Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

An Efficient Method for Identifying Lower Limb Behavior Intentions Based on Surface Electromyography

Surface electromyography(sEMG)is widely used for analyzing and controlling lower limb assisted exoskeleton robots.Behavior intention recognition based on sEMG is of great significance for achieving intelligent prosthetic and exoskeleton control.Achieving highly efficient recognition while improving performance has always been a significant challenge.To address this,we propose an sEMG-based method called Enhanced Residual Gate Network(ERGN)for lower-limb behavioral intention recognition.The proposed network combines an attention mechanism and a hard threshold function,while combining the advantages of residual structure,which maps sEMG of multiple acquisition channels to the lower limb motion states.Firstly,continuous wavelet transform(CWT)is used to extract signals features from the collected sEMG data.Then,a hard threshold function serves as the gate function to enhance signals quality,with an attention mechanism incorporated to improve the ERGN’s performance further.Experimental results demonstrate that the proposed ERGN achieves extremely high accuracy and efficiency,with an average recognition accuracy of 98.41%and an average recognition time of only 20 ms-outperforming the state-of-the-art research significantly.Our research provides support for the application of lower limb assisted exoskeleton robots.

Full ranking procedure based on best and worst frontiers

In the traditional data envelopment analysis （DEA） structure, the efficiency score for one decision making unit （DMU） is calculated by measuring the distance of the evaluated DMU to the best practice frontier. Recent researches have provided the reasonability of considering the worst practice frontier as a supple- ment to the traditional DEA techniques. The existing researches take only one type of frontier into account, and they cannot com- pare the evaluated DMU with both the best and the worst perform- ing DMUs. A DEA-based procedure is developed to consider the best and the worst frontiers in the same scenario where the ratio of two distances （RDS） measure is proposed. The principal appli- cation of this approach is for ranking, and, as a complement tool, for performance evaluation. The proposed approach can be used in a wide range of applications such as the performance evaluation of employees and others. Finally, a bookstore data set is used to illustrate the proposed approach.

A hydroxyl radical detection system using gas expansion and fast gating laser-induced fluorescence techniques

An OH radical measurement instrument based on Fluorescence Assay by Gas Expansion（FAGE）has been developed in our laboratory.Ambient air is introduced into a low-pressure fluorescence cell through a pinhole aperture and irradiated by a dye laser at a high repetition rate of 8.5 k Hz.The OH radical is both excited and detected at 308 nm using A-X（0,0）band.To satisfy the high efficiency needs of fluorescence collection and detection,a 4-lens optical system and a self-designed gated photomultiplier（PMT）is used,and gating is actualized by switching the voltage applied on the PMT dynodes.A micro channel photomultiplier（MCP）is also prepared for fluorescence detection.Then the weak signal is accumulated by a photon counter in a specific timing.The OH radical excitation spectrum range in the wavelength of 307.82–308.2 nm is detected and the excited line for OH detection is determined to be Q1（2）line.The calibration of the FAGE system is researched by using simultaneous photolysis of H2O and O2.The minimum detection limit of the instrument using gated PMT is determined to be 9.4×10~5molecules/cm^3,and the sensitivity is 9.5×10^（-7）cps/（OH·cm^（-3））,with a signal-to-noise ratio of 2 and an integration time of 60 sec,while OH detection limit and the detection sensitivity using MCP is calculated to be 1.6×10~5molecules/cm^3and 2.3×10^（-6）cps/（OH·cm^（-3））.The laboratory OH radical measurement is carried out and results show that the proposed system can be used for atmospheric OH radical measurement.