Incident and Problem Ticket Clustering and Classification Using Deep Learning

A holistic analysis of problem and incident tickets in a real production cloud service environment is presented in this paper.By extracting different bags of words,we use principal component analysis(PCA)to examine the clustering characteristics of these tickets.Then Kmeans and latent Dirichlet allocation(LDA)are applied to show the potential clusters within this Cloud environment.The second part of our study uses a pre-trained bidirectional encoder representation from transformers(BERT)model to classify the tickets,with the goal of predicting the optimal dispatching department for a given ticket.Experimental results show that due to the unique characteristics of ticket description,pre-processing with domain knowledge turns out to be critical in both clustering and classification.Our classification model yields 86%accuracy when predicting the target dispatching department.

Identifying multidisciplinary problems from scientific publications based on a text generation method

Purpose:A text generation based multidisciplinary problem identification method is proposed,which does not rely on a large amount of data annotation.Design/methodology/approach:The proposed method first identifies the research objective types and disciplinary labels of papers using a text classification technique;second,it generates abstractive titles for each paper based on abstract and research objective types using a generative pre-trained language model;third,it extracts problem phrases from generated titles according to regular expression rules;fourth,it creates problem relation networks and identifies the same problems by exploiting a weighted community detection algorithm;finally,it identifies multidisciplinary problems based on the disciplinary labels of papers.Findings:Experiments in the“Carbon Peaking and Carbon Neutrality”field show that the proposed method can effectively identify multidisciplinary research problems.The disciplinary distribution of the identified problems is consistent with our understanding of multidisciplinary collaboration in the field.Research limitations:It is necessary to use the proposed method in other multidisciplinary fields to validate its effectiveness.Practical implications:Multidisciplinary problem identification helps to gather multidisciplinary forces to solve complex real-world problems for the governments,fund valuable multidisciplinary problems for research management authorities,and borrow ideas from other disciplines for researchers.Originality/value:This approach proposes a novel multidisciplinary problem identification method based on text generation,which identifies multidisciplinary problems based on generative abstractive titles of papers without data annotation required by standard sequence labeling techniques.

Inverse Problems for Dynamic Systems: Classification and Solution Methods

The inverse problems for motions of dynamic systems of which are described by system of the ordinary differential equations are examined. The classification of such type of inverse problems is given. It was shown that inverse problems can be divided into two types: synthesis inverse problems and inverse problems of measurement (recognition). Each type of inverse problems requires separate approach to statements and solution methods. The regularization method for obtaining of stable solution of inverse problems was suggested. In some cases, instead of recognition of inverse problems solution, the estimation of solution can be used. Within the framework of this approach, two practical inverse problems of measurement are considered.

Enhanced Arithmetic Optimization Algorithm Guided by a Local Search for the Feature Selection Problem

High-dimensional datasets present significant challenges for classification tasks.Dimensionality reduction,a crucial aspect of data preprocessing,has gained substantial attention due to its ability to improve classification per-formance.However,identifying the optimal features within high-dimensional datasets remains a computationally demanding task,necessitating the use of efficient algorithms.This paper introduces the Arithmetic Optimization Algorithm(AOA),a novel approach for finding the optimal feature subset.AOA is specifically modified to address feature selection problems based on a transfer function.Additionally,two enhancements are incorporated into the AOA algorithm to overcome limitations such as limited precision,slow convergence,and susceptibility to local optima.The first enhancement proposes a new method for selecting solutions to be improved during the search process.This method effectively improves the original algorithm’s accuracy and convergence speed.The second enhancement introduces a local search with neighborhood strategies(AOA_NBH)during the AOA exploitation phase.AOA_NBH explores the vast search space,aiding the algorithm in escaping local optima.Our results demonstrate that incorporating neighborhood methods enhances the output and achieves significant improvement over state-of-the-art methods.

Vibrating Particles System Algorithm for Solving Classification Problems

Big data is a term that refers to a set of data that,due to its largeness or complexity,cannot be stored or processed with one of the usual tools or applications for data management,and it has become a prominent word in recent years for the massive development of technology.Almost immediately thereafter,the term“big data mining”emerged,i.e.,mining from big data even as an emerging and interconnected field of research.Classification is an important stage in data mining since it helps people make better decisions in a variety of situations,including scientific endeavors,biomedical research,and industrial applications.The probabilistic neural network(PNN)is a commonly used and successful method for handling classification and pattern recognition issues.In this study,the authors proposed to combine the probabilistic neural network(PPN),which is one of the data mining techniques,with the vibrating particles system(VPS),which is one of the metaheuristic algorithms named“VPS-PNN”,to solve classi-fication problems more effectively.The data set is eleven common benchmark medical datasets from the machine-learning library,the suggested method was tested.The suggested VPS-PNN mechanism outperforms the PNN,biogeography-based optimization,enhanced-water cycle algorithm(E-WCA)and the firefly algorithm(FA)in terms of convergence speed and classification accuracy.

A Preliminary Study on the Problems and Improvement of the Latest Land Use Classification System in China

The establishment of a unified land use classification system is the basis for realizing the unified management of land and sea,urban and rural areas,and aboveground and underground space.In November 2020,the Ministry of Natural Resources of the People's Republic of China issued the Classification Guide for Land and Space Survey,Planning and Use Control of Land and Sea(for Trial Implementation),which aims to establish a national unified land and sea use classification system,lay an important foundation for scientific planning and unified management of natural resources,rational use and protection of natural resources,and speed up the construction of a new pattern of land and space development and protection.However,there are still some obvious shortcomings in the Classification Guide.This paper analyzes some problems existing in this classification standard from three aspects of logicality,rigorousness and comprehensiveness,and puts forward some suggestions for further improvement.This has important practical significance to better guiding the practice of land use and land resources management,and then to achieving the goal of unified management of natural resources.

Improved Classification Approach via GEPSVM

A modified multisurface ＂proximal support vector machine classifier via generalized eigenvalues （GEPSVM for short）＂ was proposed. By defining a new principle, we designed a new classification approach via GEPSVM, namely, maximum or minimum plane distance GEPSVM （MPDGEPSVM）. Unlike GEPSVM, our approach obtains two planes by solving two simple eigenvalue problems, such that it can avoid occurrence of singular problems. Our approach, compared with GEPSVM, has better classification performalce. Moreover, MPDGEPSVM is over one order of magnitude faster than GEPSVM, and almost two orders of magnitude faster than SVM. Computational results on public datasets from UCI database illustrated the efficiency of MPDGEPSVM.

MCBC-SMOTE:A Majority Clustering Model for Classification of Imbalanced Data

Datasets with the imbalanced class distribution are difficult to handle with the standard classification algorithms.In supervised learning,dealing with the problem of class imbalance is still considered to be a challenging research problem.Various machine learning techniques are designed to operate on balanced datasets;therefore,the state of the art,different undersampling,over-sampling and hybrid strategies have been proposed to deal with the problem of imbalanced datasets,but highly skewed datasets still pose the problem of generalization and noise generation during resampling.To overcome these problems,this paper proposes amajority clusteringmodel for classification of imbalanced datasets known as MCBC-SMOTE(Majority Clustering for balanced Classification-SMOTE).The model provides a method to convert the problem of binary classification into a multi-class problem.In the proposed algorithm,the number of clusters for themajority class is calculated using the elbow method and the minority class is over-sampled as an average of clustered majority classes to generate a symmetrical class distribution.The proposed technique is cost-effective,reduces the problem of noise generation and successfully disables the imbalances present in between and within classes.The results of the evaluations on diverse real datasets proved to provide better classification results as compared to state of the art existing methodologies based on several performance metrics.

Advanced Hierarchical Fuzzy Classification Model Adopting Symbiosis Based DNA-ABC Optimization Algorithm

This paper offers a symbiosis based hybrid modified DNA-ABC optimization algorithm which combines modified DNA concepts and artificial bee colony (ABC) algorithm to aid hierarchical fuzzy classification. According to literature, the ABC algorithm is traditionally applied to constrained and unconstrained problems, but is combined with modified DNA concepts and implemented for fuzzy classification in this present research. Moreover, from the best of our knowledge, previous research on the ABC algorithm has not combined it with DNA computing for hierarchical fuzzy classification to explore the merits of cooperative coevolution. Therefore, this paper is the first to apply the mechanism of symbiosis to create a hybrid modified DNA-ABC algorithm for hierarchical fuzzy classification applications. In this study, the partition number and the shape of the membership function are extracted by the symbiosis based hybrid modified DNA-ABC optimization algorithm, which provides both sufficient global exploration and also adequate local exploitation for hierarchical fuzzy classification. The proposed optimization algorithm is applied on five benchmark University of Irvine (UCI) data sets, and the results prove the efficiency of the algorithm.

基于互信息解决多标签文本分类中的长尾问题

针对当前解决多标签文本分类中长尾问题的方法多以破坏原本数据分布为代价,在真实数据上的泛化性能下降,无法有效地缓解样本的长尾分布的问题,提出了基于互信息解决长尾问题的多标签文本分类方法(MLTC-LD)。首先,创建关于标签样本的关系矩阵,计算标签样本间的依赖关系;其次,考虑标签样本间关系程度的强弱构造邻居选择器,将拥有强关系的邻居信息作为主要语义特征并作为先验信息;最后,通过图注意力神经网络将先验信息引入分类器,实现了借助分布头部数据丰富类的知识来提高尾部数据贫乏类性能的目标。在三个不同的数据集上将MLTC-LD与八个基线模型进行了广泛的比较分析。实验结果表明,MLTC-LD与最优的HGLRN相比精确度分别提高了3.5%、0.3%、1.5%,证明了该方法的有效性。

基于改进支持向量机的皮革划痕检测方法

针对传统皮革划痕检测方法存在检测准确率低、检测效率不高的问题,提出一种基于K-means聚类算法改进支持向量机SVM的皮革划痕检测方法。首先,对支持向量机基本原理进行分析;然后采用K-means聚类算法解决支持向量机SVM的二分类问题;最后搭建一个K-means-SVM皮革划痕检测模型,通过此模型实现皮革划痕快速准确检测。试验结果表明,本模型的检测精度为96.74%,相较于传统的YOLOv5模型、CRNN模型和SVM-DS模型分别高出了18.85%、20.17%、13.06%,且本模型进行皮革划痕检测的所用时长仅为11.52 s,均低于另外3种模型。由此说明,本模型的检测精度更高,检测速度更快,满足真皮表面划痕检测的实时性和准确性需求。

运用PCNE分类系统对呼吸道疾病患者进行药学监护的应用研究

目的 运用欧洲医药保健网(PCNE)分类系统对呼吸道疾病患者进行药学监护,探索呼吸科的有效药学监护模式,促进临床合理用药。方法 选取安徽理工大学第一附属医院2022年诊断为慢性阻塞性肺疾病(COPD)和肺部感染的住院患者,分为简单组和干预组;根据PCNE分类系统,对药物相关问题(DRPs)的类型、原因、干预、干预的接受情况及解决状态等方面进行分析。结果 共纳入病例120例,简单组60例,干预组60例。DRPs发生人数方面,简单组15例,干预组45例,两组差异有统计学意义(P <0.05)。DRPs共82个,主要涉及治疗效果(51.22%)和安全性(46.34%),原因为患者药物使用方法不正确、用法用量不适宜和未定期安全监测等。药师干预中,药物层面75个(91.46%),医生层面38个(46.34%),患者层面43个(52.44%);药师干预后,接受率为97.56%,74.39%的DRPs得到解决。结论 应用PCNE分类系统进行药学监护能够增强临床药师发现和处理DRPs的能力,减少临床发生不良事件的风险,促进患者的合理、安全用药;同时还有助于药学监护实施记录的标准化和规范化,可为呼吸科患者的药学服务模式提供参考。

基于PycModel高效深度学习模型的心理咨询问题分类探究

大众心理健康问题日益受到广泛关注。为提高心理医疗资源的使用效率,采用互联网手段采集与心理咨询相关的数据,使用一种融合脚本筛选、数据整理以及利用Easydata进行主动学习式数据标注的新方法构建数据集,结合卷积神经网络和BERT预训练模型等技术,在textvec-base-chinese模型的基础上,提出了PycModel模型,以实现更加高效的心理咨询问题分类。实验结果显示,PycModel在心理咨询问题分类的准确率明显优于其他参照模型,该模型能够有效提高心理咨询的效率和效果,可以为心理健康服务提供有力的支持。

中国药物相关问题分类系统在神经内科药学监护中的应用

目的探讨中国药物相关问题分类系统在神经内科住院患者药学监护中的应用。方法选取2022年3—6月浙江大学医学院附属金华医院神经内科收治的222例住院患者为研究对象,回顾性分析临床药师工作记录。依照中国药物相关问题分类系统对药物相关问题(DRP)进行整理和分析。采用二项Logistic回归模型明确发生DRP的影响因素。结果222例患者中,有76例(34.23%)存在DRP,共识别出104个DRP。DRP主要问题类型为治疗安全性(39.42%)。DRP涉及对象均为医生,严重程度评估涉及最多的级别为“DRP到达了患者,但患者没有受到伤害”(81.73%)。DRP主要原因为“药物选择”(67.31%),其次为“用法用量”(26.92%)。共有62个(59.62%)DRP的介入方案被接受,介入方案总体接受率为87.32%。最终有61个(58.65%)DRP被解决。DRP涉及例次最多的药物类别为抗血小板药物。二项Logistic回归分析结果显示,用药品种数[OR=1.097,95%CI(1.030,1.167)]是神经内科住院患者发生DRP的影响因素(P<0.05)。结论神经内科住院患者DRP普遍存在。中国药物相关问题分类系统有助于临床药师对药学监护数据进行回顾和整理,总结共性问题和解决经验,提高药学监护效果。

新能源汽车发展现状研究综述

由于化石燃料的大量消耗,已经造成环境污染、能源短缺等问题。而新能源汽车的出现可以解决这些问题。因此,本文着重对新能源汽车进行研究,分析了新能源汽车与传统燃油车各自的优缺点。介绍了新能源汽车的历史发展阶段、主要分类、现阶段依然有待解决的问题以及未来发展趋势。对我国应对气候变化,推动人类社会可持续发展具有借鉴意义。

基于引领森林的多粒度广义长尾分类

长尾分类在现实世界中是一项不可避免且充满挑战的任务。传统方法通常只专注于类间的不平衡分布,然而近期的研究开始重视类内的长尾分布,即同一类别内,具有头部属性的样本远多于尾部属性的样本。由于属性的隐含性和其组合的复杂性,类内不平衡问题更加难以处理。为此,文中提出一种基于引领森林并使用多中心损失的广义长尾分类框架(Cognisance),旨在通过不变性特征学习的范式建立长尾分类问题的多粒度联合求解模型。首先,该框架通过无监督学习构建粗粒度引领森林(Coarse-Grained Leading Forest,CLF),以更好地表征类内关于不同属性的样本分布,进而在不变风险最小化的过程中构建不同的环境。其次,设计了一种新的度量学习损失,即多中心损失(Multi-Center Loss,MCL),可在特征学习过程中逐步消除混淆属性。同时,Cognisance不依赖于特定模型结构,可作为独立组件与其他长尾分类方法集成。在ImageNet-GLT和MSCOCO-GLT数据集上的实验结果显示,所提框架取得了最佳性能,现有方法通过与本框架集成,在Top1-Accuracy指标上均获得2%~8%的提升。

考虑残保政策的多等级工人拆卸线平衡问题建模与优化

针对拆卸企业的操作者仍以单一等级工人为主且尚未考虑雇佣残疾工人的问题,提出了考虑残疾人保障政策的多等级工人拆卸线平衡问题,建立了以最小化工作站数量、空闲均衡指标、价值指标和最大化拆卸线收益为优化目标的数学模型。基于问题特点,采用三层解码方式,设计了离散共生生物搜索算法。该算法引入莱维飞行策略,改进了互利、寄生操作,结合Pareto思想和拥挤距离机制从而筛选出多个非劣解。现有基准测试结果表明所提出算法的寻优能力和收敛性能均优于文献中的其他算法。最后,以某品牌V6发动机作为实例进一步验证所提模型和算法,与多种算法计算结果进行对比,证明所提算法计算所提模型的适用性和优越性,并为企业决策者提供多种侧重点不同的拆卸方案。

药物治疗管理结合PCNE分类系统对乙型肝炎肝硬化患者的药学服务效果评价

目的应用药物治疗管理(MTM)结合欧洲医药保健网(PCNE)的模式对乙型肝炎(乙肝)肝硬化患者进行药学服务,从临床疗效、安全性、人文效果以及药物相关问题等方面分析药学服务成效。方法将乙肝肝硬化患者随机分为药学组(50例)和仅接受传统治疗的对照组(48例),临床药师运用MTM结合PCNE分类系统对药学组进行药学服务,分别从经济效果、临床疗效和安全性、人文结果进行比较,并分析药学组药物相关问题(DRPs)。结果药学组日均用药费用及药占比以及临床指标转归优于对照组,前者药品不良反应相较后者在随访3个月时差异有统计学意义,用药依从性和生活质量在干预后和随访期间均差异有统计学意义(P<0.05)。药学组DRPs共计52个,类别主要为治疗效果不佳,原因主要有药物选择不合理和用法用量不合理,干预接受共计46个,共计解决45个。结论MTM结合PCNE分类系统的药学服务模式对乙肝肝硬化患者的治疗和后续随访具有积极作用。

求解约束优化问题的改进蛇优化算法

结合外点罚函数法与改进蛇优化算法求解约束优化问题,得到一种新的求解约束优化问题的算法WDFSO。算法WDFSO首先通过外点罚函数法将约束优化问题转化为一系列界约束优化问题,然后运用基于变异质心的对立学习策略与种群分类策略改进的蛇优化算法对所得界约束优化问题进行求解,进而获得所求约束优化问题的解。为验证算法WDFSO的有效性,选取CEC2006中19个标准约束优化问题进行数值实验,并使用Wilcoxon秩和检验来证明算法的显著性。实验结果表明,与对比算法相比,算法WDFSO求解约束优化问题具有更高的收敛精度和更好的稳定性。最后应用算法WDFSO求解两个工程约束优化问题,结果表明算法WDFSO求解性能更好。

建筑幕墙预埋件施工质量问题及处治措施

以广州市广发银行总部大楼幕墙建设项目为依托,提出预埋件质量问题三分类方案并制定相应的处治措施;对广州市黄埔区红山街某金融商业大厦幕墙预埋件质量检测结果统计分析。结果表明,Ⅱ类预埋件位置偏差问题出现频次最高,占比为64.4%,针对此制订了预埋件位置偏差纠正方案,依据偏差程度制定对应的纠偏措施,预埋件质量检测结果总合格率为95.8%,达到缩短工期的目的。