2020 23rd Euromicro Conference on Digital System Design (DSD)最新文献_第3页

System Architecture and Security Issues of Smartphone-based Point-Of-Care Devices 基于智能手机的护理点设备的系统架构和安全问题

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00059

Christian Zajc, G. Holweg, C. Steger

引用次数: 4

Buffer Sizes Reduction for Memory-efficient CNN Inference on Mobile and Embedded Devices 在移动和嵌入式设备上减少内存效率CNN推理的缓冲区大小

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00031

S. Minakova, T. Stefanov

{"title":"Buffer Sizes Reduction for Memory-efficient CNN Inference on Mobile and Embedded Devices","authors":"S. Minakova, T. Stefanov","doi":"10.1109/DSD51259.2020.00031","DOIUrl":"https://doi.org/10.1109/DSD51259.2020.00031","url":null,"abstract":"Nowadays, convolutional neural networks (CNNs) are the core of many intelligent systems, including those that run on mobile and embedded devices. However, the execution of computationally demanding and memory-hungry CNNs on resource-limited mobile and embedded devices is quite challenging. One of the main problems, when running CNNs on such devices, is the limited amount of memory available. Thus, reduction of the CNN memory footprint is crucial for the CNN inference on mobile and embedded devices. The CNN memory footprint is determined by the amount of memory required to store CNN parameters (weights and biases) and intermediate data, exchanged between CNN operators. The most common approaches, utilized to reduce the CNN memory footprint, such as pruning and quantization, reduce the memory required to store the CNN parameters. However, these approaches decrease the CNN accuracy. Moreover, with the increasing depth of the state-of-the-art CNNs, the intermediate data exchanged between CNN operators takes even more space than the CNN parameters. Therefore, in this paper, we propose a novel approach, which allows to reduce the memory, required to store intermediate data, exchanged between CNN operators. Unlike pruning and quantization approaches, our proposed approach preserves the CNN accuracy and reduces the CNN memory footprint at the cost of decreasing the CNN throughput. Rus, our approach is orthogonal to the pruning and quantization approaches, and can be combined with these approaches for further CNN memory footprint reduction.","PeriodicalId":128527,"journal":{"name":"2020 23rd Euromicro Conference on Digital System Design (DSD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126380193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Architecture of a Public Transport Supervision System Using Hybridization Models Based on Real and Predictive Data 基于真实数据和预测数据的混合模型公共交通监控系统体系结构

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00076

A. Amrani, Hakim Arezki, David Lellouche, Vivien Gazeau, Corinne Fillol, Oussama Allali, T. Lacroix

{"title":"Architecture of a Public Transport Supervision System Using Hybridization Models Based on Real and Predictive Data","authors":"A. Amrani, Hakim Arezki, David Lellouche, Vivien Gazeau, Corinne Fillol, Oussama Allali, T. Lacroix","doi":"10.1109/DSD51259.2020.00076","DOIUrl":"https://doi.org/10.1109/DSD51259.2020.00076","url":null,"abstract":"Management of a multimodal transport network is a challenging task and operators regularly have to deal with different types of disturbances that affect the quality of service of the transport system. To support them in their decision-making, we present the architecture of a multimodal supervision system that implements monitoring, prediction of affluence, disturbances, impacts and evaluation of functionalities focusing on one or multiples lines of the network. Our system uses the real-time data of transport operators to compute several key performance indicators (KPI) in order to monitor the network status and to detect disturbances. The prediction function is used to predict passengers’ attendance at stations, incident duration and the evolution of the whole network, in particular, phenomena emerging from the interconnections linked to the affected line. Finally, we present a use case of the supervision system applied to a real-time control of a bus line belonging to a very dense and busy segment of the multimodal transport network in Ile-de-France area.","PeriodicalId":128527,"journal":{"name":"2020 23rd Euromicro Conference on Digital System Design (DSD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121833514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

MULTI-modal Imaging of FOREnsic SciEnce Evidence: MULTI-FORESEE Project 法医科学证据的多模态成像:MULTI-FORESEE项目

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00068

N. Sklavos, S. Francese

引用次数: 1

Predictive Resource Management in Energy-constrained Embedded Systems 能源约束嵌入式系统中的预测资源管理

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00035

S. Crippa, G. Massari, F. Reghenzani, M. Zanella, W. Fornaciari

{"title":"Predictive Resource Management in Energy-constrained Embedded Systems","authors":"S. Crippa, G. Massari, F. Reghenzani, M. Zanella, W. Fornaciari","doi":"10.1109/DSD51259.2020.00035","DOIUrl":"https://doi.org/10.1109/DSD51259.2020.00035","url":null,"abstract":"The current trends in Internet of Things (IoT) lead to the deployment of low-power devices covering a wide range of application scenarios. These devices have the goal of executing simple tasks, automatically, usually with strict requirements in terms of space and cost. Typically, these devices have to rely on batteries or by harvesting energy devices (e.g., solar panels), in order to operate. On the other hand, IoT devices may be equipped with powerful multi-core CPUs to achieve performance goals, making the management of the energy budget a challenging task. This requires the development of an effective management system, that takes into account current and future energy budget availability, to dynamically bound the actual allocation of processing resources. Specifically, when exploiting solar panels for power supply, we can leverage on the weather forecast, to estimate the availability of energy in the near future. This paper introduces a predictive energy budget management system, targeting multi-core based embedded platforms. Thanks to both local and large-scale weather information, our solution aims at predicting the future incoming power and, accordingly, tuning the exploitable performance level to keep the system running under any environmental condition.","PeriodicalId":128527,"journal":{"name":"2020 23rd Euromicro Conference on Digital System Design (DSD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127558330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Preliminary findings on tools for the analysis of mental activity of programmers using EEG data from portable devices 使用便携式设备的脑电图数据分析程序员心理活动的工具的初步发现

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00072

Rozaliya Amirova, Vladimir Ivanov, Sergey Masyagin, Aldo Spallone, G. Succi

{"title":"Preliminary findings on tools for the analysis of mental activity of programmers using EEG data from portable devices","authors":"Rozaliya Amirova, Vladimir Ivanov, Sergey Masyagin, Aldo Spallone, G. Succi","doi":"10.1109/DSD51259.2020.00072","DOIUrl":"https://doi.org/10.1109/DSD51259.2020.00072","url":null,"abstract":"Developers are indeed the most important resource in software production, and the individual developers are hard to substitute. The core of the work of the developers of knowledge intensive systems is in their mind, and this now a growing interest in understanding how to detect and model the state of their mind. Such analysis would enable to determine and model the optimal situation to develop in terms, for instance, of speed of development, minimization of errors, etc., and, to the extent possible, to recreate or to get close to such situation while organizing the work, the processes, the tools, and so on. The problem of performing such analysis is that the most refined equipment to model the work of the mind, like the fMRI, is very expensive and not movable. However, a tool, MNE, has been developed who is able to recreate accurate approximations using EEG of the data coming from an accurate wearable device that would come from the fMRI. This is a major enabler of the research in this area and in this paper details on why to select it and how to use it are provided. Current paper makes proof-of-concept to show that EEG is applicable for for retrieving information about functional state of the brain especially with a help of MNE tool.","PeriodicalId":128527,"journal":{"name":"2020 23rd Euromicro Conference on Digital System Design (DSD)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114306859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

FPGA-based SPHINCS+ Implementations: Mind the Glitch 基于fpga的SPHINCS+实现:注意故障

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00046

D. Amiet, Lukas Leuenberger, A. Curiger, P. Zbinden

引用次数: 15

Optimizing Picnic for Limited Memory Resources 优化野餐有限的内存资源

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00041

Johannes Winkler, Andrea Höller, C. Steger

引用次数: 1

Multi Buses: Theory and Practical Considerations of Data Bus Width Scaling in FPGAs 多总线:fpga中数据总线宽度缩放的理论与实践思考

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/DSD51259.2020.00020

Lukás Kekely, Jakub Cabal, V. Pus, J. Korenek

引用次数: 3

DSD 2020 Index DSD 2020指数

2020 23rd Euromicro Conference on Digital System Design (DSD) Pub Date : 2020-08-01 DOI: 10.1109/dsd51259.2020.00112

引用次数: 0