检索结果-内蒙古大学图书馆

作者： McMahon, W Newmeyer, K Campbell, R Parsons, B DEFENSE HIGH PERFORMANCE COMPUTING MODERNIZATION PROGRAM OFFICE LORTON VA

I am excited to share with you the DoD High Performance computing Modernization program (HPCMP) Annual Highlights for 2019 and2020. As you will see, the HPCMP has had another outstanding 2 years of accomplishments and growth. Using the 2018 National DefenseStrategy as a guidepost, we have focused on supporting our customers from the government, industry, and academia with state-of-the-arthigh-performance computing (HPC) services and resources to help them find solutions to the most challenging science and technology(S and T), test and evaluation (T and E), and acquisition engineering problems facing our Department of Defense. With national defense prioritiesshifting to potential conflict with near-peer adversaries like China and Russia, the HPCMP ecosystem that has been developed for the past25 years has proven it is ideally suited to these challenges.

关键词： Test and evaluation Computational fluid dynamics Data analysis Military research Aircrafts Engineers Ship design Unmanned aerial systems Virtual prototyping Covid-19 Warfare Application software Fluid dynamics High performance computing Navy Network protocols Prototypes Sars Students Air force research laboratories

来源：评论

学校读者我要写书评

暂无评论

Exploring Approximate Adders for Accuracy- and Energy-Quality VLSI Watermarking Systems Design 16

Exploring Approximate Adders for Accuracy- and Energy-Qualit...

引用

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

Intelligent Tutoring System: A Pedagogical Model Approach Based on Deep Reinforcement Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第4期52卷 1196-1212页

作者： Alshaikh, Fatema Hewahi, Nabil Computing and Information Science program University of Bahrain Bahrain Computer science working University of Bahrain Bahrain

The primary goals of research in the fields of Artificial Intelligence (AI) and Machine Learning (ML) are to develop an autonomous agent that can perform tasks or make decisions without human intervention. Deep Reinforcement Learning (DRL) is a machine learning technique employed in Intelligent Tutoring Systems (ITS). Deep reinforcement learning is the integration of Reinforcement Learning (RL) and Deep learning (DL) techniques. In ITS, DRL provides students with individualized learning experiences based on their learning styles and preferences. This work uses a deep reinforcement learning architecture to build a pedagogical model for ITS. We present four different models. The first model is based on the Deep Q-Network (DQN) structure. The second and third models (Double DQN and Dueling DQN) are extensions of the DQN algorithm and have been further developed to address some limitations of the DQN approach. Double DQN solves the problem of overestimation of Q-values, while Dueling DQN improves the representation of the value function. The last proposed model is a hybrid model that combines the standard DQN with a learning classifier system based on Genetic Algorithms (GA). The findings of the study indicate that both Double DQN and Dueling DQN showed complete data efficiency with 100% accuracy, 1.0 F1 score, and 1.0 precision at the highest training level of 1000 episodes and 10 steps, whereas DQN performed fairly but was outperformed by advanced techniques at the same configuration level. The standard DQN achieves a precision of 0.975, an F1 score of 0.987, and an accuracy of 98%. On the other hand, the hybrid approach, which combines GA with DQN, consistently performed worse than the other three individual models in all training setups. © (2025), (International Association of Engineers). All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving Multi-Domain Learning by Balancing Batches with Domain Information 23

Improving Multi-Domain Learning by Balancing Batches with Do...

引用

29th Brazilian Symposium on Multimedia and the Web, WebMedia 2023

作者： Bender, Alexandre Thurow Souza, Emillyn Mellyne Gobetti Bender, Ihan Belmonte Corrêa, Ulisses Brisolara Araujo, Ricardo Matsumura Postgraduate Program in Computing Pelotas Brazil

ISBN: (纸本)9798400709081

Collections of data obtained or generated under similar conditions are referred to as domains or data sources. The distinct conditions of data acquisition or generation are often neglected, but understanding them is vital to address any phenomena emerging from these differences that might hinder model generalization. Multi-domain learning seeks to find the best way to train a model so that it performs adequately in all domains used during training. This paper explores multi-domain learning techniques that use explicit information about the domain of an example, in addition to its class. This study evaluates a general approach (Stew) by mixing all available data and also proposes two novel batch domain-regularization methods: Balanced Domains and Loss Sum. We train machine learning models with the listed approaches using datasets with multiple sources of data for image and audio classification tasks. The results suggest training a model using the Loss Sum method improves the results of models otherwise trained in a mix of all available data. © 2023 ACM.

关键词： Data acquisition

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

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

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

Efficiency and complexity analysis of video-based and geometry-based point cloud encoders

引用

Journal of Real-Time Image Processing 2025年第3期22卷 1-14页

作者： Santos, Cristiano Rehbein, Gustavo Costa, Eduardo Corrêa, Guilherme Porto, Marcelo Video Technology Research Group Graduate Program in Computing Universidade Federal de Pelotas RS Pelotas Brazil

3D point clouds are increasingly used in applications, such as 3D remapping, cultural heritage preservation, and virtual/augmented reality. Given their large data volume, efficient compression is crucial. The MPEG group has introduced two standards: Geometry-based Point Cloud Compression (G-PCC), for static and dynamic-acquired point clouds, and Video-based Point Cloud Compression (V-PCC), specifically for dynamic point clouds. Although both approaches achieve effective data reduction, their high computational complexity limits real-time use, especially on resource-constrained devices. This paper analyzes the computational cost and coding efficiency of G-PCC and V-PCC, identifying the most time-consuming steps. In G-PCC, the Octree-RAHT configuration offers the best trade-off between efficiency and encoding time, with recoloring alone accounting for up to 70%. In V-PCC, video encoding dominates, consuming about 92% of the total time. These findings lay the groundwork for future optimizations to reduce the complexity of more efficient implementations. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Motion Picture Experts Group standards

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

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

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

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：