检索结果-内蒙古大学图书馆

Novel Sparse Codebook Design for MIMO-SCMA

IEEE Transactions on Vehicular technology 2025年第5期74卷 8407-8412页

作者： Lei, Tuofeng Luo, Qu Ni, Shuyan Chen, Shimiao Yu, Lisu Xiao, Pei Space Engineering University Key Laboratory of Intelligent Space TTC&O Ministry of Education Beijing101416 China University of Electronic Science and Technology of China National Key Laboratory of Science and Technology on Communications Chengdu610054 China Nanchang University School of Information Engineering Nanchang330031 China Xidian University State Key Laboratory of ISN Xi'an710071 China

The combination of multiple-input multiple-output (MIMO) and sparse code multiple access (SCMA), referred to as MIMO-SCMA, can be leveraged to achieve high spectrum efficiency and provide massive connectivity for future machine-type communication networks. This paper aims to design enhanced sparse codebooks for MIMO-SCMA by jointly combining frequency and spatial diversity over Rayleigh fading channels. First, based on the pairwise error probability (PEP), novel codebook design criteria have been presented, namely the hybrid minimum product distance of the Euclidean distance (MPD-ED) and the minimum Euclidean distance of the superimposed constellation at each frequency element (MED-FE). Then, enhanced mother constellations (MC) are proposed by maximizing the MPD-ED of the MC based on the alternating optimization. Subsequently, the multi-dimensional codebooks are obtained by applying user-specific rotation of the proposed MC to maximize the MED-FE, where the unitary rotations are considered to fully leverage the Euclidean space of the transmit antennas while maintaining the MPD-ED value of the codebook. Finally, numerical results demonstrate that the proposed approach significantly outperforms the state-of-the-art codebooks. © 1967-2012 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Secure Federated Learning With Local Differential Privacy and Incentivization

IEEE Transactions on Privacy

引用

IEEE Transactions on Privacy 2024年第1期1卷 31-44页

作者： Chaudhury, Saptarshi De Reddy, Likhith Varun, Matta Sengupta, Tirthankar Chakraborty, Sandip Sural, Shamik Vaidya, Jaideep Atluri, Vijay Indian Institute of Technology Department of Computer Science and Engineering Kharagpur721302 India Rutgers University Management Science and Information Systems Department NewarkNJ07102-3122 United States

Interest in supporting Federated Learning (FL) using blockchains has grown significantly in recent years. However, restricting access to the trained models only to actively participating nodes remains a challenge even today. To address this concern, we propose a methodology that incentivizes model parameter sharing in an FL setup under Local Differential Privacy (LDP). The nodes that share less obfuscated data under LDP are awarded higher quantum of tokens, which they can later use to obtain session keys for accessing encrypted model parameters updated by the server. If one or more of the nodes do not contribute to the learning process by sharing their data, or share only highly perturbed data, they earn less number of tokens. As a result, such nodes may not be able to read the new global model parameters if required. Local parameter sharing and updating of global parameters are done using the distributed ledger of a permissioned blockchain, namely HyperLedger Fabric (HLF). Being a blockchain-based approach, the risk of a single point of failure is also mitigated. Appropriate chaincodes, which are smart contracts in the HLF framework, have been developed for implementing the proposed methodology. Results of an extensive set of experiments firmly establish the feasibility of our approach. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Learning label-specific features for decomposition-based multi-class classification

引用

Frontiers of Computer science 2023年第6期17卷 101-110页

作者： Bin-Bin JIA Jun-Ying LIU Jun-Yi HANG Min-Ling ZHANG College of Electrical and Information Engineering Lanzhou University of TechnologyLanzhou 730050China School of Computer Science and Engineering Southeast UniversityNanjing 210096China Key Laboratory of Computer Network and Information Integration(Ministry of Education) Southeast UniversityNanjing 210096China

Multi-class classification can be solved by decomposing it into a set of binary classification problems according to some encoding rules,e.g.,one-vs-one,one-vs-rest,error-correcting output *** works solve these binary classification problems in the original feature space,while it might be suboptimal as different binary classification problems correspond to different positive and negative *** this paper,we propose to learn label-specific features for each decomposed binary classification problem to consider the specific characteristics containing in its positive and negative ***,to generate the label-specific features,clustering analysis is respectively conducted on the positive and negative examples in each decomposed binary data set to discover their inherent information and then label-specific features for one example are obtained by measuring the similarity between it and all cluster *** clearly validate the effectiveness of learning label-specific features for decomposition-based multi-class classification.

关键词： machine learning multi-class classification error-correcting output codes label-specific features

来源：评论

学校读者我要写书评

暂无评论

HGCNN: Deep Graph Convolutional Network for Sensor-Based Human Activity Recognition 8

HGCNN: Deep Graph Convolutional Network for Sensor-Based Hum...

引用

8th International Conference on Big Data and information Analytics, BigDIA 2022

作者： Nian, Aixin Zhu, Xianqiang Xu, Xiang Huang, Xueqin Wang, Fei Zhao, Yu Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

Sensor-based human activity recognition(HAR) tasks often face issues of low-quality data, such as insufficient or incorrect data labels. But natural human activities are often con-textual, for example, an athlete needs to stretch before exercising. Therefore, we hypothesize unlabeled activity can be identified by contextual activity associations. Early statistical machine learning algorithms that rely on manual feature extraction frequently have knowledge constraints and can only capture superficial features, which prevents them from producing acceptable results in unsupervised or semisupervised circumstances. Deep learning on graph has made enormous strides in several disciplines in recent years because of its quick development. To address the issues highlighted above, we design a deep learning model called HGCNN based on graph neural network (GNN). Besides, we also make the sensor's time series data model as a fully connected subgraph with a sliding window size. Afterwards, a spectral graph convolution method is used to extract activity contextual relationship on the subgraph. The classification accuracy of this method on the Extra-Sensory dataset reaches 99.54% and HGCNN shows superior performance relative to previously CNN baseline, improving on macro F1-score reached up to 0.87. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A compact and closed-loop spin-exchange relaxation-free atomic magnetometer for wearable magnetoencephalography

引用

Chinese Physics B 2023年第4期32卷 277-282页

作者：郭清乾胡涛冯晓宇张明康陈春巧张欣姚泽坤徐佳玉王青付方跃张寅常严杨晓冬 Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of SciencesSuzhou 215163China School of Biomedical Engineering(Suzhou) Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230026China Jihua Laboratory Foshan 528000China School of Electronic and Information Engineering Changchun University of Science and TechnologyChangchun 130022China

Atomic magnetometers operated in the spin-exchange relaxation-free(SERF)regime are the promising sensor to replace superconducting quantum interference devices(SQUIDs)in the biomagnetism *** SERF magnetometer with compact size and good performance is crucial to the new generation of wearable magnetoencephalography(MEG)*** this paper,we developed a compact and closed-loop SERF magnetometer with the dimensions of 15.0×22.0×30.0 mm^(3)based on a single-beam *** bandwidth of the magnetometer was extended to 675 Hz while the sensitivity was maintained at 22 f T/Hz^(1/2).A nearly 3-fold enhancement of the bandwidth was obtained in comparison with the open-loop *** implementation of the closed-loop control also greatly improved the dynamic range,enabling the magnetometer to be robust against the disturbance of the ambient ***,the magnetometer was successfully applied for the detection of humanα-rhythm and auditory evoked fields(AEFs),which demonstrated the potential to be extended to multi-channel MEG measurements for future neuroscience studies.

关键词： atomic magnetometer miniaturization closed-loop magnetoencephalography(MEG)

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-Agent Resource Allocation Based on Transformer and DRL for Cloud XR Hybrid Content Transmission

引用

IEEE Internet of Things Journal 2025年第12期12卷 22110-22127页

作者： Wang, Zhaocheng Wu, Jun Wang, Rui Li, Ying Tongji University School of Computer Science and Technology Shanghai201804 China Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Tongji University College of Electronics and Information Engineering Shanghai201804 China Tongji University Shanghai Institute of Intelligent Science and Technology Shanghai201804 China Peng Cheng Laboratory Guangdong518055 China

Extended reality (XR) technologies and applications have grown rapidly in recent years. In addition to providing immersive ultra-high-definition (UHD) video, XR also allows for a haptic experience where devices can be remotely manipulated to accomplish tasks. However, varying numbers of XR users accessing the communication system can strain limited spectrum resources, posing challenges in resource allocation. Therefore, this paper studies resource blocks (RBs) allocation problem in a downlink transmission scenario where real-time cloud XR video and haptic contents need to be transmitted simultaneously. We also consider the random variation in the number of XR users and propose an Adaptive Distributed Multi-Agent Deep reinforcement learning (DRL) combined with Transformer (ADMA-DcT) for dynamic RB allocation method. This method addresses the dynamic change in network input dimensions due to user number variability using a state division module and a self-attention mechanism in the encoder module. To our knowledge, this is the first work to study the RB allocation problem in Cloud XR transmission considering simultaneous transmitting of video and haptic services with a dynamically changing user base. Our extensive simulations show that the ADMA-DcT model, end-to-end trained, outperforms other benchmarks in successfully serving a larger number of XR users under varying user number conditions, demonstrating excellent adaptivity and robustness. © 2014 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Application of Oriented Molecular Imprinting Biosensors in Biomarker Detection

引用

Journal of Analysis and Testing 2024年第4期8卷 553-568页

作者： Tianjian Lv Tiantong Chen Ziyu Zhu Ruilin Haotian Aiqin Luo Axin Liang Key Laboratory of Molecular Medicine and Biotherapy The Ministry of Industry and Information TechnologySchool of Life ScienceBeijing Institute of TechnologyBeijing100081China Department of Biomedical Engineering Chinese PLA General HospitalBeijing100853China

With the rapid development of nanomaterials,the interdisciplinary cross-linking between nanomaterials and biomedical detection is *** based on novel molecular recognition mechanisms are expected to achieve higher molecular recognition specificity and *** them,oriented molecular imprinting biosensors have recently become a research *** molecular imprinting biosensors are biosensors that can be used for specific *** are constructed by modifying template molecules with specific groups to form molecular imprinting microcavities with templateoriented recognition *** with general biosensors,oriented molecular imprinting biosensors have more directional recognition sites and fewer non-specific recognition *** unique advantage provides a higher signal-to-noise ratio for these sensors,which contributes to establishing a clear and intuitive relationship of light,electricity and other detection signals with the content of substances to be measured and has been widely used in biomarker *** this review,the types,principles and synthesis methods of oriented molecular imprinting technology are briefly *** application of oriented molecular imprinting biosensors in biomarker detection is ***,the technical bottleneck and future development trend of oriented molecular imprinting technology in the field of biosensors are discussed and summarized.

关键词： Oriented imprinting Biosensors Biomarker Detection

来源：评论

学校读者我要写书评

暂无评论

Single-mode GaSb-based laterally coupled distributed-feedback laser for CO_(2)gas detection

引用

Chinese Physics B 2023年第10期32卷 443-447页

作者：韩实现严进一曹春芳杨锦杜安天陈元宇刘若涛王海龙龚谦 Key Laboratory of Terahertz Solid State Technology Shanghai Institute of Microsystem and Information TechnologyShanghai 200050China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Shandong Provincial Key Laboratory of Laser Polarization and Information Technology School of Physics and Physical EngineeringQufu Normal UniversityQufu 273165China

We report on a GaSb-based laterally coupled distributed feedback(LC-DFB)laser with Cr gratings operating at 2004 nm for CO_(2)detection *** packaged with single-mode fiber pigtailed,the laser diode operates in the continuous-wave mode in a temperature range from-10℃to 60℃,with a maximum output power of 2 mW and a maximum side-mode suppression ratio over 30 ***-modulated absorption spectroscopy of CO_(2)demonstrates the applicability of the LC-DFB laser to tunable diode laser absorption ***,the diode junction temperature,which is measured by using the wavelength shift method,exhibits a maximum value of 17℃in the single-mode operation range.

关键词： semiconductor lasers quantum wells laser spectroscopy

来源：评论

学校读者我要写书评

暂无评论

An electrically controlled tunable photonic crystal filter based on thin-film lithium niobate

引用

Optoelectronics Letters 2024年第4期20卷 200-204页

作者： WANG Yifan YAO Yuan ZHANG Hao LIU Bo DUAN Shaoxiang LIN Wei Institute of Modern Optics College of Electronic Information and Optical EngineeringNankai UniversityTianjin 300350China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Nankai UniversityTianjin 300350China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai 519000China Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology Nankai UniversityTianjin 300350China

In this paper,we present an electrically controlled tunable narrowband filter based on a thin-film lithium niobate two-dimensional(2D)photonic *** filter incorporates a photonic crystal microcavity structure within the straight waveguide,enabling electronic tuning of the transmitted wavelength through added electrode *** optimized microcavity filter design achieves a balance between high transmission rate and quality factor,with a transmission center wavelength of 1551.6 nm,peak transmission rate of 96.1%,and quality factor of ***,the filter can shift the central wavelength of the transmission spectrum by applying voltage to the electrodes,with a tuning sensitivity of 13.8 pm/*** proposed tunable filter adopts a simple-to-fabricate air-hole structure and boasts a compact size(length:11.57μm,width:5.27μm,area:60.97μm^(2)),making it highly suitable for large-scale *** features make the filter promising for broad applications in the fields of photonic integration and optical communication.

关键词： tunable tuning waveguide

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Automated Skin Disease Diagnosis 1

Deep Learning Approach for Automated Skin Disease Diagnosis

引用

1st International Conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Prashanth, B.S. Puneeth, B.H. Manoj Kumar, M.V. Bhavana, R.K. Arshitha, K. Santhosh, S. Puneeth, S.P. Sneha, H.R. Nitte Meenakshi Institute of Technology Department of Information Science & Engineering Karnataka Bangalore560064 India Bapuji Institute of Engineering and Technology Department of Computer Science and Business Systems Karnataka Davanagere577004 India Bapuji Institute of Engineering and Technology Department of Information Science and Engineering Karnataka Davanagere577004 India

ISBN: (纸本)9798350376517

Skin diseases has been a significant challenge in healthcare, necessitating accurate and timely diagnosis for effective treatment. This paper presents research on the use of Convolutional Neural Networks (CNNs) for the categorization of skin illnesses. CNNs are a viable tool for automated skin disease detection since they successfully leverage the deep learning capabilities in image-based tasks. The research begins with a detailed review of existing methodologies and datasets in the domain of skin disease classification. Subsequently, we propose a novel CNN architecture tailored to address the unique challenges posed by dermatological images, such as variability in lesion size, color, and texture. The proposed model is trained and evaluated on a diverse and extensive dataset, ensuring its robustness and generalization capabilities across various skin conditions. The study delves into the interpretability of the CNN model, providing insights into the features learned during the training process. This analysis contributes to the understanding of how deep learning models make decisions in the context of dermatological diagnosis, enhancing the trustworthiness and acceptance of such automated systems in clinical settings. Furthermore, the paper investigates the impact of data augmentation techniques on model performance, addressing the scarcity of labeled dermatological datasets. By increasing the training data, we explore strategies to improve the model's ability to generalize to unseen cases, thereby enhancing its practical utility. Experimental results are presented and compared with state-of-the-art approaches, proving the viability of the suggested CNN architecture. © 2024 IEEE.

关键词： Convolutional neural networks

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：