检索结果-内蒙古大学图书馆

9th International Conference on Applied System Innovation, ICASI 2023

作者： Chang, Ya-Fen Tsai, Chung-Yi Tai, Wei-Liang National Taichung University of Science and Technology Department of Computer Science and Information Engineering Taichung Taiwan National Taichung University of Science and Technology Bachelor Degree Program of Artificial Intelligence Taichung Taiwan

ISBN: (纸本)9798350398380

Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.'s protocol are shown. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Gender Detection from Hand Palm Images: A PySpark-Driven Approach with VGG19 Feature Extraction and MLP Classification 6

Gender Detection from Hand Palm Images: A PySpark-Driven App...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Henedak, Mayar Tarek Ezzeldin, Ganna Waleed Mohamed, Nada Adel Hamed, Malak Essam ElMasarawi, Sarah Mahmoud Fekry, Shahd Mohamed Yasser, Tawfik Fouad, Khaled M. Fathi, Mostafa Abdelbaky, Ibrahim BMD Program ITCS Nile University Giza Egypt AlProgram ITCS Nile University Giza Egypt Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer Science and Engineering New Mansoura University Egypt Computer Science Program ITCS Nile University Giza Egypt Artificial Intelligence Department Faculty of Computers and Artificial Intelligence Benha University Banha13518 Egypt

ISBN: (纸本)9798350373875

This paper presents a comprehensive methodology for gender detection using hand palm images, leveraging image processing techniques and PySpark for scalable and efficient processing. The approach encompasses a meticulous image preprocessing pipeline, incorporating essential stages like grayscale conversion, the application ofthe Difference of Gaussians (DoG) filter, and adaptive histogram equalization. This approach not only refmes image features but also ensures scalability, accommodating large datasets seamlessly. After preprocessing of hand images, the VGG19 model is employed as a powerful feature extractor, utilizing its pre-trained convolutional layers to capture high-level abstract features from hand palm images. The fmal step was to train and fit the tabular data and extracted features on the Multilayer Perceptron (MLP) model, which is a feedforward neural network for classification tasks in PySpark. The MLP model, with its ability to learn complex patterns, proves effective in accurately predicting gender categories based on the extracted features. Finally, the model results were 94% accuracy for training and 87% testing which indicates that the model is generalizing well to unseen data. Also, another evaluation metrics were used like Precision 0.87, Recall 0.87, Fl Score 0.87 and AUC 0.92. © 2024 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Performance Chip Design With Parallel Architecture for Magnetic Field Imaging System

引用

IEEE Transactions on Instrumentation and Measurement 2024年 73卷 1-13页

作者： Lin, Ming-Yi Hsieh, Sheng-Hsien Chen, Ching-Han Lin, Chun-Hung Yuan Ze University Department of Computer Science and Engineering Taoyuan320315 Taiwan National Pingtung University of Science and Technology Program of Artificial Intelligence and Mechatronics Pingtung912301 Taiwan National Central University Department of Computer Science and Information Engineering Taoyuan32001 Taiwan International Games System Company Ltd. New Taipei City248 Taiwan

To address the limitations of typical coil detection systems and enhance the performance of traditional magnetic field imaging (MFI) systems, we propose a MFI system that uses a 4×4 array of anisotropic magnetoresistance (AMR) sensors. The core controller of the proposed system was designed using a pipelined parallelization algorithm and implemented on a high-speed field-programmable gate array (FPGA) in a fully hardware-based architecture. The designed MFI system can achieve parallel acquisition of magnetic field components from the 16-channel AMR sensor array, parallel data processing, parallel data transmission, and parallel computations in a single cycle of only 4 ms. Compared with typical detection systems, the proposed solution not only exhibits superior performance but can also provide dynamic visual representations of sensed information. © 1963-2012 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Investigating the Relation between Code Comments and Issue Resolution Time in Java Repositories 11

Investigating the Relation between Code Comments and Issue R...

引用

11th IEEE International Conference on Intelligent Computing and Information Systems, ICICIS 2023

作者： Hamza, Ahmed Ashraf El-Ramly, Mohammad Elkady, Manar Cairo University M.Sc. in Software Engineering Program Faculty of Computers and Artificial Intelligence Cairo Egypt Cairo University Faculty of Computers and Artificial Intelligence Department of Computer Sciences Cairo Egypt

ISBN: (纸本)9798350322101

Source code comments play a critical role in software development by facilitating issue resolution and reducing maintenance time and cost. However, the impact of code comments, particularly those aiding program comprehension, on expediting issue resolution remains insufficiently explored. This study investigates the impact of code comments on issue resolution time for issues related to pulling requests involving code maintenance. To this end, ten of the most popular Java repositories on GitHub were selected, and closed pull request-related issues were identified using a specific criterion. Comments were then extracted from classes modified by the pull requests, and a trained BERT model was utilized to classify them according to their usefulness. The percentage of comments relative to code size, the percentage of useful comments relative to all comments, and the average issue resolution time were computed and examined for correlations. The results indicate a negative correlation (-0.68) between the percentage of code comments in modified classes and the average issue resolution time. A stronger negative correlation (-0.73) was found between the percentage of useful code comments to all comments in modified classes and the average issue resolution time per class. These findings demonstrate that code with more comments, particularly useful ones, leads to faster issue resolution. This serves as a basis for further research into the impact of various fine-grained comment types on issue resolution time in different programming languages. Also, it can assist developers in writing more effective comments that accelerate bug-fixing and reduce software maintenance efforts. © 2023 IEEE.

关键词： computer software maintenance

来源：评论

学校读者我要写书评

暂无评论

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose E...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Jang, Hojun Kim, Young Min Seoul National University Dept. of Electrical and Computer Engineering Korea Republic of Interdisciplinary Program in Artificial Intelligence and Inmc Seoul National University Korea Republic of

ISBN: (纸本)9798331510831

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. © 2025 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Precision: Revolutionizing Skin Cancer Detection with Advanced Machine Learning 6

AI-Powered Precision: Revolutionizing Skin Cancer Detection ...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Abd-Elaziz, Mariam M. Elshafie, Basma M. Abdullah, Hagar Gerges, Karen Y. Ghanem, Ingy A. Fouad, Khaled M. El-Ghamry, Amir Moawad, Ibrahim F. El-Metwally, Sara New Mansoura University Faculty of Computer Science and Engineering Dakahlia Egypt Mansoura University New Mansoura University Faculty of Engineering Computer and Communication Program Faculty of Computer Science and Engineering Egypt Benha University Information Systems Faculty of Computers and Artificial Intelligence Egypt Mansoura University New Mansoura University Faculty of Computer and Information Sciences Faculty of Computer Science and Engineering Egypt School of Engineering and Computer Science University of Hertfordshire Gaf Egypt Ain Shams University Faculty of Computer and Information Sciences Cairo Egypt College of Computer Science and Engineering Taibah University Department of Artificial Intelligence Medina42353 Saudi Arabia

ISBN: (纸本)9798350378511

Skin cancer's increasing incidence rates necessitate advanced diagnostic tools. This research uses MobileNet architecture to develop an enhanced system for skin cancer detection. MobileNet's efficient CNN architecture, combined with Keras for model lifecycle management and TensorFlow for real-time inference, forms the foundation of this study. Using 10,015 dermatoscopic pictures from seven different classifications of skin cancer in the HAM10000 dataset, the methodology includes several key stages: image preprocessing to correct illumination and adjust resolution, data augmentation to balance the dataset, and model training using Transfer Learning. The MobileNet model was trained over 50 epochs with a comprehensive architecture incorporating multiple specialized layers. By combining large-scale data analysis and adaptive learning, this methodology demonstrates The revolutionary possibilities of AI and ML in improving skin cancer diagnostics and public health outcomes. Keywords Skin Cancer Detection, Dermatoscopic Images, Machine Learning, Deep Learning © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

From Pictures to Prompts: Analyzing and Reconstructing AI-Generated Images with BLIP2 and CLIP 24

From Pictures to Prompts: Analyzing and Reconstructing AI-Ge...

引用

8th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2024

作者： Kuo, Yi-Hsuan Chang, Hsien-Tsung Department of Computer Science and Information Engineering Chang Gung University Taoyuan China Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan China

ISBN: (纸本)9798400717383

This study presents a novel approach to analyzing and reconstructing AI-generated images using BLIP2 and CLIP models, focusing on a dataset of 268,000 Midjourney-generated images and prompts. We introduce a multi-level feature classification system encompassing 11 categories and 1,100 features, and employ BLIP2 for descriptive text generation and CLIP for feature similarity analysis. Our methodology involves image pre-processing, custom feature extraction, and image reconstruction under various conditions. The effectiveness of our approach is demonstrated through similarity scores between original and reconstructed images, ranging from 68.15 to 71.25 across different feature extraction conditions. This research contributes to the fields of natural language processing and information retrieval by offering insights into AI-generated image analysis, proposing new methods for feature extraction and reconstruction, and suggesting avenues for improving image generation models and multi-modal understanding. © 2024 Copyright held by the owner/author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

CELL SEGMENTATION IN FLUORESCENCE MICROSCOPY IMAGES

CELL SEGMENTATION IN FLUORESCENCE MICROSCOPY IMAGES

引用

2024 IET International Conference on engineering Technologies and Applications, ICETA 2024

作者： Yin, Shao-Yun Hsu, Wei-Wen Hsia, Chih-Hsien Master Program of Artificial Intelligence National Ilan University Ilan Taiwan Dept. of Computer Science and Information Engineering National Taitung University Taitung Taiwan Dept. of Computer Science and Information Engineering National Ilan University Ilan Taiwan

ISBN: (纸本)9781837242672

For microscopic cells images, cells’ morphologies are widely varied among different imaging modalities and staining methods. For fluorescence microscopy images, Poisson noises present in images due to the lightening, causing photobleaching, which makes it challenging in analysis with the deep learning models. Traditionally, median filtering can be applied to the original image for denoising, however, it also results in a blurry image, which is harmful to segmentation. In this study, the Haar Wavelet Transform is used to alleviate the photobleaching problem for cell segmentation, integrated to the framework without interfering with feature extraction by the backbone model. For our experiments, instance segmentation for fluorescence-stained cells was performed based on U-Net architecture with the method of gradient flow tracking proposed by Cellpose. And the Haar wavelet downsampling is embedded in the skip connections to verify if it can improve the segmentation performance for fluorescence images. The experimental results show that the approach of Haar wavelet downsampling embedded in the skip connections achieve superior performance among the other settings. Compared with the performance of the baseline model, the performance of the proposed model reached 0.732 in F1-score, which surpassed the one of baseline model (0.6341) by almost 0.1. © The Institution of engineering & Technology 2024.

关键词： Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization 38

Unsupervised Homography Estimation on Multimodal Image Pair ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Song, Sanghyeob Lew, Jaihyun Jang, Hyemi Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Samsung Electro-Mechanics Korea Republic of

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the difficulty of collecting ground-truth data. In response, unsupervised learning approaches have emerged. Most early methods, though, assume that the given image pairs are from the same camera or have minor lighting differences. Consequently, while these methods perform effectively under such conditions, they generally fail when input image pairs come from different domains, referred to as multimodal image pairs. To address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs. Our method employs a two-phase alternating optimization framework, similar to Expectation-Maximization (EM), where one phase reduces the geometry gap and the other addresses the modality gap. To handle these gaps, we use Barlow Twins loss for the modality gap and propose an extended version, Geometry Barlow Twins, for the geometry gap. As a result, we demonstrate that our method, AltO, can be trained on multimodal datasets without any ground-truth data. It not only outperforms other unsupervised methods but is also compatible with various architectures of homography estimators. The source code can be found at: https://***/songsang7/AltO. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：