检索结果-内蒙古大学图书馆

Testing and optimization of Recurrent Signal Processor

学校读者我要写书评

暂无评论

Testing and optimization of Recurrent Signal Processor

International Workshop on Engineering Technologies and computer science (EnT)

作者： Yury Stepchenkov Dmitry Khilko Yury Shikunov Georgy Orlov Institute of Informatics Problems Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences Moscow Russia

ISBN: (数字)9781728180908

ISBN: (纸本)9781728180915

This paper covers the optimization research for the novel data-flow computational architecture called Hybrid Architecture of Recurrent Signal Processor. The testing methodology, based on the shift towards Test-Driven Development of architecture models, is provided. We cover the toolset developed to unify the methodology for both software and hardware models. The testing results are analyzed, and the issues are formulated. We propose the pipeline extension by splitting our largest component down. We show the new pipeline utilization ratio this solution provides.

关键词： Computational modeling Testing computer architecture Pipelines Debugging Tools computer science

Increasing Self-Timed Circuit Soft Error Tolerance

学校读者我要写书评

暂无评论

Increasing Self-Timed Circuit Soft Error Tolerance

East-West Design & Test Symposium (EWDTS)

作者： Igor Sokolov Yury Stepchenkov Yury Diachenko Yury Rogdestvenski Denis Diachenko Institute of Informatics Problems Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

ISBN: (数字)9781728198996

ISBN: (纸本)9781728199009

Indication subcircuit is an essential part of the self-timed circuits. It provides acknowledgment of the self-timed circuit switching completion and ensures correct handshake interaction between functional blocks. Besides, indication subcircuit complexity is comparable with the indicated self-timed circuit's complexity. So short-term soft errors, induced by the external and internal causes in both the indication subcircuit and the indicated self-timed circuit, are equally dangerous. Indication subcircuit soft error tolerance depends, the first, on its immunity to soft errors in the indicated self-timed circuit and, the second, on its failure protection. The first aspect becomes lower critical due to the XOR cell on the first stage of the indication subcircuit. An appropriate circuitry basis decreases indication subcircuit sensitivity to the possible soft errors induced in it. Static and semi-static Muller's C-element is a traditional base component used for indication purposes. Its dual interlocked implementation improves the indication subcircuit failure protection against soft errors in its internal nodes, but not sufficiently. The article proposes a new C-element's schematic that fully tolerates it against the soft errors in all internal nodes. Besides, using C-elements with in-phase inputs and output in an indication pyramid ensures indication subcircuit protection against soft errors induced at the output of the C-elements. The proposed approach makes an indication subcircuit fully protected against all soft errors induced in it.

关键词： Transistors Complexity theory Manganese informatics Layout Standards Short-circuit currents

Modeling and debugging tools development for recurrent architecture

学校读者我要写书评

暂无评论

Modeling and debugging tools development for recurrent archi...

2019 IEEE East-West Design and Test Symposium, EWDTS 2019

作者： Khilko, Dmitry Stepchenkov, Yury Shikunov, Yury Orlov, George Institute of Informatics Problems Federal Research Center Computer Science and Control' of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781728110035

An unconventional multi-core recurrent data-flow architecture, that is being developed at Federal Research Center 'computer science and Control' of the Russian academy of sciences (FRS CSC RAS)was successfully tested on digital signal processing domain both at the model level and on a hardware sample. Based on the test results, several mechanisms had been identified that required improvement and a decision was made to investigate the architecture on other subject domains. Software and main architectural blocks debugging are carried out with the specially developed hardware and software modeling tools. The active extension and debugging of the architecture by using these tools revealed a number of shortcomings of the existing software. To eliminate these shortcomings, two problems have to be solved: To provide a high degree of reconfigurability of the architecture's imitational model (to debug its mechanisms)and implement a symbolic modeling mode (to debug its software). The redesigning results of modeling and debugging tools for recurrent data-flow architecture are discussed in the article. © 2019 IEEE.

关键词： Digital signal processing

Advanced indication of the self-Timed circuits

学校读者我要写书评

暂无评论

Advanced indication of the self-Timed circuits

2019 IEEE East-West Design and Test Symposium, EWDTS 2019

作者： Stepchenkov, Yury Diachenko, Yury Rogdestvenski, Yury Shikunov, Yury Diachenko, Denis Institute of Informatics Problems Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781728110035

Paper discusses a problem of the CMOS self-Timed circuits' indication. Large number of indicating signals in the multi-bit computational devices and registers requires an additional hardware and time for their combining and forming a single control signal that provides a request-Acknowledge interaction between interconnected self-Timed functional blocks. Indication subcircuit performs this. Multi-input hysteretic triggers allows for accelerating indication subcircuit by factor of 1.1-1.6 and reducing its complexity in several times in comparison to standard implementation basis on static and semi-static Muller's elements. A penalty for this is some short-circuit current in the worst case. © 2019 IEEE.

关键词： Timing circuits

Robust Pose Transfer with Dynamic Details using Neural Video Rendering

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Yang-Tian Huang, Hao-Zhi Wang, Xuan Lai, Yu-Kun Liu, Wei Gao, Lin The Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Xverse China The Tencent China The School of Computer Science and Informatics Cardiff University Wales United Kingdom

Pose transfer of human videos aims to generate a high-fidelity video of a target person imitating actions of a source person. A few studies have made great progress either through image translation with deep latent features or neural rendering with explicit 3D features. However, both of them rely on large amounts of training data to generate realistic results, and the performance degrades on more accessible Internet videos due to insufficient training frames. In this paper, we demonstrate that the dynamic details can be preserved even when trained from short monocular videos. Overall, we propose a neural video rendering framework coupled with an image-translation-based dynamic details generation network (D2G-Net), which fully utilizes both the stability of explicit 3D features and the capacity of learning components. To be specific, a novel hybrid texture representation is presented to encode both the static and pose-varying appearance characteristics, which is then mapped to the image space and rendered as a detail-rich frame in the neural rendering stage. Through extensive comparisons, we demonstrate that our neural human video renderer is capable of achieving both clearer dynamic details and more robust performance even on accessible short videos with only 2k∼4k frames. Copyright © 2021, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

Algebraic and geometric structures inside the Birkhoff polytope

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rajchel-Mieldzioć, Grzegorz Korzekwa, Kamil Puchala, Zbigniew Życzkowski, Karol Center for Theoretical Physics Polish Academy of Sciences Warszawa02-668 Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Kraków30-348 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice44-100 Poland

The Birkhoff polytope Bd consisting of all bistochastic matrices of order d assists researchers from many areas, including combinatorics, statistical physics and quantum information. Its subset Ud of unistochastic matrices, determined by squared moduli of unitary matrices, is of a particular importance for quantum theory as classical dynamical systems described by unistochastic transition matrices can be quantised. In order to investigate the problem of unistochasticity we introduce the set Ld of bracelet matrices that forms a subset of Bd, but a superset of Ud. We prove that for every dimension d this set contains the set of factorisable bistochastic matrices Fd and is closed under matrix multiplication by elements of Fd. Moreover, we prove that both Ld and Fd are star-shaped with respect to the flat matrix. We also analyse the set of d × d unistochastic matrices arising from circulant unitary matrices, and show that their spectra lie inside d-hypocycloids on the complex plane. Finally, applying our results to small dimensions, we fully characterise the set of circulant unistochastic matrices of order d ≤ 4, and prove that such matrices form a monoid for d = 3. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

A brief review on EEG signal pre-processing techniques for real-time brain-computer interface applications

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Venkata Phanikrishna, B. Plawiak, Pawel Jaya Prakash, Allam VIT Vellore Thamilanadu Vellore632014 India Research Scholar National Institute of Technology Odisha Rourkela769008 India Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Krakow Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland VIT Vellore India

Electro Encephalo Gram (EEG) is a monitoring method used in biomedical and computer science to understand brain activity. The neurological abilities, disabilities, and thinking of a person depend upon the signals generated by the brain. Therefore, the analysis and classification of these signals play a prominent role in estimating a person’s behavior to certain events. Manually analyzing these signals is very tedious and time-consuming, so an automated scientific tool is required to analyze the brain signals. In this work, the authors are explored various pre-processing segmentation techniques that are helpful in an automatic machine and deep learning-based classification methods available for EEG signal processing. Most of the machine learning techniques are followed (i) pre-processing, (ii) feature extraction, and (iii) classification for analyzing the EEG signals. In contrast, deep learning techniques are followed only by pre-processing and classification steps. Manual feature extraction is not required in deep learning as machine learning methods, but pre-processing is common in both techniques. Extraction of the basic sub-band components from EEG signals such as delta (δ), theta (θ), alpha (α), beta (β), and gamma (γ) are very important in pre-processing stage. These sub-bands of EEG signal have extraordinary evidence related to multiple neurophysiological processes, which are useful for further prediction & diagnosis of diseases and other emotion-based applications. This review paper elaborates various elementary ideas of extracting EEG sub-bands and the role of EEG in Brain-computer Interface (BCI) in classification. © 2021, CC BY.

关键词： Feature extraction

Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jiang, Hao Jin, Cheng Lin, Huangjing Zhou, Yanning Wang, Xi Ma, Jiabo Ding, Li Hou, Jun Liu, Runsheng Chai, Zhizhong Luo, Luyang Shi, Huijuan Qian, Yinling Wang, Qiong Li, Changzhong Han, Anjia Chan, Ronald Cheong Kin Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Tencent AI Lab Shenzhen China Department of Pathology The First Affiliated Hospital Sun Yat-sen University Guangzhou China Center of Obstetrics and Gynecology Peking University Shenzhen Hospital Shenzhen China Institute of Obstetrics and Gynecology Shenzhen PKU-HKUST Medical Center Shenzhen China Shenzhen Key Laboratory on Technology for Early Diagnosis of Major Gynecologic Diseases Shenzhen China Department of Biomedical Informatics Harvard University United States Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Anatomical and Cellular Pathology The Chinese University of Hong Kong Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China Division of Life Science The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong

Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To address this issue, we introduced Smart-CCS, a generalizable Cervical Cancer Screening paradigm based on pretraining and adaptation to create robust and generalizable screening systems. To develop and validate Smart-CCS, we first curated a large-scale, multi-center dataset named CCS-127K, which comprises a total of 127,471 cervical cytology whole-slide images collected from 48 medical centers. By leveraging large-scale self-supervised pretraining, our CCS models are equipped with strong generalization capability, potentially generalizing across diverse scenarios. Then, we incorporated test-time adaptation to specifically optimize the trained CCS model for complex clinical settings, which adapts and refines predictions, improving real-world applicability. We conducted large-scale system evaluation among various cohorts. In retrospective cohorts, Smart-CCS achieved an overall area under the curve (AUC) value of 0.965 and sensitivity of 0.913 for cancer screening on 11 internal test datasets. In external testing, system performance maintained high at 0.950 AUC across 6 independent test datasets. In prospective cohorts, our Smart-CCS achieved AUCs of 0.947, 0.924, and 0.986 in three prospective centers, respectively. Moreover, the system demonstrated superior sensitivity in diagnosing cervical cancer, confirming the accuracy of our cancer screening results by using histology findings for validation. Interpretability analysis with cell and slide predictions further indicated that the system’s decision-making aligns with clinical practice. Smart-CCS represents a significant advancement in cervical cancer screening and highlights the potential for generalizable screening in real-word practice across diverse clinical contexts. Copyright ©

关键词： Diseases

Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Palka, Filip Książek, Wojciech Plawiak, Pawel Romaszewski, Michal Książek, Kamil Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Krakow Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland

This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectra differences. In our experiments we compare GA with a classic model optimisation through grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that during model optimisation it has access to examples similar to test data. We illustrate this with experiment highlighting the importance of a validation set. Copyright © 2020, The Authors. All rights reserved.

关键词： Genetic algorithms