Design and Evaluation of SEANet: a Software-defined Networking Platform for the Internet of Underwater Things

Investigating and safeguarding our oceans is vital for a host of applications and tasks, including combating climate change, ensuring the integrity of subsea infrastructures, and for coastal protection. Achieving these essential functions depends on the deployment of cost-effective, versatile underwater sensor networks that can efficiently collect and transmit data to land. However, the success of such networks is currently hindered by the significant limitations of existing underwater modems, which limits their operational use to a narrow range of applications. This paper presents and evaluates the performance of the SEANet software-defined networking platform, for the Internet of Underwater Things (IoUT), addressing the limitations of existing underwater communication technologies. It presents the development and comprehensive testing of an adaptable, high-data-rate, and integration-friendly underwater platform that reconfigures in real-time to meet the demands of various marine applications. With an acoustic front end, the platform significantly outperforms conventional modems, achieving more than double the data rate at 150 kbit/s. Experiments conducted in oceanic conditions demonstrate its capabilities in channel characterization, OFDM link establishment, and compatibility with the JANUS communication standard. Our platform advances the IoUT by providing a versatile, scalable solution that can incorporate multiple physical layers and support an array of tasks, making it pivotal for real-time ocean data analysis and the expansion of ocean-related digital applications.

SeizNet: An AI-enabled Implantable Sensor Network System for Seizure Prediction

In this paper, we introduce SeizNet, a closed-loop system for predicting epileptic seizures through the use of Deep Learning (DL) method and implantable sensor networks. While pharmacological treatment is effective for some epilepsy patients (with ~65M people affected worldwide), one out of three suffer from drug-resistant epilepsy. To alleviate the impact of seizure, predictive systems have been developed that can notify such patients of an impending seizure, allowing them to take precautionary measures. SeizNet leverages DL techniques and combines data from multiple recordings, specifically intracranial electroencephalogram (iEEG) and electrocardiogram (ECG) sensors, that can significantly improve the specificity of seizure prediction while preserving very high levels of sensitivity. SeizNet DL algorithms are designed for efficient real-time execution at the edge, minimizing data privacy concerns, data transmission overhead, and power inefficiencies associated with cloud-based solutions. Our results indicate that SeizNet outperforms traditional single-modality and non-personalized prediction systems in all metrics, achieving up to 99% accuracy in predicting seizure, offering a promising new avenue in refractory epilepsy treatment.