检索结果-内蒙古大学图书馆

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Patankar, Rohan Sethi, Harshik Sadhukha, Aditi Banjade, Nishant Mathur, Ashwini Jain University Department of Computer Science and Engineering Specialization in Data Science Bengaluru India Jain University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350333602

Image captioning involves generating a descriptive text that encapsulates the visual information contained in an image. This ppt proposes a deep learning model for image captioning that utilizes a Vision Transformer (ViT) and a GPT-2 network. Specifically, the ViT is employed to extract image features, which are then used by the GPT-2 network to generate captions for the images. To evaluate the effectiveness of the model, experiments are conducted on a Stanford dataset comprising images and their corresponding captions, and demonstrate that our model achieves performance comparable to other state-of-the-art image captioning models. Proposed results suggest that our model has the potential to generate accurate and semantically meaningful captions for images, and could be useful for various applications such as improving the accessibility of visual media. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Secure multimedia communication: advanced asymmetric key authentication with grayscale visual cryptography

引用

Mathematical Biosciences and Engineering 2024年第3期21卷 4762-4778页

作者： Liu, Tao Vairagar, Shubhangi Adagale, Sushadevi Karthick, T. Karunya, Catherine Esther Blesswin, A. John Mary, G. Selva Tianjin Sino-German University of Applied Sciences Tianjin300350 China Department of Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune411018 India Department of Computer Engineering KJEI's Trinity Academy of Engineering Pune411048 India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Directorate of Learning and Development SRM Institute of Science and Technology Kattankulathur603203 India

The secure authentication of user data is crucial in various sectors, including digital banking, medical applications and e-governance, especially for images. Secure communication protects against data tampering and forgery, thereby bolstering the foundation for informed decision-making, whether managing traffic, enhancing public safety, or monitoring environmental conditions. Conventional visual cryptographic protocols offer solutions, particularly for color images, though they grapple with challenges such as high computational demands and reliance on multiple cover images. Additionally, they often require third-party authorization to verify the image integrity. On the other hand, visual cryptography offers a streamlined approach. It divides images into shares, where each pixel represented uniquely, thus allowing visual decryption without complex computations. The optimized multi-tiered authentication protocol (OMTAP), which is integrated with the visual sharing scheme (VSS), takes secure image sharing to the next level. It reduces share count, prioritizes image fidelity and transmission security, and introduces the self-verification of decrypted image integrity through asymmetric key matrix generators, thus eliminating external validation. Rigorous testing has confirmed OMTAP's robustness and broad applicability, thereby ensuring that decrypted images maintain their quality with a peak signal-to-noise ratio (PSNR) of 40 dB and full integrity at the receiver's end. © 2024 American Institute of Mathematical sciences. All rights reserved.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

RagaMoodSync: a deep learning framework for Hindustani Raga recommendations driven by facial emotions

引用

International Journal of Information Technology (Singapore) 2025年 1-14页

作者： Pingle, Yogesh Prabhakar Ragha, Lakshmappa K. Department of Computer Engineering Terna Engineering College University of Mumbai Maharashtra Mumbai India Department of Computer Science & Engineering (Data Science) Vidyavardhini’s College of Engineering & Technology University of Mumbai Maharashtra Mumbai India

RagaMoodSync presents an innovative framework for personalized music therapy through Hindustani Raga recommendations based on facial emotion recognition. Utilizing a Fusion-DenseNet (FusDenseNet) architecture with advanced multi-pooling for emotion detection, the system achieves high precision in identifying user moods. Integrated with a Focus Deep Collaborative Filtering (FDCF) recommendation system, RagaMoodSync delivers tailored raga suggestions that address emotional well-being and stress management. Validated with the FER2013 dataset, the framework demonstrates superior performance over existing approaches. By merging AI-driven emotion recognition with the therapeutic potential of Indian classical music, this system pioneers a novel intersection of technology and mental health care, offering a promising pathway for non-invasive emotional healing solutions. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Focus Deep Collaborative Filtering FusDenseNet RagaMoodSync

来源：评论

学校读者我要写书评

暂无评论

A Sub-element Adaptive Shock Capturing Approach for Discontinuous Galerkin Methods

引用

Communications on Applied Mathematics and Computation 2023年第2期5卷 679-721页

作者： Johannes Markert Gregor Gassner Stefanie Walch Department for Mathematics and Computer Science University of CologneWeyertal 86-9050931 CologneGermany Department for Mathematics and Computer Science Center for Data and Simulation ScienceUniversity of CologneWeyertal 86-9050931 CologneGermany I.Physikalisches Institut Center for Data and Simulation ScienceUniversity of CologneZülpicher Str.7750937 CologneGermany

In this paper,a new strategy for a sub-element-based shock capturing for discontinuous Galerkin(DG)approximations is *** idea is to interpret a DG element as a col-lection of data and construct a hierarchy of low-to-high-order discretizations on this set of data,including a first-order finite volume scheme up to the full-order DG *** dif-ferent DG discretizations are then blended according to sub-element troubled cell indicators,resulting in a final discretization that adaptively blends from low to high order within a single DG *** goal is to retain as much high-order accuracy as possible,even in simula-tions with very strong shocks,as,e.g.,presented in the Sedov *** framework retains the locality of the standard DG scheme and is hence well suited for a combination with adaptive mesh refinement and parallel *** numerical tests demonstrate the sub-element adaptive behavior of the new shock capturing approach and its high accuracy.

关键词： High-order methods Discontinuous Galerkin spectral element method Finite volume method Shock capturing Astrophysics Stellar physics

来源：评论

学校读者我要写书评

暂无评论

A causal multiomics study discriminates the early immune features of Ad5-vectored Ebola vaccine recipients

引用

The Innovation 2024年第3期5卷 77-87页

作者： Zhe Zhang Wenjing Yang Zhengshan Chen Haoang Chi Shipo Wu Wanru Zheng Ruochun Jin Busen Wang Yudong Wang Nan Huo Jinlong Zhang Xiaohong Song Liyang Xu Jun Zhang Lihua Hou Wei Chen Institute of Biotechnology Academy of Military Medical SciencesBeijing 100071China Department of Intelligent Data Science College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China Intelligent Game and Decision Lab Academy of Military ScienceBeijing 100091China

The vaccine-induced innate immune response is essential for the generation of an antibody *** date,how Ad5-vectored vaccines are influenced by preexisting anti-Ad5 antibodies during activation of the early immune response remains ***,we investigated the specific alterations in GP1,2-specific IgG-related elements of the early immune response at the genetic,molecular,and cellular levels on days 0,1,3,and 7 after Ad5-EBOV *** a causal multiomics analysis,distinct early immune responses associated with GP1,2-specific IgG were observed in Ad5-EBOV recipients with a low level of preexisting anti-Ad5 *** study revealed the correlates of the Ad5-EBOV-induced IgG response and provided mechanistic evidence for overcoming preexisting Ad5 immunity during the administration of Ad5-vectored vaccines.

关键词： vaccine immunity alterations

来源：评论

学校读者我要写书评

暂无评论

An in-depth Exploration of LAMOST Unknown Spectra Based on Density Clustering

引用

Research in Astronomy and Astrophysics 2023年第5期23卷 52-65页

作者： Hai-Feng Yang Xiao-Na Yin Jiang-Hui Cai Yu-Qing Yang A-Li Luo Zhong-Rui Bai Li-Chan Zhou Xu-Jun Zhao Ya-Ling Xun Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and TechnologyTaiyuan 030024China School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China School of Computer Science and Technology North University of ChinaTaiyuan 030051China National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China

Large sky Area Multi-Object fiber Spectroscopic Telescope(LAMOST) has completed the observation of nearly 20 million celestial objects,including a class of spectra labeled “Unknown.” Besides low signal-to-noise ratio,these spectra often show some anomalous features that do not work well with current *** this paper,a total of 637,889 “Unknown” spectra from LAMOST DR5 are selected,and an unsupervised-based analytical framework of “Unknown” spectra named SA-Frame(Spectra Analysis-Frame) is provided to explore their origins from different *** SA-Frame is composed of three parts:NAPC-Spec clustering,characterization and origin ***,NAPC-Spec(Nonparametric density clustering algorithm for spectra) characterizes different features in the “unknown” spectrum by adjusting the influence space and divergence distance to minimize the effects of noise and high dimensionality,resulting in 13 ***,characteristic extraction and representation of clustering results are carried out based on spectral lines and continuum,where these 13 types are characterized as regular spectra with low S/Ns,splicing problems,suspected galactic emission signals,contamination from city light and un-gregarious type ***,a preliminary analysis of their origins is made from the characteristics of the observational targets,contamination from the sky,and the working status of the *** results would be valuable for improving the overall data quality of large-scale spectral surveys.

关键词： methods data analysis-surveys-techniques spectroscopic-site testing-methods analytical

来源：评论

学校读者我要写书评

暂无评论

A Study on Object Detection using Faster R-CNN, Retina net, RPN_R_50_FPN, RPN_R_50_C4

A Study on Object Detection using Faster R-CNN, Retina net, ...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Kadiyam, Aswin Tirumala Someswar Padhan, Chinmaya Ranjan Panigrahi, Sibarama National Institute of Technology Computer Science and Engineering Andhra Pradesh India National Institute of Technology Intelligent Data Analytics Laboratory Computer Science and Engineering Rourkela India

ISBN: (纸本)9798350369175

The computer vision concept that involves the detection and characterization of objects in images is known as object detection. This research mainly performs this function using four popular models faster R-CNN, RetinaNet, RPN_R_50_FPN, and RPN_R_50_C4 across multiple datasets namely udacity self-driving car dataset, tomatOD dataset, and chess piece detection dataset. Faster R-CNN is famous for its outstanding accuracy although RetinaNet employs a unique focal loss function to balance between speed and accuracy. The purpose of the models RPN_R_50_FPN and RPN_R_50_C4 is to generate region proposals with high quality using different stages in the ResNet-50 backbone. For normalization techniques, the datasets are preprocessed in this research. Instead of training the models from scratch, transfer learning is used whereby starting with weights that were pre-trained on the COCO dataset and after that fine-tuning the required datasets. Accuracy was quantified by evaluating two efficiency measures which are minimum loss and total training duration. Across the different datasets, various performances were demonstrated by different models. © 2024 IEEE.

关键词： Eye protection

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Captioning Based on Vision Transformer Models

引用

computers, Materials & Continua 2022年第10期73卷 1483-1500页

作者： Samar Elbedwehy T.Medhat Taher Hamza Mohammed F.Alrahmawy Department of Data Science Faculty of Artificial IntelligenceKafrelsheikh UniversityEgypt Department of Electrical Engineering Faculty of EngineeringKafrelsheikh UniversityEgypt Department of Computer Science Faculty of Computer and Information ScienceMansouraEgypt

Image captioning is an emerging field in machine *** refers to the ability to automatically generate a syntactically and semantically meaningful sentence that describes the content of an *** captioning requires a complex machine learning process as it involves two sub models:a vision sub-model for extracting object features and a language sub-model that use the extracted features to generate meaningful ***-based vision transformers models have a great impact in vision field *** this paper,we studied the effect of using the vision transformers on the image captioning process by evaluating the use of four different vision transformer models for the vision sub-models of the image captioning The first vision transformers used is DINO(self-distillation with no labels).The second is PVT(Pyramid Vision Transformer)which is a vision transformer that is not using convolutional *** third is XCIT(cross-Covariance Image Transformer)which changes the operation in self-attention by focusing on feature dimension instead of token *** last one is SWIN(Shifted windows),it is a vision transformer which,unlike the other transformers,uses shifted-window in splitting the *** a deeper evaluation,the four mentioned vision transformers have been tested with their different versions and different configuration,we evaluate the use of DINO model with five different backbones,PVT with two versions:PVT_v1and PVT_v2,one model of XCIT,SWIN *** results show the high effectiveness of using SWIN-transformer within the proposed image captioning model with regard to the other models.

关键词： Image captioning sequence-to-sequence self-distillation transformer convolutional layer

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Improving Solar Efficiency via CNN-LSTM and Cloud-Integrated IoT Prediction 3

Improving Solar Efficiency via CNN-LSTM and Cloud-Integrated...

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Varun, P. Sunitha, T. Nagalingam, Mythili Nithiya, P. Selvakumaran, S. Mohanaprakash, T.A. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India St. Joseph's Institute of Technology OMR Department of Computer Science and Engineering Chennai600119 India Rajalakshmi Institue of Technology Department of Artificial Intelligence and Data Science Chennai India Department of Artificial Intelligence and Data Science Velammal Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institue of Technology Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Photovoltaic panel used in solar power generation is an environmentally beneficial and sustainable energy source that has been used to transform sunlight into electrical power. Arranged in large solar facilities, these panels are connected to a central inverter, which converts Direct Current (DC) to alternating current (AC) electricity with a small amount of energy loss. Clean surfaces, unhindered light exposure, and high solar irradiance are all necessary for optimal panel performance. It's critical to assess the inverter's efficiency by comparing its AC to DC power. Large-scale installations with sensor-equipped panels and inverters track performance to help with maintenance and forecasting of power generation. The Internet of Things (IoT) facilitates data accessibility and remote monitoring, which helps choose the best location for solar power generation. Smart system continuous monitoring expedites site inspections, which supports urban smart grid integration. In this research study, a hybrid machine learning model is presented by combining the attention processes, long short-term memory (LSTM) networks, and clustering approaches. This model is separated into different phases for forecasting, training, and cloud data clustering, finds pertinent historical data, builds a hybrid machine learning model, and chooses the best training model. In comparison to conventional approaches, this method significantly improves prediction accuracy, which is important for integrating photovoltaic systems into smart grids, particularly in smart cities. © 2024 IEEE.

关键词： Solar power generation

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：