首页 > 最新文献

2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)最新文献

英文 中文
Novel Methodology for Alzheimer's Disease Biomarker Identification in Plasma using Hyperspectral Microscopy 使用高光谱显微镜鉴定血浆中阿尔茨海默病生物标志物的新方法
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268654
H. Fabelo, Raquel León, S. Ortega, Francisco Balea-Fernández, C. Bilbao, G. Callicó, A. Wagner
Alzheimer’s disease (AD) is a gradually progressive neurocognitive disorder (NCD) with a preclinical phase where the patient can be asymptomatic for many years. The detection of AD in its earliest stages is one of the most active areas in Alzheimer’s science. This early diagnosis could potentially allow for early intervention and improved prognosis, once effective treatment is available. This paper proposes a novel methodology based on spectral unmixing for the identification of biomarkers in plasma samples using visual and near infrared (VNIR) hyperspectral microscopy (HSM). The study was performed using ten drop plasma samples from 10 patients (5 control and 5 case subjects affected by NCD) captured with HSM at two different magnifications: 5× and 20×. This data was processed, and a statistical analysis of the abundance estimation was performed to identify relevant endmembers to differentiate case and control groups. The results suggest the potential of HSM and plasma samples as a cost-effective early diagnosis tool.
阿尔茨海默病(AD)是一种逐渐进行性神经认知障碍(NCD),其临床前阶段患者可多年无症状。在阿尔茨海默病的早期阶段检测是阿尔茨海默病科学中最活跃的领域之一。一旦有了有效的治疗方法,这种早期诊断可能允许早期干预和改善预后。本文提出了一种基于光谱分解的等离子体样品生物标记物鉴定新方法——视近红外(VNIR)高光谱显微镜。研究使用HSM在5倍和20倍两种不同倍率下捕获的10例患者(5例对照和5例受非传染性疾病影响的患者)的10滴血浆样本进行。对这些数据进行处理,并对丰度估计进行统计分析,以识别相关的端元,以区分病例组和对照组。结果表明,HSM和血浆样本作为一种具有成本效益的早期诊断工具的潜力。
{"title":"Novel Methodology for Alzheimer's Disease Biomarker Identification in Plasma using Hyperspectral Microscopy","authors":"H. Fabelo, Raquel León, S. Ortega, Francisco Balea-Fernández, C. Bilbao, G. Callicó, A. Wagner","doi":"10.1109/DCIS51330.2020.9268654","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268654","url":null,"abstract":"Alzheimer’s disease (AD) is a gradually progressive neurocognitive disorder (NCD) with a preclinical phase where the patient can be asymptomatic for many years. The detection of AD in its earliest stages is one of the most active areas in Alzheimer’s science. This early diagnosis could potentially allow for early intervention and improved prognosis, once effective treatment is available. This paper proposes a novel methodology based on spectral unmixing for the identification of biomarkers in plasma samples using visual and near infrared (VNIR) hyperspectral microscopy (HSM). The study was performed using ten drop plasma samples from 10 patients (5 control and 5 case subjects affected by NCD) captured with HSM at two different magnifications: 5× and 20×. This data was processed, and a statistical analysis of the abundance estimation was performed to identify relevant endmembers to differentiate case and control groups. The results suggest the potential of HSM and plasma samples as a cost-effective early diagnosis tool.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126105245","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: 2
Hardware architecture for integrate-and-fire signal reconstruction on FPGA 基于FPGA的集火信号重构硬件架构
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268638
G. Carvalho, J. Ferreira, V. Tavares
Typical analogue-to-digital conversion (ADC) architectures, at Nyquist rate, tend to occupy a big portion of the integrated circuit die area and to consume more power than desired. Recently, with the rise of Interet-of-Things (IoT), there is a high demand for architectures that can have both reduced area and power consumption. Time encoding machines (TEM) might be a promising alternative. These types of encoders result in very simple and low-power analogue circuits, shifting most of its complexity to the decoding stage, typically stationed in a place with access to more resources. This paper focuses on a particular TEM, the integrate-and-fire neuron (IFN). The IFN modulation is based on a simplified first-order model of neural operation and it encodes the signal in a very power efficient manner. In the end, a novel hardware architecture for the reconstruction of the IFN encoded signal based on a spiking model will be presented. The method is demonstrated and implemented on FPGA, reaching an ENOB as high as 8.23.
典型的模数转换(ADC)架构,在奈奎斯特速率下,往往占据很大一部分集成电路的芯片面积,并消耗比预期更多的功率。最近,随着物联网(IoT)的兴起,对既能减少面积又能降低功耗的架构有很高的需求。时间编码机(TEM)可能是一个很有前途的替代方案。这些类型的编码器产生非常简单和低功耗的模拟电路,将其大部分复杂性转移到解码阶段,通常驻扎在可以访问更多资源的地方。本文关注的是一种特殊的瞬变电磁法,即整合-激发神经元(IFN)。IFN调制是基于一种简化的一阶神经操作模型,它以一种非常节能的方式对信号进行编码。最后,提出了一种新的基于尖峰模型的IFN编码信号重构硬件架构。该方法在FPGA上进行了验证和实现,ENOB高达8.23。
{"title":"Hardware architecture for integrate-and-fire signal reconstruction on FPGA","authors":"G. Carvalho, J. Ferreira, V. Tavares","doi":"10.1109/DCIS51330.2020.9268638","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268638","url":null,"abstract":"Typical analogue-to-digital conversion (ADC) architectures, at Nyquist rate, tend to occupy a big portion of the integrated circuit die area and to consume more power than desired. Recently, with the rise of Interet-of-Things (IoT), there is a high demand for architectures that can have both reduced area and power consumption. Time encoding machines (TEM) might be a promising alternative. These types of encoders result in very simple and low-power analogue circuits, shifting most of its complexity to the decoding stage, typically stationed in a place with access to more resources. This paper focuses on a particular TEM, the integrate-and-fire neuron (IFN). The IFN modulation is based on a simplified first-order model of neural operation and it encodes the signal in a very power efficient manner. In the end, a novel hardware architecture for the reconstruction of the IFN encoded signal based on a spiking model will be presented. The method is demonstrated and implemented on FPGA, reaching an ENOB as high as 8.23.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"76 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120891743","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
Algorithm-Architecture Optimization for Linear and Quadratic Regression on Reconfigurable Platforms 可重构平台上线性和二次回归的算法体系优化
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268633
Samuel López Asunción, M. López-Vallejo, J. Grajal
Linear and quadratic regressions are techniques widely used in digital signal processing applications. This paper proposes a procedure and hardware architecture for the implementation of both regression methods and their mean square error (MSE) on FPGAs. Efficient computation of the bit widths of the coefficients of the regressions is carried out by finding their maxima and minima. Based on this optimization, a low-latency memory-less implementation for the computation of the MSE is proposed. Additionally, we have implemented the proposed architecture as part of a signal modulation classifier with hard real-time constraints.
线性和二次回归是广泛应用于数字信号处理的技术。本文提出了在fpga上实现这两种回归方法及其均方误差(MSE)的程序和硬件结构。通过求回归系数的最大值和最小值,有效地计算了回归系数的位宽度。在此基础上,提出了一种低延迟无内存的MSE计算实现。此外,我们已经将所提出的架构作为具有硬实时约束的信号调制分类器的一部分实现。
{"title":"Algorithm-Architecture Optimization for Linear and Quadratic Regression on Reconfigurable Platforms","authors":"Samuel López Asunción, M. López-Vallejo, J. Grajal","doi":"10.1109/DCIS51330.2020.9268633","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268633","url":null,"abstract":"Linear and quadratic regressions are techniques widely used in digital signal processing applications. This paper proposes a procedure and hardware architecture for the implementation of both regression methods and their mean square error (MSE) on FPGAs. Efficient computation of the bit widths of the coefficients of the regressions is carried out by finding their maxima and minima. Based on this optimization, a low-latency memory-less implementation for the computation of the MSE is proposed. Additionally, we have implemented the proposed architecture as part of a signal modulation classifier with hard real-time constraints.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124036739","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: 0
Behavioral modeling of multilevel HfO2-based memristors for neuromorphic circuit simulation 神经形态电路仿真中基于hfo2的多电平记忆电阻器的行为建模
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268652
Antonio J. Pérez-Ávila, G. González-Cordero, E. Pérez, E. Quesada, Mamathamba Kalishettyhalli Mahadevaiaha, C. Wenger, J. Roldán, F. Jiménez-Molinos
An artificial neural network based on resistive switching memristors is implemented and simulated in LTspice. The influence of memristor variability and the reduction of the continuous range of synaptic weights into a discrete set of conductance levels is analyzed. To do so, a behavioral model is proposed for multilevel resistive switching memristors based on Al-doped HfO2 dielectrics, and it is implemented in a spice based circuit simulator. The model provides an accurate description of the conductance in the different conductive states in addition to describe the device-to-device variability.
在LTspice中实现并仿真了一种基于电阻开关忆阻器的人工神经网络。分析了忆阻变异性和将突触权值的连续范围减小为离散电导电平集的影响。为此,提出了一种基于al掺杂HfO2电介质的多电平电阻开关忆阻器的行为模型,并在spice电路模拟器中实现。除了描述器件间的可变性外,该模型还提供了对不同导电状态下电导的准确描述。
{"title":"Behavioral modeling of multilevel HfO2-based memristors for neuromorphic circuit simulation","authors":"Antonio J. Pérez-Ávila, G. González-Cordero, E. Pérez, E. Quesada, Mamathamba Kalishettyhalli Mahadevaiaha, C. Wenger, J. Roldán, F. Jiménez-Molinos","doi":"10.1109/DCIS51330.2020.9268652","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268652","url":null,"abstract":"An artificial neural network based on resistive switching memristors is implemented and simulated in LTspice. The influence of memristor variability and the reduction of the continuous range of synaptic weights into a discrete set of conductance levels is analyzed. To do so, a behavioral model is proposed for multilevel resistive switching memristors based on Al-doped HfO2 dielectrics, and it is implemented in a spice based circuit simulator. The model provides an accurate description of the conductance in the different conductive states in addition to describe the device-to-device variability.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"56 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126256055","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: 7
Data flow analysis from UML/MARTE models based on binary traces 基于二进制跟踪的UML/MARTE模型的数据流分析
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268671
H. Posadas, Javier Merino, E. Villar
The design of increasingly complex embedded systems requires powerful solutions from the very beginning of the design process. Model Based Design (MBD) and early simulation have proven to be capable technologies to perform initial design space analysis to optimize system design. Traditional MBD methods and tools typically rely on fixed elements, which makes difficult the evaluation of different platform configurations, communication alternatives or models of computation. Addressing these challenges require flexible design technologies able to support, from a high-level abstract model, full design space exploration, including system specification, binary generation and performance evaluation. In this context, this paper proposes a UML/MARTE based approach able to address the challenges mentioned above by improving design flexibility and evaluation capabilities, including automatic code generation, trace execution collection and trace analysis from the initial UML models. The approach focuses on the definition and analysis of the paths data follow through the different application components, as a way to understand the behavior or the different design solutions.
越来越复杂的嵌入式系统的设计从设计过程的一开始就需要强大的解决方案。基于模型的设计(MBD)和早期仿真已经被证明是能够执行初始设计空间分析以优化系统设计的技术。传统的MBD方法和工具通常依赖于固定的元素,这使得对不同平台配置、通信替代方案或计算模型的评估变得困难。解决这些挑战需要灵活的设计技术,能够从高级抽象模型支持完整的设计空间探索,包括系统规范、二进制生成和性能评估。在这种情况下,本文提出了一种基于UML/MARTE的方法,能够通过改进设计灵活性和评估能力来解决上面提到的挑战,包括自动代码生成、跟踪执行收集和来自初始UML模型的跟踪分析。该方法侧重于定义和分析数据在不同应用程序组件中遵循的路径,作为理解行为或不同设计解决方案的一种方法。
{"title":"Data flow analysis from UML/MARTE models based on binary traces","authors":"H. Posadas, Javier Merino, E. Villar","doi":"10.1109/DCIS51330.2020.9268671","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268671","url":null,"abstract":"The design of increasingly complex embedded systems requires powerful solutions from the very beginning of the design process. Model Based Design (MBD) and early simulation have proven to be capable technologies to perform initial design space analysis to optimize system design. Traditional MBD methods and tools typically rely on fixed elements, which makes difficult the evaluation of different platform configurations, communication alternatives or models of computation. Addressing these challenges require flexible design technologies able to support, from a high-level abstract model, full design space exploration, including system specification, binary generation and performance evaluation. In this context, this paper proposes a UML/MARTE based approach able to address the challenges mentioned above by improving design flexibility and evaluation capabilities, including automatic code generation, trace execution collection and trace analysis from the initial UML models. The approach focuses on the definition and analysis of the paths data follow through the different application components, as a way to understand the behavior or the different design solutions.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126407183","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: 0
DCIS 2020 Commentary DCIS 2020评论
Pub Date : 2020-11-18 DOI: 10.1109/dcis51330.2020.9268635
{"title":"DCIS 2020 Commentary","authors":"","doi":"10.1109/dcis51330.2020.9268635","DOIUrl":"https://doi.org/10.1109/dcis51330.2020.9268635","url":null,"abstract":"","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131842209","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: 0
Distributed power amplifier in GaN technology with tapered drain lines GaN技术中带锥形漏极线的分布式功率放大器
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268621
José Luis Saiz-Pérez, J. Pino, D. Mayor-Duarte, S. Khemchandani, Mario San Miguel-Montesdeoca, S. Mateos-Angulo
A Distributed Power Amplifier (DPA) with a tapered drain line is presented in this paper. The drain line impedance tapering technique allows to obtain a higher output power and efficiency compared to the conventional approach, whereas a constant drain line impedance avoids impedance changes in the power supply drive signal. The design was implemented using the D01GH/Si technology provided by the foundry OMMIC. The DPA achieves a Psat of 32 dBm and a flat gain over 14 dB in a frequency range that ranges from 1 to 8 GHz. Moreover, this circuit achieves a Power Added Efficiency (PAE) of 50%. Finally, the occupied area of the DPA is 2.2x1.2mm2 excluding pads.
提出了一种具有锥形漏极线的分布式功率放大器(DPA)。与传统方法相比,漏极线阻抗变细技术可以获得更高的输出功率和效率,而恒定的漏极线阻抗可以避免电源驱动信号中的阻抗变化。该设计是使用代工厂OMMIC提供的D01GH/Si技术实现的。在1至8 GHz的频率范围内,DPA实现了32 dBm的Psat和超过14 dB的平坦增益。此外,该电路实现了50%的功率附加效率(PAE)。最后,DPA的占用面积为2.2x1.2mm2,不包括垫块。
{"title":"Distributed power amplifier in GaN technology with tapered drain lines","authors":"José Luis Saiz-Pérez, J. Pino, D. Mayor-Duarte, S. Khemchandani, Mario San Miguel-Montesdeoca, S. Mateos-Angulo","doi":"10.1109/DCIS51330.2020.9268621","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268621","url":null,"abstract":"A Distributed Power Amplifier (DPA) with a tapered drain line is presented in this paper. The drain line impedance tapering technique allows to obtain a higher output power and efficiency compared to the conventional approach, whereas a constant drain line impedance avoids impedance changes in the power supply drive signal. The design was implemented using the D01GH/Si technology provided by the foundry OMMIC. The DPA achieves a Psat of 32 dBm and a flat gain over 14 dB in a frequency range that ranges from 1 to 8 GHz. Moreover, this circuit achieves a Power Added Efficiency (PAE) of 50%. Finally, the occupied area of the DPA is 2.2x1.2mm2 excluding pads.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134239585","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: 0
STDP Design Trade-offs for FPGA-Based Spiking Neural Networks 基于fpga的脉冲神经网络的STDP设计权衡
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268614
Rafael Medina Morillas, P. Ituero
The rise of popularity of Spiking Neural Networks has resulted in a growing interest for simulating synaptic plasticity. Among the existing choices, Spike-Timing-Dependent Plasticity (STDP) represents a reliable solution whose main weakness consists on its high computational cost. This paper proposes several high-frequency FPGA architectures for the realization of pair-based STDP. It also presents a comparison between these implementations and previous ones, and analyzes the compromise between area utilization and precision. We also suggest a SNN architecture capable of implementing in-board STDP learning. The results show that our proposals achieve high throughput and maximum frequencies starting at 400MHz, with a reasonable area utilization and precision loss. The wide range of presented designs makes this work valuable for the decision-taking process in the design and implementation of large scale SNN with different area and precision requirements.
随着脉冲神经网络的流行,人们对模拟突触可塑性的兴趣越来越大。在现有的选择中,峰值时间相关塑性(STDP)是一种可靠的解决方案,但其主要缺点是计算成本高。本文提出了几种实现基于对的STDP的高频FPGA架构。并将这些实现与以前的实现进行了比较,分析了面积利用率和精度之间的折衷。我们还提出了一种能够实现板内STDP学习的SNN架构。结果表明,我们的方案实现了高吞吐量和从400MHz开始的最大频率,并具有合理的面积利用率和精度损失。所提出的广泛设计使得这项工作对于具有不同面积和精度要求的大规模SNN的设计和实施决策过程具有价值。
{"title":"STDP Design Trade-offs for FPGA-Based Spiking Neural Networks","authors":"Rafael Medina Morillas, P. Ituero","doi":"10.1109/DCIS51330.2020.9268614","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268614","url":null,"abstract":"The rise of popularity of Spiking Neural Networks has resulted in a growing interest for simulating synaptic plasticity. Among the existing choices, Spike-Timing-Dependent Plasticity (STDP) represents a reliable solution whose main weakness consists on its high computational cost. This paper proposes several high-frequency FPGA architectures for the realization of pair-based STDP. It also presents a comparison between these implementations and previous ones, and analyzes the compromise between area utilization and precision. We also suggest a SNN architecture capable of implementing in-board STDP learning. The results show that our proposals achieve high throughput and maximum frequencies starting at 400MHz, with a reasonable area utilization and precision loss. The wide range of presented designs makes this work valuable for the decision-taking process in the design and implementation of large scale SNN with different area and precision requirements.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115658580","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: 0
Multiclass Brain Tumor Classification Using Hyperspectral Imaging and Supervised Machine Learning 基于高光谱成像和监督机器学习的多类脑肿瘤分类
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268650
Luisa Ruiz, Alberto Martín, Gemma Urbanos, Marta Villanueva, Jaime Sancho, Gonzalo Rosa, M. Villa, M. Chavarrías, Ángel Pérez, E. Juárez, Alfonso Lagares, C. Sanz
Hyperspectral Imaging (HSI) can be used as a non invasive medical diagnostic method when used in combination with Machine Learning (ML) algorithms. The significant captured data in HSI can be useful for classifying different types of brain tissues, since they gather reflectance values from different band widths below and beyond the visual spectrum. This allows ML algorithms like Support Vector Machines (SVM) and Random Forest (RF) to classify brain tissues such as tumors. Predicted results can be used to create visualizations and support neurosurgeons before injuring any tissue. This way neurosurgeons can be more precise, reducing any possible damages on healthy tissues. In this work, a proposal for the classification of in-vivo brain hyperspectral images using SVM and RF classifiers is presented. A total of four hyperspectral images from four different patients with glioblastoma grade IV (GBM) brain tumor have been selected to train models and, therefore, classify them. Five different classes have been defined during experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Results obtained suggest that SVM usually performs better than RF, generally achieving up to 97% of mean accuracy (ACC). However, RF performance had better results than SVM when classifying images used during training, obtaining almost 100% of mean ACC for all 5 classes described. This study shows the robustness of SVM and the potential of RF for real-time brain cancer detection.
当与机器学习(ML)算法结合使用时,高光谱成像(HSI)可以作为一种非侵入性医疗诊断方法。在HSI中捕获的重要数据可以用于分类不同类型的脑组织,因为它们收集了视觉光谱以下和之外不同带宽的反射值。这使得像支持向量机(SVM)和随机森林(RF)这样的机器学习算法可以对脑组织(如肿瘤)进行分类。预测结果可用于创建可视化,并在损伤任何组织之前支持神经外科医生。这样神经外科医生可以更精确,减少对健康组织的任何可能损害。在这项工作中,提出了一种使用支持向量机和射频分类器对活体脑高光谱图像进行分类的建议。四张来自四名不同的IV级胶质母细胞瘤(GBM)脑肿瘤患者的高光谱图像被选择来训练模型,从而对它们进行分类。实验确定了健康组织、肿瘤、静脉血管、动脉血管和硬脑膜五个不同的类别。得到的结果表明,SVM通常比RF表现更好,通常可达到97%的平均准确率(ACC)。然而,在对训练中使用的图像进行分类时,RF的性能优于SVM,对于所描述的所有5个类别,RF的平均ACC几乎达到100%。该研究显示了支持向量机的鲁棒性和射频在实时脑癌检测中的潜力。
{"title":"Multiclass Brain Tumor Classification Using Hyperspectral Imaging and Supervised Machine Learning","authors":"Luisa Ruiz, Alberto Martín, Gemma Urbanos, Marta Villanueva, Jaime Sancho, Gonzalo Rosa, M. Villa, M. Chavarrías, Ángel Pérez, E. Juárez, Alfonso Lagares, C. Sanz","doi":"10.1109/DCIS51330.2020.9268650","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268650","url":null,"abstract":"Hyperspectral Imaging (HSI) can be used as a non invasive medical diagnostic method when used in combination with Machine Learning (ML) algorithms. The significant captured data in HSI can be useful for classifying different types of brain tissues, since they gather reflectance values from different band widths below and beyond the visual spectrum. This allows ML algorithms like Support Vector Machines (SVM) and Random Forest (RF) to classify brain tissues such as tumors. Predicted results can be used to create visualizations and support neurosurgeons before injuring any tissue. This way neurosurgeons can be more precise, reducing any possible damages on healthy tissues. In this work, a proposal for the classification of in-vivo brain hyperspectral images using SVM and RF classifiers is presented. A total of four hyperspectral images from four different patients with glioblastoma grade IV (GBM) brain tumor have been selected to train models and, therefore, classify them. Five different classes have been defined during experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Results obtained suggest that SVM usually performs better than RF, generally achieving up to 97% of mean accuracy (ACC). However, RF performance had better results than SVM when classifying images used during training, obtaining almost 100% of mean ACC for all 5 classes described. This study shows the robustness of SVM and the potential of RF for real-time brain cancer detection.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114389490","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
Privacy-enabled system based on Elliptic Curve Cryptography to reduce risks of contagion in pandemics 基于椭圆曲线加密的隐私启用系统,以降低流行病传染的风险
Pub Date : 2020-11-18 DOI: 10.1109/DCIS51330.2020.9268632
L. Parrilla, Encarnación Castillo, Antonio García
The increase in the frequency of pandemic crises in recent years, with the current example of COVID-19, leads to the need of having technological tools that help to control the spread of these diseases in the first instance, and to avoid the generation of new outbreaks in the phases of back to normality. The main issue in these tools is the how to make their effectiveness compatible with privacy. In this work we present a system enabling secure distribution of people in closed environments such as public transport, restaurants or cinemas while maintaining privacy of health data. The system is based on Elliptic Curve Cryptography and it has been implemented on low-cost FPGA devices.
近年来,以当前的COVID-19为例,大流行危机的频率有所增加,因此需要有技术工具来帮助首先控制这些疾病的传播,并避免在恢复正常的阶段产生新的疫情。这些工具的主要问题是如何使它们的有效性与隐私兼容。在这项工作中,我们提出了一个系统,可以在公共交通、餐馆或电影院等封闭环境中安全地分配人员,同时保持健康数据的隐私。该系统基于椭圆曲线加密,并已在低成本的FPGA器件上实现。
{"title":"Privacy-enabled system based on Elliptic Curve Cryptography to reduce risks of contagion in pandemics","authors":"L. Parrilla, Encarnación Castillo, Antonio García","doi":"10.1109/DCIS51330.2020.9268632","DOIUrl":"https://doi.org/10.1109/DCIS51330.2020.9268632","url":null,"abstract":"The increase in the frequency of pandemic crises in recent years, with the current example of COVID-19, leads to the need of having technological tools that help to control the spread of these diseases in the first instance, and to avoid the generation of new outbreaks in the phases of back to normality. The main issue in these tools is the how to make their effectiveness compatible with privacy. In this work we present a system enabling secure distribution of people in closed environments such as public transport, restaurants or cinemas while maintaining privacy of health data. The system is based on Elliptic Curve Cryptography and it has been implemented on low-cost FPGA devices.","PeriodicalId":186963,"journal":{"name":"2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001090","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: 0
期刊
2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1