Summary Drowsy student state detection is helpful to understand the students' learning state, which is the necessary and basic aspect of teaching activities evaluation and assessment. The performance of traditional methods may deteriorate dramatically because of the external environment factors. In this paper, a novel drowsy student state detection method by integrating deep convolutional neural network is proposed at the first time in the literature. The proposed method avoids the complicated manual feature extraction operation and it can effectively reduce the interference of environmental factors in the application scenarios. Experimental results demonstrate that our approach can achieve high accuracy and lower error rate for drowsy student state detection. In addition, the results also show that our method outperforms traditional methods.

SummaryRouting protocols in wireless sensor networks (WSNs) typically employ a transmitter-oriented approach in which the next hop node is selected based on neighbor or network information. This approach incurs a large overhead when the accurate neighbor information is needed for efficient and reliable routing. In this paper, a novel receiver-oriented load-balancing and reliable routing (RLRR) protocol is proposed. In RLRR, an intermediate node solicits next hop candidates, each of which is to respond with its own backoff time dubbed a temporal gradient (TG). In this way, the next hop is selected without any central coordination on a packet-by-packet basis. Thus, each node needs not maintain any neighbor information. The remaining energy level used to determine the TG is always accurate and up-to-date. Furthermore, neighbor nodes whose hop count is less than the soliciting node participate in the next-hop selection process with loop-free operation guarantee. Comprehensive simulations are carried out to show that RLRR achieves relatively longer network lifetime and higher reliability than other existing schemes. Copyright

No abstract

Conserving energy so as to maximize the postdeployment active lifetime of wireless sensor networks has been one of the key challenges to unlock the potential data gathering sensor networks. One of the approaches to achieve the goal is to make the collaborative strategies on packet transmission and relaying energy efficient. However, the impact of traffic load in the lifetime of sensor networks are not considered in most of the previous research works in this area. In this paper we analyze and illustrate that some heavy traffic sensor nodes, which significantly shorten the network lifetime in the unevenly distributed traffic environments, may determine the lifetime of a sensor network. Thus we propose a dichotomy transmission power control scheme to prolong the lifetime of large-scale wireless sensor networks, which is adaptive to the traffic over the nodes and the distance of the nodes to the sink. Simulation in MATLAB can efficiently improve the lifetime performance of large-scale sensor networks.

No abstract