Deep Learning-Enhanced Cluster Head Optimization for Intrusion Detection in Wireless Sensor Networks
Bibliographic record
Abstract
Securing wireless sensor networks (WSNs) is imperative, particularly for an intrusion detection system (IDS) deployed in inaccessible terrains, which are susceptible to a multitude of security threats.This study introduces a novel IDS framework employing deep learning to curtail a spectrum of cyber assaults, including but not restricted to DoS, tampering, and sinkhole attacks.In addition to that, The crux of the proposed model depends on the optimization of the cluster head (CH) selection among sensor nodes, where nodes with superior energy levels are preferentially considered for CH roles.This research advances beyond energy-centric CH selection criteria by incorporating delay and distance considerations, culminating in the development of the Particle Distance Updated Bottlenose Dolphin Optimization (PDU-BDO) algorithm for the CH election process.Subsequently, an intrusion detection analysis is conducted via an optimized deep hierarchical voting neural network (DHVNN), with the PDU-BDO algorithm facilitating the neural network's (NN) weight tuning during training.The efficacy of the PDU-BDO algorithm, benchmarked against three extant methodologies using the NSL-KDD dataset, reflects significant performance enhancements, yielding an accuracy of 91.6%, precision of 88.2%, recall of 86%, F1-score of 82%, and a kappa score of 71.4%.Moreover, deep learning-based IDS against adversarial attacks is corroborated through real-world application scenarios, signalling a stalwart defense mechanism within the WSN paradigm.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".