检索结果-内蒙古大学图书馆

An "Opinion-Unaware" 3-D Image Quality Evaluator Using Correlation Features of Scene Components

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Raghuwanshi, Pankaj Kumar Poreddy, Ajay Kumar Reddy Appina, Balasubramanyam Kokil, Priyanka Indian Inst Technol Indore Dept Elect Engn Multimedia Engn & Perceptual Cognit Anal Grp MEPCA Indore 453552 India Indian Inst Informat Technol Design & Mfg Dept Elect & Commun Engn Adv Signal & Image Proc ASIP Lab Chennai 600127 India Sri Sivasubramaniya Nadar Coll Engn SSN Dept Comp Sci & Engn Chennai 603110 India

The rapid growth of stereoscopic (S3D) imaging has led to increased adoption across multimedia formats. However, the S3D pipeline introduces spatial, depth, and binocular rivalry errors, degrading visual quality. Quality assessment (QA) helps evaluate and improve the visual experience, ensuring comfort during prolonged exposure to S3D content. This article proposes an "opinion-unaware" QA model for S3D images based on statistical variations in the correlation map between color and depth features. The quality score of the correlation map is obtained using principal component analysis (PCA) and multivariate Gaussian modeling. A natural image quality evaluator calculates spatial scores from the luminance information of an S3D image. Finally, the overall S3D image quality is determined by a weighted mechanism that combines color, depth, and spatial scores. The weighted pooling includes the spatial score, which is otherwise ignored in correlation map calculation. Extensive experiments on four standard datasets, namely, LIVE Phase I and Phase II, Waterloo Phase I and Phase II, have demonstrated that the proposed model outperforms off-the-shelf opinion-unaware models and gives competitive performance to supervised no-reference (NR) models.

关键词： Image color analysis computational modeling Feature extraction Correlation Image quality Three-dimensional displays Visualization Training Solid modeling Data mining Correlation map Gabor decomposition multivariate Gaussian opinion-unaware principal component analysis (PCA)

来源：评论

学校读者我要写书评

暂无评论

SCL-YOLOv11: A Lightweight Object Detection Network for Low-Illumination Environments

引用

IEEE ACCESS 2025年 13卷 47653-47662页

作者： Zhuo, Shulong Bai, Hao Jiang, Lifeng Zhou, Xiaojian Duan, Xu Ma, Yiqun Zhou, Zihan Hainan Vocat Univ Sci & Technol Coll Informat Engn Haikou 571126 Hainan Peoples R China Brisight Hainan Technol & Dev Co Ltd Haikou 570216 Peoples R China Univ Int Business & Econ Business Sch Beijing 100029 Chaoyang Peoples R China

Object detection in low-light environments has been widely recognized as a critical research direction in the field of computer vision. In response to the challenges of reduced detection accuracy and high edge-deployment costs encountered by mainstream single-stage object detection models under low-light conditions, this paper proposes a lightweight object detection network based on YOLOv11, integrates StarNet, C3k2-Star, and a lightweight detail-enhanced convolution and shared convolutional detection head(LSDECD), so called SCL-YOLOv11 herein. First, the StarNet architecture is introduced into the Backbone to enhance the extraction of shallow image features and significantly reduce computational complexity. Next, Star Blocks from the StarNet framework are employed to optimize the C3k2 module in the Neck stage, thereby improving the localization accuracy of deep features without increasing network complexity. Meanwhile, the Minimum Point Distance based IoU(MPDIoU) loss function is adopted to mitigate gradient explosion risks while enhancing detection precision. Furthermore, a lightweight detail-enhancement convolution layer and a shared-convolution detection head are designed to improve the model's capability in capturing fine-grained details. Finally, a knowledge distillation procedure is conducted using SCL-YOLOv11 as the student model and YOLOv8 as the teacher model, ensuring that the proposed SCL-YOLOv11 model achieves both low complexity and excellent detection performance. Experimental results on the ExDark dataset demonstrate that the proposed algorithm achieves 67.6% mAP@0.5 and 42.4% mAP@0.5:0.95, while reducing parameter count by 38.5% and computational cost by 25.4%. Consequently, the proposed model is highly suitable for edge deployment in industrial applications and embedded development systems.

关键词： computational modeling Convolution Feature extraction Accuracy Stars computational efficiency Head Image enhancement Image edge detection Computer architecture Low-illumination environments SCL-YOLOv11 lightweight knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Co-Training Broad Siamese-Like Network for Coupled-View Semi-Supervised Learning

引用

IEEE TRANSACTIONS ON CYBERNETICS 2025年第4期55卷 1526-1539页

作者： Li, Yikai Chen, C. L. Philip Zhang, Tong South China Univ Technol Sch Comp Sci & Engn Guangdong Prov Key Lab Computat AI Models & Cognit Guangzhou 510006 Peoples R China Res Ctr Artificial Intelligence Large Model & Inte Pazhou Lab Guangzhou 510335 Peoples R China Minist Educ Hlth Intelligent Percept & Paralleled Engn Res Ctr Guangzhou 510006 Peoples R China

Multiview semi-supervised learning is a popular research area in which people utilize cross-view knowledge to overcome the limitation of labeled data in semi-supervised learning. Existing methods mainly utilize deep neural network, which is relatively time-consuming due to the complex network structure and back propagation iterations. In this article, co-training broad Siamese-like network (Co-BSLN) is proposed for coupled-view semi-supervised classification. Co-BSLN learns knowledge from two-view data and can be used for multiview data with the help of feature concatenation. Different from existing deep learning methods, Co-BSLN utilizes a simple shallow network based on broad learning system (BLS) to simplify the network structure and reduce training time. It replaces back propagation iterations with a direct pseudo inverse calculation to further reduce time consumption. In Co-BSLN, different views of the same instance are considered as positive pairs due to cross-view consistency. Predictions of views in positive pairs are used to guide the training of each other through a direct logit vector mapping. Such a design is fast and effectively utilizes cross-view consistency to improve the accuracy of semi-supervised learning. Evaluation results demonstrate that Co-BSLN is able to improve accuracy and reduce training time on popular datasets.

关键词： Training Semisupervised learning Accuracy Representation learning Deep learning Correlation Backpropagation Learning systems computational modeling Supervised learning Broad learning system (BLS) co-training multiview learning semi-supervised learning Siamese network

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Two-Stage Multivehicle Feature Fusion Method Guided by Global Feature

引用

IEEE SENSORS JOURNAL 2025年第5期25卷 9008-9018页

作者： Wang, Yakang Zhao, Baixuan Chen, Siheng Tian, Daxin Hu, Chuan Zhang, Xi Shanghai Jiao Tong Univ Sch Mech Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Cooperat Medianet Innovat Ctr CM Shanghai 200240 Peoples R China Beihang Univ Sch Transportat Sci & Engn State Key Lab Intelligent Transportat Syst Beijing Key Lab Cooperat Vehicle Infrastruct Syst Beijing 100191 Peoples R China Shanghai Jiao Tong Univ Intelligent Vehicle Inst Sch Mech Engn Shanghai 200240 Peoples R China

Effectively selecting high-quality feature from each vehicle for fusion is crucial for collaborative perception performance. However, the uncertain differences in the perceptual ranges of each vehicle pose a challenge to fusion. Current fusion methods typically feed all received features into multilayer self-attention to alleviate differences. This results in a high computational complexity that scales quadratically with connected vehicles number. To address this issue, we propose a lightweight two-stage multivehicle feature fusion method guided by global feature, which consists of two fusion stages. In the first fusion stage, we design a global feature builder (GFB) to effectively extract and aggregate the most representative features across all vehicles, constructing a feature map with a holistic perspective. Global feature can provide rich prior information for the next stage. In the second fusion stage, to effectively fuse reliable features and handle high computational complexity caused by stacking self-attention layers, we introduce a global feature-guided cross-attention fusion (GGCF) module, which interacts with the global feature as a query with features from each vehicle to obtain fusion weights. Importantly, we only need a layer of cross attention and the length of the query is one, so our method has a computational complexity linearly proportional to connected vehicles number. To validate the effectiveness of our proposed method, we conduct experiments on simulated and real-world scenario datasets. Experimental results demonstrate that our fusion method has a faster inference speed than the state-of-the-art (SOTA) model, and the 3-D detection performance achieves better performance in both real and noisy environments.

关键词： Feature extraction computational complexity Transformers Object detection Fuses Sensors Attention mechanisms Connected vehicles computational modeling Collaboration 3-D object detection cooperative perception feature fusion intelligent vehicles vehicle-to-vehicle (V2V)

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Reprogramming Framework for Cross-Device Fault Diagnosis in Edge Computing

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wang, Yanzhi Wu, Jinhong Luo, Shuyang Yu, Ziyang Zhou, Qi Huazhong Univ Sci & Technol Sch Aerosp Engn Wuhan 430074 Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Peoples R China

Fault diagnosis in mechanical equipment is essential for industrial system stability and safety. However, when applying the model to different models of devices, the difference in sample feature distribution seriously affects the diagnosis effect. At the same time, traditional cloud-based deployment faces delays and resource constraints, making it unable to meet real-time requirements. This article introduces a lightweight reprogramming framework for cross-device fault diagnosis in edge computing environments. It mainly includes cloud-based C-model training and edge-based E-model reprogramming and application stages. The model introduces a lightweight feature extraction (LFE) module and a decoupled fully connected (DFC) attention mechanism to enhance feature representation and global information capture. Through lightweight reprogramming, the E-model fits the device data in actual engineering while maintaining the diagnostic capability of the C-model. We used the NVIDIA Jetson Xavier NX kit as an edge computing platform and conducted verification experiments. The results show that the proposed method achieves good diagnostic effects on engineering equipment. At the same time, it achieves excellent lightweight indicators.

关键词： Fault diagnosis Training Adaptation models Attention mechanisms computational modeling Transfer learning Feature extraction Stability analysis Safety Edge computing Attention mechanism cross-device edge computing fault diagnosis lightweight neural network

来源：评论

学校读者我要写书评

暂无评论

Lumped-Mass Model-Based State of Charge and Core Temperature Estimation for Cylindrical Li-Ion Batteries Considering Reversible Entropy Heat

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年第5期72卷 4844-4853页

作者： Xie, Jiale Chang, Xiaobing Wang, Guang Wei, Zhongbao Dong, Zhekang North China Elect Power Univ Dept Automat Baoding 071003 Peoples R China Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China Hangzhou Dianzi Univ Sch Elect & Informat Hangzhou 310018 Peoples R China

Reliable estimation of the state of charge (SoC) and core temperature (CoT) of battery cells is paramount for formulating efficient energy and thermal management strategies. Focusing on cylindrical Li-ion batteries, this article constructs an equivalent circuit model and a two-state thermal model;then these two different-physics lumped-mass models are close-looped using bridge variables encompassing temperature, heat, and SoC. Notably, in addition to the conventional irreversible thermogenesis of ohmic effect, the generally ignored reversible entropy heat is modeled and experimentally calibrated as well. Then, both the electrical and thermal model parameters are adaptively identified using the variable forgetting factor least square algorithm. Finally, a computationally efficient and nonlinearity-compatible algorithm, namely the singular value decomposition-based Kalman filter, is utilized for the joint estimation of SoC and CoT. Experimental validations under dynamic load excitations demonstrate the robustness and accuracy of the designed scheme, achieving favorable performance with errors as low as 5% for SoC and 0.2 degrees C for CoT.

关键词： Temperature measurement Estimation Couplings computational modeling Temperature distribution Integrated circuit modeling Entropy Resistance heating Lithium-ion batteries Electrodes Core temperature (CoT) electrothermal coupling (ETC) model Li-Ion battery (LiB) reversible entropy heat state of charge (SoC)

来源：评论

学校读者我要写书评

暂无评论

Conductive Metal-Organic Frameworks and Their Electrocatalysis Applications

引用

ACS NANO 2025年第10期19卷 9484-9512页

作者： Tao, Shuhui Wang, John Zhang, Jie Natl Univ Singapore Chongqing Res Inst Chongqing 401123 Peoples R China Natl Univ Singapore Dept Mat Sci & Engn Singapore 117574 Singapore Sichuan Univ Coll Mat Sci & Engn Chengdu 610065 Peoples R China

Recently, electrically conductive metal-organic frameworks (EC-MOFs) have emerged as a wealthy library of porous frameworks with unique properties, allowing their use in diverse applications of energy conversion, including electrocatalysis. In this review, the electron conduction mechanisms in EC-MOFs are examined, while their electrical conductivities are considered. There have been various strategies to enhance the conductivities of MOFs including ligand modification, the incorporation of conducting materials, and the construction of multidimensional architectures. With sufficient conductivities being established for EC-MOFs, there have been extensive pursuits in their electrocatalysis applications, such as in the hydrogen evolution reaction, oxygen reduction reaction, oxygen evolution reaction, N2 reduction reaction, and CO2 reduction reaction. In addition, computational modeling of EC-MOFs also exerts an important impact on revealing the synthesis-structure-performance relationships. Finally, the prospects and current challenges are discussed to provide guidelines for designing promising framework materials.

关键词： metal-organic framework organic ligand synthetic strategy electrical conductivity dimensionality coordination geometry catalytic mechanism computational modeling electrochemical performance

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning for Radiowave Propagation modeling Below 6 GHz

引用

IEEE ACCESS 2025年 13卷 9755-9765页

作者： Bocus, Mohammud Z. Lodhi, Afzal Ofcom London SE1 9HA England

This paper presents the application of supervised learning and use of fully connected neural network (FCNN) for the development of a path specific propagation model for frequencies below 6 GHz. The model has been trained and tested against an extensive measurement dataset capturing several areas and the diverse topography of the UK. In addition to the measurement data, propagation environment related features that are provided as an input to the neural network have been extracted by employing quantised radio path profiles based on detailed topographic datasets (such as terrain, surface and land use). The results provide an insight in the choice of appropriate features that describe the propagation environment, trade-offs between prediction accuracy, extent of considered key features and associated complexity. The performance comparison between varying number of input features highlights that whilst an excellent prediction accuracy can be achieved when the training data include all test scenarios, it also reveals the limitations of pure data driven prediction methods and their inability to generalise. Noting the multifaceted nature and impact of propagation mechanisms and environments in conjunction with the limited availability of empirical measurements covering a wide range of spectrum bands, alternative hybrid approaches which may include physical modeling of propagation mechanisms are expected to further enhance the performance of neural networks based radiowave prediction methods. We present a simple hybrid approach in this paper that resolves the generalisation issues and provide far superior performance compared to pure physical propagation models or data driven models based on FCNN.

关键词： Feature extraction Data models Predictive models Analytical models Data mining Radiowave propagation Propagation losses Accuracy computational modeling Buildings Supervised learning fully connected neural network multi-layer perceptron radio path profile path loss path-specific prediction methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Emotion Recognition in Speech Based on Self-Supervised Learning: Cross-Attention Fusion of Acoustic and Semantic Features

引用

IEEE ACCESS 2025年 13卷 56283-56295页

作者： Deeb, Bashar M. Savchenko, Andrey V. Makarov, Ilya Moscow Inst Phys & Technol Moscow 141700 Russia RAS Res Ctr Trusted Artificial Intelligence ISP Moscow 109004 Russia Sber AI Lab Moscow 121170 Russia HSE Univ Lab Theoret Modelling AI Moscow 603093 Russia Artificial Intelligence Res Inst AIRI Moscow 105064 Russia

Speech Emotion Recognition has gained considerable attention in speech processing and machine learning due to its potential applications in human-computer interaction, mental health monitoring, and customer service. However, state-of-the-art models for speech emotion recognition use many parameters, which leads to computational complexity. In this paper, we introduce a novel deep-learning model to enhance the accuracy of emotional content detection in speech signals while maintaining a lightweight architecture compared to state-of-the-art models. The proposed model incorporates a feature encoder that significantly improves the emotional representation of acoustic features and a cross-attention mechanism to fuse acoustic features, such as Spectrograms, with semantic features extracted from the pre-trained self-supervised learning framework, enriching the emotional representation of speech. An extensive experimental study demonstrates that the proposed model achieves a weighted accuracy of 74.6% on the IEMOCAP dataset, competitive with the state-of-the-art baselines. In addition, our proposed model achieves a latency of 24 milliseconds on moderate devices while containing up to three times fewer parameters.

关键词： Feature extraction Acoustics Emotion recognition Speech recognition Accuracy computational modeling Speech enhancement Semantics Mel frequency cepstral coefficient Computer architecture Speech emotion recognition cross-attention mechanism feature fusion

来源：评论

学校读者我要写书评

暂无评论

A Simplified Fractional-Order Model Adapted to Temperature and Aging for Fast Estimation of State of Power of Lithium-Titanate Batteries

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第2期11卷 5484-5496页

作者： Dong, Sidi Zhang, Xuexia Huang, Ruike Huang, Lei Meng, Yilin Jiang, Yu Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China Southwest Jiaotong Univ Tangshan Grad Sch Tangshan 063000 Peoples R China Natl Rail Transit Electrificat & Automat Engn Tech Chengdu 611756 Peoples R China

The state of power (SOP) of lithium-titanate batteries with Li4Ti5O12 (LTO) anodes is a critical index that quantifies their capability to continuously supply or absorb energy over a specified period. For battery-powered locomotives, accurate SOP estimation is essential for developing control strategies for acceleration and regenerative braking. Nevertheless, the complexity of conventional fractional-order models (FOMs), combined with the nonadaptive estimation algorithms, poses challenges to achieving both efficient and accurate SOP estimation. In this work, a simplified fractional-order model (SFOM)-based multiconstraint algorithm (MCA) combined with an unscented Kalman filter (UKF) is proposed to fast online estimate SOP. First, the SFOM is developed by analyzing timescales of dynamic processes based on electrochemical impedance spectroscopy (EIS) across varying states of charge (SOCs), temperature, and aging conditions. Second, the MCA is designed based on the SFOM to calculate the peak current sequence required for SOP estimation, where SOP is quantified as an average of the power sequence over the peak current. Furthermore, the SOC, an essential parameter for online SOP estimation, is obtained using the SFOM-based UKF. Finally, the proposed method is validated through experiments. The results demonstrate that the proposed method not only reduces the average root-mean-square error in SOP estimation by up to 37.1% but also significantly saves calculation costs compared with traditional estimation methods.

关键词： Estimation State of charge Batteries Accuracy computational modeling Heuristic algorithms Adaptation models Temperature measurement Charge transfer Complexity theory Electrochemical impedance spectroscopy (EIS) fractional-order model lithium-titanate batteries multiconstraint algorithm (MCA) state of power (SOP) estimation

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：