AI-enabled UAVs and Multimodal Monitoring for Protected and Controlled Environment (PACE) Wed, Jul 17 2024 Research artificial intelligence IoT UAV smart agriculture This project aims to utilize advanced technologies for UAVs to enhance the efficiency, accuracy, and responsiveness of crop monitoring and management within the diverse PACE settings. The primary objectives revolve around employing a fleet of micro-UAVs equipped with cameras and LiDAR sensors to capture high-resolution images and 3D point clouds and perform multi-layered AI analysis. While cameras offer visual insights into surface-level plant health and characteristics, LiDAR provides deeper insights about plant physical attributes for a more comprehensive crop assessment. This project is
Circuits and Systems for Efficient Machine Learning and Artificial Intelligence Wed, Jul 17 2024 Research artificial intelligence machine learning hardware design Machine Learning (ML) and Artificial Intelligence (AI) applications require the use of more and more advanced algorithms for extracting meaningful information from increasingly (and sometimes incredibly) large sets of data. While the algorithmic part has recently seen significant advances (as for instance through the adoption of Deep or Convolutional Neural Networks), it sometimes comes at the cost of high computational complexity which hinders their straightforward implementability. This activity aims at advancing in this direction by: proposing architectures to reduce the computational cost
Circuits, Systems, and Algorithms for Low-power Signal Processing in IoT Nodes Implementation Wed, Jul 17 2024 Research IoT compressed sensing anomaly detection In the IoT paradigm the low-power signal processing, either analog of digital, is a key-enabling technology. Many unconventional processing techniques, either based on a statistical analysis or not, have been introduced in the effort of being able to complete a task with the lowest possible energy. A first example is given by the Compressed Sensing, an acquisition technique which relies on the sparsity of the underlying signals, to enable sampling below the classical Nyquist rate. The advantages with respect to the above “classical” technique is to transfer complexity from the acquisition
Design, Analysis, and Control Methodologies for Switching Power Converters with Improved Compatibility Properties Wed, Jul 17 2024 Research DC-DC power converters Resonant dc–dc converters A consequence of adopting IoT technologies in the area of industrial automation is to integrate smart device capabilities such as sensing, communication, knowledge management, decision-making, control, actuation, into advanced automation systems of the future in order to achieve smart maintenance and smart production execution. Yet, Industrial platforms impose stringent requirements for legacy compatibility, and this in turn imposes constraints on the switching power supply units for the IoT nodes: supplying the desired voltage/current levels with high efficiency; electrical isolation to
Implementation and Statistical Characterization of High Efficiency True Random Number Generators (RNGs) for Cryptographic Applications Wed, Jul 17 2024 Research Random number generation Cryptography Analog-to-digital converters chaos Practical implementations of RNGs can be classified into two major categories, namely pseudo-RNGs and physical-RNGs. Pseudo-RNGs are deterministic, numeric algorithms that expand short seeds into long bit sequences. Conversely, physical-RNGs rely on microscopic processes resulting in macroscopic observables which can be regarded as random noise (quantum, thermal,…). Pseudo-RNGs generally depart more from the ideal specifications: are based on finite memory algorithms, thus exhibit periodic behaviors and generate correlated samples and are therefore unsuitable for data security and cryptography
Spintronics for AI Wed, Jul 17 2024 Research In I2S, we are pushing the boundaries of innovation at the intersection of biomedical applications, neuromorphic computing, spintronics, and hardware security. Our research focuses on developing intelligent biomedical devices that enable precision medicine, personalized treatment plans, and disease diagnosis through spintronics platforms. By combining neuromorphic computing's ability to learn and adapt with spintronics' unique properties for information processing, we are creating novel solutions for secure data storage and transmission. Our work in hardware security ensures the integrity of
Spintronics for Biomedical Applications Sun, Jul 28 2024 Research Recent breakthroughs in Tunneling Magnetoresistive (TMR) sensors have shown potential for spintronic devices in biomedical applications, offering heightened sensitivity and reduced size. Spintronics, a field at the intersection of electronics and quantum mechanics, harnesses the spin of electrons for information processing and sensing. In biomedical contexts, spintronic devices are instrumental in developing advanced biomolecular and biomedical platforms. These devices enable susceptible detection of biomolecules, facilitating precise diagnostics and monitoring of biological processes. At I2S
Spintronics-based Hardware Security Primitives Sun, Jul 28 2024 Research Integrated circuits are vital for trust in cybersecurity systems, but globalization has increased security risks. Many IC companies rely on untrusted foundries, leading to threats like hardware Trojans, reverse engineering, side-channel attacks, IP piracy, and counterfeiting. These risks highlight the critical link between cybersecurity and hardware security. Cybersecurity relies on hardware security as its foundation, mitigating threats, supporting trust anchors like TPMs and PUFs, ensuring data protection, enabling robust authentication, and defending against physical attacks. Emerging
Sustainable and Scalable AI-Driven Traffic Monitoring Using Advanced Sensor Technologies Mon, Dec 4 2023 - Thu, Dec 26 2024 Research The precise monitoring and analysis of traffic situations at urban intersections have garnered significant attention in recent years, particularly with the advent of AI technologies that promise to revolutionize urban mobility. This challenge, central to effective urban traffic management, has wide-ranging implications for improving safety, reducing congestion, and optimizing traffic flow in cities worldwide. Traditional methods such as loop detectors and CCTV-based monitoring have shown potential in managing traffic, but they face practical limitations such as poor performance in low light
