Development of Data Mining Models Based on Features Ranks Voting (FRV)

Data size plays a significant role in the design and the performance of data mining models.A good feature selection algorithm reduces the problems of big data size and noise due to data redundancy.Features selection algorithms aim at selecting the best features and eliminating unnecessary ones,which in turn simplifies the structure of the data mining model as well as increases its performance.This paper introduces a robust features selection algorithm,named Features Ranking Voting Algorithm FRV.It merges the benefits of the different features selection algorithms to specify the features ranks in the dataset correctly and robustly;based on the feature ranks and voting algorithm.The FRV comprises of three different proposed techniques to select the minimum best feature set,the forward voting technique to select the best high ranks features,the backward voting technique,which drops the low ranks features(low importance feature),and the third technique merges the outputs from the forward and backward techniques to maximize the robustness of the selected features set.Different data mining models were built using obtained selected features sets from applying the proposed FVR on different datasets;to evaluate the success behavior of the proposed FRV.The high performance of these data mining models reflects the success of the proposed FRV algorithm.The FRV performance is compared with other features selection algorithms.It successes to develop data mining models for the Hungarian CAD dataset with Acc.of 96.8%,and with Acc.of 96%for the Z-Alizadeh Sani CAD dataset compared with 83.94%and 92.56%respectively in[48].

Smart Approaches to Efficient Text Mining for Categorizing Sexual Reproductive Health Short Messages into Key Themes

To promote behavioral change among adolescents in Zambia, the National HIV/AIDS/STI/TB Council, in collaboration with UNICEF, developed the Zambia U-Report platform. This platform provides young people with improved access to information on various Sexual Reproductive Health topics through Short Messaging Service (SMS) messages. Over the years, the platform has accumulated millions of incoming and outgoing messages, which need to be categorized into key thematic areas for better tracking of sexual reproductive health knowledge gaps among young people. The current manual categorization process of these text messages is inefficient and time-consuming and this study aims to automate the process for improved analysis using text-mining techniques. Firstly, the study investigates the current text message categorization process and identifies a list of categories adopted by counselors over time which are then used to build and train a categorization model. Secondly, the study presents a proof of concept tool that automates the categorization of U-report messages into key thematic areas using the developed categorization model. Finally, it compares the performance and effectiveness of the developed proof of concept tool against the manual system. The study used a dataset comprising 206,625 text messages. The current process would take roughly 2.82 years to categorise this dataset whereas the trained SVM model would require only 6.4 minutes while achieving an accuracy of 70.4% demonstrating that the automated method is significantly faster, more scalable, and consistent when compared to the current manual categorization. These advantages make the SVM model a more efficient and effective tool for categorizing large unstructured text datasets. These results and the proof-of-concept tool developed demonstrate the potential for enhancing the efficiency and accuracy of message categorization on the Zambia U-report platform and other similar text messages-based platforms.

Research on evolution of mining pressure field and fracture field and gas emission features

The relation between mining pressure field-fracture field and gas emission of working face is analyzed, and the concept that there is a stress point （or strain point） among permeability of coal is presented. It is believed that the mutation of coal permeability caused by the sudden loading or unloading of working face roof as periodic weighting occurs is the main reason that a lot of gas pour into the working face. Based on the above concept, the relation is established among abutment pressure during periodie weighting, permeability of coal seam and gas emission, and relation graph is drawn. Then the loading and unloading features of coal at the moment of fracture and non-fracture of main roof are revealed. And finally it is presented that the process of sudden loading or unloading as periodic weighting occurs plays an important role in rupture propagation of coal, analytical movement of gas and gas emission.

Identifying Metabolite and Protein Biomarkers in Unstable Angina In-patients by Feature Selection Based Data Mining Method

Unstable angina（UA） is the most dangerous type of Coronary Heart Disease（CHD） to cause more and more mortal and morbid world wide. Identification of biomarkers for UA at the level of proteomics and metabolomics is a better avenue to understand the inner mechanism of it. Feature selection based data mining method is better suited to identify biomarkers of UA. In this study, we carried out clinical epidemiology to collect plasmas of UA in-patients and controls. Proteomics and metabolomics data were obtained via two-dimensional difference gel electrophoresis and gas chromatography techniques. We presented a novel computational strategy to select biomarkers as few as possible for UA in the two groups of data. Firstly, decision tree was used to select biomarkers for UA and 3-fold cross validation was used to evaluate computational performanees for the three methods. Alternatively, we combined inde- pendent t test and classification based data mining method as well as backward elimination technique to select, as few as possible, protein and metabolite biomarkers with best classification performances. By the method, we selected 6 proteins and 5 metabolites for UA. The novel method presented here provides a better insight into the pathology of a disease.

Gender Prediction on Twitter Using Stream Algorithms with N-Gram Character Features

The rapid growth of social networks has produced an unprecedented amount of user-generated data, which provides an excellent opportunity for text mining. Authorship analysis, an important part of text mining, attempts to learn about the author of the text through subtle variations in the writing styles that occur between gender, age and social groups. Such information has a variety of applications including advertising and law enforcement. One of the most accessible sources of user-generated data is Twitter, which makes the majority of its user data freely available through its data access API. In this study we seek to identify the gender of users on Twitter using Perceptron and Nai ve Bayes with selected 1 through 5-gram features from tweet text. Stream applications of these algorithms were employed for gender prediction to handle the speed and volume of tweet traffic. Because informal text, such as tweets, cannot be easily evaluated using traditional dictionary methods, n-gram features were implemented in this study to represent streaming tweets. The large number of 1 through 5-grams requires that only a subset of them be used in gender classification, for this reason informative n-gram features were chosen using multiple selection algorithms. In the best case the Naive Bayes and Perceptron algorithms produced accuracy, balanced accuracy, and F-measure above 99%.

Importance of Features Selection,Attributes Selection,Challenges and Future Directions for Medical Imaging Data:A Review

In the area of pattern recognition and machine learning,features play a key role in prediction.The famous applications of features are medical imaging,image classification,and name a few more.With the exponential growth of information investments in medical data repositories and health service provision,medical institutions are collecting large volumes of data.These data repositories contain details information essential to support medical diagnostic decisions and also improve patient care quality.On the other hand,this growth also made it difficult to comprehend and utilize data for various purposes.The results of imaging data can become biased because of extraneous features present in larger datasets.Feature selection gives a chance to decrease the number of components in such large datasets.Through selection techniques,ousting the unimportant features and selecting a subset of components that produces prevalent characterization precision.The correct decision to find a good attribute produces a precise grouping model,which enhances learning pace and forecast control.This paper presents a review of feature selection techniques and attributes selection measures for medical imaging.This review is meant to describe feature selection techniques in a medical domainwith their pros and cons and to signify its application in imaging data and data mining algorithms.The review reveals the shortcomings of the existing feature and attributes selection techniques to multi-sourced data.Moreover,this review provides the importance of feature selection for correct classification of medical infections.In the end,critical analysis and future directions are provided.

Improving Knowledge Based Spam Detection Methods: The Effect of Malicious Related Features in Imbalance Data Distribution

Spam is no longer just commercial unsolicited email messages that waste our time, it consumes network traffic and mail servers’ storage. Furthermore, spam has become a major component of several attack vectors including attacks such as phishing, cross-site scripting, cross-site request forgery and malware infection. Statistics show that the amount of spam containing malicious contents increased compared to the one advertising legitimate products and services. In this paper, the issue of spam detection is investigated with the aim to develop an efficient method to identify spam email based on the analysis of the content of email messages. We identify a set of features that have a considerable number of malicious related features. Our goal is to study the effect of these features in helping the classical classifiers in identifying spam emails. To make the problem more challenging, we developed spam classification models based on imbalanced data where spam emails form the rare class with only 16.5% of the total emails. Different metrics were utilized in the evaluation of the developed models. Results show noticeable improvement of spam classification models when trained by dataset that includes malicious related features.

Feature Selection with Optimal Stacked Sparse Autoencoder for Data Mining

Data mining in the educational field can be used to optimize the teaching and learning performance among the students.The recently developed machine learning(ML)and deep learning(DL)approaches can be utilized to mine the data effectively.This study proposes an Improved Sailfish Optimizer-based Feature SelectionwithOptimal Stacked Sparse Autoencoder(ISOFS-OSSAE)for data mining and pattern recognition in the educational sector.The proposed ISOFS-OSSAE model aims to mine the educational data and derive decisions based on the feature selection and classification process.Moreover,the ISOFS-OSSAEmodel involves the design of the ISOFS technique to choose an optimal subset of features.Moreover,the swallow swarm optimization(SSO)with the SSAE model is derived to perform the classification process.To showcase the enhanced outcomes of the ISOFSOSSAE model,a wide range of experiments were taken place on a benchmark dataset from the University of California Irvine(UCI)Machine Learning Repository.The simulation results pointed out the improved classification performance of the ISOFS-OSSAE model over the recent state of art approaches interms of different performance measures.

Misdiagnosis Features of Ancient Clinical Records Based on Apriori Algorithm

Objective:To analyze misdiagnosis features in clinical cases of“Classified Medical Cases of Famous Physicians”and“Supplement to Classified Case Records of Celebrated Physicians.”Materials and Methods:Two hundred and five ancient misdiagnosed cases were analyzed in aspects of locations(exterior-interior type,qi-blood type and Zang‑Fu organs type)and patterns(heat-cold type and deficiency-excess type)by Apriori Algorithm Method.Results:The main types of misdiagnosis in those medical casesare as follows::Zang‑Fu location misjudgment,misjudging the interior as the exterior,misjudging deficiency pattern as excess pattern,and misjudging cold pattern as heat pattern.Among them,the most outstanding type is the misjudgment of deficiency–cold pattern as excess–heat pattern.Conclusions:(1)Accurate judgment of location and differentiation of deficiency and excess patterns are the key points in diagnosing the diseases correctly.The confusion of true deficiency–cold and pseudo‑excess–heat pattern should be taken seriously.(2)Data mining on ancient clinical cases offers a new methodology for assisting clinical diagnosis of traditional Chinese medicine.

Research on the big data feature mining technology based on the cloud computing

The cloud computing platform has the functions of efficiently allocating the dynamic resources, generating the dynamic computing and storage according to the user requests, and providing the good platform for the big data feature analysis and mining. The big data feature mining in the cloud computing environment is an effective method for the elficient application of the massive data in the information age. In the process of the big data mining, the method o f the big data feature mining based on the gradient sampling has the poor logicality. It only mines the big data features from a single-level perspective, which reduces the precision of the big data feature mining.

Human Verification over Activity Analysis via Deep Data Mining

Human verification and activity analysis(HVAA)are primarily employed to observe,track,and monitor human motion patterns using redgreen-blue(RGB)images and videos.Interpreting human interaction using RGB images is one of the most complex machine learning tasks in recent times.Numerous models rely on various parameters,such as the detection rate,position,and direction of human body components in RGB images.This paper presents robust human activity analysis for event recognition via the extraction of contextual intelligence-based features.To use human interaction image sequences as input data,we first perform a few denoising steps.Then,human-to-human analyses are employed to deliver more precise results.This phase follows feature engineering techniques,including diverse feature selection.Next,we used the graph mining method for feature optimization and AdaBoost for classification.We tested our proposed HVAA model on two benchmark datasets.The testing of the proposed HVAA system exhibited a mean accuracy of 92.15%for the Sport Videos in theWild(SVW)dataset.The second benchmark dataset,UT-interaction,had a mean accuracy of 92.83%.Therefore,these results demonstrated a better recognition rate and outperformed other novel techniques in body part tracking and event detection.The proposed HVAA system can be utilized in numerous real-world applications including,healthcare,surveillance,task monitoring,atomic actions,gesture and posture analysis.

Chimp Optimization Algorithm Based Feature Selection with Machine Learning for Medical Data Classification

Datamining plays a crucial role in extractingmeaningful knowledge fromlarge-scale data repositories,such as data warehouses and databases.Association rule mining,a fundamental process in data mining,involves discovering correlations,patterns,and causal structures within datasets.In the healthcare domain,association rules offer valuable opportunities for building knowledge bases,enabling intelligent diagnoses,and extracting invaluable information rapidly.This paper presents a novel approach called the Machine Learning based Association Rule Mining and Classification for Healthcare Data Management System(MLARMC-HDMS).The MLARMC-HDMS technique integrates classification and association rule mining(ARM)processes.Initially,the chimp optimization algorithm-based feature selection(COAFS)technique is employed within MLARMC-HDMS to select relevant attributes.Inspired by the foraging behavior of chimpanzees,the COA algorithm mimics their search strategy for food.Subsequently,the classification process utilizes stochastic gradient descent with a multilayer perceptron(SGD-MLP)model,while the Apriori algorithm determines attribute relationships.We propose a COA-based feature selection approach for medical data classification using machine learning techniques.This approach involves selecting pertinent features from medical datasets through COA and training machine learning models using the reduced feature set.We evaluate the performance of our approach on various medical datasets employing diverse machine learning classifiers.Experimental results demonstrate that our proposed approach surpasses alternative feature selection methods,achieving higher accuracy and precision rates in medical data classification tasks.The study showcases the effectiveness and efficiency of the COA-based feature selection approach in identifying relevant features,thereby enhancing the diagnosis and treatment of various diseases.To provide further validation,we conduct detailed experiments on a benchmark medical dataset,revealing the superiority of the MLARMCHDMS model over other methods,with a maximum accuracy of 99.75%.Therefore,this research contributes to the advancement of feature selection techniques in medical data classification and highlights the potential for improving healthcare outcomes through accurate and efficient data analysis.The presented MLARMC-HDMS framework and COA-based feature selection approach offer valuable insights for researchers and practitioners working in the field of healthcare data mining and machine learning.

Evolutionary Algorithm Based Feature Subset Selection for Students Academic Performance Analysis

Educational Data Mining(EDM)is an emergent discipline that concen-trates on the design of self-learning and adaptive approaches.Higher education institutions have started to utilize analytical tools to improve students’grades and retention.Prediction of students’performance is a difficult process owing to the massive quantity of educational data.Therefore,Artificial Intelligence(AI)techniques can be used for educational data mining in a big data environ-ment.At the same time,in EDM,the feature selection process becomes necessary in creation of feature subsets.Since the feature selection performance affects the predictive performance of any model,it is important to elaborately investigate the outcome of students’performance model related to the feature selection techni-ques.With this motivation,this paper presents a new Metaheuristic Optimiza-tion-based Feature Subset Selection with an Optimal Deep Learning model(MOFSS-ODL)for predicting students’performance.In addition,the proposed model uses an isolation forest-based outlier detection approach to eliminate the existence of outliers.Besides,the Chaotic Monarch Butterfly Optimization Algo-rithm(CBOA)is used for the selection of highly related features with low com-plexity and high performance.Then,a sailfish optimizer with stacked sparse autoencoder(SFO-SSAE)approach is utilized for the classification of educational data.The MOFSS-ODL model is tested against a benchmark student’s perfor-mance data set from the UCI repository.A wide-ranging simulation analysis por-trayed the improved predictive performance of the MOFSS-ODL technique over recent approaches in terms of different measures.Compared to other methods,experimental results prove that the proposed(MOFSS-ODL)classification model does a great job of predicting students’academic progress,with an accuracy of 96.49%.

Heterogeneous Ensemble Feature Selection Model(HEFSM)for Big Data Analytics

Big Data applications face different types of complexities in classifications.Cleaning and purifying data by eliminating irrelevant or redundant data for big data applications becomes a complex operation while attempting to maintain discriminative features in processed data.The existing scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.Recently ensemble methods have made a mark in classification tasks as combine multiple results into a single representation.When comparing to a single model,this technique offers for improved prediction.Ensemble based feature selections parallel multiple expert’s judgments on a single topic.The major goal of this research is to suggest HEFSM(Heterogeneous Ensemble Feature Selection Model),a hybrid approach that combines multiple algorithms.The major goal of this research is to suggest HEFSM(Heterogeneous Ensemble Feature Selection Model),a hybrid approach that combines multiple algorithms.Further,individual outputs produced by methods producing subsets of features or rankings or voting are also combined in this work.KNN(K-Nearest Neighbor)classifier is used to classify the big dataset obtained from the ensemble learning approach.The results found of the study have been good,proving the proposed model’s efficiency in classifications in terms of the performance metrics like precision,recall,F-measure and accuracy used.

Underground Coal Mine Target Tracking via Multi-Feature Joint Sparse Representation

Single-feature methods are unable to effectively track a target in an underground coal mine video due to the high background noise, low and uneven illumination, and drastic light fluctuation in the video. In this study, we propose an underground coal mine personnel target tracking method using multi-feature joint sparse representation. First, with a particle filter framework, the global and local multiple features of the target template and candidate particles are extracted. Second, each of the candidate particles is sparsely represented by a dictionary template, and reconstruction is achieved after solving the sparse coefficient. Last, the particle with the lowest reconstruction error is deemed the tracking result. To validate the effectiveness of the proposed algorithm, we compare the proposed method with three commonly employed tracking algorithms. The results show that the proposed method is able to reliably track the target in various scenarios, such as occlusion and illumination change, which generates better tracking results and validates the feasibility and effectiveness of the proposed method.

融合全局聚合与局部挖掘的建筑图像检索

针对建筑图像易受到尺度变化和局部遮挡干扰而导致检索准确率低的问题,本文提出了一种融合全局聚合与局部挖掘的建筑图像检索网络。以ResNet50为骨干网络并在其后引入多尺度特征聚合的全局分支和注意力引导特征挖掘的局部分支,再通过正交融合策略高效整合双分支互补特征。其中,多尺度特征聚合模块结合混合空洞卷积和通道注意力对全局不同尺度的目标进行自适应加权聚合,增强网络对建筑多尺度显著特征的提取;注意力引导特征挖掘模块通过信息互补注意力对最显著特征标记擦除,实现对局部区域中潜在的细节信息的挖掘。所提方法在主流建筑数据集ROxf和RPar上的平均精度均值(mAP)指标分别达到了81.54%(M)、62.43%(H)和90.28%(M)、78.35%(H)。实验结果表明,该方法有效克服了尺度变化和局部遮挡的干扰,显著提升了建筑图像检索的准确率。

矿用干式变压器故障诊断和寿命预测技术现状及展望

干式变压器故障诊断技术通过对监测数据进行分析,能够实现信号特征提取、故障诊断、状态评估和寿命预测,提高干式变压器在井下运行的安全性,降低由于故障带来的损失。文章介绍了信号特征提取方法(频率响应法、小波变换法、堆叠自编码器)、故障诊断方法(贝叶斯网络、支持向量机、BP神经网络)、状态评估和寿命预测方法(交叉熵组合预测法、灰色理论、层次分析法)的研究现状,将几种方法进行对比,并对干式变压器故障诊断技术进行展望。

融合边界注意力的特征挖掘息肉小目标网络

从结肠图像中分割息肉小目标病变区域对于预防结直肠癌至关重要,它可以为结直肠癌的诊断提供有价值的信息。然而目前现有的方法存在2个局限性:一是不能稳健捕获全局上下文信息,二是未能充分挖掘细粒度细节特征信息。因此,提出融合边界注意力的特征挖掘息肉小目标网络(transformer feature boundary network,TFB-Net)。该网络主要包括3个核心模块:首先,采用Transformer辅助编码器建立长程依赖关系,补充全局信息;其次,设计特征挖掘模块进一步细化特征,学习到更好的特征;最后,使用边界反转注意力模块加强对边界语义空间的关注,提高区域辨别能力。在5个息肉小目标数据集上进行广泛实验,实验结果表明TFBNet具有优越的分割性能。

关家崖煤矿重复采动巷道变形特征及控制对策研究

针对重复采动巷道围岩变形严重、无法复用,重复采动巷道在服务期内具有明显的叠加演化特征的问题,以关家崖煤矿13092巷道为研究背景,采用现场实测、数值模拟和理论分析的方法,对重复采动巷道变形的叠加扩展特征和控制对策进行了研究。重复采动巷道变形特征分析结果表明:①一次回采扰动下,重复采动巷道变形呈现分区和非对称破坏特征,可划分为快速变形区、强烈变形区和缓慢变形区;裂纹破坏主要在煤壁帮和煤柱帮,而顶底板较少,表现为巷道两帮显著片帮和内移;煤壁帮与顶板、煤柱帮与底板交汇处变形严重。②二次采动巷道在一次破坏基础上叠加扩展,使得非对称破坏更加显著,形成巷道围岩蝶形叠加塑性破坏区。③重复采动巷道围岩控制的重点时间为一次回采阶段,重点区域为强烈变形区和缓慢变形区的巷道煤柱帮一侧。通过分析采动巷道蝶形变形特征和破坏分区规律,提出了重复采动巷道多层次耦合控制技术,采用浅低压−深高压注浆提高煤柱支撑力,采用锚索补强提高支护体支撑力,实现耦合控制。通过加固前后变形量对比分析验证了多层次耦合控制满足巷道复用要求。

基于多特征融合的露天矿区道路负障碍检测

随着智慧矿山概念的逐步落实,智能化、无人化逐渐在矿区落实,露天矿卡车无人驾驶日益成为矿山智能化建设的主要内容,为解决露天矿区复杂多变的道路因坑洼、塌陷等路面小部分下陷出现的非规则负障碍而导致矿区无人车、重载卡车侧翻等安全难题,提升矿区安全驾驶系数,提出一种多特征融合的露天矿区道路负障碍检测方法。该方法使用BiFPN特征融合模块,提高小型负障碍检测权重占比;引入空间和通道双注意力机制提高对负障碍边缘的特征提取和特征融合能力,从而提高对道路小尺度负障碍的检测精度;采用SIoU Loss作为模型边界框损失函数并使用K-means++方法优化Anchor以提高负障碍检测模型的收敛速度和边界框定位效果,并基于遗传算法优化超参数让模型更贴合矿区场景,最终实现对矿区道路负障碍的快速精准识别。实验表明该检测模型能快速准确识别复杂背景下露天矿区道路负障碍目标,对道路负障碍目标的检测精度、召回率、平均精确度均值分别达到了96.9%、89.9%、95.3%,且该模型大小仅有12.7 MB。对比其他主流检测网络,该网络模型更适合复杂环境下露天矿区非结构化道路行驶安全需求,且该检测模型的鲁棒性好,可适配于多种情况的露天矿区,为实际环境复杂多变的露天矿区非结构化道路负向障碍检测提供了可行的方法,为露天矿无人卡车安全生产运输提供安全预警。