检索结果-内蒙古大学图书馆

Next-Gen Dermatology: Revolutionizing Dermatological Diagnostics with AI and Emergency Care Solutions 3

Next-Gen Dermatology: Revolutionizing Dermatological Diagnos...

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Yashas, D. Kashyap, M. Shivani Charan, P.R. Hemanth Kumar, G.P. Abhishek, B.K. Deekshith, C. New Horizon College of Engineering Dept of Artificial Intelligence and Machine Learning Bengaluru India New Horizon College of Engineering Dept of Information Science and Engineering Bengaluru India Bnm Institute of Technology Dept of Artificial Intelligence and Machine Learning Bengaluru India Siddaganga Institute of Technology Dept of Artificial Intelligence and Data Science Tumkur India Vidyavardhaka College of Engineering Dept of Computer Science and Engineering Mysore India

ISBN: (纸本)9798331515911

Skin health conditions should be diagnosed and treated on time so as to prevent complications and promote better health results. This paper presents an AI-based system that makes use of Convolutional Neural Networks with the InceptionV3 Architecture for predicting skin diseases at higher levels. The model, which is based on the large DermaNet dataset, classifies skin disorders fast and effectively. The system is coupled with a simple Telegram based application for the users to get a complete solution. A user can upload a photo of the affected skin area and get a diagnosis within seconds, an explanation of the disease and how severe it is in percentage. The bot also has a location and contact sharing feature that assists users in finding nearby doctors and clinics that can provide further assistance. It further provides on the spot appropriate cures for the particular condition diagnosed. Moreover, this makes it possible for the customer to fill the healthcare void in particular the neglected ones by making it easy for them to access real time high quality services. By equipping users with relevant information and appropriate actions required at the right time, this project has showcased how AI has the ability to transform the dermatological field. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Causalseg: investigating causality modeling for semi-supervised video object segmentation

引用

Multimedia Systems 2025年第3期31卷 1-16页

作者： Zhang, Zhengjin Li, Nannan Wang, Wenmin Guo, Huiwen School of Computer Science and Engineering Macau University of Science and Technology Taipa999078 China School of Computer and Artificial Intelligence Chaohu University Bantang Road Anhui Hefei238024 China Shenzhen Bochuang Robot Technology Xixiang Guangdong Shenzhen518172 China

In Semi-Supervised Video Object Segmentation (SVOS), existing methods are often hindered by the issue of spurious association due to the lack of adequate supervision information. This issue negatively impacts the segmentation performance. To address this, we introduce a novel approach that leverages causal intervention to enhance SVOS performance. Causal intervention is particularly effective in mitigating spurious associations, thereby improving segmentation performance. Our proposed causal module is a versatile component that can be seamlessly integrated into matching-based SVOS to enhance segmentation accuracy. Our approach involves three key steps. Firstly, we introduce the Causal CAM method to identify and eliminate spurious association locations within the video frame. Secondly, we adapt the IRNet to effectively generate class-specific instance map information during training. Lastly, we incorporate the AFB-URR, STCN and XMem models with our causal intervention method. Experimental results validate the effectiveness of our approach in improving object segmentation accuracy. On the DAVIS2017 dataset, our method achieved an overall J & F Mean scores of 76.3%, 85.3% and 87.5% respectively. Compared to the three benchmark methods, our approach demonstrated improvements of 1.7%, 3.4% and 1.3% respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SightAssist: A Multi-facility Machine Learning Approach for Empowering the Visually Impaired 2nd

SightAssist: A Multi-facility Machine Learning Approach for...

引用

2nd International Conference on Data science and Network Engineering, ICDSNE 2024

作者： Bandopadhyay, Saikat Dutta, Jhalak Das, Smita Datta, Soumyajit Ghosh, Debaditya Dey, Rohit Kumar Nandigrami, Jeet Department of Artificial Intelligence and Machine Learning Netaji Subhash Engineering College Kolkata India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Computer Science and Engineering National Institute of Technology Agartala India Department of Artificial Intelligence and Machine Learning Heritage Institute of Technology Kolkata India

ISBN: (纸本)9789819783359

Blindness or visual impairment ranks among the top ten disabilities affecting both men and women, impacting over 35 million individuals of all ages in India. Access to visual information is crucial for enhancing the independence and safety of blind and visually impaired individuals. There exists a compelling imperative to develop assistive technologies that can significantly improve their quality of life. This paper presents SightAssist, a multilingual software solution designed to address the challenges faced by the visually impaired community in India. SightAssist utilizes a camera-based approach to serve as a digital prosthetic eye and virtual assistant, capable of currency detection, facial recognition, and providing various functionalities to assist with daily activities. Initially, a custom-labeled dataset has been prepared using a pre-trained YOLO model. Gradually, dataset pre-processing, normalization, and semantic segmentation are employed to optimize model performance. Additionally, voice-based accessibility features have been integrated using the Web Speech API, enabling users to interact with the application through voice commands. The experimental results show the successful development of SightAssist and its potential to significantly improve the lives of visually impaired people. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale wavelet network for high-quality sparse photoacoustic imaging 2

Multi-Scale wavelet network for high-quality sparse photoaco...

引用

2nd International Academic Conference on Optics and Photonics, IACOP 2024

作者： Zhao, Xudong Hu, Shuguo Zhang, Zhiwei Wang, Mengqiu Dai, Ruoyan Lei, Lixin Wang, Zhenghui Niu, Chaojun Guo, Qianjin Academy of Artificial Intelligence Beijing Institute of Petrochemical Technology Beijing102617 China College of Computer Science and Technology Inner Mongolia University Hohhot010021 China

ISBN: (数字)9781510688827

ISBN: (纸本)9781510688810

This study introduces the Wavelet-Based Sparse Photoacoustic Reconstruction Network (WSPARN), designed to enhance the reconstruction quality of photoacoustic images under sparse sampling conditions. WSPARN utilizes the discrete wavelet transform (DWT) for multi-scale feature extraction, replacing traditional pooling layers with DWT-based downsampling. The network applies channel attention to low-frequency components and spatial attention to high-frequency components to enhance image quality. A dynamic loss function that combines mean squared error (MSE), edge, and frequency domain losses supports optimal model convergence. Validation on simulated vascular imaging data and real mouse photoacoustic tomography scans demonstrated that WSPARN not only significantly reduces artifacts and better preserves structural details compared to recent models from the past few years, but also offers computational advantages. A dedicated section on Complexity Comparison and Analysis highlights these computational benefits, showing WSPARN’s lower computational demand compared to other advanced models. Finally, an ablation study confirmed the benefits of wavelet-based downsampling in improving reconstruction accuracy, substantiating the model’s effectiveness in practical applications. © 2025 SPIE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Design for Privacy Preserved Image Representation in a Cloud Environment 12th

Hybrid Design for Privacy Preserved Image Representation in ...

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Vijay, K. Sorna Shanthi, D. Jaeyalakshmi, M. Vignesh, P. Yuvaraja, M. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India

ISBN: (纸本)9789819789450

The digital era has made seamless sharing and keeping of media such as images on cloud platforms an integral part of our lives. Still, there is a big issue about user privacy and data security in these repositories. We have thus created a very strong system that is able to do image encryption and decryption so as to protect the privacy of users while at the same time making their pictures accessible. Our system uses hybrid encryption where we try to prevent even cloud service providers from accessing the original files hence ensuring that only the owner who has been authenticated through password based authentication can decrypt or access them. In this way, it allows maintaining high privacy standards without sacrificing user convenience. It starts with preparing photos for encryption so that they are kept safe during transmission and storage. When needed by a user, images are decrypted by our system and become available only to authorized users. Consequently, users can comfortably leave their private photo albums on cloud storage systems knowing too well that their friends cannot access them thereby increasing trust in using cloud services for storing sensitive information. The aim of this work is to increase user privacy and data security in cloud repositories through employing this encryption technique. The users are guaranteed that their private details are not exposed to others enabling them to use cloud storage efficiently without interfering with their privacy at all. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Accuracy Assessment and Calibration of a 6-DOF Robotic Arm Through Simulation Data Analysis 6th

Accuracy Assessment and Calibration of a 6-DOF Robotic Arm T...

引用

6th International Conference on Computational intelligence in Pattern Recognition, CIPR 2024

作者： Kailash, M. Jones, Aida Babu, K. Dinesh Praveen, S. Department of Artificial Intelligence and Data Science KCG College of Technology Tamil Nadu Chennai India

ISBN: (纸本)9789819780891

This study focuses on refining the real-time positional accuracy of a 6-degree-of-freedom (6-DOF) robotic arm’s end effector by comparing the actual X, Y, and Z axis positions with those calculated from joint angles using DH parameters. Through the application of linear regression analysis, variations between these datasets are identified and quantified. The derived variations are then used to adjust the DH parameter-based calculations, resulting in significantly improved accuracy for the robotic arm’s end-effector positioning. This approach offers a systematic method for enhancing the precision of calculated positional data, thereby contributing to the advancement of robotic arm operations across diverse fields. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Multi-level Attention-enhanced Learning for Fine-Grained Visual Classification 24

Multi-level Attention-enhanced Learning for Fine-Grained Vis...

引用

8th International Conference on computer science and artificial intelligence, CSAI 2024

作者： Ding, Kaifeng Yang, Caolin Yang, Chengzhuan Zheng, Zhonglong School of Computer Science and Technology School of Artificial Intelligence Zhejiang Normal University ZheJiang Jinhua China

ISBN: (纸本)9798400718182

Due to significant intra-class variations and subtle inter-class differences, fine-grained images often pose challenges. In this paper, we propose a multi-level attention-enhanced network framework to address this issue. First, we employ convolutional features to crop the original images to focus on the main part and mitigate the interference of backgrounds on classification. Second, we design a scale-adaptive local discriminative region generation module based on the main part’s images, effectively selecting locally detailed and rich image patches. It is worth noting that our proposed method only utilizes image-level labels. Finally, we extensively tested our method on three benchmark datasets, including the CUB-200-2011, Stanford Cars, and FGVC Aircraft. The experimental results demonstrate that our method achieves comparable or better classification performance than previous state-of-the-art fine-grained visual classification methods. © 2024 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Ac...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Chen, Zhaoyu Li, Xing Huang, Qian Geng, Qiang Yang, Tianjin Han, Shihao College of Information Science and Technology & Artificial Intelligence Nanjing Forestry University China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350368741

Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method. © 2025 IEEE.

关键词： 3D action recognition D-Hyperpoint KAN-HyperpointNet point cloud sequence

来源：评论

学校读者我要写书评

暂无评论

Healthcare Data Protection and Biometric Access on Cloud Platforms 6

Healthcare Data Protection and Biometric Access on Cloud Pla...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Gayathri, S. Devaraj, S. Muthupandi, B. Vishwaraj, S. Department of Artificial Intelligence and Data Science K S Rangasamy College of Technology Tiruchengode India

ISBN: (纸本)9798331522667

This paper discusses about various fingerprint recognition methods, each founded on different principles, in search of a robust and efficient technique. The research concentrates on designing an easy yet efficient alternative for fingerprint recognition. The technique is divided into two main stages: the first is the acquisition of human fingerprint samples, and the second is the development and implementation of an advanced fingerprint recognition system. One of the features of the method is feature extraction using multiple iterations of the two-dimensional discrete cosine transform (DCT) to extract robust features. This method combines thumbprints from both hands for better recognition. The experiments show that the proposed technique is capable of yielding a good recognition accuracy. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Hybrid AI-Electronic Systems for Real-Time Edge Processing in IoT Networks 3

Hybrid AI-Electronic Systems for Real-Time Edge Processing i...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Sweety Prasanna Kiruba, G. Esakki Madura, E. Kumar, Bura Vijay Kavitha, M. Reddy, T. Srinivas Athiraja, A. Bannari Amman Institute of Technology Department of Computer Technology Tamil Nadu Sathyamangalam India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Sathyamangalam India School of Computer Science and Artificial Intelligence Sr University Warangal India Kathir College of Engineering Department of Artificial Intelligence and Data Science Neelambur Coimbatore India Malla Reddy Engineering College Department of Ece Main Campus Maisammaguda Telangana Medchal India Hyderabad India

ISBN: (纸本)9798331515911

Real-time data processing is facing many issues as a result of the Internet of Things' rapid expansion, especially at the network's edge where latency, bandwidth, and compute resources are limited. The creation of hybrid AI-electronic systems for real-time edge processing is investigated as a solution to these problems. To improve the effectiveness and precision of data processing in Internet of Things contexts, the research combines machine learning algorithms with sophisticated electronic circuits. The techniques include creating a brand-new hybrid framework that blends edge computing and AI models and focuses for low latency and low power consumption. When compared to conventional edge processing systems, extensive simulations and real-world research show a 25% reduction in processing latency and a 15% gain in data categorization accuracy. According to the findings, the suggested hybrid AI-electronic system can successfully handle the requirements of contemporary IoT networks and offer a scalable real-time edge processing solution. This strategy has potential for use in smart city applications, industrial automation, and other fields in the future. © 2025 IEEE.

关键词： Adversarial machine learning

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：