An improved lightweight network based on deep learning for grape recognition in unstructured environments

In unstructured environments,dense grape fruit growth and the presence of occlusion cause difficult recognition problems,which will seriously affect the performance of grape picking robots.To address these problems,this study improves the YOLOx-Tiny model and proposes a new grape detection model,YOLOX-RA,which can quickly and accurately identify densely growing and occluded grape bunches.The proposed YOLOX-RA model uses a 3×3 convolutional layer with a step size of 2 to replace the focal layer to reduce the computational burden.The CBS layer in the ResBlock_Body module of the second,third,and fourth layers of the backbone layer is removed,and the CSPLayer module is replaced by the ResBlock-M module to speed up the detection.An auxiliary network(AlNet)with the remaining network blocks was added after the ResBlock-M module to improve the detection accuracy.Two depth-separable convolutions(DsC)are used in the neck module layer to replace the normal convolution to reduce the computational cost.We evaluated the detection performance of SSD,YOLOv4 SSD,YOLOv4-Tiny,YOLO-Grape,YOLOv5-X,YOLOX-Tiny,and YOLOX-RA on a grape test set.The results show that the YOLOX-RA model has the best detection performance,achieving 88.75%mAP,a recognition speed of 84.88 FPS,and model size of 17.53 MB.It can accurately detect densely grown and shaded grape bunches,which can effectively improve the performance of the grape picking robot.

Metagenomic Profiling of Viruses Associated with Rhipicephalus microplus Ticks in Yunnan Province,China

Ticks are well known as vectors of many viruses which usually do great harm to human and animal health.Yunnan Province,widely covered by flourishing vegetation and mainly relying on farming husbandry,is abundant with Rhipicephalus microplus ticks.Therefore,it is of great significance to characterize the viral profile present in R.microplus parasitizing on cattle in Yunnan Province.In this study,a total of 7387 R.microplus ticks were collected from cattle and buffalo in the northwest and southeast areas of Yunnan Province from 2015 to 2017.We investigated the virome of R.microplus using next-generation sequencing(NGS)and the prevalence of important identified viruses among tick groups by RT-PCR.It revealed the presence of diverse virus concerning chu-,rhabdo-,phlebo-,flavi-and parvo-viruses in Yunnan.These viruses consist of single-stranded,circular and segmented sense RNAs,showing a greatly diversity in genomic organization.Furthermore,continuous epidemiological survey among ticks reveals broad prevalence of three viruses(Yunnan mivirus 1,Wuhan tick vrius 1 and YN tick-associated phlebovirus 1)and two possible prevalent viruses including a flavivirus-like segmented virus(Jingmen tick virus)and a bovine hokovirus 2 in Yunnan.Serological investigation among cattle indicates that these identified viruses may be infectious to cattle and can elicit corresponding antibody.Our findings on R.microplus-associated viral community will contribute to the prevention of viral disease and tracking the viral evolution.Further analysis is needed to better elucidate the pathogenicity and natural circulation of these viruses.

Highly sensitive colorimetric detection of NH3 based on Au@Ag@AgCl core-shell nanoparticles

Abstract:As an important component of the atmosphere,ammonia(NH_(3))plays a very important role in maintaining the balance of environment.However,it is also one of the most toxic gases that can cause damage to the human respiratory system and mucous membranes even at low concentrations.As such,development of highly sensitive and selective NH_(3)sensors is of high significance for environmental monitoring and health maintenance.Herein,we have synthesized Au@Ag@Ag Cl core-shell nanoparticles(NPs)by oxidative etching and precipitating Au@Ag core-shell NPs using FeCl3 and further used them as optical probes for the colorimetric detection of NH_(3).The sensing mechanism is based on the fact that the etching of NH_(3)on AgCl and Ag shell leads to the variations of ingredients and core-to-shell ratio of the Au@Ag@AgCl NPs,thereby inducing noticeable spectral and color changes.By replacing the outmost layer of Ag with AgCl,not only is the stability of the sensor against oxygen significantly enhanced,but also is the sensitivity of the method improved.The method exhibits good linear relationship for the detection of NH_(3)from 0 to 5000 mmol/L with the limit of detection of 6.4 mmol/L.This method was successfully applied to the detection of simulated air polluted by NH_(3),indicating its practical applicability for environmental monitoring.This method shows great potential for on-site NH_(3)detection particularly in remote area,where a simple,fast,low-cost,and easy-to-handle method is highly desirable.