Abstract:

In this talk, first we introduce Cryptocurrency. We then discuss the underlying technology of Cryptocurrency i.e., Blockchain. Afterwards, we discuss its historical development, its architecture, where it is used and how it is implemented. We will also cover some technical details of these technologies. Finally, we discuss the future of Cryptocurrency in Pakistan.

Abstract:

Machine learning applications for prognosis and health management usually face data unavailability, complexity, and drift due to the massive and rapid evolution of data volume, velocity, and variety (3V). Advances in deep learning have brought many improvements in this area, providing generative modeling, nonlinear abstractions, and adaptive learning to meet these challenges. Deep learning aims to learn from representations that provide a coherent abstraction of the original feature space, enabling it to be more meaningful and less complex. However, the data complexity associated with various distortions, such as higher noise levels, remains challenging to overcome. In this context, recurrent expansion algorithms have recently been introduced to explore deeper representations than ordinary deep networks, enabling even better feature mapping. In contrast to traditional deep learning, where abstracting inputs extract meaningful representations, recurrent expansion merges entire deep networks into one, allowing inputs, maps, and estimated targets to be explored as primary sources of learning. These three sources of information provide additional knowledge about their interactions in a deep network. Furthermore, recurrent expansion provides the ability to investigate the estimated targets of multiple networks and learn significant features, improving its accuracy with each round.

Abstract:

Serious games, games designed with objectives other than entertainment, have emerged as powerful tools across various fields, from education and healthcare to corporate training and social awareness. This keynote address will provide an overview of serious games research; methodologies, design frameworks and models and evaluation approaches beside exploring how technological advancements such as AI, virtual reality (VR), and augmented reality (AR) have transformed the design and application of these games. We will examine current trends, including interdisciplinary collaboration, the role of games in education (game-based learning, GBL) , healthcare and training besides the growing importance of effective assessment and evaluation methods. We will address the challenges of serious game, highlight key issues such as balancing engagement with educational effectiveness, interpreting and mapping content to game design elements and evaluation methods. Looking forward, we will explore how emerging technologies and new research partnerships will shape the future of serious games, with potential applications in new areas such as climate change awareness and civic engagement. The keynote will conclude with a call to action for researchers, developers, and stakeholders to collaborate and innovate, leveraging the full potential of serious games to drive positive change in society. Through this comprehensive exploration, the address aims to inspire ongoing research and development in this dynamic and impactful field.

Abstract:

Abstract:

Query processing, a technique for retrieving objects from a database in a reliable and efficient way; has achieved tremendous success at both research and industry levels. It operates by retrieving only those data points that strictly satisfy the conditions specified in the query or returning an empty result if otherwise. Recent developments in query processing attempt to relax these stringent requirements, by retrieving the best, most preferred data points from a database. These queries known as skyline queries rely on the notion of Pareto dominance, have achieved significant success, as they are widely used in applications related to multi-criteria decision making; wherein several conflicting criteria need to be evaluated in the process of making decision. It is more challenging when there are too many criteria to be considered while the data points to be analysed are those generated and transmitted from sensing devices also known as sensing data. This group of sensors which constitutes a wireless sensor network monitors data points at different sites and transmits these data points to a central site for further analysis. Inevitably, the network lifetime is reduced due to energy consumption for transmitting these sensing data. Furthermore, with the growth of network sizes, the sensing data become massive. Intuitively, it is crucial to reduce the transmission energy consumption for energy efficient of skyline query computation by filtering the unwarranted data points in the sensor networks.

Abstract:

In the rapidly evolving energy landscape, microgrids are emerging as vital components for achieving energy resilience, efficiency, and sustainability. This talk will focus on the transformative role of data-driven approaches in enhancing microgrid energy management systems. By utilizing advanced forecasting techniques, real-time optimization, and integration of IoT technologies, the operational efficiency of microgrids can be improved. The presentation will delve into key areas such as energy demand and electricity price forecasting, renewable energy price forecasting, and reinforcement learning applications for adaptive energy management. Moreover, it will address the economic, social, and environmental objectives that guide energy management strategies, alongside critical challenges such as higher renewable energy integration, cybersecurity concerns, data management complexities, and the impact of climate change on energy systems. This talk will offer valuable insights into the future of microgrid technology and its role in building smarter, more sustainable energy infrastructures

Abstract:

The integration of electric vehicles (EVs) into power grid infrastructure presents a transformative opportunity for both the energy and transportation sectors; however, it also introduces significant challenges. As EV adoption rises, the demand for effective grid management solutions becomes increasingly critical, particularly to address the variable energy consumption patterns and the stochastic nature of EV users associated with large-scale charging. This talk will discuss the opportunities presented by technologies such as vehicle-to-grid (V2G), decentralized energy storage, and the alignment of EV charging with renewable energy sources. It will also explore challenges related to grid stability, electric load management, communication infrastructure, standardized services, and e-mobility data space management. By leveraging smart grid technologies, standardized protocols, and data analytics, we can turn these challenges into opportunities for a sustainable, resilient, and efficient energy system. The session aims to provide valuable insights for stakeholders in energy management, urban planning, and policy-making, outlining a roadmap for a future where EVs and power grids are seamlessly integrated.

Abstract:

In the word’s of Andrew Ng, Stanford Professor and Chief AI Scientist at Google Brain “Every time there’s a technological disruption, it gives people an opportunity to remake large parts of the world to be better for future generations to grow up in.” Today, we are faced with another technological interruption with Industry 4.0, where physical systems have gone online in the form of cyber physical systems giving birth to the smart factories known as Industry 4.0. Among the prominent technologies shaping the future are Robotics and AI. The late 1800s and early 1900s was an exciting time for Physics, where we had a breakthrough in understanding the laws of physics every few days. Today, it’s an interesting time for AI. Be it generation of photo realistic images, scene explanation, deep conversations or being context aware, the AI systems of today have forced chief scientists to believe that such systems are at some level of consciousness and sentience.

Abstract:

Artificial Intelligence (AI) has revolutionized modern healthcare in various domains. AI is enhancing diagnostics, treatment planning, and patient management through technologies such as machine learning (ML), natural language processing (NLP) and robotics. AI systems analyze medical data including radiological imaging, pathological data and patient records, to detect diseases, predict outcomes and personalize treatments, improving accuracy and early disease detection. AI-driven tools also enable remote patient monitoring and telemedicine, increasing access to care. In drug discovery, AI accelerates the identification of new therapies. These innovations result in increased efficiency, reduced costs, and improved patient outcomes. AI is enhancing healthcare not only in early and accurate diagnosis but also in disease prediction, patient profiling, and personalized medicine discovery. However, ethical challenges still persist, like ensuring data privacy, preventing bias in AI models and navigating evolving regulatory frameworks. Collaboration between AI developers and health professionals is critical to overcoming these challenges and unlocking AI's full potential in advancing predictive, preventive, and personalized medicine. Despite the obstacles, AI’s role in health care is anticipated to expand, offering significant benefits to patients and providers equally.

Abstract:

Computer Vision is a field of Artificial Intelligence that allows computers to obtain meaningful data from visual inputs such as images and videos The insights gained from computer vision are then used to take automated actions. Early detection of cancer is one of the most important solutions through computer vision. In order to reduce the diagnosis error rate, the idea of introducing computer vision techniques is gaining increasing support In this talk, recent advances in Computer Vision techniques for Oncology and Pathology will be discussed including Prostate cancer classification through computer vision, abnormalities and disease detection in Gastro-Intestinal Tract Images and Predicting Drug Response to Cancer Cell Lines using Deep Learning.