The energy harvesting cognitive wireless sensor network(EHCWSN) introduces energy harvesting technology and cognitive radio technology into the traditional wireless sensor network(WSN), which significantly prolongs the working life of the sensor node and effectively alleviates the congestion problem of the unlicensed spectrum. As the gap in the NMSEs between TDMA- and STLC-OAC-based strategies was observed to increase as the number of sUAVs increased, it can be concluded that the proposed STLC-OAC strategy is advantageous for UAV-based data collection systems, especially when a large number of sUAVs report the sensing data. Furthermore, the proposed STLC-OAC strategy can reduce the normalized mean square error (NMSE) of the estimated average value of the data relative to that of the TDMA-based method. Using the efficient data collection protocol of the proposed STLC-OAC strategy, the overall operation time for data collection can be significantly reduced relative to s TDMA-based strategy. To this end, we propose an efficient OAC strategy using a space-time line code (STLC) scheme that can achieve a full spatial diversity gain. In this method, multiple single-antenna sensing UAVs (sUAVs) report the sensing data to a two-antenna data-collection UAV (dUAV) through the OAC strategy. To reduce the required data collection time for a time-division multiple access (TDMA)-based protocol, an over-the-air computation (OAC) strategy was employed, and the average values of data computed. In this study, we investigated a data collection system for multiple unmanned aerial vehicles (UAVs) in the sky. Moreover, we discuss the applications of compacted DNNs in various IoT applications and outline future directions. We also elaborate on the diversity of these approaches and make side-by-side comparisons. We categorize compacting-DNNs technologies into three major types: 1) network model compression, 2) Knowledge Distillation (KD), 3) modification of network structures. Hence, this paper presents a comprehensive study on compacting-DNNs technologies. Despite tremendous advances in compacting DNNs, few surveys summarize compacting-DNNs technologies, especially for IoT applications. Therefore, it is a necessity to investigate the technologies to compact DNNs. However, DNNs inevitably bring high computational cost and storage consumption due to the complexity of hierarchical structures, thereby hindering their wide deployment in Internet-of-Things (IoT) devices, which have limited computational capability and storage capacity. This type of noise reducer has got rid of the current situation that the neural network noise reducer consumes too much power and is inefficient, and has certain advantages.ĭeep Neural Networks (DNNs) have shown great success in completing complex tasks. The system is used to eliminate noise in the aerial image. Based on this, a new anti-convergence-convolution neural network noise reduction system for the operation of UAV airborne embedded equipment is proposed. In this paper, how to eliminate the noise of aerial image is to be talked, the multi-channel pruning technology is used to pruning the RnResNet network. Pictures that use aerial drones for aerial photography in rainy weather will appear noise. However, UAV aerial photography is greatly affected by the weather. Especially in the field of aerial remote sensing, the emergence of UAV technology has enabled the geographical information of remote areas that are not concerned to be quickly presented. In the past ten years, civil drone technology has developed rapidly, and UAV (Unmanned Aerial Vehicle) has been widely used in various industries.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |