Convergence Speed Research Articles

YOLOrot2.0: A novel algorithm for high-precision rice seed size measurement with real-time processing

We present YOLOrot2.0, an automated algorithm for measuring the dimensions of rice seeds, which holds significant importance in evaluating grain quality and genetic breeding research. The current methods for rice seed measurement exhibit various limitations, such as the need for seed preprocessing and selection, specialized equipment for measurement, and prolonged measurement time. To address these issues, YOLOrot2.0 introduces the following improvements: Firstly, it utilizes an anchor-free detection algorithm to optimize the detection of rotated targets. Secondly, the utilization of the Kalman Filter IoU loss function, which combines the horizontal bounding box and smooth L1 loss function, accelerates the convergence speed of the network. Moreover, the YOLOv8 architecture was adjusted by modifying certain convolutional layers and the Context to Fusion module to enhance the detection capabilities for smaller targets. Finally, YOLOrot2.0 enables direct processing of the entire image, eliminating the need for image partitioning and resulting in substantial time and processing savings. Experimental results demonstrate that YOLOrot2.0 achieves an mAP (mean average precision) score of 0.95, surpassing other comparative algorithms. Additionally, YOLOrot2.0 provides highly accurate measurements of seed length and width, closely aligned with ground truth values. Notably, YOLOrot2.0 achieves real-time detection by achieving an average detection time of only 11.5 ms for images sized 3000×4000 pixels.

Multi-UAV Cooperative Pursuit of a Fast-Moving Target UAV Based on the GM-TD3 Algorithm

Recently, developing multi-UAVs to cooperatively pursue a fast-moving target has become a research hotspot in the current world. Although deep reinforcement learning (DRL) has made a lot of achievements in the UAV pursuit game, there are still some problems such as high-dimensional parameter space, the ease of falling into local optimization, the long training time, and the low task success rate. To solve the above-mentioned issues, we propose an improved twin delayed deep deterministic policy gradient algorithm combining the genetic algorithm and maximum mean discrepancy method (GM-TD3) for multi-UAV cooperative pursuit of high-speed targets. Firstly, this paper combines GA-based evolutionary strategies with TD3 to generate action networks. Then, in order to avoid local optimization in the algorithm training process, the maximum mean difference (MMD) method is used to increase the diversity of the policy population in the updating process of the population parameters. Finally, by setting the sensitivity weights of the genetic memory buffer of UAV individuals, the mutation operator is improved to enhance the stability of the algorithm. In addition, this paper designs a hybrid reward function to accelerate the convergence speed of training. Through simulation experiments, we have verified that the training efficiency of the improved algorithm has been greatly improved, which can achieve faster convergence; the successful rate of the task has reached 95%, and further validated UAVs can better cooperate to complete the pursuit game task.

Revolutionizing swarm dynamics: the role of receptive fields in enhancing convergence and stability

The classic Vicsek model, while influential in understanding swarm behavior, has limitations in achieving motion consensus and convergence speed, especially under varying conditions of density and noise. This study aims to introduce a novel receptive field mechanism to the Vicsek model to enhance its performance in terms of motion consensus and convergence speed within swarms. The modified model divides a particle’s surrounding area into excitation and inhibition zones based on distinct functions. This structural modification is designed to enrich evolutionary behavior and improve consensus convergence capabilities. Experimental outcomes indicate that the proposed model achieves faster convergence rates towards motion consensus under various density and noise conditions compared to traditional models. Specifically, while classic Vicsek models fail to converge to an overall polarization state under high noise levels and exhibit quasi-periodic oscillations, the enhanced model demonstrates stable convergence without oscillatory behavior across both low- and high-noise environments. The findings highlight the superior evolutionary consistency characteristics of the improved model, offering new theoretical and practical insights into the stability and controllability of swarms. This advancement presents significant implications for the development of more robust swarm systems.

Optimal containment control for multi‐agent systems using fast adaptive dynamic programming

AbstractIn this paper, an innovative adaptive dynamic programming (ADP) algorithm with fast convergence speed is designed for the optimal containment control problem of discrete‐time linear multi‐agent systems. Precisely, a quadratic input energy cost function, including local containment error information and actuator information in the neighborhood, is designed for each follower. Solving the stationary condition of the cost function, the optimal containment controllers are obtained. Traditional ADP methods use actor–critic neural networks to approximate optimal costs and control strategies, it is time‐consuming to solve large‐scale multi‐agent problems due to the computational complexity of neural networks. In order to seek faster convergence speed of optimal containment control without knowing the model information, the fast ADP algorithm framework is designed, it is proved theoretically that the convergence speed is determined by some configurable parameters, and the whale optimization algorithm is employed to globally optimize the parameters of given spaces to derive the optimal configuration. Finally, numerical simulation results are given to verify the effectiveness of the designed algorithm.

An Improved Whale Optimization Algorithm with Adaptive Fitness‐Distance Balance

AbstractWhale optimization algorithm (WOA) is a new bio‐meta‐heuristic algorithm presented to simulate the predatory humpback whales' behavior in the ocean. In previous studies, WOA has been observed to exhibit lower accuracy and slower convergence rates. In this paper, we propose an improved the WOA by innovatively incorporating an adaptive fitness‐distance balance strategy, namely AFWOA. AFWOA can continuously and efficiently identify the maximum potential candidate solutions from the population within the search process, thus improving the accuracy rate and convergence speed of the algorithm. Through various experiments in IEEE CEC2017 and an ill‐conditional problem, AFWOA is proven to be more competitive than the original WOA, several other state‐of‐the‐art WOA variants and other four classic meta‐heuristic algorithms. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

A Hybrid Nonlinear Whale Optimization Algorithm with Sine Cosine for Global Optimization.

The whale optimization algorithm (WOA) is constructed on a whale's bubble-net scavenging pattern and emulates encompassing prey, bubble-net devouring prey, and stochastic capturing for prey to establish the global optimal values. Nevertheless, the WOA has multiple deficiencies, such as restricted precision, sluggish convergence acceleration, insufficient population variety, easy premature convergence, and restricted operational efficiency. The sine cosine algorithm (SCA) constructed on the oscillation attributes of the cosine and sine coefficients in mathematics is a stochastic optimization methodology. The SCA upgrades population variety, amplifies the search region, and accelerates international investigation and regional extraction. Therefore, a hybrid nonlinear WOA with SCA (SCWOA) is emphasized to estimate benchmark functions and engineering designs, and the ultimate intention is to investigate reasonable solutions. Compared with other algorithms, such as BA, CapSA, MFO, MVO, SAO, MDWA, and WOA, SCWOA exemplifies a superior convergence effectiveness and greater computation profitability. The experimental results emphasize that the SCWOA not only integrates investigation and extraction to avoid premature convergence and realize the most appropriate solution but also exhibits superiority and practicability to locate greater computation precision and faster convergence speed.

Decision Transformer-Based Efficient Data Offloading in LEO-IoT.

Recently, the Internet of Things (IoT) has witnessed rapid development. However, the scarcity of computing resources on the ground has constrained the application scenarios of IoT. Low Earth Orbit (LEO) satellites have drawn people's attention due to their broader coverage and shorter transmission delay. They are capable of offloading more IoT computing tasks to mobile edge computing (MEC) servers with lower latency in order to address the issue of scarce computing resources on the ground. Nevertheless, it is highly challenging to share bandwidth and power resources among multiple IoT devices and LEO satellites. In this paper, we explore the efficient data offloading mechanism in the LEO satellite-based IoT (LEO-IoT), where LEO satellites forward data from the terrestrial to the MEC servers. Specifically, by optimally selecting the forwarding LEO satellite for each IoT task and allocating communication resources, we aim to minimize the data offloading latency and energy consumption. Particularly, we employ the state-of-the-art Decision Transformer (DT) to solve this optimization problem. We initially obtain a pre-trained DT through training on a specific task. Subsequently, the pre-trained DT is fine-tuned by acquiring a small quantity of data under the new task, enabling it to converge rapidly, with less training time and superior performance. Numerical simulation results demonstrate that in contrast to the classical reinforcement learning approach (Proximal Policy Optimization), the convergence speed of DT can be increased by up to three times, and the performance can be improved by up to 30%.

Imbalanced image classification algorithm based on fine-grained analysis

Fine-grained attribute analysis and data imbalance have always been research hotspots in the field of computer vision. Due to the complexity and diversity of fine-grained attribute images, traditional image classification methods have shortcomings in paying attention to fine-grained attributes of images and perform poorly when dealing with imbalanced data sets. To overcome these problems, this study proposes a fine-grained image threshold classification algorithm based on deep metric learning. By introducing a metric learning method, the focus on fine-grained attributes of images is enhanced. At the same time, by applying pairwise loss and proxy loss, the classification accuracy of the model is improved and the model convergence speed is accelerated. In order to deal with the problem of data imbalance, a classifier based on threshold analysis is designed. The classifier uses threshold analysis technology to achieve multi-level classification of fine-grained images, thereby improving the problem of low classification accuracy of a few categories in imbalanced data sets. Experimental results show that the proposed fine-grained image threshold classification algorithm based on deep metric learning is significantly superior to other methods in terms of classification accuracy.

Decomposition based estimation of distribution algorithm for high-level synthesis design space exploration

High-Level Synthesis (HLS) has evolved significantly due to the increasing complexity of integrated circuit design and the demand for efficient design methodologies. HLS, which raises the abstraction level of design specification, allows designers to focus on hardware functionality, thus enhancing productivity and reducing verification efforts. However, a key challenge in HLS is efficiently exploring the vast design space to find the Pareto-optimal designs. In this paper, we introduce a novel approach for multi-objective design space exploration in HLS. Our methodology decomposes the design space exploration problem into simpler sub-problems using the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) framework and utilizes the Estimation of Distribution Algorithm (EDA) to build a probabilistic model for generating candidate solutions, thereby reducing the required number of expensive synthesis runs. Experimental results show that the proposed method has a faster convergence speed and reduces the number of syntheses by 24.34% to 32.01%, which significantly outperforms state-of-the-art works. Our approach achieves superior Pareto fronts with the lowest average ADRS value, outperforming Lattice-expl, ϵ -Constraint GA, and NSGA-II by 85.64%, 39.90%, and 33.31% respectively.

A novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps

Although deep learning has gained popularity in the field of fault diagnosis, its limitations are also equally apparent, including: (1) heavy reliance on a substantial volume of labeled samples; (2) a lack of interpretability. To confront these issues, this article proposes a novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps. A comparison between the raw data and the model's hidden layer representations is conducted to minimize feature loss. The model commences by preliminarily learning fault information that is intermixed with noise, leveraging a substantial corpus of unlabeled data. In response to the intricacy of downstream tasks, an interpretable feature reconstruction module is introduced. This module employs a nonlinear surrogate model to fit and elucidate the learned features, embedding the explanation scores into the features to reconstruct the samples, a process utilized for model fine-tuning. The feature reconstruction module capitalizes on the explanatory power of the surrogate model, guiding the model to concentrate more on features with significant impact. This method not only provides interpretability during model training but also expedites the convergence speed of the model. Finally, two hydraulic pump experiment cases are used to verify the effectiveness of the model, and the results show that our method has obvious advantages in reducing label dependence and increasing model reliability for decision making.

Analytical model of an active noise control system for performance analysis of adaptive algorithms in HVAC system

In real-world acoustic scenarios related to the problem with the low-frequency noise such as HVAC systems, the signal is a stochastic, non-stationary and time-varying process where the performance of the active noise control technique mainly depends on the characteristics of the adaptive filtering techniques. In this paper, a method for analytical modeling of active noise control of signals in MATLAB/Simulink is presented, in which the acquisition of audio signals is provided by using a National Instruments control and acquisition module. For the realization of the active noise control, an adaptive filtering system model for signal analysis has been developed, using three adaptive algorithms (LMS,RLS and NLMS). The analysis of the characteristics of each of the three investigated adaptive algorithms is performed according to four parameters: Mean Square Error (MSE), convergence speed, stability and robustness. The conclusions are presented through a comparative analysis of the results obtained from the implemented methodology. The individual characteristics and parameters that are observed for correct adaptation and optimal results of each of the adaptive filters are explained in detail.

Design of Intelligent Firefighting and Smart Escape Route Planning System Based on Improved Ant Colony Algorithm.

Due to the lack of real-time planning for fire escape routes in large buildings, the current route planning methods fail to adequately consider factors related to the fire situation. This study introduces a real-time fire monitoring and dynamic path planning system based on an improved ant colony algorithm, comprising a hierarchical arrangement of upper and lower computing units. The lower unit employs an array of sensors to collect environmental data in real time, which is subsequently transmitted to an upper-level computer equipped with LabVIEW. Following a comprehensive data analysis, pertinent visualizations are presented. Capitalizing on the acquired fire situational awareness, a propagation model for fire spreading is developed. An enhanced ant colony algorithm is then deployed to calculate and plan escape routes by introducing a fire spread model to enhance the accuracy of escape route planning and incorporating the A* algorithm to improve the convergence speed of the ant colony algorithm. In response to potential anomalies in sensor data under elevated temperature conditions, a correction model for data integrity is proposed. The real-time depiction of escape routes is facilitated through the integration of LabVIEW2018 and MATLAB2023a, ensuring the dependability and safety of the path planning process. Empirical results demonstrate the system's capability to perform real-time fire surveillance coupled with efficient escape route planning. When benchmarked against the traditional ant colony algorithm, the refined version exhibits expedited convergence, augmented real-time performance, and effectuates an average reduction of 17.1% in the length of the escape trajectory. Such advancements contribute significantly to enhancing evacuation efficiency and minimizing potential casualties.

Improving the Kepler optimization algorithm with chaotic maps: comprehensive performance evaluation and engineering applications

The Kepler Optimisation Algorithm (KOA) is a recently proposed algorithm that is inspired by Kepler’s laws to predict the positions and velocities of planets at a given time. However, although promising, KOA can encounter challenges such as convergence to sub-optimal solutions or slow convergence speed. This paper proposes an improvement to KOA by integrating chaotic maps to solve complex engineering problems. The improved algorithm, named Chaotic Kepler Optimization Algorithm (CKOA), is characterized by a better ability to avoid local minima and to reach globally optimal solutions thanks to a dynamic diversification strategy based on chaotic maps. To confirm the effectiveness of the suggested approach, in-depth statistical analyses were carried out using the CEC2020 and CEC2022 benchmarks. These analyses included mean and standard deviation of fitness, convergence curves, Wilcoxon tests, as well as population diversity assessments. The experimental results, which compare CKOA not only to the original KOA but also to eight other recent optimizers, show that the proposed algorithm performs better in terms of convergence speed and solution quality. In addition, CKOA has been successfully tested on three complex engineering problems, confirming its robustness and practical effectiveness. These results make CKOA a powerful optimisation tool in a variety of complex real-world contexts. After final acceptance, the source code will be uploaded to the Github account: nawal.elghouate@usmba.ac.ma.

Design and stability performance optimization of a novel hybrid inspection robot walking device for smart grid applications

Inspecting in high-altitude windy environments requires maintaining a stable attitude to avoid significant oscillations, which is a crucial factor in advancing the use of hybrid power transmission line inspection robots (PTLIRs) in real-world scenarios for the electrical power and energy industry. We developed and optimized a novel walking device to improve the safety of hybrid PTLIRs operating in strong wind conditions. First, we investigate the operational conditions of transmission line inspection and design a walking device capable of transporting a flight device to be suspended under the line for inspection purposes. Second, a force equilibrium analysis is performed to explore the relationship between the key structural parameters of the walking device and the wind-induced deflection of the robot. A multiobjective optimization model is formulated to minimize the maximum deflection angle of the robot along three axes under wind loads. Finally, an optimization algorithm, using an improved non-dominated sorting particle swarm optimization (NSPSO) approach, is proposed to solve the model with good global search ability and fast convergence speed. A test platform is constructed to collect the wind deflection angle of a self-developed hybrid PTLIR under the transmission line. The test results demonstrate that the walking device can carry 30 kg to move along the transmission line. The average deflection angle of the robot around the Z axis is the highest under the influence of wind force level 7 (wind speed of 15.5 m/s) perpendicular to the windward surface of the robot. After optimization, the maximum deflection angle is limited to 10.38°, aligning within safety thresholds. The optimization algorithm effectively reduces the maximum deflection angles around the X, Z, and Y axes by 33.19 %, 39.21 %, and 13.23 %, with minimal average errors of 2.40 %, 3.87 %, and 2.13 %, respectively. The research in this paper can solve the bottleneck problem of robot practicality, which has important theoretical significance and practical application value for the safety, stability, and intelligent operation and maintenance management of power transmission lines.

Improved YOLOv5s Fabric Defect Detection Algorithm Based on the Fusion of Global Attention Mechanism and Decoupling Head

During fabric production, machine malfunctions and yarn breakages can lead to defects, affecting product quality. Thus, fabric defect detection is crucial for quality control. Existing detection systems struggle with speed and accuracy, especially for small defects, due to the diversity of defect types and shapes. This paper introduces an improved YOLOv5s algorithm, YOLOv5s-GSD, which enhances detection performance by integrating a Global Attention Mechanism (GAM), the SIOU loss function, and a decoupling head. The GAM enhances focus on relevant features, improving detection accuracy; the SIOU loss function replaces the GIOU loss function to optimize the vector angle of regressions, enhancing convergence speed and accuracy; and the decoupling head separates classification and regression tasks, further improving detection performance. Experimental results show the improved algorithm achieves an accuracy of 97.6% and a recognition rate of 36 frames per second, effectively reducing the miss rate of small targets.

Bounded Containment Maneuvering Protocols for Marine Surface Vehicles With Quantized Communications and Tracking Errors Constrained Guidance: Theory and Experiment.

A new type of containment maneuvering protocols for multiple marine surface vehicles (MSVs) is developed to follow a parameterized path in this work, where the tracking errors are constrained within finite time and the information needed to be transmitted is quantized during coordination. To achieve containment maneuvering of multiple MSVs, a two-objective coordinated control framework is proposed. For the geometric objective, by developing tan-type barrier Lyapunov functions (BLFs) and extended Lyapunov condition-based finite-time guidance laws, the performance of the parameterized line-of-sight guidance framework, including convergence speed and tracking error constraints, is improved. For the dynamic objective, based on quantized control strategy and smooth saturation functions, novel bounded containment maneuvering protocols are proposed to dramatically alleviate the burden of communications among MSVs and ensure more faster dynamic behavior on tracking the path updating speed. Both theoretical analysis and experimental tests with comparative studies illustrate the validity of the proposed containment maneuvering strategy.

Finite-Time Adaptive Control for Electro-Hydraulic Braking Gear Transmission Mechanism with Unilateral Dead Zone Nonlinearity

Autonomous vehicles require more precise and reliable braking control, and electro-hydraulic braking (EHB) systems are better adapted to the development of autonomous driving. However, EHB systems inevitably suffer from unilateral dead zone nonlinearity, which adversely affects the position tracking control. Therefore, a finite-time adaptive control strategy was designed for unilateral dead zone nonlinearity. Initially, the unilateral dead zone nonlinearity was reformulated into a matched disturbance term and an unmatched disturbance term to reduce the adverse effects of disturbances, thereby enhancing system controllability. Then, the “complexity explosion” in the design of the control strategy was avoided by command filtering, and the design process of the controller was simplified. Furthermore, the finite-time control theory was employed to boost the system’s convergence speed, thereby enhancing control performance. In order to ensure the stability of the system under the dead zone disturbance, the unknown disturbance terms were estimated. The stability of the control strategy was validated through the finite-time stability theorem and the Lyapunov function. Eventually, simulations and hardware-in-the-loop (HIL) experiments validated the feasibility and availability of the finite-time adaptive control strategy.

Adaptive search for broad attention based vision transformers

Vision Transformer (ViT) has prevailed among computer vision tasks for its powerful capability of image representation recently. Frustratingly, the manual design of efficient architectures for ViTs can be laborious, often involving repetitive trial and error processes. Furthermore, the exploration of lightweight ViTs remains limited, resulting in inferior performance compared to convolutional neural networks. To tackle these challenges, we propose Adaptive Search for Broad attention based Vision Transformers, called ASB, which automates the design of efficient ViT architectures by utilizing the broad search space and an adaptive evolutionary algorithm. The broad search space facilitates the exploration of a novel connection paradigm, enabling more comprehensive integration of attention information to improve ViT performance. Additionally, an efficient adaptive evolutionary algorithm is developed to efficiently explore architectures by dynamically learning the probability distribution of candidate operators. Our experimental results demonstrate that the adaptive evolution in ASB efficiently learns excellent lightweight models, achieving a 55% improvement in convergence speed over traditional evolutionary algorithms. Moreover, the effectiveness of ASB is validated across several visual tasks. For instance, on ImageNet classification, the searched model attains a performance of 77.8% with 6.5M parameters and outperforms state-of-the-art models, including EfficientNet and EfficientViT networks. On mobile COCO panoptic segmentation, our approach delivers 43.7% PQ. On mobile ADE20K semantic segmentation, our method attains 40.9% mIoU. The code and pre-trained models will be available soon in ASB-Code.

Application of SPNGO-VMD-SVM in rolling bearing fault diagnosis

Abstract Traditional bearing fault feature extraction and fault classification methods have low recognition accuracy and limited recognition capability in noisy environments. To address this problem, this paper proposes an improved northern eagle algorithm (SPNGO) to optimize the variational modal decomposition (VMD) and support vector machine (SVM) to achieve bearing fault diagnosis. Firstly, to overcome the disadvantages of NGO, such as easy fall into local optimal solutions and slow convergence speed, the Sine Cosine Strategy (SCA) and Position Optimisation Search Algorithm (POS) are introduced to optimize the NGO, and the superiority of the SPNGO algorithm is proved through the comparison of different algorithms. Then, SPNGO-VMD is used to adaptively decompose the vibration signals of faulty bearings and generate multiple modal components IMF. The effective IMF components are screened based on the craggy principle to reconstruct the signals. Finally, the reconstructed feature signals are input into SPNGO-SVM for fault classification and compared with other fault diagnosis models. The study results show that the fault diagnosis accuracy of SPNGO-VMD-SVM can reach 96.67%, which can effectively improve the accuracy of bearing fault diagnosis.

A Novel Reinforcement Learning-Based Particle Swarm Optimization Algorithm for Better Symmetry between Convergence Speed and Diversity

This paper introduces a novel Particle Swarm Optimization (RLPSO) algorithm based on reinforcement learning, embodying a fundamental symmetry between global and local search processes. This symmetry aims at addressing the trade-off issue between convergence speed and diversity in traditional algorithms. Traditional Particle Swarm Optimization (PSO) algorithms often struggle to maintain good convergence speed and particle diversity when solving multi-modal function problems. To tackle this challenge, we propose a new algorithm that incorporates the principles of reinforcement learning, enabling particles to intelligently learn and adjust their behavior for better convergence speed and richer exploration of the search space. This algorithm guides particle learning behavior through online updating of a Q-table, allowing particles to selectively learn effective information from other particles and dynamically adjust their strategies during the learning process, thus finding a better balance between convergence speed and diversity. The results demonstrate the superior performance of this algorithm on 16 benchmark functions of the CEC2005 test suite compared to three other algorithms. The RLPSO algorithm can find all global optimum solutions within a certain error range on all 16 benchmark functions, exhibiting outstanding performance and better robustness. Additionally, the algorithm’s performance was tested on 13 benchmark functions from CEC2017, where it outperformed six other algorithms by achieving the minimum value on 11 benchmark functions. Overall, the RLPSO algorithm shows significant improvements and advantages over traditional PSO algorithms in aspects such as local search strategy, parameter adaptive adjustment, convergence speed, and multi-modal problem handling, resulting in better performance and robustness in solving optimization problems. This study provides new insights and methods for the further development of Particle Swarm Optimization algorithms.