Convergence of Artificial Intelligence, Machine Learning, Biometrics, Cloud/Fog/Edge Computing and Internet-of-Things for Smart Environments
Prof. Vincenzo Piuri,
FIEEE, Department of computer Science Università degli Studi di Milano, Italy
Adaptability and advanced services for ambient intelligence require an intelligent technological support for understanding the current needs and the desires of users in the interactions with the environment for their daily use, as well as for understanding the current status of the environment also in complex situations. This infrastructure constitutes an essential base for smart living. Various technologies are nowadays converging to support the creation of efficient and effective infrastructures for ambient intelligence.
Artificial intelligence can provide flexible techniques for designing and implementing monitoring and control systems, which can be configured from behavioral examples or by mimicking approximate reasoning processes to achieve adaptable systems. Machine learning can be effective in extracting knowledge form data and learn the actual and desired behaviors and needs of individuals as well as the environment to support informed decisions in managing the environment itself and its adaptation to the people’s needs.
Biometrics can help in identifying individuals or groups: their profiles can be used for adjusting the behavior of the environment. Machine learning can be exploited for dynamically learning the preferences and needs of individuals and enrich/update the profile associated either to such individual or to the group. Biometrics can also be used to create advanced human-computer interaction frameworks.
Cloud computing environments will be instrumental in allowing for world-wide availability of knowledge about the preferences and needs of individuals as well as services for ambient intelligence to build applications easily. This talk will analyze the opportunities offered by these technologies to support the realization of adaptable operations and intelligent services for smart living in an ambient intelligent infrastructures
Full-Duplex Communications: Antenna Story
Prof. Dejan S. Filipovic
Antenna Research Group (ARG)
Department of Electrical, Computer, and Energy Engineering
University of Colorado Boulder, CO 80309-0425
Full-duplex (FD), also known as simultaneous transmit and receive (STAR), is a key enabling technology for the next-generation wireless systems operating in spectrum congested and contested environments. Transmitting (TX) and receiving (RX) at the same time and over the same frequency channel results in significant improvements in communication systems throughput and spectral efficiency therefore allowing greater amount of digital traffic over wireless. In defense applications, for example electronic warfare, ability to simultaneously jam and listen allows for the platform’s greater protection and enhanced situational awareness. The chief challenge associated with FD systems is the required high TX/RX isolation. For example, with 0dBm output power, over 100dB of isolation is required for a typical WiFi transceiver. If TX power is higher, the required isolation easily surpasses 130dB. This high level of isolation may be obtained with transceivers that combine multiple layers of self-interference cancellation including digital back-end processing. Since the apertures are the “eyes and ears” of RF transceivers, the antenna layer is therefore critically important. Nowadays, ~40-50% of the required isolation can be achieved with a well-designed STAR antenna subsystem inching us ever closer to meeting this, not so long ago considered impossible task.
This talk focuses on the role of antennas in FD systems. As we will show, the classification of antenna apertures, motivated by their underlining principle of operation, yield various options for system engineers. Design and performance of monostatic STAR antennas covering different bandwidths and fields of view is reviewed and their suitability for given application is discussed. Circulator-less and circulator-enabled approaches are considered and appropriate tradeoffs are discussed. The presented configurations achieve similar or better isolation levels than some other recently proposed (not necessarily true STAR) topologies, while preserving TX/RX beam and polarization integrity over the entire wide instantaneous or tunable narrow bandwidths and for different coverage requirements. What was deemed impossible a decade ago is now just around the corner.
Cloud, Fog and Mist Computing for Real-Time Applications
Resource Allocation and Scheduling Issues
Prof. Helen Karatza
Department of Informatics
Aristotle University of Thessaloniki, Greece
Due to the ongoing growth of the IoT applications, Cloud computing is inadequate for transferring huge amounts of data generated by IoT devices. Consequently, Fog and Mist computing emerged as new computing models to meet the requirements of low latency. Fog computing extends the traditional cloud model closer to where the IoT data are created. Mist computing is a lightweight type of fog computing, that brings fog capabilities even closer to the IoT infrastructure. Most of the IoT applications are delay-sensitive, therefore, appropriate resource allocation and scheduling algorithms for real-time applications are required to increase the capacity of cloud, fog and mist computing architectures.
In this talk we will highlight novel techniques and solutions to address challenges in resource allocation and scheduling of real-time applications in cloud, fog and mist systems and we will conclude with future research directions in the cloud, fog and mist computing areas.