Research on Interactive Teaching for Intelligent Algorithm of

Engineering Big Data

Lehui Su

Quanzhou University of Information Engineering, Quanzhou, China

Keywords: Engineering Big Data, Intelligent Algorithm, Interactive Teaching.

Abstract: In the process of engineering construction, there are often a large number of engineering construction-related

data and the scientific and accuracy of data processing and analysis often directly affect the quality of

engineering construction. With the increase of the scale and quantity of construction projects, it is difficult

for manual data analysis and processing to meet the current needs of engineering construction. The application

of big data intelligent algorithm to scientifically process engineering data information is the main development

trend in the future. In this regard, as the main position of training big data talents in the new era, colleges and

universities need to actively introduce advanced teaching concepts, improve and innovate the teaching mode

of big data intelligent algorithm for the field of engineering construction, and then train more comprehensive

engineering big data talents. Based on this, this paper explores interactive teaching strategies. First, it

introduces the basic principles of intelligent algorithm of big data in engineering, then deeply analyzes the

practical problems faced in the teaching of intelligent algorithm of big data in engineering at present, and

finally discusses interactive teaching strategies oriented to intelligent algorithm of big data in engineering in

detail for reference.

1 INTRODUCTION

With the improvement of China's comprehensive

national strength, the scale and quantity of China's

infrastructure construction have gradually increased,

and the rapid development of infrastructure

construction, especially in the field of underground

space construction and development, China now

ranks in the forefront of the world. The construction

environment of urban underground space is usually

harsh, the hydrogeological conditions are complex,

and the construction process is often affected by the

environment and leads to safety accidents. Therefore,

it is necessary to make full use of big data intelligent

information technology in geological investigation

and other links before construction, and fully grasp

the project reality, which can provide scientific basis

for subsequent project decision-making. In addition,

the engineering construction process involves a large

amount of design, survey, construction data

information, big data technology analysis and

processing can make the engineering construction

more safe and efficient. In the face of the current

social shortage of engineering big data talents, some

universities currently offer artificial intelligence

algorithm courses and classify artificial intelligence

as one of the basic courses of engineering majors.

However, it is found in teaching practice that the

theory of artificial intelligence algorithm is not

mature for high-dimensional complex data. Therefore,

in daily teaching, teachers also need to combine the

concept of interactive teaching, and on the premise of

completing basic teaching tasks, visually demonstrate

the application of intelligent algorithms of big data to

students through visual teaching means, so as to

deepen students' understanding of knowledge. This

paper studies interactive teaching means based on

intelligent algorithms of engineering big data.

2 PRINCIPLE ANALYSIS OF

ENGINEERING BIG DATA

INTELLIGENT ALGORITHM

2.1 Basic Principles and Methods of

Deep Learning

Through practical investigation, it is found that most

students of engineering disciplines in colleges and

universities have weak algorithm foundation and

should strengthen their learning in courses such as

Su, L.

Research on Interactive Teaching for Intelligent Algorithm of Engineering Big Data.

DOI: 10.5220/0012273500003807

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 2nd International Seminar on Artiﬁcial Intelligence, Networking and Information Technology (ANIT 2023), pages 39-45

ISBN: 978-989-758-677-4

linear algebra and optimization, especially linear

equation solving and matrix derivation, which are of

great use for the research of engineering big data

algorithms(Wenchun Liu, 2022). Compared with the

traditional machine learning algorithm, deep learning

algorithm is more adaptable to the development needs

of the times, but its mechanism is complex and more

detailed, and it is not ideal to explain to students only

from the formula deduction level. Therefore, it is

suggested to start from the deep learning traceability,

combined with the explanation of the working

mechanism of biological nervous system, and

naturally lead to the concept of artificial neural

network. To be specific, the first step is to explain the

definition of artificial neuron-perceptron clearly, and

then derive artificial neural network according to its

role and characteristics of multi-layer perception

mechanism and applicable scenarios, and highlight

the excellent nonlinear fitting performance of

artificial neural network combined with visual

examples. The principle and mechanism of deep

learning are relatively complex and not easy to be

understood by students. The above teaching methods

can explain the deep learning concept in layers and

help students quickly master the basic knowledge of

engineering big data.

If deep learning is to achieve the desired effect,

some existing problems need to be solved first,

including updating parameters, calculating gradients

and other contents need to be improved. At present,

various schools of thought contend, and research on

deep learning has never stopped, and various

solutions have been proposed one after another.

These fragmented solutions seem to be chaotic and

methodical, but as a developing discipline,

engineering big data has a great demand for these rich

solution proposals and valuable practical experience.

Sorting out and summarizing these methods,

combined with in-depth research on the underlying

motivation and development concept, is of great

significance for the subsequent construction of deep

learning systems and the sorting out of the

development context. It is also conducive to the

flexible practical application of deep learning

concepts (Guantian Wang, 2022).

2.2 Deep Learning Based on PyTorch

Deep learning technology is the organic integration of

emerging cutting-edge technologies in many fields,

involving a variety of course knowledge content.

Deep learning has a wide range of functions, although

the realization of each function does not rely on the

use of esoteric mathematical knowledge, but it is

obviously very difficult to efficiently integrate deep

learning modules and apply them in millions and tens

of millions of big data. Therefore, for students with

weak basic knowledge, integrating each module from

zero to one is like a fantasy. Fortunately, through

continuous practice and exploration and research, it is

no longer a dream to effectively realize the basic

module of deep learning. Mature deep learning

libraries such as PyTorch and Ten-sorFlow have been

put into practice. Students with weak foundation can

also start quickly and solve various practical

problems (Kunbo Xu, 2022). Especially for

engineering students, most of them have poor

programming foundation. Courses based on deep

learning library will explore the construction of

online interactive programming environment based

on Jupyter, provide students with relevant learning

procedures, and help students explore deep learning

methods in practice with visual teaching methods.

Thus, the application of deep learning technology can

be used more quickly to solve practical problems

faced in current engineering construction and

improve practical ability.

3 THE APPLICATION OF BIG

DATA INTELLIGENT

ALGORITHMS FOR

ENGINEERING

3.1 Application of Engineering Big

Data Intelligent Algorithm for TBM

Tunneling Parameter Prediction

and Decision

In tunnel engineering, the application of full-section

tunnel boring machine (TBM) is very critical. For

long tunnels that are difficult to be successfully

excavated by traditional drilling and blasting methods,

TBM can reveal multiple advantages such as fast

excavation, safety and reliability, and green

environmental protection (

Bin Liu, 2021). TBM

operation requires higher professional quality and

experience of operators. If the operation construction

process is affected by adverse geological conditions,

or encounter lithology mutation, and no timely

scientific countermeasures are taken, the TBM will be

damaged or inefficient. Combined with a large

number of engineering examples, the information of

TBM driving parameters is deeply analyzed and

studied, and the matching adjustment of TBM driving

parameters is carried out according to the geological

ANIT 2023 - The International Seminar on Artiﬁcial Intelligence, Networking and Information Technology

and rock mass conditions. It can be seen that in the

process of TBM intelligent operation, the rational

application of artificial intelligence big data

technology to scientifically analyze engineering data

information is the key to ensure the efficiency of

excavation. Big data algorithms give full play to the

role of Bridges and accurately connect TBM

intelligent excavation with rock geological

information. In this process, with the continuous

change of geological rock mass conditions, TBM

excavation parameters can also be visually presented,

which plays a key guiding role in improving the

safety of TBM excavation and is of great significance.

3.2 Application of Engineering Big

Data Intelligent Algorithm for

Tunnel Advance Geological

Prediction

Tunnel advance geological prediction refers to the

geological condition report obtained from the

exploration of geotechnical bodies of underground

engineering combined with advanced modern drilling

and geophysical exploration technology, which is an

effective exploration means to macro-control the

structure of geotechnical bodies and groundwater

conditions in front of the construction (Ronghu Cao,

2022). Accurate and reliable tunnel geological

prediction plays a guiding role in the subsequent

construction, and can effectively prevent the impact

of geological disasters such as water gusher and rock

burst during the construction process to ensure the

smooth construction of the project. Among them, the

most commonly used geophysical exploration

technology is geophysical inversion, which attempts

to reconstruct the geological structure after obtaining

effective data information from observation. For this

kind of highly nonlinear problem, linear method is

often adopted to solve it, which leads to a certain

uncertainty and multiple solutions in the solution

process. Combined with the comprehensive

consideration of historical exploration data and

excavation data in previous regions, these valuable

experiences can provide a reference basis and

sufficient big data constraints for geophysical

inversion, and also play a certain role in improving

the above problems. It can be seen that the reasonable

application of engineering big data in tunnel

advanced geological prediction can provide solutions

to some problems currently faced by geophysical

exploration technology. The application of deep

learning method based on big data intelligent

algorithm in geophysical inversion has become a

feature of current research, and its application also

reflects the advanced nonlinear mapping ability in the

face of practical problems.

3.3 Application of Engineering Big

Data Intelligent Algorithm for

Geological Sketch

The main object of geological sketch is the field

geological image, and the geological form and spatial

structure are described in detail with the help of

sketch method, including geological structure,

geomorphic landscape and other aspects. For

complex geological phenomena that are difficult to

express in words, geological sketch can be visually

presented in the form of sketch, which can not only

improve work efficiency, but also provide a complete

reference for subsequent construction. Geological

sketch can be simply divided into two parts: field

work and interior work. First, field work refers to the

investigation of the regional geological conditions

where underground Wells and alleyways are located,

the collection of lithology, structure and other data

information, and then the collation and analysis of the

data information collected by field work, the

description of the geological conditions investigated

in accordance with relevant regulations and design

proportions, and the annotation of key points (Wenjia

Li, 2022). The whole process of geological sketch

drawing is very complicated and cumbersome, which

requires very high professional ability and

comprehensive quality of staff. The application of

engineering big data algorithm in this process is

expected to reduce manual intervention and enable

geological sketch to develop in the direction of

automation. At the same time, it can also play a key

role in mining the complex relationship between

geological sketch and previous photos.

4 PROBLEMS EXISTING IN THE

TEACHING OF INTELLIGENT

ALGORITHM OF

ENGINEERING BIG DATA

4.1 Problems Existing in the Course

Setting of Engineering Big Data

Intelligent Algorithm Teaching

In recent years, with the improvement of China's

comprehensive national strength, China's

construction industry is developing rapidly, and the

scale and quantity of construction projects are

Research on Interactive Teaching for Intelligent Algorithm of Engineering Big Data

increasing day by day. After more than ten years of

development, China's construction engineering field

has accumulated a lot of valuable practical experience

and stored massive engineering data (Wenchang Yu,

2022). Currently in the rapid development of the

information age, in this context, the application of big

data has obviously become the key to the progress and

development of major industries. However, in the

college education system, although the courses on big

data and artificial intelligence algorithms continue to

be offered, the courses on practical application cases

are very scarce. Students are often familiar with the

knowledge and skills of artificial intelligence

algorithms, but they are unable to start when facing

the data information in real engineering. It can be seen

that the biggest problem in the current teaching of

engineering big data intelligent algorithm in colleges

and universities is that engineering data processing

and artificial intelligence algorithm teaching are

independent of each other and not closely related,

only as independent teaching content to teach

students relevant knowledge, the teaching concept is

not forward-looking and advanced, and the lack of

effective combination with actual cases. In addition,

the teaching of cutting-edge methods of artificial

intelligence algorithm and engineering data

processing needs to set pre-courses, which is also

relatively lacking in most colleges and universities at

present, resulting in students' lack of understanding of

cutting-edge knowledge of artificial intelligence

algorithm, limiting the cultivation of students'

creativity, and the application of engineering big data

in practical projects, which lacks innovation in

solving problems (Caiyun Yang, 2021).

4.2 Problems in Teaching Methods of

Engineering Big Data Intelligent

Algorithm Teaching

For different types of subjects, there should be some

differences in teaching methods. Take urban

underground engineering teaching as an example, the

course content involves geotechnical engineering,

exploration, engineering mechanics and other related

knowledge content, the teaching content is relatively

fixed, and the teaching method is also based on

traditional teaching, with teachers explaining in class

and students practicing independently after class.

Compared with the teaching of urban underground

engineering, there are obvious differences in the

teaching methods of artificial intelligence. Daily

teaching of artificial intelligence involves the

processing and analysis of massive high-dimensional

data, and it is difficult to explain clearly the

mechanism and principle contained therein only

through the text presentation of textbooks and the oral

explanation of teachers. At the same time, the subject

of artificial intelligence has certain particularity.

Artificial intelligence technology, including deep

learning, has been widely used in various industries

in society. The current theoretical research is

relatively backward, and it has been unable to meet

the practical application needs of artificial

intelligence technology (Mingyang Deng, 2021).

5 INTERACTIVE TEACHING

STRATEGY FOR

ENGINEERING BIG DATA

INTELLIGENT ALGORITHM

5.1 Establish Engineering Big Data

Artificial Intelligence Algorithm

Course Group

Based on the above discussion of the current

difficulties in the teaching of engineering big data

intelligent algorithm in colleges and universities, this

paper proposes the establishment of engineering big

data artificial intelligence algorithm course group.

First of all, for the integration of artificial intelligence

and engineering big data, establish a new curriculum

system and add pre-courses. Taking urban

underground engineering teaching as an example, the

basic knowledge of artificial intelligence applied in

the teaching process is integrated and analyzed, and

integrated into the existing course design, a

comprehensive classroom teaching courseware is

made, and a pre-course is set up based on these

elements to help students quickly master the basic

knowledge related to the intelligent algorithm of big

data engineering. Secondly, the engineering data

processing course and the artificial intelligence

course contain some common elements, and teachers

can analyze and process these common elements in

the pre-class design, and introduce the frontier

knowledge of artificial intelligence into the actual

teaching (Fan Li, 2021). Taking the teaching of

geophysical exploration as an example, this course

involves many theories of artificial intelligence

knowledge, such as artificial neural networks, which

are relatively backward in the context of the new era.

Relevant contents of artificial intelligence courses

can be introduced into the teaching of geophysical

exploration, and cutting-edge knowledge of artificial

intelligence algorithms can be fully integrated into the

teaching of engineering big data to form a new

ANIT 2023 - The International Seminar on Artiﬁcial Intelligence, Networking and Information Technology

teaching model. Update the teaching content. Finally,

the rapid development of artificial intelligence in

recent years, as a multi-disciplinary interdisciplinary

integration of composite technology science, artificial

intelligence closely follows the pace of development

of The Times, widely used in all fields of society,

especially in the construction of construction

engineering reflects valuable application value.

Therefore, teachers should timely follow up to

understand the latest development of artificial

intelligence, master cutting-edge knowledge, and

combine other disciplines and related engineering

examples to skillfully integrate these knowledge into

daily teaching to create a new type of engineering big

data artificial intelligence algorithm course. Through

the teaching of cutting-edge technology and the

necessary practical guidance, students can apply their

knowledge to solve the problems faced by practical

engineering construction and inspire their innovation.

The engineering big data artificial intelligence

algorithm course group can be divided into three parts:

advance course, basic course and innovation course.

The content of advance course includes basic

artificial intelligence introduction, geophysical

inversion introduction and TBM application

mentioned above. Basic courses include principles of

seismic exploration, basic principles and basic

methods of deep learning, etc. The innovative course

content includes deep reinforcement learning, deep

learning practice based on PyTorch, etc. (Cheng Wan,

2021).

5.2 Rational Application of Interactive

Teaching Means

With the in-depth analysis of the characteristics of

artificial intelligence algorithms, in addition to the

basic knowledge content such as the flow of artificial

intelligence algorithms, teachers can also adopt visual

and interactive teaching methods to visually present

obscure knowledge concepts in the daily teaching

process. It is of great significance for students to

deeply understand the principles behind artificial

intelligence algorithms and achieve the expected

teaching effect. It is especially beneficial for students

with weak information foundation. First of all, for the

pre-course repeatedly mentioned in this paper,

teachers can strengthen the application research of

artificial intelligence visualization means in the pre-

course, so as to provide help for students to intuitively

understand the application of artificial intelligence

algorithms. Secondly, in order to facilitate students to

consolidate knowledge network and verify theoretical

concepts, teachers can conduct interactive simulation

experiment training and appropriate programming

exercises in class for the relevant basic theoretical

basis involved in the engineering big data artificial

intelligence course (Hongqing Song, 2021). Finally,

as we all know, innovation ability is the basic

requirement for talent training in the new era. As the

main position of talent training, colleges and

universities should take the cultivation of students'

innovation ability as the main educational goal.

In the innovative practice class, teachers should focus

on guiding students to think about the practical ideas,

motivations, means, etc. of artificial intelligence

algorithm application examples in engineering big

data, and continuously strengthen guidance in the

teaching process, appropriately throw out reasonable

problems, and guide students to find problems while

taking appropriate means to solve problems. All in all,

the application of interactive teaching strategies in the

classroom of engineering big data artificial

intelligence algorithms can intuitively display

artificial intelligence-related algorithms and

processes to students with the help of advanced

interactive technology, simplify artificial intelligence

algorithms, facilitate students' learning and

understanding, and then quickly master artificial

intelligence algorithms and apply them to engineering

practice.

5.3 Build a Two-Way Interaction

Mechanism Between Artificial

Intelligence Algorithm Teaching

and Engineering Big Data Practice

The main goal of the research on engineering big data

processing and analysis technology is to solve the

problems faced in the process of engineering

construction in the new era. The latest artificial

intelligence algorithms that have been continuously

studied, are also implemented in actual projects, and

the reliability of the algorithm can only be verified

after application experiments (Xiang Li, 2021). The

research object of artificial intelligence algorithms is

numbers, is data information, but deep research

purpose and connotation, is still a scientific and

technological means to serve the actual engineering,

artificial intelligence algorithm research must not be

separated from the practical application of

engineering, otherwise it is only the spiritual carnival

of scientific researchers, self-entertainment. The in-

depth mining of engineering big data information, as

well as the research and utilization of artificial

intelligence algorithms, need to be based on practical

applications, and need to be improved, optimized,

verified and upgraded in continuous practice. In this

Research on Interactive Teaching for Intelligent Algorithm of Engineering Big Data

way, it can fully reflect the application value of

engineering big data and promote the application of

artificial intelligence technology to the direction of

automation and complexity.

6 INTERACTIVE TEACHING

EXAMPLE FOR

ENGINEERING BIG DATA

INTELLIGENT ALGORITHM

6.1 Visual Explanation of Basic

Principles Interactive Teaching

Examples

The artificial neuron mentioned above is also called

the perceptron, which is a simulated neuron based on

the biological neuron mechanism, capable of binary

classification, operation logic and or not (Jingyan

Wang, 2021). A multi-layer perceptron MLP with

powerful nonlinear mapping ability can be formed by

superposition of multiple artificial neurons.

According to the universal approximation theorem, if

the multi-layer perceptron has a hidden layer, all the

complex functions can be fitted successfully when

there are enough artificial neurons. Take some

interactive small programs as examples, artificial

neurons are freely combined into small Bump.

Through appropriate adjustment of Bump parameters,

it can be made to fit part of the function, of course, if

there are enough neurons, it can accurately fit any

complex function. On this basis, the multi-layer

perceptron expands into a six-layer artificial neural

network. Then the problem of double helix line

classification is an example to carry out interactive

teaching practice, visualize the response

characteristics of neurons and the update of weights,

and intuitively present the working mechanism of

artificial neural network to students, which is

convenient for students to understand.

6.2 Interactive Teaching Examples of

Intuitive Interpretation of Gradient

Backpropagation

As a key learning point of deep learning technology,

gradient backpropagation is the basic technology that

can effectively update the gradient of artificial neural

network. Gradient backpropagation learning divides

into two forms: pure mathematical derivation and

computational graph assisted derivation. For students

with engineering background, the derivation mode

based on computational graph is more intuitive and

practical, and two key points of computational graph

and chain rule should be paid attention to in the

application process (Rangsheng Gong, 2021). With

the help of the calculation diagram, the calculation

process of various operations can be visually

presented by graphical method. The application of

calculation diagram and chain rule enables neural

network calculation to be solved quickly and

efficiently by using automatic differentiation. At

present, all major deep learning libraries adopt auto-

grad automatic differentiation system, so there is no

need to pay too much attention to gradient calculation,

and only need to pay attention to the definition of

network layer structure, as well as input and output

operations. This undoubtedly provides convenient

conditions for users to build deep learning neural

networks. Figure 1 shows the gradient

backpropagation operations corresponding to several

complex network layer operations.

Figure 1. Gradient backpropagation operations

corresponding to complex network layer operations.

7 CONCLUSION

To sum up, in order to promote the upgrading of

China's industrial structure and become a world

transportation competing nation, colleges and

universities should carry out the reform of

engineering talent training mode, since they are the

main positions of talent training. The solutions

includes the curriculum design, teaching concept and

teaching means. In recent years, China's continuous

development and construction has accumulated a

large number of engineering data and valuable

practical experience. According to the summary and

analysis of these data, combined with the demand for

intelligent algorithms of engineering big data,

teachers can introduce interactive teaching methods

to design relevant courses to guide students to deepen

their understanding of the application of artificial

intelligence algorithms. Under the interactive

teaching mode oriented to the intelligent algorithm of

ANIT 2023 - The International Seminar on Artiﬁcial Intelligence, Networking and Information Technology

engineering big data, a large number of talents in the

field of artificial intelligence have emerged in

colleges and universities. More latest technological

achievements have appeared in various competitions,

which cannot only help solve practical engineering

problems, but also lay a solid foundation for the

cultivation of talents in the field of intelligent

construction.

REFERENCES

Wenchun Liu. Research on interactive query technology of

big Data based on improved deep learning algorithm (J).

Journal of Qiqihar University: Natural Science Edition,

2022, 38(3):6.

Guantian Wang, Yande Liu, Xiaogang Jiang, et al. Research

on the teaching method of Big Data Technology Basic

Course in the background of Intelligent Manufacturing

Engineering (J). China Science and Technology

Economy News Database Education, 2022(6):4.

Kunbo Xu, Yanqin Zhang, Xiaohui Li, et al. Research and

exploration of engineering practice education system for

new engineering (J). China Science and Technology

Journal Database Research, 2022(8):3.

Bin Liu, Peng Jiang, Lichao Nie, et al. Teaching reform and

Exploration of Underground space engineering in Smart

City for training new engineering talents (J). Journal of

Higher Education, 2021, 7(27):5.

Ronghu Cao, Juan Rui, Hui Tang, Gelei Feng, Yan Xu.

Application Oriented Big Data Intelligence Theory and

Method curriculum design and Practice (J). Computer

Education, 2022(8):80-84. (in Chinese)

Wenjia Li, Lan Shi, Hangxu Ji, et al. Research and

implementation of FLInk-oriented load Balancing task

Scheduling Algorithm (J). Computer Engineering and

Science, 2022, 44(7):11.

Wenchang Yu, Zheqing Zhang. Experimental design and

Practice of Programming Course under the background

of Engineering Certification: A case study of "Object-

oriented Programming" course (J). Journal of Chizhou

University, 2022, 36(3):136-139.

Caiyun Yang, Jianwen Fang, Xiaolong Zhou, et al.

Improving the quality of engineering Practice Education

from the perspective of integration of production and

education: A case study of Data Science and Big Data

Technology majors in local applied universities (J).

Journal of Higher Education, 2021, 7(31):5.

Mingyang Deng. Research and practice exploration of

Intelligent Course Cloud service system from the

perspective of Big Data (J). Journal of Mudanjiang

University, 2021, 30(4):107-112.

Fan Li. An analysis of the achievement evaluation

mechanism of graduation requirements for Engineering

Education Certification: Based on the background of

Education Big Data (J). Journal of Yuzhang Normal

University, 2021, 36(5):5.

Cheng Wan, Yiqing Gu, Xinxia Zhang, Yuyun Wei.

Construction and application of simulation clinical Big

Data teaching platform based on CDM (J). Education

and Teaching Forum, 2021(50):4.

Hongqing Song, Shuyi Du, Yuanchun Zhou, et al. Big data

intelligent platform and application analysis for oil and

gas resource development (J). Chinese Journal of

Engineering Science, 2021, 43(2):14.

Xiang Li, Yunyang Yan, Liuyang Wang, Yuanyuan Wang.

Curriculum reform practice of Web development

technology for Engineering Education Certification (J).

Journal of Computer Education, 2021, (2):131-134,139.

Jingyan Wang, Deqiu Zhang, Muqin Li, et al. Research on

Smart classroom teaching design under the background

of Big Data in the new era (J). Chinese Science and

Technology Journal Database (Full text) Education

Science, 2021(4):1.

Rangsheng Gong, Sugui Li, Min Lin. Construction of Big

Data Technology intelligent teaching Platform from the

perspective of lifelong Education (J). Electronic

Technology and Software Engineering, 2021, (12):172-

173.

Research on Interactive Teaching for Intelligent Algorithm of Engineering Big Data