检索结果-内蒙古大学图书馆

16th IEEE Latin American Symposium on Circuits and Systems, LASCAS 2025

作者： Da Rosa, Morgana Da Costa, Eduardo Soares, Rafael Graduate Program on Computing Pelotas Brazil Graduate Program on Electronic Engineering and Computing Pelotas Brazil

ISBN: (纸本)9798331522124

Approximate computing (AxC) has emerged as a viable alternative to enhance computational efficiency by leveraging the intrinsic error resilience of many applications. One of the leading strategies of AxC involves exploring different approximation adder (AxA) configurations as a viable form of reducing power consumption in many applications. This work explores the use of AxAs in a hybrid watermarking technique that combines discrete Haar-Wavelet (DHWT) and discrete cosine transforms (DCT). The proposed hybrid method, HyDHWCT, integrates these transforms to improve robustness and imperceptibility in watermarking systems while optimizing for energy efficiency. We evaluate the performance of various AxAs, including Copy, ETA, LOA, Truncation (Trunc), VLSPPAs, and the AxPPA, regarding energy consumption, circuit area, and error resilience. Our results demonstrate that the AxPPA-based HyDHWCT offers superior accuracy and energy-quality trade-offs over other state-of-the-art AxAs. Specifically, the AxPPA on HyDHWCT with K = 1 achieves up to 72.85% energy savings and 88.32% area savings compared to the exact HyDHWCT while maintaining high accuracy, with a normalized cross-correlation (NC) of 0.9949 and a structural similarity (SSIM) of 0.9920 for the extracted watermark. These results make the AxPPA-based HyDHWCT a highly effective solution for robust and energy-efficient watermarking systems. © 2025 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Low-Power Level-2 Discrete Haar Wavelet Transform with Approximate Adders for ECG Signal 16

A Low-Power Level-2 Discrete Haar Wavelet Transform with App...

引用

16th IEEE Latin American Symposium on Circuits and Systems, LASCAS 2025

作者： Seidel, Henrique Da Rosa, Morgana Lopes, Rodrigo Da Costa, Eduardo Soares, Rafael Graduate Program on Computing Pelotas Brazil Graduate Program on Electronic Engineering and Computing Pelotas Brazil

ISBN: (纸本)9798331522124

We present an energy-efficient implementation of the level-2 Pruned Discrete Haar Wavelet Transform (PDHWT-2) for R-peak detection in ECG signals. Approximate computing techniques were employed, including five well-established approximate adders (AxPPA, COPY, ETA-I, LOA, and Trunc) and bit truncation (T), to reduce energy consumption while maintaining accuracy above 99% for reliable R-peak detection. By focusing on the second-level detail coefficient (D2) for peak detection and pruning the approximation coefficient, the PDHWT-2 design achieves significant reductions in computational complexity. The architecture, evaluated with ECG signals from the MIT-BIH database, maintained accuracy above 99% even with aggressive bit truncation and approximation, ensuring reliable medical-grade analysis. Integration of approximate adders (AxAs) and truncation enabled significant power and area savings. Specifically, the use of the AxPPA demonstrated power savings of up to 40% with area reductions of around 45%, making the PDHWT-2 a highly efficient solution for low-power ECG monitoring systems. © 2025 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhancing dynamic ensemble selection: combining self-generating prototypes and meta-classifier for data classification

引用

Neural computing and Applications 2024年第32期36卷 20295-20320页

作者： Manastarla, Alberto Silva, Leandro A. Graduate Program in Electrical Engineering and Computing Mackenzie Presbyterian University R. da Consolação 930 - Consolação SP Sao Paulo01302-907 Brazil Computing and Informatics Faculty and Graduate Program in Electrical Engineering and Computing Mackenzie Presbyterian University R. da Consolação 930 - Consolação SP Sao Paulo01302-907 Brazil

In dynamic ensemble selection (DES) techniques, the competence level of each classifier is estimated from a pool of classifiers, and only the most competent ones are selected to classify a specific test sample and predict its class labels. A significant challenge in DES is efficiently estimating classifier competence for accurate prediction, especially when these techniques employ the K-Nearest Neighbors (KNN) algorithm to define the competence region of a test sample based on a validation set (known as the dynamic selection dataset or DSEL). This challenge is exacerbated when the DSEL does not accurately reflect the original data distribution or contains noisy data. Such conditions can reduce the precision of the system, induce unexpected behaviors, and compromise stability. To address these issues, this paper introduces the self-generating prototype ensemble selection (***) framework, which combines meta-learning with prototype selection. The proposed meta-classifier of *** supports multiple classification algorithms and utilizes meta-features from prototypes derived from the original training set, enhancing the selection of the best classifiers for a test sample. The method improves the efficiency of KNN in defining competence regions by generating a reduced and noise-free DSEL set that preserves the original data distribution. Furthermore, the *** framework facilitates tailored optimization for specific classification challenges through the use of hyperparameters that control prototype selection and the meta-classifier operation mode to select the most appropriate classification algorithm for dynamic selection. Empirical evaluations of twenty-four classification problems have demonstrated that *** outperforms state-of-the-art DES methods as well as traditional single-model and ensemble methods in terms of accuracy, confirming its effectiveness across a wide range of classification contexts. © The Author(s), under exclusive licence to Springer-Ver

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

An Ultra Low-Energy VLSI Approximate Discrete Haar Wavelet Transform for ECG Data Compression 30

An Ultra Low-Energy VLSI Approximate Discrete Haar Wavelet T...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Cardozo, Arthur Rosa, Morgana M. A. Soares, Rafael Costa, Eduardo Bampi, Sergio Graduate Program on Computing Pelotas Brazil Graduate Program on Electronic Engineering and Computing Pelotas Brazil Porto Alegre Brazil

ISBN: (纸本)9798350326499

This work proposes an ultra-low-energy ECG data compression with VLSI DHWT-based (discrete Haar wavelet transform) architecture to enable storage and transmission in resource-constrained environments. We present original, pruned, and approximate DHWT (ODHWT, PDHWT, and AxDHWT, respectively) hardware architectures for ECG data compression at ultra-high energy efficiency. Our best proposal employing the AxDHWT hardware architecture requires just five additions only. Using a PDHWT technique to improve energy efficiency observes the evolution of the signal-to-noise ratio and the ultimate impact on the ECG data compression application. The DHWT-based configurations architecture proposal achieves a minimum compression ratio of 0.125 (i.e., 1/8) and a PRD (percent root difference) © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A NEWBORN EMBODIED TURING TEST FOR COMPARING OBJECT SEGMENTATION ACROSS ANIMALS AND MACHINES 12

A NEWBORN EMBODIED TURING TEST FOR COMPARING OBJECT SEGMENTA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Garimella, Manjulata Pak, Denizhan Wood, Justin N. Wood, Samantha M.W. Department of Informatics School of Informatics Computing & Engineering Department of Psychological & Brain Sciences Cognitive Science Program Program in Neuroscience

Newborn brains rapidly learn to solve challenging object perception tasks, including segmenting objects from backgrounds and recognizing objects across new viewing situations. Conversely, modern machine learning (ML) algorithms are "data hungry," requiring more training data than brains to reach similar performance levels. How do we close this learning gap between brains and machines? Here, we introduce a new benchmark-a Newborn Embodied Turing Test (NETT) for object segmentation-in which newborn animals and machines are raised in the same environments and tested with the same tasks, permitting direct comparison of their learning. First, newborn chicks were raised in controlled environments containing a single object rotating on a single background, then their recognition performance was tested across new backgrounds and viewpoints. Second, we performed "digital twin" experiments in which artificial agents were reared and tested in virtual environments that mimicked the rearing and testing conditions of the chicks. We inserted a variety of ML "brains" into the artificial agents and measured whether those algorithms learned common object recognition behavior as chicks. All newborn chicks solved this one-shot object segmentation task, successfully learning background-invariant object representations that generalized across new backgrounds and viewpoints. In contrast, none of the artificial agents solved the task, instead learning background-dependent representations that failed to generalize across new backgrounds and viewpoints. This digital twin design exposes core limitations in current ML algorithms in developing brain-like object perception. Our NETT is publicly available for comparing ML algorithms with newborn chicks. We argue that NETT benchmarks can help researchers build embodied AI systems that learn as efficiently and robustly as newborn brains. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Compact Model Build Upon Dynamic Weighting Artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compressors Topologies 30

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compresso...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Lopes, Rodrigo Antonietti, Leonardo Rosa, Morgana M. A. Costa, Eduardo Soares, Rafael Bampi, Sergio Graduate Program on Computing Pelotas Brazil Graduate Program on Electronic Engineering and Computing Pelotas Brazil PPGC & PGMICRO - Informatics Institute Porto Alegre Brazil

ISBN: (纸本)9798350326499

Addition units are present across many computational kernels inherent in various error-tolerant applications, including machine learning, signal, image, and video processing. Notably, adder compressors are the target when high speed and low power are the main design concerns. This work introduces energy-efficient structures of 3-2 approximate adder compressors (Ax3-2) and three distinct versions of 4-2 approximate adder compressors (Ax4-2). We compared our proposed Ax3-2 and Ax4-2 compressors with state-of-the-art energy-efficient approximate adder compressors (AxACs). Both Ax3-2 and Ax4-2 models passed through rigorous tests as standalone units. Furthermore, we integrated the Ax4-2 models into an essential application kernel appearing in video coding, i.e., the Sum Squared Differences (SSD) video accelerator. We introduce Ax3-2 and Ax4-2 that yield a new Pareto front concerning both energy-quality and area-quality trade-offs, thereby demonstrating a marked improvement over the prevailing state-of-the-art energy-efficient AxACs. © 2023 IEEE.

关键词： Adders

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Routing Protocol in Flying Ad Hoc Networks: A Review

引用

Computers, Materials & Continua 2025年第2期82卷 1615-1643页

作者： Priyanka Manjit Kaur Deepak Prashar Leo Mrsic Arfat Ahmad Khan Department of Computer Science and Engineering(CSE) Lovely Professional UniversityPhagwara144411India Department for Program Engineering Algebra UniversityGradiscanska 24Zagreb10000Croatia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

“Flying Ad Hoc Networks(FANETs)”,which use“Unmanned Aerial Vehicles(UAVs)”,are developing as a critical mechanism for numerous applications,such as military operations and civilian *** dynamic nature of FANETs,with high mobility,quick node migration,and frequent topology changes,presents substantial hurdles for routing protocol *** the preceding few years,researchers have found that machine learning gives productive solutions in routing while preserving the nature of FANET,which is topology change and high *** paper reviews current research on routing protocols and Machine Learning(ML)approaches applied to FANETs,emphasizing developments between 2021 and *** research uses the PRISMA approach to sift through the literature,filtering results from the SCOPUS database to find 82 relevant *** research study uses machine learning-based routing algorithms to beat the issues of high mobility,dynamic topologies,and intermittent connection in *** compared with conventional routing,it gives an energy-efficient and fast decision-making solution in a real-time environment,with greater fault tolerance *** protocols aim to increase routing efficiency,flexibility,and network stability using ML’s predictive and adaptive *** comprehensive review seeks to integrate existing information,offer novel integration approaches,and recommend future research topics for improving routing efficiency and flexibility in ***,the study highlights emerging trends in ML integration,discusses challenges faced during the review,and discusses overcoming these hurdles in future research.

关键词： FANET protocol machine learning

来源：评论

学校读者我要写书评

暂无评论

A Physical-Based Artificial Neural Networks Compact Modeling Framework for Emerging FETs

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 223-230页

作者： Yang, Ya-Shu Li, Yiming Kola, Sekhar Reddy Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory The Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Communications Engineering Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan

We report a compact modeling framework based on the Grove-Frohman (GF) model and artificial neural networks (ANNs) for emerging gate-all-around (GAA) MOSFETs. The framework consists of two ANNs;the first ANN constructed with the drain current model not only can capture the main trend of device I - V characteristics but also can predict its variation even when the amount of training data for the ANN is insufficient or outside the range of applied biases. The second one is then designed to improve the model accuracy by further minimizing the errors between the target and the model outputs. We implement the proposed framework to accurately model emerging GAA nanosheet (NS) MOSFETs and complementary FETs (CFETs) without suffering from divergent issues in circuit simulation. In addition, nonphysical behaviors, such as nonzero current at zero bias, do not occur in the modeling framework. Compared to recently reported machine-learning (ML) models, our approach can achieve a similar level of model accuracy with merely 20% amount of the training data. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Code Pattern Reuse and Pattern Preference Consistency in Novice programmers 23rd

An Empirical Study of Code Pattern Reuse and Pattern Prefe...

引用

23rd International Conference on Web-Based Learning, ICWL 2024 was held in conjunction with the 9th International Symposium on Emerging Technologies for Education, SETE 2024

作者： Lei, Philip I. S. Mendes, António José Lam, Chan-Tong CISUC Department of Informatics Engineering University of Coimbra Coimbra Portugal Computing Program Macao Polytechnic University Macao SAR China

ISBN: (纸本)9789819644063

After learning the basic features of a programming language, such as expressions and control statements, novice programmers need to combine these features to solve programming questions. Some of these combined code snippets are reusable constructs useful to solve future questions. They are referred to as plans, schemas, or patterns in the literature. An example of such a pattern is determining the equality of three values using the ‘equal and logical and operators. Previous research has investigated the acquisition of these patterns by observing and interviewing novice programmers as they solve programming problems. In this paper, we test the hypothesis that students tend to reuse acquired patterns to solve subsequent problems by analyzing a computer science education dataset called CodeWorkout, which contains students’ code submissions for introductory-level programming questions. We employed directed labeled tree to represent the Abstract Syntax Tree (AST) of the submitted code and the patterns. To search for a pattern, we first applied the subgraph isomorphism algorithm VF2 with wildcard node labels to identify candidate matches, followed by enforcing the proper ordering of descendant nodes between the pattern and the candidate matches. Experimental results demonstrate that our approach effectively identifies common usage of patterns. Moreover, the findings indicate that if a student employs a pattern in one question, they are likely to reuse the same pattern in a subsequent question. This paper also reveals that when multiple alternative patterns exist for the same function, students tend to maintain their preference for a particular alternative while solving different questions. These insights can inform future curriculum design and instructional strategies in programming education. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

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：