SPECIAL TRACK ON
Track 1- AI and Machine Learning Techniques and their advancements in various Electrical Engineering Applications
Workshop Chair: Dr. T. Venkatesh, School of Electrical and Electronics Engineering, SASTRA University, Thanjavur, India
Dr. Padmanaban Sanjeevikumar, Department of Energy Technology, Aalborg University, Esbjerg 6700 Denmark
There is no doubt that we are living in a large data driven era, evidenced by the phenomenon that the amount of data being continually generated at unprecedented and ever increasing scales. These piles of data are obtained due to large scale studies conducted in numerous industries varying from sciences to engineering including networking, biomedical, business strategies, etc. Thus, in present scenario, it is incredible that the amount of digital data collected from various platforms is rapidly increasing and therefore this massive data expansion can be collectively called as ‘Big Data’. Artificial intelligence and machine learning techniques have been widely studied in many fields such as medicine, astronomy, biology, and engineering. These techniques are found to be successful in providing possible solutions to determine the underlying information from the complex datasets. In case of big data, the size of data sets is so large and complex which makes it hard to crack with the usage of traditional learning methods since the established process of learning from conventional datasets was not designed to and will not work well with high volumes of data. However, learning from these vast and complex data is expected to bring significant change in the overall performance of the data driven classifiers. At the same time, it brings tremendous challenges like data imbalance, increasing learning and testing times, difficulty in achieving higher prediction rates, etc. This special session will be devoted to the current state-of-the-art research in the ‘AI and Machine Learning Techniques and their advancements in various Electrical Engineering Applications’. The guest editors solicit recent results mainly concerned with recent advances and challenges in the theory and applications of Machine learning techniques in the broader aspects of electrical engineering. The session invites unpublished work/papers to cover fundamental of Machine Learning techniques, future perspective of AI/Machine Learning, its application and research in various aspects of Electrical Engineering industries. The session will benefit participants from academics, R&D institutions, professional engineers from utilities, and research scholars at masters and PhD programs in the area of Machine Learning and computational Algorithms. Topics Covered:
The topics of interest mentioned below may be specially emphasised on -
Advanced machine learning techniques to manage big data
Applications of various algorithms to large datasets gathered in business intelligence, healthcare, smart sensor networks and power grids
Applications of big data for monitoring and evaluation of various utilities
Scalability and performance of machine learning techniques on big data
Challenges in managing big data
Dynamic machine learning (including fuzzy deep learning) used on Industrial big data
Data Sampling methods and latest trends in handling class imbalance problem in large datasets
Robust and hybrid classifiers for Classification, Regression and Prediction problems
Algorithms for network monitoring and security threats detection while handling industrial big data
Probabilistic Models and Methods
Deep learning based classification methods and Evolutionary computation for various classification problems
Machine learning based classification of image, signal, text, etc.
Applications of deep learning for building chatbots
Usage of machine learning techniques and their application areas include, but are not limited to: telecommunication, electrical and power engineering, logistics, manufacturing, robotics, automation, sensors, security, healthcare, administration, e-learning, decision making, business and finance, bioinformatics, and several engineering related fields.
Paper Submission Link:
Track 2- Role of Big Data and Cloud Computing in adaptive learning and security
Workshop Chair (s): Dr. Ashutosh Kumar Dubey, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
Dr. Vishal Kumar, Bipin Tripathi Kumaon Institute of Technology, Uttarakhand, India
Dr. Abhishek Kumar, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
In terms of data management Big data and Cloud computing have shown an emerging aspect through adaptive learning and computational technologies. There are several areas of research where the combination of these two techniques has been used for the more benefit. Both the technologies have the capability to enhance the revenue of the company while reducing the investment cost. Cloud computing is found to be useful in providing the local staff and resources on demand, while Big data is useful in the decision processing and handling the huge amount of data. The analysis of different computation techniques in terms of Big data and Cloud computing is important as it can provide better data visualization, computing solutions, real time analytics, automation and data sharing. Then security aspects are also important as data sharing should be done in the secure environment. The session invites unpublished manuscripts to cover fundamental of Big data and Cloud Computing along with the impact of machine learning techniques, data mining techniques and nature inspired algorithms. The session will benefit participants from academics, R&D institutions, professional engineers, and research scholars in the same area. Topics of interest include, but are not limited to the following: 1. Big data technologies 2. Data visualization 3. Data mining tools and techniques, machine learning algorithms for big data 4. Cloud computing platforms 5. Distributed file systems and databases and scalable storage systems 6. Scalable big data frameworks, platforms and visualization solutions 7. Clouds for big data and high-performance computing 8. Cloud foundations for connected devices and real-time analytics 9. Cloud, utility, edge and serverless computing paradigms 10. Multi-cloud management, aggregation and resource sharing 11. Algorithms for energy-efficient, fast and secure computing in clouds 12. Software engineering for cloud-native applications and Big Data 13. Data security 14. Computational analysis of big data and cloud computing
Paper Submission Link:
Track 3- Workshop on Software Defined Network & Network Function Virtualization
Workshop Chair: Sanjay Sharma, Thapar University, India
The distributed control are hard to manage as each individual
network devices has to be configured separately (usually using
vendor specific commands) by network operator. Apart from
configuration complexity, the control plane and the data plane are
embedded inside the same network device; which makes network
inflexible and nonadaptive to innovations and evolution. Software
Defined Network (SDN) is an emerging control plane architecture
that addresses these limitations of a distributed control plane.
Its key features are:
• It separates control logic from the network/forwarding elements thus simplifying network operations.
• It advocates centralized control to simplify network policy alteration and boost/promote innovation by introducing the ability to program the network.
• It adopts flow abstraction thus unifying the behaviour of different types of network devices like router, switches, middle boxes, firewalls etc.
The Open networking foundation (ONF) defines SDN as a programmable network architecture where the control plane and data plane are separate. By decoupling control and data planes, the network intelligence and state can be logically centralized, the forwarding infrastructure can be conveniently abstracted to the application plane, and innovation is boosted independently at each plane. Network function virtualization (NFV) separates the network functions from the underlying hardware appliances by transferring network functions from dedicated hardware to general software running on commercial offtheshelf (COTS) equipments, i.e., virtual machines. The major advantage of using NFV is to reduce middleboxes deployed in the traditional networks to take the advantages of cost savings and bring flexibility. On the other side, NFV technology also supports the coexists of multitenancy of network and service functions, through allowing the usage of one physical platform for different services, applications, and tenants.
Paper Submission Link: