Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine

Satellite image classification is crucial in various applications such as urban planning,environmental monitoring,and land use analysis.In this study,the authors present a comparative analysis of different supervised and unsupervised learning methods for satellite image classification,focusing on a case study in Casablanca using Landsat 8 imagery.This research aims to identify the most effective machine-learning approach for accurately classifying land cover in an urban environment.The methodology used consists of the pre-processing of Landsat imagery data from Casablanca city,the authors extract relevant features and partition them into training and test sets,and then use random forest(RF),SVM(support vector machine),classification,and regression tree(CART),gradient tree boost(GTB),decision tree(DT),and minimum distance(MD)algorithms.Through a series of experiments,the authors evaluate the performance of each machine learning method in terms of accuracy,and Kappa coefficient.This work shows that random forest is the best-performing algorithm,with an accuracy of 95.42%and 0.94 Kappa coefficient.The authors discuss the factors of their performance,including data characteristics,accurate selection,and model influencing.

A Synthesizing Land-cover Classification Method Based on Google Earth Engine: A Case Study in Nzhelele and Levhuvu Catchments, South Africa

This study designed an approach to derive land-cover in the South Africa with insufficient ground samples, and made a case demonstration in Nzhelele and Levhuvu catchments, South Africa. The method was developed based on an integration of Landsat 8, Sentinel-1, and Shuttle Radar Topography Mission(SRTM) Digital Elevation Model(DEM), and the Google Earth Engine(GEE) platform. Random forest classifier with 300 trees is employed as land-cover classification model. In order to overcome the defect of insufficient ground data, the stratified sampling method was used to generate the training and validation samples from the existing land-cover product. Likewise, in order to recognize different land-cover categories, the percentile and monthly median composites were employed to expand input metrics of random forest classifier. Results showed that the overall accuracy of the land-cover of Nzhelele and Levhuvu catchments, South Africa in 2017–2018 reached to 76.43%. Three important results can be drawn from our research. 1) The participation of Sentinel-1 data can slightly improve overall accuracy of land-cover while its contribution on land-cover classification varied with land types. 2) Under-fitting problem was observed in the training of non-dominant land-cover categories using the random sampling, the stratified sampling method is recommended to make sure the classification accuracy of non-dominant classes. 3) When related reflectance bands participated in the training process, individual Normalized Difference Vegetation index(NDVI), Enhanced Vegetation Index(EVI), Soil Adjusted Vegetation Index(SAVI), Normalized Difference Built-up Index(NDBI) have little effect on final land-cover classification result.

Engineering geological classification of the structural planes for hydroelectric projects in Emeishan Basalts

The scale and characteristics of rock mass are important indexes of the rock mass structural plane classification. This paper firstly analyzes the spatial distribution characteristics, the structural plane types （original structural plane, tectonic structural plane and hypergenic structural plane） and the associated features of the Emeishan basalts and then studies the classification schemes of the built hydropower structure planes of different rock areas （the east district, the central district and the west district） in the Emeishan basalt distribution area, Southwest China. Based on the analysis and comparison of the scale and the engineering geological characteristics of the typical structure planes in the basalt hydroelectric Stations, the types of structural planes are used in the first order classification. The secondary order classification is made by considering the impact factors of rock mass quality, e.g., the state of the structural planes, infilling, joint opening, extending length, the grade of weathering and strength. The engineering geological classification for Emeishan basalt is proposed. Because there are no evidences of a large structure presenting in study area, the first-order （Ⅰ） controlling structural planes do not appear in the classification, there only appear Ⅱ, Ⅲ, Ⅳ and Ⅴ grade structural planes influencing the rock-mass quality. According to the different rock-block types in bedding fault zone, the second-grade （Ⅱ） structural planes consisted of bedding fault zone is further classified into Ⅱ1, Ⅱ2 and Ⅱ3. The third-grade （Ⅲ） structural planes constructed by intraformational faulted zones are not subdivided. According to the different characteristics of intrusion, alteration and weathering unloading structural planes, the Ⅳ grade structure plane is divided into Ⅳ1, Ⅳ2 and Ⅳ3. According to the development characteristics of joints and fractures, the V grade structure plane is divided into fracture Ⅴ1 and columnar joint Ⅴ2. In all, the structural planes are classified into four groups with nine subsets. The research proposes the engineering geological classification of the structural plane for the hydropower project in the Emishan basalts, and the result of the study has a potential application in similar regions.

Automated Artificial Intelligence Empowered White Blood Cells Classification Model

White blood cells (WBC) or leukocytes are a vital component ofthe blood which forms the immune system, which is accountable to fightforeign elements. The WBC images can be exposed to different data analysisapproaches which categorize different kinds of WBC. Conventionally, laboratorytests are carried out to determine the kind of WBC which is erroneousand time consuming. Recently, deep learning (DL) models can be employedfor automated investigation of WBC images in short duration. Therefore,this paper introduces an Aquila Optimizer with Transfer Learning basedAutomated White Blood Cells Classification (AOTL-WBCC) technique. Thepresented AOTL-WBCC model executes data normalization and data augmentationprocess (rotation and zooming) at the initial stage. In addition,the residual network (ResNet) approach was used for feature extraction inwhich the initial hyperparameter values of the ResNet model are tuned by theuse of AO algorithm. Finally, Bayesian neural network (BNN) classificationtechnique has been implied for the identification of WBC images into distinctclasses. The experimental validation of the AOTL-WBCC methodology isperformed with the help of Kaggle dataset. The experimental results foundthat the AOTL-WBCC model has outperformed other techniques which arebased on image processing and manual feature engineering approaches underdifferent dimensions.

Applying rock mass classifications to carbonate rocks for engineering purposes with a new approach using the rock engineering system

Classical rock mass classification systems are not applicable to carbonate rocks,especially when these are affected by karst processes.Their applications to such settings could therefore result in outcomes not representative of the real stress-strain behavior.In this study,we propose a new classification of carbonate rock masses for engineering purposes,by adapting the rock engineering system(RES) method by Hudson for fractured and karstified rock masses,in order to highlight the problems of implementation of geomechanical models to carbonate rocks.This new approach allows a less rigid classification for carbonate rock masses,taking into account the local properties of the outcrops,the site conditions and the type of engineering work as well.

基于Google Earth Engine的前郭县春季农田覆膜提取

本文基于Google Earth Engine(GEE)云平台,综合考虑光学影像的波段反射率、光谱指数特征和雷达影像的极化、纹理特征,分别构建仅使用光学特征、仅使用雷达特征以及光学和雷达特征组合3种特征输入组合;根据精度确定最佳输入特征后,分别结合机器学习中的分类与回归树、支持向量机、最小距离分类法、梯度提升树和随机森林5种方法建立覆膜提取模型,依据结果精度评估不同方法的性能,并基于最优化模型提取出最终的覆膜农田面积。结果表明:①最佳输入特征为波段反射率特征+光谱指数特征+极化特征+纹理特征;②采用随机森林方法建立的模型精度最高,研究区I的总体精度达到了95.84%,Kappa系数为0.95,地物错分率为1.2%,明显优于其他4种方法(地物错分率较分类与回归树、支持向量机、最小距离和梯度提升树法降低0.8%、7.3%、38.0%和0.3%),研究区II的验证精度达到了87.84%,证明该模型在覆膜提取中可以取得更加准确的结果;③使用本文方法得到2022年研究区I覆膜农田面积为1302.48 km2,估算地膜使用量约为7585.62 t。本文综合考虑光学和雷达影像在地物识别中的特点建立模型,可以准确、高效的识别农田地膜,掌握地膜面积,对环境治理与防治具有重要意义。

The Study on the personnel training mode based on the occupation ability development and excellence engineer training

As the application undergraduate course colleges and universities, a distinctive talent training system must be formed to achieve the target of practical and innovative talents training, which needs to constantly explore and innovate teaching mode. In the paper, talent training model based on the occupation ability development and Excellence Engineer training has carried on the deep discussion and research, thorough study and research.

Comparative analysis on soil engineering classifications of China and America

Based on China National Standard of Soil Engineering Classification (GB/T 50145-2007) and the Unified Soil Classification System of American Society for Testing Materials (ASTM D-2478), two kinds of soil laboratory engineering classification methods were discussed and analyzed from the aspects of the definition in particle fraction, classification of soil type and evaluation standard for soil gradation. There is a same limit of fine grains fraction in the two standards, and there are three main types of soil in GB/T 50145-2007 and two in ASTM D-2487. Different evaluation standards of gradation are put forward for gravels and sands in ASTM D-2487. Same criteria of A line, B line and controlling value of plastic index are in the plasticity chart of both standards.

Document classification approach by rough-set-based corner classification neural network

A rough set based corner classification neural network, the Rough-CC4, is presented to solve document classification problems such as document representation of different document sizes, document feature selection and document feature encoding. In the Rough-CC4, the documents are described by the equivalent classes of the approximate words. By this method, the dimensions representing the documents can be reduced, which can solve the precision problems caused by the different document sizes and also blur the differences caused by the approximate words. In the Rough-CC4, a binary encoding method is introduced, through which the importance of documents relative to each equivalent class is encoded. By this encoding method, the precision of the Rough-CC4 is improved greatly and the space complexity of the Rough-CC4 is reduced. The Rough-CC4 can be used in automatic classification of documents.

Classification Method fo Urban Solid Waste Disposal Sites

One of the environmental liabilities left by abandoned urban waste disposal sites, closed without the correct procedures, is the risk of exposure to their effluents, whose emissions may occur for many years. The purpose of the proposed methodology, referred to as SISTAVAFE, an assessment system of a closed landfill, is to contribute in the risk assess- ment of exposure to leachate as well as to suggest procedures for site monitoring, according to different levels of care and urgency. The method is based on four matrices that help make an initial evaluation of the risk source, potential target and the surface and underground environmental paths. This paper only addresses the contamination caused by liquid effluents.

Diversity-accuracy assessment of multiple classifier systems for the land cover classification of the Khumbu region in the Himalayas

Land cover classification of mountainous environments continues to be a challenging remote sensing problem,owing to landscape complexities exhibited by the region.This study explored a multiple classifier system(MCS)approach to the classification of mountain land cover for the Khumbu region in the Himalayas using Sentinel-2 images and a cloud-based model framework.The relationship between classification accuracy and MCS diversity was investigated,and the effects of different diversification and combination methods on MCS classification performance were comparatively assessed for this environment.We present ten MCS models that implement a homogeneous ensemble approach,using the high performing Random Forest(RF)algorithm as the selected classifier.The base classifiers of each MCS model were developed using different combinations of three diversity techniques:(1)distinct training sets,(2)Mean Decrease Accuracy feature selection,and(3)‘One-vs-All’problem reduction.The base classifier predictions of each RFMCS model were combined using:(1)majority vote,(2)weighted argmax,and(3)a meta RF classifier.All MCS models reported higher classification accuracies than the benchmark classifier(overall accuracy with 95% confidence interval:87.33%±0.97%),with the highest performing model reporting an overall accuracy(±95% confidence interval)of 90.95%±0.84%.Our key findings include:(1)MCS is effective in mountainous environments prone to noise from landscape complexities,(2)problem reduction is indicated as a stronger method over feature selection in improving the diversity of the MCS,(3)although the MCS diversity and accuracy have a positive correlation,our results suggest this is a weak relationship for mountainous classifications,and(4)the selected diversity methods improve the discriminability of MCS against vegetation and forest classes in mountainous land cover classifications and exhibit a cumulative effect on MCS diversity for this context.

Kinematic Analysis and Rock Mass Classifications for Rock Slope Failure at USAID Highways

Rock slope kinematic analysis and rock mass classifications has been conducted at the 17^(th) km to 26^(th) km of USAID(United States Agency for International Development)highway in Indonesia.This research aimed to examine the type of rock slope failures and the quality of rock mass as well.The scan-line method was performed in six slopes by using a geological compass to determine rock mass structure on the rock slope,and the condition of joints such as persistence,aperture,roughness,infilling material,weathering and groundwater conditions.Slope kinematic analysis was performed employing a stereographic projection.The rock slope quality and stability were investigated based on RMR(rock mass rating)and SMR(slope mass rating)parameters.The rock slope kinematic analysis revealed that planar failure was likely to occur in Slope 1,3,and 4,the wedge failure in Slope 1 and 6,and toppling failure in Slope 2,5,and 6.The RMR rating is ranging from 57 to 64 and can be categorized as Fair to Good rock.The SMR rating revealed that the failure probability of Slope 3 was 90%,while it was from 40%to 60%for others.Despite the uniform RMR for all slopes,the SMR was significantly different.The detailed quantitative consideration of orientation of joint sets and geometry of the slope contributed to such differences in outcomes.

Epilepsy Radiology Reports Classification Using Deep Learning Networks

The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are unstructured,the manual information extraction is time-consuming and requires specific expertise.In this paper,a comprehensive method is proposed to classify epilepsy and non-epilepsy real brain MRI radiology text reports automatically.This method combines the Natural Language Processing technique and statisticalMachine Learning methods.122 realMRI radiology text reports(97 epilepsy,25 non-epilepsy)are studied by our proposed method which consists of the following steps:(i)for a given text report our systems first cleans HTML/XML tags,tokenize,erase punctuation,normalize text,(ii)then it converts into MRI text reports numeric sequences by using indexbased word encoding,(iii)then we applied the deep learning models that are uni-directional long short-term memory(LSTM)network,bidirectional long short-term memory(BiLSTM)network and convolutional neural network(CNN)for the classifying comparison of the data,(iv)finally,we used 70%of used for training,15%for validation,and 15%for test observations.Unlike previous methods,this study encompasses the following objectives:(a)to extract significant text features from radiologic reports of epilepsy disease;(b)to ensure successful classifying accuracy performance to enhance epilepsy data attributes.Therefore,our study is a comprehensive comparative study with the epilepsy dataset obtained from numeric sequences by using index-based word encoding method applied for the deep learning models.The traditionalmethod is numeric sequences by using index-based word encoding which has been made for the first time in the literature,is successful feature descriptor in the epilepsy data set.The BiLSTM network has shown a promising performance regarding the accuracy rates.We show that the larger sizedmedical text reports can be analyzed by our proposed method.

生物质碳材料的孔道分析

生物质碳材料的孔道类型和孔径大小制约着材料有效的活性位点数量,影响材料的性能。孔道分类又是孔径分析的前提条件,因此,建立孔道分类的方法非常有意义。随着生物质碳材料的深入研究,研究者对其孔道分析的要求逐渐提高。由于实际的吸脱附等温线具有不规则性,难以匹配IUPAC规范中的吸脱附等温线,所以,用实际的吸脱附等温线与IUPAC规范中的吸脱附等温线进行匹配对生物质碳材料的孔道进行分类准确度不能得到保证。使用自制生物质碳材料,运用物理吸附仪对其进行表征,采用BET方程(Brunauer-Emmett-Teller)、T-plot方法(Thickness-plot)、DFT方法(Non-local Density Functional Theory)、BJH(Barrett Joyner And Halenda)方法对其孔道进行分析。研究表明,采用孔隙率和比表面积占有率对其进行孔道分类,可以准确地定义出微孔生物质碳材料、介孔生物质碳材料和微介孔生物质碳材料,从而建立了孔隙率和比表面积占有率的孔道分类新方法。用标准样品对孔隙率和比表面积占有率的孔道分类新方法进行论证,结果一致。方法准确可靠、实用性高。

基于PIE-Engine融合改进特征的农作物分类研究

准确、及时地了解作物种植结构和信息在粮食安全、经济到政治等人类活动的许多方面都发挥着至关重要的作用。基于结合面向对象随机森林算法(Random forest,RF)和一站式地球科学大数据实时计算平台(Pixel Information Expert-Engine),探讨了结合面向对象随机森林算法与时间序列哨兵1号合成孔径雷达(SAR)数据后向散射系数对大规模作物分类的影响,并结合哨兵1号和哨兵2号主被动遥感数据,探讨植被指数特征和纹理特征的不同组合对后向散射系数、光谱特征和作物分类精度的提高。结果表明,结合面向对象随机森林算法,可明显削弱分类的椒盐效果,且基于融合时间序列的多特征SAR和光学数据的分类精度最高,SAR数据的分类精度最低。本研究采用的方法和平台能够准确、高效地进行土地利用分类工作,具有很好的推广价值。

专业技术类职业与技能类职业的差异、划分与职业标准建设

专业技术人员与技能人员是职业分类的两个相关类别,但在分类过程中,一些“跨界”职业究竟应如何归类尚存争议,且此科分类事关后续职业标准开发、人才队伍建设、技能等级评价(或专业技术等级考核)等,亟需深入研究。基于对职业分类的功能作用、职业分类大典的修订背景的梳理,通过回溯《中华人民共和国职业分类大典(2022年版)》修订过程,凝练出科学划分专业技术类职业和技能类职业的依据,尝试建立判定两类职业表述和专业技术或技能等级描述的标准话语体系,为两类人员职业生涯的贯通、接续发展提供依据,旨在为完善我国现代职业分类、职业标准体系提供理论基础。

ILO国际尘肺影像分类法与我国尘肺诊断标准要点的比较

文章对国际劳工组织的国际尘肺影像分类法(ILO 2022)和我国尘肺病诊断标准(GBZ 70—2015)从胸片质量,肺区、小阴影、密集度和大阴影的定义和分级,胸膜病变,附加符号,诊断和分期,标准片,使用条件7个方面进行比较。虽然GBZ 70—2015在描述肺实质改变参数的定义,如肺区、小阴影、密集度、大阴影,与ILO 2022基本一致,但两者并不完全一样,我国的诊断标准为职业病诊断服务,在诊断分级上有自己的特点。我国将尘肺病分为三期,在分期时同时考虑了小阴影密集度和影响肺区。GBZ 70—2015未纳入医用显示屏读片,且仍使用以高千伏胸片为主的胶片为标准片,落后于ILO 2022。文章为GBZ 70-2015的修订提供了参考。

考虑占用率的大型停车库泊位动态分配模型

为提高驾驶员泊车效率,本文考虑不同停车库占用率下的停车库运营者及驾驶员泊位分配需求,构建大型停车库泊位分配模型。本文引入停车库占用率将停车库空满等级划分为空闲泊位充裕时段、空闲泊位适中时段、空闲泊位紧缺时段,综合考虑停车库运营者运营管理需求与驾驶员快速寻泊需求,以寻位行驶时间、离开停车库行驶时间为参数构建运营管理时间效用函数,以寻位行驶时间、停车入位耗时、步行时间为参数构建驾驶员泊车耗时效用函数;将运营管理时间效用与驾驶员泊车耗时效用加权统一为总时间效用,以总时间效用最大化为目标,建立兼顾停车库运营者及驾驶员泊位分配需求的泊位分配模型;引入泊位利用率、停车总耗时量化模型性能。以西安市某大型商业停车库为例,选取9:00、11:30、13:00表征空闲泊位充裕、空闲泊位适中、空闲泊位紧缺时段进行泊位分配。不同停车库空满等级下,停车库内空闲泊位的总时间效用与停车总耗时均呈负显著相关,其中,空闲泊位充裕时段,停车库内空闲泊位的总时间效用与停车总耗时的相关性最弱,相关系数为-0.461;空闲泊位紧缺时段,停车库内空闲泊位的总时间效用与泊位利用率呈正显著相关,相关系数为0.710。研究表明本模型可在优选停车总耗时较小泊位的基础上,为停车高峰时段预留利用率较高的泊位,提高空闲泊位紧缺时段的泊车效率及驾驶员的泊车满意度。

土木工程话土木

Civil Engineering这个学科在中国以两种天然材料土和木命名,称为土木工程,可见华夏文明与这两种材料间的密切关系。中国古代的殿堂庙宇基本都是木结构建筑,这与其他古文明主要以石料建造大型建筑物不同。该文从地理、历史、经济与文明属性对此进行分析,指出华夏文明的特殊性。土为人类提供了栖息、载体、武器、工具和材料,也是人类衣食之源。中国自古至今主要用土治水,所谓“水来土掩”;黄土高原自古至今窑洞都是当地居民重要的居所。几千年来,中国先民在不同的地域创建不同型式的木结构住房,雄伟壮丽的名楼殿宇代表了中国古代木结构工程的高超技艺。在治水过程中,中国古人因地制宜地将土与木相结合,创造了形式多样的加筋土。文章分析土的特殊性与多样性,指出岩土工程仍然需要依靠丰富的经验和成熟的案例进行工程决策。

基于预训练模型与BiLSTM-CNN的多标签代码坏味检测方法

为了提高多标签代码坏味检测的准确率,提出一种基于预训练模型与BiLSTM-CNN的多标签代码坏味检测方法DMSmell(deep multi-smell)。首先,利用静态分析工具获取源代码中的文本信息和结构度量信息,并采用2种检测规则对代码坏味实例进行标记;其次,利用CodeBERT预训练模型生成文本信息对应的词向量,并分别采用BiLSTM和CNN对词向量和结构度量信息进行深度特征提取;最后,结合注意力机制和多层感知机,完成多标签代码坏味的检测,并对DMSmell方法进行了性能评估。结果表明:DMSmell方法在一定程度上提高了多标签代码坏味检测的准确率,与基于分类器链的方法相比,精确匹配率提高了1.36个百分点,微查全率提高了2.45个百分点,微F1提高了1.1个百分点。这表明,将文本信息与结构度量信息相结合,并利用深度学习技术进行特征提取和分类,可以有效提高代码坏味检测的准确性,为多标签代码坏味检测的研究和应用提供重要的参考。