检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Elbaz, Ran Yehudai, Gilad Galun, Meirav Maron, Haggai Technion – Israel Institute of Technology Electrical and Computer Engineering Center for Data Science New York University United States Weizmann Institute of Science NVIDIA Research United States

Reconstructing training data from trained neural networks is an active area of research with significant implications for privacy and explainability. Recent advances have demonstrated the feasibility of this process for several data types. However, reconstructing data from group-invariant neural networks poses distinct challenges that remain largely unexplored. This paper addresses this gap by first formulating the problem and discussing some of its basic properties. We then provide an experimental evaluation demonstrating that conventional reconstruction techniques are inadequate in this scenario. Specifically, we observe that the resulting data reconstructions gravitate toward symmetric inputs on which the group acts trivially, leading to poor-quality results. Finally, we propose two novel methods aiming to improve reconstruction in this setup and present promising preliminary experimental results. Our work sheds light on the complexities of reconstructing data from group invariant neural networks and offers potential avenues for future research in this domain. © 2024, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Dynamic Topology Management in Ad-Hoc Networks for Improved Performance

Dynamic Topology Management in Ad-Hoc Networks for Improved ...

引用

International Conference on Advances in Information Technology (ICAIT)

作者： A.S. Anakath R. Kannadasan G. Simi Margarat A. Pasumpon Pandian Antony Sibiya Varghese V Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Vellore Tamil Nadu India Department of Computer Science and Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering CARE College of Engineering Trichy India Department of Artificial Intelligence and Data Science GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Optimization in ad hoc networks is a highly specialized task because the structure of the network is loosely formed, and each node is independently responsible for its operation. In order to obtain a better result from this solely formed networks this report offer extensive Dynamic Topology Management (DTM) method. Dynamic routing protocols lager lines, dividend balancing, Life-saving administration, guarantee of reliability, cross-layer design, security aspects and the on-time monitoring and discovery of topology changes are the main objectives and steps to be accomplished. Real-time Location monitoring and forest structure discovery are made possible by employing adaptive routing protocols, namely Dynamic Source Routing(DSR) and Ad-Hoc On-Demand Distance Vector(AODV). Also, the algorithms are capable of making advance adjustments to routing routes and resource allocations drawn from the mobility patterns forecasting which is vital. Load balancing methods, which distribute traffic in a network evenly, enable the system to run efficiently and avoid problems caused by overloading. Algorithms that are energy-efficient and make the best use of energy resources having their topology's optimized are introduced to the streamlined energy distribution systems. These algorithms are focused on the node's energy level. Through fault tolerance techniques which recognize and handle failures in nodes and partitioned networks, connectedness activity is a continuous one. Through QoS perception, the network topology might automatically be tailored to conform to the given quality criteria, thus not restricting the choice for differing applications. The proposed could have defenses against adversary nodes and their potential DDoS attacks which will enhance network protection. Yet another advantage of an architectural style that promotes cross-layer collaboration is enhanced topology management which is the goal around which the functions of various levels of the protocol stack revolve

关键词： Network topology Aerodynamics Routing Ad hoc networks Routing protocols Real-time systems Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Fusion Residual Network For Single Image Rain Removal

引用

Journal of computers (Taiwan) 2023年第2期34卷 129-140页

作者： He, Jia-Chen Fu, Ming-Jian Lin, Li-Qun College of Physics and Information Engineering Fuzhou University Fuzhou350000 China College of Computer and Data Science Fuzhou University Fuzhou350000 China

Deep learning has been widely used in single image rain removal and demonstrated favorable universality. However, it is still challenging to remove rain streaks, especially in the nightscape rain map which exists heavy rain and rain streak accumulation. To solve this problem, a single image nightscape rain removal algorithm based on Multi-scale Fusion Residual Network is proposed in this paper. Firstly, based on the motion blur model, evenly distributed rain streaks are generated and the dataset is recon-structed to solve the lack of nightscape rain map datasets. Secondly, according to the characteristics of the night rain map, multi-scale residual blocks are drawn on to reuse and propagate the feature, so as to ex-ploit the rain streaks details representation. Meanwhile, the linear sequential connection structure of multi-scale residual blocks is changed to a u-shaped codec structure, which tackles the problem that features cannot be extracted effectively due to insufficient scale. Finally, the features of different scales are com-bined with the global self-attention mechanism to get different rain streak components, then a cleaner re-stored image is obtained. The quantitative and qualitative results show that, compared to the existing algo-rithms, the proposed algorithm can effectively remove rain streaks while retaining detailed information and ensuring the integrity of image information. © 2023 computer Society of the Republic of China. All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Enhancing Kidney Stone Detection in CT scans with Image Processing and the DCNN-RELM Model

Enhancing Kidney Stone Detection in CT scans with Image Proc...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Manjula Prabakaran Jesmin Zakaria S Kannan Santhiya P Rajasekar P M V Rathnamma Department of CSE- (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh India Department of Electronics & Communication Engineering (ECE) NSHM Knowledge Campus Durgapur West Bengal India Department of Computer Science and Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Trichy Tamilnadu India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamilnadu India Department of CSE KLM College of Engineering for Women Kadapa Andhra Pradesh India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

CT of the urinary system, abdomen, and kidneys appears to improve kidney stone screening and identification. Segmentation and categorization are essential for kidney stone identification and management. This work developed a semi-automatic kidney stone detection system using geometric concepts and image processing. The main steps include model training, feature extraction, segmentation, embossing, and preprocessing. Preprocessing involves trimming the input image to remove unnecessary kidney regions to focus on critical CT scan locations. Relief embossing enhanced image details. Segmentation accurately classified veins and blood arteries to define kidney stone boundaries. CNN-RELM was our training model. Compared to CNN and ELM models, the recommended system performed better. Its 93.87% kidney stone detection and localization accuracy prove its reliability. The semi-automatic system's reliable kidney stone detection and segmentation method may improve clinical decision-making. Combining CNN-RELM modeling and enhanced image processing could lead to medical imaging applications.

关键词： Training Image segmentation Accuracy Three-dimensional displays Computed tomography Embossing data preprocessing Reliability Kidney Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter

arXiv

引用

arXiv 2023年

作者： Chen, Yiqun T. Zou, James Department of Biomedical Data Science Stanford University StanfordCA94305 United States Departments of Biomedical Data Science Electrical Engineering and Computer Science Stanford University StanfordCA94305 United States

Recent progress in generative artificial intelligence (gen-AI) has enabled the generation of photo-realistic and artistically-inspiring photos at a single click, catering to millions of users online. To explore how people use gen-AI models such as DALLE and StableDiffusion, it is critical to understand the themes, contents, and variations present in the AI-generated photos. In this work, we introduce TWIGMA (TWItter Generative-ai images with Metadata), a comprehensive dataset encompassing over 800,000 gen-AI images collected from Jan 2021 to March 2023 on Twitter, with associated metadata (e.g., tweet text, creation date, number of likes), available at https://***/records/8031785. Through a comparative analysis of TWIGMA with natural images and human artwork, we find that gen-AI images possess distinctive characteristics and exhibit, on average, lower variability when compared to their non-gen-AI counterparts. Additionally, we find that the similarity between a gen-AI image and natural images is inversely correlated with the number of likes. Finally, we observe a longitudinal shift in the themes of AI-generated images on Twitter, with users increasingly sharing artistically sophisticated content such as intricate human portraits, whereas their interest in simple subjects such as natural scenes and animals has decreased. Our findings underscore the significance of TWIGMA as a unique data resource for studying AI-generated images. © 2023, CC BY.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition with label-noisy under Dual-Branch Noise Extraction and Suppression

引用

IEEE Transactions on Affective Computing 2024年

作者： Li, Yunfei Liu, Hao Jiang, Daihong Liang, Jiuzhen Changzhou University School Of Computer Science And Artificial Intelligence Changzhou China Xuzhou University Of Technology School Of Information Engineering School Of Big Data Xuzhou China

Noisy labels in Facial Expression Recognition (FER) datasets severely affect the performance of FER models. We propose a novel dual-branch noise extraction and suppression method to address this issue. This algorithm reduces the model's impact from noisy labels by decreasing the dataset noise ratio and suppressing label-noisy samples. The method comprises three primary stages: sample extraction, pseudo-label generation, and re-training. The approach initially extracts label-noisy samples from the dataset by computing an exponential moving average of the model predictions and the joint probability distribution matrix of noisy and actual labels. The remaining samples form a clean dataset. Next, the training weights of the clean dataset are utilized to assign appropriate pseudo-labels to the label-noisy samples. Subsequently, the noisy labels are replaced with pseudo-labels to create a corrected dataset. The corrected and clean datasets are combined to create the reconstructed dataset, reducing noisy labels within the dataset. Finally, the model is retrained using the reconstructed dataset. Furthermore, this study introduces a novel gradient suppression smoothing function specifically designed to mitigate the impact of label-noisy samples in the dataset during the re-training process. The proposed algorithm is robust, with accuracies of 91.17%, 91.56%, and 91.58% on the RAF-DB dataset with 10%, 20%, and 30% noisy labels, and accuracies of 89.91%, 90.17%, and 89.69% on the corresponding FERPlus. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG signals using Machine learning algorithms 2

Classification of EEG signals using Machine learning algorit...

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Suganyadevi, S. Shanmuga Priya, S. Kiruba, B. Gomathi, M. Kalshetty, Jagadevi. N. Kpr Institute of Engineering and Technology Department of ECE Coimbatore India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Coimbatore India Nitte Meenakshi Institute of Technology Department of Computer Science & Engineering Bengaluru India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

An alternative to human expert-performed manual identification is automatic detection of epilepsy using electroencephalogram (EEG) data. Automatic epilepsy detection from EEG data need high classification performance in order to eliminate false positives. A classification strategy for automated epilepsy identification using EEG data is being proposed in this work. The signals generated form the EEG device were transformed using the DWT before feature extraction was carried out. Based on various statistical parameters and crossing frequency features, an algorithm dubbed GBMs fusion was developed to identify EEG data. As an added bonus, the significant traits were first selected using a genetic algorithm. EEG data from the University of Bonn has been used to test the suggested method's ability to distinguish between normal and ictal EEG patterns. Experimentation has shown that the suggested GBMs fusion may increase the EEG classification performance. It is also possible to identify epilepsy from EEG data with a 100% accuracy using the suggested GBMs fusion. © 2022 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

HerbSimNet: Deep Learning -Based Classification of Indian Medicinal Plants with High Inter-Class Similarities

引用

Procedia computer science 2025年 258卷 765-774页

作者： N. Shobha Rani Bhavya K R Pushpa B.R. Ragavendra M. Devadas Department of Artificial Intelligence and Data Science GITAM School of Technology Bengaluru GITAM (Deemed to be) University India Department of Computer Science and Engineering GITAM School of Technology Bengaluru GITAM (Deemed to be) University India Department of Computer Science School of Computing Mysuru Amrita Vishwa Vidyapeetham India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Medicinal plant species recognition is important across diverse sectors such as Ayurveda, agriculture, environment conservation and botanical research. Specific groups of plants in Indian medicinal plant ecosystem exhibit significant inter-class similarities due to varying abundance and ecological factors. To address the challenges involved in the process of classifying these species in this work a deep learning model Herb-SimNet is proposed. The Herb-SimNet analyzes similarity of plant species over other plant species using vision based deep learning and machine learning techniques. The proposed model works based on the combination of wavelet features and convolutional features extracted using three sequential convolution layers to extract the prominent features that distinguish variations among the inter class similarity plant species. To perform experiments, a dataset is created by capturing medicinal plant leaf images using box model in plain background and uniform lighting. A smart phone captured twelve Indian medicinal plant species comprising of about 1400+ samples that belongs different plant species but similar morphological structure is collected. Baseline experiments are carried out between Herb-SimNet and other state-of-the-art deep learning models for classification based on the proposed dataset. The outcomes demonstrate that Herb_SimNet provides clear interpretation one plant variety with others and achieves superior accuracy in prediction than that of state-of-the-art approaches. Furthermore, the model demonstrates better generalization towards the other inter-class similarity groups considered for testing. In conclusion, the proposed dataset and Herb-SimNet plays a a crucial role in advancement of research concerning Indian medicinal plant species classification resulting into enhancement of AI-based technology for biodiversity conservation and ethnobotanical studies.

关键词： Classification inter-class similarities confusing plant species medicinal plants wavelet image features

来源：评论

学校读者我要写书评

暂无评论

Perceptual Video Summarization Using Keyframes Extraction Technique 3

Perceptual Video Summarization Using Keyframes Extraction Te...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Rajitha Jasmine, R. Nimmagadda, Padmaja Sudhakar, K. Benitha Christinal, J. Rajasekar, P. Syed Musthafa, A. R. M. K. Engineering College Department of Information Technology Kavaraipettai India Mohan Babu University Department of Electronics and Communication Tirupati India Madanapalle Institute of Technology Department of Computer Science Madanapalle India Panimalar Engineering College Department of Information Technology Chennai India Srm Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu India M. Kumarasamy College of Engineering Department of Information Technology Karur India

ISBN: (纸本)9798350336238

The growth of video content in recent years is a challenging problem due to increased memory storage and time consuming for analyzing content of the video. Therefore, there is a need to reduce the content for human usage. This paper presents a keyframes technique that uses co-occurrence matrix and permutation computation for perceptual video summarization (PVS). The Human Visual System (HVS) needs to incorporate the PVS. It helps to allow for the importance of perceptually significant contents. The proposed method uses different kinds of videos to evaluate the effectiveness of the work. The subjective evaluation scores have evaluated the proposed work. © 2023 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Towards Large-scale Chemical Reaction Image Parsing via a Multimodal Large Language Model

arXiv

引用

arXiv 2025年

作者： Chen, Yufan Leung, Ching Ting Sun, Jianwei Huang, Yong Li, Linyan Chen, Hao Gao, Hanyu Department of Chemical and Biological Engineering Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Department of Chemistry Hong Kong University of Science and Technology Hong Kong Department of Data Science City University of Hong Kong Hong Kong

Artificial intelligence (AI) has demonstrated significant promise in advancing organic chemistry research;however, its effectiveness depends on the availability of high-quality chemical reaction data. Currently, most published chemical reactions are not available in machine-readable form, limiting the broader application of AI in this field. The extraction of published chemical reactions into structured databases still relies heavily on manual curation, and robust automatic parsing of chemical reaction images into machine-readable data remains a significant challenge. To address this, we introduce the Reaction Image Multimodal large language model (RxnIM), the first multimodal large language model specifically designed to parse chemical reaction images into machine-readable reaction data. RxnIM not only extracts key chemical components from reaction images but also interprets the textual content that describes reaction conditions. Together with specially designed large-scale dataset generation method to support model training, our approach achieves excellent performance, with an average F1 score of 88% on various benchmarks, surpassing literature methods by 5%. This represents a crucial step toward the automatic construction of large databases of machine-readable reaction data parsed from images in the chemistry literature, providing essential data resources for AI research in chemistry. The source code, model checkpoints, and datasets developed in this work are released under permissive licenses. An instance of the RxnIM web application can be accessed at https://***/spaces/CYF200127/RxnIM. © 2025, CC BY.

关键词： data curation

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：