International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Invisible Configuration Conflicts Detector Using Machine Learning a Random Forest–Based Intelligent Framework for Software Configuration Conflict Detection |
|---|---|
| ABSTRACT | IoT-enabled cyber-physical systems are widely used in smart cities, industries, healthcare, and home automation because they improve efficiency and connectivity. However, these systems are highly vulnerable to cyber-attacks due to weak security mechanisms, limited device resources, and large-scale interconnected networks. Attacks such as DDoS, data injection, and malware can seriously affect system reliability and safety. Therefore, accurate and fast intrusion detection is essential for protecting IoT environments. This project presents a hybrid deep learning framework for detecting security attacks in IoT-enabled cyber-physical systems. The proposed model combines two deep learning classifiers, Convolutional Neural Network (CNN) and Deep Belief Network (DBN), to improve attack detection performance. To enhance classification accuracy, the model parameters are optimized using a novel hybrid metaheuristic optimization algorithm called Seagull Adapted Elephant Herding Optimization (SAEHO), which integrates the strengths of Seagull Optimization and Elephant Herding Optimization for better exploration and exploitation. The framework follows three main stages: preprocessing and normalization, feature extraction using statistical and higher-order statistical features, and final classification into attack or benign traffic. The proposed system is evaluated using two benchmark datasets, UNSW-NB15 and BoT-IoT, and performance is measured using metrics such as accuracy, sensitivity, specificity, and precision. Experimental results show that the Hybrid Classifier + SAEHO approach achieves better detection accuracy and improved performance compared to conventional deep learning and optimization-based methods. |
| AUTHOR | DR. T.V.S SRIRAM, RAMKRISHNA, K. MANOJ Sr. Asst. Professor, Dept. of MCA, NSRIT, Visakhapatnam, AP, India Asst. Professor, Dept. of MCA, NSRIT, Visakhapatnam, AP, India Dept. of MCA, NSRIT, Visakhapatnam, AP, India |
| VOLUME | 186 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1407045 |
| pdf/45_Invisible Configuration Conflicts Detector Using Machine Learning a Random Forest–Based Intelligent Framework for Software Configuration Conflict Detection.pdf | |
| KEYWORDS | |
| References | [1] K. Min, J. Yoon, M. Kang, D. Lee, E. Park, and J. Han, “Detecting depression on video logs using audiovisual features,” no. 2023, doi: 10.1057/s41599-023-02313-6. [2] H. Zhang, H. Wang, S. Han, W. Li, and L. Zhuang, “Computer Methods and Programs in Biomedicine Detecting depression tendency with multimodal features,” Comput. Methods Programs Biomed., vol. 240, no. January 2022, p. 107702, 2023, doi: 10.1016/j.cmpb.2023.107702. [3] J. Jovel, R. Greiner, and R. Greiner, “An Introduction to Machine Learning Approaches for Biomedical Research,” vol. 8, no. December, pp. 1–15, 2021, doi: 10.3389/fmed.2021.771607. [4] J. Maurya and S. Prakash, “Heart Disease Prediction and Diagnosis Using IoT, ML, and Cloud Computing,” in International Conference on Innovative Computing and Communications, A. E. Hassanien, O. Castillo, S. Anand, and A. Jaiswal, Eds., Singapore: Springer Nature Singapore, 2024, pp. 419–430. [5] I. Conference, “Feature Selection and Imbalanced Data Handling for Depression Detection : Feature Select ion and Imbalanced Data Handling for Depression Detection,” no. September 2023, 2018, doi: 10.1007/978-3-030-05587-5. [6] R. Islam, M. A. Kabir, A. Ahmed, A. R. M. Kamal, and H. Wang, “Depression detection from social network data using machine learning techniques,” Heal. Inf. Sci. Syst., vol. 6, no. 1, pp. 1–12, 2018, doi: 10.1007/s13755-018-0046-0. [7] H. Alsagri, “Machine Learning-based Approach for Depression Detection in Twitter Using Content and Activity Features,” vol. 1, pp. 1–16. [8] A. Ahmed, R. Sultana, M. T. R. Ullas, M. Begom, M. M. I. Rahi, and M. A. Alam, “A Machine Learning Approach to detect Depression and Anxiety using Supervised Learning,” 2020 IEEE Asia-Pacific Conf. Comput. Sci. Data Eng. CSDE 2020, pp. 4–9, 2020, doi: 10.1109/CSDE50874.2020.9411642. [9] S. J. T. J, I. J. Jacob, and A. K. Mandava, “D-ResNet-PVKELM : deep neural network and paragraph vector based kernel extreme machine learning model for multimodal depression analysis,” pp. 25973–26004, 2023. [10] D. Kumar, U. Subrajeet, M. Niraj, and K. Singh, “An early assessment of Persistent Depression Disorder using machine learning algorithm,” Multimed. Tools Appl., no. 0123456789, 2023, doi: 10.1007/s11042-023-17369-4. [11] D. Pokrajac, “The successful discrimination of depression from EEG could be attributed to proper feature extraction and not to a particular classification method,” vol. 0123456789, pp. 443–455, 2020, doi: 10.1007/s11571-020-09581-x. [12] A. Albtoush and M. Ferna, “Quick extreme learning machine for large-scale classification,” vol. 8, pp. 5923–5938, 2022, doi: 10.1007/s00521-021-06727-8. |
