A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments
Data drift caused due to network changes, new device additions, or model degradation alters the patterns learned by ML/DL models, resulting in poor classification performance. This creates the need for a generalized, drift-resilient model that can learn without retraining in dynamic environments. To...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45922/ |
| _version_ | 1848827527506690048 |
|---|---|
| author | Waseem, Quadri Wan Isni Sofiah, Wan Din Aamir, Muhammad |
| author_facet | Waseem, Quadri Wan Isni Sofiah, Wan Din Aamir, Muhammad |
| author_sort | Waseem, Quadri |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Data drift caused due to network changes, new device additions, or model degradation alters the patterns learned by ML/DL models, resulting in poor classification performance. This creates the need for a generalized, drift-resilient model that can learn without retraining in dynamic environments. To maintain high accuracy, such a model must classify previously unseen IoT devices effectively. In this study, we propose a three-tier incremental architecture (CNN-PN-RF) combining Convolutional Neural Network (CNN) for feature extraction, Prototypical Network (PN) for class embedding, and Random Forest (RF) for robust classification. The model utilizes six aggregated diverse IoT datasets.Two similarly structured datasets (Dataset 1 and Dataset 2) were created from it, differing in training-testing splits, with some device CSV files withheld to test on unseen classification. Phase 1 employs a stand-alone CNN-based model with L2 regularization, dropout, and early stopping, achieving 70.96% accuracy. Phase 2 integrates CNN with RF, using SMOTE for class balancing and PCA for dimensionality reduction, attaining 83.79% accuracy. Phase 3 introduces PN to finalize the CNN-PN-RF model, enhancing classification issue of feature clustering, intra-class separability, and small-class support. Final accuracy, precision, recall, and F1-score were 99.56%, 99.66%, 99.56%, and 99.59% for Dataset 1, and 99.80% for all metrics on Dataset 2. The model was compared with state-of-the-art approaches and validated on unseen IoT subsets of both datasets, showing better generalization capability. |
| first_indexed | 2025-11-15T04:02:08Z |
| format | Article |
| id | ump-45922 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T04:02:08Z |
| publishDate | 2025 |
| publisher | Nature Publishing Group |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-459222025-10-15T04:19:46Z https://umpir.ump.edu.my/id/eprint/45922/ A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments Waseem, Quadri Wan Isni Sofiah, Wan Din Aamir, Muhammad QA75 Electronic computers. Computer science Data drift caused due to network changes, new device additions, or model degradation alters the patterns learned by ML/DL models, resulting in poor classification performance. This creates the need for a generalized, drift-resilient model that can learn without retraining in dynamic environments. To maintain high accuracy, such a model must classify previously unseen IoT devices effectively. In this study, we propose a three-tier incremental architecture (CNN-PN-RF) combining Convolutional Neural Network (CNN) for feature extraction, Prototypical Network (PN) for class embedding, and Random Forest (RF) for robust classification. The model utilizes six aggregated diverse IoT datasets.Two similarly structured datasets (Dataset 1 and Dataset 2) were created from it, differing in training-testing splits, with some device CSV files withheld to test on unseen classification. Phase 1 employs a stand-alone CNN-based model with L2 regularization, dropout, and early stopping, achieving 70.96% accuracy. Phase 2 integrates CNN with RF, using SMOTE for class balancing and PCA for dimensionality reduction, attaining 83.79% accuracy. Phase 3 introduces PN to finalize the CNN-PN-RF model, enhancing classification issue of feature clustering, intra-class separability, and small-class support. Final accuracy, precision, recall, and F1-score were 99.56%, 99.66%, 99.56%, and 99.59% for Dataset 1, and 99.80% for all metrics on Dataset 2. The model was compared with state-of-the-art approaches and validated on unseen IoT subsets of both datasets, showing better generalization capability. Nature Publishing Group 2025-10 Article PeerReviewed pdf en https://umpir.ump.edu.my/id/eprint/45922/1/A%20generalized%20three-tier%20hybrid%20model%20for%20classifying%20unseen%20%28IoT%20devices%29%20in%20smart%20home%20environments.pdf Waseem, Quadri and Wan Isni Sofiah, Wan Din and Aamir, Muhammad (2025) A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments. Scientific Reports, 15 (35388). pp. 1-32. ISSN 2045-2322. (Published) https://doi.org/10.1038/s41598-025-19303-0 |
| spellingShingle | QA75 Electronic computers. Computer science Waseem, Quadri Wan Isni Sofiah, Wan Din Aamir, Muhammad A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title | A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title_full | A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title_fullStr | A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title_full_unstemmed | A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title_short | A generalized three-tier hybrid model for classifying unseen (IoT devices) in smart home environments |
| title_sort | generalized three-tier hybrid model for classifying unseen (iot devices) in smart home environments |
| topic | QA75 Electronic computers. Computer science |
| url | https://umpir.ump.edu.my/id/eprint/45922/ https://umpir.ump.edu.my/id/eprint/45922/ |