Personal tools
Log in

Advanced Data Analysis with Machine Learning

Course: Advanced Data Analysis with Machine Learning

Code: 3ФЕИТ07008

ECTS points: 6 ECTS

Number of classes per week: 3+0+0+3

Lecturer: Asst. Prof. Dr. Hristijan Djoreski

Course Goals (acquired competencies): Analysis of structured and unstructured data. Working with algorithms of Artificial Intelligence, Machine Learning, and Deep Learning.

Course Syllabus: Advanced Data analysis of different types of data, including: structured and unstructured data, time series, pictures, sound, and similar. Processing and analysis of the data using Artificial Intelligence, Machine Learning and Deep Learning methods. Application of these methods to analyse the data: pre-processing of data (filtering), attribute extraction, building classification and regression models, clustering, visualization of data and models, comparison of models. Implementation of the methods using Java or Python development environment (Weka, sklearn, tflearn, numpy, matplotlib, pandas, TensorFlow, Keras, Pythorch).

Literature:

Required Literature

No.

Author

Title

Publisher

Year

1

Ordóñez, F.J.; Roggen, D

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Sensors  2016

2016

2

Vyas, N.; Farringdon, J.; Andre, D.; Stivoric, J.I.

Machinelearning and sensor fusion for estimating continuous energy expenditure

In Proceedings of the Innovative Applications of Artificial Intelligence Conference

2011

3

Hammerla NY, Halloran S, Plötz T.

Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables

IJCAI 2016

2016

Additional Literature

No.

Author

Title

Publisher

Year

1

Chavarriaga, R.; Sagha, H.; Calatroni, A.; Digumarti, S.; Tröster, G.; Millán, J.; Roggen, D.

The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition

Pattern Recognit. Lett. 2013

2013

2

Yu Guan, Thomas Ploetz

Ensembles of Deep LSTM Learners for Activity Recognition using Wearables

Ubicomp 2017

2017

3

Sebastian Munzner, Philip Schmidt, Attila Reiss, Michael Hanselmann, Rainer Stiefelhagen, Robert Durichen

CNN-based Sensor Fusion Techniques for Multimodal Human Activity Recognition

Ubicomp 2017

2017