Search

Machining scheme selection is presently time-consuming and inefficient due to singularity and uncertainty in decision-making. Typically, the selection is based on a singular feature, with eventual outcomes remaining uncertain. In response, this paper proposes a feature-group-oriented re-optimized bacterial foraging algorithm to solve this problem by selecting the optimal machining schemes for multiple similar features in one part at once. Our focus is on designing the re-optimized bacterial foraging algorithm to optimize machining schemes, which considers the processes of chemotaxis, fine-tuning, replication, and adaptive migration with re-optimization. Then, comparative studies with varying weights and algorithms are conducted as an illustration of machining scheme selection for the hole feature-group. The results indicate that the re-optimized bacterial foraging algorithm accurately produces three distinct machining schemes based on varying weights. Additionally, the optimal average value outperforms other algorithms in the comparative study, demonstrating the algorithm's validity and superiority. [ABSTRACT FROM AUTHOR]

Intelligent algorithms have shown promise in supporting marketing strategy decisions through data mining. However, existing methods have primarily relied on expertise, lacking autonomous decision-making abilities. Consequently, a marketing strategy decision model based on particle swarm optimization and multi-objective programming is proposed. This study first explores the potential for integrating particle optimization and multi-objective programming models partially, and then assesses the overall effectiveness of each marketing strategy by defining a fitness function. Subsequently, the particle swarm optimization algorithm is employed to search for and optimize decision variables to identify the optimal combination of marketing strategies. Finally, several simulation experiments are conducted using external real data. The research findings indicate that the algorithm's error rate in this study was initially 0.23. However, after 500 training sessions, it decreased to 0.08 and maintained a relatively low level. The proportion of marketing strategy revenue increased by 15.2 percentage points between 0 and 100 training sessions, then remained relatively stable at over 30%. Its revenue proportion continued to rise during the training process, significantly surpassing that of other algorithms. [ABSTRACT FROM AUTHOR]

Low-impact development (LID) practices are critical for mitigating urban stormwater runoff and alleviating flood risks. The strategic placement of LID facilities is paramount to optimizing their efficacy within urban landscapes. This study conducts a comprehensive bibliometric analysis of LID-related literature over the past decade, utilizing data visualization tools to elucidate key disciplines, publication trends, and the prevalence of various optimization algorithms. We delve into the application of multi-objective optimization (MOO) algorithms in LID facility layout, examining their practical applications, theoretical underpinnings, and case studies. The paper also scrutinizes the strengths and limitations of these algorithms, proposing future research trajectories that leverage MOO to enhance LID's role in urban stormwater management. [ABSTRACT FROM AUTHOR]

The Particle Swarm Optimization (PSO) algorithm faces several inherent challenges when applied to dynamic and large-scale optimization problems. These challenges encompass the issues of outdated particle memory, inadequate scalability in high-dimensional search spaces, the incapability to detect environmental changes, a continual trade-off between exploration and exploitation, and the potential loss of population diversity within the problem space. To address these challenges, we propose a novel hybrid PSO algorithm, denoted as Parent–Child Multi-Swarm Clustered Memory (PCSCM). PCSCM is explicitly designed to leverage an enhanced memory system, capable of mitigating the issue of outdated particle memory after convergence, and efficiently adapting to changing environmental conditions. This innovative memory system retains and retrieves promising solutions from the past when environmental alterations occur. Additionally, PCSCM introduces clustering mechanisms for particles within each swarm, aimed at augmenting diversity within the problem space. This clustering strategy substantially bolsters the algorithm's performance in tracking evolving optimal solutions and positively contributes to its scalability. Crucially, the clustering approach is implemented not only for the main population but also for stored solutions in memory, which collectively strike a balance between exploration and exploitation. In the proposed method, particle swarms are divided into parent and child swarms, with parent swarms dedicated to preserving diversity; while, child swarms focus on identifying local solutions. These clustering and memory strategies are consistently applied within each sub-swarm to effectively address the challenges posed by high-dimensional search spaces. In addition to addressing challenges related to dynamic optimization, our proposed Parent–Child Multi-Swarm Clustered Memory (PCSCM) algorithm introduces an innovative mechanism for detecting environmental changes. This novel approach enhances the algorithm's adaptability by efficiently identifying moments when the optimization environment undergoes significant shifts. The detection of such changes is a crucial aspect of the PCSCM algorithm, contributing to its robust performance in dynamic scenarios. The effectiveness and robustness of the PCSCM algorithm are substantiated through extensive simulation experiments. These experiments provide insights into PCSCM's behavior in dynamic environments and showcase its ability to scale proficiently in high-dimensional settings. Particularly noteworthy are the results obtained when benchmarked against the Moving Peaks Benchmark and Generalized Moving Peaks Benchmark. These results not only underscore the algorithm's efficiency but also demonstrate its superiority when compared to several existing state-of-the-art optimization methods, including Multi-Swarm PSO, AmQSO, CPSO, Cellular PSO, FMSO, mQSO10 (5 + 5q), and DPSABC. [ABSTRACT FROM AUTHOR]

The relevant experimental data of the fouling formation process of a heat exchanger were obtained through the fouling monitoring experimental platform. Whereafter, with regard to the conventional particle swarm optimization (PSO) algorithm, this study commenced from the iteration formula and innovatively presented an optimization approach for improving the inertia weight, thereby obtaining the improved particle swarm optimization (IPSO) algorithm. The wavelet neural network (WNN) was optimized through the application of the IPSO–WNN algorithm, resulting in the development of the IPSO–WNN model. Utilizing this model, a predictive model for fouling thermal resistance was constructed, incorporating input variables such as conductivity, pH, dissolved oxygen, average wall temperature, and bulk temperature, while the output variable represented fouling thermal resistance. Comparative analyses demonstrated that the IPSO–WNN model exhibited superior prediction accuracy and robust generalization capabilities to that of the conventional WNN and PSO–WNN models, as evidenced by significantly lower values across all indicators, including MAPE, MAE, and RMSE. The IPSO algorithm effectively optimized the initial parameters of the WNN, addressing the challenge of local minimum and enhancing the model's overall capacity to identify optimal solutions. This model effectively captures the dynamic trends of fouling thermal resistance during its growth stage and approaches the asymptotic value in the stable stage. Precise prediction models for heat exchanger fouling contribute valuable insights for its prediction in practical industrial applications. [ABSTRACT FROM AUTHOR]

Background: 5G technology will revolutionize wireless communications, emphasizing spectrum efficiency. Pervasive device connectivity requires unprecedented spectrum resources to allow flawless Internet of Things (IoT) communication. Thus, dynamic spectrum sharing (DSS) is essential for 5G and IoT cohabitation without spectral congestion. Objective: This study examines how DSS improves 5G network speed and efficiency, especially in an IoT-dominated context. The main goals are strategies and methods to maximize spectrum sharing among 5G and IoT devices for resilient, scalable, and uninterrupted connectivity. Methods: Using simulation and testing, this study assesses 5G DSS algorithms and models for latency, throughput, and reliability. The current study compares conventional spectrum allocation and dynamic sharing strategies in various IoT applications. Results: 5G networks with DSS have improved spectrum usage and performance. Optimized algorithms reduce latency and increase throughput even in IoT-heavy situations. Conclusion: DSS is vital to strengthening 5G networks for IoT applications. DSS supports and expands IoT ecosystems by reducing spectrum scarcity and improving network performance, laying the groundwork for the 5G era's rush of connected devices and applications. DSS algorithms need further research to meet changing technology and application needs.

Frequency modulated continuous wave (FMCW) radar is an advantageous sensor scheme for target estimation and environmental perception. However, existing algorithms based on discrete Fourier transform (DFT), multiple signal classification (MUSIC) and compressed sensing, etc., cannot achieve both low complexity and high resolution simultaneously. This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar. Firstly, we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy. Secondly, we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data, which improves the efficiency of continuous target tracking. These two approaches have improved the algorithm efficiency by nearly 2–4 orders of magnitude without losing accuracy and resolution. Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.

Convolutional Neural Networks (CNNs) are among the most prevalent deep learning techniques employed across various domains. The computational complexity of CNNs is largely attributed to the convolution operations. These operations are computationally demanding and significantly impact overall model performance. Traditional CNN implementations convert convolutions into matrix operations via the im2col (image to column) technique, facilitating parallelization through advanced BLAS libraries. This study identifies and investigates a significant yet intricate pattern of data redundancy within the matrix-based representation of convolutions, a pattern that, while complex, presents opportunities for optimization. Through meticulous analysis of the redundancy inherent in the im2col approach, this paper introduces a mathematically succinct matrix representation for convolution, leading to the development of an optimized FFT-based convolution with finer FFT granularity. Benchmarking demonstrates that our approach achieves an average speedup of 14 times and a maximum speedup of 17 times compared to the regular FFT convolution. Similarly, it outperforms the Im2col+GEMM approach from NVIDIA's cuDNN library, achieving an average speedup of three times and a maximum speedup of five times. Our FineGrained FFT convolution approach, when integrated into Caffe, a widely used deep learning framework, leads to significant performance gains. Evaluations using synthetic CNNs designed for real-world applications show an average speedup of 1.67 times. Furthermore, a modified VGG network variant achieves a speedup of 1.25 times. [ABSTRACT FROM AUTHOR]

Powder metallurgy (PM) technology is extensively employed in the manufacturing sector, yet its processing presents numerous challenges. To alleviate these difficulties, green machining of PM green compacts has emerged as an effective approach. The aim of this research is to explore the deformation features of green compacts and assess the impact of various machining parameters on the force of cutting. The cutting variables for compacts of PM green were modeled, and the cutting process was analyzed using Abaqus (2022) software. Subsequently, the orthogonal test ANOVA method was utilized to evaluate the significance of each parameter for the cutting force. Optimization of the machining parameters was then achieved through a genetic algorithm for neural network optimization. The investigation revealed that PM green compacts, which are brittle, undergo a plastic deformation stage during cutting and deviate from the traditional model for brittle materials. The findings indicate that cutting thickness exerts the most substantial influence on the cutting force, whereas the speed of cutting, the tool rake angle, and the radius of the rounded edge exert minimal influence. The optimal parameter combination for the cutting of PM green compacts was determined via a genetic algorithm for neural network optimization, yielding a cutting force of 174.998 N at a cutting thickness of 0.15 mm, a cutting speed of 20 m/min, a tool rake angle of 10°, and a radius of the rounded edge of 25 μm, with a discrepancy of 4.05% from the actual measurement. [ABSTRACT FROM AUTHOR]

Amazons is a computerized board game with complex positions that are highly challenging for humans. In this paper, we propose an efficient optimization of the Monte Carlo tree search (MCTS) algorithm for Amazons, fusing the 'Move Groups' strategy and the 'Parallel Evaluation' optimization strategy (MG-PEO). Specifically, we explain the high efficiency of the Move Groups strategy by defining a new criterion: the winning convergence distance. We also highlight the strategy's potential issue of falling into a local optimum and propose that the Parallel Evaluation mechanism can compensate for this shortcoming. Moreover, We conducted rigorous performance analysis and experiments. Performance analysis results indicate that the MCTS algorithm with the Move Groups strategy can improve the playing ability of the Amazons game by 20–30 times compared to the traditional MCTS algorithm. The Parallel Evaluation optimization further enhances the playing ability of the Amazons game by 2–3 times. Experimental results show that the MCTS algorithm with the MG-PEO strategy achieves a 23% higher game-winning rate on average compared to the traditional MCTS algorithm. Additionally, the MG-PEO Amazons program proposed in this paper won first prize in the Amazons Competition at the 2023 China Collegiate Computer Games Championship & National Computer Games Tournament. [ABSTRACT FROM AUTHOR]

In a landscape where interest in prime sieving has waned and practitioners are few, we are still hoping for a domain renaissance, fueled by a resurgence of interest and a fresh wave of innovation. Building upon years of extensive research and experimentation, this article aims to contribute by presenting a heterogeneous compilation of generic tweaks and boosters aimed at revitalizing prime sieving methodologies. Drawing from a wealth of resurfaced knowledge and refined sieving algorithms, techniques, and optimizations, we unveil a diverse array of strategies designed to elevate the efficiency, accuracy, and scalability of prime sieving algorithms; these tweaks and boosters represent a synthesis of old wisdom and new discoveries, offering practical guidance for researchers and practitioners alike. [ABSTRACT FROM AUTHOR]

The maximum utilization of hydrocracking tail oil becomes increasingly important for petrochemical industry. The aim of this work is to develop optimized distillation processes to achieve various high‐valued qualified oil products from hydrocracking tail oil. Six different oil products is produced and the steady‐state distillation process, which aims to fractionate six qualified narrow distillates is established. The algorithm method incorporating divided‐wall column (DWC) configuration was introduced into the steady‐state design. Compared with traditional separation sequences, the DWC configuration leads to an energy‐saving potential up to 11.17%. Furthermore, effective dynamic control strategies were proposed, demonstrating precise and efficient control performance. In the presence of a 15% feed disturbance, the dynamic control structure is capable of maintaining the product distillation range near the set value. This comprehensive study provides a thorough investigation into the efficient utilization of hydrocracking tail oil, establishing a robust theoretical foundation for its industrial application. [ABSTRACT FROM AUTHOR]

Highlights Proposed an improved IPSO-RELM model. Improved the standard PSO algorithm from three aspects. IPSO was combined to optimize the model structure parameters of RELM. Selected historical feature variables in the RELM model. Established IPSO-RELM temperature prediction methods in edible fungi greenhouse. Maintaining a suitable microclimate environment in a greenhouse is essential for edible fungus growth. This study aims to predict the greenhouse temperature for edible fungi more accurately and efficiently and to provide decision support for their production management. For this purpose, a new method that combines the improved particle swarm optimization (IPSO) with the regularized extreme learning machine (RELM) network algorithm was proposed to enhance the accuracy and efficiency of temperature prediction. The proposed method selects RELM as the basic model that can be effectively applied to the prediction of complex nonlinear systems and makes three improvements to the standard PSO and the parameter optimization for RELM based on IPSO. In addition, four-month temperature data acquisition experiments were carried out in the Daxing District of Beijing, and the time series dataset of greenhouse temperature was collected, preprocessed, and further used to train and validate the proposed models. The results show that the IPSO-RELM model is superior to extreme learning machine (ELM), RELM, least squares support vector regression (LSSVR), and back propagation neural network (BPNN) for predicting the temperature of edible fungi greenhouses, with the least mean-square error (MSE) and large coefficient of determination (R2) values of 0.441 and 0.985, respectively. The results also demonstrated the necessity of incorporating historical variables into predictive modeling. The Wilcoxon signed-rank test is further used to verify that the prediction performance of the IPSO-RELM model is significantly different from the other developed algorithms. Because this study considers multiple historical environmental factors that affect greenhouse temperature, it is applicable to various greenhouse scenarios and has universal applicability. This study provides insights for RELM network-related research and the methods for temperature prediction in other application scenarios, as well as practical decision-making for the temperature control and environmental management of the edible fungi greenhouse. [ABSTRACT FROM AUTHOR]

Formal Concept Analysis (FCA) is a key tool in data analysis and knowledge discovery, yet its application is challenged by the complexity of concept lattices in large datasets. This paper presents the Kernel Concept Set Approach (KCS), a novel methodology that overcomes the limitations of traditional lattice reduction techniques by integrating a flexible derivation cost function and focusing on the frequency and structural importance of concepts. Unlike conventional methods, KCS efficiently operates in a general metric space, reducing computational costs and providing a dynamic approach to conceptual clustering. A comparative study with the K-means Dijkstra on Lattice (KDL) method highlights KCS's superiority in simplifying lattice complexity and enhancing clustering quality. KCS not only maintains crucial data structures but also facilitates the approximation of formal concept lattices, establishing it as an efficient alternative for structured data analysis. [ABSTRACT FROM AUTHOR]

The three spacecraft of the space gravitational wave antenna employ heterodyne interferometry to mitigate the effects of Doppler shift. Constrained by laser relative intensity noise (RIN) and the sampling frequency constraints of phase readout circuits, the widespread adoption of fixed offset frequencies effectively regulates the frequency of heterodyne interferometric beat notes within a reasonable frequency domain of [5 MHz, 25 MHz]. In this work, a high-precision fitness genetic algorithm for heterodyne interferometry is utilized to generate the initial offset frequency distribution scheme. To address issues with unreasonable switching times and offset frequency settings in the initial scheme for partial frequency domains, optimization strategies are proposed from three aspects: frequency domain selection extension, switch times control, and numerical low frequency. Results demonstrate that the optimization of frequency domain selection extension narrows the reasonable frequency domain to [5 MHz, 15 MHz] and [7 MHz, 17 MHz]. Optimization of switch times control ensures that switching times of offset frequency distribution scheme generated under the settings of [6 MHz, 17 MHz] and wider frequency domains can be controlled within a reasonable range of 6 to 13 times. Fixed offset frequency settings are generally reduced by 24.3% after low-frequency optimization. This methodology and result can provide a reliable reference for Program Taiji and even related space gravitational wave antenna projects. [ABSTRACT FROM AUTHOR]

This paper aims to comprehensively explore the pivotal role of simulation and modeling in the field of Artificial Intelligence (AI). It focuses on elucidating the diverse applications of simulation and modeling in training AI systems, optimizing algorithms, and enhancing decision-making processes. To achieve this objective, we conducted an extensive review of the literature from the Scopus database, employing a well-defined selection process. We utilized keywords such as "simulation," "modeling," "Artificial Intelligence," and related terms to identify relevant papers published within the last 10 years. The selection criteria included assessing the relevance, quality, contribution, and recent citations of the papers. After a rigorous screening process, we selected 40 papers with the highest overall scores for inclusion in our review. The selected papers encompass a wide range of domains where simulation and modeling play a vital role in advancing AI applications. These domains include manufacturing, healthcare, energy consumption prediction, public sector decision-making, education, environmental modeling, and more. Our review highlights how AI leverages simulation and modeling to improve predictive accuracy, optimize resource allocation, and enhance decision-making processes across diverse sectors. We also discuss the potential future directions in the integration of simulation and modeling with AI, emphasizing its significance in various fields. [ABSTRACT FROM AUTHOR]

Due to the current focus of research on ankle rehabilitation robots on structural design, there is still limited research on ankle human–machine interaction technology. In order to enable rehabilitation robots to conduct personalized rehabilitation training based on patients’ ankle movement intentions, we propose a new ankle motion recognition method based on plantar pressure. First, we designed a plantar pressure collection system based on array sensors. Then, we collected nine types of ankle joint motion pressure data from five volunteers and conducted algorithm selection, data processing, and algorithm optimization. Finally, we proposed a small sample optimization algorithm based on support vector machine, with an average recognition rate of 93.16%. The recognition method proposed in this paper can be combined with ankle rehabilitation robots to achieve active rehabilitation functions, laying the foundation for the clinical application of active rehabilitation technology. [ABSTRACT FROM AUTHOR]

The systematic generation of prime numbers has been almost ignored since the 1990s, when most of the IT research resources related to prime numbers migrated to studies on the use of very large primes for cryptography, and little effort was made to further the knowledge regarding techniques like sieving. At present, sieving techniques are mostly used for didactic purposes, and no real advances seem to be made in this domain. This systematic review analyzes the theoretical advances in sieving that have occurred up to the present. The research followed the PRISMA 2020 guidelines and was conducted using three established databases: Web of Science, IEEE Xplore and Scopus. Our methodical review aims to provide an extensive overview of the progress in prime sieving—unfortunately, no significant advancements in this field were identified in the last 20 years. [ABSTRACT FROM AUTHOR]

Analyzing and understanding emotional expressions in user comments is a crucial and complex task in business. Conducting text sentiment analysis is of great significance. This paper constructs a novel DIBTBL model that integrates an extended sentiment dictionary, an improved swarm intelligence algorithm, and deep learning techniques to accurately capture and analyze user emotions. Firstly, this paper expands the sentiment dictionary to extract emotion feature words from the review text. Secondly, the BERT model embeds these emotional feature words and pre-processed text into high-dimensional semantic space to obtain richer semantic representations and improve sentiment classification performance. Then, the TextCNN-BiLSTM feature extraction model is established to balance the grasping ability of local and global features. Fourthly, this paper innovatively improves the swarm intelligence algorithm BWO to optimize the parameters of the TextCNN-BiLSTM. Finally, MLP is employed for sentiment classification. The experimental data is crawled from Ctrip, China’s largest hotel booking website. In the comparative experiment, the proposed model achieves a higher accuracy than TBL, DTBL, BTBL, and IBTBL by 2.94%, 2.44%, 1.64%, and 0.66%, respectively. In addition, we compare the proposed model with seven advanced models in the open dataset waimai_10k. The experimental results indicate that this model outperforms all the other models, with an average improvement in accuracy of 8.21%. The study offers precise insights into user sentiment, assisting companies in better understanding and meeting customer needs.

The fuel consumption rate of a diesel engine is closely related to its operating speed. In order to minimize the fuel consumption rate of the diesel engine, this paper studies the optimal operating speed of the diesel generator set, and designs the optimal operating speed curve of the diesel generator based on the actual situation. Aiming at the phenomenon that the load changes at any time in the actual working condition of the diesel generator set, this paper designs a fuzzy adaptive PID control algorithm for the diesel engine governor and realizes algorithm optimization. Using MATLAB platform simulation analysis, it is verified that the fuzzy adaptive PID controller after algorithm optimization has better dynamic response and stability performance in diesel generator system.

To address the problem of inefficient continuous multi-task scheduling operations, a scheduling model was established with the optimization objective of minimum total scheduling time to solve the problem of agricultural machinery continuous performing multiple tasks in agricultural production in hilly areas. An Improved Non-dominated Sorting Genetic Algorithm-III (Improved NSGA-III) was proposed to solve the agricultural machinery scheduling problem. The algorithm employed a two-stage coding mechanism to ensure the uniform distribution of the population and reduce the search solution space. The selection of paternal individuals is based on crowding degree, enabling individuals with better genes to participate in evolution. The domain search strategy of partial solution was introduced to improve the global search ability of the algorithm. The performance of the Improved NSGA-III algorithm and the other three algorithms was compared using farmland data from the experimental area. Results showed that the Improved NSGA-III algorithm outperforms the other three algorithms in terms of minimum total scheduling time, with reductions of 13.89%, 43.81% and 57.19%, respectively, verifying the effectiveness and reliability of the algorithm.

Fish stock assessment is crucial for sustainable marine fisheries management in rangeland ecosystems. To address the challenges posed by the overfishing of offshore fish species and facilitate comprehensive deep-sea resource evaluation, this paper introduces an improved fish sonar image detection algorithm based on the you only look once algorithm, version 5 (YOLOv5). Sonar image noise often results in blurred targets and indistinct features, thereby reducing the precision of object detection. Thus, a C3N module is incorporated into the neck component, where depth-separable convolution and an inverse bottleneck layer structure are integrated to lessen feature information loss during downsampling and forward propagation. Furthermore, lowercase shallow feature layer is introduced in the network prediction layer to enhance feature extraction for pixels larger than $ 4 \times 4 $. Additionally, normalized weighted distance based on a Gaussian distribution is combined with Intersection over Union (IoU) during gradient descent to improve small target detection and mitigate the IoU's scale sensitivity. Finally, traditional non-maximum suppression (NMS) is replaced with soft-NMS, reducing missed detections due to occlusion and overlapping fish targets that are common in sonar datasets. Experiments show that the improved model surpasses the original model and YOLOv3 with gains in precision, recall and mean average precision of 2.3%, 4.7% and 2.7%, respectively, and 2.5%, 6.3% and 6.7%, respectively. These findings confirm the method's effectiveness in raising sonar image detection accuracy, which is consistent with model comparisons. Given Unmanned Underwater Vehicle advancements, this method holds the potential to support fish culture decision-making and facilitate fish stock resource assessment.

S-boxes, the key nonlinear component in numerous cryptographic systems, play a crucial role in ensuring security. The quest for random highly nonlinear S-boxes, a desirable attribute for better diffusion and confusion properties, is, therefore, a critical endeavor in cryptographic research. However, generating such nonlinear S-boxes often involves significant computational effort, presenting a major challenge for researchers. This paper addresses this gap by proposing an optimized version of the Simulated Annealing (SA) algorithm specifically tailored for efficient generation of highly nonlinear S-boxes. Our work introduces a multithreaded implementation of the SA algorithm, a heuristic search method known for its proficiency in combinatorial optimization. The multithreading feature enhances computational efficiency, making our approach more suitable for large-scale cryptographic applications. We further optimize the algorithm by incorporating additional exit criteria for both internal and external loops, which significantly reduces the computational complexity associated with the nonlinear substitution generation process. Furthermore, we undertake comprehensive experiments to identify the optimal parameters of the SA algorithm, aiming to maximize the probability of generating target S-boxes while minimizing the number of iterations. This optimization step provides a clear pathway to improve the success rate of the generation process. The results of our study demonstrate a significant improvement over previous works, showing a 30–40% enhancement in the generation of nonlinear S-boxes. [ABSTRACT FROM AUTHOR]

Based on the background of dynamic mining pressure monitoring and pressure prediction research on the No. 232205 working face of the Meihuajing coal mine, this study systematically investigates the predictive model of mining pressure manifestation on the working face of the Meihuajing coal mine by integrating methods such as engineering investigation, theoretical analysis, and mathematical modeling. A mining pressure manifestation prediction method based on IA-PSO-BP is proposed. The IA-PSO optimization algorithm is applied to optimize the hyperparameters of the BP neural network, and the working face mining pressure prediction model based on IA-PSO-BP is established. The mean absolute error (MAE), mean square error (MSE), and coefficient of determination (R2) are selected as evaluation indicators to compare the prediction performance of the BP model, PSO-BP model, and IA-PSO-BP model. The experimental results of the model show that the convergence speed of the IA-PSO-BP model is about eight times faster than that of the BP model and two times faster than that of the PSO-BP model. Compared with the BP and PSO-BP models, the IA-PSO-BP model has the smallest MAE and MSE and the largest R2 on the three different data sets of the test set, indicating significantly improved prediction accuracy. The predicted results conform to the periodic variation pattern of mining pressure data and are consistent with the actual situation in the coal mine. [ABSTRACT FROM AUTHOR]

The objective of this work is to improve the existing Wireless Sensor Network coverage optimization method. The pigeon-inspired optimization algorithm was first evaluated, and its shortcomings were noted. The pigeon-inspired optimization method was then enhanced with the good point set, Yin-Yang optimization algorithm, and opposition-based learning. To test the improved algorithm, five representative standard functions were chosen: sphere function (f1), Rosenbrock function (f2), Levy function (f3), Schwefel function (f4), and Levy function N.13 (f5). The algorithm's speed of convergence may be determined by the first two functions, which are unimodal. The final three functions, which are multimodal, can extract several local optimal values from the local optimum. In comparison with other known algorithms, the improved Yin-Yang PIO algorithm showed the highest optimization accuracy and stability. Three sets of experiments were performed to optimize the WSN coverage with different parameters. The first series of experiments suggest that Yin–Yang PIO has the best optimization effect, with a coverage rate of 99.51% (10.22% higher with PIO and 6.41% higher compared with PSO). The second and third series of experiments show that Yin-Yang PIO significantly increased the WSN coverage ratio, up to 99.9%. The algorithm can be applied to optimize WSN coverage in various environments. Future research can extend the research scope to include other optimization problems in IoT.

Classification algorithms are crucial in developing predictive models that identify and classify soil fertility levels based on relevant attributes. However, optimizing classification algorithms presents a major challenge in enhancing the accuracy and effectiveness of these models. Therefore, this research aims to optimize the classification algorithm in soil fertility analysis using ensemble learning techniques, specifically Soft Voting Ensemble. This research method is designed to understand soil fertility levels in modern agriculture by comparing the performance of various classification algorithms and ensemble approaches. Using a dataset from the Purwodadi Department of Agriculture, this study examines the optimization of algorithm parameters such as Random Forest, Gradient Boosting, and Support Vector Machine (SVM) and the implementation of Soft Voting Ensemble. Before applying Soft Voting Ensemble, each algorithm was evaluated with the following results: Random Forest achieved an accuracy of 90.93%, precision of 91.08%, recall of 90.33%, and F1-Score of 90.70%; Gradient Boosting achieved an accuracy of 91.53%, precision of 91.19%, recall of 91.56%, and F1-Score of 91.38%; SVM achieved an accuracy of 88.91%, precision of 89.66%, recall of 87.45%, and F1-Score of 88.54%. After implementing Soft Voting Ensemble, the accuracy improved to 91.63%, with an average precision of 91.21%, recall of 91.77%, and F1-Score of 91.49%. This study divided the data into 80% for training data and 20% for testing data. These findings indicate that the Soft Voting Ensemble has the potential to enhance agricultural productivity and sustainability.

Amazons is a computerized board game with complex positions that are highly challenging for humans. In this paper, we propose an efficient optimization of the Monte Carlo tree search (MCTS) algorithm for Amazons, fusing the ‘Move Groups’ strategy and the ‘Parallel Evaluation’ optimization strategy (MG-PEO). Specifically, we explain the high efficiency of the Move Groups strategy by defining a new criterion: the winning convergence distance. We also highlight the strategy’s potential issue of falling into a local optimum and propose that the Parallel Evaluation mechanism can compensate for this shortcoming. Moreover, We conducted rigorous performance analysis and experiments. Performance analysis results indicate that the MCTS algorithm with the Move Groups strategy can improve the playing ability of the Amazons game by 20–30 times compared to the traditional MCTS algorithm. The Parallel Evaluation optimization further enhances the playing ability of the Amazons game by 2–3 times. Experimental results show that the MCTS algorithm with the MG-PEO strategy achieves a 23% higher game-winning rate on average compared to the traditional MCTS algorithm. Additionally, the MG-PEO Amazons program proposed in this paper won first prize in the Amazons Competition at the 2023 China Collegiate Computer Games Championship & National Computer Games Tournament.

In a landscape where interest in prime sieving has waned and practitioners are few, we are still hoping for a domain renaissance, fueled by a resurgence of interest and a fresh wave of innovation. Building upon years of extensive research and experimentation, this article aims to contribute by presenting a heterogeneous compilation of generic tweaks and boosters aimed at revitalizing prime sieving methodologies. Drawing from a wealth of resurfaced knowledge and refined sieving algorithms, techniques, and optimizations, we unveil a diverse array of strategies designed to elevate the efficiency, accuracy, and scalability of prime sieving algorithms; these tweaks and boosters represent a synthesis of old wisdom and new discoveries, offering practical guidance for researchers and practitioners alike.

Abstract Background The determination of nutrient content in the petiole is one of the important methods for achieving cotton fertilization management. The establishment of a monitoring system for the nutrient content of cotton petioles during important growth periods under drip irrigation is of great significance for achieving precise fertilization and environmental protection. Methods A total of 100 cotton fields with an annual yield of 4500–7500 kg/ha were selected among the main cotton-growing areas of Northern Xinjiang. The nitrate nitrogen (NO3 −–N), inorganic phosphorus (PO4 3−–P) and inorganic potassium (K+–K) content and yield of cotton petioles were recorded. Based on a yield of 6000 kg/ha as the dividing line, a two-level and yield-graded monitoring system for NO3 −–N, PO4 3−–P and K+–K in cotton petioles during important growth periods was established, and predictive yield models for NO3 −–N, PO4 3−–P and K+–K in petioles during important growth periods were established. Results The results showed found that the yields of the 100 cotton fields surveyed were normally distributed. Therefore, two yield grades were classified using 6000 kg/ha as a criterion. Under different yield-graded, the NO3 −–N, PO4 3−–P and K+–K content of petiole at important growth stages was significantly positively correlated with yield. Further, the variation range of NO3 −–N, PO4 3−–P and K+–K content in petioles could be used as a standard for yield-graded. In addition, a yield prediction model for the NO3 −–N, PO4 3−–P and K+–K content of petioles was developed. The SSO-BP validation model performed the best (R2 = 0.96, RMSE = 0.06 t/ha, MAE = 0.05 t/ha) in the full bud stage, which was 12.9% higher than the BP validation model. However, the RMSE and MAE were decreased by 86.7% and 88.1%, respectively. Conclusion The establishment of NPK nutrition monitor system of cotton petioles under drip irrigation based on yield-graded provides an important basis for nutrition monitor of cotton petiole under drip irrigation in Xinjiang. It also provides a new method for cotton yield prediction.

The oil-gas mixed transportation pipeline has a high internal corrosion rate. Hence, accurately predicting the internal corrosion rate of mixed transportation pipelines is of great significance to improve the integrity management of pipelines. In response to this problem,the evaluation index system and data set were constructed based on the field monitoring results at first, and the Kernel Principal Component Analysis(KPCA) was used for dimensionality reduction. Then, the Improved Grasshopper Optimization Algorithm(IGOA) was adopted to optimize the Extreme Learning Machine(ELM), the optimal network structure and the excitation function were determined, and the combined prediction model of KPCA-IGOA-ELM was proposed. With this model, prediction was performed based on 8 groups of data, and comparison was made with the results of other models to verify the prediction results. The results showed that three principal components were extracted by KPCA, and the network structure of ELM model was simplified. Among them, H2S partial pressure, CO2 partial pressure, calcium ion, chloride ion, temperature and flow rate have significant contribution to corrosion. In addition, the network structure of the optimal ELM model was determined as 3-32-1 by trial algorithm, and the excitation function was the Sigmoid function, having the minimum root mean square error.Moreover, the RMSE, MAPE and Theil IC of the KPCA-IGOA-ELM combined prediction model are 0.002 56, 2.458 34 and 1.113, respectively,and the average training time is 4.19 s, which are all superior to other models. It is proved that the KPCA-IGOA-ELM model is an excellent algorithm for oil-gas mixed transportation pipelines, which could be popularized and applied in practice.

This study examines the impact of welding heat input on the residual stress and welding deformation of large, thin-walled constructions made of ultra-high strength steel using a single shot calculation method. These structures are susceptible to warpage distortion after welding, which negatively affects production precision. The study uses an interactive orthogonal experimental design to optimize welding parameters and investigate their influence on deformation. Results reveal that welding speed has the most significant impact on deformation, followed by welding voltage and current. The optimal welding parameters (v = 60 cm/min, I = 160 A, U = 16 V) are validated through simulation and experiment, which reduce deformation by 5.4%. After optimization, the pump arm's side bending volume and warpage volume decrease by 4.06% and 9.56%, respectively, and welding deformation significantly reduces. Experimental verification shows a maximum error of 2.6%, indicating the accuracy of the finite element model. This study provides a theoretical basis for improving the performance of welding large, thin-walled box structures.

An air-source heat pump simulation model, accounting for evaporator and condenser pressure drop, has been developed. The model is capable of computing the heat pump's coefficient of performance (COP) under different ambient temperatures and relative humidities above frosting conditions. This research extends an existing iterative simulation method that relies on the equalization of logarithmic mean temperature differences (LMTDs) calculated through two different approaches by adding a pressure drop simulation. Frictional and acceleration pressure drop is considered, computed iteratively. Simulation results for three different refrigerants, R410A, R32 and R290, are compared. The model's accuracy is validated by comparing simulated COP values with measured COP values from the reference heat pump datasheet. The model closely replicates the measured COP values above frosting conditions, with only a slight underestimation of approximately 1.5%. Results show a substantial impact of ambient temperature on the COP. For instance, an ambient temperature of 20 ◦C, compared to 7 ◦C, results in a COP increase of up to 35%, while an ambient temperature of −10 ◦C leads to a 26% reduction in COP. Relative humidity enhances the COP if air moisture condensation becomes possible. Higher condenser capacities negatively affect the COP. The study highlights the differences in pressure drop characteristics between the condenser and the evaporator for the modeled heat pump, with maximum pressure drops of 220 kPa and 50 kPa for the condenser and evaporator, respectively. Additionally, the choice of refrigerant significantly influences pressure drop, with R32 displaying the lowest pressure drop, R410A showing the highest condenser pressure drop, and R290 causing the highest evaporator pressure drop.

In order to solve the problems of the cumbersome user authentication process, insecure identity information, and vulnerable authentication system in traditional identity authentication, a distributed identity authentication method based on blockchain technology is proposed, which utilizes decentralization and is not easy to tamper with characteristics of blockchain and asymmetric encryption to improve the security and stability of user identity authentication system. On this basis, a digital identity authentication optimization scheme is designed, including the use of a hash chain to improve the data structure and the consistency of node data by optimizing the consensus mechanism to enhance authentication security and efficiency. Finally, the automation of authentication is also achieved by introducing smart contracts. The experimental results show that the computational spend of blockchain technology is 55.47% and 97.36% less than the two traditional algorithms, and the overall security score is 22, while the conventional scheme is only 12.5. The blockchain-based authentication mechanism improves the reliability and efficiency of the authentication system.

In this paper, we found that the traditional FCM clustering algorithm is over-sensitive to noise or outliers, and AP clustering is added on the basis of the FCM algorithm to improve and optimize the FCM algorithm. The improved and optimized algorithm is used to derive high-frequency words for teaching English majors, and the hot knowledge map of English teaching is studied according to the high-frequency words. Construct the knowledge map framework and utilize the knowledge map framework to build the U+ English teaching interactive sharing platform. Adopt a top-down approach to construct the knowledge graph, and after defining entity relationships and attributes, propose the learning path recommendation method of the U+ platform based on the knowledge graph. Comparative experiments are used to analyze the teaching effect of the U+ platform and students’ English learning engagement. After 8 weeks of interactive and shared learning on the U+ platform, the students in the experimental class improved their English single choice, perfect fill-in-the-blank, and reading comprehension scores by 2, 4, and 3 points, respectively, and the U+ platform had obvious help in improving the students’ English scores, and the platform was effective in teaching. The mean value of the positive dimension of learning engagement of the students in the experimental class is 4.1634, with an interval range of [4,4.3], and they are positively engaged in English learning, and the mean value of the negative dimension is 1.8341, with a range of [1.6,2.4], and there are fewer negative performances, and the U+ platform has a positive impact on the student’s English learning engagement.

This paper explores the digital learning model from the 4 paths of macro education reform. The four paths of macro education reform include improving the education system, changing the education model, updating education content, and establishing a comprehensive evaluation system. The construction of a learning port is based on the aspects of the learning environment and learning service, as well as research on the characteristics of digital learning modes. Based on BP neural networks, an evaluation model for community education digital resources has been established. The defects of the BP neural network are optimized by using an artificial fish school-frog jump hybrid algorithm, and 19 index factors are selected to construct the evaluation system of digital learning resources. Students’ digital learning abilities and the degree of innovation of digital learning resources in community education were separately analyzed using pre-and post-tests. The average performance of students in the experimental class improved by 9.89 points, and the score interval improved to [85,98], which was significantly better than the control class. The most obvious effect is the improvement of resource use performance, from 7.596 to 9.161. Improved learning ability and innovation of learning resources can be achieved through the use of digital learning modes.

Text detection and recognition are widely used in daily life. Although it is a very rich market, it has very difficult challenges in practical application. The complex and changeable natural scenes lead to the complex background of the text in the image, which also reflects the research value of text information recognition and extraction in natural scenes. To solve the many problems faced by the recognition of Chinese characters, such as complex shapes and diverse structures, this paper uses VGG16 to extract features and introduces a two-layer bidirectional LSTM network. It improves Faster R-CNN by using a RPN to extract candidate boxes and adjust the position of candidate regions. In this paper, the improved model Faster BLSTM-CNN is tested, and the effectiveness experiment of feature extraction, the difference comparison before and after the improvement of the algorithm, and the comparison experiment with the traditional recognition algorithm are carried out respectively. And it finally carried out an experimental comparison of the combination of text recognition and positioning, and obtained the results. The algorithm Faster BLSTM-CNN in this paper is better in the localization and recognition of Chinese characters in the dataset. In the natural scene, the recognition rate of Faster BLSTM-CNN in this paper is 81.54%, the positioning accuracy is 88.14%, and the detection speed is 86 ms, which has improved performance. Therefore, the improvement of Faster R-CNN is effective. It can effectively locate and recognize Chinese characters in natural scenes. [ABSTRACT FROM AUTHOR]

With the development of noisy intermediate-scale quantum machines, quantum processors show their supremacy in specific applications. To better understand the quantum behavior and verify larger quantum bit (qubit) algorithms, simulation on classical computers becomes crucial. However, as the simulated number of qubits increases, the full-state simulation suffers exponential memory increment for state vector storing. In order to compress the state vector, some existing works reduce the memory by data encoding compressors. Nevertheless, the memory requirement remains massive. Meanwhile, others utilize compact decision diagrams (DD) to represent the state vector, which only demands linear memory size. However, the existing DD-based simulation algorithm possesses many redundant calculations that require further exploration. Besides, the traditional normalization-based nodes merging method of DD amplifies the side influences of approximate error. Therefore, to tackle the above challenges, in this paper, we first fully explore the redundancies in the recursive-based DD simulation (RecurSim) algorithm. Inspired by the regularities of the quantum circuit model, a scale-based simulation (ScaleSim) algorithm is proposed, which removes plenty of unnecessary computations. Furthermore, to eliminate the influences of approximate error, we propose a new pre-check DD building method, namely PCB, which maintains the accuracy of DD representation and produces more memory saving. Comprehensive experiments show that our method achieves up to 24124.2 × acceleration and 3.2 × 10 7 × memory reduction than traditional DD-based methods on quantum algorithms while maintaining the representation accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Chemical Engineering (China) / Huaxue Gongcheng is the property of Hualu Engineering Science & Technology Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The challenges posed by cross-scale effects, large computational requirements, high nonlinearity, and complex interactions of multiple physical phenomena constitute major obstacles to the effectiveness and accuracy of welding simulations for large structural components. Therefore, achieving accurate welding simulation to predict and effectively control welding deformation of substantial engineering structural parts is essential to ensure welding quality and improve production efficiency. This paper reviews the current research status of welding numerical simulation of large engineering components, including the establishment of the finite element model, optimization of the heat source model, selection of appropriate finite element calculation method, and the control of welding deformation through optimization algorithm. In addition, the strategies to improve the precision and efficiency of welding numerical simulation and control welding deformation of engineering components are analyzed and discussed. The future development of welding numerical simulation will focus on balancing simulation accuracy and simulation efficiency and optimizing welding parameters to control welding deformation efficiently. [Display omitted] [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Birds and experienced glider pilots frequently use atmospheric updrafts for long-distance flight and energy conservation, with harvested energy from updrafts serving as the foundation. Inspired by their common characteristics in autonomous soaring, a reinforcement learning algorithm, the Twin Delayed Deep Deterministic policy gradient, is used to investigate the optimal strategy for an unpowered glider to harvest energy from thermal updrafts. A round updraft model is utilized to characterize updrafts with varied strengths. A high-fidelity six-degree-of-glider model is used in the dynamic modeling of a glider. The results for various flight initial positions and updraft strengths demonstrate the effectiveness of the strategy learned via reinforcement learning. To enhance the updraft perception ability and expand the applicability of the trained glider agent, an extra wind velocity differential correction module is introduced to the algorithm, and a strategy symmetry method is applied. Comparison experiments regarding round updraft, the Gedeon thermal model, and Dryden continuous turbulence indicate the crucial role of the further optimized methods in improving the updraft-sensing ability of the reinforcement learning glider agent. With optimized methods, a glider trained in a simplified thermal updraft with a simple training method can have more effective flight strategies. [ABSTRACT FROM AUTHOR]