检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2025年第11期49卷 165-176页

作者： Ilias, Shaik Mohammad Sharmila, V. Ceronmani Durga, V. Sathya Dept. of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India Department of Information Technology Hindustan Institute of Technology and Science Chennai India Department of Computer Science&Engineering Hindustan Institute of Technology and Science Chennai India

If adversaries were to obtain quantum computers in the future, their massive computing power would likely break existing security schemes. Since security is a continuous process, more substantial security schemes must be developed. Current PQC schemes primarily focus on data security or key exchange, and further improvement towards enhanced PQC primitives is required. Our proposal in this research is an innovative paradigm for PQC-focused cloud data security. The proposed HEDT approach achieves encryption and decryption with significantly lower latency (20% improvement) and higher reliability than AES, DES, and RSA, as demonstrated through experimental results. Furthermore, ECSIDH, a hybrid key exchange mechanism combining SIDH and ECDH, improves security strength by 50% while maintaining computational costs within 1.13x of SIDH. Compared to individual key exchange schemes like SIDH, ECSIDH offers superior security as a PQC candidate. These results confirm the robustness and efficiency of the proposed framework in ensuring secure data outsourcing and key exchange in cloud environments. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Moth flame optimization algorithm for efficient feature selection and hybrid classification technique for intrusion detection system

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Keerthanarani, U. Selvakumar, V. Singaravelan, S. Raja, S. Edwin Thenmozhi, K. Shunmugam, D. Arun Dept. of Computer Science and Engineering P.S.R Engineering College Sivakasi India Dept.Of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai Avadi India Dept. Of Computer Science and Engineering Coimbatore Institute of Engineering and Technology Coimbatore India Dept. Of Electronics and Communication Engineering P.S.R Engineering College Sivakasi India

The rapid expansion of the Internet of Things (IoT) brings numerous benefits but further presents fresh difficulties, especially in terms of security. The distributed and interconnected nature of IoT devices makes them susceptible to various security threats. An Intrusion Detection System (IDS) plays a crucial role in safeguarding IoT networks by monitoring, detecting, and responding to potential security incidents. The Internet of Things (IoT) connects billions of devices, sensors, and systems, transforming industries and everyday life. However, this extensive interconnectivity also introduces significant security risks, making Intrusion Detection Systems (IDS) a critical component for safeguarding IoT environments. Feature selection is a crucial aspect of building effective Intrusion Detection Systems (IDS). Selecting relevant features not only helps in achieving better classification accuracy but also contributes to reducing false alarm rates. In the proposed system a moth flame optimizer is utilized to select the efficient features from the dataset, overall accuracy of over 97%. Further it is classified employing Random Forest and J48 classifier which attains high classification accuracy and low false alarm rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Realtime Sign Language Detection and Multilingual Translation System

Enhanced Realtime Sign Language Detection and Multilingual T...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Kakkar, Madhur Daniel, John Sudha, D. Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331538538

Sign language is the communication medium that is utilized by the hearing-impaired community. The medium is visual and it uses hand signs and symbols for communication. Over 300 different types of sign languages present in the world today. Sign language uses gestures and hand movements for the majority of the words and finger spellings for the rest. Nonverbal speakers face a lot of challenges while interacting with verbal speakers. Even non-verbal speakers who speak different sign languages face difficulties communicating with each other. This project proposes an enhanced real-time system which detects gestures and finger spellings of multiple sign languages, and translates them into multiple spoken languages. The proposed system aims to utilize CNN network for finger spelling recognition and Long Short-Term Memory (LSTM) network for gesture interpretation. The system will use computer vision for accurate gesture detection and Google Translator API for recognizing signs which will be translated into multiple spoken languages. Initial tests with isolated datasets indicate promising accuracy for both finger spelling and gesture recognition. The goal of the completed system is to help aid communication between verbal and non-verbal speakers and to provide an efficient mode of communication between the two communities. © 2025 IEEE.

关键词： Interactive computer systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Layered Approach to IoT Cybersecurity in Smart Cities 3

Multi-Layered Approach to IoT Cybersecurity in Smart Cities

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Benjamine, Daniel Anto Madhavan, K. Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of Technology Chennai India

ISBN: (纸本)9798331527549

Internet of Things (IoT) has been rapidly growing over the past years. There have been many cybersecurity challenges faced by IoT-based smart cities in existing work for the energy, health and transportation sectors. These cybersecurity challenges are crucial to remove in the IoT sector to implement a safe and secure IoT based smart city. Vulnerabilities across layers in IoT are analyzed and a multi-layered model of security is proposed to enhance data integrity and communication security by using AI, blockchain and ML. This paper would also present several policy recommendations to stakeholders and IoT developers for building a safe urban IoT ecosystem. © 2025 IEEE.

关键词： Cybersecurity frameworks IoT smart city technologies urban

来源：评论

学校读者我要写书评

暂无评论

Dots to Dialogue: Enhancing Accessibility through Braille Image-to-Speech Conversion 3

Dots to Dialogue: Enhancing Accessibility through Braille Im...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Shwetha, B.S. Sirisha, M. Vachana, U. Kadlimatti, Aditya Manjushree, N.S. Dept. of Computer Science and Engineering Bangalore Institute of Technology Bengaluru India

ISBN: (纸本)9798331527549

Braille script serves as a fundamental medium of communication for individuals with visual impairments. However, its interpretation by non-experts poses a significant challenge, hindering inclusivity in education and daily interactions. This study proposes a system that leverages Convolutional Neural Networks (CNNs) and the Google Text-to-Speech (GTTS) library to translate Braille text into multilingual speech. This research addresses the challenge of Braille literacy among visually impaired individuals by developing a system that translates Braille text into multilingual speech. The proposed solution utilizes advanced CNNs for accurate Braille character recognition and integrates GTTS technology for real-time speech output. The results demonstrate a significant improvement in accessibility and communication for users, with an accuracy rate of 97.28% achieved using the AlexNet model." © 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

Advances in Remote Sensing Technologies for Ecological Monitoring and Applications in Carbon Stock Estimation 3

Advances in Remote Sensing Technologies for Ecological Monit...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sadhasivam, Shankaripriya Gayathri, G. Poongothai, P. Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of technology Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

This review explores recent advancements that are made in remote sensing, enabling detailed analysis of our ecosystem through high resolution and multispectral imaging. The recent advancements in remote sensing includes developments useful for generation of synthetic images using GAN such as StyleGAN3 and for estimation of carbon stocks in forest using OBIA. Ecotones like mangroves and saltmarsh are crucial for carbon sequestration but mapping them accurately was challenging due to spectral similarity and seasonal variations. Focusing on coastal protection by this review examines the mapping methodologies such as random forest classification, OBIA and FID for habitat distinction, canopy area assessment and analysis. Through these technologies data accuracy can be enhanced for better monitoring. This review concludes with a discussion of AI-powered image synthesis and classification. © 2025 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Optimizing Kidney Stone Detection with Vision Transformers and CNNs: A Transfer Learning Strategy

Optimizing Kidney Stone Detection with Vision Transformers a...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Kulkarni, Supritha Suhaas Rao, S. Chopra, Tushar Kumar Yeshwanth, S.P. Bhanushree, K.J. Suneetha, K.R. Bangalore Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331508685

Kidney stones are a common and impactful urological condition, with timely and accurate diagnosis being critical to prevent complications such as renal damage and avoid invasive treatments. This study explores the use of advanced deep learning models, including Vision Transformers (ViT), Swin Transformer and Convolutional Neural Networks (CNNs) - specifically XResNet-50, VGG-16, MobileNetV2 and AlexNet - to enhance kidney stone detection from CT scan images. Leveraging a robust dataset of annotated CT scans in JPG format, the approach employs transfer learning which leverages features learnt from the ImageNet dataset to optimize model performance, focusing on classifying cases as either "Kidney Stone Present"or "Kidney Stone Absent". To further improve diagnostic reliability, the Grad-CAM (Gradient-weighted Class Activation Mapping) identifies and localizes kidney stones within CT images, enhancing understanding of the model's decision-making and supporting interpretability. Addressing challenges related to dataset imbalance, model interpretability, and generalizability across healthcare settings. By refining these models for kidney stone detection, the main objective of this work is to build a reliable diagnostic tool that aids in clinical judgement and treatment planning, ultimately enhancing patient outcomes and encouraging broader clinical adoption. © 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

Automail AI: Intelligent Voice-Controlled Email Generator 3

Automail AI: Intelligent Voice-Controlled Email Generator

引用

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

作者： Jayaram, Kavitha Mandagere, Samarth Gopisetti, Sampriti Sahit, S. Bnm Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331515911

The complexity of contemporary communication further emphasizes the need to automate monotonous work to increase efficiency and effectiveness. This paper introduces a new advance, voice-controlled Automail AI, in the form of an email generation tool that automatically sends an email according to end-user-specified keywords. Automail AI utilizes NLP, ML, and Speech Recognition to differentiate formal emails from informal ones and draft appropriate responses as the situation demands. It has been tuned with Naive Bayes Classifier that yields a better level of accuracy as compared to models such as Decision Tree, SVM, and Logistic Regression. Setting the benchmark for Automated Communication tools, Automail AI combines diverse technologies like SMTP to guarantee secure Email delivery, Google Text-to-Speech or GTTS for auditory feedback, and a module providing an interface for speech recognition that offers the possibility to use the tool with no hands. © 2025 IEEE.

关键词： Automail AI email generation GTTS machine learning Naive Bayes natural language processing SMTP speech recognition

来源：评论

学校读者我要写书评

暂无评论

Advancing Pediatric Appendicitis Diagnosis: Harnessing CNN and Hybrid Models with Ultrasound Imaging

Advancing Pediatric Appendicitis Diagnosis: Harnessing CNN a...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Kulkarni, Supritha Sharma, Sanchit Manavi, J. Vachana, U. Bhargavi, M.S. Bangalore Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331508685

Pediatric appendicitis, an acute inflammatory disease, arises from the obstruction of the appendix, often due to inflammation or a fecalith. This common abdominal emergency in children presents diagnostic challenges due to its varied clinical manifestations, which can lead to misdiagnosis or higher perforation rates stemming from atypical symptoms. This research investigates the use of deep learning, more especially Convolutional Neural Networks (CNNs), by utilizing ultrasonic imaging data, which is less expensive, non-invasive, and quicker than the other approaches now in use. Several variants are evaluated including a basic CNN and more advanced hybrid models such as CNN-Support Vector Regression, CNN-Transformer, and Hierarchical Deep CNN, to identify the most optimal model to significantly enhance diagnostic accuracy, for young patients facing this condition. The study's main goal is to develop a highly accurate and dependable diagnostic tool for evaluating the severity of pediatric appendicitis by differentiating between simple and complex cases and identifying whether surgery is required to inform treatment plans. Various challenges that need to be tackled are managing significant dataset imbalances, enhancing interpretability and transparency for real-world clinical settings, and ensuring the robustness and adaptability of all these models across various healthcare environments. © 2025 IEEE.

关键词： Pediatrics

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：