Title: Testing AI systems
Abstract: Today Artificial intelligence ( AI ) is at the centre stage for enterprises embracing digital transformation. AI systems are predicated upon generation of insights and patterns from large input data. Testing AI systems is complex due to the lack of test oracles and non deterministic nature of relationships. We present a bird's-eye view of testing challenges of AI systems. We also popular techniques for testing AI systems. Key among them include metamorphic testing, and Testing of explainability.
Srinivas Padmanabhuni is a Ph.D. in Artificial Intelligence. Srinivas Padmanabhuni co-founded CityMandi.com a next-generation AI-enabled smart B2B startup in Agri Tech focused on farm to fork. He has been the past president of ACM India, the top professional organization of computing professionals. He is the chief Mentor for Tarah technologies an AI consulting and training company. He specializes in areas of software engineering, AI and Machine Learning. Earlier, he was a Principal Research Scientist and Associate Vice President at Infosys where he overlooked the university innovation ecosystem, alongside research and innovation group in Infosys Labs. He has won several other awards including the excellence award for Innovation at Infosys, Research excellence award at the University of Alberta, and Merit award at IIT Kanpur.
Title: IoT in Smart Grid: A Software Engineering Perspective
Abstract: An important goal of Smart Grid Technology (SGT) is to leverage modern Information and Communication Technology (ICT) infrastructure to help monitor and control of the power system more effectively. This transforms conventional power system networks into smart energy grids that will be responsible for intelligent management, operation, and control of energy flow. With the increase in penetration of SGT in power systems, there has been a growing demand of real time visualization, monitoring, and control of the power system network. To do so, a large amount of sensor data is required at a very fast rate from every corner of the power system network. Accordingly, a strong two-way communication between various smart grid applications and the system devices are required. As the power system resources are scattered in a wide geography, the measurement sensing devices need to have TCP/IP layer enabled so that the data can be routed over a long distance. Using Internet of Things (IoT) enabled devices, the said objective can be achieved in the smart grid network. However, with the large-scale deployment of IoT devices, the IoT data received at the smart grid control center will be very large. Further, the data sent by IoT devices has large volume, high velocity, high degree of uncertainty, and large variety of data. Therefore, such kind of data can be classified as big data. Due to such a huge size of big data received at the control center, analysis of the received data in real-time is really a challenging and complex task. To address this, various artificial intelligence and machine learning tools are required to be developed. The objective this tutorial is to discuss the challenges and the software engineering solutions to these challenges. The tutorial will talk about –
Bio: Dr. Ankush Sharma is currently working as associate professor in the department of
electrical engineering at Indian Institute of Technology (IIT) Kanpur, India. Prior to that, he was
working as Assistant Professor at IIT Bhubaneswar, India. In addition to academic experience of
around 4 years, he also has close to 16 years of software industry experience, primarily in the
Power system and smart grid domains. He holds Ph.D. and M. Tech. degrees in Electrical
Engineering from IIT Kanpur and B. Tech. degree in Electrical Engineering from Harcourt
Butler Technological Institute Kanpur. He has been Project Management professional (PMP®)
certified in 2009 from Project Management Institute (PMI), USA and holds MBA degree in