Citrus flies are important quarantine pests in citrus plantations. Electronic traps (e-traps) based on computer vision are the most popular types of equipment for monitoring them. However, most current e-traps are inefficient and unreliable due to requiring manual operations and lack of reliable detection and identification algorithms of citrus fly images. To address these problems, this paper presents a monitoring scheme based on automatic e-traps and novel recognition algorithms. In this scheme, the prototype of an automatic motor-driven e-trap is firstly designed based on a yellow sticky trap. A motor autocontrol algorithm based on Local Binary Pattern (LBP) image analysis is proposed to automatically replace attractants in the e-trap for long-acting work. Furthermore, for efficient and reliable statistics of captured citrus flies, based on the differences between two successive sampling images of the e-trap, a simple and effective detection algorithm is presented to continuously detect the newly captured citrus flies from the collected images of the e-trap. Moreover, a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) is proposed to exploit discriminative local features of citrus fly images to recognize the citrus flies in the images. Finally, extensive simulation experiments validate the feasibility and efficiency of the designed e-trap prototype and its autocontrol algorithm, as well as the reliability and effectiveness of the proposed detection and recognition algorithms for citrus flies.
11 December 2017 in Physica A: Statistical Mechanics and its Applications
The Energy Finite Element Analysis (EFEA) has been developed for computing the structural vibration and the interior noise level of complex structural-acoustic systems by solving numerically governing differential equations with energy densities as primary variables. In this paper a complete simulation process for evaluating airborne noise in an automotive vehicle is presented and validated through extensive comparison to test data. The theoretical elements associated with the important paths of the noise transfer from the exterior of the vehicle to the interior acoustic space are discussed. The steps required for developing an EFEA model for a vehicle are presented. The model is developed based on the physical construction of the vehicle system and no test measurements are utilized for adjusting the numerical model. An acoustic noise source is placed at each one of four vehicle locations (engine compartment, front left tire patch, rear left tire patch, and exhaust) where typical exterior noise sources are present in an operating vehicle. The exterior acoustic field is evaluated numerically by the Energy Boundary Element Analysis (EBEA). The acoustic loading from each source is applied on all of the outer parts of the vehicle EFEA model and the interior noise level is computed in the frequency range of 200Hz - 8,000Hz. Predictions for the interior noise level (expressed in a noise reduction format) are compared with test results for all four excitations. The ability of the EFEA method to conduct a panel contribution analysis is used for identifying the panels which contribute the most to the power flow from the structure to the interior acoustic space. Such information is useful in making design decisions when implementing noise mitigation strategies.
The platoon control of connected and automated vehicles is one of the important research directions in the area of intelligent transportation systems. In order to achieve better platoon control of connected and automated vehicles, we propose a hybrid communication architecture that combines the high stability of VANET and the long-distance transmission of cellular networks. Based on the new communication architecture, we used the Two-step clustering method to cluster the vehicle platoon and further established a new vehicle control strategy with cluster head as the following target. Finally, through simulation, the fluctuation characteristics of the traffic flow under the new control strategy and the traditional car-following strategies are compared. The results show that the new control strategy constructed in this paper has smaller velocity fluctuations compared to the traditional car-following strategies. Also, less time is needed for the new control strategy to stabilize traffic flow.