Rate-Distortion Classification for Self-Tuning IoT Networks
| Autor: | Michele Zorzi, Michele Rossi, Davide Zordan |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Signal processing
FOS: Computer and information sciences Computer science Computer Networks and Communications Real-time computing 02 engineering and technology Lossy compression 01 natural sciences Signal Machine Learning (cs.LG) Computer Science - Networking and Internet Architecture Software Distortion 0202 electrical engineering electronic engineering information engineering Discrete cosine transform Data mining Networking and Internet Architecture (cs.NI) Artificial neural network business.industry Classification Feature extraction Neural networks Hardware and Architecture 010401 analytical chemistry 020206 networking & telecommunications 0104 chemical sciences Support vector machine Computer Science - Learning business Wireless sensor network Data compression |
| Zdroj: | ICC Workshops |
| DOI: | 10.48550/arxiv.1706.08877 |
| Popis: | The Internet of Things, like many future wireless sensor networks, is expected to follow a software defined paradigm, where protocol parameters and behaviors will be dynamically tuned as a function of the signal statistics. New protocols will be then injected as a software when certain events occur. For instance, new data compressors could be (re)programmed on-the-fly as the monitored signal type or its statistical properties change. In this paper, a lossy compression scenario is considered, where the application tolerates some distortion of the gathered signal in return for improved energy efficiency. To reap the full benefits of this paradigm, an automatic sensor profiling approach is discussed, where the signal class, and in particular the corresponding rate-distortion curve, is automatically assessed using machine learning tools (namely, support vector machines and neural networks). This curve can be reliably estimated on-the-fly through the computation of a small number (from ten to twenty) of statistical features on time windows of a few hundreds samples. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|