检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Fidêncio, Aline Xavier Grün, Felix Klaes, Christian Iossifidis, Ioannis Robotics and BCI Laboratory Institute of Computer Science Ruhr West University of Applied Sciences Mülheim an der Ruhr Germany Faculty of Electrical Engineering and Information Technology Ruhr University Bochum Bochum Germany KlaesLab Department of Neurosurgery University Hospital Knappschaftskrankenhaus Ruhr University Bochum Bochum Germany Faculty of Computer Science Ruhr University Bochum Bochum Germany

Brain-computer interfaces (BCIs) are developed for individuals with motor disabilities to offer alternative methods of communication, such as controlling and interacting with external devices. These systems are designed to improve quality of life, particularly for those with limited mobility. BCIs that rely on non-invasive recordings, such as electroencephalography (EEG), have been developed for a wide range of scenarios due to their practicality and safety. However, BCI performance is often limited by non-stationarities in the EEG data, which can arise from changes in the subject’s mental state or device characteristics, such as electrode impedance. These challenges motivate ongoing research into the development of adaptive BCIs capable of handling such variations. Over the past years, the interest in using the so-called error-related potentials (ErrPs) to improve BCI performance has increased. This is because ErrPs represent the neural response to both self-made and external errors and can be measured using non-invasive techniques. These signals have been combined with different BCI paradigms and used in different works to improve BCI performance via error correction or adaptation. In this work we introduce and explore a new approach for creating an adaptive ErrP-based BCI by evaluating the use of reinforcement learning (RL). This study demonstrates the feasibility of a RL-driven adaptive brain-computer interface (BCI) framework that integrates error-related potentials (ErrPs) and motor imagery. By employing two RL agents to dynamically adapt to EEG non-stationarities, we validate the framework on both a publicly available motor imagery dataset and using a novel experimental protocol involving a fast-paced game designed to enhance user engagement. Results highlight the framework’s potential: RL agents successfully learned control policies from user interactions, achieving robust performance across datasets. However, a critical finding emerged from the game-based p

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Full-Duplex Communication for ISAC: Joint Beamforming and Power Optimization

Full-Duplex Communication for ISAC: Joint Beamforming and Po...

引用

作者： He, Zhenyao Xu, Wei Shen, Hong Ng, Derrick Wing Kwan Eldar, Yonina C. You, Xiaohu Southeast University National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China The University of New South Wales School of Electrical Engineering and Telecommunications SydneyNSW2052 Australia Weizmann Institute of Science Faculty of Mathematics and Computer Science Rehovot7610001 Israel

Beamforming design has been widely investigated for integrated sensing and communication (ISAC) systems with full-duplex (FD) sensing and half-duplex (HD) communication, where the base station (BS) transmits and receives radar sensing signals simultaneously while the integrated communication operates in either downlink or uplink. To achieve higher spectral efficiency, in this paper, we extend existing ISAC beamforming design to a general case by considering the FD capability for both radar and communication. Specifically, we consider an FD ISAC system, where the BS performs target detection and communicates with multiple downlink users and uplink users reusing the same time and frequency resources. We jointly optimize the downlink dual-functional transmit signal and the uplink receive beamformers at the BS and the transmit power at the uplink users. The problems are formulated under two criteria: power consumption minimization and sum rate maximization. The downlink and uplink transmissions are tightly coupled due to both the desired target echo and the undesired interference received at the BS, making the problems challenging. To handle these issues in both cases, we first determine the optimal receive beamformers in closed forms with respect to the BS transmit beamforming and the user transmit power. Subsequently, we invoke these results to obtain equivalent optimization problems and propose iterative algorithms to solve them. In addition, we consider a special case under the power minimization criterion and propose an alternative low complexity design. Numerical results demonstrate that the optimized FD communication-based ISAC brings tremendous improvements in terms of both power efficiency and spectral efficiency compared to the conventional ISAC with HD communication. © 1983-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Advanced GAF routing protocol using the goal attainment method in WSN 2021

Advanced GAF routing protocol using the goal attainment meth...

引用

4th International Conference on Networking, information Systems and Security, NISS 2021

作者： Aznaoui, Hanane Ullah, Arif Raghay, Said Aziz, Layla LAMAI Laboratory FSTG Cadi Ayyad University Marrakech Morocco Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia

ISBN: (纸本)9781450388719

Various technologies have been developed to better improve lifestyles, including Wireless Sensor Networks (WSNs), used in multiple areas of research and consisting of a large number of sensor nodes. Drums in the area of interest, sensors collect data and transmit it to the base station (BS). Therefore, the key indicator for the design of WSN is the lifetime of the network. In this article, we provide an optimized GAF routing protocol that has been improved to optimize power consumption. It provides a multi-target version, which can maximize the coverage of communication between nodes to improve coverage efficiency. This is one of the key issues in the deployment of the sensor network, followed by the elected leader to minimize the proportion of active sensor nodes. The end goal is to minimize energy consumption. All these objectives are taken into account in our proposed version. The experimental results prove that in terms of performance, number of dead nodes, and energy consumption, the objectives proposed by this new version of GAF are superior to the existing basic and optimized GAF-GAF research. The practice has proven that the proposed target GAF can improve network lifetime. © 2021 ACM.

关键词： Dead nodes WSN Energy-Consumption Location-based routing Optimized GAF Attainment goals

来源：评论

学校读者我要写书评

暂无评论

CasCenter: A Cascaded Center Network for Visual Tracking

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Qun Zhang, Haijun Yang, Kai Shi, Yong-Guo Zeng, Deqiang Yap, Wun-She Xili University Town Department of Computer Science Harbin Institute of Technology Shenzhen518055 China WuHan Textile University School of Computer Science and Artificial Intelligence Wuhan430200 China Neijiang Normal University School of Mathematics and Information Science Data Recovery Key Laboratory of Sichuan Province Neijiang641100 China Universiti Tunku Abdul Rahman Lee Kong Chian Faculty of Engineering and Science Sungai Long43000 Malaysia

Object tracking has advanced significantly with Transformer-based architectures in recent years. However, replacing convolutional layers with global cross-attention in the tracking head of these architectures results in a loss of object-centric inductive bias. Consequently, existing Transformer-based methods often struggle with complex real-life scenarios, such as low resolution, background clutter, and scale variation. To address this issue, we propose a new vision Transformer-based anchor-free tracking framework named CasCenter. Specifically, the framework features a cascade attention module in the decoder that propagates tracking cues from the previous tracking head to refine object features in a coarse-to-fine manner, enabling the tracker to focus more effectively on the target. Additionally, to further improve tracking stability and accuracy, we incorporate SIoU loss, a multi-scale tracking head, and a Gaussian mask-constrained cross-attention mechanism that emphasizes target regions while suppressing background interference. Extensive experiments demonstrate the superiority of our proposed CasCenter. © 1975-2011 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Illumination-Enhanced Infrared and Low-Light Visible Image Fusion

Illumination-Enhanced Infrared and Low-Light Visible Image F...

引用

IEEE International Conference on Image Processing

作者： Guohua Lv Xinyue Fu Chaoqun Sima Yanlong Xu Baodong Zhang Hanju Bao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Lianxin Intelligent Technology (Shandong) Co. Ltd Jinan China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Infrared and visible image fusion aims to generate fused images with rich texture details and salient targets. However, existing methods often ignore illumination conditions, and the fusion results under low-light conditions lack texture details. To solve this problem, we propose an illumination-enhanced infrared and visible image fusion method, named IEFusion. Specifically, we first design a feature decomposition network based on retinex theory to obtain enhanced features of infrared and visible images. Then, the cross-modal feature fusion module is used to fuse important features. Finally, a gradient-enhanced image reconstructor is designed to enhance the gradient and generate a fused image. In addition, we design a contrastive learning module to guide the network to focus on deep features and maximize the mutual information of fused and enhanced images. Extensive experiments demonstrate the superiority of our IEFusion over the state-of-the-art methods, in both qualitative and quantitative metrics.

关键词： Measurement Fuses Lighting Contrastive learning Feature extraction Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Zhiqiang Zhang Yongqiang Jiang Qian Gao Zhipeng Wang Key Laboratory of Computing Power Network and information Security Ministry of Eaucation Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Jinan China

Existing multimodal recommendation research still faces some challenges, such as not being able to fully mine the implicit relevance information of neighbor nodes, and the unreasonable weight allocation to imbalanced nodes. To address the aforementioned challenges, this paper introduces a new multimodal recommendation model called NS-MAR+. Specifically, the model firstly constructs a neighbor similarity graph convolutional network to capture the implicit relevance information and reasonably assigns the attention weights through the graph attention mechanism. Secondly, the model introduces a modal alignment and fusion mechanism by using a multilayer perceptron (MLP) to map image and text features into a shared space for comparison and fusion. In addition, the model constructs a user co-interaction graph and an item semantic graph based on the original information and performs graph convolution operations to enhance the preference information of users and items, and to better capture the interactions and internal features between users and items. Finally, MLP is employed to aggregate user and item representations and predict personalized recommendation rankings. To validate the experiment's efficacy, this paper compares with several leading multimodal recommendation models on public datasets with a performance improvement of 1% to 3%. The experimental outcomes indicate that the model in this paper has good superiority and accuracy in multimodal recommendation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross Modal Sentiment Classification of Social Media Based on Meta Heuristic Algorithm

Cross Modal Sentiment Classification of Social Media Based o...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wantong Du Wanli Min Yushui Geng Hu Liang Hehu Zhou Ministry of Education Shandong Computer Science Center Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Synthesis Electronic Technology Co. Ltd

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The evolution of online social media has reshaped public behaviors, and social data infused with emotions provides crucial decision support for sentiment analysis tasks. Conventional multimodal approaches, influenced by redundant information in feature extraction during sentiment analysis, often focus solely on modality interactions without considering the unique content of each modality. This paper introduces the HGB-HFN model, addressing feature redundancy by optimizing extracted features using metaheuristic algorithm techniques, achieving a higher accuracy optimal feature dataset at lower computational costs. To counteract the neglect of modal-independent information, a hybrid fusion approach is adopted. It prioritizes visual features to extract precise semantic and emotional information from textual content, training multiple base classifiers to learn independent and diverse discriminative information. Comparative experiments on streaming datasets MOSI and MOSEI demonstrate the computational approach’s superiority in both accuracy and efficiency over existing methods.

关键词： Training Sentiment analysis Visualization Accuracy Social networking (online) Metaheuristics Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Grover's Quantum Algorithm Simulation: Cloud-Based Parallel Computing Enhancements 4

A Novel Approach to Grover's Quantum Algorithm Simulation: C...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Gejea, Adugna Mekonnen Mayakannan, S. Palacios, Rosana Marianela Hamad, Abdulsattar Abdullah Sundaram, Barani Alghamdi, Wajdi Bule Hora University Department of Computer Science Ethiopia Vidyaa Vikas College of Engineering and Technology Department of Mechanical Engineering Tamilnadu Namakkal India Department of Marketing Engineering Riobamba060155 Ecuador Dijlah University College Department of Medical Laboratory Techniques Baghdad Iraq King Abdulaziz University Faculty of Computing and Information Technology Department of Information Technology Jeddah21589 Saudi Arabia

ISBN: (纸本)9798350300888

A truly universal quantum computer is still on the small scale at the present. There has been no transition from the laboratory use of quantum computers to more widespread use of the technology. As a result, quantum simulation has emerged as the accepted norm for supporting the validation of quantum algorithms. Many conventional algorithms benefit from grover's quantum search method because it accelerates their usage of search heuristics. For better multi-core load balancing, memory utilization, and simulation efficiency, this research presented a high-performance grover method simulation that combines the benefits of grover's technique with the parallel of cloud computing. This study also suggests and experimentally compares five distinct cloud-based computing architectures that are well-suited to quantum simulation. Through research and testing, this study also verifies the optimization's efficiency. Depending on the size of the current configuration, the experimental results reveal that the simulation can reach 31 bits. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A Commitment and Ring Signature based Scheme for Amount and Identity Privacy Protection in Blockchain

A Commitment and Ring Signature based Scheme for Amount and ...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Shiyong Huang Haocong Li Ruoting Xiong Wei Ren Jie He Yi Ren School of Computer Science China University of Geosciences Wuhan China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University China School of Computer Science Beijing Jiaotong University Beijing China School of Computing Science University of East Anglia Norwich UK Beijing Key Laboratory of Urban Spatial Information Engineering Beijing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Blockchain has been envisioned as an anonymous cryptocurrency framework and can be applied in various applications such as e-payment, share economics, and distributed ledger. Although an account is anonymous, privacy in terms of consumption behaviors still imposes leakage risks. For example, an adversary may infer the consumption capability related to an account further by analyzing the history of consumption records. It is thus of critical importance to design a solution to preserve the anonymity of both transaction amount and transaction peer’s identity, which is changeable because the amount must be still authenticated in anonymity. In this paper, we propose a scheme by using Pedersen commitment to anonymize the transaction amount, and together using ring signature to conceal the transaction peer’s identity while maintaining authentication. Especially, we further improve the security of anonymous authentication enabled by ring signature by introducing accountability, which can defend against double-spending attacks by penalization and empower auditability. The extensive performance and security analysis justify the applicability of the proposed scheme.

关键词： Economics Privacy Distributed ledger Authentication Blockchains information filtering Security

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

arXiv

引用

arXiv 2024年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 2024, CC BY.

关键词： Qubits

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：