A5091197122- Parallel Computing and Optimization Techniques
- Radiation Effects in Electronics
- Low-power high-performance VLSI design
- Embedded Systems Design Techniques
- Advanced Memory and Neural Computing
- Green IT and Sustainability
- Energy Efficient Wireless Sensor Networks
- Real-Time Systems Scheduling
- Distributed systems and fault tolerance
- Context-Aware Activity Recognition Systems
- Distributed and Parallel Computing Systems
- Structural Health Monitoring Techniques
- Advancements in Semiconductor Devices and Circuit Design
- IoT and Edge/Fog Computing
- Energy Harvesting in Wireless Networks
- Power Systems Fault Detection
- Ferroelectric and Negative Capacitance Devices
- Underwater Vehicles and Communication Systems
- Indoor and Outdoor Localization Technologies
- Cloud Computing and Resource Management
- Advanced Data Storage Technologies
- Network Time Synchronization Technologies
- Numerical Methods and Algorithms
- Caching and Content Delivery
- VLSI and FPGA Design Techniques
Hospital de Clínicas da Unicamp
2018-2024
Universidade Estadual de Campinas (UNICAMP)
2015-2024
University of California, Los Angeles
2010-2015
Universidade Federal de Santa Catarina
2006-2015
Software (Spain)
2006-2008
Context-awareness is the ability of software systems to sense and adapt their physical environment. Many contemporary mobile applications changing locations, connectivity states, available computational energy resources, proximity other users devices. Nevertheless, there little systematic support for context-awareness in operating systems. Because this, application developers must build own adaptation engines, dealing directly with sensors polluting code complex decisions. In this paper, we...
Abstract Photon-counting hybrid pixel detector chips, such as those based on the Medipix3RX technology, have been central to advancements in spectral and multi-dimensional imaging at synchrotron facilities. As these facilities continue improve with ongoing upgrades, there is a growing demand for large-area cameras that not only handle increased X-ray flux performances but also integrate effectively into various scientific setups minimal power consumption. This work focuses optimizing energy...
Instance and temperature-dependent power variation has a direct impact on quality of sensing for battery-powered long-running applications. We measure characterize the active leakage an ARM Cortex M3 processor show that, across temperature range 20 -60, there is 10% in power, power. introduce variability-aware duty cycling methods cycle (DC) abstraction TinyOS which allows applications to explicitly specify lifetime minimum DC requirements individual tasks, dynamically adjusts rates so that...
Time synchronization is a keystone of Wireless Sensor Networks (WSN). It fundamental to coordinate the action nodes in network and it also critical element several security mechanisms. In this paper, we discuss evaluate time strategy behind Trustful Space-Time Protocol (TSTP), which explores protocol's cross-layer architecture speculatively peek through timestamps geographic info present message headers, implementing high-accuracy clock with minimal insertion explicit messages. We protocol...
Modern integrated circuits, fabricated in nanometer technologies, suffer from significant power/performance variation across-chip, chip-to-chip and over time due to aging ambient fluctuations. Furthermore, several existing emerging reliability loss mechanisms have caused increased transient, intermittent permanent failure rates. While this variability has been typically addressed by process, device circuit designers, there a recent push towards sensing adapting the various layers of...
Position awareness is a desirable feature for many applications of Wireless Sensor Networks. The Received Signal Strength Indication radio channel provides feasible way estimating distance between nodes because its use doesn't require any additional hardware but transceiver. main drawback using RSSI instability and interference susceptibleness noticed in real environments. This work shows an evaluation implementation location algorithm wireless sensor networks presents improvements that...
Modern integrated circuits, fabricated in nanometer technologies, suffer from significant power/performance variation across-chip, chip-to-chip and over time due to aging ambient fluctuations. Furthermore, several existing emerging reliability loss mechanisms have caused increased transient, intermittent permanent failure rates. While this variability has been typically addressed by process, device circuit designers, there a recent push towards sensing adapting the various layers of...
Instance and temperature-dependent leakage power variability is already a significant issue in contemporary embedded processors, one which expected to increase importance with scaling of semiconductor technology. We measure characterize this current microprocessors, show that aware duty cycle scheduling produces 7.1× improvement sensing quality for desired lifetime. In contrast, pessimistic estimations consumption leave 61% the energy untapped, datasheet specifications fail meet required...
Approximate Computing offers enhanced energy efficiency by exploring quality relaxation on applications. Application-agnostic hardware-level techniques can provide high benefits under certain scenarios, but their integration a general-purpose architecture presents novel control challenges. We present Risk-5, an extension of the RISC-V that implements mechanisms to orchestrate multiple coexisting approximation within architecture. In approximate hardware capabilities are exposed software...
In a wireless sensor network, several nodes obtain local data and communicate among themselves in order to create global vision of an object study.The idea self-managed network low-power, autonomous devices, that collects from environment propagates information through link brought about new challenges requirements application run-time support.Several research projects have aimed at solving the problem system support for networks.However, most them failed dealing with two requirements:...
Real-time, fine-grained power consumption information enables energy optimization and adaptation for operating systems applications. Due to the high cost associated with dedicated sensors, however, most computers do not have ability measure disaggregated at a component or subsystem level. We present DiPART (Disaggregated Power Analysis in Real Time), tool estimate based on performance (event) counters single, system-wide sensor. With only one sensor overall system consumption, is able...
Abstract In this paper we summarize recent results and contributions from the NSF Expedition on Variability-Aware Software, a five year, multi-university effort to tackle problem of hardware variations its implications opportunities in software. The has made characterization online monitoring (particularly microprocessors flash memories), proposed new coding techniques for variability-tolerant storage, provided tools platforms development variability-aware software, created runtime support...
The collapse of overhead power line guyed towers is one the leading causes grid failures, subjecting electricity companies to pay considerable, high-value fines. In this way, current work proposes a novel and complete framework for remote monitoring mechanical stresses in towers. method comprises mesh network data forwarding neural networks improve performance Low-Power Lossy Networks. also considers use multiple sensors sensor fusion technique. As result, risk cable reduces, due preventive...
Position awareness is a desirable feature for many applications of Wireless Sensor Networks. The Received Signal Strength Indication radio channel provides feasible way estimating distance between nodes because its use doesnpsilat require any additional hardware but transceiver. main drawback using RSSI instability and interference susceptibleness noticed in real environments. This work shows an evaluation location algorithm wireless sensor networks presents new calibration approach that...
Embedded software often needs to be ported from one system another. This may happen for a number of reasons among which are the need using less expensive hardware or extra resources. Application portability can achieved through an architecture-independent software/hardware interface. is not straight-forward task in realm embedded systems, since they have very specific platforms. work shows how application-oriented component-based operating was developed allow and application portability....
Due to modularity and heterogeneity in wireless sensor networks sensing devices, a application developed for given platform will seldom be portable different one, unless the run-time support systems on those platforms deliver mechanisms that abstract encapsulate an adequate manner. In this article we propose software/hardware interface is able families of devices uniform fashion. We define classes based their finality (e.g. acceleration, temperature), establish common substrate each class....
Power management strategies for embedded systems typically rely on static, application driven deactivation of components (e.g. sleep, suspend), or dynamic voltage and frequency scaling. However, the design implementation these in operating system often fail to deal with real-time quality-of-service (QoS) requirements. The EPOS implements an infra-structure that supports both static (application-driven) (system-driven) power management. In this work, infrastructure is used explore energy as a...
Large-scale actuator control problems in Cyber-Physical Systems (CPSs) are often expressed within the networked optimization model. While significant advances have taken place techniques, their widespread adoption practical implementations is impeded by complexity of inter-node coordination and lack programming support that necessary for sharing information coherently between distributed concurrent controller processes. In this paper, we propose a shared memory (DSM) architecture abstracts...
RISC-V is supported by a series of design and simulation tools that enable simple instruction set customization rapid exploration application-specific accelerators. Evaluating the performance energy impact specific choices optimizations on applications remains, however, challenging. Traditional RT- or Gate-level simulation, while fairly precise, complex slow, is, therefore, typically limited to small fractions code. Functional faster, imprecise lacks detailed information presented...
In this work, we propose a framework capable of transparently switching between multiple hardware and software implementations embedded system components to cope with adapt dynamic runtime characteristics such as power, throughput quality service. The reconfiguration process is decomposed into small steps that it preemptable, transparent, compliant real-time requirements. We present Private Automatic Branch eXchange(PABX) case study for the framework, investigate three its components: an...