Miquel Roca

Dr. Miquel Roca


Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
CFChristiam Camilo Franco Frasser
Christiam Camilo Franco Frasser
PLPablo Linares-Serrano
Pablo Linares-Serrano
IRIván Díez de Los Ríos
Iván Díez de Los Ríos
AMAlejandro Morán
Alejandro Morán
ESErik S. Skibinsky-Gitlin
Erik S. Skibinsky-Gitlin
Josep L. RossellóJosep L. Rosselló
Josep L. Rosselló
Edge artificial intelligence (AI) is receiving a tremendous amount of interest from the machine learning community due to the ever-increasing popularization of the Internet of Things (IoT). Unfortunately, the incorporation of AI characteristics to edge computing devices presents the drawbacks of being power and area hungry for typical deep learning techniques such as convolutional neural networks (CNNs). In this work, we propose a power-and-area efficient architecture based on the exploitation of the correlation phenomenon in stochastic computing (SC) systems. The proposed architecture solves the challenges that a CNN implementation with SC (SC-CNN) may present, such as the high resources used in binary-to-stochastic conversion, the inaccuracy produced by undesired correlation between signals, and the complexity of the stochastic maximum function implementation. To prove that our architecture meets the requirements of edge intelligence realization, we embed a fully parallel CNN in a single field-programmable gate array (FPGA) chip. The results obtained showed a better performance than traditional binary logic and other SC implementations. In addition, we performed a full VLSI synthesis of the proposed design, showing that it presents better overall characteristics than other recently published VLSI architectures.

25 October 2019 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
ACAlejandro Morán Costoya
Alejandro Morán Costoya
CFChristiam Camilo Franco Frasser
Christiam Camilo Franco Frasser
MRMiquel Roca
Miquel Roca
Josep L. RossellóJosep L. Rosselló
Josep L. Rosselló

22 December 2022 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
ACAlejandro Morán Costoya
Alejandro Morán Costoya
LPLuis Parrilla
Luis Parrilla
MRMiquel Roca
Miquel Roca
JFJoan Font
Joan Font
EIEugeni Isern
Eugeni Isern
VCVincent Canals
Vincent Canals
Nowadays Internet of Things (IoT) and mobile systems use more and more Machine Learning based solutions, which implies a high computation cost with a low energy consumption. This is causing a revival of interest in unconventional hardware computing methods capable of implementing both linear and nonlinear functions with less hardware overhead than conventional fixed point and floating point alternatives. Particularly, this work proposes a novel Radial Basis Function Neural Network (RBF-NN) hardware implementation based on Stochastic Computing (SC), which applies probabilistic laws over conventional digital gates. Several complex functions design to implement RBF-NN are presented and theoretically analyzed, such as the squared Euclidean distance and the stochastic Gaussian kernel similarity function between input samples and prototypes. The efficiency and performance of the methodology is tested over well-known pattern recognition tasks, including the MNIST dataset. The results show a low-cost methodology in terms of logic resources and power, along with an inherent capability to implement complex functions in a simple way. This methodology enables the implementation of massively parallel large scale RBF-NN with relatively low hardware requirements while maintaining 96.20% accuracy, which is nearly the same for the floating point and fixed point models (96.4% and 96.25%, respectively).

19 November 2002
Verified
Conference Paper
Open access
JSJaume Segura
Jaume Segura
MRMiquel Roca
Miquel Roca
DMD. Mateo
D. Mateo
ARA. Rubio
A. Rubio
I/sub DDQ/ testing is a powerful strategy for detecting defects that do not alter the logic behavior of CMOS ICs. Such a technique is very effective especially in the detection of bridging defects although some opens can be also detected. However, an important set of open and parametric defects escape quiescent power supply current testing because they prevent current elevation. Extending the consumption current testing time, from the static period to the dynamic one (i.e. considering the transient current), defects not covered with I/sub DDQ/ can be detected. Simulations using an on-chip sensor show that this technique can reach a high coverage for defects preventing current and also for those raising the static power consumption.

1 December 2021 in Electronics
Verified
Journal Article
Open access
PDF file
CFChristiam Camilo Franco Frasser
Christiam Camilo Franco Frasser
MRMiquel Roca
Miquel Roca
Josep L. RossellóJosep L. Rosselló
Josep L. Rosselló
Stochastic computing (SC) is a probabilistic-based processing methodology that has emerged as an energy-efficient solution for implementing image processing and deep learning in hardware. The core of these systems relies on the selection of appropriate Random Number Generators (RNGs) to guarantee an acceptable accuracy. In this work, we demonstrate that classical Linear Feedback Shift Registers (LFSR) can be efficiently used for correlation-sensitive circuits if an appropriate seed selection is followed. For this purpose, we implement some basic SC operations along with a real image processing application, an edge detection circuit. Compared with the literature, the results show that the use of a single LFSR architecture with an appropriate seeding has the best accuracy. Compared to the second best method (Sobol) for 8-bit precision, our work performs 7.3 times better for the quadratic function; a 1.5 improvement factor is observed for the scaled addition; a 1.1 improvement for the multiplication; and a 1.3 factor for edge detection. Finally, we supply the polynomials and seeds that must be employed for different use cases, allowing the SC circuit designer to have a solid base for generating reliable bit-streams.

AGAina M Galmes-Panades
Aina M Galmes-Panades
EAEscarlata Angullo-Martínez
Escarlata Angullo-Martínez
SMSofía Mira Martínez
Sofía Mira Martínez
Miquel Bennasar-VenyMiquel Bennasar-Veny
Miquel Bennasar-Veny
RCRocío Zamanillo Campos
Rocío Zamanillo Campos
IRIgnacio Ricci-Cabello
Ignacio Ricci-Cabello
Background: Type 2 diabetes mellitus (T2DM) is a highly prevalent disease associated with an increased risk of comorbidities, premature death, and health costs. Prediabetes is a stage of glucose alteration previous to T2DM, that can be reversed. The aim of the study is to develop and evaluate a low-intensity, multifaceted, digital intervention to prevent T2DM. The intervention comprises: (1) the use of mobile health technology to send tailored text messages promoting lifestyle changes to people at risk of T2DM and (2) the provision of online education to primary healthcare physicians and nurses about management of prediabetes. Methods: In stages 1–4 we will design, develop and pilot-test the intervention. In Stage 5 we will conduct a phase II, six-month, three-arm, cluster randomized, clinical trial with 42 primary care professionals and 420 patients at risk of T2DM. Patients will be allocated to a control group (usual care), intervention A (patient messaging intervention), or intervention B (patient messaging intervention plus online education to their primary healthcare professionals). The primary outcome will be glycated haemoglobin. All the procedures obtained ethical approval in June 2021 (CEI-IB Ref No: IB4495/21PI). Discussion: Digital health interventions can effectively prevent T2DM and reduce important T2DM risk factors such as overweight or hypertension. In Spain, this type of intervention is understudied. Moreover, there is controversy regarding the type of digital health interventions that are more effective. Findings from this study may contribute to address T2DM prevention, through a low-cost and easily implementable intervention.