Fabric handle depends on physical and mechanical properties, which are measured by the two well-know systems, i.e., Kawabata's Evaluation System for Fabrics (KES-F) by Japan and Fabric Assurance by Simple Testing (FAST) by Austria. However, the two systems are too expensive and time-costing. A new comprehensive handle evaluation system for fabrics and yarns (CHES-FY) developed based on the single-test multiple indicator measuring principle can reflect the weight, bending, friction and tension basic mechanical behavior as well as handle through only one pulling-out test.The present paper is to select characteristic indexes from the pulling-out force and distance curve acquired by the CHES-FY system, and the characteristics make a vector which expresses the handle of the fabric based on Karhunen-Loève (K-L) transformation; the other is to make clustering on handle of measured fabrics based on K-means fuzzy clustering. The experiments of thirty fabrics and comparisons between experimental and theoretical results were conducted, which shows that K-means fuzzy clustering algorithm is effective and accurate in sorting fabric handle based on the features selected from the pulling-out force and distance curve of the CHES-FY system.
In order to relieve the problem of unbalanced energy consumption of sensor nodes near the base station in the wireless sensor network, this paper proposes a mobile multi-sink nodes path planning algorithm with energy balance (hexHPSO). An optimization model is established by considering the energy consumption of each group, network lifetime, and movement path of the mobile sink nodes. Meanwhile, a hybrid positive and negative particle swarm optimization algorithm (HPNPSOA) is proposed to solve the optimization model to obtain a path with optimal grid traversal order and optimal parking position. Compared with the DOSM algorithm, GLRM algorithm, and RWM algorithm, the hexHPSO algorithm improves the network lifetime by 68%. The experimental results show that the hexHPSO algorithm can effectively balance the energy consumption, alleviate hotspot phenomenon, and extend the network lifetime. INDEX TERMS Wireless sensor networks, mobile multi-sink nodes, path planning, hybrid positive and negative particle swarm optimization, network lifetime.
Corn diseases are one of the significant constraints to high–quality corn production, and accurate identification of corn diseases is of great importance for precise disease control. Corn anthracnose and brown spot are typical diseases of corn, and the early symptoms of the two diseases are similar, which can be easily misidentified by the naked eye. In this paper, to address the above problems, a three–dimensional–two–dimensional (3D–2D) hybrid convolutional neural network (CNN) model combining a band selection module is proposed based on hyperspectral image data, which combines band selection, attention mechanism, spatial–spectral feature extraction, and classification into a unified optimization process. The model first inputs hyperspectral images to both the band selection module and the attention mechanism module and then sums the outputs of the two modules as inputs to a 3D–2D hybrid CNN, resulting in a Y–shaped architecture named Y–Net. The results show that the spectral bands selected by the band selection module of Y–Net achieve more reliable classification performance than traditional feature selection methods. Y–Net obtained the best classification accuracy compared to support vector machines, one–dimensional (1D) CNNs, and two–dimensional (2D) CNNs. After the network pruned the trained Y–Net, the model size was reduced to one–third of the original size, and the accuracy rate reached 98.34%. The study results can provide new ideas and references for disease identification of corn and other crops.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.