Maize Leaf Disease Recognition Based on Improved Convolutional Neural Network ShuffleNetV2.

The occurrence of maize diseases is frequent but challenging to manage. Traditional identification methods have low accuracy and complex model structures with numerous parameters, making them difficult to implement on mobile devices. To address these challenges, this paper proposes a corn leaf disease recognition model SNMPF based on convolutional neural network ShuffleNetV2. In the down-sampling module of the ShuffleNet model, the max pooling layer replaces the deep convolutional layer to perform down-sampling. This improvement helps to extract key features from images, reduce the overfitting of the model, and improve the model's generalization ability. In addition, to enhance the model's ability to express features in complex backgrounds, the Sim AM attention mechanism was introduced. This mechanism enables the model to adaptively adjust focus and pay more attention to local discriminative features. The results on a maize disease image dataset demonstrate that the SNMPF model achieves a recognition accuracy of 98.40%, representing a 4.1 percentage point improvement over the original model, while its size is only 1.56 MB. Compared with existing convolutional neural network models such as EfficientNet, MobileViT, EfficientNetV2, RegNet, and DenseNet, this model offers higher accuracy and a more compact size. As a result, it can automatically detect and classify maize leaf diseases under natural field conditions, boasting high-precision recognition capabilities. Its accurate identification results provide scientific guidance for preventing corn leaf disease and promote the development of precision agriculture.

Identification of leaf diseases in field crops based on improved ShuffleNetV2.

Rapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lightweight crop leaf disease recognition model based on improved ShuffleNetV2. First, the repetition number and the number of output channels of the basic module of the ShuffleNetV2 model are redesigned to reduce the model parameters to make the model more lightweight while ensuring the accuracy of the model. Second, the residual structure is introduced in the basic feature extraction module to solve the gradient vanishing problem and enable the model to learn more complex feature representations. Then, parallel paths were added to the mechanism of the efficient channel attention (ECA) module, and the weights of different paths were adaptively updated by learnable parameters, and then the efficient dual channel attention (EDCA) module was proposed, which was embedded into the ShuffleNetV2 to improve the cross-channel interaction capability of the model. Finally, a multi-scale shallow feature extraction module and a multi-scale deep feature extraction module were introduced to improve the model's ability to extract lesions at different scales. Based on the above improvements, a lightweight crop leaf disease recognition model REM-ShuffleNetV2 was proposed. Experiments results show that the accuracy and F1 score of the REM-ShuffleNetV2 model on the self-constructed field crop leaf disease dataset are 96.72% and 96.62%, which are 3.88% and 4.37% higher than that of the ShuffleNetV2 model; and the number of model parameters is 4.40M, which is 9.65% less than that of the original model. Compared with classic networks such as DenseNet121, EfficientNet, and MobileNetV3, the REM-ShuffleNetV2 model not only has higher recognition accuracy but also has fewer model parameters. The REM-ShuffleNetV2 model proposed in this study can achieve accurate identification of crop leaf disease in complex field backgrounds, and the model is small, which is convenient to deploy to the mobile end, and provides a reference for intelligent diagnosis of crop leaf disease.

Distributed global output-feedback formation control without velocity measurement for multiple unmanned surface vehicles.

This article studies the distributed formation control problem for multiple unmanned surface vehicles (USVs) considering uncertain coefficient matrixes, unmeasurable velocities, and time-varying disturbances. The main contributions are as follows: First, a global coordinate translation is proposed to partially linearize the nonlinear dynamic model equipped with the unmeasurable velocity. Second, based on the global coordinate translation, a novel type of fixed-time extended two-state observer (FTETSO) is developed to estimate unmeasurable velocities and total disturbances for each vehicle. Wherein, the estimation errors will converge to zero within a fixed time. Meanwhile, considering estimation accuracy, a two-state extension is proposed to replace a single-state extension. Third, using a sliding model-based control technique, an FTETSO-based distributed global output-feedback fixed-time formation controller (GOFFC) is elaborately developed. Based on the proposed controller, the fixed-time convergence of the closed-loop system is ensured. Finally, the validity and stability of the proposed control approach are verified by simulations.

Interleaved Periodic Event-Triggered Communications-Based Distributed Formation Control for Cooperative Unmanned Surface Vessels.

This article addresses the distributed formation control issue of cooperative unmanned surface vessels (USVs) under interleaved periodic event-triggered communications. First, an adaptive event-based control protocol is designed, where the event-based neural network (NN) scheme is developed to compensate for uncertain model dynamics. Upon the designed control protocol, an interleaved periodic event-triggered mechanism (IPETM) is subsequently proposed to achieve the communication objective. Unlike the common continuous event-triggered methods and periodic event-triggered methods, in which multiple nodes are allowed to trigger their events at the same time, the proposed IPETM ensures that USVs detect their events at different times to avoid the simultaneous event triggering of different nodes. By this virtue, traffic jamming in common wireless environments can be prevented, such that potential communication delays and faults are naturally avoided. In addition, the event detecting instants of the presented IPETM are also discrete and periodic, such that it can be performed under low-computational frequencies. Through Lyapunov-based analysis, it is verified that all closed-loop signals can converge to an arbitrary small compact set with exponential convergence rates. Simulation results demonstrate the effectiveness and superiority of the proposed control scheme.

Automatic vessel plate number recognition for surface unmanned vehicles with marine applications.

In the practical application scenarios of USVs, it is necessary to identify a vessel in order to accomplish tasks. Considering the sensors equipped on the USV, visible images provide the fastest and most efficient way of determining the hull number. The current studies divide the task of recognizing vessel plate number into two independent subtasks: text localization in the image and its recognition. Then, researchers are focusing on improving the accuracy of localization and recognition separately. However, these methods cannot be directly applied to USVs due to the difference between these two application scenarios. In addition, as the two independent models are serial, there will be inevitable propagation of error between them, as well as an increase in time costs, resulting in a less satisfactory performance. In view of the above, we proposed a method based on object detection model for recognizing vessel plate number in complicated sea environments applied to USVs. The accuracy and stability of model have been promoted by recursive gated convolution structure, decoupled head, reconstructing loss function, and redesigning the sizes of anchor boxes. To facilitate this research, a vessel plate number dataset is established in this paper. Furthermore, we conducted a experiment utilizing a USV platform in the South China Sea. Compared with the original YOLOv5, the mAP (mean Average Precision) value of proposed method is increased by 6.23%. The method is employed on the "Tian Xing" USV platform and the experiment results indicates both the ship and vessel plate number can be recognized in real-time. In both the civilian and military sectors, this has a great deal of significance.

Mediation Effect of Corporate Tax Burden and the Relationship between Environmental Regulation and Firm Performance.

This paper took the panel data of 1052 heavily-polluting listed companies from both the Shanghai and Shenzhen Stock Exchange from 2010 to 2017 to empirically analyze the impact of environmental regulation (ERG) on firm performance (FP). The article introduces a mediating effect model to test the mediating role of corporate tax burden (ETR) within the relationship between ERG on FP. The results showed that: (1) ERG has exerted a significant enhancement effect on the performance of heavily polluted firms via the ETR reduction mechanism. (2) The mediating effect of ETR depends on the duration of ERG. A significant time lag exists before the mediating effect starts to work, and the magnitude of the mediating effect increases with the time lag from the execution of the ERG. (3) The mediating effect of ETR varies significantly with the nature of corporate property rights. It is significant for the state-owned firms, while for non-state-owned firms, there is no evidence supporting the existence of the mediating effect of ETR despite ERG still having a significant direct-impact on FP. Based on these findings, we discuss the policy suggestion to optimize the impact of environmental regulation policies in terms of incentivizing the green development of polluting firms.

Adaptive model-parameter-free fault-tolerant trajectory tracking control for autonomous underwater vehicles.

This paper provides a model-parameter-free control strategy for the trajectory tracking problem of the autonomous underwater vehicle exposed to external disturbances and actuator failures. Two control architectures have been constructed such that the system states could be forced to the desired trajectories with acceptable performance. By combining sliding mode control (SMC) technology and adaptive algorithm, the first control architecture is developed for tracking missions under healthy actuators. Taking actuator failures scenario into account, system reliability is improved considerably by the utilization of a passive fault-tolerant technology in the second controller. Benefitting from properties of Euler-Lagrange systems, the nonlinear dynamics of the underwater vehicles could be handled properly such that the proposed controllers could be developed without model parameters. Finally, the validity of the proposed controllers is demonstrated by theoretical analysis and numerical simulations.

Bioremediation capability evaluation of benzene and sulfolane contaminated groundwater: Determination of bioremediation parameters.

Benzene and sulfolane are commonly used but hazardous chemicals in the petrochemical industry and their leakage and inappropriate disposal certainly causes serious soil and groundwater contamination. In this research, the bioremediation potential of groundwater contaminated with benzene and sulfolane was evaluated, and the operating parameters for bioremediation were established through laboratory batch experiments. Among the various bacterial consortia, the bacterial population of monitoring well c (MWc) contained the highest sulfolane and benzene removal efficiencies. When the dissolved oxygen (DO) level was >1 mg L-1, the bacterial population of MWc showed excellent removal efficiencies toward high and low concentrations of benzene and sulfolane. The C:N:P ratio of 100:10:1 in media facilitated sulfolane and benzene biodegradation, and the degradation time was greatly reduced. Adding additional phosphate into real groundwater could slightly increase benzene removal efficiency. Trace elements only slightly enhanced benzene degradation. On the contrary, additional phosphate and trace elements supplementary did not enhance sulfolane degradation. However, sulfolane removal efficiency could be significantly improved through bioaugmentation of specific sulfolane degrading bacterium and 100% sulfolane removal efficiency was achieved.

Recipes for simulated vomitus.

We developed and demonstrated the stability of recipes for simulated vomitus for use in experiments characterizing occupational exposures to body fluid during simulated healthcare activities. The recipes can be easily adapted to make other simulated bodily fluids at low costs and surrogates added to facilitate detection.

Environmental and body contamination from cleaning vomitus in a health care setting: A simulation study.

BACKGROUND: Environmental service workers may be exposed to pathogens during the cleaning of pathogen-containing bodily fluids. METHODS: Participants with experience cleaning hospital environments were asked to clean simulated, fluorescein-containing vomitus using normal practices in a simulated patient room. Fluorescein was visualized in the environment and on participants under black lights. Fluorescein was quantitatively measured on the floor, in the air, and on gloves and shoe covers. RESULTS: In all 21 trials involving 7 participants, fluorescein was found on the floor after cleaning and on participants' gloves. Lower levels of floor contamination were associated with the use of towels to remove bulk fluid (ρ = -0.56, P = .01). Glove contamination was not associated with the number or frequency of contacts with environmental surfaces, suggesting contamination occurs with specific events, such as picking up contaminated towels. Fluorescein contamination on shoe covers was measured in 19 trials. Fluorescein was not observed on participants' facial personal protective equipment, if worn, or faces. Contamination on other body parts, primarily the legs, was observed in 8 trials. Fluorescein was infrequently quantified in the air. CONCLUSIONS: Using towels to remove bulk fluid prior to mopping is part of the recommended cleaning protocol and should be used to minimize residual contamination. Contamination on shoes and the floor may serve as reservoirs for pathogens.

Wake structure and hydrodynamic performance of flapping foils mimicking fish fin kinematics.

Numerical simulations are used to investigate the wake structure and hydrodynamic performance of bionic flapping foils. The study is motivated by the quest to understand the fluid dynamics of fish fins and use it in the underwater propulsion. The simulations employ an immersed boundary method that makes it possible to simulate flows with complex moving boundaries on fixed Cartesian grids. A detailed analysis of the vortex topology shows that the wake of flapping foils is dominated by two sets of complex shaped vortex rings that convect at oblique angles to the wake centerline. The wake of these flapping foils is characterized by two oblique jets. Simulations are also used to examine the wake vortex and hydrodynamic performance over a range of Strouhal numbers and maximum pitch angles and the connection between the foil kinematics, vortex dynamics and force production is discussed. The results show that the variety law of the hydrodynamic performance with kinematic parameters strongly depends on the flow dynamics underlying the force production, including the orientation, interconnection and dissipation rate of the vortex rings.

Contact patterns during cleaning of vomitus: A simulation study.

BACKGROUND: Environmental service workers cleaning bodily fluids may transfer pathogens through the environment and to themselves through contacts. METHODS: Participants with experience in cleaning of hospital environments were asked to clean simulated vomitus using normal practices in a simulated patient room while being videorecorded. Contacts with environmental surfaces and self were later observed. RESULTS: In 21 experimental trials with 7 participants, environmental surfaces were contacted 26.8 times per trial, at a frequency of 266 contacts per hour, on average. Self-contact occurred in 9 of 21 trials, and involved 1-18 contacts, mostly to the upper body. The recommended protocol of cleaning bodily fluids was followed by a minority of participants (2 of 7), and was associated with fewer surface contacts, improved cleaning quality, and different tool use. Participants used different cleaning practices, but each employed similar practices each time they performed an experimental trial. CONCLUSIONS: Training in the use of the recommended protocol may standardize cleaning practices and reduce the number of surface contacts.

Numerical study on the hydrodynamics of thunniform bio-inspired swimming under self-propulsion.

Numerical simulations are employed to study the hydrodynamics of self-propelled thunniform swimming. The swimmer is modeled as a tuna-like flexible body undulating with kinematics of thunniform type. The wake evolution follows the vortex structures arranged nearly vertical to the forward direction, vortex dipole formation resulting in the propulsion motion, and finally a reverse Kármán vortex street. We also carry out a systematic parametric study of various aspects of the fluid dynamics behind the freely swimming behavior, including the swimming speed, hydrodynamic forces, power requirement and wake vortices. The present results show that the fin thrust as well as swimming velocity is an increasing function of both tail undulating amplitude Ap and oscillating amplitude of the caudal fin θm. Whereas change on the propulsive performance with Ap is associated with the strength of wake vortices and the area of suction region on the fin, the swimming performance improves with θm due to the favorable tilting of the fin that make the pressure difference force more oriented toward the thrust direction. Moreover, the energy loss in the transverse direction and the power requirement increase with Ap but decrease with θm, and this indicates that for achieving a desired swimming speed increasing θm seems more efficiently than increasing Ap. Furthermore, we have compared the current simulations with the published experimental studies on undulatory swimming. Comparisons show that our work tackles the flow regime of natural thunniform swimmers and follows the principal scaling law of undulatory locomotion reported. Finally, this study enables a detailed quantitative analysis, which is difficult to obtain by experiments, of the force production of the thunniform mode as well as its connection to the self-propelled swimming kinematics and vortex wake structure. The current findings help provide insights into the swimming performance and mechanisms of self-propelled thunniform locomotion.

Bipaddled anterolateral thigh perforator flap for simultaneous reconstruction of bilateral buccal defects following oral cancer ablation or release of oral submucous fibrosis.

It is a challenge to simultaneously reconstruct bilateral buccal defects following oral cancer ablation or release of oral submucous fibrosis. In this study, we report two cases where bipaddled anterolateral thigh perforator flaps were used to resurface two separate buccal defects.

Free anterolateral thigh flap harvesting from paralytic limbs in post-polio syndrome.

We report two cases of poliomyelitis in which an anterolateral thigh myocutaneous free flap was harvested from the paralytic limb for oral reconstruction. We observed a decrease in the pedicle diameter of the anterolateral thigh flap, but the blood supply to the skin paddle was adequate.

Fluid Dynamics of Biomimetic Pectoral Fin Propulsion Using Immersed Boundary Method.

Numerical simulations are carried out to study the fluid dynamics of a complex-shaped low-aspect-ratio pectoral fin that performs the labriform swimming. Simulations of flow around the fin are achieved by a developed immersed boundary (IB) method, in which we have proposed an efficient local flow reconstruction algorithm with enough robustness and a new numerical strategy with excellent adaptability to deal with complex moving boundaries involved in bionic flow simulations. The prescribed fin kinematics in each period consists of the power stroke and the recovery stroke, and the simulations indicate that the former is mainly used to provide the thrust while the latter is mainly used to provide the lift. The fin wake is dominated by a three-dimensional dual-ring vortex wake structure where the partial power-stroke vortex ring is linked to the recovery-stroke ring vertically. Moreover, the connection of force production with the fin kinematics and vortex dynamics is discussed in detail to explore the propulsion mechanism. We also conduct a parametric study to understand how the vortex topology and hydrodynamic characteristics change with key parameters. The results show that there is an optimal phase angle and Strouhal number for this complicated fin. Furthermore, the implications for the design of a bioinspired pectoral fin are discussed based on the quantitative hydrodynamic analysis.

A Sea-Sky Line Detection Method for Unmanned Surface Vehicles Based on Gradient Saliency.

Special features in real marine environments such as cloud clutter, sea glint and weather conditions always result in various kinds of interference in optical images, which make it very difficult for unmanned surface vehicles (USVs) to detect the sea-sky line (SSL) accurately. To solve this problem a saliency-based SSL detection method is proposed. Through the computation of gradient saliency the line features of SSL are enhanced effectively, while other interference factors are relatively suppressed, and line support regions are obtained by a region growing method on gradient orientation. The SSL identification is achieved according to region contrast, line segment length and orientation features, and optimal state estimation of SSL detection is implemented by introducing a cubature Kalman filter (CKF). In the end, the proposed method is tested on a benchmark dataset from the "XL" USV in a real marine environment, and the experimental results demonstrate that the proposed method is significantly superior to other state-of-the-art methods in terms of accuracy rate and real-time performance, and its accuracy and stability are effectively improved by the CKF.

Self-inflicted, trans-optic canal, intracranial penetrating injury with a ballpoint pen.

Trans-orbital penetrating injuries are not common. If not promptly treated, these injuries can lead to serious disabilities and even death. A 60-year-old man, who had multiple underlying diseases, was admitted to our medical ward for the treatment of aspiration pneumonia; he attempted suicide by inserting a ballpoint pen into his left eye. CT of the brain showed a foreign body penetrating through the left optic canal into the intracranial parasellar region without obvious intracranial haemorrhage. The foreign body was withdrawn smoothly at bedside without a craniotomy. The patient was then transferred to the ICU for neuro-observation. The patient recovered with complete left ophthalmoplegia but intact visual function. Acute management of a trans-orbital penetrating injury involves prompt neuroimaging examinations and knowledge of common recurring patterns of injury. All clinicians should be aware of the psychological condition of each patient, and suicide precautions should be considered during clinical practice.

Hydrodynamic analysis of rigid and flexible pectoral fins.

Numerical study on unsteady hydrodynamic characteristics of rigid and flexible pectoral fins in viscous flow-field was performed in the present study. The effect of key kinematical parameters on the propulsion performance was analyzed. The propulsion mechanism was explored by evolution of wake vortices. Computational results revealed that optimal combination for investigated parameters was U = 4C, Φ(FLA) = 45°, ΔΦ(FL) = 60° and α(0) = 0.2. Wake vortices were shed from two edges of fin and fin tip and convect downstream as well as laterally. For flexible pectoral fin, the shedding time was delayed and shed wake vortices keep longer time near the fin that led to difference in variation amplitude of hydrodynamics as compared to rigid fin. The hydrodynamic performance of flexible fin was superior to that of rigid fin for low incoming velocity. However, the opposite situation occured for high incoming velocity.

Dose-response models for selected respiratory infectious agents: Bordetella pertussis, group a Streptococcus, rhinovirus and respiratory syncytial virus.

BACKGROUND: Dose-response assessment is one step in quantitative microbial risk assessment (QMRA). Four infectious microbes capable of causing respiratory diseases important to public health, and for which dose-response functions have not been available are: Bordetella pertussis (whooping cough), group A Streptococcus (pharyngitis), rhinovirus (common cold) and respiratory syncytial virus (common cold). The objective of this study was to fit dose-response functions for these microbes to published experimental data. METHODS: Experimental infectivity data in human subjects and/or animal models were identified from the peer-reviewed literature. The exponential and beta-Poisson dose-response functions were fitted using the method of maximum likelihood, and models compared by Akaike's Information Criterion. RESULTS: Dose-response functions were identified for each appropriate data set for the four infectious microbes. Statistical and graphical measures of fit are presented. CONCLUSIONS: With the fitted dose-response functions it will be possible to perform QMRA for these microbes. The dose-response functions, however, have a number of limitations associated with the route of exposure, use of animal hosts, and quality of fit. As a result, thoughtfulness must be used in selecting one dose-response function for a QMRA, and the function should be recognized as a significant source of uncertainty. Nonetheless, QMRA offers a transparent, systematic framework within which to understand the mechanisms of disease transmission, and evaluate interventions.