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.

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.

Machine Learning-Driven Classification for Enhanced Rule Proposal Framework

In enterprise operations,maintaining manual rules for enterprise processes can be expensive,time-consuming,and dependent on specialized domain knowledge in that enterprise domain.Recently,rule-generation has been automated in enterprises,particularly through Machine Learning,to streamline routine tasks.Typically,these machine models are black boxes where the reasons for the decisions are not always transparent,and the end users need to verify the model proposals as a part of the user acceptance testing to trust it.In such scenarios,rules excel over Machine Learning models as the end-users can verify the rules and have more trust.In many scenarios,the truth label changes frequently thus,it becomes difficult for the Machine Learning model to learn till a considerable amount of data has been accumulated,but with rules,the truth can be adapted.This paper presents a novel framework for generating human-understandable rules using the Classification and Regression Tree(CART)decision tree method,which ensures both optimization and user trust in automated decision-making processes.The framework generates comprehensible rules in the form of if condition and then predicts class even in domains where noise is present.The proposed system transforms enterprise operations by automating the production of human-readable rules from structured data,resulting in increased efficiency and transparency.Removing the need for human rule construction saves time and money while guaranteeing that users can readily check and trust the automatic judgments of the system.The remarkable performance metrics of the framework,which achieve 99.85%accuracy and 96.30%precision,further support its efficiency in translating complex data into comprehensible rules,eventually empowering users and enhancing organizational decision-making processes.

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.

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.

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.

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.

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.

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。

Ignition Pattern Analysis for Automotive Engine Trouble Diagnosis Using Wavelet Packet Transform and Support Vector Machines

Engine spark ignition is an important source for diagnosis of engine faults.Based on the waveform of the ignition pattern,a mechanic can guess what may be the potential malfunctioning parts of an engine with his/her experience and handbooks.However,this manual diagnostic method is imprecise because many spark ignition patterns are very similar.Therefore,a diagnosis needs many trials to identify the malfunctioning parts.Meanwhile the mechanic needs to disassemble and assemble the engine parts for verification.To tackle this problem,an intelligent diagnosis system was established based on ignition patterns.First,the captured patterns were normalized and compressed.Then wavelet packet transform（WPT） was employed to extract the representative features of the ignition patterns.Finally,a classification system was constructed by using multi-class support vector machines（SVM） and the extracted features.The classification system can intelligently classify the most likely engine fault so as to reduce the number of diagnosis trials.Experimental results show that SVM produces higher diagnosis accuracy than the traditional multilayer feedforward neural network.This is the first trial on the combination of WPT and SVM to analyze ignition patterns and diagnose automotive engines.

Robustness Assessment and Adaptive FDI for Car Engine

A new on-line fault detection and isolation （FDI） scheme proposed for engines using an adaptive neural network classifier is evaluated for a wide range of operational modes to check the robustness of the scheme in this paper. The neural classifier is adaptive to cope with the significant parameter uncertainty, disturbances, and environment changes. The developed scheme is capable of diagnosing faults in on-line mode and the FDI for the closed-loop system with can be directly implemented in an on-board crankshaft speed feedback is investigated by diagnosis system （hardware）. The robustness of testing it for a wide range of operational modes including robustness against fixed and sinusoidal throttle angle inputs, change in load, change in an engine parameter, and all these changes occurring at the same time. The evaluations are performed using a mean value engine model （MVEM）, which is a widely used benchmark model for engine control system and FDI system design. The simulation results confirm the robustness of the proposed method for various uncertainties and disturbances.

Kansei Engineering Applied to the Form Design of Injection Molding Machines

This study investigated the relationship between a subject’s evaluation of injection molding machines (IMMs) and formal design features using Kansei engineering. This investigation used 12 word pairs to evaluate the IMM configurations and employed the semantic differential method to explore the perception of 60 interviewees of 12 examples. The relationship between product feature design and corresponding words was derived by multiple regression analysis. Factor analysis reveals that the 12 examples can be categorized as two styles—advanced style and succinct style. For the advanced style, an IMM should use a rectangular form for the clamping-unit cover and a full-cover for the injection-unit. For the succinct style, the IMM configuration should use a beveled form for the safety cover and a vertical rectangular form for the clamping-unit cover. Quantitative data and suggested guidelines for the relationship between design features and interviewee evaluations are useful to product designers when formulating design strategies.

Solution to new word perplexity in immersion bilingual teaching of engineering graphics

Numerous and specialized words are main obstacles in immersion bilingual teaching of engineering graphics. A feasible solution to this problem is given by classifying new words into three categories. The fear of new words among students is overcome and the effect of bilingual teaching is greatly improved .

EDCMS:A Content Management System for Engineering Documents

Engineers often need to look for the right pieces of information by sifting through long engineering documents, It is a very tiring and time-consuming job. To address this issue, researchers are increasingly devoting their attention to new ways to help information users, including engineers, to access and retrieve document content. The research reported in this paper explores how to use the key technologies of document decomposition （study of document structure）, document mark-up （with EXtensible Mark- up Language （XML）, HyperText Mark-up Language （HTML）, and Scalable Vector Graphics （SVG））, and a facetted classification mechanism. Document content extraction is implemented via computer programming （with Java）. An Engineering Document Content Management System （EDCMS） developed in this research demonstrates that as information providers we can make document content in a more accessible manner for information users including engineers.The main features of the EDCMS system are： 1） EDCMS is a system that enables users, especially engineers, to access and retrieve information at content rather than document level. In other words, it provides the right pieces of information that answer specific questions so that engineers don＇t need to waste time sifting through the whole document to obtain the required piece of information. 2） Users can use the EDCMS via both the data and metadata of a document to access engineering document content. 3） Users can use the EDCMS to access and retrieve content objects, i.e. text, images and graphics （including engineering drawings） via multiple views and at different granularities based on decomposition schemes. Experiments with the EDCMS have been conducted on semi-structured documents, a textbook of CADCAM, and a set of project posters in the Engineering Design domain. Experimental results show that the system provides information users with a powerful solution to access document content.

Applications of Data Mining Theory in Electrical Engineering

In this paper, we adopt a novel applied approach to fault analysis based on data mining theory. In our researches, global information will be introduced into the electric power system, we are using mainly cluster analysis technology of data mining theory to resolve quickly and exactly detection of fault components and fault sections, and finally accomplish fault analysis. The main technical contributions and innovations in this paper include, introducing global information into electrical engineering, developing a new application to fault analysis in electrical engineering. Data mining theory is defined as the process of automatically extracting valid, novel, potentially useful and ultimately comprehensive information from large databases. It has been widely utilized in both academic and applied scientific researches in which the data sets are generated by experiments. Data mining theory will contribute a lot in the study of electrical engineering.