检索结果-内蒙古大学图书馆

Spectral reconstruction for Internet of Things Based on Parallel Fusion of CNN and Transformer

IEEE INTERNET OF THINGS JOURNAL 2025年第4期12卷 3549-3562页

作者： Sun, Bangyong Wu, Changyu Yu, Mengying Xian Univ Technol Sch Printing Packaging & Digital Media Xian 710048 Peoples R China

Spectral imaging acquires more analyzable and distinguishable information than RGB imaging and has become an emerging technique powering Internet of Things (IoT). Thus, generating spectral images from existing RGB cameras is instrumental to high-level vision tasks. In this article, an IoT-oriented spectral reconstruction model with parallel fusion of convolutional neural network (CNN) and transformer (PFCT) is proposed to efficiently recover hyperspectral images (HSIs) from RGB counterparts, facilitating low-cost and nonhardware-specific spectral image acquisition. Recent works mainly utilize CNNs to extract local features by stacking more layers, ignoring the latent correlations of global features. In our PFCT network, we take advantage of lightweight CNNs to efficiently perceive local details, and exploit transformer blocks to fully capture the global context. Based on the architecture, a parallel fusion module is further designed to deeply interact and fuse the features obtained by CNN and Transformer in both directions. The final output spectral image is generated with same spatial sizes of the original image based on the deeply fused features. Consequently, the proposed PFCT network achieved high performance on four benchmark data sets compared to several state-of-the-art networks with a relatively small number of parameters.

关键词： Image reconstruction Hyperspectral imaging Convolutional neural networks Feature extraction Transformers Imaging reconstruction algorithms Convolutional neural network (CNN) Internet of Things (IoT) spectral reconstruction transformer

来源：评论

学校读者我要写书评

暂无评论

Phase Current reconstruction and Suppression in a Single Current Sensor Measurement-Based Four-Phase SRM-Integrated Drive System

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Cai, Jun Liu, Zeyuan Song, Shoujun Nanjing Univ Informat Sci & Technol C MEIC CICAEET Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Automat Nanjing 210044 Peoples R China Anhui Jianzhu Univ Sch Mech & Elect Engn Hefei 230009 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210042 Peoples R China Northwestern Polytech Univ Coll Automat Xian 710072 Peoples R China

In this article, a compact single current sensor measurement-based four-phase switched reluctance motor (SRM)-integrated drive system is developed. Based on the current measurement characteristics of this drive system, the phase current reconstruction and demagnetization current suppression strategies are proposed. To ensure reliable operation of the SRM, two key issues are considered: 1) the four-phase current should be obtained from the only measured bus current signal and 2) as the nonconducting phases are unable to demagnetize normally with traditional control algorithms, serious negative torque effects exist. For the first issue, a four-phase current reconstruction method is proposed by decoupling the adjacent two-phase currents in the overlapping conduction regions. For the second issue, high-frequency pulses are injected in the shared upper power switch of the bridge arm where the conducting phase is located, providing rapid demagnetization for the other phase in the same bridge arm. The two methods are fully decoupled and can be integrated freely to achieve current reconstruction and demagnetization of current suppression. Based on these methods, a hybrid control algorithm that can satisfy the operation requirement in different speed ranges is developed for the SRM drive. Experiments have been implemented in an 8/6 structure SRM prototype-based system, and detailed experimental results verify the effectiveness of the proposed methods.

关键词： Current measurement Demagnetization Topology Phase measurement Power measurement Electronic mail Accuracy Torque Switched reluctance motors reconstruction algorithms Demagnetization current suppression integrated power converter phase current reconstruction single current sensor measurement switched reluctance motor (SRM)

来源：评论

学校读者我要写书评

暂无评论

Phase Current reconstruction for DTP-PMSM With Single Current Sensor Using Synchronous Filtering reconstruction Method

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2025年第6期40卷 8528-8539页

作者： Zhao, Wenxiang Ma, Sen Tao, Tao Wu, Yunjiang Ling, Jincheng Wang, Huanan Jiangsu Univ Sch Elect Informat Engn Zhenjiang 212013 Peoples R China Nanjing Inst Technol Sch Elect Power Engn Nanjing 211167 Peoples R China

In dual three-phase permanent magnet synchronous motor (DTP-PMSM) drive, six-phase current information is critical to motor control. However, the adoption of multiple current sensors increases the size and cost of inverters. To mitigate this issue, this article proposes a method to reconstruct six-phase currents of a DTP-PMSM by using a single current sensor (SCS). First, the SCS is repositioned to a current branch. Then, sampling is performed twice in one period based on the switching state of a single bridge arm. Therefore, two orthogonal phase currents are achieved. Furthermore, the synchronous filtering reconstruction method is proposed. Through this method, the harmonic current information is extracted from two orthogonal currents and the remaining four-phase currents are reconstructed. Overall, six-phase currents can be accurately reconstructed by using an SCS, for which the hardware cost and inverter size can be reduced. The proposed method is validated by both simulation and experiments.

关键词： Vectors reconstruction algorithms Harmonic analysis Power harmonic filters Switches Pulse width modulation Current measurement Inverters Filtering Bridge circuits Dual three-phase permanent magnet synchronous motor (DTP-PMSM) phase current reconstruction single current sensor (SCS) synchronous filtering reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Multiscale reconstruction Framework Based on Edge-Enhanced Guidance for In-Line X-Ray Phase-Contrast CT With Limited-Angle Projections

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Li, Yimin Zhao, Yuanyuan Ma, Chenyang Li, Fangzhi Wang, Ziyao Lv, Wenjuan Ji, Dongjiang Jian, Jianbo Zhao, Xinyan Zhao, Yuqing Hu, Chunhong Tianjin Med Univ Sch Biomed Engn & Technol Tianjin 300070 Peoples R China Tianjin Univ Technol & Educ Sch Sci Tianjin 300222 Peoples R China Tianjin Med Univ Gen Hosp Tianjin 300052 Peoples R China Capital Med Univ Beijing Friendship Hosp Liver Res Ctr Beijing 100050 Peoples R China

The in-line X-ray phase-contrast computed tomography (IL-XPCCT) serves as an effective tool for studying organ function and pathologies. However, IL-XPCCT approaches often result in high radiation doses due to long scan times. To address this issue, a limited angel sampling strategy is frequently employed. However, limited-angle projection data can lead to severe divergence phenomena at sample edges or boundaries, significantly reducing image quality and affecting subsequent image analysis. In this work, we propose a novel multiscale reconstruction framework based on edge-enhanced guidance (MSRF-EEG) for IL-XPCCT limited-angle CT reconstruction. The MSRF-EEG framework consists of two primary subnetworks: an edge-enhanced subnetwork (EESN) and a multiscale reconstruction subnetwork (MSRSN). By fully considering the imaging characteristics of the IL-XPCCT, the EESN is designed to explore the edge enhancement characteristics from the IL-XPCCT images prior to phase retrieval, which is then utilized to compensate for edge distortions during the reconstruction process. The MSRSN performs image reconstruction with edge-enhanced guidance across multiple scales simultaneously. Furthermore, to better leverage the edge enhancement characteristics before phase retrieval for reconstructing the IL-XPCCT images from limited-angle projections, an edge aggregation (EAG) module and an edge attention (EAT) module are incorporated into the MSRSN. Simulations and real data experiments are conducted to evaluate the performance of our proposed MSRF-EEG framework. Compared with the existing competitive algorithms, both quantitative and qualitative results demonstrate that the proposed method can significantly enhance reconstruction quality under different sampling angles and improve detail restoration and edge preservation.

关键词： Image reconstruction Image edge detection Computed tomography Imaging X-ray imaging TV Detectors Decoding reconstruction algorithms Phase measurement Edge enhancement in-line X-ray phase-contrast computed tomography (IL-XPCCT) limited-angle reconstruction phase retrieval

来源：评论

学校读者我要写书评

暂无评论

SCA-CVENet: A Spatial-Channel-Attention Collaborative Cost Volume Enhancement Network for High-Quality Depth reconstruction

引用

IEEE ACCESS 2025年 13卷 58264-58280页

作者： Tian, Mao Zhao, Xudong Lv, Xiong Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing 400065 Peoples R China

Accurate and complete depth map prediction from a set of overlapping multi-view stereo images has received extensive attention in the fields of photogrammetry and computer vision. Despite the tremendous efforts made in multi-view depth map reconstruction in recent years, the accuracy and completeness of the reconstructed depth map in matching difficulty areas needs to be further improved. In this paper, to address this issue, we propose SCA-CVENet, which is an efficient spatial-channel-attention collaborative cost volume enhancement network for high-quality depth map reconstruction. The main contributions of SCA-CVENet are the channel attention weight (CAW)-based cost volume enhancement module that can effectively filter the redundant channel information of the feature volumes to boost the feature representation of the cost volumes, and the spatial attention weight (SAW)-based cost volume enhancement module that can significantly improve the robustness of the cost volumes in textureless and repetitive texture areas, to produce more accurate and complete depth map reconstruction results. First, a weight-sharing hierarchical feature extraction subnetwork is adopted to extract robust multi-scale feature maps. Second, the SAW generation subnetwork is adopted, which incorporates the group-wise correlation (GWC)-based cost volume adaptive fusion module and 3D hourglass module to produce an accurate SAW. Finally, the coarse-to-fine cascade depth prediction subnetwork incorporates the CAW- and SAW-based cost volume enhancement modules into the cascade network architecture to predict a high-quality depth map. Three publicly available benchmark datasets-the DTU, BlendedMVS, and Tanks & Temples datasets-were utilized to validate the performance of SCA-CVENet, and the comprehensive experimental results demonstrate that SCA-CVENet obtains a superior performance on all the datasets in terms of accuracy and completeness.

关键词： Costs Image reconstruction Accuracy Three-dimensional displays reconstruction algorithms Robustness Information filters Memory management Feature extraction Collaboration Depth prediction multi-view depth map reconstruction channel attention weight (CAW) spatial attention weight (SAW) cascade network architecture

来源：评论

学校读者我要写书评

暂无评论

Clinical and Deep-Learned Evaluation of MR-Guided Self-Supervised PET reconstruction

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2025年第3期9卷 337-346页

作者： Hopson, Jessica B. Ellis, Sam Flaus, Anthime Mcginnity, Colm J. Neji, Radhouene Reader, Andrew J. Hammers, Alexander Kings Coll London Dept Biomed Engn London SE1 7EH England Kings Coll London Guys & St Thomas PET Ctr London SE1 7EH England Siemens Healthcare Ltd MR Res Collaborat Camberley GU15 3YL England

Reduced dose positron emission tomography (PET) lowers the radiation dose to patients and reduces costs. Lower-count data, however, degrades reconstructed image quality. Advanced reconstruction methods help mitigate image quality losses, but it is important to assess the resulting images from a clinical perspective. Two experienced clinicians assessed four PET reconstruction algorithms for [F-18]FDG brain data, compared to a clinical standard reference (maximum-likelihood expectation-maximization (MLEM)), based on seven clinical image quality metrics: global quality rating, pattern recognition, diagnostic confidence (all on a scale of 0-4), sharpness, caudate-putamen separation (CP), noise, and contrast (on a scale between 0-2). The reconstruction methods assessed were a guided and unguided version of self-supervised maximum a posteriori EM (MAPEM) (where the guidance case used the patient's MR image to control the smoothness penalty). For 3 of the 11 patient datasets reconstructed, post-smoothed versions of the MAPEM reconstruction were also considered, where the smoothing was with the point-spread-function used in the resolution modelling. Statistically significant improvements were observed in sharpness, CP, and contrast for self-supervised MR-guided MAPEM compared to MLEM. For example, MLEM scored between 1-1.1 out of 2 for sharpness, CP, and contrast, whereas self-supervised MR-guided MAPEM scored between 1.5-1.75. In addition to the clinical evaluation, pretrained convolutional neural networks (CNNs) were used to assess the image quality of a further 62 images. The CNNs demonstrated similar trends to the clinician, showing their potential as automated standalone observers. Both the clinical and CNN assessments suggest when using only 5% of the standard injected dose, self-supervised MR-guided MAPEM reconstruction matches the 100% MLEM case for overall performance. This makes the images far more clinically useful than standard MLEM.

关键词： reconstruction algorithms Standards Positron emission tomography Image quality Smoothing methods Noise Measurement Kernel Imaging Image quality assessment image reconstruction positron emission tomography (PET) imaging PET-magnetic resonance (PET-MR) imaging self-supervision self-supervision

来源：评论

学校读者我要写书评

暂无评论

Progressively Prompt-Guided Models for Sparse-View CT reconstruction

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2025年第4期9卷 447-459页

作者： Li, Jiajun Du, Wenchao Cui, Huanhuan Chen, Hu Zhang, Yi Yang, Hongyu Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ West China Hosp Chengdu 610041 Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu 610065 Peoples R China

While sparse-view computed tomography (CT) remarkably reduces the ionizing radiation dose, the reconstructed images have been compromised by streak-like artifacts, affecting clinical diagnostics. The deep unrolled methods have achieved promising results by integrating powerful regularization terms with deep learning technologies into iterative reconstruction algorithms. However, leading works focus on designing powerful regularization term to capture image and noise priors, which always requires carefully designed blocks, and leads to heavy computational burden while bringing over-smoothness into results. In this article, we integrate the idea of prompt learning into the general regularization terms, and propose a progressively prompt-guided model (shorted by PPM) to alleviate above problems. More specifically, we inject a prompting module into each unrolled block to perceive more native priors in a self-adaptive manner, which would capture more effective image and noise priors to guide high-quality CT reconstruction. Furthermore, we propose a progressively guiding strategy to facilitate high-quality prompt generation while speeding model convergence. Extensive experiments on multiple sparse-view CT reconstruction benchmarks demonstrate that our PPM achieves state-of-the-art performance in terms of artifact reduction and structure preservation while with fewer parameters and higher-inference efficiency.

关键词： Image reconstruction Computed tomography Iterative methods Noise Computational modeling Plasmas Degradation Convergence Transformers reconstruction algorithms Iterative reconstruction progressively prompt guiding (PPG) prompt learning sparse-view computed tomography (CT)

来源：评论

学校读者我要写书评

暂无评论

A Novel Environment reconstruction Method based on Distributed NLOS Signals 16

A Novel Environment Reconstruction Method based on Distribut...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Yu, Fangrui Li, Junlin Xie, Wei Zhang, Kehao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Integrated Sensing and Communication (ISAC) is a rapidly evolving field with extensive application prospects. Environmental reconstruction (ER) is an important content of ISAC. Existing ER techniques often require large sample sizes or specific signals, which significantly limit their application. User Equipments (UEs) widely distributed in the environment and their communication signals provide an adequate measurement basis. However, there are challenges in utilizing communication signals due to limited research, and difficulties in identifying and extracting Non-Line-of-Sight (NLOS) signals. This paper proposes a distributed ER algorithm based on Angle of Arrival (AOA) and Time of Flight (TOF) information of NLOS signals, enabling identification and utilization of various order NLOS signals under complex NLOS conditions. A series of simulation delays validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Non line of sight propagation Reflection reconstruction algorithms Mirror pointing Signal processing Environmental sensing Wireless communications

来源：评论

学校读者我要写书评

暂无评论

ThinTact: Thin Vision-Based Tactile Sensor by Lensless Imaging

引用

IEEE TRANSACTIONS ON ROBOTICS 2025年 41卷 1139-1154页

作者： Xu, Jing Chen, Weihang Qian, Hongyu Wu, Dan Chen, Rui Tsinghua Univ Dept Mech Engn Beijing 100084 Peoples R China

Vision-based tactile sensors have drawn increasing interest in the robotics community. However, traditional lens-based designs impose minimum thickness constraints on these sensors, limiting their applicability in space-restricted settings. In this article, we propose ThinTact, a novel lensless vision-based tactile sensor with a sensing field of over 200 mm(2) and a thickness of less than 10 mm. ThinTact utilizes the mask-based lensless imaging technique to map the contact information to CMOS signals. To ensure real-time tactile sensing, we propose a real-time lensless reconstruction algorithm that leverages a frequency-spatial-domain joint filter based on discrete cosine transform. This algorithm achieves computation significantly faster than existing optimization-based methods. In addition, to improve the sensing quality, we develop a mask optimization method based on the generic algorithm and the corresponding system matrix calibration algorithm. We evaluate the performance of our proposed lensless reconstruction and tactile sensing through qualitative and quantitative experiments. Furthermore, we demonstrate ThinTact's practical applicability in diverse applications, including texture recognition and contact-rich object manipulation.

关键词： Imaging Tactile sensors Robot sensing systems Image reconstruction Robots Real-time systems Optical sensors Optical imaging Lenses reconstruction algorithms Lensless imaging mask optimization real-time reconstruction tactile sensing

来源：评论

学校读者我要写书评

暂无评论

FRI Sampling of ECG Signals Based on the Gaussian Second-Order Derivative Model

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第7期12卷 9300-9313页

作者： Huang, Guoxing Guo, Jing Wang, Jingwen Zhang, Yu Lu, Weidang Wang, Ye Zhejiang Univ Technol Coll Informat Engn Key Lab Commun Networks & Applicat Zhejiang Prov Hangzhou 310023 Peoples R China Lishui Univ Fac Engn Lishui 323000 Peoples R China

This article presents a novel under-sampling method for ECG signals, aimed at reducing the sampling rate and power consumption in IoT-based ECG wearable devices. The key contribution addresses the common issue of model mismatch in existing methods, which negatively impacts signal reconstruction accuracy. Initially, the ECG signal is modeled as a linear combination of several Gaussian second-order derivative functions, which can be efficiently represented with only a few parameters, thus mitigating the problem of large model matching errors. To further enhance reconstruction accuracy, an improved two-channel finite rate of innovation sampling framework is introduced, effectively addressing the nonideal effects caused by the low-pass filter during sampling. Additionally, a modified annihilating filter reconstruction algorithm is proposed, allowing high-precision signal reconstruction using a small number of sampling points to estimate parameters. The validity of the proposed method is confirmed through simulations with real ECG signals from the MIT-BIH arrhythmia database, and a hardware platform is developed to verify its feasibility in a practical system. Experimental results demonstrate that, compared to the existing methods, the proposed approach significantly reduces reconstruction error (achieving a PRD as low as 2.29% and an SRR of 11.77 dB), and exhibits better robustness in noisy environments.

关键词： Electrocardiography Accuracy Internet of Things Technological innovation Signal reconstruction reconstruction algorithms Parameter estimation Monitoring Mathematical models Low-pass filters Finite rate of innovation (FRI) Gaussian second-order derivative (GSD) function nonideal effects parametric reconstruction

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：