No abstract

No abstract

No abstract

In wireless sensor networks (WSNs), collecting data with mobile sinks is an effective way to solve the ''energy hole problem''. However, most of existing algorithms of mobile sinks ignore the load balance of rendezvous nodes, which will significantly shorten the network lifetime. Moreover, most mobile sinks are usually required to visit locations of sensor nodes without taking advantage of their communication ranges. Therefore, this paper proposes an energy-efficient trajectory planning algorithm (EETP) based on multi-objective particle swarm optimization (MOPSO) to shorten the trajectory length of the mobile sink and balance the load of rendezvous nodes. EETP aims to reduce the delay in data delivery and prolong the network lifetime. To shorten the trajectory length of the mobile sink, we design a mechanism to select potential visiting points within communication overlapping ranges of sensor nodes, rather than locations of sensor nodes. Additionally, according to trajectory characteristics of the mobile sink, we design an effective trajectory encoding method that can generate a trajectory containing an unfixed number of visiting points. The simulation results show that the proposed EETP is superior to existing WRP, CB and the MOPSO-based algorithm, in terms of delay in data delivery, network lifetime and energy consumption. INDEX TERMS Mobile sink, MOPSO, load balance of rendezvous nodes, trajectory planning.

Symptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have been proven to be effective in image classification, but their use to identify nutrient deficiencies in rice has received little attention. In the present study, we explore the accuracy of different DCNNs for diagnosis of nutrient deficiencies in rice. A total of 1818 photographs of plant leaves were obtained via hydroponic experiments to cover full nutrition and 10 classes of nutrient deficiencies. The photographs were divided into training, validation, and test sets in a 3 : 1 : 1 ratio. Fine-tuning was performed to evaluate four state-of-the-art DCNNs: Inception-v3, ResNet with 50 layers, NasNet-Large, and DenseNet with 121 layers. All the DCNNs obtained validation and test accuracies of over 90%, with DenseNet121 performing best (validation accuracy = 98.62 ± 0.57%; test accuracy = 97.44 ± 0.57%). The performance of the DCNNs was validated by comparison to color feature with support vector machine and histogram of oriented gradient with support vector machine. This study demonstrates that DCNNs provide an effective approach to diagnose nutrient deficiencies in rice.