An epileptic seizure is a brief episode of symptoms and signs caused by excessive electrical activity in the brain. One of the major chronic neurological diseases, epilepsy, affects millions of individuals worldwide. Effective detection of seizure events is critical in the diagnosis and treatment of patients with epilepsy. Neurologists monitor the electrical activity in the brains of patients to identify epileptic seizures by employing advanced sensing techniques, including electroencephalograms and electromyography. Machine learning-based classification of the EEG signal can help differentiate between normal signals and the patterns associated with epileptic seizures. This work presents a novel approach for the classification of epileptic seizures using random neural network (RNN). The proposed model has been trained and tested using two publicly available datasets: CHB-MIT and BONN, provided by Children’s Hospital Boston-Massachusetts Institute of Technology and the University of Bonn, respectively. The results obtained from multiple experiments highlight that the proposed scheme outperformed traditional classification schemes such as artificial neural network and support vector machine. The proposed RNN-based model achieved accuracies of 93.27% and 99.84% on the CHB-MIT and BONN datasets, respectively.

Empirical propagation models are vital tools for planning and deployment of any wireless communication network as they depend less on terrain data and are faster to execute. In this paper, NS3 is used to simulate radio propagation for Long range wide area network (LoRaWAN) at 868 MHz in an urban environment using the Okumura-Hata model, the COST-231 Hata, and the COST 231 Walfish-Ikegami (COST-WI). LoRaWAN use radio frequency 868 MHz for communication in Europe. The predicted received signal strength values are compared with the real-world measurements taken in the city of Glasgow to analyze the validity and accuracy of the empirical models when used for planning and coverage prediction in LoRaWAN networks. The comparison between models and measurements shows that Okumura-Hata under-estimated the received signal strength in Glasgow city scenario while COST-WI over-estimated the same power. Similarly, the Okumura-Hata model showed higher accurate predictions whereas COST-WI accuracy was the least. The magnitude of mean absolute error indicates how big or small models prediction error can be expected. This study can be used to give an insight into the effectiveness and accuracy of empirical propagation models for evaluation of Internet of Things (IoT) connectivity with LoRaWAN networks in a non-line of sight (NLOS) urban environment.

Freezing of Gait (FOG) is an episodic absence of forward movement in Parkinson’s Disease (PD) patients and represents an onset of disabilities. FOG hinders daily activities and increases fall risk. There is high demand for automating the process of FOG detection due to its impact on health and well being of individuals. This work presents WiFreeze, a noninvasive, line of sight, and lighting agnostic WiFi-based sensing system, which exploits ambient 5G spectrum for detection and classification of FOG. The core idea is to utilize the amplitude variations of wireless Channel State Information (CSI) to differentiate between FOG and activities of daily life. A total of 225 events with 45 FOG cases are captured from 15 patients with the help of 30 subcarriers and classification is performed with a deep neural network. Multiresolution scalograms are proposed for time–frequency signatures of human activities, due to their ability to capture and detect transients in CSI signals caused by transitions in human movements. A very deep Convolutional Neural Network (CNN), VGG-8K, with 8K neurons each, in fully connected layers is engineered and proposed for transfer learning with multiresolution scalogram features for detection of FOG. The proposed WiFreeze system outperforms all existing wearable and vision-based systems as well as deep CNN architectures with the highest accuracy of 99.7% for FOG detection. Furthermore, the proposed system provides the highest classification accuracies of 94.3% for voluntary stop and 97.6% for walking slow activities, with improvements of 9% and 23%, respectively, over the best performing state-of-the-art deep CNN architecture.

Little work has been reported on the magnitude and impact of interference with the performance of Internet of Things (IoT) applications operated by Long-Range Wide-Area Network (LoRaWAN) in the unlicensed 868 MHz Industrial, Scientific, and Medical (ISM) band. The propagation performance and signal activity measurement of such technologies can give many insights to effectively build long-range wireless communications in a Non-Line of Sight (NLOS) environment. In this paper, the performance of a live multi-gateway in indoor office site in Glasgow city was analysed in 26 days of traffic measurement. The indoor network performances were compared to similar performance measurements from outdoor LoRaWAN test traffic generated across Glasgow Central Business District (CBD) and elsewhere on the same LoRaWAN. The results revealed 99.95% packet transfer success on the first attempt in the indoor site compared to 95.7% at the external site. The analysis shows that interference is attributed to nearly 50 X greater LoRaWAN outdoor packet loss than indoor. The interference measurement results showed a 13.2–97.3% and 4.8–54% probability of interfering signals, respectively, in the mandatory Long-Range (LoRa) uplink and downlink channels, capable of limiting LoRa coverage in some areas.