Module Information

معلومات المادة الدراسية

Module Title

Engineering Data Analytics

Module Delivery

Module Type

Core

☒ Theory

☒ Lecture

☐ Lab

☒ Tutorial

☐ Practical

☐ Seminar

Module Code

GPPE303

ECTS Credits

4

SWL (hr/sem)

100

Module Leve

UGx11  3

Semester of Delivery

5

Administering Department

GPPE

 College

COGE

Module Leader

Nuhad AbdulWahed

 e-mail

E-mail

Module Leader’s Acad. Title

Lecturer

Module Leader’s Qualification

Ph.D.

Module Tutor

Name (if available)

 e-mail

E-mail

Peer Reviewer Name

Name

 e-mail

E-mail

Scientific Committee Approval Date

01/06/2023

Version Number

1.0

Relation with other Modules

العلاقة مع المواد الدراسية الأخرى

Prerequisite module

None

Semester

Co-requisites module

None

Semester

Module Aims, Learning Outcomes and Indicative Contents

أهداف المادة الدراسية ونتائج التعلم والمحتويات الإرشادية

 Module Objectives

أهداف المادة الدراسية

1. Introduce the concept of data analytics in chemical engineering and its applications.
2. Highlight the importance of data-driven decision-making in the industry.
3. Provide an overview of data collection methods, data types, and preprocessing techniques.
4. Explore exploratory data analysis techniques for data summarization, visualization, and pattern identification.
5. Cover statistical analysis, hypothesis testing, regression analysis, and correlation.
6. Introduce machine learning fundamentals, including supervised and unsupervised learning algorithms.
7. Focus on predictive modeling, feature selection, model evaluation, and performance metrics.
8. Discuss data mining and pattern recognition techniques, such as association rule mining and text mining.
9. Cover time-series analysis, including data preprocessing, forecasting techniques, and trend analysis.
10. Introduce big data concepts, handling large-scale data sets, and scalable analytics in chemical engineering.
11. Showcase case studies and real-world applications of data analytics in chemical engineering.
12. Discuss ethical considerations and challenges in data analytics.

Module Learning Outcomes

مخرجات التعلم للمادة الدراسية

1. Understand the fundamentals of data analytics and its significance in chemical engineering.
2. Gain proficiency in data collection, preprocessing, and exploratory data analysis techniques.
3. Apply statistical analysis, hypothesis testing, and regression analysis in chemical engineering problems.
4. Familiarize with machine learning algorithms and their applications in classification and regression tasks.
5. Acquire skills in predictive modeling, feature selection, and model evaluation using appropriate metrics.
6. Develop knowledge in data mining techniques and their relevance to chemical engineering.
7. Gain expertise in time-series analysis, forecasting, and trend analysis for temporal data.
8. Understand the challenges and considerations of big data analytics in chemical engineering.
9. Apply data analytics techniques to solve real-world problems and case studies in chemical engineering.
10. Recognize the ethical implications and challenges associated with data analytics.

Indicative Contents

المحتويات الإرشادية

Indicative content includes the following.

Introduction to Data Analytics in Chemical Engineering

Overview of data analytics and its applications in chemical engineering, Importance of data-driven decision-making in industry,

Data Collection and Preprocessing

Data types and formats commonly encountered in chemical engineering, Data collection methods and sources, Data cleaning and preprocessing techniques (e.g., missing data handling, outlier detection),

Exploratory Data Analysis (EDA)

Descriptive statistics and data visualization techniques, Data summarization and feature engineering, Identifying patterns and relationships in data,

Statistical Analysis and Hypothesis Testing

Probability distributions and statistical inference, Hypothesis formulation and testing, Regression analysis and correlation,

Machine Learning Fundamentals

Introduction to machine learning algorithms, Supervised learning (classification and regression), Unsupervised learning (clustering and dimensionality reduction),

Predictive Modeling

Model evaluation and selection, Feature selection and regularization, Model performance metrics,

Data Mining and Pattern Recognition

Association rule mining, Sequential pattern mining, Text mining and sentiment analysis,

Time-Series Analysis

Time-series data characteristics and preprocessing, Time-series forecasting techniques, Seasonality and trend analysis,

Big Data Analytics in Chemical Engineering

Introduction to big data concepts and technologies, Handling large-scale data sets in chemical, engineering, Scalable analytics and distributed computing frameworks

Case Studies and Applications

Application of data analytics techniques in chemical engineering, Real-world case studies and projects

Ethical considerations and challenges in data analytics

Learning and Teaching Strategies

استراتيجيات التعلم والتعليم

Strategies

The main strategy that will be adopted in delivering this module is to encourage students’ participation in the exercises, while at the same time refining and expanding their critical thinking skills. This will be achieved through classes, interactive tutorials and by considering types of simple experiments involving some sampling activities that are interesting to the students.

Student Workload (SWL)

الحمل الدراسي للطالب محسوب لـ ١٥ اسبوعا

Structured SWL (h/sem)

الحمل الدراسي المنتظم للطالب خلال الفصل

44

Structured SWL (h/w)

الحمل الدراسي المنتظم للطالب أسبوعيا

3

Unstructured SWL (h/sem)

الحمل الدراسي غير المنتظم للطالب خلال الفصل

56

Unstructured SWL (h/w)

الحمل الدراسي غير المنتظم للطالب أسبوعيا

4

Total SWL (h/sem)

الحمل الدراسي الكلي للطالب خلال الفصل

100

Module Evaluation

تقييم المادة الدراسية

As

Time/Number

Weight (Marks)

Week Due

Relevant Learning Outcome

Formative assessment

Quizzes

2

10% (10)

5 and 10

LO #1, #2 and #3

Assignments

2

20% (20)

2 and 12

LO #3, #4 and #5

Projects / Lab.

0

10% (10)

Continuous

All

Report

1

10% (10)

13

LO #4,and #5

Summative assessment

Midterm Exam

1.5hr

10% (10)

7

LO #1 - #4

Final Exam

2hr

50% (50)

16

All

Total assessment

100% (100 Marks)

Delivery Plan (Weekly Syllabus)

المنهاج الاسبوعي النظري

Week 

Material Covered

Week 1

Introduction to data analytics in chemical engineering and its applications.

Week 2

Data collection methods, types, and formats encountered in chemical engineering.

Week 3

Data cleaning and preprocessing techniques, handling missing data, and detecting outliers.

Week 4

Descriptive statistics, data visualization, and exploratory data analysis.

Week 5

Probability distributions, statistical inference, and hypothesis testing.

Week 6

Regression analysis, correlation, and feature engineering.

Week 7

Introduction to machine learning algorithms and supervised learning.

Week 8

Unsupervised learning techniques, including clustering and dimensionality reduction.

Week 9

Model evaluation, selection, and performance metrics.

Week 10

Data mining techniques, association rule mining, and sequential pattern mining.

Week 11

Text mining and sentiment analysis in chemical engineering data.

Week 12

Time-series data characteristics, preprocessing, and forecasting techniques.

Week 13

Seasonality and trend analysis in time-series data.

Week 14

Introduction to big data concepts, handling large-scale data sets, and scalable analytics.

Week 15

Case studies, applications, ethical considerations, and challenges in data analytics.

Week 16

Preparatory week before the final Exam

Learning and Teaching Resources

مصادر التعلم والتدريس

Text

Available in the Library?

Required Texts

Title: "Introduction to Data Mining for the Life Sciences"

Author: Rob Sullivan

Publisher: MIT Press

Year: 2020

No

Recommended Texts

Machine Learning and Data Science in Chemical Engineering

Hanyu Gao*, Li-Tao Zhu, Zheng-Hong Luo, Marco A. Fraga, and I-Ming Hsing

No

Websites

https://pubs.acs.org/doi/10.1021/acs.iecr.2c01788

                                                                     Grading Scheme

مخطط الدرجات

Group

Grade

التقدير

Marks %

Definition

Success Group

(50 - 100)

A - Excellent

امتياز

90 - 100

Outstanding Performance

B - Very Good

جيد جدا

80 - 89

Above average with some errors

C - Good

جيد

70 - 79

Sound work with notable errors

D - Satisfactory

متوسط

60 - 69

Fair but with major shortcomings

E - Sufficient

مقبول

50 - 59

Work meets minimum criteria

Fail Group

(0 – 49)

FX – Fail

راسب (قيد المعالجة)

(45-49)

More work required but credit awarded

F – Fail

راسب

(0-44)

Considerable amount of work required

Note: Marks Decimal places above or below 0.5 will be rounded to the higher or lower full mark (for example a mark of 54.5 will be rounded to 55, whereas a mark of 54.4 will be rounded to 54. The University has a policy NOT to condone "near-pass fails" so the only adjustment to marks awarded by the original marker(s) will be the automatic rounding outlined above.