检索结果-内蒙古大学图书馆

Analysis of classifier training on synthetic data for cross-domain datasets

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cortés, Andoni Rodríguez, Clemente Vélez, Gorka Barandiarán, Javier Nieto, Marcos Deparment of Intelligent Transportation Systems and Engineering Deparment Vicomtech Paseo Mikeletegi 57 San Sebastian20009 Spain Dpt. of Computer Architecture San Sebastian Spain

A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts of data costs considerable time, material and effort. To mitigate this problem, the use of synthetic images combined with real data is a popular approach, widely adopted in the scientific community to effectively train various detectors. In this study, we examined the potential of synthetic data-based training in the field of intelligent transportation systems. Our focus is on camera-based traffic sign recognition applications for advanced driver assistance systems and autonomous driving. The proposed augmentation pipeline of synthetic datasets includes novel augmentation processes such as structured shadows and gaussian specular highlights. A well-known DL model was trained with different datasets to compare the performance of synthetic and real image-based trained models. Additionally, a new, detailed method to objectively compare these models is proposed. Synthetic images are generated using a semi-supervised errors-guide method which is also described. Our experiments showed that a synthetic image-based approach outperforms in most cases real image-based training when applied to cross-domain test datasets (+10% precision for GTSRB dataset) and consequently, the generalization of the model is improved decreasing the cost of acquiring images. © 2024, CC BY-NC-ND.

关键词： Advanced driver assistance systems

Predictive and diagnosis models of stroke from hemodynamic signal monitoring

学校读者我要写书评

暂无评论

arXiv 2023年

作者： García-Terriza, Luis Risco-Martín, José L. Roselló, Gemma Reig Ayala, José L. Dpt. of Computer Architecture and Automation Complutense University of Madrid Spain Stroke Care Unit Hospital Universitario de La Princesa Spain

This work presents a novel and promising approach to the clinical management of acute stroke. Using machine learning techniques, our research has succeeded in developing accurate diagnosis and prediction real-time models from hemodynamic data. These models are able to diagnose stroke subtype with 30 minutes of monitoring, to predict the exitus during the first 3 hours of monitoring, and to predict the stroke recurrence in just 15 minutes of monitoring. Patients with difficult access to a CT scan, and all patients that arrive at the stroke unit of a specialized hospital will benefit from these positive results. The results obtained from the real-time developed models are the following: stroke diagnosis around 98% precision (97.8% Sensitivity, 99.5% Specificity), exitus prediction with 99.8% precision (99.8% Sens., 99.9% Spec.) and 98% precision predicting stroke recurrence (98% Sens., 99% Spec.). © 2023, CC BY-SA.

关键词： Forecasting

Adiabatic training for Variational Quantum Algorithms

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Acosta, Ernesto Gutiérrez, Carlos Cano Botella, Guillermo Campos, Roberto Dpt. Computer Science and AI University of Granada Granada18071 Spain Computer Architecture and Automation Department Complutense University of Madrid Madrid28040 Spain Theoretical Physics Department Complutense University of Madrid Madrid28040 Spain

This paper presents a new hybrid Quantum Machine Learning (QML) model composed of three elements: a classical computer in charge of the data preparation and interpretation;a Gate-based Quantum computer running the Variational Quantum Algorithm (VQA) representing the Quantum Neural Network (QNN);and an adiabatic Quantum computer where the optimization function is executed to find the best parameters for the VQA. As of the moment of this writing, the majority of QNNs are being trained using gradient-based classical optimizers having to deal with the barren-plateau effect [5]. Some gradient-free classical approaches such as Evolutionary Algorithms have also been proposed to overcome this effect [4]. However, to the knowledge of the authors, adiabatic quantum models have not been used to train VQAs. The paper compares the results of gradient-based classical algorithms against adiabatic optimizers showing the feasibility of integration for gate-based and adiabatic quantum computing models, opening the door to modern hybrid QML approaches for High Performance Computing. © 2024, CC BY-NC-SA.

关键词： Quantum computers

Decision Support Framework for Automating the Optimization of Edge Computing Federations

学校读者我要写书评

暂无评论

Decision Support Framework for Automating the Optimization o...

Annual Modeling and Simulation Conference (ANNSIM)

作者： Antonio F. Rodríguez-Liria Román Cárdenas Patricia Arroba José M. Moya José L. Risco-Martín Gabriel Wainer Laboratorio de Sistemas Integrados (LSI) CCS–Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain Dpt. of Systems and Computer Engineering Carleton University Ottawa ON Canada

Modern IoT applications present demanding Quality of Service (QoS) requirements that can no longer rely on a centralized solution to offload compute-intensive tasks. Edge Computing tackles these limitations by extending the Cloud to the edge of the network. However, the distributed and complex nature of Edge infrastructures introduces new technical challenges that must be addressed to develop a successful solution. Modeling, Simulation, and Optimization (M&S&O) tools can aid in the automatic design of modern Edge deployments. Here we present a decision support module that allows practitioners to automatically improve aspects of their Edge infrastructure by applying different optimization algorithms, such as simulated annealing, tabu search, and stochastic hill climbing. Furthermore, the structure of this module allows us to extend the available optimization methods if needed. We illustrate how this tool can help us to improve energy consumption policies of Edge Computing facilities and reduce their operational costs.

关键词：

Multi-objective Optimization of Energy Consumption and Execution Time in a Single Level Cache Memory for Embedded Systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Álvarez, Josefa Díaz Risco-Martín, José L. Manuel Colmenar, J. Centro Universitario de Mérida Universidad de Extremadura Mérida06800 Spain Dpt. of Computer Architecture and Automation Complutense University of Madrid C/Prof. José García Santesmases 9 Madrid28040 Spain Dpt. of Computer Science Rey Juan Carlos University Móstoles28933 Spain

Current embedded systems are specifically designed to run multimedia applications. These applications have a big impact on both performance and energy consumption. Both metrics can be optimized selecting the best cache configuration for a target set of applications. Multi-objective optimization may help to minimize both conflicting metrics in an independent manner. In this work, we propose an optimization method that based on Multi-Objective Evolutionary Algorithms, is able to find the best cache configuration for a given set of applications. To evaluate the goodness of candidate solutions, the execution of the optimization algorithm is combined with a static profiling methodology using several well-known simulation tools. Results show that our optimization framework is able to obtain an optimized cache for Mediabench applications. Compared to a baseline cache memory, our design method reaches an average improvement of 64.43% and 91.69% in execution time and energy consumption, respectively. © 2023, CC BY-SA.

关键词： Evolutionary algorithms

A Survey of Recent Developments in Testability, Safety and Security of RISC-V Processors

学校读者我要写书评

暂无评论

A Survey of Recent Developments in Testability, Safety and S...

IEEE European Test Symposium (ETS)

作者： Jens Anders Pablo Andreu Bernd Becker Steffen Becker Riccardo Cantoro Nikolaos I. Deligiannis Nourhan Elhamawy Tobias Faller Carles Hernandez Nele Mentens Mahnaz Namazi Rizi Ilia Polian Abolfazl Sajadi Mathias Sauer Denis Schwachhofer Matteo Sonza Reorda Todor Stefanov Ilya Tuzov Stefan Wagner Nuša Zidarič Institute of Smart Sensors University of Stuttgart Stuttgart Germany Universitat Politècnica de València Spain Dpt. of Computer Science University of Freiburg Freiburg Germany Institute of Software Engineering University of Stuttgart Stuttgart Germany Dpt. of Control and Computer Engineering Politecnico di Torino Turin Italy Institute of Computer Architecture and Computer Engineering University of Stuttgart Stuttgart Germany LIACS Leiden University Leiden Netherlands Advantest Europe Boeblingen Germany

With the continued success of the open RISC-V architecture, practical deployment of RISC-V processors necessitates an in-depth consideration of their testability, safety and security aspects. This survey provides an overview of recent developments in this quickly-evolving field. We start with discussing the application of state-of-the-art functional and system-level test solutions to RISC-V processors. Then, we discuss the use of RISC-V processors for safety-related applications; to this end, we outline the essential techniques necessary to obtain safety both in the functional and in the timing domain and review recent processor designs with safety features. Finally, we survey the different aspects of security with respect to RISC-V implementations and discuss the relationship between cryptographic protocols and primitives on the one hand and the RISC-V processor architecture and hardware implementation on the other. We also comment on the role of a RISC-V processor for system security and its resilience against side-channel attacks.

关键词：

Modeling methodology for the accurate and prompt prediction of symptomatic events in chronic diseases

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pagán, Josue Risco-Martín, José L. Moya, José M. Ayala, José L. Dpt. of Computer Architecture and Automation Complutense University of Madrid Madrid28040 Spain CCS-Center for Computational Simulation Campus de Montegancedo UPM Boadilla del Monte28660 Spain LSI-Integrated Systems Laboratory Technical University of Madrid Madrid28040 Spain

Prediction of symptomatic crises in chronic diseases allows to take decisions before the symptoms occur, such as the intake of drugs to avoid the symptoms or the activation of medical alarms. The prediction horizon is in this case an important parameter in order to fulfill the pharmacokinetics of medications, or the time response of medical services. This paper presents a study about the prediction limits of a chronic disease with symptomatic crises: the migraine. For that purpose, this work develops a methodology to build predictive migraine models and to improve these predictions beyond the limits of the initial models. The maximum prediction horizon is analyzed, and its dependency on the selected features is studied. A strategy for model selection is proposed to tackle the trade off between conservative but robust predictive models, with respect to less accurate predictions with higher horizons. The obtained results show a prediction horizon close to 40 minutes, which is in the time range of the drug pharmacokinetics. Experiments have been performed in a realistic scenario where input data have been acquired in an ambulatory clinical study by the deployment of a non-intrusive Wireless Body Sensor Network. Our results provide an effective methodology for the selection of the future horizon in the development of prediction algorithms for diseases experiencing symptomatic crises. © 2024, CC BY-SA.

关键词： Forecasting

A HYPOTHESIS-DRIVEN METHOD BASED ON MACHINE LEARNING FOR NEUROIMAGING DATA ANALYSIS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Saez, Juan Manuel Gorriz Clemente, R. Martin Puntonet, C.G. Ortiz, A. Ramirez, J. Suckling, John Dasci Institute University of Granada Granada Spain Dpt. Signal Theory and Communications University of Seville Seville Spain Dpt. Computer Architecture and Tech. University of Granada Granada Spain Dpt. Communication Engineering University of Malaga Malaga Spain Department of Psychiatry University of Cambridge Cambridge United Kingdom

There remains an open question about the usefulness and the interpretation of Machine learning (MLE) approaches for discrimination of spatial patterns of brain images between samples or activation states. In the last few decades, these approaches have limited their operation to feature extraction and linear classification tasks for between-group inference. In this context, statistical inference is assessed by randomly permuting image labels or by the use of random effect models that consider between-subject variability. These multivariate MLE-based statistical pipelines, whilst potentially more effective for detecting activations than hypotheses-driven methods, have lost their mathematical elegance, ease of interpretation, and spatial localization of the ubiquitous General linear Model (GLM). Recently, the estimation of the conventional GLM has been demonstrated to be connected to an univariate classification task when the design matrix is expressed as a binary indicator matrix. In this paper we explore the complete connection between the univariate GLM and MLE regressions. To this purpose we derive a refined statistical test with the GLM based on the parameters obtained by a linear Support Vector Regression (SVR) in the inverse problem (SVR-iGLM). Subsequently, random field theory (RFT) is employed for assessing statistical significance following a conventional GLM benchmark. Experimental results demonstrate how parameter estimations derived from each model (mainly GLM and SVR) result in different experimental design estimates that are significantly related to the predefined functional task. Moreover, using real data from a multisite initiative the proposed MLE-based inference demonstrates statistical power and the control of false positives, outperforming the regular GLM. © 2022, CC BY.

关键词： Magnetic resonance imaging

A New Family of XDEVS Simulators for Enhanced Performance

学校读者我要写书评

暂无评论

A New Family of XDEVS Simulators for Enhanced Performance

Annual Modeling and Simulation Conference (ANNSIM)

作者： Román Cárdenas Patricia Arroba José L. Risco-Martín Laboratorio de Sistemas Integrados (LSI) CCS–Center for Computational Simulation Universidad Politécnica de Madrid ETSI Telecomunicación Madrid Spain Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain

Modeling and Simulation (M&S) techniques are extensively used for analyzing complex systems. Among different approaches, the Discrete EVent System specification (DEVS) mathematical formalism presents a robust methodology for defining complex models. The xDEVS framework is a cross-platform tool that provides a uniform Application Programming Interface (API) to simulate DEVS-based models using different programming languages like C++, Java, or Python. However, executing DEVS models on embedded devices equipped with small processors usually requires lower-level programming languages. This paper introduces xDEVS/Rust and xDEVS/C, two new xDEVS interfaces written in Rust and C, respectively. These new implementations bring xDEVS closer to supporting the execution of DEVS models in embedded systems. Also, they feature remarkably high performance, making them a valuable option for simulating complex systems in traditional platforms. We illustrate how competitive these new implementations are by comparing them with some of the fastest state-of-the-art simulators.

关键词：