检索结果-内蒙古大学图书馆

Diabetic Retinopathy Severity Detection an Automated Tool 1

World Conference on Information Systems for Business Management, ISBM 2023

作者： Rao, Supriya B. Shetty, S. Shailesh Padmanayana Thanmayee, S. Divya Department of AI&ML New Horizon College of Engineering Bangalore India Department of CS and Business System Srinivas Institute of Technology Mangalore India Department of CSE Srinivas Institute of Technology Mangalore India Department of Data Science Srinivas University Institute of Engineering and Technology Mangalore India Department of CSE AJ Institute of Engineering and Technology Mangalore India

ISBN: (数字)9789819986125

ISBN: (纸本)9789819986118

Diabetics start to occur when there is not enough insulin secretion in the body. Diabetes is the primary cause of diabetic retinopathy in patients, which leads to vision impairment. The main reason for vision impairment is that lesions get accumulated in the retina. Early detection of diabetic retinopathy using the fundus images surely helps in faster recovery of the patient. Manual detection of the severity of diabetic retinopathy requires time, which may cause a delay in cure. To automate the process of severity detection, a convolutional neural network (CNN) is developed and presented, which is capable to predict the severity of the diabetic retinopathy in the fundus images. A model developed can learn the features of the retinal images and predict either of the five stages of diabetic retinopathy that is non-proliferative diabetic retinopathy, mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy, severe non-proliferative diabetic retinopathy, and proliferative diabetic retinopathy. Images were enhanced using various methods. After conducting tests on the model using random test data, the model proved to be reliable resulting in 95.5% specificity and 93.5% sensitivity. With this specificity and sensitivity, our model is reliable when deployed to the real world where the doctors in the medical field can rely on in detecting the presence of diabetic retinopathy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

SE-Resnet152 Model: Early Corn Leaf Disease Identification and Classification using Feature Based Transfer Learning Technique

SE-Resnet152 Model: Early Corn Leaf Disease Identification a...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Kalpana, Ponugoti Chanti, Yerrolla Ravi, G. Regan, D. Pareek, Piyush Kumar Avn Institute of Engineering & Technology Department of Cse Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Sona College of Technology Dept of Ece Salem India Siddartha Institute of Science and Technology Department of Ece Puttur India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

Various corn leaf diseases reduce the quantity and quality of corn crop production, so early detection and classification are important for preventing crop yield. However, the detection and classification of corn leaf disease are more difficult due to the regions of the leaf blur and noise effect. To solve the above-mentioned problems, a feature-based transfer learning approach called the Convolutional Deep Learning (CDL) model is proposed. First, the images of corn leaves taken from Plant Village are preprocessed with Green Channel Conversion (GCC) and Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithms to enhance low-contrast images. Then the important features are extracted through ResNet152, which contains two fully connected layers with a sigmoid function. Next, squeeze and excitation are combined with ResNet152 to gain better performance in detection and classification. The proposed SE-ResNet152 model outperforms with a Precision 98.71%, Recall 98.14%, F1-score 96.87% and accuracy 99.02% respectively compared to existing model like U-Net and ResNet50 models. © 2023 IEEE.

关键词： Convolutional Neural Network Deep Learning Green Channel Extraction Low-Contrast Images ResNet152

来源：评论

学校读者我要写书评

暂无评论

Wireless Capsule Endoscopy Bleeding Images Classification using CNN Based Model

Wireless Capsule Endoscopy Bleeding Images Classification us...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Kumar, Gotte Ranjith Jeyasudha, J. Ravi, G. Jagadesh, T. Madhura, G.K. Sr University School of Computer Science & Artificial Intelligence Warangal India Srm Insitute of Science and Technology Department of Computational Intelligence Chennai India Sona College of Technology Dept of Ece Salem India Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

Wireless Capsule Endoscopy (WCE) is an effective utensil with probe alimentary region diseases and executes effortless visualizing in intestine. Numerous enterprises produce its broad connection and adaptation challenging things comparable efficacity, forbearance, immunity, and consummation. Self-regulated study of the WCE handed datafile is of immense significance for discriminating peculiarity. Detecting a case's gastrointestinal region through WCE outcomes a huge datafile that involves a significant quantum moment with an exceptional competence put from the therapeutic knowledge. So many computers-backed, eyesight-grounded results can be recommended to determine this controversy, so far it don't give asked position in delicacy, farther advancements just the same as demanded. Combine with deep neural network to develop a proposed model called BIR (bleedy image recognizer) to classify images of bleeding detected by a WCE. The BIR model is combination of MobileNet and a custom-built BERT model. BIR utilizes the MobileNet model for original-position calculation for its lesser calculation energy demand and latterly the affair is fed to the BERT model for farther processing. utilized a datafiles consisting of 1650 pictures captured by WCE for the purpose of training and testing the BIR mode. © 2023 IEEE.

关键词： BERT models Bleedy image recognizer computer vision deep learning gastrointestinal tract infection Wireless capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

Exploiting Persistent CPU Cache for Scalable Persistent Hash Index 40

Exploiting Persistent CPU Cache for Scalable Persistent Hash...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Zhang, Bowen Zheng, Shengan Nie, Liangxu Qi, Zhenlin Huang, Linpeng Mei, Hong Shanghai Jiao Tong University Department of Computer Science and Engineering China AI Institute Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence China

ISBN: (纸本)9798350317152

Byte-addressable persistent memory (PM) has been widely studied in the past few years. Recently, the emerging eADR technology further incorporates CPU cache into the persistence domain. The persistent CPU cache is promising to optimize the write performance of PM-based storage systems and facilitate the design of concurrent crash-consistent data structures. In this paper, we propose Spash, a highly scalable persistent hash index for PM systems with persistent CPU cache. Spash fully exploits the benefits of persistent CPU cache to implement a durable linearizable index with low PM access overhead and high concurrency. Spash employs a fine-grained extendible hash architecture and a metadata-free segment design to minimize the number of PM accesses. Moreover, Spash adopts adaptive in-place updates and compacted-flush insertions, which dramatically conserve scarce PM write bandwidth by absorbing a large amount of PM write in the persistent CPU cache. Furthermore, Spash proposes a two-phase concurrency protocol and a collaborative staged doubling mechanism, which leverage the persistent CPU cache and hardware transactional memory to achieve lock-free concurrency and durable linearizability. Spash outperforms the other state-of-the-art persistent hash indexes in YCSB workloads by up to 19.6×. © 2024 IEEE.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

Efficient Text-Only Domain Adaptation For CTC-Based ASR

Efficient Text-Only Domain Adaptation For CTC-Based ASR

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Chen, Chang Gong, Xun Qian, Yanmin Ai Institute Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350306897

For connectionist temporal classification (CTC) based speech recognition (ASR) models, text-only domain adaptation still faces several challenges. In this study, we propose an efficient text-only domain adaptation method for CTC-based models. We introduce the assistant textual adapter (ATA) to learn textual features and transform them into the latent space of the acoustic encoder. With the help of the ATA module, the adaptation is achieved by fine-tuning the top layers of the acoustic encoder with the target domain text. Meanwhile, further improvement can be obtained by the integration with shallow fusion (SF). Adapted from LibriSpeech, experiments show that the proposed method can achieve averaged 29.7% relative WER reduction (WERR) compared with the un-adapted baseline on WSJ, and 10.5% WERR compared to SF as well. Moreover, it also shows 15.4∼37.1% WERR for 10 GigaSpeech target domains test sets compared to the un-adapted baseline, and also 6.5% WERR on average compared with SF. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Movie Recommendation Systems Using Filtering Techniques on IMDB and Rotten Tomatoes 15

Comparative Analysis of Movie Recommendation Systems Using F...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Majhi, Santosh Kumar Sahani, Preetipadma Pradhan, Rosy Acharya, Biswaranjan Grivokostopoulou, Foteini Kanavos, Andreas Gerogiannis, Vassilis C. Department of Computer Science and Information Technology Bilaspur India Veer Surendra Sai University of Technology Department of Computer Science and Engineering Odisha Burla India Veer Surendra Sai University of Technology Department of Electrical Engineering Odisha Burla India Marwadi University Department of Computer Engineering Ai Rajkot India Computer Technology Institute and Press 'Diophantus' Patras Greece Ionian University Department of Informatics Corfu Greece University of Thessaly Department of Digital Systems Larissa Greece

ISBN: (纸本)9798350368833

Recommendation systems are pivotal in industries like entertainment, where competitiveness is intense. This study enhances movie recommendations by utilizing rich datasets from IMDB and Rotten Tomatoes, incorporating movie ratings, user profiles, audience scores, and critics' reviews. These elements were subjected to sentiment analysis to refine the data quality. We explored three filtering techniques: content-based, which analyzes movie features;collaborative, which processes user behavior patterns;and hybrid, combining both to leverage their strengths. The effectiveness of these methods was assessed using Mean Average Precision at k (MAP-k) and Root Mean Square Error (RMSE), with our results showing notable improvements in recommendation accuracy. For instance, the hybrid method achieved a MAP ©k of 0.271 and an RMSE of 0.634, indicating enhanced precision and reliability of the recommendations. These findings suggest significant potential for improving user satisfaction and retention in digital platforms, demonstrating the benefit of integrating diverse data sources and analytical techniques in recommendation systems.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Real-time Gesture Recognition for Sign Language Communication with CNN

Real-time Gesture Recognition for Sign Language Communicatio...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Pandiyan, K. Kamal Raj, T. Monikarchana, Y. Jayashree, A. Judith Varshini, J.C. Shenbaga Valli, S. Srm Arts and Science College Kattankulathur Department of Cs with Ai Chennai India RajaRajeswari College of Engineering Department of Cse Banglore India Mohan Babu University Department of Mathematics India Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala EngineeringCollege Avadi Department of Computer Science and Business Systems Chennai India Aurobindo Pre University College Department of Computer Science Bangalore India J.P. College of Engineering Department of Computer Science and Engineering Tenkasi India

ISBN: (纸本)9798350375442

Communicating with hearing-impaired people is difficult. Meeting society's requirements requires developing systems that can recognize indications and notify people. Deaf-mute people now have better support thanks to sign language. Sign language-using hearing-impaired persons can enhance their communication and social skills with real-time gesture detection devices. The author presents a full CNN-based, real-time sign language recognition approach in this research. This system includes data collecting, preprocessing, architectural design, training, and real-time deployment. CNNs are trained on a vast and diverse sign language motion dataset. To increase model generalizability across signals and contexts, data preparation generally includes normalization, scaling, and augmentation. For optimal picture recognition, the CNN architecture is thoroughly trained and verified. A real-time video processing pipeline captures and prepares frames for CNN-based recognition. The model uses quantization and hardware acceleration for real-time performance to enhance efficiency. User-friendly interfaces make the system accessible to hearing-impaired people. Testing and assessment have shown the system's accuracy and resilience, permitting its actual deployment. Continuous improvement involves monitoring system performance and altering the model to fix issues and improve usability. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Intelligence of Things: A Spatial Context-Aware Control System for Smart Devices

arXiv

引用

arXiv 2025年

作者： Kalivarathan, Sukanth Mohamed, Muhmmad Abrar Raja Ravikumar, Aswathy Harini, S. School of Computer Science and Engineering Vellore Institute of Technology Chennai India AI/ML Consultant Sustainable Living Labs India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

This paper introduces Intelligence of Things (INOT), a novel spatial context-aware control system that enhances smart home automation through intuitive spatial reasoning. Current smart home systems largely rely on device-specific identifiers, limiting user interaction to explicit naming conventions rather than natural spatial references. INOT addresses this limitation through a modular architecture that integrates Vision Language Models with IoT control systems to enable natural language commands with spatial context (e.g.,"turn on the light near the window"). The system comprises key components including an Onboarding Inference Engine, Zero-Shot Device Detection, Spatial Topology Inference, and Intent-Based Command Synthesis. A comprehensive user study with 15 participants demonstrated INOT’s significant advantages over conventional systems like Google Home Assistant, with users reporting reduced cognitive workload (NASA-TLX scores decreased by an average of 13.17 points), higher ease-of-use ratings, and stronger preference (14 out of 15 participants). By eliminating the need to memorize device identifiers and enabling context-aware spatial commands, INOT represents a significant advancement in creating more intuitive and accessible smart home control systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Security in Group Message Communication Using Multi-Party Key Distribution Technique

引用

Journal of Mobile Multimedia 2024年第5期20卷 961-996页

作者： Haldar, Bilas Sinha, Rohit Paul, Pranam Department of Computer Science and Engineering The Neotia University Sarisha Diamond Harbour Road West Bengal South 24 Parganas 743368 India AI Labs Academy Pvt. Ltd. West Bengal Kolkata 700091 India Department of Computer Science and Engineering Global Institute of Engineering and Management Palpara More NH-34 Krishnanagar West Bengal Nadia 741102 India

Authentication and authorization techniques are essential for any kind of secure transaction over the Internet. It enables and empowers mechanisms to implement highly secure systems such as digital financial transition systems, hospitality management systems, and defence organizations. Most of the work on these techniques has been done based on single-user authorization. It is less secure than the multi-user authorization technique. Multi-party settings require the authorization of the majority user pool, the work is still in its nascent stage. Hence the presented work includes a multi-user authentication technique based on the approach of arithmetic greatest common divisor. This method aims to significantly enhance the security and reliability of the authorization process. Additionally, the proposed work also presented innovative encryption and decryption techniques for the security of data transformation using a modified N prime RSA algorithm. Furthermore, this work also discussed the application of the proposed methodology in the hospitality industry to ensure the security of customer data. The results of this work indicate that the suggested techniques enhance the security of data transformation and improve the time efficiency of key generation, encryption, and decryption techniques. © 2024 River Publishers.

关键词： authentication decryption encryption hospitality industry Key generation N prime RSA security analysis

来源：评论

学校读者我要写书评

暂无评论

Cancer Diseases Diagnosis Using Deep Transfer Learning Architectures 1st

Cancer Diseases Diagnosis Using Deep Transfer Learning Archi...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Promy, Tania Ferdousey Joya, Nadia Islam Turna, Tasfia Haque Sukhi, Zinia Nawrin Ashraf, Faisal Bin Uddin, Jia Department of Computer Science and Engineering School of Data Science Brac University Dhaka Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon Korea Republic of

ISBN: (纸本)9783031346187

Cancer is a lethal disease among the diseases in the world. It is clinically known as ‘Malignant Neoplasm’ which is a vast group of diseases that encompasses unmonitored cell expansion. It can begin anywhere in the body such as the breast, skin, liver, lungs, brain, and so on. As reported by the National Institutes of Health (NIH), the projected growth of new cancer cases is forecast at 29.5 million and cancer-related deaths at 16.4 million through 2040. There are many medical procedures to identify the cancer cell, such as mammography, MRI, CT scan, which are common methods for cancer diagnosis. The methods used above have been found to be ineffective and necessitate the development of new and smarter cancer diagnostic technologies. Persuaded by the phenomena of medical image classification using deep learning, our recommended initiative targets to analyze the performance of different deep transfer learning models for cancer cell diagnosis. In this paper, we have used VGG16, Inception V3 and MobileNet V2 deep architectures to diagnosis the breast cancer (KAU-BCMD dataset), lung cancer (IQ-OTH/NCCD dataset) and skin cancerHam10000). Experimental results demonstrate that VGG16 architecture shows comparatively higher accuracy by exhibiting 98.5% of accuracy for breast cancer, 99.90% for lung cancer and 93% for skin cancer dataset. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Diseases

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：