检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Shirisha, N. Shilpa, K. Meghana, C.H. Rahman, Mohammed Abdul MLR Institute of Technology Dept. of Computer Science and Engineering Hyderabad India MLR Institute of Technology Dept. of Computer Science and Engineering Nalgonda India

ISBN: (纸本)9798331523893

Knee osteoarthritis (KOA) is a prevalent joint disorder diagnosed using imaging modalities like MRI, CT scans, and X-rays, with X-rays being the most cost-effective. Early detection is crucial for effective management. This study presents an automated deep learning approach to detect and classify KOA severity based on the Kellgren-Lawrence (KL) grading system using single posteroanterior standing knee X-ray images. Utilizing the Osteoarthritis Initiative dataset, we employed transfer learning to fine-tune DenseNet-201, enhancing model performance. Additionally, knowledge distillation was applied to reduce computational complexity while maintaining accuracy. Our model achieved over 95% accuracy on both testing and cross-validation datasets, outperforming existing methods. This approach offers a reliable tool for early KOA diagnosis and grading, potentially aiding clinical decision-making © 2025 IEEE.

关键词： Diagnostic radiography

来源：评论

学校读者我要写书评

暂无评论

Recognition of Fingerprint Images using CNN for Cybercrime Detection System 2

Recognition of Fingerprint Images using CNN for Cybercrime D...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Kavitha, T. Patil, Bhimaraya Saraswathi, S. Rajarajeswari, S. Patil, Anita New Horizon College of engineering Dept. of Computer Engineering Bangalore India Sri Sivasubramaniya Nadar College of Engineering Dept. of Computer Science Engineering Chennai India Vellore Institute of Technology School of computer science and engineering Vellore India City Engineering College Dept. of Information Science Bengaluru India

ISBN: (纸本)9798350372892

Fingerprint identification plays a crucial role in crime detection, but manual analysis is time-consuming and error-prone. This research aims to develop an automated system for accurate and efficient fingerprint matching using machine learning. The proposed approach involves image acquisition, preprocessing, feature extraction, and classification. Fingerprint images are enhanced, binarized, and segmented. Minutiae (ridge endings and bifurcations) are extracted as features. A convolutional neural network (CNN) is trained on a dataset of fingerprint images for classification. By comparing algorithms, Random Forest achieved over 8 1 % accuracy, outperforming Decision Trees (nearly 75% accuracy). The trained CNN model can accurately match fingerprints from crime scenes with potential suspects, providing reliable evidence. The developed system offers law enforcement agencies an automated and accurate fingerprint identification tool, improving crime-solving efficiency and reducing manual effort. The proposed approach showcases the potential of machine learning in forensic applications. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Call Translator with Voice Cloning Using Transformers 9

Call Translator with Voice Cloning Using Transformers

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Khan, Nawaz Fateen Hemanth, Nandan Goyal, Navyae Pranav, K.R. Agarwal, Pooja Pes University Computer Science Engineering Dept. Bangalore India

ISBN: (纸本)9798350394474

Voice Cloning employs technology and algorithms to create an artificial or synthetic reproduction of a person's voice. To understand and mimic the distinct vocal qualities of the target speaker, including tone, pitch, cadence, and pronunciation, a machine learning model must be trained on audio samples of the speaker. This project presents itself as a revolutionary approach to the enduring problem of successful cross-lingual interactions, the paper's novel approach to speech-to-speech machine translation that incorporates voice cloning. This method allows us to synthesize speech in the target language while maintaining the original speaker's vocal characteristics. The model algorithms such as Whisper AI(WER 5% for transcription, No-Language-Left-Behind-200(44% more accurate than other models) for translation, Tacotron for speech synthesis and multiple transformers for voice cloning will be incorporated. The Voice Cloning model operates effectively on unseen voices, transcending the limitations of voice cloning will be incorporated. The voice cloning model operates effectively on unseen voices, transcending the limitations of relying solely on pre-trained models. The model successfully clones users' voices in a different language with an approximate latency of 10 seconds. © 2024 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Sentient Sound waves: Elevating Emotional Communication with AI-Generated Speech Technology 5

Sentient Sound waves: Elevating Emotional Communication with...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Roshan, Rahul G. Roshan, Rohit Sohan, M.H. Raj, S.M. Sutharsan Prasad, V.R. Badri Dept. of Computer Science and Engineering PES University Bangalore India

ISBN: (纸本)9798350361155

This research-based project is about a new way to put feelings into computer-generated speech. It has two stages: text emotion detection and emotional speech synthesis. In the former part, labeled text data is used to build models to spot the emotions. This model learns to change pitch, volume, and rhythm based on the given emotion. During the latter phase, the text is changed into neutral speech using text-to-speech (TTS) methods. The model is used for practice to find the emotion in the text, tagging the text with that emotion. Also, a deep-learning model known as a tacotron is employed to make an emotional-sounding speech. The model perfectly uses machine learning strategies to blend feelings into speech. This opens up possibilities for turning plain text into speech with feelings of varied emotions. The proposed system makes a novice and important contribution to natural language processing for emotion identification and deep learning for emotional speech synthesis. © 2024 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Investigation of VGG 16 Transfer Learning and CNN Integrated Brain Tumour Detection

Investigation of VGG 16 Transfer Learning and CNN Integrated...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Dept. of Electronics and Engineering Dehradun India

ISBN: (纸本)9798350388534

This study had conducted an intensive exploration of the possibilities of VGG-16 and VGG-19 Convolutional Neural Network models for picture categorisation. Using a thorough method comprising substantial training and severe testing, we may observe both steady loss decrease and significant model accuracy improvements. It is assumed that the models may appropriately keep track of subtle variations in data to which they are adversarial while identifying regular patterns they may generalize. The VGG models' architecture is quite sophisticated, but as seen above, they give strong classification accuracy, with performance in nearly ideal 99 percent in many trials. This integration proves that extremely advanced deep learning instruments are competent to handle and complete even very sophisticated picture recognition assignments. Additionally, our experiments identify a few essential aspects of model adjustment and tuning identifying important techniques considerably enhancing CNN outcomes in application scenarios. This study is pioneering for the automatic picture identification discipline since it provided a strong understanding of the generality and model quicker than many real-world models. Additionally, it exhibits that the CNN structures enhance artificial intelligence's power to recognize visual input and could improve many sectors like the surveillance and health systems. The findings defined here may now open the door to more progress in deep learning and picture process analyses while reiterated the importance of CNN in modern technology. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling Insights: Vision-Based Data Mining Analysis of Webpages in Transition from HTML 3 to HTML 5 5

Unveiling Insights: Vision-Based Data Mining Analysis of Web...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Chaudhary, Meena Pooja Chandwani, Gunjan Manav Rachna University Dept. of Computer Science and Technology Faridabad India Galgotias University Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350383522

Deep web material is accessed with web database requests, and returned information is packaged into dynamically generated web pages known as deep Web pages. Due to their intricate structure, it is tedious task to retrieve organized data from deep web pages. A great many approaches to address this problem are yet to be proposed, but all of them have inherent drawbacks because they are based on the website and the programming language. The contents of Sites are always shown for users to search daily, like the common two-dimensional media. This motivates us to search for an alternative way to extract deep Web information, by using some interesting popular visual features from deep Webpages, to address the limitations of past works. A novel blog vision approach is proposed in this paper to overcome these issues. This technique uses visual features in deep web pages specifically to conduct deep web data extraction. This paper also recommends a new appraisal measure to capture the required human activity to make maximum mining. The proposed methodology is highly efficient in the deep network data extraction, according to our studies with a large set of web-based data bases. © 2024 IEEE.

关键词： Data mining HTML 3 HTML5 Vision based technique Web Content Mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced Level Brain Tumor Identification Using CNN, VGG16 and ResNet Models 2

Enhanced Level Brain Tumor Identification Using CNN, VGG16 a...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Sambandam, Rakoth Kandan Jyoshna, Mallela Christ University Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350383652

The comprehension of brain growths is significantly improved through the identification and categorization of these disorders. Still, their discovery is relatively grueling due to their variability in terms of position, shape, and size. Fortunately, deep literacy has revolutionized the field and significantly improved recognition, prediction, and opinion in various healthcare areas, including brain excrescences. The main goal of this study is to thoroughly review exploration that utilizes CNN, VGG16, and RESNET infrastructures to classify brain excrescences using MRI images. The performance of these models varied significantly, with CNN, VGG16, and RESNET achieving an emotional delicacy of 99.6. Additionally, ResNet and VGG16 achieved rigor of 92.4 and 89.7 independently. Likewise, the visualization of the decision-making processes of these models has provided valuable insight into the features they prioritize. By incorporating these models into their practice, healthcare professionals have the opportunity to enhance their individual capabilities, eventually leading to improved patient outcomes. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ENHANCING E-HEALTH CYBERSECURITY AND RESILIENCE: SHIFTING FROM MONOLITHIC TO MICROSERVICES ARCHITECTURE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2025年第1期87卷 21-34页

作者： Contașel, Cristian Rughiniș, Răzvan Trancă, Dumitru Cristian Țurcanu, Dinu Dept. of Computer Science and Engineering National University of Science and Technology POLITEHNICA Bucharest Romania Dep. of Software Engineering and Automatics Technical University of Moldova Chișinău Moldova

This study provides an innovative architectural model for e-Health systems that aims to improve cyber resilience while maintaining high availability under fluctuating traffic loads. We examined typical cybersecurity incidents in the field of e-Health, their correlations with architectural defects, and frequent design patterns in currently operational systems. A testing approach based on our research finds those weaknesses and proposes viable fixes. In this paper, a comprehensive support strategy for transitioning from conventional monolithic architectures to microservices is presented. This change makes use of cloud computing's vertical and horizontal scalability to maximize resource utilization while ensuring system reliability. We also discuss deployment ideas for the new microservices, focusing on operational resilience and cybersecurity in e-Health environments. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Masked Ciphertext Comparison without Masking Conversions using Register Rotation and Chinese Remainder Theorem 15

Masked Ciphertext Comparison without Masking Conversions usi...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Kim, Geumtae Seo, Eunyoung Lee, Yongwoo No, Jong-Seon Seoul National University Dept. Electrical and Computer Engineering Seoul Korea Republic of Dept. Electrical Engineering and Computer Science Daegu Korea Republic of Inha University Dept. Electrical and Computer Engineering Incheon Korea Republic of

ISBN: (纸本)9798350364637

In this paper, we propose a novel method for masked comparison using register rotation technique without masking conversions. In key encapsulation mechanisms (KEMs), ciphertext comparison is essential to ensure the security, but it is one of the most computationally expensive operations in masking environment. Previous works on masked ciphertext comparison have mainly focused on masking conversion and its post-processing. However, the proposed method introduces another register-based approach, which eliminates the need for time-consuming masking conversion and solely relies on register rotation using Chinese remainder theorem (CRT). © 2024 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Heads-Up Multitasker: Simulating Atention Switching On Optical Head-Mounted Displays

Heads-Up Multitasker: Simulating Atention Switching On Optic...

引用

2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024

作者： Bai, Yunpeng Ikkala, Aleksi Oulasvirta, Antti Zhao, Shengdong Wang, Lucia J. Yang, Pengzhi Xu, Peisen Dept. of Computer Science National University of Singapore Singapore Dept. of Computer Science Aalto University Espoo Finland Dept. of Information and Communications Engineering Aalto University Helsinki Finland School of Creative Media Dept. of Computer Science City University of Hong Kong Hong Kong Hong Kong Dept. of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge United States Dept. of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Dept. of Computer Science IPAL National University of Singapore Singapore

ISBN: (纸本)9798400703300

Optical Head-Mounted Displays (OHMDs) allow users to read digital content while walking. A better understanding of how users allocate attention between these two tasks is crucial for improving OHMD interfaces. This paper introduces a computational model for simulating users' attention switches between reading and walking. We model users' decision to deploy visual attention as a hierarchical reinforcement learning problem, wherein a supervisory controller optimizes attention allocation while considering both reading activity and walking safety. Our model simulates the control of eye movements and locomotion as an adaptation to the given task priority, design of digital content, and walking speed. The model replicates key multitasking behaviors during OHMD reading while walking, including attention switches, changes in reading and walking speeds, and reading resumptions. © 2024 Copyright held by the owner/author(s)

关键词： Reinforcement 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：