Automated detection and classification of construction workers' loss of balance events using wearable insole pressure sensors

Fall on the same level is the leading cause of non-fatal injuries in construction workers; however, identifying loss of balance events associated with specific unsafe surface conditions in a timely manner remain challenging. The objective of the current study was to develop a novel method to detect and classify loss of balance events that could lead to falls on the same level by using foot plantar pressure distributions data captured from wearable insole pressure sensors. Ten healthy volunteers participated in experimental trials, simulating four major loss of balance events (e.g., slip, trip, unexpected step-down, and twisted ankle) to collect foot plantar pressure distributions data. Supervised machine learning algorithms were used to learn the unique foot plantar pressure patterns, and then to automatically detect loss of balance events. We compared classification performance by varying window sizes, feature groups and types of classifiers, and the best classification accuracy (97.1%) was achieved when using the Random Forest classifier with all feature groups and a window size of 0.32 s. This study is important to researchers and site managers because it uses foot plantar pressure distribution data to objectively distinguish various potential loss of balance events associated with specific unsafe surface conditions. The proposed approach can allow practitioners to proactively conduct automated fall risk monitoring to minimize the risk of falls on the same level on sites.     

基于TDC的施工人员非健康工作姿态评估研究

为预防施工人员因长期非健康工作姿态导致肌肉骨骼类疾病(WMSDs),利用3D人体姿态识别模型识别施工人员的非健康工作姿态,并提出施工人员非健康工作姿态评估机制.基于时间膨胀卷积网络(TDC)训练Human 3.6M数据集得到3D人体姿态识别模型;利用模型确定施工人员作业时躯干的倾斜角度α,根据《人机工程学-静态工作姿态...     

Classification of clustered microseismic events in a coal mine using machine learning

Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines. Although machine learning has been widely applied in seismic data processing, feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated. In this research, two groups of seismic events with a minimum local magnitude (M_L) of −3 were observed in an underground coal mine. They were respectively located around a dyke and the longwall face. Additionally, two types of undesired signals were also recorded. Four machine learning methods, i.e. random forest (RF), support vector machine (SVM), deep convolutional neural network (DCNN), and residual neural network (ResNN), were used for classifying these signals. The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy. The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy. As mining is a dynamic progress which could change the characteristics of seismic signals, the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining. A cascaded workflow consisting of database update, model training, signal prediction, and results review was established. By progressively calibrating the DCNN model, it achieved up to 99% prediction accuracy. The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.     

基于TSP203系统和GA-SVM的围岩超前分类预测

 为有效地进行隧道围岩类别超前分类,提出基于TSP203系统和遗传–支持向量机的围岩类别超前分类方法。以TSP203系统为基础,从探测结果中提取有用信息,建立围岩类别超前分类指标体系,并采用支持向量机进行围岩超前分类预测。建立围岩类别超前分类指标体系时,采用TSP203中可有效识别的围岩分类参数来实现：岩体完整性系数、泊松比、静态扬氏模量、主要结构面与洞轴线的夹角、不连续结构面状态和地下水发育情况。确定支持向量机参数时,采用遗传算法在解空间里进行全局搜索,以改善支持向量机在围岩分类中的识别精度。最后将该方法应用于实际工程,结果表明该方法实际可行,在围岩类别超前分类中具有较高的准确性,为围岩类别超前分类提供了一种新思路。     

Automated defect detection in sewer closed circuit television images using histograms of oriented gradients and support vector machine

Condition assessment of municipal sewer pipes using closed circuit television (CCTV) inspections is known to be time consuming, costly, and prone to errors primarily due to operator fatigue or novicity. Automated detection of defects can provide a valuable tool for ensuring the quality, accuracy, and consistency of condition data, while reducing the time and cost of the inspection process. This paper presents an efficient pattern recognition algorithm to support automated detection and classification of pipe defects in images obtained from conventional CCTV inspection videos. The algorithm employs the histograms of oriented gradients (HOG) and support vector machine (SVM) to identify pipe defects. The algorithm involves two main steps: (1) image segmentation to extract suspicious regions of interest (ROI) that represent candidate defect areas; and (2) classification of the ROI using SVM classifier that was trained using sets of HOG features extracted from positive and negative examples of the defect. Proposed algorithm is applied to the problem of detecting tree root intrusions. The performance of linear and radial basis function SVM classifiers evaluated. The algorithm was tested on a set of actual CCTV videos obtained from the cities of Regina and Calgary in Canada. Experimental results demonstrated the viability and robustness of the algorithm.     

Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning

Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are generated,reflecting the interaction between the TBM system and surrounding rock,and these data can be used to evaluate the rock mass quality.This study proposed a stacking ensemble classifier for the real-time prediction of the rock mass classification using TBM operation data.Based on the Songhua River water conveyance project,a total of 7538 TBM tunnelling cycles and the corresponding rock mass classes are obtained after data preprocessing.Then,through the tree-based feature selection method,10 key TBM operation parameters are selected,and the mean values of the 10 selected features in the stable phase after removing outliers are calculated as the inputs of classifiers.The preprocessed data are randomly divided into the training set(90%)and test set(10%)using simple random sampling.Besides stacking ensemble classifier,seven individual classifiers are established as the comparison.These classifiers include support vector machine(SVM),k-nearest neighbors(KNN),random forest(RF),gradient boosting decision tree(GBDT),decision tree(DT),logistic regression(LR)and multilayer perceptron(MLP),where the hyper-parameters of each classifier are optimised using the grid search method.The prediction results show that the stacking ensemble classifier has a better performance than individual classifiers,and it shows a more powerful learning and generalisation ability for small and imbalanced samples.Additionally,a relative balance training set is obtained by the synthetic minority oversampling technique(SMOTE),and the influence of sample imbalance on the prediction performance is discussed.     

一种冲击地压多参量前兆信息辨识模型及方法

 针对冲击地压预警困难这一难题,基于地音监测提出一种新的前兆信息辨识模型及方法。在固定大小的时间窗口内对地音监测信号进行时频域特征提取,得到11个表征冲击地压灾害前兆的多维特征向量,以实际地音监测数据为训练样本,基于SVM理论建立冲击地压多参量前兆信息辨识模型;提出一种新的SVM学习方法,用于解决工程实际应用中的大规模不平衡数据集训练问题,提高SVM分类准确率及速度。利用地音实测数据作为学习样本对支持向量机进行训练,建立相应的前兆辨识模型进行辨识,准确率达到93.87%。实验分析表明,这种方法有效可靠,样本辨识速度快,能够满足在线监测要求,具有工程应用前景。     

Ground-level ozone prediction by support vector machine approach with a cost-sensitive classification scheme

For ground-level ozone (O(3)) prediction, a predictive model, with reliable performance not only on non-polluted days but, more importantly, on polluted days, is favored by public authorities to issue alerts, so that concerned citizens and industrial organizations could take precautions to avoid exposure and reduce harmful emissions. However, the class imbalance problem, i.e., in some collected field data, number of O(3) polluted days are much smaller than that of non-polluted days, will deteriorate the model performance on minority class-O(3) polluted days. Despite support vector machine (SVM) obtaining promising results in air quality prediction, in this study, a cost-sensitive classification scheme is proposed for the standard support vector classification model (S-SVC) in order to investigate whether the class imbalance plagues S-SVC. The S-SVC with such scheme is named as CS-SVC. Experiments on imbalanced data sets collected from two air quality monitoring sites in Hong Kong show that 1) S-SVC is still sensitive to class imbalance problem; 2) compared with S-SVC, CS-SVC effectively avoids class imbalance problem with lower percentage of false negative on O(3) polluted days but with higher percentage of false positive on non-polluted days; 3) compared with both S-SVC and CS-SVC, support vector regression model (SVR), after converting its output to binary one, only has similar performance with S-SVC, which indicates class imbalance problem also impairs the regressor model. From point of protecting public health, CS-SVC, which less likely misses to forecast O(3) polluted days, is recommended here.     

Machine learning-based automatic control of tunneling posture of shield machine

For a tunnel driven by a shield machine, the posture of the driving machine is essential to the construction quality and environmental impact. However, the machine posture is controlled by the experienced driver of shield machine by setting hundreds of tunneling parameters empirically. Machine learning(ML) algorithm is an alternative method that can let the computer to learn from the driver’s operation and try to model the relationship between parameters automatically. Thus, in this paper, three...     

基于模糊数学的TBM施工岩体质量分级研究

 根据隧道掘进机(TBM)施工进度将围岩分为施工条件好、施工条件较好、施工条件较差和施工条件差4个等级。利用模糊数学方法,采用岩石单轴抗压强度UCS和岩体完整性指标KV,分别建立UCS和KV关于TBM施工岩体质量4级分级的隶属度函数。采用单极性S形函数,分别构建UCS和KV的权重函数。这样,基于模糊数学的最大隶属度准则,就可以对TBM施工的岩体质量进行分级。同时,给出3个施工实例,演算表明,预测的结果与TBM施工实际相吻合,表明该分级方法简单而实用,具有很好的应用前景。     

基于支持向量机的砂土液化预测模型

分析了砂土液化的主要影响因素,建立了砂土液化的支持向量机预测模型。该模型能通过有限经验数据的学习,建立砂土液化类型与其影响因素之间的非线性关系。运用所建立的模型对具体的砂土液化类型进行了评判,评判结果表明,基于线性核的支持向量机分类器不能有效地建立液化类型与影响因素之间的非线性映射,而基于多项式核及径向基核函数的分类器能正确判定砂土是否液化。     

膨胀土等级判别的遗传支持向量机多分类方法

针对支持向量机模型中的参数难以确定的状况,提出了遗传支持向量机方法,即利用遗传算法来搜索支持向量机与核函数的参数,避免了人为选择参数的盲目性,同时提高了支持向量机的推广预测能力,并将该方法应用于膨胀土胀缩等级的判别分类问题。考虑影响膨胀土判别的重要因素,选用液限、胀缩总率、塑性指数、天然含水量和自由膨胀率5个指标作为模型的判别因子,以4类膨胀土胀缩等级作为相应的输出,以膨胀土实测数据作为学习样本进行训练,建立相应分类函数对待判样本进行分类。研究结果表明：遗传支持向量机模型分类性能良好,预测精度高,是膨胀土     

Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit

Accidental falls (slips, trips, and falls from height) are the leading cause of occupational death and injury in construction. As a proactive accident prevention measure, near miss can provide valuable data about the causes of accidents, but collecting near-miss information is challenging because current data collection systems can largely be affected by retrospective and qualitative decisions of individual workers. In this context, this study aims to develop a method that can automatically detect and document near-miss falls based upon a worker's kinematic data captured from wearable inertial measurement units (WIMUs). A semi-supervised learning algorithm (i.e., one-class support vector machine) was implemented for detecting the near-miss falls in this study. Two experiments were conducted for collecting the near-miss falls of ironworkers, and these data were used to test developed near-miss fall detection approach. This WIMU-based approach will help identify ironworker near-miss falls without disrupting jobsite work and can help prevent fall accidents.     

基于图像识别技术的汽油、无水乙醇燃烧火焰识别研究

为了实现基于视频图像对火灾现场存在助燃剂的分类识别,对燃烧火焰的特征进行分析,根据汽油和无水乙醇引燃后各自特有的燃烧现象,结合火焰的视频图像识别算法实现对汽油和无水乙醇燃烧火焰的识别。首先,基于图像的灰度阈值得到其疑似火焰区域,再提取其H、S、I颜色分量和面积变化特征;并提取燃烧图像的小波高频能量特征和LBP直方图特征;最后将特征向量输入SVM分类器进行分类识别。试验表明,SVM对汽油和无水乙醇燃烧火焰的识别分类准确率可达98.5%,可较好地实现对汽油、无水乙醇燃烧火焰的区分。     

基于自注意力的隧道视频火灾识别技术研究

针对公路隧道火灾样本量少、深度学习效果不理想的问题，研究一种小样本学习技术，以提高对隧道火灾样本的利用率，并在此基础上利用成熟的机器学习方法，提出一种基于自注意力的隧道视频火灾识别技术。该技术采用自注意力机制结合SVM分类器搭建火焰识别模型，该模型针对各项特征对火焰识别的重要性分配不同的注意力权重，形成注意力矩阵，并将权重矩阵与特征向量的值相加权，通过SVM的Hinge Loss进行线性支持向量机分类，对公路隧道火灾进行识别和预警。在火灾识别训练过程中，通过对火焰疑似区域进行检测，并利用数据增强技术达到样本扩增的目的，随后采用多通道融合的特征提取方式构建特征向量，输入设计的自注意力火焰识别模型中，通过梯度下降优化器进行小批量模型训练，降低迭代次数，最终获得最优特征权重参数，得到最佳识别模型。试验结果表明，该方法在模型训练时收敛较快，在火焰识别时相比未使用小样本学习的传统SVM算法，准确率提高了5%，因此能在小样本环境下有效提高火灾识别的准确度。     

Mixed‐Integer Linear Programming on Work‐Rest Schedule Design for Construction Sites in Hot Weather

An appropriate design of work‐rest schedule is recognized as an efficient way in providing better ergonomic environment, improving labor productivity as well as safety. Construction workers usually undertake physically demanding tasks in an outdoor environment, with awkward postures and repetitive motions. This study proposes a mixed‐integer linear programming approach to optimize the work‐rest schedule for construction workers in hot weather for the objective of maximizing the total productive time. The model takes into consideration the physical and physiological conditions of the workers, the working environment, the nature of the jobs and the minimum rest duration of the government regulation. The results of numerical experiments show that the proposed model outperforms a default work‐rest schedule by up to 10% in terms of total productive time. This implies considerable cost savings for the construction industry.     

Metaheuristic optimization within machine learning-based classification system for early warnings related to geotechnical problems

This study proposes a novel classification system integrating swarm and metaheuristic intelligence, i.e., a smart firefly algorithm (SFA), with a least squares support vector machine (LSSVM). Benchmark functions were used to validate the optimization performance of the SFA. The experimental results showed that the SFA obtained 100% success rate in searching the optimum for most benchmark functions. The SFA was then integrated with the LSSVM to create a metaheuristic optimized classification model. A graphical user interface was developed for the proposed classification system to assist engineers and researchers in executing advanced machine learning tasks. The system was applied to several geotechnical engineering problems that involved measuring the groutability of sandy silt soil, monitoring seismic hazards in coal mines, predicting postearthquake soil liquefaction, and determining the propensity of slope collapse. The prediction problems in these studies were complex because they were dependent on various physical factors, and such factors exhibited highly nonlinear relations. The analytical results revealed that the metaheuristic optimization within machine learning-based classification system exhibited a groutability prediction accuracy of 95.42%, seismic prediction accuracy of 93.96%, soil liquefaction prediction accuracy of 95.18%, and soil collapse prediction accuracy of 95.45%. Hence, the proposed system is a promising tool to provide decision-makers with timely warnings of geotechnical hazards.     

基于支持向量机的边坡稳定性预测模型

根据影响边坡稳定性的主要因素,建立了边坡稳定性的支持向量机预测模型。该模型通过有限的经验数据的学习,建立了边坡稳定性与其影响因素之间的非线性关系。运用所建立的模型对具体的岩体边坡进行了判定,由结果知,基于线性核的支持向量机分类器不能有效地建立边坡稳定与影响因素之间的非线性映射,而基于神经网络核及径向基函数核的分类器能正确判定边坡的稳定性。     

A multiple kernel learning-based decision support model for contractor pre-qualification

Due to the complex nature of the contractor pre-qualification such as subjectivity, non-linearity and multi-criteria, advanced model should be required for achieving a high accuracy of this decision-making process. Previous studies have been conducted to build up quantitative decision models for contractor pre-qualification, among them artificial neural network (ANN) and support vector machine (SVM) have been proved to be desirable in solving the pre-qualification problem with regards to their higher accuracy and efficiency for solving the non-linear problem of classification. Based on the algorithm of SVM, multiple kernel learning (MKL) method was developed and it has been proved to perform better than SVM in other areas. Hence, MKL is proposed in this research, the capability of MKL was compared with SVM through a case study. From the result, it has been proved that both SVM and MKL perform well in classification, and MKL is more preferable than SVM, with a proper parameter setting. Therefore, MKL can enhance the decision making of contractor pre-qualification.