Pancreatic Cancer Data Classification with Quantum Machine Learning

Quantum computing is a promising new approach to tackle the complex real-world computational problems by harnessing the power of quantum mechanics principles.The inherent parallelism and exponential computational power of quantum systems hold the potential to outpace classical counterparts in solving complex optimization problems,which are pervasive in machine learning.Quantum Support Vector Machine(QSVM)is a quantum machine learning algorithm inspired by classical Support Vector Machine(SVM)that exploits quantum parallelism to efficiently classify data points in high-dimensional feature spaces.We provide a comprehensive overview of the underlying principles of QSVM,elucidating how different quantum feature maps and quantum kernels enable the manipulation of quantum states to perform classification tasks.Through a comparative analysis,we reveal the quantum advantage achieved by these algorithms in terms of speedup and solution quality.As a case study,we explored the potential of quantum paradigms in the context of a real-world problem:classifying pancreatic cancer biomarker data.The Support Vector Classifier(SVC)algorithm was employed for the classical approach while the QSVM algorithm was executed on a quantum simulator provided by the Qiskit quantum computing framework.The classical approach as well as the quantum-based techniques reported similar accuracy.This uniformity suggests that these methods effectively captured similar underlying patterns in the dataset.Remarkably,quantum implementations exhibited substantially reduced execution times demonstrating the potential of quantum approaches in enhancing classification efficiency.This affirms the growing significance of quantum computing as a transformative tool for augmenting machine learning paradigms and also underscores the potency of quantum execution for computational acceleration.

Comparative Study of Transfer Learning Models for Retinal Disease Diagnosis from Fundus Images

While the usage of digital ocular fundus image has been widespread in ophthalmology practice,the interpretation of the image has been still on the hands of the ophthalmologists which are quite costly.We explored a robust deep learning system that detects three major ocular diseases:diabetic retinopathy(DR),glaucoma(GLC),and age-related macular degeneration(AMD).The proposed method is composed of two steps.First,an initial quality evaluation in the classification system is proposed to filter out poorquality images to enhance its performance,a technique that has not been explored previously.Second,the transfer learning technique is used with various convolutional neural networks(CNN)models that automatically learn a thousand features in the digital retinal image,and are based on those features for diagnosing eye diseases.Comparison performance of many models is conducted to find the optimal model which fits with fundus classification.Among the different CNN models,DenseNet-201 outperforms others with an area under the receiver operating characteristic curve of 0.99.Furthermore,the corresponding specificities for healthy,DR,GLC,andAMDpatients are found to be 89.52%,96.69%,89.58%,and 100%,respectively.These results demonstrate that the proposed method can reduce the time-consumption by automatically diagnosing multiple eye diseases using computer-aided assistance tools.

基于解纠缠表示学习的人脸反欺骗算法

针对现有人脸反欺骗模型面对不同应用场景识别精度低、泛化性能不佳的问题,引入解纠缠表示学习,提出一种基于解纠缠表示学习的人脸反欺骗方法。该方法采用U-Net架构和ResNet-18作为编/解码器。首阶段训练中,通过输入真实样本使得编码器仅学习到真实样本相关信息。第二阶段,构建对抗性学习网络,输入不具标签的样本,将预训练的编码器输出和新编码器输出进行特征融合,由解码器重建图像,在鉴别器中与原始图像进行对抗训练,以实现特征的解耦。模型与一些经典人脸反欺骗方法相比,有着更好的检测性能,在OULU-NPU数据集的数个实验中,最低的检测错误率仅为0.8%,表现优于STDN等经典检测方法。该人脸反欺骗方法通过分阶段训练的方式,使得模型在对抗性训练中获得了相比端到端模型更具判别性的特征表示,在欺骗特征图输出阶段采用多分类策略,减小了不同的图像噪声对分类结果的影响,在公开数据集上的实验验证了算法的有效性。

Noisy speech emotion recognition using sample reconstruction and multiple-kernel learning

Speech emotion recognition （SER） in noisy environment is a vital issue in artificial intelligence （AI）. In this paper, the reconstruction of speech samples removes the added noise. Acoustic features extracted from the reconstructed samples are selected to build an optimal feature subset with better emotional recognizability. A multiple-kernel （MK） support vector machine （SVM） classifier solved by semi-definite programming （SDP） is adopted in SER procedure. The proposed method in this paper is demonstrated on Berlin Database of Emotional Speech. Recognition accuracies of the original, noisy, and reconstructed samples classified by both single-kernel （SK） and MK classifiers are compared and analyzed. The experimental results show that the proposed method is effective and robust when noise exists.

One-against-all-based Hellinger distance decision tree for multiclass imbalanced learning

Since traditional machine learning methods are sensitive to skewed distribution and do not consider the characteristics in multiclass imbalance problems,the skewed distribution of multiclass data poses a major challenge to machine learning algorithms.To tackle such issues,we propose a new splitting criterion of the decision tree based on the one-against-all-based Hellinger distance(OAHD).Two crucial elements are included in OAHD.First,the one-against-all scheme is integrated into the process of computing the Hellinger distance in OAHD,thereby extending the Hellinger distance decision tree to cope with the multiclass imbalance problem.Second,for the multiclass imbalance problem,the distribution and the number of distinct classes are taken into account,and a modified Gini index is designed.Moreover,we give theoretical proofs for the properties of OAHD,including skew insensitivity and the ability to seek a purer node in the decision tree.Finally,we collect 20 public real-world imbalanced data sets from the Knowledge Extraction based on Evolutionary Learning(KEEL)repository and the University of California,Irvine(UCI)repository.Experimental and statistical results show that OAHD significantly improves the performance compared with the five other well-known decision trees in terms of Precision,F-measure,and multiclass area under the receiver operating characteristic curve(MAUC).Moreover,through statistical analysis,the Friedman and Nemenyi tests are used to prove the advantage of OAHD over the five other decision trees.

AdaBoost算法研究进展与展望

AdaBoost是最优秀的Boosting算法之一,有着坚实的理论基础,在实践中得到了很好的推广和应用.算法能够将比随机猜测略好的弱分类器提升为分类精度高的强分类器,为学习算法的设计提供了新的思想和新的方法.本文首先介绍Boosting猜想提出以及被证实的过程,在此基础上,引出AdaBoost算法的起源与最初设计思想;接着,介绍AdaBoost算法训练误差与泛化误差分析方法,解释了算法能够提高学习精度的原因;然后,分析了AdaBoost算法的不同理论分析模型,以及从这些模型衍生出的变种算法;之后,介绍AdaBoost算法从二分类到多分类的推广.同时,介绍了AdaBoost及其变种算法在实际问题中的应用情况.本文围绕AdaBoost及其变种算法来介绍在集成学习中有着重要地位的Boosting理论,探讨Boosting理论研究的发展过程以及未来的研究方向,为相关研究人员提供一些有用的线索.最后,对今后研究进行了展望,对于推导更紧致的泛化误差界、多分类问题中的弱分类器条件、更适合多分类问题的损失函数、更精确的迭代停止条件、提高算法抗噪声能力以及从子分类器的多样性角度优化AdaBoost算法等问题值得进一步深入与完善.

应用多分类多核学习支持向量机的变压器故障诊断方法

提出一种基于多分类多核学习支持向量机的变压器故障诊断方法,相对于传统的2分类支持向量机,该方法有如下特点:算法针对单一的优化目标函数求解,只需设计1组参数,降低了支持向量机在解决多类问题中模型构造和参数选择的难度;核函数是多个基核函数的组合,提高了分类的精度;将模型分解为2个凸优问题进行求解,问题的复杂度低,求解速度快。诊断实例表明,该方法能保证较高的诊断准确率,具有较好的实用性和推广性。

一种面向人脸识别的加权代价敏感局部保持投影

传统的局部保持降维方法追求最低的识别错误率,即假设每一类的错分代价都是相同的.这个假设在真实的人脸识别应用中往往是不成立的.人脸识别是一个多类的代价敏感和类不平衡问题.例如,在人脸识别的门禁系统中,将入侵者错分成合法者的损失往往高于将合法者错分成入侵者的损失.因此,每一类的错分代价是不同的.另外,如果任一类合法者的样本数少于入侵者的样本数,该类合法者和入侵者就是类别不平衡的.为此,将错分代价融入到局部保持的降维模型中,提出了一种错分代价最小化的局部保持降维方法.同时,采用加权策略平衡了各类样本对投影方向的贡献.在人脸数据集AR,PIE,Extended Yale B上的实验结果表明了该算法的有效性.

基于核聚类方法的多层次支持向量机分类树

针对解决多类模式识别问题的SVM方法进行研究,在比较几种常用的多类SVM分类算法的基础上,提出一种基于核聚类方法的多层次SVM分类树,将核空间中的无监督学习方法和有监督学习方法结合起来,实现了一种结构更加简洁清晰、计算效率更高的多层SVM分类树算法,并在实验中取得了良好的结果.

基于核聚类方法的多层次支持向量机分类树

针对解决多类模式识别问题的SVM方法进行研究,在比较常用的几种多类SVM分类算法基础上,提出了一种基于核聚类方法的多层次SVM分类树,将核空间中的无监督学习方法和有监督学习方法结合起来,实现了一种结构更加简洁清晰、计算效率更高的多层SVM分类树算法,并在实验中取得了良好的结果。

基于Huffman树的多类SVM方法

提出了一种基于Huffman树的支持向量机多类分类方法。二叉树方法是一种常用的多类分类方法,它的关键问题在于如何构造合理的结构以获得较高的推广能力。为解决该问题,按照Huffman树的构造过程自下向上地构造二叉树,使易于分割的类处于上层结点。实验结果表明,该方法与One-vs-One和DAGSVM方法的分类效果相当。

核极化的多核LSSVM及其在分类中的应用

为了解决最小二乘支持向量机对于选择核函数盲目性的问题,将核度量标准核极化和多核学习引入最小二乘支持向量机中,提出了基于核极化的多核最小二乘支持向量机算法。算法首先利用核极化确定每个基本核函数的权系数,再根据多核学习原理组合多核函数,然后,建立多核最小二乘支持向量机模型,并进行模型的学习训练和预测。UCI数据上的试验结果表明,所提出的算法比SVM、最小二乘支持向量机和其他的多核学习方法具有更高的分类准确率。

基于教与学优化算法的基因表达谱选择性集成分类

针对基因表达谱的高维、小样本及高噪声等特点,提出一种选择性集成分类方法。首先,采样改进的分类信息指数法进行属性约简,剔除大量无效基因实现降维;然后,基于bootstrap技术的样本扰动和核模糊粗糙集的特征扰动构建多个样本子集,训练多个基分类器;最后,采用教与学优化算法构建选择性集成分类器。仿真实验结果表明,算法在分类精度、集成规模及稳定性等方面具有较强优势。

多分类转导支持向量机

为了完成分类学习,传统的支持向量机基于带标记信息的经验数据归纳出一个通用的决策函数。而转导支持向量机则不同,它考虑包含测试集在内的所有数据信息并致力于最小化测试样本的分类错误数。在已有的2类分类方法的基础上构造了直接求解多类分类问题的的转导支持向量机。

支撑向量机多类分类方法的研究

支撑向量机是一种基于统计学理论的新的学习算法,它采用了结构风险最小化原则,能有效地解决过学习问题,具有很强的泛化能力。传统支撑向量机针对两类分类问题,为了深入地分析实际应用中的大规模和多类别的问题,通过对一次性求解法、一对多、一对一、有向无环图方法的原理和实现方法进行分析,从速度和精度两方面对这些方法的优缺点进行了归纳和总结,并通过实验进行了验证和比较。实验结果表明,各种方法可以获得不同的分类器推广能力及训练速度和测试速度,也为今后如何更好地解决支撑向量机多类分类问题指明了方向。

Diagnosis of Various Skin Cancer Lesions Based on Fine-Tuned ResNet50 Deep Network

With the massive success of deep networks,there have been signi-cant efforts to analyze cancer diseases,especially skin cancer.For this purpose,this work investigates the capability of deep networks in diagnosing a variety of dermoscopic lesion images.This paper aims to develop and ne-tune a deep learning architecture to diagnose different skin cancer grades based on dermatoscopic images.Fine-tuning is a powerful method to obtain enhanced classication results by the customized pre-trained network.Regularization,batch normalization,and hyperparameter optimization are performed for ne-tuning the proposed deep network.The proposed ne-tuned ResNet50 model successfully classied 7-respective classes of dermoscopic lesions using the publicly available HAM10000 dataset.The developed deep model was compared against two powerful models,i.e.,InceptionV3 and VGG16,using the Dice similarity coefcient(DSC)and the area under the curve(AUC).The evaluation results show that the proposed model achieved higher results than some recent and robust models.

A multiple-kernel LSSVR method for separable nonlinear system identifcation

In some nonlinear dynamic systems, the state variables function usually can be separated from the control variables function, which brings much trouble to the identification of such systems. To well solve this problem, an improved least squares support vector regression （LSSVR） model with multiple-kernel is proposed and the model is applied to the nonlinear separable system identification. This method utilizes the excellent nonlinear mapping ability of Morlet wavelet kernel function and combines the state and control variables information into a kernel matrix. Using the composite wavelet kernel, the LSSVR includes two nonlinear functions, whose variables are the state variables and the control ones respectively, in this way, the regression function can gain better nonlinear mapping ability, and it can simulate almost any curve in quadratic continuous integral space. Then, they are used to identify the two functions in the separable nonlinear dynamic system. Simulation results show that the multiple-kernel LSSVR method can greatly improve the identification accuracy than the single kernel method, and the Morlet wavelet kernel is more efficient than the other kernels.

多核多类关联向量机的高分辨率影像目标检测

从高分辨率遥感图像数据中准确检测多类目标的任务对于检测速度和模型训练时间提出了较高的要求。文章提出了一种MKL_mRVM方法:该方法采用基于快速边缘似然最大算法直接计算mRVM分类器的决策函数,避免了传统RVM重复计算目标函数Hessian矩阵的过程,并且因为不需要构造一系列两类分类器,缩短了多类模型的训练时间;同时,将多个基础核引入多类模型,训练过程中采用交叉验证方法确定基础核权重,在随机分出的确认集上检验分类器的精度,选取使得分类模型精度最高的值作为权重的优化结果。实验结果表明,该方法能够在保持解的稀疏性的前提下,有效地缩短模型训练时间。

基于高维映射感知器网络的机器学习分类方法

利用Rosenblatt感知器网络的权值学习方法,提出一种解决线性不可分样本的多类分类方法.该方法不需要考虑使用何种核函数,将高维坐标值作为分类信息的函数,直接解决非线性多类分类问题.对双螺旋线数据分类应用的结果表明:基于高维映射感知器网络的多类分类机器学习方法可以有效解决非线性数据的分类问题,并能够提高分类效率和准确度.

基于模糊机会约束的超球支持向量机

针对不确定数据多分类问题,提出一种基于模糊机会约束的超球支持向量机(FCC-HSVM).在球结构支持向量机的基础上,引入模糊事件的可能性测度,得到模糊机会约束规划及其对偶规划.利用球结构的优点,每类样本只参与一个超球体的训练,直接求解多分类模型,提出FCC-HSVM的快速学习算法,显著缩短多分类情况下训练时间.数据试验表明:这种支持向量机分类精度较高,训练速度快,适合解决不确定数据多分类问题.