检索结果-内蒙古大学图书馆

ENG 2025年第4期6卷 75-75页

作者： Lara-Arellano, Edgar Takacs, Andras Tovar-Arriaga, Saul Rodriguez-Resendiz, Juvenal Univ Autonoma Queretaro Fac Ingn Queretaro 76010 Mexico

This work presents a method for classifying EEG (Electroencephalogram) signals generated when a person concentrates on specific words, defined as "Imagined Speech". Imagined speech is essential to enhance problem-solving, memory, and language development. In addition, imagined speech is beneficial because of its applications in therapy fields like managing anxiety or improving communication skills. EEG measures the electrical activity of the brain. EEG signal classification is difficult as the machine learning (ML) algorithm has to learn how to categorize the signal linked to the imagined word. This work proposes a novel method to generate a specific feature vector to achieve classification with superior accuracy results to those found in the state of the art. The method leverages a genetic algorithm to create an optimal feature combination for the classification task and machine learning model. This algorithm can efficiently explore ample feature space and identify the most relevant features for the task. The proposed method achieved an accuracy of 96% using eight electrodes for EEG signal recordings.

关键词： imagined speech EEG feature extraction genetic algorithm classification optimization algorithms signal processing biomedical

来源：评论

学校读者我要写书评

暂无评论

Multi-scale grid model-based optimization algorithm for tobacco logistics distribution routes

Multi-scale grid model-based optimization algorithm for toba...

引用

2024 International Conference on Smart Transportation and City Engineering, STCE 2024

作者： Zhou, Jingjing Longnan Company of Gansu Province Tobacco Corporation Gansu Longnan China

ISBN: (纸本)9781510690585

The current conventional tobacco logistics distribution route optimization algorithm mainly optimizes the route by optimizing the vehicle configuration and site selection nodes, which leads to poor optimization results due to the lack of consideration of distribution costs. In this regard, a multi-scale grid model-based tobacco logistics distribution route optimization algorithm is proposed. With the distribution cost as the optimization objective, a growth multi-scale network model is constructed with the distribution nodes, and a distribution route optimization model is built. In the experiments, the optimization performance of the proposed method is verified. The experimental results show that the distribution route optimization model constructed by the proposed method has a high convergence of the algorithm and has a more desirable optimization effect. © 2025 SPIE.

关键词： distribution routes multi-scale grid model optimization algorithms tobacco logistics

来源：评论

学校读者我要写书评

暂无评论

Advanced swarm intelligence algorithms in quantum circuit design

引用

INTERNATIONAL JOURNAL OF PARALLEL EMERGENT AND DISTRIBUTED SYSTEMS 2025年第1期40卷 1-20页

作者： Horackova, Libuse Zelinka, Ivan VSB Tech Univ Ostrava IT4Innovat 17. listopadu 2172-15 Ostrava 708 00 Czech Republic VSB Tech Univ Ostrava Quantum Comp Lab IT4Innovat Ostrava Czech Republic VSB Tech Univ Ostrava Dept Comp Sci Ostrava Czech Republic

This study explores the potential of employing algorithms like iSOMA, Differential Evolution, Particle Swarm optimization, Grey Wolf optimization, and Ant Colony optimization for the design of quantum computing circuits. Utilizing the Qiskit environment, the research involved simulating a straightforward quantum circuit with variable parameters. To substantiate the effectiveness of these algorithms, three distinct experimental setups were conducted under varying conditions and degrees of freedom. The findings reveal that these algorithms are not only suitable for simulations but also excel in identifying solutions that conserve qubits. A comparative analysis of the methods was performed using the Friedman test, followed by the Nemenyi post-hoc test to evaluate their relative performance.

关键词： Quantum computation quantum circuit Qiskit optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Mushroom species classification and implementation based on improved MobileNetV3

引用

JOURNAL OF FOOD SCIENCE 2025年第4期90卷 e70186页

作者： Peng, Jun Li, Song Li, Hui Lan, Zhiwei Ma, Zhipeng Xiang, Chao Li, Shoutai Chongqing Univ Technol Coll Mech Engn Chongqing Peoples R China Chongqing Hualv Biotechnol Co Ltd Chongqing Peoples R China Southwest Univ Coll Engn & Technol Chongqing Peoples R China

Current methods for mushroom species classification face limitations in generalization ability and lack exploration of model deployment. To address these issues, this study systematically compares five models, including Transformer and common convolutional neural networks. MobileNetV3 was chosen as the model for this study, combining transfer learning with the adaptive hybrid optimizer (AHO) and dynamic cyclic learning rate strategies proposed in this research. The AHO merges Adam's fast convergence with stochastic gradient descent's stable fine-tuning. It adjusts the learning rate dynamically based on training progress, enabling quick convergence early on and precise adjustments later. The optimized model was trained, validated, and deployed on a dataset constructed in this study, which includes 3633 images covering three types of mushrooms. The model achieved a validation accuracy of 98.13% and an average test accuracy of 97.98%, with the smallest standard deviation of validation loss fluctuation (0.0343), confirming the model's stability. Notably, due to the slightly larger number of images in the Matsutake training subset (1412 images) compared to the other two categories (1148 and 1073 images), the test accuracy for Matsutake (99.28%) was slightly higher than that for Red mushroom (96.97%) and Beefsteak mushroom (97.69%), highlighting a minor limitation. However, the recall and F1 scores for each class are balanced, suggesting that the model exhibits robust performance in addressing interclass similarities, as corroborated by t-SNE visualization and Grad-CAM analysis. Additionally, the study confirmed the feasibility of practical application through deployment on PC, Android, and embedded platforms, providing a guiding solution for laboratory research, wild mushroom picking, and automated mushroom sorting. Practical Application This study provides an AI model based on a lightweight neural network for identifying different mushroom species. It can be widely appl

关键词： convolutional neural networks mobilenetv3 mushroom species classification optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Inventory Costs in Manufacturing Systems Using Trapezoidal and Pentagonal Fuzzy Numbers

引用

JOURNAL OF MATHEMATICS 2025年第1期2025卷

作者： Dhandapani, Prasantha Bharathi Kalaichelvan, Kalaiarasi Ramalingam, Soundaria Biomy, Mohamed Radwan, Taha Sri Eshwar Coll Engn Dept Math Coimbatore 641202 Tamil Nadu India Bharathidasan Univ Cauvery Coll Women Autonomous PG & Res Dept Math Tiruchirappalli 620018 Tamil Nadu India Srinivas Univ Dept Math Mangalore 574146 India Qassim Univ Coll Business & Econ Dept Management Informat Syst Buraydah 51452 Saudi Arabia

Every manufacturing industry strives to always provide impeccable goods. Due to machine failures, labor issues, etc., this is practically unachievable in real-world situations during the manufacturing run time. As a result, things of subpar quality are produced by the equipment systems. The inferior-quality products are improved at a cost to make them better, and then they are prepared for sale. The nonlinear programming Lagrangian method is used to determine the best solution, which affects the average monthly cost. In the suggested model, the graded mean integration representation method is used to describe defuzzification while trapezoidal and pentagonal fuzzy numbers are used to calculate the optimal cost though there are different types of fuzzy numbers available that are used to test the optimality. The main aim of the paper is to compare the trapezoidal and pentagonal fuzzy numbers to test the optimal total cost. As a result, the trapezoidal fuzzy number gives an accurate result in all cases, while in the pentagonal fuzzy number, there is a slight deviation in the fuzzy case. So when we go with a higher-order fuzzy number, the accuracy of the optimal total cost changes. Finally, a graphic comparison using MATLAB is carried out for the two fuzzy numbers and the best out of them is found.

关键词： decision making fuzzy logics inventory model optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

An Improved Branch-and-bound Algorithm for Sum-of-linear-ratios Problem

引用

IAENG International Journal of Applied Mathematics 2025年第2期55卷 369-377页

作者： Ding, Xianfeng Mei, Hanbing Wen, Pengfei Yi, Xiaolin Qin, Yiyu Luo, Qianmei School of Science Southwest Petroleum University Chengdu610500 China

This paper presents a fresh global optimization algorithm specifcally designed for the sum-of-linear-ratios problem. Initially, auxiliary variables are introduced to reformulate the original problem into an equivalent form, and the equivalence of the optimal solution in this new formulation is established. Additionally, the linear relaxation technique is applied to simplify the objective function and constraint conditions of the equivalent problem, thereby obtaining a linear relaxation programming problem. By resolving a progression of linear programming instances, the upper bound of the original problem undergoes continuous updates, while the linear relaxation problem offers a viable and effcient lower bound for the original problem. Subsequently, an improved branch-and-bound algorithm for tackling the original problem is introduced, incorporating hybrid division rules. The convergence of this algorithm is demonstrated. Ultimately, numerical experiments validate the feasibility and effcacy of the proposed algorithm. © (2024), (International Association of Engineers). All rights reserved.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Zeroth-Order Adaptive Frank–Wolfe Algorithm for Resource Allocation in Internet of Things: Convergence Analysis

引用

IEEE Internet of Things Journal 2025年第11期12卷 17765-17779页

作者： Liu, Muhua Zhu, Yajie Wu, Qingtao Ji, Zhihang Zhao, Xuhui Zheng, Ruijuan Henan University of Science and Technology Longmen Laboratory School of Information Engineering Luoyang471023 China Henan University of Science and Technology School of Information Engineering Luoyang471023 China

A pivotal problem in the Internet of Things (IoT) is resource allocation, where the goal is to optimize allocation strategies of IoT resources. In general, resource allocation problems are formulated as constrained optimization problems, which can be effectively solved by the zeroth-order Frank-Wolfe algorithm. However, the existing zeroth-order Frank-Wolfe algorithms suffer from slow convergence since they scale the zeroth-order gradient in all directions. For this reason, we propose a faster zeroth-order Frank-Wolfe algorithm, referred to as ZO-AdaSFW, which incorporates adaptive gradient methods and the variance-reduced technique (SPIDER) into the zeroth-order Frank-Wolfe algorithm. Moreover, ZO-AdaSFW can achieve the convergence rate of O(T-1) in the convex setting, where T is the time horizon. Meanwhile, we also prove that ZO-AdaSFW has the best-known convergence rate O(T-1/2) among zeroth-order algorithms in the nonconvex setting. In addition, the experimental results show that the performance of ZO-AdaSFW outperforms state-of-the-art zeroth-order Frank-Wolfe algorithms on different applications. © 2014 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Fairness aware secure energy efficiency maximization for UAV-assisted data collection in backscattering networks

引用

VEHICULAR COMMUNICATIONS 2025年 52卷

作者： Zeng, Jiawang Mishra, Deepak Gharakheili, Hassan Habibi Seneviratne, Aruna Univ New South Wales Sch Elect Engn & Telecommun Sydney Australia

Autonomous vehicles for intelligent surveillance in rural areas increasingly demand low-cost and reliable data collection technologies to perform dense monitoring across extended areas. Backscattering communication has been employed for this purpose, primarily for low-cost and energy efficiency reasons. This paper considers a backscattering data collection system empowered by unmanned aerial vehicles (UAVs) to overcome the challenge of wireless coverage and provide backscattering tags with physical-layer security. Relevant prior works only focused on the secrecy of backscattering communications, while the limited battery of UAVs was overlooked during the underlying vehicle control. This paper aims to jointly optimize the trajectory of multiple UAVs and choice of tags, as well as tags' reflection parameters, to manage data leakage and total energy consumed by UAVs during a round of data collection. Our specific contributions are threefold. (1) We propose a 3D multiUAV backscattering data collection framework and formulate an optimization problem to maximize the ratio of secrecy across all tags to the power consumption of UAVs subject to some practical constraints. (2) We show that our problem is non-convex and partition it into three sub-problems, transform objective functions, and relax certain constraints to obtain approximate convex problems that yield suboptimal solutions. (3) We evaluate the efficacy of our proposed intelligent security protocol for UAV-assisted data collection, compare its performance with some baseline schemes, our protocal achieve leading performance in terms of secrecy energy efficiency. We also provide the impact of parameters on the secrecy energy efficiency, as well as quantify its complexity via extensive simulations.

关键词： Vehicle control optimization algorithms Rotary-wing UAV communications Backscatter networks Security protocol Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Hybrid salp swarm maximum power point tracking algorithm for photovoltaic systems in highly fluctuating environmental conditions

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-24页

作者： Jamaludin, Mohd Nasrul Izzani Tajuddin, Mohammad Faridun Naim Younis, Tarek Thanikanti, Sudhakar Babu Khishe, Mohammad Univ Malaysia Perlis Fac Elect Engn & Technol Arau 02600 Malaysia Aswan Univ Dept Elect Engn Aswan 81528 Egypt Chaitanya Bharathi Inst Technol Dept Elect & Elect Engn Hyderabad 500075 India Imam Khomeini Naval Sci Univ Nowshahr Dept Elect Engn Nowshahr Iran Yuan Ze Univ Innovat Ctr Artificial Intelligence Applicat Taoyuan City Taiwan Appl Sci Private Univ Appl Sci Res Ctr Amman 11937 Jordan Jadara Univ Res Ctr Irbid Jordan

The maximum power delivered by a photovoltaic system is greatly influenced by atmospheric conditions such as irradiation and temperature and by surrounding objects like trees, raindrops, tall buildings, animal droppings, and clouds. The partial shading caused by these surrounding objects and the rapidly changing atmospheric parameters make maximum power point tracking (MPPT) challenging. This paper proposes a hybrid MPPT algorithm that combines the benefits of the salp swarm algorithm (SSA) and hill climbing (HC) techniques. As long as the rate of change of irradiance does not exceed a specific limit, the HC mode is applied to track the global maximum power point (GMPP). Once a high rate of change in irradiation is detected, the SSA mode is activated. Moreover, the proposed algorithm employs the concept of boundary conditions to handle fast and slow fluctuating irradiance patterns. A comprehensive comparative evaluation of the proposed hybrid SSA-HC with state-of-the-art MPPT algorithms has been undertaken. Four distinct cases have been examined, including irradiance conditions with varying rates of change and partial shading conditions. The proposed hybrid SSA-HC algorithm has been validated and tested using a developed hardware setup, simulated in MATLAB for solar photovoltaic (PV) systems, and compared with standard SSA and HC. The performance of the tracking capability of this proposed hybrid technique at both steady-state and dynamic conditions under rapid and gradual irradiance changes demonstrates its superiority over recent state-of-the-art algorithms.

关键词： Maximum power point tracking optimization algorithms Fluctuating environments Partial shading Solar PV system

来源：评论

学校读者我要写书评

暂无评论

A Novel Community Detection Algorithm Based on Node Propagation and Attraction

引用

IEEE Access 2025年 13卷 69161-69174页

作者： Fu, Lidong Xie, Xinxing Dou, Zengfa Bai, Yun Zhao, Xi Xi'an University of Science and Technology College of Computer Science and Technology Xi'an710600 China Qinghai Institute of Technology School of Computer and Information Science Xining810016 China Xi'an University School of Information Engineering Xi'an710065 China Xi'an Big Data Service Center Xi'an710007 China

High-quality community detection in complex networks typically relies on the similarity between nodes to select communities. However, when a node exhibits the same similarity with different communities, it becomes ambiguous to determining the optimal community assignment for that node, potentially leading to incorrect predictions and affecting the accuracy of community assignments for other nodes. To address this problem, this paper proposes a novel community detection algorithm based on node propagation and attraction. The algorithm first introduces a node propagation strategy, which identifies high-propagation nodes based on their connectivity and core attributes. These high-propagation nodes form the initial backbone and framework of communities, minimizing the interference of low-propagation nodes on community structure. Subsequently, an attraction definition is introduced, which starts from high-propagation nodes to select partitioning methods based on their relationships with neighboring nodes, using the attraction among these nodes facilitate community organization and propagation, aiming to enhance community quality. Finally, in the community optimization phase, the algorithm effectively improves the accuracy of partitions that result from similar attractions by considering the association degree between nodes and communities. Experimental results demonstrate that, on both synthetic and real networks, the proposed algorithm outperforms various existing community detection algorithms. © 2013 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：