检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Shengdong Jia, Fan Li, Xiang Zhang, Hao Shi, Jun Ma, Liyan Ying, Shihui Department of Mathematics School of Science Shanghai University Shanghai200444 China Institute University of Utah Salt Lake CityUT84102 United States School of Computer Science and Technology East China Normal University Shanghai China School of Communication and Information Engineering Shanghai University Shanghai200444 China School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200444 China Shanghai Institute of Applied Mathematics and Mechanics The School of Mechanics and Engineering Science Shanghai University Shanghai200072 China

Few-shot semantic segmentation (FSS) methods have shown great promise in handling data-scarce scenarios, particularly in medical image segmentation tasks. However, most existing FSS architectures lack sufficient interpretability and fail to fully incorporate the underlying physical structures of semantic regions. To address these issues, in this paper, we propose a novel deep unfolding network, called the Learned Mumford-Shah Network (LMSNet), for the FSS task. Specifically, motivated by the effectiveness of pixel-to-prototype comparison in prototypical FSS methods and the capability of deep priors to model complex spatial structures, we leverage our learned Mumford-Shah model (LMS model) as a mathematical foundation to integrate these insights into a unified framework. By reformulating the LMS model into prototype update and mask update tasks, we propose an alternating optimization algorithm to solve it efficiently. Further, the iterative steps of this algorithm are unfolded into corresponding network modules, resulting in LMS-Net with clear interpretability. Comprehensive experiments on three publicly available medical segmentation datasets verify the effectiveness of our method, demonstrating superior accuracy and robustness in handling complex structures and adapting to challenging segmentation scenarios. These results highlight the potential of LMS-Net to advance FSS in medical imaging applications. Our code will be available at: https:// ***/SDZhang01/LMSNet Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Flow of Jeffrey Fluid Near Impulsively Moving Plate with Nanoparticle and Activation Energy

SSRN

引用

SSRN 2022年

作者： Trivedi, Mumukshu Otegbeye, O. Ansari, Md Sharifuddin Fayaz, Touseef Institute of management Nirma University Ahmedabad India School of Computer Science and Applied Mathematics Faculty of Science University of the Witwatersrand Johannesburg South Africa School of Technology Pandit Deendayal Energy University Gandhinagar382421 India

Present mathematical study looks over unsteady MHD flow and heat transfer of Jeffrey nanofluid at impulsive moving plate. Heat transfer aspect is carried out by incorporating the impacts of viscous dissipation and activation energy. Equations, describing flow, are non-dimensionalised by implementing compatible transformations and retained in same form. We exercised an accurate numerical algorithm (bi-variate spectral quailinaerisation method) to generate solution of non-linear coupled partial differential equations. Approximate solutions are substantiated by evaluating solution and residual based error norms over number of iterations. These error analysis confirms approximate solutions with sufficient accuracy. © 2022, The Authors. All rights reserved.

关键词： Activation energy

来源：评论

学校读者我要写书评

暂无评论

Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting

arXiv

引用

arXiv 2024年

作者： Lim, Soon Hoe Wang, Yijin Yu, Annan Hart, Emma Mahoney, Michael W. Li, Xiaoye S. Erichson, N. Benjamin Department of Mathematics KTH Royal Institute of Technology Sweden Nordita KTH Royal Institute of Technology Stockholm University Sweden International Computer Science Institute Department of Statistics University of California at Berkeley United States Center for Applied Mathematics Cornell University United States Department of Mathematics Emory University United States Lawrence Berkeley National Laboratory United States

Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impact of the specific choice of probability path model on forecasting performance remains under-explored. In this work, we demonstrate that forecasting spatio-temporal data with flow matching is highly sensitive to the selection of the probability path model. Motivated by this insight, we propose a novel probability path model designed to improve forecasting performance. Our empirical results across various dynamical system benchmarks show that our model achieves faster convergence during training and improved predictive performance compared to existing probability path models. Importantly, our approach is efficient during inference, requiring only a few sampling steps. This makes our proposed model practical for real-world applications and opens new avenues for probabilistic forecasting. © 2024, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on the Classification of the Edibility of Mushrooms

A Comprehensive Study on the Classification of the Edibility...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Saurav Verma Om Pandey Tanupriya Choudhury Ayan Sar Ketan Kotecha School of Computer Science University of Petroleum and Energy Studies Dehradun Uttarakhand India CSE Dept. Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India Symbiosis Center for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India

Food is very integral when it comes to sustaining life. However, it is crucial to identify what food to eat. Mother Nature finds ways to scare away animals. Over time, plants have evolved to prevent animals from eating them, like having chilies, poisonous leaves, or even deadly fruits just so animals don't eat them. Animals eat them or get itches from them many times before learning that a particular plant is dangerous. But we can't let humans learn like this too. So, to prevent people from eating such poisonous food, we need to find ways to distinguish the food as edible or poisonous. Different species of mushrooms also come in this category and we can tell from the different properties of their various parts to characterize healthy-to-eat mushrooms. In this research, we attempt to find the best machine-learning model to identify edible mushrooms from tabulated visually distinguishable details of different mushroom samples. At this point in time, this research was crucial as the work done in this field has withered over time and the results have now become obsolete. The main reason for this drastic change is the increase in performance of the machine learning models themselves as well as the field as a whole has gone through tremendous changes and improvements. Every day, some changes keep coming and this field is progressing a lot. So, it becomes important that such kinds of studies keep on coming from our fellow researchers to keep all the work up to date.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model

Context-aware Emotion Recognition Based on Vision-Language P...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： XingLin Li Xinde Li Chuanfei Hu Huaping Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Nanjing Center for Applied Mathematics Nanjing China Southeast University Shenzhen Research Institute Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Aware Emotion Recognition (CAER), and were incorporated structure of the Contrastive Language–Image Pre-training (CLIP) model as promising alternative to classifier. There are two parts in CAER-CLIP model. In the visual part, facial expressions and contextual information of the image are simultaneously extracted to obtain the final feature embeddings, which are then used as a learnable “class” token for text-image pairing with desired module. In the textual part, we use text labels for emotion recognition classes as input. The outputs were merged to participate the comparative study to generated parameters of the model. The experiments demonstrate the effectiveness of the proposed method and show that our CAER-CLIP outperforms the state-of-the-art results on the CAER benchmark. The ablation experiment verified the effectiveness of both the classifier-based and text-based (ours without classifier) models, demonstrating that our method with the CAER-CLIP structure performed better, and the incorporation of a text encoder in the deep network model architecture effectively enhancing recognition accuracy.

关键词： Training Emotion recognition Visualization Accuracy Text recognition Face recognition Benchmark testing Feature extraction Data mining Context modeling

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

引用

Procedia computer science 2023年 218卷 2675-2683页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes; (i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database.

关键词： Eye abnormality Diabetic retinopathy Fundus imaging Deep-Learning Classification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Scheme for Modulation Classification under Fading Channels

Deep Learning Scheme for Modulation Classification under Fad...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Sajjad A. Ghauri Mubashar Sarfraz Gunjan Chhabra Keshav Kaushik Asim Zafar Inam Ullah Khan School of Engineering & Applied Sciences ISRA University Islamabad Pakistan Faculty of Engineering and Computing NUML University Islamabad Pakistan Department of CSE Graphic Era Hill University Graphic Era Deemed to be University Dehradun Uttarakhand India Amity School of Engineering and Technology Amity University Punjab India Department of Computer Science National University of Technology Islamabad Pakistan

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

The field of automatic modulation classification using deep neural networks has undergone significant development in recent years. In this research, M-QAM and N-PSK modulation formats have been considered for classification. The deep neural network architecture is directly fed with raw signals that are often corrupted with channel noise and fading effects such as Rayleigh and Nakagami. The proposed classifier structure also incorporates normalized cumulants of higher order from the received signal. The proposed DNN architecture’s performance is evaluated by comparing its efficiency for raw data and extracted features-based classification. We have validated the classifier efficiency through three different cases. Our proposed classifier demonstrates remarkable capability in efficiently classifying modulation formats.

关键词： Nakagami distribution Deep learning Noise Modulation Artificial neural networks computer architecture Rayleigh channels Feature extraction Robustness Data mining

来源：评论

学校读者我要写书评

暂无评论

UGV-CBRN: An Unmanned Ground Vehicle for Chemical, Biological, Radiological, and Nuclear Disaster Response

arXiv

引用

arXiv 2024年

作者： Schwaiger, Simon Muster, Lucas Novotny, Georg Schebek, Michael Wöber, Wilfried Thalhammer, Stefan Böhm, Christoph University of Applied Sciences Technikum Wien Faculty of Industrial Engineering Vienna1200 Austria Graz University of Technology Faculty of Computer Science and Biomedical Engineering Institute of Software Technology Inffeldgasse 16b/II Graz8010 Austria University of Natural Resources and Life Sciences Department of Biotechnology Institute for Computational Biology Muthgasse 18 Vienna1190 Austria

Robotic search and rescue (SAR) supports response teams by accelerating disaster assessment and by keeping operators away from hazardous environments. In the event of a chemical, biological, radiological, and nuclear (CBRN) disaster, robots are deployed to identify and locate radiation sources. Human responders then assess the situation and neutralize the danger. The presented system takes a step toward enhanced integration of robots into SAR teams. Integrating autonomous radiation mapping with semi-autonomous substance sampling and online analysis of the CBRN threat lets the human operator localize and assess the threat from a safe distance. Two LiDARs, an IMU, and a Geiger counter are used for mapping the surrounding area and localizing potential radiation sources. A mobile manipulator with six Degrees of Freedom manipulates valves and samples substances that are analyzed by an onboard Raman spectrometer. The human operator monitors the mission’s progression from a remote location defining target locations and directing the semi-autonomous manipulation processes. Diverse recovery behaviours aid robot deployment, system state monitoring, as well as recovery of hard- and software. Field tests showcase the capabilities of the presented system during trials at the CBRN disaster response challenge European Robotics Hackathon (EnRicH). We provide recorded sensor data and implemented software through a GitHub repository: https://***/TW-Robotics/ search-and-rescue-robot-2024. © 2024, CC BY.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between Modalities with Cross-Modal Generative AI and Large Model

Bridging the Gap Between Modalities with Cross-Modal Generat...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Arun Pratap Srivastava Priyanka Gupta Vijilius Helena Raj Manish Gupta Neha Khare Muntather Almusawi Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh Institute of Aeronautical Engineering Dundigal Hyderabad Department of Applied Sciences New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Department of Computer Science & Engineering IES Insititute of Technology and Management IES University Bhopal M.P. India The Islamic university Najaf Iraq

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

The Multi-Modal Cross-Attention Network (MCAN) is a revolutionary way to bridge the gap between varied data modalities that has emerged in response to the growing field of cross-modal generative AI and huge models. In this work, we highlight the substantial benefits of MCAN and provide its important contributions, aims, motivations, research issues, and solutions. MCAN has changed the game by dominating key performance indicators. One of its most distinguishing features is its innate accuracy in aligning various data modalities. This alignment is made easier with the use of cutting-edge cross-modal attention techniques, guaranteeing the smooth incorporation of data from many sources like pictures, text, and audio. When it comes to reconstructing information from several sources, The intended meaning is more likely to be preserved since MCAN makes material more semantically consistent. Uniformity is crucial for content-based recall and image-text matching. With its advanced ethical concerns in content creation and greater generalization to unseen material, MCAN is a cutting-edge solution in the rapidly developing area of cross-modal generative AI. When it comes to huge models and cross-modal generative AI, MCAN is a major step forward.

关键词： Ethics Leadership Generative AI Semantics Key performance indicator Production Data models

来源：评论

学校读者我要写书评

暂无评论

A study of three butterflies: entanglement wedge method, OTOC and pole-skipping

arXiv

引用

arXiv 2024年

作者： Baishya, Banashree Chakraborty, Adrita Padhi, Nibedita Department of Physics Indian Institute of Technology Guwahati North Guwahati781039 India Faculty of Physics and Applied Computer Science AGH University of Krakow al. A. Mickiewicza 30 Krakow30-059 Poland Department of Physics National Tsing-Hua University Hsinchu30013 Taiwan Department of Physics Indian Institute of Technology Kharagpur Kharagpur721302 India

In this work, we investigate two salient chaotic features, namely Lyapunov exponent and butterfly velocity, in the context of an asymptotically Lifshitz black hole background with an arbitrary critical exponent. These features are computed using three methods: entanglement wedge method, out-of-time-ordered correlator computation and pole-skipping. We present a comparative study of the aforementioned features where all of these methods yield exactly similar results for the butterfly velocity and Lyapunov exponent. This establishes an equivalence between all three methods for probing chaos in the chosen gravity background. Furthermore, we evaluate the chaos at the classical level by computing the eikonal phase and Lyapunov exponent from the bulk gravity. These quantities emerge as nontrivial functions of the anisotropy index. By examining the classical eikonal phase, we uncover different scattering scenarios in the near-horizon and near-boundary regimes. We also discuss potential limitations regarding the choice of the turning point of the null geodesic in our approach. © 2024, CC BY.

关键词： Lyapunov functions

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：