Knowledge discovery for behavioral patterns in wireless sensor networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The research consolidated in this thesis is motivated by the recent evolvement of wireless technologies and microelectronic devices, which instigated the emergence of Wireless Sensor Networks (WSNs). Many WSN-based applications have come about; these applications are related, but not limited, to the fields of military, environment and health care. Research in WSNs is still in its early stages, and efforts have been put forward to design fast, reliable, and fault-tolerant protocols that guarantee acceptable levels of quality for events delivery, to meet the limited capabilities of sensor nodes and the effects of unreliable wireless communication. In this thesis, we focus on the design of a Knowledge-based framework for extracting behavioral patterns regarding sensor nodes from WSNs. Three types of behavioral patterns are introduced: Sensor Association Rules, Coverage-based Rules and Sensor Chronological Patterns. The proper steps in the Knowledge Discovery process that pertain to the extraction of the behavioral patterns are defined. These steps are: (i) a formal definition of the required 'knowledge'; (ii) the data preparation stage that covers the communication aspects of the process of preparing data that is needed to extract these patterns; (iii) the data mining techniques that are essential for extracting the required patterns. A set of schemes have been proposed to attain these steps, and meet the critical properties of WSNs. In contrast to other techniques, the proposed behavioral patterns are mainly about the sensor nodes, instead of the area under monitoring. The direct application of the proposed patterns is enhancing the performance of WSNs by participating in the resource management process of sensor nodes, and reducing the undesired cons of wireless communication; thus improving the Quality of Service of WSNs. Several experiments have been conducted, using synthetic and real data, to report about the performance of proposed schemes.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it