Search

Cryo-electron micrograph images have various characteristics such as varying sizes, shapes, and distribution densities of individual particles, severe background noise, high levels of impurities, irregular shapes, blurred edges, and similar color to the background. How to demonstrate good adaptability in the field of image vision by picking up single particles from multiple types of cryo-electron micrographs is currently a challenge in the field of cryo-electron micrographs. This paper combines the characteristics of the MixUp hybrid enhancement algorithm, enhances the image feature information in the pre-processing stage, builds a feature perception network based on the channel self-attention mechanism in the forward network of the Swin Transformer model network, achieving adaptive adjustment of self-attention mechanism between different single particles, increasing the network's tolerance to noise, Incorporating PReLU activation function to enhance information exchange between pixel blocks of different single particles, and combining the Cross-Entropy function with the softmax function to construct a classification network based on Swin Transformer suitable for cryo-electron micrograph single particle detection model (Swin-cryoEM), achieving mixed detection of multiple types of single particles. Swin-cryoEM algorithm can better solve the problem of good adaptability in picking single particles of many types of cryo-electron micrographs, improve the accuracy and generalization ability of the single particle picking method, and provide high-quality data support for the three-dimensional reconstruction of a single particle. In this paper, ablation experiments and comparison experiments were designed to evaluate and compare Swin-cryoEM algorithms in detail and comprehensively on multiple datasets. The Average Precision is an important evaluation index of the evaluation model, and the optimal Average Precision reached 95.5% in the training stage Swin-cryoEM, and the single particle picking performance was also superior in the prediction stage. This model inherits the advantages of the Swin Transformer detection model and is superior to mainstream models such as Faster R-CNN and YOLOv5 in terms of the single particle detection capability of cryo-electron micrographs. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) play a prominent role in solving problems in various domains such as pattern recognition, image tasks, and natural language processing. In recent years, neural architecture search (NAS), which is the automatic design of neural network architectures as an optimization algorithm, has become a popular method to design CNN architectures against some requirements associated with the network function. However, many NAS algorithms are characterised by a complex search space which can negatively affect the efficiency of the search process. In other words, the representation of the neural network architecture and thus the encoding of the resulting search space plays a fundamental role in the designed CNN performance. In this paper, to make the search process more effective, we propose a novel compact representation of the search space by identifying network blocks as elementary units. The study in this paper focuses on a popular CNN called DenseNet. To perform the NAS, we use an ad-hoc implementation of the particle swarm optimization indicated as PSO-CNN. In addition, to reduce size of the final model, we propose a segmentation method to cut the blocks. We also transfer the final model to different datasets, thus demonstrating that our proposed algorithm has good transferable performance. The proposed PSO-CNN is compared with 11 state-of-the-art algorithms on CIFAR10 and CIFAR100. Numerical results show the competitiveness of our proposed algorithm in the aspect of accuracy and the number of parameters. [ABSTRACT FROM AUTHOR]

For wireless sensor network (WSN) coverage problems, since the sensing range of sensor nodes is a circular area with symmetry, taking symmetry into account when deploying nodes will help simplify problem solving. In addition, in view of two specific problems of high node deployment costs and insufficient effective coverage in WSNs, this paper proposes a WSN coverage optimization method based on the improved grey wolf optimizer with multi-strategies (IGWO-MS). As far as IGWO-MS is concerned, first of all, it uses Sobol sequences to initialize the population so that the initial values of the population are evenly distributed in the search space, ensuring high ergodicity and diversity. Secondly, it introduces a search space strategy to increase the search range of the population, avoid premature convergence, and improve search accuracy. And then, it combines reverse learning and mirror mapping to expand the population richness. Finally, it adds Levy flight to increase the disturbance and improve the probability of the algorithm jumping out of the local optimum. To verify the performance of IGWO-MS in WSN coverage optimization, this paper rasterizes the coverage area of the WSN into multiple grids of the same size and symmetry with each other, thereby transforming the node coverage problem into a single-objective optimization problem. In the simulation experiment, not only was IGWO-MS selected, but four other algorithms were also selected for comparison, namely particle swarm optimization (PSO), grey wolf optimizer (GWO), grey wolf optimization based on drunk walk (DGWO), and grey wolf optimization led by two-headed wolves (GWO-THW). The experimental results demonstrate that when the number of nodes for WSN coverage optimization is 20 and 30, the optimal coverage rate and average coverage rate using IGWO-MS are both improved compared to the other four comparison algorithms. To make this clear, in the case of 20 nodes, the optimal coverage rate of IGWO-MS is increased by 13.19%, 1.68%, 4.92%, and 3.62%, respectively, compared with PSO, GWO, DGWO, and GWO-THW; while IGWO-MS performs even better in terms of average coverage rate, which is 16.45%, 3.13%, 11.25%, and 6.19% higher than that of PSO, GWO, DGWO, and GWO-THW, respectively. Similarly, in the case of 30 nodes, compared with PSO, GWO, DGWO, and GWO-THW, the optimal coverage rate of the IGWO-MS is increased by 15.23%, 1.36%, 5.55%, and 3.66%; the average coverage rate is increased by 16.78%, 1.56%, 10.91%, and 8.55%. Therefore, it can be concluded that IGWO-MS has certain advantages in solving WSN coverage problems, which is reflected in that not only can it effectively improve the coverage quality of network nodes, but it also has good stability. [ABSTRACT FROM AUTHOR]

Petroleum is a critical industrial material. In the process of oilfield development, the Fisher's optimal segmentation method is often used to solve the problem of division and combination of layer series of development. However, when encountering the problem of long samples, this method has particularly obvious drawbacks due to the high storage requirements of the calculation process. Therefore, in practical work, the Fisher's optimal binary segmentation method is generally used instead. Although it avoids storage problems, it is prone to falling into local optima. On the basis of analyzing the shortcomings of Fisher's optimal segmentation and optimal binary segmentation algorithms, this paper processes a genetic clustering algorithm. This algorithm overcomes the problem of Fisher's optimal binary segmentation algorithm easily falling into local optima and solves the problem of high storage capacity requirements in the calculation process of Fisher's optimal segmentation algorithm. Taking the data of 17 subzones in S-2 8-11 sand groups of the Shahejie Formation of the Lower Tertiary in the Dongxin area as an example, this algorithm is applied to divide and combine layer series of development. The experimental results show that the algorithm's partitioning results are reasonable and can optimize the selection of development layers and provide decision support for the production of oil and gas resources. [ABSTRACT FROM AUTHOR]

The gazelle optimization algorithm (GOA) is an iterative optimization method inspired by the agile movements of gazelles, employing adaptive step sizes and velocity adjustments for rapid convergence in continuous search spaces. However, GOA tends to lack diversity, leading to issues like local minima trapping and premature convergence. This paper addresses these limitations by introducing dynamic opposition-based learning (OBL) and incorporating a balanced sine-control-logistic chaotic mapping system, resulting in the improved GOA (IGOA). Dynamic OBL accelerates the search process, improving learning and selecting superior candidate solutions, while chaotic mapping in chaotic local search widens ranges for exploration and local optima escape. Evaluating IGOA against seven algorithms, including GOA and others, across 31 general test functions, the results consistently showcase IGOA's superior efficiency in achieving solutions closest to optima, early convergence, and hit rate when compared to alternative algorithms. [ABSTRACT FROM AUTHOR]

To overcome the disadvantages of premature convergence and easy trapping into local optimum solutions, this paper proposes an improved particle swarm optimization algorithm (named NDWPSO algorithm) based on multiple hybrid strategies. Firstly, the elite opposition-based learning method is utilized to initialize the particle position matrix. Secondly, the dynamic inertial weight parameters are given to improve the global search speed in the early iterative phase. Thirdly, a new local optimal jump-out strategy is proposed to overcome the "premature" problem. Finally, the algorithm applies the spiral shrinkage search strategy from the whale optimization algorithm (WOA) and the Differential Evolution (DE) mutation strategy in the later iteration to accelerate the convergence speed. The NDWPSO is further compared with other 8 well-known nature-inspired algorithms (3 PSO variants and 5 other intelligent algorithms) on 23 benchmark test functions and three practical engineering problems. Simulation results prove that the NDWPSO algorithm obtains better results for all 49 sets of data than the other 3 PSO variants. Compared with 5 other intelligent algorithms, the NDWPSO obtains 69.2%, 84.6%, and 84.6% of the best results for the benchmark function ( f 1 - f 13 ) with 3 kinds of dimensional spaces (Dim = 30,50,100) and 80% of the best optimal solutions for 10 fixed-multimodal benchmark functions. Also, the best design solutions are obtained by NDWPSO for all 3 classical practical engineering problems. [ABSTRACT FROM AUTHOR]

To overcome the disadvantages of premature convergence and easy trapping into local optimum solutions, this paper proposes an improved particle swarm optimization algorithm (named NDWPSO algorithm) based on multiple hybrid strategies. Firstly, the elite opposition-based learning method is utilized to initialize the particle position matrix. Secondly, the dynamic inertial weight parameters are given to improve the global search speed in the early iterative phase. Thirdly, a new local optimal jump-out strategy is proposed to overcome the "premature" problem. Finally, the algorithm applies the spiral shrinkage search strategy from the whale optimization algorithm (WOA) and the Differential Evolution (DE) mutation strategy in the later iteration to accelerate the convergence speed. The NDWPSO is further compared with other 8 well-known nature-inspired algorithms (3 PSO variants and 5 other intelligent algorithms) on 23 benchmark test functions and three practical engineering problems. Simulation results prove that the NDWPSO algorithm obtains better results for all 49 sets of data than the other 3 PSO variants. Compared with 5 other intelligent algorithms, the NDWPSO obtains 69.2%, 84.6%, and 84.6% of the best results for the benchmark function ( f 1 - f 13 ) with 3 kinds of dimensional spaces (Dim = 30,50,100) and 80% of the best optimal solutions for 10 fixed-multimodal benchmark functions. Also, the best design solutions are obtained by NDWPSO for all 3 classical practical engineering problems. [ABSTRACT FROM AUTHOR]

Identifying the location of the sensor nodes is a challenging aspect of Wireless Sensor Networks (WSNs) in a distributed environment. It is vital to understand where data and events come from when sensor nodes collect data and report on them. This paper uses a nature-inspired Jaya algorithm to estimate the location coordinates of target nodes in a distributed architecture of WSNs. The Jaya algorithm handles the nonlinear optimization problem of node localization in a randomly distributed sensor node configuration. The range-based, Received Signal Strength Indicator method is used for the distance estimation. MATLAB software is used to assess the proposed work, and a comparison is made with the Particle Swarm Optimization, Krill Herd Optimization, and Salp Swarm Algorithm based node localization algorithms in terms of localization error and computation time. The localization error analysis is done for the different numbers of anchor nodes and different values of degree of irregularity to verify the effectiveness of the proposed work. [ABSTRACT FROM AUTHOR]

This research paper develops a novel hybrid approach, called hybrid particle swarm optimization–teaching–learning-based optimization (hPSO-TLBO), by combining two metaheuristic algorithms to solve optimization problems. The main idea in hPSO-TLBO design is to integrate the exploitation ability of PSO with the exploration ability of TLBO. The meaning of "exploitation capabilities of PSO" is the ability of PSO to manage local search with the aim of obtaining possible better solutions near the obtained solutions and promising areas of the problem-solving space. Also, "exploration abilities of TLBO" means the ability of TLBO to manage the global search with the aim of preventing the algorithm from getting stuck in inappropriate local optima. hPSO-TLBO design methodology is such that in the first step, the teacher phase in TLBO is combined with the speed equation in PSO. Then, in the second step, the learning phase of TLBO is improved based on each student learning from a selected better student that has a better value for the objective function against the corresponding student. The algorithm is presented in detail, accompanied by a comprehensive mathematical model. A group of benchmarks is used to evaluate the effectiveness of hPSO-TLBO, covering various types such as unimodal, high-dimensional multimodal, and fixed-dimensional multimodal. In addition, CEC 2017 benchmark problems are also utilized for evaluation purposes. The optimization results clearly demonstrate that hPSO-TLBO performs remarkably well in addressing the benchmark functions. It exhibits a remarkable ability to explore and exploit the search space while maintaining a balanced approach throughout the optimization process. Furthermore, a comparative analysis is conducted to evaluate the performance of hPSO-TLBO against twelve widely recognized metaheuristic algorithms. The evaluation of the experimental findings illustrates that hPSO-TLBO consistently outperforms the competing algorithms across various benchmark functions, showcasing its superior performance. The successful deployment of hPSO-TLBO in addressing four engineering challenges highlights its effectiveness in tackling real-world applications. [ABSTRACT FROM AUTHOR]

The Dung beetle optimization algorithm is a kind of group intelligence optimization algorithm proposed by Jiankai Xue in 2022, which has the characteristics of strong optimization-seeking ability and fast convergence but suffers from the defect of easily falling into local optimum at the late stage of optimization-seeking as other group intelligence optimization algorithms. To address this problem, this paper proposes a dung beetle search algorithm (QHDBO) based on quantum computing and a multi-strategy hybrid. The good point set strategy is used to initialize the initial population of dung beetles. That makes the initial population more evenly distributed, and reduces the likelihood of the algorithm falling into a local optimum solution. The convergence factor and dynamic balance between the number of Spawning and foraging dung beetles is proposed. That allows the algorithm to focus on the global search in the early stages and local exploration in the later stages. The quantum computing based t-distribution variation strategy is used to variate the optimal global solution, that prevents the algorithm from falling into a local optimum. To verify the performance of the QHDBO algorithm, this paper compares QHDBO with six other swarm intelligence algorithms through 37 test functions and practical engineering application problems. The experimental results show that the improved dung beetle optimization algorithm significantly improves convergence speed and optimization accuracy and has good robustness. • Good point set strategy for initializing populations. • Multi-strategy fusion balancing pre-global exploration and post-local search. • Quantum computing interferes with t-distribution variation strategies. [ABSTRACT FROM AUTHOR]