Short-term Course on Deep Learning Applications for Smart Cities at NIT Rourkela [Sep 11-15]: Register by Sep 10

"This opportunity is brought to you by Team SAMMAT for free."

Registrations are open for a Short-term Course on Deep Learning Applications for Smart Cities at NIT Rourkela on 11-15 September 2023. The last date of registration is 10 September.

About the STC

Deep learning applications have the potential to revolutionize smart cities by providing intelligent solutions to various urban challenges. It offers the ability to analyze and make sense of large volumes of data, enabling more efficient and intelligent management of urban infrastructure including health systems, public safety measures, optimization of energy consumption, waste management, and management of smart city grids.

Here are several key motivations for utilizing deep learning in smart city applications:

Remote health monitoring and prognosis: Use of Deep Learning technologies can also overcome the burden of chronic disease by development of a system to monitor biomedical signals and medical images. By analyzing patient data, including medical records, genetic information, and lifestyle factors, deep learning algorithms can identify patterns and indicators that aid in the early detection and prediction of diseases. This enables healthcare providers to deliver personalized care to patients in remote locations, reduce hospital readmissions, and improve access to healthcare services.

Biometric security: There is also a dire need to substantially improve human recognition and authentication capabilities in the critical and challenging areas ranging from individual threat, privacy to law enforcement, border control and security at the global level. Deep learning has made significant advancements in biometric applications, revolutionizing the field of biometrics with its ability to extract meaningful and discriminative features from complex data.

Enhanced Quality of Life: Deep learning applications can contribute to improving the overall quality of life in smart cities. For example, deep learning algorithms can analyze social media data to understand public sentiment, identify areas of improvement, and tailor public services to meet the needs of residents. Additionally, smart personal assistants powered by deep learning can provide personalized recommendations and assistance to individuals, enhancing convenience and well-being. Deep learning algorithms can analyze environmental data, such as air quality measurements, weather patterns, and pollution levels, to monitor and manage the urban environment effectively.

Overall, deep learning has the potential to transform smart cities by harnessing the power of data and artificial intelligence to optimize resource utilization, improve efficiency, enhance public safety, and create more sustainable and livable urban environments.

The workshop will have three major tracks:

Deep Learning applications for Biometrics and Digital Forensics
Deep Learning applications for Biomedical Engineering
Deep Learning applications for Intelligent urban infrastructure.

Workshop Objectives

To provide participants with an in-depth picture on the state-of-the-art in new and emerging applications of Deep Learning for smart cities.
To provide research and application oriented learning for secure and healthy society using Deep Learning methods.
To impart hands-on sessions on tools for bimetrics, biomedical engineering and intelligent multimedia
To provide the academic body of knowledge on Deep Learning-enabled transformation in public services

Topics

Granular Mining in Video Analytics: Shallow to Deep Learning
Dictionary learning based IOT solutions for smart cities o Deep learning-based data hiding for smart healthcare.
Multimedia Quality Assessment and it’s application in Deep Learning o Intelligent Visual Analysis for Pedestrian Safety and Beyond
Optimisation in deep learning: Are we really optimising cost functions?
Role of Deep Learning models for Biomedical Applications
Image Annotation: Then and Now
Advances in Deep Learning for Biomedical Image Processing: Challenges and Future Directions
Application of AI to stroke rehabilitation
Deep Learning applications for biomedical signal processing
Electricity load forecast using environmental adaptation method and artificial neural network
Convolutional neural networks for NLP
Matlab: Deep Learning Applications for Biomedical Engineering

Target Participants

The short-term course is of immense interest for UG/ PG students, research scholars/professionals, staff/ faculty members and industry professionals working in the area of Intelligent Transportation Systems for Smart Cities. The participants having Computer Science and Engineering, Electronics and Communication Engineering, and Electrical Engineering background will be benefitted with this shortterm course.