Recent technological developments pave the path for deep learning-based techniques to be used in almost every domain of life. The precision of deep learning techniques make it possible for these to be used in the medical field for the classification and detection of various diseases. Recently, the coronavirus (COVID-19) pandemic has put a lot of pressure on the health system all around the world. The diagnosis of COVID-19 is possible by PCR testing and medical imagining. Since COVID-19 is highly contagious, diagnosis using chest X-ray is considered safe in various situations. In this study, a deep learning-based technique is proposed to classify COVID-19 infection from other non-COVID-19 infections. To classify COVID-19, three different pre-trained models named EfficientNetB1, NasNetMobile and MobileNetV2 are used. The augmented dataset is used for training deep learning models while two different training strategies have been used for classification. In this study, not only are the deep learning model fine-tuned but also the hyperparameters are fine-tuned, which significantly improves the performance of the fine-tuned deep learning models. Moreover, the classification head is regularized to improve the performance. For the evaluation of the proposed techniques, several performance parameters are used to gauge the performance. EfficientNetB1 with regularized classification head outperforms the other models. The proposed technique successfully classifies four classes that include COVID-19, viral pneumonia, lung opacity, and normal, with an accuracy of 96.13%. The proposed technique shows superiority in terms of accuracy when compared with recent techniques present in the literature.

Underwater Sensor Networks (UWSNs) utilise acoustic waves with comparatively lower loss and longer range than those of electromagnetic waves. However, energy remains a challenging issue in addition to long latency, high bit error rate, and limited bandwidth. Thus, collision and retransmission should be efficiently handled at Medium Access Control (MAC) layer in order to reduce the energy cost and also to improve the throughput and fairness across the network. In this paper, we propose a new reservation-based distributed MAC protocol called ED-MAC, which employs a duty cycle mechanism to address the spatial-temporal uncertainty and the hidden node problem to effectively avoid collisions and retransmissions. ED-MAC is a conflict-free protocol, where each sensor schedules itself independently using local information. Hence, ED-MAC can guarantee conflict-free transmissions and receptions of data packets. Compared with other conflict-free MAC protocols, ED-MAC is distributed and more reliable, i.e., it schedules according to the priority of sensor nodes which based on their depth in the network. We then evaluate design choices and protocol performance through extensive simulation to study the load effects and network scalability in each protocol. The results show that ED-MAC outperforms the contention-based MAC protocols and achieves a significant improvement in terms of successful delivery ratio, throughput, energy consumption, and fairness under varying offered traffic and number of nodes.

An underwater sensor network (UWSN) has recently attracted considerable attention due to its ability to discover and monitor the aquatic environment. However, its acoustic communication has posed several inherent characteristics, such as high latency, low available bandwidth, and high bit error rate. These unique characteristics have made contention-based medium access control (MAC) protocols inefficient for UWSNs. They are most expensive and are not as effective as they are in terrestrial networks. Through this principle, a contention-free MAC protocol is, therefore, considered to be more reliable and flexible to overcome the consequences of applying acoustic signals and also to achieve a high performance (improving the energy efficiency and throughput across the network) by eliminating the chance of collision. In this paper, we propose a novel energy-conserving and collision-free depth-based layering MAC (DL-MAC) protocol for UWSNs. DL-MAC is able to deal with the underwater MAC challenges, such as the near-far effect, spatial-temporal uncertainty, and hidden/exposed terminal problems. It is able to efficiently schedule the transmission and reception operations in each side by using the concept of layering and a distributed clustering algorithm. By using a TDMA-based principle, DL-MAC can assign separate time slots to every sensor node individually to access the medium without any possibility of collision. Our extensive simulation study shows that DL-MAC outperforms other protocols in terms of throughput, packet delivery ratio, energy consumption, and packets lost under varying traffic rates and the numbers of nodes. INDEX TERMS Underwater sensor networks (UWSNs), medium access control (MAC), depth-based layering, distributed clustering approach, collision-free MAC protocol.

Underwater Sensor Networks (UWSN) utilise acoustic waves with comparatively lower loss and longer range in underwater environment than electromagnetic waves. However, energy remains a challenging issue in addition to long latency, high bit error rate, and limited bandwidth. Thus, collision and retransmission should be efficiently handled at MAC layer in order to reduce the energy cost and also to improve the throughput and fairness across the network. In this paper, we therefore propose a new reservation-based distributed MAC protocol, which employs a duty cycle mechanism to address the spatial-temporal uncertainty and the hidden node problem to effectively reduce collisions and retransmissions. Our extensive simulation study reveals that our proposed protocol can efficiently handle the traffic contention to achieve significant improvement in terms of energy consumption, throughput, and fairness.Index Terms-Underwater acoustic networks, Underwater MAC protocols, Duty cycle mechanism.

The Medium Access Control (MAC) layer protocol is the most important part of any network, and is considered to be a fundamental protocol that aids in enhancing the performance of networks and communications. However, the MAC protocol’s design for underwater sensor networks (UWSNs) has introduced various challenges. This is due to long underwater acoustic propagation delay, high mobility, low available bandwidth, and high error probability. These unique acoustic channel characteristics make contention-based MAC protocols significantly more expensive than other protocol contentions. Therefore, re-transmission and collisions should effectively be managed at the MAC layer to decrease the energy cost and to enhance the network’s throughput. Consequently, handshake-based and random access-based MAC protocols do not perform as efficiently as their achieved performance in terrestrial networks. To tackle this complicated problem, this paper surveys the current collision-free MAC protocols proposed in the literature for UWSNs. We first review the unique characteristic of underwater sensor networks and its negative impact on the MAC layer. It is then followed by a discussion about the problem definition, challenges, and features associated with the design of MAC protocols in UWANs. Afterwards, currently available collision-free MAC design strategies in UWSNs are classified and investigated. The advantages and disadvantages of each design strategy along with the recent advances are then presented. Finally, we present a qualitative comparison of these strategies and also discuss some possible future directions.