Machine Learning: An Overview

Machine learning is an Artificial Intelligence (or AI) application, an idea that came into being by giving machines access to data and letting them learn by themselves. AI has been making headlines, especially since ChatGPT was introduced. Malaysia has taken many significant steps to embrace and integrate the technology into various sectors. These include encouraging large companies to build AI infrastructure, creating AI training opportunities (for example, the local media reported Microsoft and Google plan to invest USD 2.2 billion and USD 2 billion, respectively, in the said activities), and, as part of AI Talent Roadmap 2024-2030, establishing AI faculty in one of its public universities (i.e., “Universiti Teknologi Malaysia”) leading the way in the integration and teaching of AI throughout the country. This article introduces several products developed by the author (for the energy and transportation industries) and recommends their improvement by incorporating Machine learning.

Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review

In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.

Theoretical Study on Non-transmission High Efficient Parallel Camber Grinding Machine

Be directed against the development trend of modern CNC grinding machine towards high precision and high efficiency, some general weaknesses of existing camber grinding machine are analyzed in detail. In order to develop new type CNC camber grinding machine that can grind complex die, and genuinely achieved accurate feed and high efficient grinding, a new type camber grinding machine is put forward, called non-transmission virtual-shaft CNC camber grinding machine. Its feed system is a parallel mechanism that is directly driven by linear step motor. Therefore, traditional transmission types, such as the ball lead-screw mechanisms, the gears, the hydraulic transmission system, etc. are cancelled, and the feed system of new type CNC camber grinding machine can truly possess non-creep, good accuracy retentiveness a wide range of feed-speed change, high kinematical accuracy and positioning precision, etc. In order to realize that the cutting motion is provided with high grinding speed, step-less speed variation, high rotational accuracy, good dynamic performance, and non-transmission, the driving technology of hollow rotor motor is applied to drive the spindle of new type grinding machine,thus leading to the elimination of the transmission parts of cutting motion. The principle structure model of new type camber grinding machine is advanced. The selection, control gist and driving circuit line of the linear step motor are expounded. The main technology characteristics and application advantages of non-transmission virtual-shaft CNC camber grinding machine are introduced.

Man-object, Interpersonal and Man-machine Relationships——An Ethical Perspective on Artificial Intelligence

Traditional social ethics has always been centered on human relationships. In recent years, modern ethics began to systematically reflect the relationships between humans and objects, and the future ethics will need to account for the relationships between humans and intelligent machines. This is mainly because humans may be overtaken by machines in intelligence through which humans gain dominance over all other natural objects. On the ethical thinking of the man-machine relationship, an idea is to be inclined to do subtraction rather than addition. Specifically, we should give priority to and focus on limiting the means and abilities of intelligent machines rather than how to cultivate and set the value judgments of their friendliness. In other words, we should concentrate on how to limit the development of intelligent machines to specialization and miniaturization, especially keeping them within the scope of non-violence.

Machine Learning Technology for Evaluation of Liver Fibrosis, Inflammation Activity and Steatosis (LIVERFASt^TM)

Using the latest available artificial intelligence (AI) technology, an advanced algorithm LIVERFAStTM has been used to evaluate the diagnostic accuracy of machine learning (ML) biomarker algorithms to assess liver damage. Prevalence of NAFLD (Nonalcoholic fatty liver disease) and resulting NASH (nonalcoholic steatohepatitis) are constantly increasing worldwide, creating challenges for screening as the diagnosis for NASH requires invasive liver biopsy. Key issues in NAFLD patients are the differentiation of NASH from simple steatosis and identification of advanced hepatic fibrosis. In this prospective study, the staging of three different lesions of the liver to diagnose fatty liver was analyzed using a proprietary ML algorithm LIVERFAStTM developed with a database of 2862 unique medical assessments of biomarkers, where 1027 assessments were used to train the algorithm and 1835 constituted the validation set. Data of 13,068 patients who underwent the LIVERFAStTM test for evaluation of fatty liver disease were analysed. Data evaluation revealed 11% of the patients exhibited significant fibrosis with fibrosis scores 0.6 - 1.00. Approximately 7% of the population had severe hepatic inflammation. Steatosis was observed in most patients, 63%, whereas severe steatosis S3 was observed in 20%. Using modified SAF (Steatosis, Activity and Fibrosis) scores obtained using the LIVERFAStTM algorithm, NAFLD was detected in 13.41% of the patients (Sx > 0, Ay 0). Approximately 1.91% (Sx > 0, Ay = 2, Fz > 0) of the patients showed NAFLD or NASH scorings while 1.08% had confirmed NASH (Sx > 0, Ay > 2, Fz = 1 - 2) and 1.49% had advanced NASH (Sx > 0, Ay > 2, Fz = 3 - 4). The modified SAF scoring system generated by LIVERFAStTM provides a simple and convenient evaluation of NAFLD and NASH in a cohort of Southeast Asians. This system may lead to the use of noninvasive liver tests in extended populations for more accurate diagnosis of liver pathology, prediction of clinical path of individuals at all stages of liver diseases, and provision of an efficient system for therapeutic interventions.

Accurate Measurement Method for Tube's Endpoints Based on Machine Vision

Tubes are used widely in aerospace vehicles, and their accurate assembly can directly affect the assembling reliability and the quality of products. It is important to measure the processed tube＇s endpoints and then fix any geometric errors correspondingly. However, the traditional tube inspection method is time-consuming and complex operations. Therefore, a new measurement method for a tube＇s endpoints based on machine vision is proposed. First, reflected light on tube＇s surface can be removed by using photometric linearization. Then, based on the optimization model for the tube＇s endpoint measurements and the principle of stereo matching, the global coordinates and the relative distance of the tube＇s endpoint are obtained. To confirm the feasibility, ll tubes are processed to remove the reflected light and then the endpoint＇s positions of tubes are measured. The experiment results show that the measurement repeatability accuracy is 0.167 mm, and the absolute accuracy is 0.328 ram. The measurement takes less than 1 min. The proposed method based on machine vision can measure the tube＇s endpoints without any surface treatment or any tools and can realize on line measurement.

Self-adaptive large neighborhood search algorithm for parallel machine scheduling problems

A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely not all jobs can be scheduled within specified scheduling horizons due to the limited machine capacity. The objective is thus to maximize the overall profits of processed jobs while respecting machine constraints. A first-in- first-out heuristic is applied to find an initial solution, and then a large neighborhood search procedure is employed to relax and re- optimize cumbersome solutions. A machine learning mechanism is also introduced to converge on the most efficient neighborhoods for the problem. Extensive computational results are presented based on data from an application involving the daily observation scheduling of a fleet of earth observing satellites. The method rapidly solves most problem instances to optimal or near optimal and shows a robust performance in sensitive analysis.

Identification of activity stop locations in GPS trajectories by density-based clustering method combined with support vector machines

The identification of activity locations in con- tinuous GPS trajectories is an essential preliminary step in obtaining person trip data and for activity-based trans- portation demand forecasting. In this research, a two-step methodology for identifying activity stop locations is pro- posed. In the first step, an improved density-based spatial clustering of applications with noise （DBSCAN） algorithm identifies stop points and moving points; then in the second step, the support vector machines （SVMs） method distin- guishes activity stops from non-activity stops among the identified stop points. A time sequence constraint and a direction change constraint are applied as improvements to DBSCAN （yielding an improved algorithm known as C-DBSCAN）. Then three major features are extracted for use in the SVMs method： stop duration, mean distance to the centroid of a cluster of points at a stop location, and the shorter of distances from current location to home and to the workplace. The proposed methodology was tested using GPS data collected from mobile phones in the Nagoya area of Japan. The C-DBSCAN algorithm achieves an accuracy of 90 % in identifying stop points in the first step, while the SVMs method is 96 % accurate in distin- guishing the locations of activity stops from non-activity stops in the second step. Compared to other variants of DBSCAN used to identify activity locations from GPS trajectories, this two-step method is generally superior.

Impact of machine perfusion of the liver on post-transplant biliary complications: A systematic review

AIM To review the clinical impact of machine perfusion(MP) of the liver on biliary complications post-transplantation, particularly ischaemic-type biliary lesions(ITBL). METHODS This systematic review was performed in accordance with the Preferred Reporting Systematic Reviews and MetaAnalysis(PRISMA) protocol. The following databases were searched: PubMed, MEDLINE and Scopus. The keyword "liver transplantation" was used in combination with the free term "machine perfusion". Clinical studies reporting results of transplantation of donor human livers following ex situ or in situ MP were analysed. Details relating to donor characteristics, recipients, technique of MP performed and post-operative biliary complications(ITBL, bile leak and anastomotic strictures) were critically analysed.RESULTS Fifteen articles were considered to fit the criteria for this review. Ex situ normothermic MP was used in 6 studies, ex situ hypothermic MP in 5 studies and the other 4 studies investigated in situ normothermic regional perfusion(NRP) and controlled oxygenated rewarming. MP techniques which have per se the potential to alleviate ischaemia-reperfusion injury: Such as hypothermic MP and NRP, have also reported lower rates of ITBL. Other biliary complications, such as biliary leak and anastomotic biliary strictures, are reported with similar incidences with all MP techniques. There is currently less clinical evidence available to support normothermic MP as a mitigator of biliary complications following liver transplantation. On the other hand, restoration of organ to full metabolism during normothermic MP allows assessment of hepatobiliary function before transplantation, although universally accepted criteria have yet to be validated.CONCLUSION MP of the liver has the potential to have a positive impact on post-transplant biliary complications, specifically ITBL, and expand extended criteria donor livers utilisation.

Adaptive support vector machine decision feedback equalizer

An adaptive support vector machine decision feedback equalizer（ASVM-DFE） based on the least square support vector machine（LS-SVM） is proposed,it solves linear system iteratively with less computational intensity.An adaptive non-singleton fuzzy support vector machine decision feedback equalizer（ANSFSVMDFE） is also presented,it adopts the non-singleton fuzzy Gaussian kernel function with similar characteristic of pre-filter and is modified with a space transformation based approach.Simulations under nonlinear time variant channels show that ASVM-DFE and ANSFSVM-DFE perform very well on nonlinear equalization and ANSFSVM-DFE acts especially well in resisting abrupt interference.

Modeling and Optimization of Electrical Discharge Machining of SiC Parameters, Using Neural Network and Non-Dominating Sorting Genetic Algorithm (NSGA II)

Silicon Carbide (SiC) machining by traditional methods with regards to its high hardness is not possible. Electro Discharge Machining, among non-traditional machining methods, is used for machining of SiC. The present work is aimed to optimize the surface roughness and material removal rate of electro discharge machining of SiC parameters simultaneously. As the output parameters are conflicting in nature, so there is no single combination of machining parameters, which provides the best machining performance. Artificial neural network (ANN) with back propagation algorithm is used to model the process. A multi-objective optimization method, non-dominating sorting genetic algorithm-II is used to optimize the process. Affects of three important input parameters of process viz., discharge current, pulse on time (Ton), pulse off time (Toff) on electric discharge machining of SiC are considered. Experiments have been conducted over a wide range of considered input parameters for training and verification of the model. Testing results demonstrate that the model is suitable for predicting the response parameters. A pareto-optimal set has been predicted in this work.

A Wavelet Spectrum Technique for Machinery Fault Diagnosis

Rotary machines are widely used in various applications. A reliable machinery fault detection technique is critically needed in industries to prevent the machinery system’s performance degradation, malfunction, or even catastrophic failures. The challenge for reliable fault diagnosis is related to the analysis of non-stationary features. In this paper, a wavelet spectrum (WS) technique is proposed to tackle the challenge of feature extraction from these non-stationary signatures;this work will focus on fault detection in rolling element bearings. The vibration signatures are first analyzed by a wavelet transform to demodulate representative features;the periodic features are then enhanced by cross-correlating the resulting wavelet coefficient functions over several contributive neighboring wavelet bands. The effectiveness of the proposed technique is examined by experimental tests corresponding to different bearing conditions. Test results show that the developed WS technique is an effective signal processing approach for non-stationary feature extraction and analysis, and it can be applied effectively for bearing fault detection.

基于机器视觉与光谱融合的柑橘品质无损检测分级系统设计与试验

针对柑橘果径、着色率和内部糖度3项关键品质指标,基于双锥滚子式果杯传输线设计了一套柑橘综合品质无损检测分级系统,该系统主要包括喂料部分、机器视觉检测模块、近红外光谱检测模块和分级执行部分.机器视觉检测模块采用单相机拍摄不断翻滚的柑橘视频来获取大量不同姿态的柑橘图像,并进行轮廓提取,以单个柑橘所有帧图像的最小外接圆直径的平均值计算果径,以每一帧图像得到的其二维黄色占比的平均值作为全表面着色率.在近红外光谱检测模块中设计了透射式光路,采集柑橘透射率光谱,并按在线检测时柑橘出现的两种高频姿态建立了混合姿态糖度检测模型,对比不同预处理方法下的建模结果,选取应用效果较优的多元散射校正(MSC)后建立的偏最小二乘法(PLS)模型.在线试验结果表明:果径检测的最大绝对误差为-1.42 mm,着色率检测的最大绝对误差为0.048,糖度检测结果的相关系数为0.817,均方根误差为0.658%.内外品质的联合检测分级按判别树决策方法确定了3种品质的联合分级方式,在分选速度为5个/s时,综合分级的平均准确率可达到91.16%,该检测分级系统整体结构简单,对于类球形水果具有较强的适用性,在产业化应用上有很大的潜力.

基于机器学习构建肺腺癌骨转移自动化模型

目的采用机器学习算法对关键变量进行识别,并对肺腺癌(LUAD)患者骨转移风险进行预测。方法回顾性分析2019年1月至2022年6月淮南东方医院集团附属肿瘤医院收治的132例确诊非小细胞肺癌(NSCLC)患者的临床资料,包括是否发生骨转移、年龄、性别、病理类型、吸烟状况、T分期、N分期、骨转移前是否有其他部位的转移,以及癌胚抗原(CEA)、碱性磷酸酶(ALP)、鳞状细胞癌抗原(SCCA)、糖类抗原125(CA125)、细胞角蛋白19片段抗原21-1(CYFRA21-1)、神经元特异性烯醇化酶(NSE)、钙(CA)水平。采用LASSO回归分析方法来筛选与骨转移相关的关键特征,并将其用于构建6种机器学习模型,另收集63例NSCLC患者的临床数据用于模型的外部验证。不同模型的预测性能通过受试者工作特征曲线(ROC曲线)来评估。校准曲线和DCA曲线用于验证所建模型的准确性和获益能力。使用SHAP包对logistic模型进行解释。结果LASSO回归分析最终筛选了4个重要变量,包括性别、N分期、CEA水平和糖类抗原CA125水平。在6种机器学习模型中,logistic模型在训练集(AUC=0.710)、测试集(AUC=0.705)和外部验证集(AUC=0.655)均具有最佳的预测效能和稳定性。SHAP图显示在logistic模型中4个变量的权重从高到低依次为CEA、性别、T分期和CA125。成功构建了LUAD骨转移的机器学习模型和网页计算器。结论logistic预测模型可以识别LUAD骨转移高风险患者,这有助于临床医生指导高危患者做出适当预防措施。

基于时频域综合分析的无创血糖检测技术研究

无创血糖检测技术是一种间接测量血液中葡萄糖含量的方法,其不损伤人体组织具有安全、快捷、无创的特点,打破了传统血糖检测的局限性,具有重要的研究价值。光电容积脉搏波信号因携带多种生理病理信息,被广泛应用于各种临床研究,也是目前实现无创血糖检测技术的重点关注对象。目前基于光电容积脉搏波信号的无创血糖检测研究,仅考虑了时间域或频率域单独作用时对系统建模的贡献。信号的时域分析虽能描述PPG信号幅值随时间的变化,却无法直观反映PPG信号频率的能量分布,因此单一域的信号分析不能全面表达PPG信号,从而导致信息丢失。采用频域分析方法提取信号频谱时,需要利用信号的全部时域信息,是一种全局的变换,可能会造成特定时间或特定频率段内的信号特性丢失。提出了一种基于光电容积脉搏波(PPG)时频域综合分析的无创血糖检测新方法,采用时域-频域并行法综合考量光电容积脉搏波信号与血糖间的联系。以时域分析为基准,利用聚类分析法在PPG信号时域中提取代表波形,分析波形特征点与血糖相关性,确定波形时域特征参数。在此基础上,利用快速傅里叶变换将脉搏波时域信号转换至频率域,采取主成分分析手段研究频谱信息,确立频域特征量。通过口服葡萄糖耐糖实验(OGTT)对获取的波形信号提取时频域特征参数,以实时检测的有创血糖浓度值作为参考,构建基于BP神经网络的无创血糖检测模型,同时为提升模型精度实现模型最优化,应用遗传算法对模型进行二次修正,最终实现模型测试集平均绝对误差(MAE)为1.13 mmol·L^(-1),均方根误差(RMSE)为1.42 mmol·L^(-1)。Parkers共识网络栅格(Parkers CEG)评估结果显示:在A区与B区的预测结果分别占80.3%、19.7%,实验结果表明该方法具有良好的预测精度,为实现日常血糖无创监测可行性提供了理论基础及可靠性依据。有助于完善糖尿病的检测与监测体系,更好地全面判断病情,及时预防、指导、治疗糖尿病。

基于改进ELM和计算机视觉的核桃缺陷检测

目的:解决现有食品生产企业在核桃缺陷检测中存在的准确性低和效率差等问题。方法:提出一种结合改进极限学习机和计算机视觉的核桃缺陷快速无损检测方法。通过计算机视觉采集核桃大部分表面图像信息,通过高斯滤波对图像进行预处理,通过迭代和保留信息变量法对颜色和纹理特征进行优化,最后,通过改进蝴蝶算法对极限学习机参数(随机权重和偏差)进行优化,实现核桃缺陷快速无损检测,并对所提缺陷检测方法的性能进行验证。结果:试验方法可以实现核桃多种缺陷的有效判别。与常规方法相比,试验方法在核桃缺陷检测中具有更优的检测准确率和效率,检测准确率>98.00%,平均检测时间<9.00 ms。结论:将智能算法和机器视觉技术相结合可以实现核桃缺陷的快速无损检测。

数据驱动模式下基于非平行超平面SVM算法的贸易经济预测

数据驱动的多元化发展导致数据异构性增强、维度提升和特征量规模扩大,给贸易经济分析带来更大挑战。为了提高贸易经济分析的科学性,采用非平行超平面支持向量机算法(support vector machine,SVM)对贸易经济进行预测分析。首先,根据贸易经济影响因素进行主成分分析,获取影响贸易经济的关键特征,并对特征进行量化和去噪处理。然后,采用广义特征值最接近支持向量机(proximal support vector machine via generalized eigenvalues,GEPSVM)进行贸易经济预测分类。根据预测指标要求,选择核函数GEPSVM算法(KGEPSVM算法)对分类的非平行超平面求解,通过类别划分函数获得经济预测结果。实证分析表明,对比常用的非平行超平面支持向量机算法,所提算法的贸易经济预测性能更优,而且在常用贸易经济指标的预测中,表现出较高预测精度和稳定性。

基于机器学习的水泥基灌浆料强度预测方法

针对采用小直径芯样法准确预测水泥基灌浆料抗压强度的问题,使用压力试验机分别对水泥基灌浆料标准尺寸试块和小直径芯样进行抗压强度试验,并基于试验数据,采用支持向量机回归(SVR)和随机森林回归(RFR)对水泥基灌浆料抗压强度进行回归预测。结果表明:标准尺寸试块均呈正反相接的四角锥体破坏形态,而高径比为0.7和1.0的小直径芯样呈正反相接的圆锥体破坏形态,高径比为1.2的小直径芯样呈斜裂缝剪切破坏形态;标准尺寸试块和小直径芯样的抗压强度值均服从正态分布,且无离群值;随着龄期的增长,标准尺寸试块和小直径芯样的抗压强度提高,且具有早期强度较高的特性;直径46 mm芯样的抗压强度较小,且更易受加工精度的影响;在给定的龄期和直径下,高径比为0.7的芯样抗压强度值最大,抗压强度离散程度最小;RFR预测模型对水泥基灌浆料抗压强度的预测效果更优。所提方法可较准确预测水泥基灌浆料抗压强度,为水泥基灌浆料抗压强度的预测研究提供了参考。

基于NMF-KELM的资源环境承载力评价与预测

资源环境承载力评价与预测对区域可持续发展有重要的指导意义。本文提出了基于非负矩阵分解(NMF)和核极限学习机(KELM)的资源环境承载力评价与预测方法,在构建江西省资源环境承载力指标体系的基础上,引入NMF对2005—2020年该地区资源环境承载力状况进行量化测度和系统分析,利用加权灰关联法和全排列多边形图示法对承载力结果验证分析,建立了基于NMF-KELM的承载力预测模型并对承载力的演变趋势进行预测。研究结果表明:①2005—2020年,江西省资源环境承载力指数由0.0963提高至0.7975,整体呈波动上升趋势,高速发展的社会经济是承载力的最直接驱动力。②NMF、加权灰关联法和全排列多边形图示法三者反映的趋势和结论是一致的,NMF评价结果更客观。③环境系统成为制约江西省资源环境承载力提高的主要因素,其中万元GDP工业废气排放量是最重要的影响因素。④与BP神经网络和灰色模型相比,基于NMF-KELM的承载力预测模型拟合精度高,能够更好地预测江西省资源环境承载力的演变趋势。

基于Fabric的海量交易数据上链预处理机制

Hyperledger Fabric是一种国内外广泛使用的联盟链框架,在基于Fabric技术的一些业务中具有协同组织众多、交易操作频繁、事务冲突增加等特点。Fabric采用的多版本并发控制技术能够在一定程度上解决部分交易冲突,提升系统并发性,但其机制不完善,会出现部分交易数据无法正常上链存储的问题。为了实现海量交易数据完整、高效、可信的上链存储,提出一种基于Fabric预言机的数据上链预处理机制。设计海量数据冲突预处理(MCPP)方法,通过检测、监听、延时提交、事务加锁、重排序缓存等方式实现主键冲突交易数据的完整上链。引入数据传输保障措施,在传输过程中利用非对称加密技术防止恶意节点伪造认证信息,确保交易数据链外处理前后的一致性。通过理论分析和实验结果表明,该机制可有效解决联盟链平台中海量交易数据上链时的并发冲突问题,当交易数据规模达到1 000和10 000时,MCPP的时效性比LMLS提高了38%和21.4%,且成功率接近100%,具有高效性和安全性,同时在无并发冲突情况下不影响Fabric系统性能。