检索结果-内蒙古大学图书馆

Cross-modal heterogeneous graph reasoning network for visual question answering

Neural Computing and Applications 2025年 1-21页

作者： Zhang, Jing Teng, Jiong Ding, Weichao Wang, Zhe Department of Computer Science and Engineering East China University of Science and Technology Shanghai China

Most current Visual Question Answering (VQA) methods struggle to achieve effective cross-modal interaction between visual and semantic information, resulting in difficulties in accurately combining visual content with contextual semantics for answer prediction. To address this problem, a Cross-modal Heterogeneous Graph Reasoning Network (CHGRN) is proposed for VQA, incorporating a novel Cross-modal Reasoning Module (CRM) to enhance the interactive analysis between images and questions, enabling more profound joint reasoning of visual and semantic features. The CRM improves cross-modal information reasoning by effectively analyzing and understanding the visual semantic information in the target regions of images. Additionally, an answer type prediction module is introduced, employing multi-task learning with answer type annotations to filter out irrelevant semantic information, thereby improving reasoning accuracy. Moreover, the semantic-assisted attention-aligned decoder ensures precise alignment between visual and semantic data. Extensive experiments demonstrate that the proposed CHGRN achieves excellent performance in visual question answering and outperforms most state-of-the-art methods on widely used public datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid DF and SIR Forwarding Strategy in Conventional and Distributed Alamouti Space-Time Coded Cooperative Networks

引用

computer Modeling in engineering & sciences 2025年第2期142卷 1933-1954页

作者： Slim Chaoui Omar Alruwaili Faeiz Alserhani Haifa Harrouch Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Computer Science Department Applied CollegeUniversity of HailHail55424Saudi Arabia

In this paper,we propose a hybrid decode-and-forward and soft information relaying(HDFSIR)strategy to mitigate error propagation in coded cooperative *** the HDFSIR approach,the relay operates in decode-and-forward(DF)mode when it successfully decodes the received message;otherwise,it switches to soft information relaying(SIR)*** benefits of the DF and SIR forwarding strategies are combined to achieve better performance than deploying the DF or SIR strategy ***-form expressions for the outage probability and symbol error rate(SER)are derived for coded cooperative communication with HDFSIR and energy-harvesting ***,we introduce a novel normalized log-likelihood-ratio based soft estimation symbol(NL-SES)mapping technique,which enhances soft symbol accuracy for higher-order modulation,and propose a model characterizing the relationship between the estimated complex soft symbol and the actual high-order modulated ***-more,the hybrid DF-SIR strategy is extended to a distributed Alamouti space-time-coded cooperative *** evaluate the~performance of the proposed HDFSIR strategy,we implement extensive Monte Carlo simulations under varying channel *** demonstrate significant improvements with the hybrid technique outperforming individual DF and SIR strategies in both conventional and distributed Alamouti space-time coded cooperative ***,at a SER of 10^(-3),the proposed NL-SES mapping demonstrated a 3.5 dB performance gain over the conventional averaging one,highlighting its superior accuracy in estimating soft symbols for quadrature phase-shift keying modulation.

关键词： Cooperative communication soft information relaying soft symbols modeling cooperative diversity gain distributed Alamouti space-time code

来源：评论

学校读者我要写书评

暂无评论

Thermal Conductivity Measurement of Extrusion-Printed Silver Using Modulated Photothermal Radiometry

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2025年第3期4卷 126-136页

作者： Corona, Javier Schlake, Ellie Kandadai, Nirmala Oregon State University Department of Electrical and Computer Engineering CorvallisOR97331 United States

Flexible printed electronics is a rapidly growing field with applications in conformal and flexible devices. However, the physical properties of the films created by many state-of-the-art printing methods become highly dependent on printing parameters, resulting in varying thermal properties often differing significantly from their bulk ink components. To understand the influence of the printing process, we build upon our previous work, where a noncontact optical technique, known as modulated photothermal radiometry (MPTR), was used to measure the thermal conductivity of aerosol-jet-printed thin films. In this work, we use the method to study the thermal properties of extrusion-printed silver on glass and alumina substrates. A noise-resistant data analysis fitting technique is applied using a 2-D heat transfer model. The thermal conductivity measurement is validated using the Weidemann-Franz (WF) relationship from measured electrical conductivity values. © 2022 IEEE.

关键词： Extrusion

来源：评论

学校读者我要写书评

暂无评论

Sequential Design Process of a 350-kW Class Dual Three-Phase IPMSM for a Wheeled Armored Vehicle

IEEE Open Journal of Industry Applications

引用

IEEE Open Journal of Industry Applications 2025年 6卷 237-248页

作者： Son, Ji-Chang Kwon, Min-Su Lim, Dong-Kuk University of Ulsan Department of Electrical Electronics and Computer Engineering Ulsan44610 Korea Republic of

Optimal design of a traction motor is a complex process, as various requirements and constraints need to be satisfied. In addition, consideration of various physical aspects, such as stress and heat, is necessary to ensure the stability of the motor, including mechanical rigidity and insulation breakdown. In this article, to derive the optimal design of an interior permanent magnet synchronous motor (IPMSM), a novel sequential design process consisting of conceptual design, detailed design, and optimal design is proposed. The conceptual design enables the rapid execution of multiple case studies, as static electromagnetic analysis is used. The overall geometric parameters are determined through electromagnetic analysis in the detailed design stage and an initial model that satisfies the requirements is derived. Finally, in the optimal design stage, the optimal model is quickly derived using a machine learning method, and the stability of the model is examined through multiphysics analysis. To validate the applicability to the practical motor, design optimization for a 350-kW class dual three-phase IPMSM for a wheeled armored vehicle is conducted, and the feasibility of the proposed method is verified based on the experimental results of the manufactured prototype. © 2020 IEEE.

关键词： Armored vehicles

来源：评论

学校读者我要写书评

暂无评论

Secure signal and image transmissions using chaotic synchronization scheme under cyber-attack in the communication channel

引用

Soft Computing 2025年第1期29卷 339-353页

作者： Nobakht, Shaghayegh Ahmadi, Ali-Akbar Industrial Automation Laboratory Electrical and Computer Engineering Department Kharazmi University Tehran Iran

In this paper, problem of secure message (signal and image) transmission is studied. The message is encrypted by masking it with a chaotic system state and then transmitted to receiver-side via a communication channel. It is assumed that the communication channel may be prone to a cyber-attack. The transmission system dynamics in presence of the cyber-attack in the communication channel is modeled by a singular dynamical system. Then, at the receiver-side, a novel observer is designed to recover the message together with the cyber-attack signal. Estimation of the cyber-attack is crucial for monitoring the communication channel and enable a network supervisor to mitigate the adverse consequences and make an appropriate strategy. It is assumed neither restrictions on the message nor on the cyber-attack signals. This makes the proposed scheme, the best solution in the real applications. Moreover, comparing to the existing methods which two public and private channels are required, only one communication channel is used in this paper for transmission the encrypted signal which results in a cheaper solution. Solving the optimization problem can be easily performed with the help of the existing toolboxes such as YALMIP and CVX software in MATLAB. Finally, numerical simulations for signal and image transmission are presented to justify the applicability and superior performance of the proposed scheme. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Printing Stretchable Electronics With Fused Filament Fabrication

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2025年第2期4卷 98-107页

作者： Jahan, Sharmin Lazarus, Nathan University of Delaware Electrical and Computer Engineering Department NewarkDE19716 United States

Additive manufacturing is a powerful approach forintegrating flexible and stretchable conductors into complex3-D structures, but many current printing technologies, suchas direct ink writing (DIW), are expensive and challengingto access for many potential users, such as hobbyists andsmall companies. In this work, a low-cost commercial fusedfilament fabrication (FFF) 3-D printer is used to manufacturelow-resistivity stretchable serpentine conductors. By using dualextruder heads, serpentines are printed in a highly conductivemetal-particulate-based composite on a thermoplastic elastomer(TPE) part and demonstrated to survive mechanical strains of upto 25%, sufficient for use in close contact with the human *** electroless plating is also demonstrated to metalize theprinted traces, depositing a thin layer of copper for improvedelectrical conductivity. Using this approach, we demonstrateconductivity improvements by about three orders of magnitude(∼ 103) over past FFF printed serpentines, a major milestonein making stretchable electronics cheaper and more *** resulting stretchable conductors are then demonstrated toprint devices, including stretchable inductors and stretchableinterconnect on a soft robotic actuator. © 2022 IEEE.

关键词： Reinforced plastics

来源：评论

学校读者我要写书评

暂无评论

Design and Utilization of Multiskewed Multibit Flip-Flop Cells for Timing Optimization: Design and Technology Co-Optimization Approach

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 1084-1097页

作者： Kim, Suwan Kim, Taewhan Seoul National University Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Utilizing multibit flip-flops (MBFFs) in circuit implementation offers a considerable saving on the dynamic power dissipated at the clock networks. However, indiscreetly allocating MBFFs by grouping single-bit flip-flops at the logic synthesis or placement stage in order to greedily save dynamic power severely hinders a full applicability of useful clock skew scheduling to the individual flip-flops in MBFFs, failing in effectively optimizing circuit timing. This is because the two internal clock inverters, consequently, the clock skew value, in an MBFF are shared by all of the flip-flops in the MBFF. This work overcomes this inherent limitation of inflexibility in MBFFs for useful clock skew scheduling by proposing a comprehensive design and technology co-optimization (DTCO) framework. To this end, we devise a new layout of MBFF cells called multiskewed MBFF layout, in which different clock skew values can be set to the individual internal flip-flops at the cost of additional internal clock inverters. With the multiskewed MBFFs, we propose a three-step DTCO flow: 1) DTCO-based flip-flop clustering at the logic stage, which clusters flip-flops considering multiskewed MBFFs;2) DTCO based on in-place MBFF debanking technique at the preroute stage to facilitate the full applicability of useful skew scheduling at the subsequent stages;and 3) DTCO utilizing MBFF cell layout diversification at the post-route stage, by which useful clock skew scheduling can effectively resolve timing violations. Through experiments with OpenCores benchmark circuits, it is shown that our proposed DTCO flow of reinforcing the effectiveness of useful clock skew scheduling on circuits with MBFF instances is able to reduce the worst and total negative slacks by 36.73% and 50.76%, respectively, while decreasing the clock and total power consumption by 43.46% and 22.70% over that produced by the conventional flow using a state-of-the-art commercial tool. © 2024 IEEE.

关键词： Flip flop circuits

来源：评论

学校读者我要写书评

暂无评论

Exploring Hyperdimensional Computing Robustness Against Hardware Errors

引用

IEEE Transactions on computers 2025年第6期74卷 1963-1977页

作者： Zhang, Sizhe Juretus, Kyle Jiao, Xun Villanova University Department of Electrical and Computer Engineering VillanovaPA19085 United States

Brain-inspired hyperdimensional computing (HDC) is an emerging machine learning paradigm leveraging high-dimensional spaces for efficient tasks like pattern recognition and medical diagnostics. As a lightweight alternative to deep neural networks, HDC offers smaller model sizes, reduced computation, and memory-centric processing. However, deploying HDC in safety-critical applications, such as healthcare and robotics, is challenged by hardware-induced errors. This paper investigates HDC's robustness to memory errors via extensive bit-flip injection experiments on item and associative memories. Results reveal that certain bit-flips severely degrade accuracy. To address this, we introduce the Hyperdimensional Bit-Flip Search (HD-BFS), a similarity-guided method for identifying vulnerabilities and crafting efficient attacks, where flipping just 6 critical bits—3.9% of random bit-flips—reduces accuracy to chance levels. We further propose Hyperdimensional Accelerated Bit-Flip Search (HD-ABFS), which narrows the search space by targeting critical dimensions and most significant bits (MSBs), achieving up to 282x speedup over HD-BFS. Finally, we develop an effective protection mechanism to enhance model safety. These insights highlight HDC's resilience to random errors, offer robust defenses against targeted attacks, and advance the security and reliability of HDC systems. © 1968-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Entanglement-Controlled Quantum Federated Learning

引用

IEEE Internet of Things Journal 2025年第11期12卷 18318-18330页

作者： Park, Soohyun Lee, Hyunsoo Jung, Soyi Park, Jihong Bennis, Mehdi Kim, Joongheon The Division of Computer Science Sookmyung Women’s University Seoul04310 Korea Republic of The Department of Electrical and Computer Engineering Korea University Seoul02841 Korea Republic of The Department of Electrical and Computer Engineering Ajou University Suwon16499 Korea Republic of Singapore The Centre for Wireless Communications University of Oulu Oulu90014 Finland

According to the advances in quantum computing and distributed learning, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. To successfully opeate QFL under various and dynamic channel conditions in Internet of Things (IoT) environments, this paper develops a novel depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs), and thus, proposes an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eSQNNs. Even though the proposed eSQNN-based eSQFL is superior, training the depth-controllable eSQNN architecture is challenging due to high entanglement entropy and inter-depth interference. Therefore, the proposed method in this paper mitigates the interference using entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing inter-depth quantum state differences, respectively. Furthermore, the proposed method optimizes the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. The novelty of this work is evaluated via extensive simulations in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Data Collection for Bayesian Inference of Hidden Markov Models

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1217-1232页

作者： Alali, Mohammad Imani, Mahdi Northeastern University Department of Electrical and Computer Engineering BostonMA02115 United States

Hidden Markov models (HMMs) are a powerful class of dynamical models for representing complex systems that are partially observed through sensory data. Existing data collection methods for HMMs, typically based on active learning or heuristic approaches, face challenges in terms of efficiency in stochastic domains with costly data. This article introduces a Bayesian lookahead data collection method for inferring HMMs with finite state and parameter spaces. The method optimizes data collection under uncertainty using a belief state that captures the joint distribution of system states and models. Unlike traditional approaches that prioritize short-term gains, this policy accounts for the long-term impact of data collection decisions to improve inference performance over time. We develop a deep reinforcement learning policy that approximates the optimal Bayesian solution by simulating system trajectories offline. This pretrained policy can be executed in real time, dynamically adapting to new conditions as data is collected. The proposed framework supports a wide range of inference objectives, including point based, distribution based, and causal inference. Experimental results across three distinct systems demonstrate significant improvements in inference accuracy and robustness, showcasing the effectiveness of the approach in uncertain and data-limited environments. © 2020 IEEE.

关键词： Deep reinforcement learning

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：