检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Tianjian Zhou, Hao Liu, Shuo Guo, Kaiwen Hou, Yiwen Du, Haohua Liu, Zhi Li, Xiang-Yang School of Computer Science and Technology University of Science and Technology China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology China Deqing Alpha Innovation Institute Zhejiang Huzhou China School of Cyber Science and Technology Beihang University China Department of Computer and Network Engineering The University of Electro-Communications Tokyo182-8585 Japan

The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations for particular tasks. However, building the feature extraction component for such systems requires extensive domain-specific expertise or data. The exceptionally rapid development of foundation models is likely to usher in newfound abilities in such intelligent sensing. We propose a new scheme for sensing model, which we refer to as semi-generalist sensing model (SGSM). SGSM is able to semiautomatically solve various tasks using relatively less task-specific labeled data compared to traditional systems. Built through the analysis of the common theoretical model, SGSM can depict different modalities, such as the acoustic and Wi-Fi signal. Experimental results on such two heterogeneous sensors illustrate that SGSM functions across a wide range of scenarios, thereby establishing its broad applicability. In some cases, SGSM even achieves better performance than sensor-specific specialized solutions. Wi-Fi evaluations indicate a 20% accuracy improvement when applying SGSM to an existing sensing model. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Modeling topical relevance for multi-turn dialogue generation 29

Modeling topical relevance for multi-turn dialogue generatio...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Hainan Lan, Yanyan Pang, Liang Chen, Hongshen Ding, Zhuoye Yin, Dawei CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS China *** Beijing China University of Chinese Academy of Sciences China

ISBN: (纸本)9780999241165

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

A Fusion Neural network Incorporating Attention for Sensor-Based Human Activity Recognition 3

A Fusion Neural Network Incorporating Attention for Sensor-B...

引用

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lu, Limeng Zhang, Chuanlin Cao, Kai Deng, Dao Institute of Chinese Ethnic Information Technology Northwest Minzu University Lanzhou China Key Laboratory of China's Ethnic Languages and Information Technology Ministry of Education Lanzhou China Northwest Minzu University School of Mathematics and Computer Science Lanzhou China Northwest Minzu University Key Laboratory of Streaming Data Computing Technologies and Application Lanzhou China

ISBN: (纸本)9781665459112

Even though the RNN, LSTM, and other networks are used to extract dependencies in time series, sensor-based human behavior recognition (HAR) still faces some difficulties, and the ability of deep learning (DL) networks to extract features still needs to be improved. We propose a fusion neural network in which an optimized small optimized Convolutional Block Attention Module (MP-CBAM) is suitable for HAR tasks to extract samples. The MP-CBAM is added to two branches Convolutional Neural network (CNN) with different convolution kernel sizes, and the fused features are labeled with GRU for temporal dependence. Then the softmax function is used for classification. We validate on benchmark datasets UCI-HAR and WISDM and accuracies of 97.15% and 9S.9S% are obtained, respectively, demonstrating the adaptation of our framework to both single-sensor and multi-sensor devices. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Neural network Based Preselection for Expensive Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Transfer Learning network for Characterization of Stroke Patients’ Motor Execution from Multi-Channel EEG-Recordings

An Efficient Deep Transfer Learning Network for Characteriza...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Oluwarotimi Williams Samuel Mojisola Grace Asogbon Frank Kulwa Alistair A. McEwan Sunday Timothy Aboyeji Rami Khushaba Peng Fang Guanglin Li School of Computing and Data Science Research Centre University of Derby Derby United Kingdom Shenzhen Institute of Advanced Technology (SIAT) Chinese Academy of Sciences (CAS) Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS Shenzhen China Australian Centre for Field Robotics Sydney University Chippendale NSW Australia

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Recent advances in stroke rehabilitation technology have been focused on developing Intelligent Rehabilitation Robots (IRR) that can effectively engage post-stroke patients (PSP) in intuitive motor training for full function recovery. Most existing rehabilitation robots incorporate functionalities that are passive in nature, constraining PSP to predetermined trajectories that often deviate from patients’ limb movement intentions, consequently hindering recovery. To resolve this issue, a robust deep-transfer learning driven network (DTLN) is developed to adequately characterize PSP’s motion intention signatures from neural oscillations towards achieving intuitive and active training. Thus, we investigated and proposed the utilization of mu-frequency spectrum (muFS) based CWT approach for Scalograms construction, which serves as inputs to the DTLN model that characterizes multiple classes of PSP’s motor execution signatures from multi-channel electroencephalography (EEG) recordings. Then, we evaluated the proposed method using EEG data from six PSP and compared the decoding results to those of related approaches under similar experimental settings. The proposed method resulted in a significant increment of 10.84 % - 13.19% decoding accuracy across stroke patients and better convergence in comparison to other methods. Additionally, the method exhibited distinct task separability for individual motor execution signature across patients. In conclusion, our method offers a consistently accurate decoding of motor tasks that could enable intuitively active robotic training in PSPs with impaired motor function.

关键词： Training Accuracy Transfer learning Stroke (medical condition) Motors Assistive robots Electroencephalography Decoding Trajectory Robots

来源：评论

学校读者我要写书评

暂无评论

Energy-time entanglement coexisting with fiber-optical communication in the telecom C band

引用

Physical Review A 2023年第2期108卷 L020601-L020601页

作者： Yun-Ru Fan Yue Luo Zi-Chang Zhang Yun-Bo Li Sheng Liu Dong Wang De-Chao Zhang Guang-Wei Deng You Wang Hai-Zhi Song Zhen Wang Li-Xing You Chen-Zhi Yuan Guang-Can Guo Qiang Zhou Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu 610054 China Department of Fundamental Network Technology China Mobile Research Institute Beijing 100053 China Southwest Institute of Technical Physics Chengdu 610041 China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai 200050 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei 230026 China

We study the coexistence of energy-time entanglement with fiber-optical communication in the telecom C band. The property of noise from wavelength-multiplexed classical channels is characterized with different wavelength settings. With the largest noise, i.e., the worst case, we measure the entanglement property of the distributed energy-time entangled photon pairs at different data rates of fiber-optical communication. After being distributed over 40-km spooled fiber coexisting with a bidirectional data rate of 20 Gbps, a visibility of 82.01±1.10% is obtained by measuring the Franson interference. With the Bennett-Brassard-Mermin 1992 (BBM92) protocol, a secret key rate of 343 bits per second is reached over the 40-km spooled fiber coexisting with a bidirectional data rate of 10 Gbps. Our result paves the way for developing a cost-effective quantum entanglement network compatible with fiber communication systems.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Load Balancing Strategy Of "Container Virtual Machine" Cloud Microservice Based On Deadline Limit 14

A Load Balancing Strategy Of "Container Virtual Machine" Clo...

引用

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Xia, Hong Liu, MengDi Chen, YanPing Jin, XiaoMin Wang, ZhongMin Wang, FengWei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China ZTE Corporation No.55 Hi-tech Road South Shenzhen518057 China

ISBN: (纸本)9781665499781

Aiming at the problem of workflow scheduling under the "container virtual machine" two-tier structure in cloud microservice workflow application, a "container virtual machine" load balancing strategy based on deadline limit (container virtual machine load) is proposed. Balance strategy), CV LBMs strategy first obtains the optimal economic configuration of the corresponding instance of the micro service according to historical data, and calculated the list of remaining resources in the leased virtual machine;Determined whether the virtual machine is on the virtual machine according to the container image list in the virtual machine. Whether a corresponding container image exists, and create a new container on the virtual machine that already has a container image to reduce the time to extract the container image. The workflow simulation results showed that compared with the existing algorithms, the C-V LBMs strategy had the ability to meet the deadline success rate and reduced the cost. © 2022 IEEE

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A DoS-attack Resilient Control Approach for AIOT-enabled Systems

A DoS-attack Resilient Control Approach for AIOT-enabled Sys...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Cao, Xiaoya Chen, Zhenya Liu, Weisheng Liu, Yuanlong Wang, Wenting Wang, Xin Yang, Ming Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China State Grid Shandong Electric Power Company Jinan China State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (纸本)9798350312270

This paper presents a novel controller design for dealing with the challenges posed by Denial-of-Service (DoS) attacks in the context of Artificial Intelligence of Things (AIOT). The proposed design employs a prediction approach that utilizes uniform quantization for both encoder and decoder, aiming to effectively mitigate data loss during data transmission in scenarios involving DoS attacks. Furthermore, the study investigates the application of dynamic system design as a means to enhance the security defense mechanisms of AIOT, consequently bolstering the overall resilience of the system. The effectiveness and practicality of the proposed approach are validated through comprehensive simulations, providing empirical evidence of its efficacy. © 2023 IEEE.

关键词： System stability

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：