Network Traffic Classification for Internet of Things Based on Deep Learning Models
Bibliographic record
Abstract
Internet of Things (IoT) is a system of interconnected computing devices. The continuous growth of the number of IoT devices leads to expansive traffic. It is crucial to study the behaviour of network flows for Internet Service Providers (ISPs) to manage the performance of the IoT network. The Network Traffic Classifier (NTC) is the foremost essential tool in finding the network flows and behavioural aspects of a network such as network latency, volume, bandwidth consumption and many more. The success of deep learning models extended to the NTC as well. The current deep learning based solutions for the NTC contributed to considerable success. However, the current so- lutions are proposed to classify the flows that are captured in monitored network. In the real world, IoT traffic is diverse and heterogeneous in nature. Therefore in the ever-evolving IoT world, it is challenging to keep up the classification model trained with flows that are captured in controlled environment. Hence, in this research the effort is made to design the model that can classify the traffic flows from real world. A supervised deep learning method is proposed to classify network traffic and chi-square algorithm is used to select the features that can provide best information about the flows. The proposed method achieves 70% accuracy. The time distribution wrapper over the Convolutional Neural Network (CNN) is employed to extract the network features. The Long-Short Term Memory (LSTM) layer is applied to classify the network flows. The thesis explains a detailed study of feature engineering, successful deep learning models, and the research results.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".