Classification of cardiac arrhythmia using a convolutional neural network and bi-directional long short-term memory.

Cardiac arrhythmia is a leading cause of cardiovascular disease, with a high fatality rate worldwide. The timely diagnosis of cardiac arrhythmias, determined by irregular and fast heart rate, may help lower the risk of strokes. Electrocardiogram signals have been widely used to identify arrhythmias due to their non-invasive approach. However, the manual process is error-prone and time-consuming. A better alternative is to utilize deep learning models for early automatic identification of cardiac arrhythmia, thereby enhancing diagnosis and treatment. In this article, a novel deep learning model, combining convolutional neural network and bi-directional long short-term memory, is proposed for arrhythmia classification. Specifically, the classification comprises five different classes: non-ectopic (N), supraventricular ectopic (S), ventricular ectopic (V), fusion (F), and unknown (Q) beats. The proposed model is trained, validated, and tested using MIT-BIH and St-Petersburg data sets separately. Also, the performance was measured in terms of precision, accuracy, recall, specificity, and f1-score. The results show that the proposed model achieves training, validation, and testing accuracies of 100%, 98%, and 98%, respectively with the MIT-BIH data set. Lower accuracies were shown for the St-Petersburg data set. The performance of the proposed model based on the MIT-BIH data set is also compared with the performance of existing models based on the MIT-BIH data set.

An enhanced dynamic transmission opportunity scheme to support varying traffic load over wireless campus networks.

Transmission opportunity (TXOP) is a key factor to enable efficient channel bandwidth utilization over wireless campus networks (WCN) for interactive multimedia (IMM) applications. It facilitates in resource allocation for the similar categories of multiple packets transmission until the allocated time is expired. The static TXOP limits are defined for various categories of IMM traffics in the IEEE802.11e standard. Due to the variation of traffic load in WCN, the static TXOP limits are not sufficient enough to guarantee the quality of service (QoS) for IMM traffic flows. In order to address this issue, several existing works allocate the TXOP limits dynamically to ensure QoS for IMM traffics based on the current associated queue size and pre-setting threshold values. However, existing works do not take into account all the medium access control (MAC) overheads while estimating the current queue size which in turn is required for dynamic TXOP limits allocation. Hence, not considering MAC overhead appropriately results in inaccurate queue size estimation, thereby leading to inappropriate allocation of dynamic TXOP limits. In this article, an enhanced dynamic TXOP (EDTXOP) scheme is proposed that takes into account all the MAC overheads while estimating current queue size, thereby allocating appropriate dynamic TXOP limits within the pre-setting threshold values. In addition, the article presents an analytical estimation of the EDTXOP scheme to compute the dynamic TXOP limits for the current high priority traffic queues. Simulation results were carried out by varying traffic load in terms of packet size and packet arrival rate. The results show that the proposed EDTXOP scheme achieves the overall performance gains in the range of 4.41%-8.16%, 8.72%-11.15%, 14.43%-32% and 26.21%-50.85% for throughput, PDR, average ETE delay and average jitter, respectively when compared to the existing work. Hence, offering a better TXOP limit allocation solution than the rest.

Intersection-Based Link-Adaptive Beaconless Forwarding in Urban Vehicular Ad-Hoc Networks.

Remote monitoring applications in urban vehicular ad-hoc networks (VANETs) enable authorities to monitor data related to various activities of a moving vehicle from a static infrastructure. However, urban environment constraints along with various characteristics of remote monitoring applications give rise to significant hurdles while developing routing solutions in urban VANETs. Since the urban environment comprises several road intersections, using their geographic information can greatly assist in achieving efficient and reliable routing. With an aim to leverage this information, this article presents a receiver-based data forwarding protocol, termed Intersection-based Link-adaptive Beaconless Forwarding for City scenarios (ILBFC). ILBFC uses the position information of road intersections to effectively limit the duration for which a relay vehicle can stay as a default forwarder. In addition, a winner relay management scheme is employed to consider the drastic speed decay in vehicles. Furthermore, ILBFC is simulated in realistic urban traffic conditions, and its performance is compared with other existing state-of-the-art routing protocols in terms of packet delivery ratio, average end-to-end delay and packet redundancy coefficient. In particular, the results highlight the superior performance of ILBFC, thereby offering an efficient and reliable routing solution for remote monitoring applications.