Sensor data collection and analysis is crucial for a successful implementation of Internet of Things (IoT) application. On completion of the module, students will develop competencies in developing an IoT application using an array of smart sensor that collects a variety of data types such as status, location, automation, and actionable data obtainable in smart sensors. Students will be competent in using smart sensors to transfer data through a gateway and the various network protocol stack such as transport, network, and link layer. Student will also be competent in performing basic analysis on data collected to solve engineering related problems.

The power of Internet of Things (IoT) lies in its ability to change the way businesses think and operate. On completion of the module, students will develop competencies in architecting, developing, and deploying IoT applications in the engineering field to solve problems. Student will also be competent in applying technologies such as edge computing and data analytics in IoT systems to monitor, automate and provide insights for decision making.

On completion of the module, students should be able to apply data mining principles to the dissection of large complex data sets, including those in very large databases or through web mining. Student will also be able to clean data, which includes finding and removing unwanted bits of data in spreadsheets, formatting data correctly, dealing with inconsistencies in the data, and structuring of data for effective use.

On completion of the module, students will be competent in making sense of data through various data visualization techniques. Learners will also be competent in working collaboratively in teams to present data in an effective way to gain deeper insights into engineering data, as well as to present efficient information visualization to different levels of stake holders in an organization.

Artificial intelligence is a transformative technology, generally refers to the ability of digital computing devices that can perform tasks commonly associated with intelligent beings. Through this module, Student will gain a holistic view of AI landscape – from its humble origin to bleeding edge technologies and applications of today. Learners will be introduced to historically significant AI systems and their underlying AI concepts. They will explore different classical and modern AI techniques and understand the three essential ingredients that drive modern AI – big-data, big-compute, and advanced algorithms. Learners will also examine the ethical and legal aspects of AI technologies as well as the exciting future trends. On completion of the modules, students should be able to experience the concepts of AI through no to low coding methods. Students will create basic program logic and AI model through fun and engaging project.

Machine learning allows the user to feed a computer algorithm an immense amount of data and have the computer analyze and make data-driven recommendations and decisions based on only the input data. On completion of the module, students will develop competencies in applying machine learning algorithms, including both supervised and unsupervised learning for AI modelling, using industry standard libraries/framework. Student will also be competent in determining appropriate machine learning algorithms for different use cases across engineering verticals.

Deep learning has delivered big technology breakthroughs and is regarded as the major driver of artificial intelligence. It has a significant impact in most industries, and the trend will continue well into near future. Through this module, students will be introduced to essential theories and practical skills in deep learning. They will explore the different types of deep learning network and their applications in solving problems in different domains. Students will use appropriate deep learning frameworks to construct and train artificial neural networks to solve some interesting tasks. In addition, students will also acquire practical skills to address common learning problems associated with deep learning networks.

Supervised learning is a type of Machine Learning algorithm that models relationships and dependencies between the target prediction output and input features. On completion of the module, students will develop competencies in applying relevant predictive modelling techniques to predict the desired business outcomes and meet the service expectation of the stakeholders. Students will also be able to evaluate the accuracy and effectiveness of different predictive models using relevant metrics as well as to support peer learning.