF, Khan MF, et al. Machine learning-driven IoT device for women’s safety: a real-time sexual harassment prevention system. Multimedia Tools and Applications. 2024;84(23):27251-27280. doi:10.1007/s11042-024-20228-5
  9. P. M. Mah, I. Skalna, T. Pełech-Pilichowski, T. Derlecki, V. Mah, and K. Nyamka, “Enabling digital transformation and knowledge migration: The impact of NLP, AI, and ML in mobile applications,” 2024, doi:10.29119/1641-3466.2023.184.13.
  10. Hien DTT, Hau PV. Enhancing Web Application Security: A Deep Learning and NLP-based Approach for Accurate Attack Detection. Journal of Science and Technology on Information security. 2023:77-87. doi:10.54654/isj.v3i20.1008
  11. S. Salmi and L. Oughdir, “Automatic detection of safety requests in web and mobile applications using natural language processing techniques,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 3, pp. 3489–3497, 2024.
  12. Vallabhaneni R, Vaddadi SA, Somanathan Pillai SEV, Addula SR, Ananthan B. MobileNet based secured compliance through open web application security projects in cloud system. Indonesian Journal of Electrical Engineering and Computer Science. 2024;35(3):1661. doi:10.11591/ijeecs.v35.i3.pp1661-1669
  13. Chowdhury M, Dewan U. Privilege: An Innovative Mobile Application Featuring Passengers Transport Riding Safety Checking, Driver Selection, and Emergency Assistance. 2024 4th International Conference on Data Engineering and Communication Systems (ICDECS). 2024:1-6. doi:10.1109/icdecs59733.2023.10503104
  14. Moreira FWR, Hermes G, de Lima JMM. Development of a Cross Platform Mobile Application Using Gemini to Assist Visually Impaired Individuals. 2024 9th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS). 2024:559-566. doi:10.1109/iciibms62405.2024.10792854
  15. Dsouza VS, Leyens L, Brand A. Employing bibliometrics and natural language processing (NLP) to analyse real-world applications of adverse drug reaction. Exploratory Research in Clinical and Social Pharmacy. 2025;18:100592. doi:10.1016/j.rcsop.2025.100592
  16. Doig A, Abanto N, Wong L. A Mobile Application for the Immediate Detection and Response to Violent Attacks in Urban Environments Utilizing Speech-to-Text and Natural Language Processing. Engineering, Technology & Applied Science Research. 2025;15(6):28710-28718. doi:10.48084/etasr.13189
  17. C. Iluno Amalachukwu, O. C. Okeke, I. Mgbeafuluik, “Development of a deep learning technology to improve human-computer interaction for visually impaired,” International Journal of Real-Time Applications and Computing Systems, vol. 3, no. 1, 2026.
  18. Dhiyaussalam, K. N. P. Pamungkas, and S. ’Uyun, “Improving predictive accuracy: A comparative study of SMOTE and machine learning on heart disease data,” in AIP Conference Proceedings, vol. 3326, no. 1, 2026, p. 060005.
Support