准确地预测多年冻土区地表冻结天数对于当前地表环境有重大意义。当前地表冻结地区融化时间推后,融化结束时间提前,总体冻结时长增加。对于传统置信规则库来说,只考虑了其精准性的问题,而对于地表冻结时长天数,其可解释性具有重大意义,需要考虑水汽、气体以及在融化过程之中的能量交换过程。因此本文使用因子分析法,对于影响地表冻结天数的因素提取因子,然后使用可解释性置信规则库,对地表冻结天数进行可解释性预测,使用中国东北地区的数据进行案例研究,结果表明可解释性置信规则库可以对多年冻土区地表冻结天数进行有效预测,验证了模型的有效性。Accurate prediction of the number of days of surface freezing in perennial permafrost regions is of great significance for the current surface environment. Currently, the thawing time is pushed back in the surface freezing region, the thawing end time is advanced, and the overall freezing duration increases. For the traditional belief rule base, only its accuracy is considered, but for the surface freezing duration days, its interpretability is of great significance, and it needs to consider the water vapor, gas, and the energy exchange process during the melting process. Therefore, this paper uses the factor analysis method to extract the factors for the number of days of surface freezing, and then uses the interpretable confidence rule base to predict the number of days of surface freezing with interpretability, and uses the data from Northeast China to conduct a case study, and the results show that the interpretable belief rule base can effectively predict the number of days of surface freezing in the perennial permafrost region, which verifies the effectiveness of the model.
相机标定是视觉测量中的关键步骤,其目的是确定相机的内外参数,以提高图像处理的精度和可靠性。为解决传统相机标定中标定精度低、鲁棒性弱等一系列问题,提出了基于鲸鱼优化算法的相机标定方法,本方法结合鲸鱼优化算法的全局搜索能力,优化相机参数。在实验中,首先通过张正友标定法获取相机的初始参数。随后,使用鲸鱼优化算法在全局范围内对标定参数进行优化,以最小化重投影误差。实验结果表明,基于鲸鱼优化算法的标定方法相比传统方法具有更高的精度和更强的鲁棒性。Camera calibration is a critical step in vision measurement, the purpose of which is to determine the internal and external parameters of the camera to improve the accuracy and reliability of image processing. In order to solve a series of problems such as low calibration accuracy and weak robustness in traditional camera calibration, a camera calibration method based on whale optimization algorithm was proposed, which combined with the global search ability of whale optimization algorithm to optimize camera parameters. In the experiment, the initial parameters of the camera were obtained by Zhang Zhengyou’s calibration method. Subsequently, the whale optimization algorithm was used to optimize the calibrated parameters on a global scale to minimize the reprojection error. Experimental results show that the calibration method based on whale optimization algorithm has higher accuracy and stronger robustness than the traditional method.
电池以其卓越的储能能力,成为现代科技与生活不可或缺的能源核心,因此对电池老化状态精准诊断和预测是非常重要的。对于一般预测方法而言,电化学模型依赖电池内部机制进行预测,但高度敏感于材料、结构及工作条件变化。机器学习模型依赖高质量大数据与先进算法估算电池健康,但受限于数据质量和算法选择。鉴于上述模型的不足,本文提出了一种创新的电池健康预测模型——基于置信规则库的预测模型。通过构建一系列基于不确定性和模糊性处理的规则,有效应对电池内部状态的复杂性和外部环境的多变性。经实验验证该模型能够提高预测的准确性和可靠性,为锂离子电池健康状态估计及寿命预测领域提供了新的思路和方法,有望在未来能源管理和电池维护中发挥重要作用。Batteries, with their exceptional energy storage capabilities, have emerged as an indispensable energy core in modern technology and daily life. Consequently, accurate diagnosis and prediction of battery aging status are of paramount importance. Traditional prediction methods, such as electrochemical models, rely on the internal mechanisms of batteries for prediction but are highly sensitive to changes in materials, structures, and operating conditions. On the other hand, machine learning models estimate battery health based on high-quality big data and advanced algorithms, yet they are constrained by data quality and algorithm selection. Given the limitations of these models, this paper introduces an innovative battery health prediction model—a prediction model based on a Belief Rule Base. By constructing a series of rules that address uncertainty and fuzziness, it effectively tackles the complexity of the battery’s internal state and the variability of the external environment. Experimental validation demonstrates that this model enhances prediction accuracy and reliability, offering new insights and methodologies for lithium-ion battery health state estimation and lifetime prediction. It is anticipated to play a pivotal role in future energy management and battery maintenance.
空气质量一直是公众和社会最关注的环境问题之一,其质量已经因为经济活动而受到损害。然而,由于空气的复杂性以及人类活动对空气的影响,预测空气质量是一项不小的挑战。传统上使用单一的机器学习模型预测空气质量时,在各种AQI波动趋势下难以获得良好的预测结果。为了有效地解决这一问题,本文提出了一种分层置信规则库(Hierarchy Belief Rule Base-RFI)预测模型,为空气质量预测提供了一种有用的方法。首先,为了提高模型的精准度,采用了随机森林来对关键特征进行筛选,同时对未被筛选出的特征进行ER融合。其次,提出了空气质量预测方法的可解释性准则,以规范整个建模过程的可解释性。然后给出了模型的推理和优化方法。最后通过实验验证了该模型的有效性。Air quality has always been one of the top environmental concerns of the public and society, and its quality has been compromised by economic activities. However, due to the complexity of the air and the impact of human activities on it, predicting air quality is not a small challenge. Traditionally, when a single machine learning model is used to predict air quality, it is difficult to obtain good prediction results under various AQI fluctuation trends. In order to solve this problem effectively, a prediction model based on Hierarchy Belief Rule Base-RFI is proposed in this paper, which provides a useful method for air quality prediction. First of all, in order to improve the accuracy of the model, random forest is used to screen the key features, and ER fusion is carried out on the features that are not screened. Secondly, the interpretability criteria of air quality prediction methods are proposed to standardize the interpretability of the whole modeling process. Then the inference and optimization methods of the model are given. Finally, the validity of the model is verified by experiments.
在交通标志检测任务中,交通标志的准确识别对于自动驾驶和智能交通系统至关重要。本文对Yolov8s模型改进并在CCTSDB2021数据集中进行实验以评估模型的性能,我们采取了以下改进,引入了专门针对小目标设计的检测头,该检测头通过优化特征图的尺度,增强了模型对小尺寸交通标志的识别能力。采用了SIoU损失函数,有助于提升小目标的定位精度。使用模块Star Block集成了一个轻量化模块LB,该模块通过减少参数量同时保持模型检测能力。在CCTSDB2021数据集上的实验结果表明,经过以上改进的Yolov8s模型在检测小尺寸交通标志时,不仅提高了检测准确率,而且减少了一定的参数量,展现了模型改进的有效性。In the traffic sign detection task, accurate recognition of traffic signs is crucial for autonomous driving and intelligent transportation systems. In this paper, we improve the Yolov8s model and conduct experiments in the CCTSDB2021 dataset to evaluate the performance of the model. We have made the following improvements: introducing a detection head specifically designed for small targets. This detection head enhances the model’s recognition ability for small-sized traffic signs by optimizing the scale of the feature map. The SIoU loss function is adopted, which helps to improve the positioning accuracy of small targets. Using the module Star Block, we integrated a lightweight module LB. This module reduces the number of parameters while maintaining the model’s detection ability. The experimental results on the CCTSDB2021 dataset show that the improved Yolov8s model not only improves the detection accuracy but also reduces a certain number of parameters when detecting small-sized traffic signs, demonstrating the effectiveness of model improvement.
玉米作为全球最重要的粮食作物之一,其产量预测在确保粮食安全、优化农业管理以及支持政策制定方面具有重要意义。本文系统综述了当前玉米产量预测领域的主要方法,包括传统的作物预测系统模型、数据驱动的机器学习模型以及近年来迅速发展的深度学习模型,深入分析了气候、土壤、遥感和社会经济等多种预测变量对产量预测精度的影响。通过对现有研究的成果进行总结,本文揭示了不同模型的优劣势,并指出了现阶段研究中存在的不足,如模型泛化能力有限、多模态数据融合的挑战等。最后,本文对未来研究提出了展望,建议进一步探索多源数据的整合、优化模型的适应性以及提升预测的解释性,以推动玉米产量预测技术向更精准、智能化方向发展。本文为未来的玉米产量预测研究提供了有价值的理论基础和实践指导。Maize is one of the most important crops globally, and accurate yield prediction is crucial for food security, agricultural management, and policy decisions. This paper reviews key methods for maize yield prediction, including crop prediction models, machine learning, and deep learning. It analyzes the impact of variables like climate, soil, remote sensing, and socioeconomic factors on prediction accuracy. By summarizing current research, this paper highlights the strengths and limitations of these models and addresses challenges such as limited generalization and multimodal data integration. Finally, it proposes future directions for improving model adaptability and prediction precision, offering valuable insights for further research.
暂无评论