No abstract

No abstract

No abstract

In medical body area network (MBAN) sensors are attached to a patient's body for continuous and real-time monitoring of biomedical vital signs. Sensors send patient's data to hospital base station so that doctors/caregivers can access it and be timely informed if patient's condition goes critical. These tiny sensors have low data rates, small transmission ranges, limited battery power and processing capabilities. Ensuring reliability in MBAN is important due to the critical nature of patient's data because any wrong/missing/delayed data can create a situation in which doctors may take wrong decisions about patient's health which can have fatal results. Data transmission reliability in MBAN can be ensured by retransmissions, acknowledgments or guaranteed time slot mechanism but it causes more power consumption. We propose an efficient MAC mechanism to achieve both reliability and energy efficiency at an acceptable tradeoff level. The proposed MAC mechanism not only overcomes the limitations of ZigBee MAC mechanism such as inefficient CSMA/CA and underutilization of guaranteed time slots, but also adapts for different traffic types such as emergency and normal traffic. Our results show that application level throughput and packet delivery ratio increase and packet loss decreases. We also optimize energy utilization by tuning macMaxCSMABackoffs and macMinBE parameters of ZigBee MAC mechanism.

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face analysis tasks, including ethnicity and race classification. We propose a race-classification algorithm using a prior face segmentation framework. A deep convolutional neural network (DCNN) was used to construct a face segmentation model. For training the DCNN, we label face images according to seven different classes, that is, nose, skin, hair, eyes, brows, back, and mouth. The DCNN model developed in the first phase was used to create segmentation results. The probabilistic classification method is used, and probability maps (PMs) are created for each semantic class. We investigated five salient facial features from among seven that help in race classification. Features are extracted from the PMs of five classes, and a new model is trained based on the DCNN. We assessed the performance of the proposed race classification method on four standard face datasets, reporting superior results compared with previous studies.