Car crashes are among the top ten leading causes of death; they could mainly be attributed to distracted drivers. An advanced driver-assistance technique (ADAT) is a procedure that can notify the driver about a dangerous scenario, reduce traffic crashes, and improve road safety. The main contribution of this work involved utilizing the driver’s attention to build an efficient ADAT. To obtain this “attention value”, the gaze tracking method is proposed. The gaze direction of the driver is critical toward understanding/discerning fatal distractions, pertaining to when it is obligatory to notify the driver about the risks on the road. A real-time gaze tracking system is proposed in this paper for the development of an ADAT that obtains and communicates the gaze information of the driver. The developed ADAT system detects various head poses of the driver and estimates eye gaze directions, which play important roles in assisting the driver and avoiding any unwanted circumstances. The first (and more significant) task in this research work involved the development of a benchmark image dataset consisting of head poses and horizontal and vertical direction gazes of the driver’s eyes. To detect the driver’s face accurately and efficiently, the You Only Look Once (YOLO-V4) face detector was used by modifying it with the Inception-v3 CNN model for robust feature learning and improved face detection. Finally, transfer learning in the InceptionResNet-v2 CNN model was performed, where the CNN was used as a classification model for head pose detection and eye gaze angle estimation; a regression layer to the InceptionResNet-v2 CNN was added instead of SoftMax and the classification output layer. The proposed model detects and estimates head pose directions and eye directions with higher accuracy. The average accuracy achieved by the head pose detection system was 91%; the model achieved a RMSE of 2.68 for vertical and 3.61 for horizontal eye gaze estimations.

It is critical for intelligent vehicles to be capable of monitoring the health and well-being of the drivers they transport on a continuous basis. This is especially true in the case of autonomous vehicles. To address the issue, an automatic system is developed for driver’s real emotion recognizer (DRER) using deep learning. The emotional values of drivers in indoor vehicles are symmetrically mapped to image design in order to investigate the characteristics of abstract expressions, expression design principles, and an experimental evaluation is conducted based on existing research on the design of driver facial expressions for intelligent products. By substituting a custom-created CNN features learning block with the base 11 layers CNN model in this paper for the development of an improved faster R-CNN face detector that detects the driver’s face at a high frame per second (FPS). Transfer learning is performed in the NasNet large CNN model in order to recognize the driver’s various emotions. Additionally, a custom driver emotion recognition image dataset is being developed as part of this research task. The proposed model, which is a combination of an improved faster R-CNN and transfer learning in NasNet-Large CNN architecture for DER based on facial images, enables greater accuracy than previously possible for DER based on facial images. The proposed model outperforms some recently updated state-of-the-art techniques in terms of accuracy. The proposed model achieved the following accuracy on various benchmark datasets: JAFFE 98.48%, CK+ 99.73%, FER-2013 99.95%, AffectNet 95.28%, and 99.15% on a custom-developed dataset.

In medical environments, a wireless body sensor network (WBSN) is used to operate remotely, and sensor nodes are employed. It consists of sensor nodes installed on a human body to monitor a patient’s condition, such as heartbeat, temperature, and blood sugar level, and are functionalized and controlled by remote devices. A WBSN consists of nodes that are actually sensors in nature and are operated with a short range of communication. These sensor nodes are fixed with limited computation power and the main concern is energy consumption and path loss. In this paper, we propose a new protocol named energy-efficient distance- and link-aware body area (EEDLABA) with a clustering mechanism and compare it with the current link-aware and energy-efficient body area (LAEEBA) and distance-aware relaying energy-efficient (DARE) routing protocols in a WBSN. The proposed protocol is an extended type of LAEEBA and DARE in which the positive features have been deployed. The clustering mechanism has been presented and deployed in EEDLABA for better performance. To solve these issues in LAEEBA and DARE, the EEDLABA protocol has been proposed to overcome these. Path loss and energy consumption are the major concerns in this network. For that purpose, the path loss and distance models are proposed in which the cluster head (CH) node, coordinator (C) node, and other nodes, for a total of nine nodes, are deployed on a human body. The results have been derived from MATLAB simulations in which the performance of the suggested EEDLABA has been observed in assessment with the LAEEBA and DARE. From the results, it has been concluded that the proposed protocol can perform well in the considered situations for WBSNs.

Underwater acoustic sensor networks (UWASNs) aim to find varied offshore ocean monitoring and exploration applications. In most of these applications, the network is composed of several sensor nodes deployed at different depths in the water. Sensor nodes located at depth on the seafloor cannot invariably communicate with nodes close to the surface level; these nodes need multihop communication facilitated by a suitable routing scheme. In this research work, a Cluster-based Cooperative Energy Efficient Routing (CEER) mechanism for UWSNs is proposed to overcome the shortcomings of the Co-UWSN and LEACH mechanisms. The optimal role of clustering and cooperation provides load balancing and improves the network profoundly. The simulation results using MATLAB show better performance of CEER routing protocol in terms of various parameters as compared to Co-UWSN routing protocol, i.e., the average end-to-end delay of CEER was 17.39, Co-UWSN was 55.819 and LEACH was 70.08. In addition, the average total energy consumption of CEER was 9.273, and LEACH was 45.33. The packet delivery ratio of CEER was 53.955, CO-UWSN was 42.047, and LEACH was 30.31. The stability period CEER was 130.9, CO-UWSN was 129.3, and LEACH was 119.1. The obtained results maximized the lifetime and improved the overall performance of the CEER routing protocol.

No abstract