Gianmarco Cerutti
A5061643938- Particle Detector Development and Performance
- Radiation Detection and Scintillator Technologies
- Speech and Audio Processing
- Particle physics theoretical and experimental studies
- Music and Audio Processing
- Astrophysics and Cosmic Phenomena
- Music Technology and Sound Studies
- IoT-based Smart Home Systems
- Energy Efficient Wireless Sensor Networks
- Speech and dialogue systems
- Video Surveillance and Tracking Methods
- Parallel Computing and Optimization Techniques
- Particle Accelerators and Free-Electron Lasers
- IoT and Edge/Fog Computing
- Radioactivity and Radon Measurements
- Embedded Systems Design Techniques
- Image Enhancement Techniques
- Neutrino Physics Research
- Experimental and Theoretical Physics Studies
- Scientific Measurement and Uncertainty Evaluation
- Advanced Radiotherapy Techniques
- Context-Aware Activity Recognition Systems
- Gyrotron and Vacuum Electronics Research
- Neural Networks and Applications
- Radioactive Decay and Measurement Techniques
Fondazione Bruno Kessler
2018-2022
ETH Zurich
2020
Sapienza University of Rome
2017-2018
European Organization for Nuclear Research
1983-1996
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, energy resources. This challenge discourages IoT implementation, where efficient use of resources required. However, current embedded technologies microcontrollers have increased their capabilities without penalizing efficiency. paper addresses application sound event at edge, optimizing techniques on...
Detection of human presence is a key feature in Human Computer Interaction. Solutions based on cameras are attractive, but require computer vision techniques to extract meaningful data, which can be expensive from computational point view. In this work, we present new system that merges low resolution thermal camera with advanced extraction such as Convolutional Neural Networks. We demonstrate the possibility adapt their execution resource-constrained platform without significant loss...
Keyword spotting (KWS) is a crucial function enabling the interaction with many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as human-computer interface. For applications, KWS entry point for interactions device and, thus, an always-on workload. Many are mobile and their battery lifetime heavily impacted by continuously running services. similar services thus focus when optimizing overall power consumption. This work addresses...
FPGA-synthesizable soft-processor cores are commonly used in many digital system applications with low-medium production volume, to control heterogeneous dedicated computational units and I/O units. In such contexts, the inherently multi-tasking nature of processor operation demands for a cost-effective energy-efficient multi-threaded execution, either as multi-core architecture or single-core. This work presents an experimental exploration microarchitecture design solutions soft core...
A ring imaging Cherenkov (RICH) detector system has been built and is now in full operation within the DELPHI experiment. Large data samples of Z/sup 0/ decays are being collected with good resolution on observed angles. Several studies using RICH have already performed limited samples. Disturbance caused by shrinkage polymeric construction materials migration radiator substance reported. These effects counteracted do not endanger quality data.< <ETX...
Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on deep neural networks (DNNs) are very effective, but highly demanding terms of memory, power, throughput when targeting ultra-low power always-on devices.
Deploying Internet of Things (IoT) in our cities will enable them to become smarter, thanks the connection everything everywhere, such as smart meters, street lighting, trash bin sensors, parking areas. However, a centralized-architecture approach, where all sensors and actuators send receive data from cloud, is not sustainable terms both amount flooding cloud energy required keep these alive. This particularly true field vision be handled transmitted can high, while real information we are...
One quarter of the Forward Ring Imaging Cherenkov (Forward RICH) detector has been installed and operated in DELPHI experiment. The covers forward-backward regions (15 degrees < theta <35 ). Two radiator systems are used for particle identification momentum range up to 40 GeV/c, i.e., a liquid perfluorohexane perfluorobutane gas. UV-photons with wavelengths from approximately 170 nm 200 (7.3-6.2 eV) detected high efficiency. total active area photon is 8 m/sup 2/.< <ETX...
A prototype module of a High density Projection Chamber (HPC) has been tested in an electron beam. The HPC, with the shower conversion separated from charge collection, offers simple, homogeneous large volume detector energy resolution 12.5%/√E and exceptionally fine granularity both along transverse to axis. results test are presented together description calorimeter system.
The Forward Ring Imaging Cherenkov detector covers both end-cap regions of the DELPHI experiment at LEP in polar angle 15/spl deg/>
Keyword spotting (KWS) is a crucial function enabling the interaction with many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as human-computer interface. For applications, KWS entry point for interactions device and, thus, an always-on workload. Many are mobile and their battery lifetime heavily impacted by continuously running services. similar services thus focus when optimizing overall power consumption. This work addresses...
Keyword spotting (KWS) is a crucial function enabling the interaction with many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as human-computer interface. For applications, KWS entry point for interactions device and, thus, an always-on workload. Many are mobile and their battery lifetime heavily impacted by continuously running services. similar services thus focus when optimizing overall power consumption. This work addresses...