检索结果-内蒙古大学图书馆

IEEE International conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Kam Chi Loong Shihao Han Sishuo Liu Ning Lin Zhongrui Wang Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong China ACCESS - AI Chip Center for Emerging Smart Systems Hong Kong Science Park Hong Kong China School of Astronautics Harbin Institute of Technology Harbin China School of Microelectronics Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350380408

ISBN: (纸本)9798350380415

Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficiency compared to conventional von Neumann architectures. However, existing research has primarily focused on hardware architecture and network co-design for large-scale neural networks, without considering resource constraints. In this study, we aim to develop edge-friendly deep neural networks (DNNs) for accelerators based on resistive random-access memory (RRAM). To achieve this, we propose an edge compilation and resource-constrained RRAM-aware neural architecture search (NAS) framework to search for optimized neural networks meeting specific hardware constraints. Our compilation approach integrates layer partitioning, duplication, and network packing to maximize the utilization of computation units. The resulting network architecture can be optimized for either high accuracy or low latency using a one-shot neural network approach with Pareto optimality achieved through the Non-dominated Sorted Genetic Algorithm II (NSGA-II). The compilation of mobile-friendly networks, like Squeezenet and MobilenetV3 small can achieve over 80% of utilization and over 6x speedup compared to ISAAC-like framework with different crossbar resources. The resulting model from NAS optimized for speed achieved 5x-30x speedup. The code for this paper is available at https://***/ArChiiii/rram_nas_comp_pack.

关键词： Computer architecture Parallel processing Network architecture In-memory computing Solids Hardware Common information Model (computing) Neural architecture search Low latency communication Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Raspberry Pi-Based Device for Finger Veins Collection and the Image processing-Based Method for Minutiae Extraction 1

引用

20th International conference on Computer information systems and Industrial Management Applications, CISIM 2021

作者： Szymkowski, Maciej Faculty of Computer Science Bialystok University of Technology Bialystok Poland

ISBN: (数字)9783030843403

ISBN: (纸本)9783030843397

Biometrics is one of the most important ways to secure users’ data. It gained popularity due to effectiveness and ease of usage. It was proven that diversified solutions based on measurable traits can guarantee higher security levels than traditional authentication-based (logins and passwords). The most popular are fingerprint and iris (especially in mobile devices). In this work we would like to present our own algorithm connected with finger veins features extraction. At the beginning all details of the device for samples collection are given. In the further part significant information related to finger veins extraction are described in the details. Image processing methods were used to show that even with traditional, well-known algorithms it is possible to obtain precise information about human veins. The final step in our algorithm is connected with feature vector generation. In this work we do not present a classification stage as it is out of its scope. © 2021, Springer Nature Switzerland AG.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Deep learning methods for point-of-care ultrasound examination

Deep learning methods for point-of-care ultrasound examinati...

引用

International IEEE conference on Signal-Image Technologies and Internet-Based System

作者： Giacomo Ignesti Chiara Deri Gennaro D’Angelo Lorenza Pratali Antonio Bruno Antonio Benassi Ovidio Salvetti Davide Moroni Massimo Martinelli Institute of Information Science and Technologies National Research Council of Italy Pisa Italy Department of Computer Science University of Pisa Pisa Italy Institute of Clinical Physiology National Research Council of Italy Pisa Italy

Point-of-care Test (POCT) is the delivery of medical care at or near the patient’s bedside. Primarily employed in emergencies, where rapid diagnosis and treatment are critical, POCT is now being used in domestic telehealth solutions, as in the TiAssisto project, thanks to technological advances such as the development of portable and affordable devices, high-speed Internet connections, video conferencing, and Artificial Intelligence (AI). Ultrasound (US) images of internal organs and structures are valuable tools in POCT medicine since this examination is portable, quick, and cost-effective. USs can help diagnose different conditions, including heart problems, abdominal pain, and pneumonia. Deep learning algorithms have proven to be highly effective in image recognition, enabling physicians to make informed decisions on-site. This article presents a pipeline approach providing remarkable and reliable results to handle point-of-care ultrasound examinations, making use of methods for: a) automating text cleaning for privacy based on an optical Character Recognition (OCR) algorithm; b) scrolling through the video frames and annotating them using an ad hoc implemented tool; c) classifying various signs in US using a state of the art deep learning algorithm, that is an adaptive efficient method ensembling two EfficientNet-b0 weak models; d) benchmarking medical plausibility to address transparency and human in the loop setting using a post hoc explanation visual explanation method, i.e. *** involved physician’s feedback remarks that this system can detect important signs in pulmonary US imaging. However, the dataset is not yet the final one since the TiAssisto project is still ongoing, with a planned conclusion in February 2024. Our ultimate goal is not merely to develop a classification system but to create an effective healthcare support system that can be used beyond primary healthcare facilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Primer on silicon neuromorphic photonic processors: architecture and compiler

引用

NANOPHOTONICS 2020年第13期9卷 4055-4073页

作者： de Lima, Thomas Ferreira Tait, Alexander N. Mehrabian, Armin Nahmias, Mitchell A. Huang, Chaoran Peng, Hsuan-Tung Marquez, Bicky A. Miscuglio, Mario El-Ghazawi, Tarek Sorger, Volker J. Shastri, Bhavin J. Prucnal, Paul R. Queens Univ Dept Phys Engn Phys & Astron Kingston ON KL7 3N6 Canada Princeton Univ Dept Elect Engn Princeton NJ 08544 USA George Washington Univ Dept Elect & Comp Engn Washington DC 20052 USA

Microelectronic computers have encountered challenges in meeting all of today's demands for information processing. Meeting these demands will require the development of unconventional computers employing alternative processing models and new device physics. Neural network models have come to dominate modern machine learning algorithms, and specialized electronic hardware has been developed to implement them more efficiently. A silicon photonic integration industry promises to bring manufacturing ecosystems normally reserved for microelectronics to photonics. Photonic devices have already found simple analog signal processing niches where electronics cannot provide sufficient bandwidth and reconfigurability. In order to solve more complex information processing problems, they will have to adopt a processing model that generalizes and scales. Neuromorphic photonics aims to map physical models of optoelectronic systems to abstract models of neural networks. It represents a new opportunity for machine information processing on sub-nanosecond timescales, with application to mathematical programming, intelligent radio frequency signal processing, and real-time control. The strategy of neuromorphic engineering is to externalize the risk of developing computational theory alongside hardware. The strategy of remaining compatible with silicon photonics externalizes the risk of platform development. In this perspective article, we provide a rationale for a neuromorphic photonics processor, envisioning its architecture and a compiler. We also discuss how it can be interfaced with a general purpose computer, i.e. a CPU, as a coprocessor to target specific applications. This paper is intended for a wide audience and provides a roadmap for expanding research in the direction of transforming neuromorphic photonics into a viable and useful candidate for accelerating neuromorphic computing.

关键词： neuromorphic computing optical neural networks photonic integrated circuits silicon photonics ultrafast information processing

来源：评论

学校读者我要写书评

暂无评论

A 0.06-mm2 Current-Mode Noise-Shaping SAR based Temperature-to-Digital Converter with a 4.9-nJ Energy/Conversion

A 0.06-mm2 Current-Mode Noise-Shaping SAR based Temperature-...

引用

Custom Integrated Circuits conference (CICC)

作者： Antonio Aprile Michele Folz Daniele Gardino Piero Malcovati Edoardo Bonizzoni University of Pavia Pavia Italy TDK InvenSense Assago Italy

MEMS accelerometers and gyroscopes employed in state-of-the-art battery-supplied motion sensing systems require ultra-low energyper-conversion (<10nJ) digital temperature data to compensate for the thermal drift of their sensed quantities. Furthermore, in order to meet the increasingly stringent demands of the market, the cost-effectiveness of these devices should be ensured by compact temperature compensation solutions (<0.1 mm2), referred to as Temperature-to-Digital Converters (TDCs). Taking the moderate accuracy requirements (<2%) for the considered application into account, BJT-based sensors are a good option for the analog part of the TDC, since their low-cost 1 -pt calibration is sufficient [1] –[3]; moreover, considering that also the resolution requirements are moderate (<200mK), with the goal of minimizing the TDC conversion energy, a SAR-based architecture to perform the analog-to-digital conversion is undoubtedly the best approach [4] –[6]. In this paper we introduce a Noise Shaping (NS) SAR based TDC with a resolution refining process exploiting an error-feedback approach; the sensor, equipped with an NPN-based bipolar core, has been completely designed in the current domain, feature that allows opamp-less signal processing. A block diagram of the proposed NSSAR based TDC is shown in Fig. 1. The BJT Core is composed by proportional and complementary to-absolute-temperature (PTAT and CTAT) current sources, which generate the signals needed for the temperature-to-digital conversion ($\mathrm{I}_{\mathrm{P}\mathrm{T}\mathrm{A}\mathrm{T}}$, IREF* and IREF = IPTATI + ICTATI) [4]. These signals are delivered to the Current-Mode NS-SAR by means of three interface circuits, an n-type current mirror and two current buffers. IPTAT contains the temperature information to be converted while IREF**, a replica of IREF*, is provided as a reference signal to a binary p-type 4-bit current steering DAC, which scales it sequentially according to a successive approximation

关键词： Temperature sensors Temperature distribution Energy resolution Refining Signal processing algorithms Sensors Noise shaping

来源：评论

学校读者我要写书评

暂无评论

Image Clipping Strategy of Object Detection for Super Resolution Image in Low Resource Environment 5th

Image Clipping Strategy of Object Detection for Super Resolu...

引用

5th International conference on Cognitive systems and Signal processing, ICCSIP 2020

作者： Huang, Lei Zhang, Xiaokai Qiang, Baohua Chen, Jinlong Yang, Hongbo Yang, Minghao Guilin University of Electronic Technology Guilin541000 China Beijing Information Science and Technology University Beijing100192 China Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9789811623356

Nowadays, deep learning based object detection algorithms have been widely discussed in various application fields. Some super resolution images are not fully supported by the deep learning network structure in low resource hardware devices. An example is the embedded hardware installed on satellite with the super resolution image as input. Traditional methods usually clip the large scale image into small multiple block images, and merge the detect results from clipped images. However, there is still a lack of corresponding strategy to analyze the relationship between detection efficient, including cost time, detection accuracies and the size of block images. To this end, this paper proposes a strategy of image clipping for super resolution images on low resource hardware environment of object detection algorithm. In methodology, we consider the relationship among the number of chip cores, the number of image targets, image input resolution, image block numbers and propose an evaluation method for the optimal efficiency of object detection on low resource hardware. In experiments, the classic Haar detection algorithm runs on TI6678 chips with 8 CPU cores shared with 2.0 G RAM. It shows that the utilization efficiency of object detection algorithm in chip is related to the ratio of segmentation, the number of partitions and the number of CPU cores used. The exploration in this work is also helpful for researchers and developers optimize other algorithms, such as Fast R-CNN, YOLO, on other similar low resource environment in the future. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Experimental anonymous conference key agreement using linear cluster states

引用

Physical Review Research 2023年第3期5卷 033222-033222页

作者： Lukas Rückle Jakob Budde Jarn de Jong Frederik Hahn Anna Pappa Stefanie Barz Institute for Functional Matter and Quantum Technologies Universität Stuttgart 70569 Stuttgart Germany Center for Integrated Quantum Science and Technology (IQST) Universität Stuttgart 70569 Stuttgart Germany Electrical Engineering and Computer Science Department Technische Universität Berlin 10587 Berlin Germany Dahlem Center for Complex Quantum Systems Freie Universität Berlin 14195 Berlin Germany Fraunhofer-Institute for Open Communication Systems FOKUS 10589 Berlin Germany

Multipartite entanglement enables secure and anonymous key exchange between multiple parties in a network. Greenberger-Horne-Zeilinger states have been introduced as resource states for anonymous key exchange protocols, in which an anonymous subset of parties within a larger network establishes a secret key. However, the use of other types of multipartite entanglement for such protocols remains relatively unexplored. Here, we demonstrate that linear cluster states can serve as a versatile and potentially scalable resource in such applications. We implemented an anonymous key exchange protocol with four photons in a linear cluster state and established a shared key between three parties in our network. We show how to optimize the protocol parameters to account for noise and to maximize the finite key rate under realistic conditions. As cluster states have been established as a flexible resource in quantum computation, we expect that our demonstration provides a first step towards their hybrid use for networked computing and communication.

关键词： optical quantum information processing Quantum communication Quantum networks Quantum optics

来源：评论

学校读者我要写书评

暂无评论

A haze removal method based on additional depth information and image fusion 2nd

A haze removal method based on additional depth information ...

引用

2nd International conference on Sensor Networks and Signal processing, SNSP 2019

作者： Tian, Tian Zhang, Bin Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9789811549168

To address the problem of image degradation in foggy days, we propose a haze removal method based on additional depth information and image fusion. With recent advances in depth-sensing technology, it has been realized that sensing devices can produce depth images in which the depth value are quite accurate. We adopt the depth estimation dataset of Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) which contains images collected from different real-world environments. The additional information includes the LiDaR scanning points and original depth images which can be used to estimate the optical depth of each point in the scene. In this paper, we investigate how to use additional depth information to remove haze for a single image. Our method focuses on LiDaR depth imaging, image fusion, and the atmospheric scattering model. We use LiDaR scanning points as input and then deduce a rough depth image with prominent features. The rough depth image is then combined with original depth image to improve reliability of depth estimation by image fusion. Using the atmospheric scattering model, we can remove haze for a single image. Experimental results show that our proposed approach provides better performance of dehazing under different fog conditions and holding the details of remote sensing images than current research methods. © Springer Nature Singapore Pte Ltd 2021.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Embedded Flu Detection System based Cough Sound using MFCC and kNN Algorithm

Embedded Flu Detection System based Cough Sound using MFCC a...

引用

Science and information Technology in Smart Administration (ICSINTESA), International conference of

作者： Aldi Jayadi Barlian Henryranu Prasetio Sabriansyah Rizqika Akbar Edita Rosana Widasari Dahnial Syauqy Dept. of Computer Engineering Faculty of Computer Science Universitas Brawijaya Malang Indonesia

ISBN: (纸本)9781665472890

Flu is an infectious respiratory disease caused by viruses that affected people every year. In some cases, flu can lead to hospitalization and even death. Figure out whether the flu also affects community is considered challenging for preventing wide outbreaks. Therefore, we propose an efficient flu detection using embedded system. The proposed method for flu detection based on Mel Frequency Cepstral Coefficient (MFCC) and K-Nearest Neighbor (kNN) algorithm which can effectively distinguish cough sounds. The cough is a flu symptom since flu will cause a dry cough. The effectiveness of the proposed method is evaluated in the task of classifying the flu or non-flu from the 270 subjects of the COUGHVID dataset that provides crowdsourced cough recordings. Furthermore, the proposed method is implementing on embedded devices-based Raspberry Pi. Based on experimental results, the proposed system presents 80% of accuracy, 4.370 seconds of execution time, and 27% of Central processing Unit (CPU) usage. This result indicates that the proposed system is non-invasive, reliable, easy to apply, and can reduce the workload testing in local health centers.

关键词： Embedded systems Pulmonary diseases Classification algorithms Central processing Unit Recording Reliability Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Computer Networking for Management information System of Unmanned Vehicles 22

Computer Networking for Management Information System of Unm...

引用

22nd International conference on Transparent optical Networks (ICTON)

作者： Sokolov, Sergey Boguslavsky, Andrey Keldysh Inst Appl Math RAS Miusskaya Sq 4 Moscow 125047 Russia

ISBN: (纸本)9781728184234

The ever-increasing need for the large-scale implementation of unmanned vehicles requires situational awareness of such vehicles. In this case two general directions are possible. The first: simplification and fixing situations with vehicles movements. The second: improving the onboard control system and its information component. We focus on the second direction in our study. information support of vehicles, especially systems of technical vision, requires ever-increasing computing resources and intelligent technologies in algorithmic support. The experience of our research shows that reconfigurable high-performance heterogeneous resources are the effective software and hardware tool for information support of autonomous vehicles Such devices combine sequentially parallel processing of visual data. In the process of developing such resources, we use a heterogeneous computer network based on the PCI express bus. The report describes the general scheme of such a network, considers hardware and software configurations for solving application task, gives the results of experiments to solve the issues of collecting and processing visual data, and discusses the prospects for the development of this approach.

关键词： intelligent technologies neural network architectures tensor processors serial-parallel processing unmanned vehicles

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：