基于自适应Borderline-SMOTE过采样的LightGBM不平衡数据分类算法

针对传统机器学习算法在面对不平衡数据集进行分类时所导致的错误分类、召回率低等问题,提出了一种自适应Borderline-SMOTE过采样的LightGBM不平衡数据集分类算法。在Borderline-SMOTE的基础上,首先采用动态调整采样倍率来控制合成样本的数量,避免过度生成新样本。然后,随机选择边界样本的两个K近邻合成中间样本,用于线性插值生成新样本,一定程度上避免了样本重叠的问题。最后,使用某运营商新办宽带用户及其使用情况数据集,在自适应Borderline-SMOTE过采样方法前提下,验证了LightGBM比KNN和RF有更好的效果。在数据集上与其他流行过采样方法进行实验比较,结果显示,所提出的算法有效地提高了不平衡数据的分类性能。

Research on Euclidean Algorithm and Reection on Its Teaching

In this paper,we prove that Euclid's algorithm,Bezout's equation and Divi-sion algorithm are equivalent to each other.Our result shows that Euclid has preliminarily established the theory of divisibility and the greatest common divisor.We further provided several suggestions for teaching.

基于Borderline-SMOTE和双Attention的入侵检测方法

随着互联网的发展,网络环境愈加复杂,由此导致的网络安全问题不断出现,因此网络安全的防护成为一项重要研究课题。针对真实网络环境中采集到的流量数据非平衡以及传统机器学习方法提取特征表示不准确等问题,文中提出一种基于Borderline-SMOTE和双Attention的入侵检测方法。首先对入侵数据进行Borderline-SMOTE过采样处理,解决了数据非平衡问题,并且利用卷积网络在图像特征提取方面的优势,将一维流量数据转化为灰度图像;然后通过双注意力网络分别从通道维度和空间维度对低维特征进行维度更新,得到更精准的特征表示;最后利用Softmax分类器对流量数据进行分类预测。所提方法的仿真实验均已在NSL-KDD数据集上得到验证,其准确率达到99.24%,相比其他常用方法准确率更高。

基于Borderline-Smote算法改进的FastText中文情感极性分析

针对单一的FastText模型在不平衡中文语料中的情感极性分析效果不好,以及传统Jieba分词对广领域中文文本适应性不强,数据倾斜导致中文情感极性分析的准确率和召回率产生波动等问题,提出一种基于Borderline-Smote算法改进的FastText中文情感极性分析,通过过采样Borderline-Smote和pkuseg中文分词等预处理方式分别解决分类中数据倾斜、涉及领域广的问题,再与FastText结合进行中文情感极性分析。实验结果表明,该模型在中文情感极性分析中的准确率得到了一定的提高。

改进边界分类的Borderline-SMOTE过采样方法

针对不平衡数据中类重叠区域易造成分类错误的问题,提出一种引入合成因子改进边界分类的Borderline-SMOTE过采样方法(IBSM).首先根据少数类样本近邻分布情况找出处于边界的少数类样本,然后计算边界样本对应的合成因子,并根据其取值更新该样本需生成的样本数,最后在近邻中根据合成因子挑选距离最近的top-Z少数类样本进行新样本生成.将提出的方法与八种采样方法在KNN和SVM两种分类器、10个KEEL不平衡数据集上进行对比实验,结果表明,提出的方法在大部分数据集上的F1,G-mean,AUC(Area under Curve)均获得最优值,且F1与AUC的Friedman排名最优,证明所提方法和其余采样方法相比,在处理不平衡数据中的边界样本分类问题时有更好的表现,通过合成因子设定一定的约束条件与分配策略,可以为同类研究提供思路.

基于Borderline-SMOTE算法与Stacking集成学习的前列腺肿瘤风险预测研究

目的:应用数据挖掘方法,建立高准确率的组合模型,对前列腺肿瘤患者的风险进行预测,为前列腺癌(prostate cancer,PCa)的预防和诊断提供参考。方法:选择在临床医学科学数据中心(301医院)进行前列腺穿刺活检的患者682例,运用互信息作为评价标准筛选出与PCa有关的特征属性;针对机器学习的XgBoost、Logistic回归、Adaboost、K近邻和随机森林算法构建单一模型,应用5折交叉验证算法筛选出预测能力较优的3种模型;使用过采样处理,构建基于Borderline-SMOTE的单一模型及构建基于Borderline-SMOTE的Stacking组合模型并探究不同组合方式的影响;最后选择301医院与芜湖弋矶山医院的37例临床病例作为外部验证集对模型进行检验。结果:通过互信息筛选出19个关键特征属性;在单一模型的研究中发现随机森林模型、XgBoost模型以及AdaBoost模型这3种模型表现较优;而基于Borderline-SMOTE的单一模型使得标签属性趋于平衡,AUC值有大幅提升;构建的3种基于Borderline-SMOTE的Stacking组合模型中以XgBoost、随机森林为初级分类器,AdaBoost为次级分类器的组合模型预测能力最好,其准确率为0.9454,召回率为0.9375,精确度为0.9573,F_(1)分数为0.9470,AUC高达0.9823,并且该组合模型在临床验证集上的预测也有较好效果。结论:Borderline-SMOTE过采样处理不平衡数据集十分有效,相较于单一模型的预测,基于多模型融合的Stacking集成学习方式的PCa风险预测方法有着更高的预测精度和良好的推广性能,更有助于PCa的临床诊断。

Underwater four-quadrant dual-beam circumferential scanning laser fuze using nonlinear adaptive backscatter filter based on pauseable SAF-LMS algorithm

The phenomenon of a target echo peak overlapping with the backscattered echo peak significantly undermines the detection range and precision of underwater laser fuzes.To overcome this issue,we propose a four-quadrant dual-beam circumferential scanning laser fuze to distinguish various interference signals and provide more real-time data for the backscatter filtering algorithm.This enhances the algorithm loading capability of the fuze.In order to address the problem of insufficient filtering capacity in existing linear backscatter filtering algorithms,we develop a nonlinear backscattering adaptive filter based on the spline adaptive filter least mean square(SAF-LMS)algorithm.We also designed an algorithm pause module to retain the original trend of the target echo peak,improving the time discrimination accuracy and anti-interference capability of the fuze.Finally,experiments are conducted with varying signal-to-noise ratios of the original underwater target echo signals.The experimental results show that the average signal-to-noise ratio before and after filtering can be improved by more than31 d B,with an increase of up to 76%in extreme detection distance.

MCWOA Scheduler:Modified Chimp-Whale Optimization Algorithm for Task Scheduling in Cloud Computing

Cloud computing provides a diverse and adaptable resource pool over the internet,allowing users to tap into various resources as needed.It has been seen as a robust solution to relevant challenges.A significant delay can hamper the performance of IoT-enabled cloud platforms.However,efficient task scheduling can lower the cloud infrastructure’s energy consumption,thus maximizing the service provider’s revenue by decreasing user job processing times.The proposed Modified Chimp-Whale Optimization Algorithm called Modified Chimp-Whale Optimization Algorithm(MCWOA),combines elements of the Chimp Optimization Algorithm(COA)and the Whale Optimization Algorithm(WOA).To enhance MCWOA’s identification precision,the Sobol sequence is used in the population initialization phase,ensuring an even distribution of the population across the solution space.Moreover,the traditional MCWOA’s local search capabilities are augmented by incorporating the whale optimization algorithm’s bubble-net hunting and random search mechanisms into MCWOA’s position-updating process.This study demonstrates the effectiveness of the proposed approach using a two-story rigid frame and a simply supported beam model.Simulated outcomes reveal that the new method outperforms the original MCWOA,especially in multi-damage detection scenarios.MCWOA excels in avoiding false positives and enhancing computational speed,making it an optimal choice for structural damage detection.The efficiency of the proposed MCWOA is assessed against metrics such as energy usage,computational expense,task duration,and delay.The simulated data indicates that the new MCWOA outpaces other methods across all metrics.The study also references the Whale Optimization Algorithm(WOA),Chimp Algorithm(CA),Ant Lion Optimizer(ALO),Genetic Algorithm(GA)and Grey Wolf Optimizer(GWO).

基于改进Borderline-Smote-GBDT的冠心病预测

针对样本不平衡问题,提出一种基于欧氏距离改进的Borderline-Smote过采样算法。首先根据欧式距离判断少数类样本类别;然后根据边界上的少数类样本的k近邻数据找出线性直线,由同侧近邻数据判别是否为噪音;最后重新判别删除噪音的剩余少数类样本的类别,对边界少数类样本和密集的非边界区域的少数类样本过采样合成新样本。等磁场图和二维电流密度图中提取的心磁特征数据集经过改进Borderline-Smote过采样处理,结果表明改进Borderline-SmoteGBDT冠心病预测模型相比Borderline-Smote-GBDT模型准确率提高8.4%,精确率提高2.9%,召回率提高9.1%,AUC提高4.6%。此外,与逻辑回归、随机森林、k近邻、极端随机树模型对比发现,GBDT结果最优,改进Borderline-Smote-GBDT准确率、召回率、精确率、AUC分别为91.7%、91.7%、81.8%、87.1%,验证了该模型的可行性。

Enhancing Cancer Classification through a Hybrid Bio-Inspired Evolutionary Algorithm for Biomarker Gene Selection

In this study,our aim is to address the problem of gene selection by proposing a hybrid bio-inspired evolutionary algorithm that combines Grey Wolf Optimization(GWO)with Harris Hawks Optimization(HHO)for feature selection.Themotivation for utilizingGWOandHHOstems fromtheir bio-inspired nature and their demonstrated success in optimization problems.We aimto leverage the strengths of these algorithms to enhance the effectiveness of feature selection in microarray-based cancer classification.We selected leave-one-out cross-validation(LOOCV)to evaluate the performance of both two widely used classifiers,k-nearest neighbors(KNN)and support vector machine(SVM),on high-dimensional cancer microarray data.The proposed method is extensively tested on six publicly available cancer microarray datasets,and a comprehensive comparison with recently published methods is conducted.Our hybrid algorithm demonstrates its effectiveness in improving classification performance,Surpassing alternative approaches in terms of precision.The outcomes confirm the capability of our method to substantially improve both the precision and efficiency of cancer classification,thereby advancing the development ofmore efficient treatment strategies.The proposed hybridmethod offers a promising solution to the gene selection problem in microarray-based cancer classification.It improves the accuracy and efficiency of cancer diagnosis and treatment,and its superior performance compared to other methods highlights its potential applicability in realworld cancer classification tasks.By harnessing the complementary search mechanisms of GWO and HHO,we leverage their bio-inspired behavior to identify informative genes relevant to cancer diagnosis and treatment.

基于Borderline-SMOTE-IHT混合采样的改进GWO-SVM变压器故障诊断方法

针对变压器故障数据不均衡导致变压器故障诊断精度不高的问题,提出一种基于Borderline-SMOTE-IHT混合采样的改进GWO-SVM变压器故障诊断方法。首先,利用Borderline-SMOTE算法选择最具代表性的边界样本生成少数类新样本,利用IHT算法剔除多数类中的噪声样本或边缘样本,增大类间特征的差异性。其次,基于差分进化思想,在灰狼算法中引入动态收敛因子和概率突变机制,对SVM模型中的惩罚因子和核参数进行优化,以提高算法的全局搜索能力和收敛精度。最后,通过实验对比分析,证明了所提方法的有效性。

Rao Algorithms-Based Structure Optimization for Heterogeneous Wireless Sensor Networks

The structural optimization of wireless sensor networks is a critical issue because it impacts energy consumption and hence the network’s lifetime.Many studies have been conducted for homogeneous networks,but few have been performed for heterogeneouswireless sensor networks.This paper utilizes Rao algorithms to optimize the structure of heterogeneous wireless sensor networks according to node locations and their initial energies.The proposed algorithms lack algorithm-specific parameters and metaphorical connotations.The proposed algorithms examine the search space based on the relations of the population with the best,worst,and randomly assigned solutions.The proposed algorithms can be evaluated using any routing protocol,however,we have chosen the well-known routing protocols in the literature:Low Energy Adaptive Clustering Hierarchy(LEACH),Power-Efficient Gathering in Sensor Information Systems(PEAGSIS),Partitioned-based Energy-efficient LEACH(PE-LEACH),and the Power-Efficient Gathering in Sensor Information Systems Neural Network(PEAGSIS-NN)recent routing protocol.We compare our optimized method with the Jaya,the Particle Swarm Optimization-based Energy Efficient Clustering(PSO-EEC)protocol,and the hybrid Harmony Search Algorithm and PSO(HSA-PSO)algorithms.The efficiencies of our proposed algorithms are evaluated by conducting experiments in terms of the network lifetime(first dead node,half dead nodes,and last dead node),energy consumption,packets to cluster head,and packets to the base station.The experimental results were compared with those obtained using the Jaya optimization algorithm.The proposed algorithms exhibited the best performance.The proposed approach successfully prolongs the network lifetime by 71% for the PEAGSIS protocol,51% for the LEACH protocol,10% for the PE-LEACH protocol,and 73% for the PEGSIS-NN protocol;Moreover,it enhances other criteria such as energy conservation,fitness convergence,packets to cluster head,and packets to the base station.

Product quality prediction based on RBF optimized by firefly algorithm

With the development of information technology,a large number of product quality data in the entire manufacturing process is accumulated,but it is not explored and used effectively.The traditional product quality prediction models have many disadvantages,such as high complexity and low accuracy.To overcome the above problems,we propose an optimized data equalization method to pre-process dataset and design a simple but effective product quality prediction model:radial basis function model optimized by the firefly algorithm with Levy flight mechanism(RBFFALM).First,the new data equalization method is introduced to pre-process the dataset,which reduces the dimension of the data,removes redundant features,and improves the data distribution.Then the RBFFALFM is used to predict product quality.Comprehensive expe riments conducted on real-world product quality datasets validate that the new model RBFFALFM combining with the new data pre-processing method outperforms other previous me thods on predicting product quality.

Multi-Strategy Assisted Multi-Objective Whale Optimization Algorithm for Feature Selection

In classification problems,datasets often contain a large amount of features,but not all of them are relevant for accurate classification.In fact,irrelevant features may even hinder classification accuracy.Feature selection aims to alleviate this issue by minimizing the number of features in the subset while simultaneously minimizing the classification error rate.Single-objective optimization approaches employ an evaluation function designed as an aggregate function with a parameter,but the results obtained depend on the value of the parameter.To eliminate this parameter’s influence,the problem can be reformulated as a multi-objective optimization problem.The Whale Optimization Algorithm(WOA)is widely used in optimization problems because of its simplicity and easy implementation.In this paper,we propose a multi-strategy assisted multi-objective WOA(MSMOWOA)to address feature selection.To enhance the algorithm’s search ability,we integrate multiple strategies such as Levy flight,Grey Wolf Optimizer,and adaptive mutation into it.Additionally,we utilize an external repository to store non-dominant solution sets and grid technology is used to maintain diversity.Results on fourteen University of California Irvine(UCI)datasets demonstrate that our proposed method effectively removes redundant features and improves classification performance.The source code can be accessed from the website:https://github.com/zc0315/MSMOWOA.

Falcon Optimization Algorithm-Based Energy Efficient Communication Protocol for Cluster-Based Vehicular Networks

Rapid development in Information Technology(IT)has allowed several novel application regions like large outdoor vehicular networks for Vehicle-to-Vehicle(V2V)transmission.Vehicular networks give a safe and more effective driving experience by presenting time-sensitive and location-aware data.The communication occurs directly between V2V and Base Station(BS)units such as the Road Side Unit(RSU),named as a Vehicle to Infrastructure(V2I).However,the frequent topology alterations in VANETs generate several problems with data transmission as the vehicle velocity differs with time.Therefore,the scheme of an effectual routing protocol for reliable and stable communications is significant.Current research demonstrates that clustering is an intelligent method for effectual routing in a mobile environment.Therefore,this article presents a Falcon Optimization Algorithm-based Energy Efficient Communication Protocol for Cluster-based Routing(FOA-EECPCR)technique in VANETS.The FOA-EECPCR technique intends to group the vehicles and determine the shortest route in the VANET.To accomplish this,the FOA-EECPCR technique initially clusters the vehicles using FOA with fitness functions comprising energy,distance,and trust level.For the routing process,the Sparrow Search Algorithm(SSA)is derived with a fitness function that encompasses two variables,namely,energy and distance.A series of experiments have been conducted to exhibit the enhanced performance of the FOA-EECPCR method.The experimental outcomes demonstrate the enhanced performance of the FOA-EECPCR approach over other current methods.

Application of DSAPSO Algorithm in Distribution Network Reconfiguration with Distributed Generation

With the current integration of distributed energy resources into the grid,the structure of distribution networks is becoming more complex.This complexity significantly expands the solution space in the optimization process for network reconstruction using intelligent algorithms.Consequently,traditional intelligent algorithms frequently encounter insufficient search accuracy and become trapped in local optima.To tackle this issue,a more advanced particle swarm optimization algorithm is proposed.To address the varying emphases at different stages of the optimization process,a dynamic strategy is implemented to regulate the social and self-learning factors.The Metropolis criterion is introduced into the simulated annealing algorithm to occasionally accept suboptimal solutions,thereby mitigating premature convergence in the population optimization process.The inertia weight is adjusted using the logistic mapping technique to maintain a balance between the algorithm’s global and local search abilities.The incorporation of the Pareto principle involves the consideration of network losses and voltage deviations as objective functions.A fuzzy membership function is employed for selecting the results.Simulation analysis is carried out on the restructuring of the distribution network,using the IEEE-33 node system and the IEEE-69 node system as examples,in conjunction with the integration of distributed energy resources.The findings demonstrate that,in comparison to other intelligent optimization algorithms,the proposed enhanced algorithm demonstrates a shorter convergence time and effectively reduces active power losses within the network.Furthermore,it enhances the amplitude of node voltages,thereby improving the stability of distribution network operations and power supply quality.Additionally,the algorithm exhibits a high level of generality and applicability.

Quantitatively characterizing sandy soil structure altered by MICP using multi-level thresholding segmentation algorithm

The influences of biological,chemical,and flow processes on soil structure through microbially induced carbonate precipitation(MICP)are not yet fully understood.In this study,we use a multi-level thresholding segmentation algorithm,genetic algorithm(GA)enhanced Kapur entropy(KE)(GAE-KE),to accomplish quantitative characterization of sandy soil structure altered by MICP cementation.A sandy soil sample was treated using MICP method and scanned by the synchrotron radiation(SR)micro-CT with a resolution of 6.5 mm.After validation,tri-level thresholding segmentation using GAE-KE successfully separated the precipitated calcium carbonate crystals from sand particles and pores.The spatial distributions of porosity,pore structure parameters,and flow characteristics were calculated for quantitative characterization.The results offer pore-scale insights into the MICP treatment effect,and the quantitative understanding confirms the feasibility of the GAE-KE multi-level thresholding segmentation algorithm.

A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm

Real-time intelligent lithology identification while drilling is vital to realizing downhole closed-loop drilling. The complex and changeable geological environment in the drilling makes lithology identification face many challenges. This paper studies the problems of difficult feature information extraction,low precision of thin-layer identification and limited applicability of the model in intelligent lithologic identification. The author tries to improve the comprehensive performance of the lithology identification model from three aspects: data feature extraction, class balance, and model design. A new real-time intelligent lithology identification model of dynamic felling strategy weighted random forest algorithm(DFW-RF) is proposed. According to the feature selection results, gamma ray and 2 MHz phase resistivity are the logging while drilling(LWD) parameters that significantly influence lithology identification. The comprehensive performance of the DFW-RF lithology identification model has been verified in the application of 3 wells in different areas. By comparing the prediction results of five typical lithology identification algorithms, the DFW-RF model has a higher lithology identification accuracy rate and F1 score. This model improves the identification accuracy of thin-layer lithology and is effective and feasible in different geological environments. The DFW-RF model plays a truly efficient role in the realtime intelligent identification of lithologic information in closed-loop drilling and has greater applicability, which is worthy of being widely used in logging interpretation.

Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

Genetic algorithm assisted meta-atom design for high-performance metasurface optics

Metasurfaces,composed of planar arrays of intricately designed meta-atom structures,possess remarkable capabilities in controlling electromagnetic waves in various ways.A critical aspect of metasurface design involves selecting suitable meta-atoms to achieve target functionalities such as phase retardation,amplitude modulation,and polarization conversion.Conventional design processes often involve extensive parameter sweeping,a laborious and computationally intensive task heavily reliant on designer expertise and judgement.Here,we present an efficient genetic algorithm assisted meta-atom optimization method for high-performance metasurface optics,which is compatible to both single-and multiobjective device design tasks.We first employ the method for a single-objective design task and implement a high-efficiency Pancharatnam-Berry phase based metalens with an average focusing efficiency exceeding 80%in the visible spectrum.We then employ the method for a dual-objective metasurface design task and construct an efficient spin-multiplexed structural beam generator.The device is capable of generating zeroth-order and first-order Bessel beams respectively under right-handed and left-handed circular polarized illumination,with associated generation efficiencies surpassing 88%.Finally,we implement a wavelength and spin co-multiplexed four-channel metahologram capable of projecting two spin-multiplexed holographic images under each operational wavelength,with efficiencies over 50%.Our work offers a streamlined and easy-to-implement approach to meta-atom design and optimization,empowering designers to create diverse high-performance and multifunctional metasurface optics.