Wireless Body Area Network (WBAN) is an interconnection of small bio-sensor nodes that are deployed in/on different parts of human body. It is used to sense health-related data such as rate of heart beat, blood pressure, blood glucose level, Electro-cardiogram (ECG), Electro-myography (EMG) etc. of human body and pass these readings to real-time health monitoring systems. WBANs is an important research area and is used in different applications such as medical field, sports, entertainment, social welfare etc. Bio-Sensor Nodes (BSNs) or simply called as Sensor Nodes (SNs) are the main backbone of WBANs. SNs normally have very limited resources due to its smaller size. Therefore, minimum consumption of energy is an essential design requirement of WBAN schemes. In the proposed work, Energy-efficient Harvested-Aware clustering and cooperative Routing Protocol for WBAN (E-HARP) are presented. The presented protocol mainly proposes a novel multi-attribute-based technique for dynamic Cluster Head (CH) selection and cooperative routing. In the first phase of this two-phased technique, optimum CH is selected among the cluster members, based on calculated Cost Factor (CF). The parameters used for calculation of CF are; residual energy of SN, required transmission power, communication link Signal-to-Noise-Ratio (SNR) and total network energy loss. In order to distribute load on one CH, E-HARP selects new CH in each data transmission round. In the second phase of E-HARP, data is routed with cooperative effort of the SN, which saves the node energy by prohibiting the transmission of redundant data packets. To evaluate the performance of the proposed technique, comprehensive experimentations using NS-2 simulation tool has been conducted. The results are compared with some latest techniques named as EH-RCB, ELR-W, Co-LAEEBA, and EECBSR. The acquired results show a significant enhancement of E-HARP in terms of network stability, network life time, throughput, end-to-end delay and packet delivery ratio.

Image segmentation is considered as a key research topic in the area of computer vision. It is pivotal in a broad range of real-life applications. Recently, the emergence of deep learning drives significant advancement in image segmentation; the developed systems are now capable of recognizing, segmenting, and classifying objects of specific interest in images. Generally, most of these techniques primarily focused on the asymmetric field of view or frontal view objects. This work explores widely used deep learning-based models for person segmentation using top view data set. The first model employed in this work is Fully Convolutional Neural Network (FCN) with Resnet-101 architecture. The network consists of a set of max-pooling and convolution layers to identify pixel-wise class labels and prediction of the mask. The second model is based on FCN called U-Net with Encoder-Decoder architecture. The encoder is mainly comprised of a contracting path, also called an encoder, which captures the context in the image and symmetric expanding path called decoder to enable accurate location. The third model used for top view person segmentation is a DeepLabV3 model also with encoder-decoder architecture. The encoder consists of trained Convolutional Neural Network (CNN) to encode feature maps of the input image. The decoder is used for up-sampling and reconstruction of output using important information extracted by the encoder. All segmentation models are firstly tested using pre-trained models (trained on frontal view data set). To improve the performance, these models are further trained using person data set captured from a top view. The output of all models consists of a segmented person in the top view images. The experimental results reveal the effectiveness and performance of segmentation models by achieving IoU of 83%, 84%, and 86% and mIoU of 80% 82%and 84% for FCN, U-Net, and DeepLabv3 respectively. Furthermore, the discussion is provided for output results with possible future guidelines.

Sensor networks feature low-cost sensor devices with wireless network capability, limited transmit power, resource constraints, and limited battery energy. Cooperative routing exploits the broadcast nature of wireless medium and transmits cooperatively using nearby sensor nodes as relays. It is a promising technique that utilizes cooperative communication to improve the communication quality of single-antenna sensor nodes. In this paper, we propose a cooperative transmission scheme for underwater sensor networks (UWSNs) to enhance the network performance. Cooperative diversity has been introduced to combat fading. Cooperative UWSN (Co-UWSN) is proposed, which is a reliable, energy-efficient, and high throughput routing protocol for UWSN. Destination and potential relays are selected that utilize distance and signal-to-noise ratio computation of the channel conditions as cost functions. This contributes to sufficient decrease in path losses occurring in the links and transferring of data with much reduced path loss. Simulation results show that Co-UWSN protocol performs better in terms of end-to-end delay, energy consumption, and network lifetime. Selected protocols for comparison are energy-efficient depth-based routing (EEDBR), improved adaptive mobility of courier nodes in threshold-optimized depth-based routing (iAMCTD), cooperative routing protocol for UWSN, and cooperative partner node selection criteria for cooperative routing Coop (Re and dth).