Amount Of Calculation Research Articles

An efficient and lightweight banana detection and localization system based on deep CNNs for agricultural robots

Accurate detection and localization of fruits in natural environments is a key step for fruit picking robots to achieve precise harvesting. However, existing banana detection and positioning methods have two main limitations in practical applications: a large number of model parameters that make deployment difficult, and a need for performance improvement. To tackle the above issues, a high-precision and lightweight banana bunch recognition and localization method was proposed and deployed on edge devices for application. First, a Slim-Banana model was proposed based on the improvement of YOLOv8l. In order to reduce the model calculation amount and maintain high performance, GSConv was introduced in the Slim-Banana model to replace the standard convolution, and combined with grouped convolution and spatial convolution. At the same time, the cross-stage local network (GSCSP) module was designed to reduce the computational complexity and the complexity of the network structure through a single-stage aggregation method. Then, the RealSense depth sensor is combined with TOF technology to perform image registration and 3D localization of the banana. Finally, the pipeline is deployed on the Nvidia Orin NX edge device and its performance and resource consumption in actual work are deeply analyzed. Experimental results show that the detection precision, recall, mAP and inference time of our method are 0.947, 0.948, 0.98 and 113.6ms respectively, the network memory size required is 4449MiB, and the average localization errors in the X-axis, Y-axis and Z-axis directions are 13.47mm, 12.87mm and 13.87mm respectively. To our knowledge, this is the first work that implements banana detection and localization on edge devices. Experimental results show that compared with existing methods, our method achieves better performance in complex orchard environments, achieving efficient and lightweight banana recognition and localization.

Adaptive condition-aware high-dimensional decoupling remote sensing image object detection algorithm

Remote Sensing Image Object Detection (RSIOD) faces the challenges of multi-scale objects, dense overlap of objects and uneven data distribution in practical applications. In order to solve these problems, this paper proposes a YOLO-ACPHD RSIOD algorithm. The algorithm adopts Adaptive Condition Awareness Technology (ACAT), which can dynamically adjust the parameters of the convolution kernel, so as to adapt to the objects of different scales and positions. Compared with the traditional fixed convolution kernel, this dynamic adjustment can better adapt to the diversity of scale, direction and shape of the object, thus improving the accuracy and robustness of Object Detection (OD). In addition, a High-Dimensional Decoupling Technology (HDDT) is used to reduce the amount of calculation to 1/N by performing deep convolution on the input data and then performing spatial convolution on each channel. When dealing with large-scale Remote Sensing Image (RSI) data, this reduction in computation can significantly improve the efficiency of the algorithm and accelerate the speed of OD, so as to better adapt to the needs of practical application scenarios. Through the experimental verification of the RSOD RSI data set, the YOLO-ACPHD model in this paper shows very satisfactory performance. The F1 value reaches 0.99, the Precision value reaches 1, the Precision-Recall value reaches 0.994, the Recall value reaches 1, and the mAP value reaches 99.36%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, which indicates that the model shows the highest level in the accuracy and comprehensiveness of OD.

Mechanism of uneven densification in PBX compression molding

The uneven density distribution during compression molding of polymer bonded explosive (PBX ) seriously affects the mechanical properties of high-energy material components and the precise output ability of shock waves. Investigating the multi-scale densification evolution laws and density non-uniformity mechanism of PBX composite powders is crucial for understanding the density non-uniformity phenomenon of energetic material components and evaluating the differences in macroscopic mechanical response. To this end, we developed a new dual-scale 3D discrete element method (DEM) model for PBX compression molding, which can increase the computational quantity of macroscopic powders by about an order of magnitude while considering the true morphology of mesoscopic explosive crystals. First, the densification behavior at different scales were analyzed using the developed 3D DEM models, including the rearrangement of macroscopic powder during the low strain stage, the deformation of macroscopic powders and mesoscopic bonding failure inside the powders during the high strain stage. Furtherly, the types and percentages of microcracks at the crystal-binder interface and inside the binder at the mesoscale during the macro powder deformation in the compression densification process were quantified. The characteristics of pore distribution and evolution laws of porosity and density uniformity during compression densification were revealed by simulations and X-ray μCT scanning. Finally, the mechanism of density non-uniformity was elucidated from multiple perspectives including displacement, force chain, contact fabric, and stress distribution. Subsequently, different degrees of energy dissipation behavior and the same gradient attenuation pattern were captured at different scales. This indicates that axial stress attenuation and density inhomogeneity are co-dominant results of the gradient attenuation of different scales of energy during layer-by-layer transfer along the loading direction. The potential induced mechanism of uneven density and stress attenuation were explained for the first time from the perspective of energy dissipation by this finding.

A novel image dehazing algorithm for complex natural environments

As an essential preprocessing step in computer vision tasks, image dehazing is preparatory work in many practical applications. To ensure the navigation safety of intelligent ships in complex haze weather, this paper proposes a lightweight real-time dehazing method for the natural environment based on an all-in-one dehazing network. Specifically, a hybrid dilated convolution is used to construct a dehazing network, which effectively expands the receptive field and improves the ability to extract characteristic information without increasing the calculation amount of the model. Secondly, a hybrid attention module is developed to enhance the model's ability to remove haze while retaining more detailed features by giving weights to light haze and heavy haze areas in the image. Finally, considering the subjective perception of human eyes, a mixed loss function is designed to address image dimness and color distortion after dehazing. Through experiments on both synthetic and real-world haze datasets, the proposed method attains ideal dehazing results and has high real-time performance. It can dehaze under different haze conditions, address the critical challenge of degraded visual perception in severe weather conditions of intelligent ship navigation on inland rivers in complex environments, and promote intelligent ships' development.

Hand-object pose estimation based on HOPE-net and attention mechanism

Abstract Hand-object pose estimation is an important part of studying hand pose, focusing on the joint detection of hand and object poses. Although CNN has shown advantages in various hand pose estimation, due to various problems such as the complex structure of the hand pose and self-occlusion, there are limitations in the extraction of image features and the amount of calculation. Existing studies have shown that GCNs have a good performance in dealing with such problems. In this paper, we propose to combine the attention module with two adaptive GCNs, and perform feature enhancement operations on hand features. While ensuring the accuracy of feature extraction, it can effectively improve the network calculation speed and avoid some questions such as self-occlusion. Experimental results show that, through end-to-end training, the algorithm has a great performance on the problem of hand-object pose estimation.

Wigner Function Method for Describing Electromagnetic Field in Plasma-Like Media with Spatial Dispersion and Resonant Dissipation

The paper gives a systematic presentation of the Wigner function method (Weyl formalism) for modeling the propagation and absorption of electromagnetic waves in anisotropic and gyrotropic dissipative media with spatial dispersion. A general kinetic equation for the Wigner function (tensor) is formulated, and its asymptotic expansion up to the second order for smoothly inhomogeneous and weakly dissipative media is constructed. As a result, a modification of the method of the kinetic equation for rays is proposed, based on the stochastic description of rays, making it possible to increase the accuracy of numerical modeling of wave problems with strong transverse inhomogeneity of the absorption coefficient without increasing the amount of calculations. The technique developed can be used to describe the propagation, absorption, and scattering of electron-cyclotron waves in high-temperature plasma of magnetic traps for controlled fusion in cases where standard modeling methods do not provide the necessary accuracy.

An Intelligent Parameter Identification Algorithm of Linear Fuzzy Fractional Differential Equation

Abstract The traditional linear generation fuzzy fractional differential equation parameter identification algorithm lacks the update of parameter identification process, has large amount of calculation, slow convergence speed of parameter identification and strong dependence on initial values. In this paper, a new intelligent recognition algorithm for linearly generated fuzzy fractional differential equations is proposed. The parameters of the equation are re expressed by the constant level set. The piecewise constant level set algorithm based on equation parameter intelligent identification is used to solve the steady-state solution of fractional differential equation, and the non convergence problem caused by too much calculation is solved. A new algorithm scheme for linearly generating fuzzy fractional differential equations is established, the constraints of the level set of the differential equations are calculated, and the updated algorithm for parameter identification of the equation is obtained. The evolutionary algorithm is used to solve the updating algorithm to realize the intelligent identification algorithm of linear fractional fuzzy differential equations. Experimental results show that the algorithm has the advantages of fast convergence speed, high calculation accuracy and low initial value.

Lightweight Improved Transmission Line External Mechanical Damage Threats Detection Algorithm

In monitoring transmission line external damage prevention, due to the limited memory computing power of the equipment, the image needs to be transmitted to the data center at regular intervals, resulting in a high false negative rate. Therefore, this paper proposes a target detection method based on lightweight YOLOv5s. First, DSConv and improved E‐ELAN are used in Backbone to reduce the model's parameters. Then, GSConv and VoV‐GSCSP are introduced in Neck to reduce the complexity of the model. Finally, the Mish activation function achieves more effective feature transfer. According to the experimental findings, the proposed model's parameters are about 37% smaller than the original model's, and the calculation amount is about 53% smaller. The detection accuracy on the self‐built data set is the same, which proves that the proposed algorithm can reduce the model while maintaining high detection performance. It has specific practical significance for the terminal real‐time detection of external mechanical damage targets. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

An exploration of the influence of ZnO NPs treatment on germination of radish seeds under salt stress based on the YOLOv8-R lightweight model

BackgroundSince traditional germination test methods have drawbacks such as slow efficiency, proneness to error, and damage to seeds, a non-destructive testing method is proposed for full-process germination of radish seeds, which improves the monitoring efficiency of seed quality.ResultsBased on YOLOv8n, a lightweight test model YOLOv8-R is proposed, where the number of parameters, the amount of calculation, and size of weights are significantly reduced by replacing the backbone network with PP-LCNet, the neck part with CCFM, the C2f of the neck part with OREPA, the SPPF with FocalModulation, and the Detect of the head part with LADH. The ablation test and comparative test prove the performance of the model. With adoption of germination rate, germination index, and germination potential as the three vitality indicators, the seed germination phenotype collection system and YOLOv8-R model are used to analyze the full time-series sequence effects of different ZnO NPs concentrations on germination of radish seeds under varying degrees of salt stress.ConclusionsThe results show that salt stress inhibits the germination of radish seeds and that the inhibition effect is more obvious with the increased concentration of NaCl solution; in cultivation with deionized water, the germination rate of radish seeds does not change significantly with increased concentration of ZnO NPs, but the germination index and germination potential increase initially and then decline; in cultivation with NaCl solution, the germination rate, germination potential and germination index of radish seeds first increase and then decline with increased concentration of ZnO NPs.

Multiple UAVs Networking Oriented Consistent Cooperation Method Based on Adaptive Arithmetic Sine Cosine Optimization

With the rapid development of the Internet of Things, the Internet of Vehicles (IoV) has quickly drawn considerable attention from the public. The cooperative unmanned aerial vehicles (UAVs)-assisted vehicular networks, as a part of IoV, has become an emerging research spot. Due to the significant limitations of the application and service of a single UAV-assisted vehicular networks, efforts have been put into studying the use of multiple UAVs to assist effective vehicular networks. However, simply increasing the number of UAVs can lead to difficulties in information exchange and collisions caused by external interference, thereby affecting the security of the entire cooperation and networking. To address the above problems, multiple UAV cooperative formation is increasingly receiving attention. UAV cooperative formation can not only save energy loss but also achieve synchronous cooperative motion through information communication between UAVs, prevent collisions and other problems between UAVs, and improve task execution efficiency. A multi-UAVs cooperation method based on arithmetic optimization is proposed in this work. Firstly, a complete mechanical model of unmanned maneuvering was obtained by combining acceleration limitations. Secondly, based on the arithmetic sine and cosine optimization algorithm, the mathematical optimizer was used to accelerate the function transfer. Sine and cosine strategies were introduced to achieve a global search and enhance local optimization capabilities. Finally, in obtaining the precise position and direction of multi-UAVs to assist networking, the cooperation method was formed by designing the reference controller through the consistency algorithm. Experimental studies were carried out for the multi-UAVs’ cooperation with the particle model, combined with the quadratic programming problem-solving technique. The results show that the proposed quadrotor dynamic model provides basic data for cooperation position adjusting, and our simplification in the model can reduce the amount of calculations for the feedback and the parameter changes during the cooperation. Moreover, combined with a reference controller, the UAVs achieve the predetermined cooperation by offering improved navigation speed, task execution efficiency, and cooperation accuracy. Our proposed multi-UAVs cooperation method can improve the quality of service significantly on the UAV-assisted vehicular networks.

Strategies of Automated Machine Learning for Energy Sustainability in Green Artificial Intelligence

Automated machine learning (AutoML) is recognized for its efficiency in facilitating model development due to its ability to perform tasks autonomously, without constant human intervention. AutoML automates the development and optimization of machine learning models, leading to high energy consumption due to the large amount of calculations involved. Hyperparameter optimization algorithms, central to AutoML, can significantly impact its carbon footprint. This work introduces and investigates energy efficiency metrics for advanced hyperparameter optimization algorithms within AutoML. These metrics enable the evaluation and optimization of an algorithm’s energy consumption, considering accuracy, sustainability, and reduced environmental impact. The experimentation demonstrates the application of Green AI principles to AutoML hyperparameter optimization algorithms. It assesses the current sustainability of AutoML practices and proposes strategies to make them more environmentally friendly. The findings indicate a reduction of 28.7% in CO2e emissions when implementing the Green AI strategy, compared to the Red AI strategy. This improvement in sustainability is achieved with a minimal decrease of 0.51% in validation accuracy. This study emphasizes the importance of continuing to investigate sustainability throughout the life cycle of AI, aligning with the three fundamental pillars of sustainable development.

Night target detection algorithm based on improved YOLOv7

Aiming at the problems of error detection and missing detection in night target detection, this paper proposes a night target detection algorithm based on YOLOv7(You Only Look Once v7). The algorithm proposed in this paper preprocesses images by means of square equalization and Gamma transform. The GSConv(Group Separable Convolution) module is introduced to reduce the number of parameters and the amount of calculation to improve the detection effect. ShuffleNetv2_×1.5 is introduced as the feature extraction Network to reduce the number of Network parameters while maintaining high tracking accuracy. The hard-swish activation function is adopted to greatly reduce the delay cost. At last, Scylla Intersection over Union function is used instead of Efficient Intersection over Union function to optimize the loss function and improve the robustness. Experimental results demonstrate that the average detection accuracy of the proposed improved YOLOv7 model is 88.1%. It can effectively improve the detection accuracy and accuracy of night target detection.

Hybrid attention transformer with re-parameterized large kernel convolution for image super-resolution

Single image super-resolution is a well-established low-level vision task that aims to reconstruct high-resolution images from low-resolution images. Methods based on Transformer have shown remarkable success and achieved outstanding performance in SISR tasks. While Transformer effectively models global information, it is less effective at capturing high frequencies such as stripes that primarily provide local information. Additionally, it has the potential to further enhance the capture of global information. To tackle this, we propose a novel Large Kernel Hybrid Attention Transformer using re-parameterization. It combines different kernel sizes and different steps re-parameterized convolution layers with Transformer to effectively capture global and local information to learn comprehensive features with low-frequency and high-frequency information. Moreover, in order to solve the problem of using batch normalization layer to introduce artifacts in SISR, we propose a new training strategy which is fusing convolution layer and batch normalization layer after certain training epochs. This strategy can enjoy the acceleration convergence effect of batch normalization layer in training and effectively eliminate the problem of artifacts in the inference stage. For re-parameterization of multiple parallel branch convolution layers, adopting this strategy can further reduce the amount of calculation of training. By coupling these core improvements, our LKHAT achieves state-of-the-art performance for single image super-resolution task.

A Curved Surface Integral Method for Reliability Analysis of Multiple Failure Modes System with Non-Overlapping Failure Domains

Abstract In the study of reliability of systems with multiple failure modes, approximations can be obtained by calculating the probability of failure for each state function. The first-order reliability method and the second-order reliability method are effective, but they may introduce significant errors when dealing with certain nonlinear situations. Simulation methods such as line sampling method and response surface method can solve implicit function problems, but the large amount of calculation results in low efficiency. The curved surface integral method (CSI) has good accuracy in dealing with nonlinear problems. Therefore, a system reliability analysis method (CSIMMS) is proposed on the basis of CSI for solving multiple failure modes system reliability problems with non-overlapping failure domains. The order of magnitude of the failure probability is evaluated based on the reliability index and the degree of nonlinearity, ignoring the influence of low order of magnitude failure modes, and reducing the calculation of the system failure probability. Finally, CSIMMS and other methods are compared by three numerical examples, and the results show the stability and accuracy of the proposed method.

Album of animated drawings as an innovative means of teaching algebra in the digital environment of bilingual students

Introduction. Digitalization of education has opened up new opportunities for the development and application of the didactic potential of digital technologies in teaching algebra in the context of bilingualism. This determined the purpose of this work, which is to create a methodological system for teaching algebra to bilingual students and an album of animated drawings in a digital environment. Scientific and pedagogical research focuses on the problem of mathematical training of schoolchildren in the context of bilingualism. From the point of view of improving the quality of education, it is advisable to rely on visual-figurative and associative thinking developed by bilingual students. Materials and methods. The experimental study involved 50 students of the seventh grade of gymnasium No. 5 in the city of Kyzyl, Republic of Tyva (Russian Federation). The methods of comparative analysis of scientific, pedagogical and methodological sources, empirical and statistical methods (Student's t-test) are applied. Results. A methodological system for teaching algebra to bilingual students using an album of animated drawings in a digital environment has been developed. An album of animated drawings is presented, implemented in the form of an electronic training course in the electronic learning system of Tuvan State University and the results of its application in teaching algebra to bilingual students. As a result of the experiment, it was revealed that in the absence of statistically significant differences in the control and experimental groups at the time of the initial control, since tэмп = 2,00 < tкр = 2,01, during the final control, tэмп = 2,80 > tкр = 2,01 at the significance level p < 0,05. This indicates that the compared groups are significantly different and the experimental hypothesis about the effectiveness of using an album of animated drawings as an innovative means of teaching seventh grade algebra in the digital environment of bilingual students is confirmed. Conclusion. The use of an album of animated drawings as an innovative means of teaching algebra in the digital environment of bilingual students of the seventh grade of the Republic of Tyva increases the effectiveness of learning by increasing the clarity of algebraic concepts and statements, reducing the amount of non-essential calculations, as well as the use of mechanisms for rapid assessment of learning outcomes using a developed system of bilingual prompts. The proposed learning tool forms and develops an experimental research style of learning.

Three discs for the Mittenpunkt

The aim of this paper is to give a solution to three conjectures from Euclidean geometry concerning the location of the Mittenpunkt. The first two are solved without dependence on computer technology and with only a moderate amount of calculations. They were initially tackled by heavy calculations using computer algebra systems.

Practical Method for Voltage Control in Active Distribution Network Based on Sensitivity

Abstract The access of a large number of distributed photovoltaic power stations makes the voltage problem of the distribution network more prominent, but also provides controllable resources for the distribution network. In order to exploit the regulation potential of distributed photovoltaic power stations in active distribution networks, a practical method for voltage control based on sensitivity is proposed. The adjustment nodes and adjustment amounts are determined according to sensitivity. Based on the power flow equation, the voltage sensitivity calculation is appropriately simplified to reduce the amount of calculation. By combining forecast data and network topology, a control architecture for parallel calculation of sensitivity analysis, reactive power regulation capacity analysis, and real-time voltage control is proposed. This architecture decouples sensitivity calculation from real-time regulation and control, improving the processing speed and reliability of real-time voltage regulation and control. A case study based on a 10kV distribution network in a certain area shows that although the proposed sensitivity calculation method has some deviation, it can meet the requirements of engineering practicality and effectively achieve voltage over-limit control.

Embedded exponential Runge–Kutta–Nyström methods for highly oscillatory Hamiltonian systems

Exponential/extended Runge–Kutta–Nyström (ERKN) methods have been validated by numerous theoretical and numerical results to be more efficient and suitable than classical Runge–Kutta–Nyström (RKN) methods in dealing with highly oscillatory Hamiltonian systems. Once numerical solutions are required to achieve a prescribed local error tolerance for practical problems, the embedded ERKN pairs with adaptive stepsize are needed. Given the higher efficiency of high-order methods than low-order methods, this paper focuses on high-order embedded ERKN pairs. Using the particular mapping from RKN methods into ERKN methods, we establish an approach to constructing high-order embedded ERKN pairs. By diagonalizing the frequency matrix, an implementation algorithm with less calculation amount than the direct calculation procedure is proposed for high-dimensional problems. In addition, the dispersion and dissipation of the ERKN pairs ERKN4(3) and ERKN8(6) are analyzed. Furthermore, the application of ERKN pairs to an important highly oscillatory problem, i.e., the wave equation prescribed with different boundary conditions is discussed. For the periodic boundary condition, a special implementation algorithm incorporated with FFT techniques is presented, which decreases the calculation amount in one time step from O(N2) to O(Nlog⁡N). Finally, numerical results with the FPU problem, the Klein–Gordon equation in the nonrelativistic limit regime, and a two-dimensional wave equation demonstrate the superiority of ERKN pairs over classical RKN pairs.

High-precision object detection network for automate pear picking

To address the urgent need for agricultural intelligence in the face of increasing agricultural output and a shortage of personnel, this paper proposes a high precision object detection network for automated pear picking tasks. The current object detection method using deep learning does not fully consider the redundant background information of the pear detection scene and the mutual occlusion characteristics of multiple pears, so that the detection accuracy is low and cannot meet the needs of complex automated pear picking detection tasks. The proposed, High-level deformation-perception Network with multi-object search NMS(HDMNet), is based on YOLOv8 and utilizes a high-level Semantic focused attention mechanism module to eliminate irrelevant background information and a deformation-perception feature pyramid network to improve accuracy of long-distance and small scale fruit. A multi-object search non-maximum suppression is also proposed to choose the anchor frame in a combined search method suitable for multiple pears. The experimental results show that the HDMNet parameter amount is as low as 12.9 M, the GFLOPs is 41.1, the mAP is 75.7%, the mAP50 reaches 93.6%, the mAP75 reaches 70.2%, and the FPS reaches 73.0. Compared with other SOTA object detection methods, it has the transcend of real-time detection, low parameter amount, low calculation amount, high precision, and accurate positioning.

THE IMPROVED ROAD DEFECT DETECTION ALGORITHM BASED ON YOLOv8s

Road defect detection is a key task to ensure road safety and repair damage in a timely manner. However, traditional manual inspection methods are inefficient and costly. To address such problems, a BL-YOLOv8 enhanced road defect detection algorithm is proposed. By integrating the BiFPN concept, the neck structure of the YOLOv8s model is reconstructed, reducing model parameters, computational load and overall size, and introducing a dynamic large convolution kernel attention mechanism (LSK-attention) to expand the model's receptive field and improve the accuracy of target detection. The experimental results show that on the road defect data set (KITTI), the number of parameters is reduced by 23.03 %, the amount of calculation is reduced by 5.85 %, and the average accuracy of mAP@0.5 is increased by 2.1 %, verifying the effectiveness of this method for automatic road defect detection technology effectiveness.