检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Jiawei Chen, Shizhan Han, Zongbo Li, Wei Tang, Jijun Guo, Fei Tianjin University College of Intelligence and Computing Tianjin300072 China Nankai University College of Artificial Intelligence Tianjin518055 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Central South University School of Computer Science and Engineering Changsha410083 China

ISBN: (纸本)9798350386226

The emergence of single-cell multi-omics sequencing technology has enabled the simultaneous profiling of diverse omics data within individual cells. It offers a more comprehensive perspective on cellular phenotypes and heterogeneity. However, single-cell multi-omics data are inherently high-dimensional and heterogeneous. Due to technical limitations and scarce starting materials, the data are often affected by noise and dropout effects. To address these challenges, we propose a novel multitask driven multi-level dynamical fusion algorithm for single-cell multi-omics cell type annotation, named scMMDyn. Our approach incorporates reconstruction and classification auxiliary tasks to guide the training of trustworthy modules at both the feature and modality levels. It executes dynamical fusion during these stages and finally achieves cross-modality fusion via an attention mechanism. This method effectively mitigates data quality issues through reconstruction tasks and feature-level dynamical fusion while providing interpretability at both feature and modality levels. Experimental results across diverse single-cell multi-omics datasets show that our method surpasses existing approaches in cell type annotation. © 2024 IEEE.

关键词： cell type annotation multi-task mutli-level dynamical fusion single-cell multi-omics trustworthy

来源：评论

学校读者我要写书评

暂无评论

Mask Learning Enabled Multi-Rate Text Semantic Communications

Mask Learning Enabled Multi-Rate Text Semantic Communication...

引用

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Mingtong Zhang Haixia Zhang School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

Deep learning (DL)-based semantic communication has been deemed a promising communication paradigm to break through the bottleneck of traditional communications. However, most of the existing research focuses on designing semantic communication systems with a fixed rate, which is inflexible and inefficient for practical dynamic scenarios. To address this problem, this paper proposes a mask learning enabled multi-rate text semantic communication (MMSC) scheme. Specifically, by incorporating the target rate as side information, a lightweight rate-aware attention module is developed to improve the DL model's adaptability. Then, an effective feature masking method with learnable padding is proposed, wherein a padding-related regularization loss is designed to assist the recovery of the masked symbols. Through end-to-end mask learning, arbitrary rates with high semantic recovery performance can be achieved. Simulation results demonstrate that the proposed MMSC scheme outper-forms the other multi-rate semantic communication methods in terms of bilingual evaluation understudy (BLEU) score.

关键词： Deep learning Adaptation models Correlation Communication systems Simulation Conferences Semantics Symbols Vectors

来源：评论

学校读者我要写书评

暂无评论

Active Sensing for Target Tracking: A Bayesian Optimisation Approach

Active Sensing for Target Tracking: A Bayesian Optimisation ...

引用

International Conference on Information Fusion

作者： Xingchi Liu Lyudmila Mihaylova Department of Automatic Control and Systems Engineering University of Sheffield Sheffield UK Scientific Computing Department Rutherford Appleton Laboratory Science and Technology Facilities Council UK

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

Active sensing plays an essential role in searching and tracking a target without initial target state information. This paper studies the active sensing approach for sensor management problems using multiple unmanned aerial vehicles based on the received signal strength measurements of the target. A Bayesian optimisation-based approach is proposed which adopts the Gaussian process method to model the received signal strength in an area over time and then the expected improvement acquisition function is leveraged to decide where to take new measurements considering the uncertainty of the Gaussian process. A unique contribution of this paper consists of the designed spatial-temporal composite kernel function that accounts for the time-varying nature of the signal strength. Numerical results obtained from different measurement noise levels and varying initial Bayesian optimisation settings demonstrate that the proposed approach can efficiently schedule multiple unmanned aerial vehicles to locate the target within a minimum number of initial data. Particularly, it achieves at most $57 \%$ lower tracking error and $46 \%$ lower lost-track probability as compared to the benchmark approach.

关键词： Target tracking Atmospheric measurements Gaussian processes Particle measurements Autonomous aerial vehicles Sensors Bayes methods Kernel Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Joint Task Offloading and Service Caching for Vehicular Edge computing with Energy Constraints

Joint Task Offloading and Service Caching for Vehicular Edge...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Yifan Gao Haixia Zhang Qianqian Liu Yiqin Deng School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

Vehicular edge computing (VEC) enables vehicles to offload their tasks to idle vehicles for processing. To process tasks, the needed service model should be stored ahead. Considering the storage of vehicles is limited and downloading the service model upon tasks causes repeated data transmission, it is necessary to determine which service models should be cached and which tasks should be offloaded. For vehicles, the task completion time is crucial due to their mobility nature. Therefore, balancing the completion time and energy consumption for vehicles with limited battery capacity in highly dynamic system remains a significant challenge. To address this, we jointly designed task offloading and service caching scheme to minimize the tasks completion time in a cache-assisted VEC scenario while satisfying the long-term average energy constraints. We adopt Lyapunov optimization and Deep reinforcement learning (D RL) based Task offloading and Service caching (LDTS) to solve the proposed problem. Specifically, the Lyapunov optimization is used to tackle the issues of long-term energy consumption constraints by transforming the original problem into per-slot optimization problems that can be resolved using a model-free DRL method. Simulation results demonstrate that the LDTS method can minimize the completion time while satisfying the constraints of the long-term energy consumption budget. The results indicate that the LDTS method outperforms other benchmark methods.

关键词： Wireless communication Energy consumption Computational modeling Simulation Signal processing algorithms Signal processing Data models Resource management Optimization Edge computing

来源：评论

学校读者我要写书评

暂无评论

Dual-Scale Cellular Traffic Prediction Based on FastDTW for Graph Neural Network

Dual-Scale Cellular Traffic Prediction Based on FastDTW for ...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Junrong Jia Haixia Zhang Xiaotian Zhou School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

Cellular traffic prediction is crucial to the network efficiency as it provides prior knowledge to guide the wireless resource allocation. The artificial intelligence (AI) based traffic prediction can provide better prediction performance and has drawn increasing interests. Nevertheless, most existing works utilized Euclidean structure data, which can provide traffic prediction to only certain grid area rather than specific spot, such as each base station (BS). To give more precise BS level prediction, in this work we propose a dual-scale spatiotemporal prediction framework based on fast dynamic time warping (FastDTW) algorithm. The proposed framework can capture both the overall neighborhood relationship of historical traffic and the local neighborhood relationship graph to improve the prediction accuracy. More importantly, due to the utilization of FastDTW, it solves the disadvantage of the high complexity of the dynamic time warping (DTW) algorithm and completes the prediction at the BS level more efficiently. Simulation results confirms the generality and performance of the proposed method, which outperforms the benchmark algorithms.

关键词： Wireless communication Knowledge engineering Heuristic algorithms Simulation Signal processing algorithms Signal processing Predictive models Prediction algorithms Spatiotemporal phenomena Resource management

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Analysis Based on Video Face Analysis

Deepfake Detection Analysis Based on Video Face Analysis

引用

International Computer Sciences and Information Technologies (CSIT)

作者： Oleh Pitsun Nazar Melnyk Khrystyna Lipianina-Honcharenko Department of Computer Engineering West Ukrainian National University Ternopil Ukraine Department for Information-Computing Systems and Control West Ukrainian National University Ternopil Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The article examines the detection of manipulation of multimedia content, in particular in the form of videos and photos. The concept of deepfake is considered, the means and technologies involved in deepfake are analyzed, current and promising methods of detecting and preventing fake multimedia content are evaluated. Approaches to the methods of creating fakes on videos with elements of manipulation of the human face are defined. Faceswap and Deepfakes Web are found to be the most powerful solutions used to generate deepfakes. An analysis of tools for detecting deepfakes on the face was carried out, which made it possible to highlight the main technologies, libraries, and datasets used to search for fakes. The DeepFake Detection Challenge (DFDC) Model, Forensically, and others have been found to have significant potential and sample size to accurately detect human-faced fakes. This paper proposes a generalized approach to the detection of deep fakes on the human face using machine learning and computer vision technologies

关键词： Training Deep learning Deepfakes Recurrent neural networks Computational modeling Streaming media Libraries Software tools Information technology Faces

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Analysis Based on Video Face Analysis 19

Deepfake Detection Analysis Based on Video Face Analysis

引用

19th IEEE International Conference on Computer Science and Information Technologies, CSIT 2024

作者： Pitsun, Oleh Melnyk, Nazar Lipianina-Honcharenko, Khrystyna West Ukrainian National University Department of Computer Engineering Ternopil Ukraine West Ukrainian National University Department for Information-Computing Systems and Control Ternopil Ukraine

ISBN: (纸本)9798331542627

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mask Learning Enabled Multi-Task Semantic Communication with Adaptive Rate control

Mask Learning Enabled Multi-Task Semantic Communication with...

引用

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Yue Guan Haixia Zhang Mingtong Zhang School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

Semantic communication, a novel paradigm in communication, could significantly enhance communication efficiency by extracting and transmitting semantic information relevant to artificial intelligence (AI) tasks. In practice, a device may need to perform multiple AI tasks, and the semantic features required for each task are usually different. If multiple tasks share a single encoder to extract generalized semantic features, there is unnec-essary communication overhead. To solve the above issue, this paper introduces a mask learning enabled multi-task semantic communication system with adaptive rate control (ARC-MTSC) to extract and transmit customized semantic features according to different tasks. First, a lightweight feature selection network (FSN) is proposed, which can change the number of features depending on variable channel conditions and choose desired features for each task. Then, to achieve adaptive rate control, the FSN generates a mask vector to dynamically adjust the number of transmitted features, allowing the system to adaptively balance transmission rate and task performance. The results of the simulation demonstrate that the ARC-MTSC greatly decreases transmission overhead while maintaining negligible performance loss compared to the single-task baseline.

关键词： Performance evaluation Adaptive systems Simulation Semantics Feature extraction Multitasking Propagation losses Vectors Data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios engineering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

来源：评论

学校读者我要写书评

暂无评论

Parameter identification of nonlinear system via a dynamic frequency approach and its energy harvester application

引用

Acta Mechanica Sinica 2020年第3期36卷 606-617页

作者： Zhiwei Zhang Wei Wang Chen Wang Tianjin Key Laboratory of Nonlinear Dynamics and Chaos Control Tianjin UniversityTianjin 300350China School of Computing and Engineering Hud

A dynamic frequency-based parameter identification approach is applied for the nonlinear system with periodic *** from the energy equation,the presented method uses a dynamic frequency to precisely obtain the analytical limit cycle expression of nonlinear system and utilizes it as the mathematic foundation for parameter *** from the time-domain approaches,the strategy of using limit cycle to describe the system response is unaffected by the influence of phase *** analytical expression is fitted with the value sets from phase coordinates measured in periodic oscillation of the nonlinear systems,and the unknown parameters are identified with the interior-reflective Newton *** the performance of this identification methodology is verified by an oscillator with nonlinear stiffness and ***,numerical simulations under noisy environment also verify the efficiency and robustness of the identification ***,we apply this parameter identification method to the modeling of a large-amplitude energy harvester,to improve the accuracy of mechanical *** surprisingly,good agreement is achieved between the experimental data and identified *** also verifies that the proposed approach is less time-consuming and more accuracy in identification procedure.

关键词： Parameter identification Dynamic frequency Nonlinear system Energy harvester

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：