星空传媒

AI based performance enhancement of LP-WAN technologies for IoT

The rapid growth of Internet-of-Things (IoT) in the current decade has led to the development of a multitude of new access technologies targeted at low-power, wide area networks (LP-WANs). This proposal considers using deep learning techniques to enhance the performance of LP-WAN technologies for IoT, including design choices and their implications. We consider LoRaWAN, WavIoT, random phase multiple access (RPMA), narrowband IoT (NB-IoT), as well as LTE-M and assess their performance in terms of signal propagation, coverage and energy conservation. By 2025, up to 75 billion devices would be connected in IoT, with a potential economic impact. The key underpinning of IoT is the large number of interconnected devices that exchange information and enable services. Although IoT connectivity will be dominated by short-range technologies for many years, the researchers predict that by 2025, 25% of wireless industrial IoT connections will be provided with low power, wide area network (LP-WAN) technologies. This work allows scaling up the network density while maintaining low packet collision rate and significantly enhances the transmission delay and the energy consumption. Also, a deep learning-based Collision Aware transmission Priority Scheduling Technique (CAPST) will be used.

AI based performance’s improvements for 6G wireless communications

The demand for wireless connectivity has grown exponentially over the last few decades. 5G with far more features than 4G is already deployed worldwide. Beyond 5G, some fundamental issues that need to be addressed are high system capacity, higher data rates, lower latency, higher security, and improved QoS. The 6G communication system is expected to be a global communication facility. It is envisioned that the per user bit rate in 6G will be approximately 1 Tb/sec [1]. Also, the 6G system is expected to provide simultaneous wireless connectivity that is 1000 times higher than 5G. A few of the critical motivating trends behind the evolution of 6G communication systems are high data rate, high reliability, low latency, high energy efficiency, high spectral efficiency, new spectra, green communication, intelligent networks, and sensing. Hence, the 6G system will be driven by many technologies. A few expected vital technologies for 6G are: AI, THz communications, Optical wireless communications, FSO fronthaul/backhaul network, ultra mMIMO, and cell-free communications.

AI based project for early detection of Atrial Fibrillation

Atrial fibrillation (AF) is the most common sustained heart arrhythmia. However, as many cases are asymptomatic, a large proportion of patients remain undiagnosed until serious complications arise. Therefore, early detection of AF is crucial for increasing the success rate of the treatment. In this project, we are investigating, using electronic medical record (EMR) data sets, the application of machine learning (ML) and looking at the replacement of traditional check lists for determining the risk of a person having or developing AF. This project proposes approaches on developing an automated indicator of identifying AF’s risk, where state-of-the-art ML and deep learning (DL) techniques will be used to get better accuracy, specificity, and sensitivity for predicting AF. Checklists are designed to provide the medical specialist with information they can use to choose the best treatment for patients if they have been diagnosed with AF. The goal of the proposed automated indicator is to diagnose AF early, efficiently and accurately using the EMR data sets. This project is also include using wearables to measure and incorporate additional vital signs into the data sets to provide early warning before the onset of fibrillation.