检索结果-内蒙古大学图书馆

International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)

作者： Mounika, B. Udayaraju, P. Varma, Ch Vinod Narayana, T. V. Jyothi, Pyla Devi, Chokkakula SRKR Engn Coll Dept CSE Bhimavaram India SRKR Engn Coll Dept ECE Bhimavaram India Maharaj VijayaramGajapathi Raj Coll Engn A Dept CSE Vizianagaram India Nadimpalli Satyanarayana Raju Inst Technol A Dept CSE Visakhapatnam India

ISBN: (纸本)9798350389432;9798350389449;9798350389456

This research looks into whether it is possible to use SNNs along with deep learning methods to find occlusions in virtual reality and augmented reality images. The next step goes into more detail about the basic ideas behind SNNs and the benefits they offer, such as event-driven processing and low power usage, which are both very important for real-time augmented and virtual reality systems. After that, we'll talk about our one-of-a-kind occlusion recognition system, which uses both deep learning and SNNs. Utilizing both virtual and real-world AR and VR datasets, we conduct experiments to test how well our method works. These results show a big improvement in the accuracy of occlusion recognition compared to previous methods. We also find out how well our system works with computers and how many resources it needs. This shows that it can be used on AR and VR devices that don't have a lot of resources. In the end of this research, it is shown that spiking neural networks and deep learning methods can make it easier to find occlusions in AR/VR pictures. Our method improves augmented and virtual reality experiences by getting rid of this major problem. This opens up new possibilities in many areas, such as education, training, simulations, and gaming.

关键词： Spiking Neural Networks (SNNs) deep learning Occlusion Detection Augmented reality (AR) Virtual reality (VR) image processing Neural Network Architectures Event-Based processing Spike-Based processing

来源：评论

学校读者我要写书评

暂无评论

Diversity-based two-phase pruning strategy for maximizing image segmentation generalization with applications in transmission electron microscopy

引用

MACHINE learning-SCIENCE AND TECHNOLOGY 2025年第2期6卷 025021-025021页

作者： Ye, Ze-Wei Hsueh, Hung-Wei Hsu, Shu-Han Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan Taiwan

For artificial intelligence applications in transmission electron microscopy (TEM), hardware and computational constraints often obstruct real-time data processing, inflating operational costs, consuming valuable instrument time, and heightening the risk of damage to beam-sensitive specimens, thereby complicating reliable data interpretation. To address these issues, we propose a two-stage pruning strategy that reduces deep-learning model size and computational overhead while preserving high performance and generalization across diverse datasets. Unlike conventional pruning techniques, which typically rely solely on weight magnitude and risk overlooking critical variability and directional properties in weight vectors, our approach initially removes filters with low magnitude and insufficient variability, followed by pruning filters with high linear similarity to eliminate redundancy. This one-shot pruning process, followed by fine-tuning, minimizes accuracy loss and mitigates barriers to deep learning integration in TEM workflows. Our method expedites TEM analysis, enabling more efficient, real-time, and cost-effective materials characterization. Additionally, this work lays a foundation for investigating the broader applicability and versatility to different architectures and tasks, particularly in resource-constrained environments where both model size and computational efficiency are critical.

关键词： transmission electron microscopy artificial intelligence deep learning segmentation pruning diversity similarity

来源：评论

学校读者我要写书评

暂无评论

ClGanNet: A novel method for maize leaf disease identification using ClGan and deep CNN

引用

SIGNAL processing-image COMMUNICATION 2024年 120卷

作者： Sharma, Vivek Tripathi, Ashish Kumar Daga, Purva Nidhi, M. Mittal, Himanshu Malaviya Natl Inst Technol Jaipur Jaipur India Indira Gandhi Delhi Tech Univ Women Delhi India

With the advancement of technologies, automatic plant leaf disease detection has received considerable attention from researchers working in the area of precision agriculture. A number of deep learning-based methods have been introduced in the literature for automated plant disease detection. However, the majority of datasets collected from real fields have blurred background information, data imbalances, less generalization, and tiny lesion features, which may lead to over-fitting of the model. Moreover, the increased parameter size of deep learning models is also a concern, especially for agricultural applications due to limited resources. In this paper, a novel ClGan (Crop Leaf Gan) with improved loss function has been developed with a reduced number of parameters as compared to the existing state-of-the-art methods. The generator and discriminator of the developed ClGan have been encompassed with an encoder-decoder network to avoid the vanishing gradient problem, training instability, and non-convergence failure while preserving complex intricacies during synthetic image generation with significant lesion differentiation. The proposed improved loss function introduces a dynamic correction factor that stabilizes learning while perpetuating effective weight optimization. In addition, a novel plant leaf classification method ClGanNet, has been introduced to classify plant diseases efficiently. The efficiency of the proposed ClGan was validated on the maize leaf dataset in terms of the number of parameters and FID score, and the results are compared against five other state-of-the-art GAN models namely, DC-GAN, W-GAN, WGanGP, InfoGan, and LeafGan. Moreover, the performance of the proposed classifier, ClGanNet, was evaluated with seven state-of-the-art methods against eight parameters on the original, basic augmented, and ClGan augmented datasets. Experimental results of ClGanNet have outperformed all the considered methods with 99.97% training and 99.04% testing acc

关键词： Plant disease identification deep learning Data augmentation Lesion differentiation Crop leaf generative adversarial network net deep CNN

来源：评论

学校读者我要写书评

暂无评论

MBUDepthNet: real-time Unsupervised Monocular Depth Estimation Method for Outdoor Scenes

引用

IEEE ACCESS 2024年 12卷 63598-63609页

作者： Bian, Zhekai Wang, Xia Liu, Qiwei Lv, Shuaijun Wei, Ranfeng Beijing Inst Technol Sch Opt & Photon Beijing 100081 Peoples R China Beijing Inst Technol Sch Opt & Photon Key Lab Photoelect Imaging Technol & Syst Minist Educ China Beijing 100081 Peoples R China

Monocular depth estimation technology has emerged as a critical component across a variety of outdoor applications like robotics, augmented reality, autonomous driving, and 3D reconstruction. Mainstream monocular depth estimation methods consistently face challenges in applications requiring real-time performances, as they exhibit considerable computational complexity, resulting in poor runtime performance. Here, we propose an innovative processing module named MDE-Lite. Based on that, we develop a lightweight yet effective depth estimation network named MBUDepthNet. Besides, we build a training scheme with multiple loss functions. Experimental validation on KITTI dataset demonstrates that our method not only rivals mainstream methods in terms of accuracy but also exhibits superior computational efficiency. Compared to the method using ResNet-18, our method achieves a 22% higher frame rate in terms of frames per second.

关键词： Estimation Training Feature extraction real-time systems Neural networks Supervised learning Computer vision deep learning depth estimation unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

CNN based plant disease identification using PYNQ FPGA

引用

SYSTEMS AND SOFT COMPUTING 2024年 6卷

作者： Perumal, Vivek Karthick Supriyaa, T. Santhosh, P. R. Dhanasekaran, S. Sona Coll Technol Dept ECE Salem Tamil Nadu India Sri Eshwar Coll Engn Dept ECE Coimbatore India

This research presents a novel approach for plant disease identification utilizing Convolutional Neural Networks (CNNs) and the PYNQ FPGA platform. The study leverages the parallel processing capabilities of FPGAs to accelerate CNN inference, aiming to enhance the efficiency of plant disease detection in agricultural settings. The implementation involves optimizing the CNN architecture for deployment on the PYNQ FPGA, considering factors such as image size and learning rates. Through experimentation, the research refines hyper parameters, achieving improved accuracy and F1 scores. Visualizations using heat maps highlight the CNN's reliance on color, shape, and texture for feature extraction in disease identification. The integration of FPGA technology demonstrates promising advancements in real-time, high-performance plant disease classification, offering potential benefits for precision agriculture and crop management. This research contributes to the growing field of FPGA-accelerated deep learning applications in agro technology, addressing challenges in plant health monitoring and fostering sustainable agricultural practices.

关键词： CNN image processing Plant Disease FPGA PYNQ

来源：评论

学校读者我要写书评

暂无评论

Bridging the simulation-to-real gap of depth images for deep reinforcement learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 253卷

作者： Jang, Yoonsu Baek, Jongchan Jeon, Soo Han, Soohee Pohang Univ Sci & Technol Dept Convergence IT Engn 77 Cheongam Ro Pohang Si 36763 Gyeongbuk South Korea Pohang Univ Sci & Technol Dept Elect Engn 77 Cheongam Ro Pohang Si 36763 Gyeongbuk South Korea Elect & Telecommun Res Inst 218 Gajeong Ro Daejeon 34129 South Korea Univ Waterloo Dept Mech & Mechatron Engn 200 Univ Ave West Waterloo ON N2L 3G1 Canada

While deep reinforcement learning (DRL) models are effective at learning appropriate actions from highdimensional data, they require large amounts of costly and time-consuming training data to be collected in real -world settings. For this reason, collecting data in simulations offers a promising alternative, but transferring policy networks from simulation to reality can be challenging due to differences in perception between the virtual and real worlds. This paper proposes a two-level method to bridge the simulation-toreality (sim-to-real) gap for depth images, specifically for autonomous environmental navigation that uses DRL. Simulated depth images are first translated at a perception level through generative adversarial network (GAN) to make them look like real data from a depth sensor. Simulated and GAN-generated depth images are encoded into latent representations, and the encoder is trained in the latent space to make the two images paired. This encoder is trained simultaneously with a reinforcement learning network model to extract domain-invariant and task-relevant features from depth images and map the behavioral similarity of states to the latent space. Our experimental results demonstrate that our approach can effectively bridge the sim-to-real gap, enabling policies learned in simulation to maintain their control performance in the real world.

关键词： Autonomous navigation Depth image Mobile robot Sim-to-real

来源：评论

学校读者我要写书评

暂无评论

SABA: Scale-adaptive Attention and Boundary Aware Network for real-time semantic segmentation

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 282卷

作者： Luo, Huilan Liu, Chunyan Shark, Lik-Kwan Jiangxi Univ Sci & Technol Sch Informat Engn Ganzhou 341000 Peoples R China Univ Cent Lancashire Appl Digital Signal & Image Proc Res Ctr Sch Engn Preston England

Balancing accuracy and speed is crucial for semantic segmentation in autonomous driving. While various mechanisms have been explored to enhance segmentation accuracy in lightweight deep learning networks, adding more mechanisms does not always lead to better performance and often significantly increases processing time. This paper investigates a more effective and efficient integration of three key mechanisms - context, attention, and boundary - to improve real-time semantic segmentation of road scene images. Based on an analysis of recent fully convolutional encoder-decoder networks, we propose a novel Scale-adaptive Attention and Boundary Aware (SABA) segmentation network. SABA enhances context through a new pyramid structure with multi-scale residual learning, refines attention via scale-adaptive spatial relationships, and improves boundary delineation using progressive refinement with a dedicated loss function and learnable weights. Evaluations on the Cityscapes benchmark show that SABA outperforms current real-time semantic segmentation networks, achieving a mean intersection over union (mIoU) of up to 76.7% and improving accuracy for 17 out of 19 object classes. Moreover, it achieves this accuracy at an inference speed of up to 83.4 frames per second, significantly exceeding real-time video frame rates. The code is available at https://***/liuchunyan66/SABA.

关键词： real-time semantic segmentation Context enhancement Multi-scale adaptive attention Boundary awareness

来源：评论

学校读者我要写书评

暂无评论

time-Series Data-Driven PM2.5 Forecasting: From Theoretical Framework to Empirical Analysis

引用

ATMOSPHERE 2025年第3期16卷 292-292页

作者： Wu, Chunlai Wang, Ruiyang Lu, Siyu Tian, Jiawei Yin, Lirong Wang, Lei Zheng, Wenfeng Univ Elect Sci & Technol China Sch Automation Chengdu 610054 Peoples R China Hanyang Univ Dept Comp Sci & Engn Ansan 15577 South Korea Louisiana State Univ Dept Geog & Anthropol Baton Rouge LA 70803 USA

PM2.5 in air pollution poses a significant threat to public health and the ecological environment. There is an urgent need to develop accurate PM2.5 prediction models to support decision-making and reduce risks. This review comprehensively explores the progress of PM2.5 concentration prediction, covering bibliometric trends, time series data characteristics, deep learning applications, and future development directions. This article obtained data on 2327 journal articles published from 2014 to 2024 from the WOS database. Bibliometric analysis shows that research output is growing rapidly, with China and the United States playing a leading role, and recent research is increasingly focusing on data-driven methods such as deep learning. Key data sources include ground monitoring, meteorological observations, remote sensing, and socioeconomic activity data. deep learning models (including CNN, RNN, LSTM, and Transformer) perform well in capturing complex temporal dependencies. With its self-attention mechanism and parallel processing capabilities, Transformer is particularly outstanding in addressing the challenges of long sequence modeling. Despite these advances, challenges such as data integration, model interpretability, and computational cost remain. Emerging technologies such as meta-learning, graph neural networks, and multi-scale modeling offer promising solutions while integrating prediction models into real-world applications such as smart city systems can enhance practical impact. This review provides an informative guide for researchers and novices, providing an understanding of cutting-edge methods, practical applications, and systematic learning paths. It aims to promote the development of robust and efficient prediction models to contribute to global air pollution management and public health protection efforts.

关键词： PM2.5 deep learning bibliometric analysis LSTM transformer time-series

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Evolutionary Neural Architecture Search

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2024年第3期28卷 566-569页

作者： Sun, Yanan Xue, Bing Zhang, Mengjie Yen, Gary G. Sichuan Univ Coll Comp Sci Chengdu 610064 Peoples R China Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6140 New Zealand Victoria Univ Wellington Ctr Data Sci & Artificial Intelligence Wellington 6140 New Zealand Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74074 USA

deep neural networks (DNNs) have shown remarkable performance in solving a wide variety of real-world problems, ranging from image recognition to natural language processing and self-driving vehicles. In principle, the achievements of DNNs are mainly contributed by their deep architectures, which can learn meaningful representations at different levels. This can greatly enhance the performance of the subsequent machine-learning algorithms. However, manually designing an optimal deep architecture for a particular problem requires a rich knowledge of both the investigated problem domain and the DNNs, which is not necessarily held by every end user interested in this area.

关键词： Special issues and sections Artificial neural networks Performance evaluation Machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Lightweight deep-learning Algorithm for Welding Defect Detection in New Energy Vehicle Battery Current Collectors

引用

IEEE SENSORS JOURNAL 2024年第13期24卷 21655-21668页

作者： Yuan, Lei Chen, Yanrong Tang, Hai Gao, Ren Wu, Wenhuan Hubei Univ Automot Technol Sch Elect & Informat Engn Hubei Key Lab Energy Storage & Power Battery Shiyan 442002 Peoples R China

The future direction of global automotive development is electrification, and the battery current collector (BCC) is an essential component of new energy vehicle batteries. However, the welding defects in the BCC during the welding process are characterized by a disorganized distribution, extensive size variations, multiple types, and ambiguous features, posing challenges for detecting welding defects in the current collector. This article proposes a lightweight deep-learning algorithm called MGNet for detecting welding defects in the current collectors. We introduce a lightweight MDM module based on multiscale channels, which utilizes deep dynamic convolutions as its basic structure to extract compelling features while reducing computational complexity. We also propose a lightweight feature fusion network called GS_GFPN, which fully leverages the semantic information of the backbone network feature maps while reducing parameter redundancy and maintaining detection accuracy. Experimental evaluations on both the BCC surface defect database and the publicly available Northeastern University (NEU) surface defect database demonstrate that MGNet outperforms existing methods with significant improvements in detection accuracy. The mean average precision (mAP) at IoU threshold 0.5 is 93.9%-78.0%, respectively, with frames per second (FPS) of 212.8 and 238.1 and a model weight of only 3.1 M. Moreover, the algorithm is successfully deployed on the NVIDIA Jetson Nano embedded device, enabling real-time defect detection for practical industrial applications.

关键词： Batteries Welding Feature extraction Computational modeling image processing Defect detection deep learning Battery current collector (BCC) deep learning defect detection model deployment

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：