检索结果-内蒙古大学图书馆

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Khushal A Kishore A Tejas Neswi Mohana K Badarinath Computer Science and Engineering (Cyber Security) RV College of Engineering® Bengaluru India Computer Science and Engineering RV College of Engineering® Bengaluru India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

According to the National Interagency Fire Center (NIFC) forest fires pose a major threat to our planet, causing severe ecological, economic, and human loss, with an estimated 7 million acres of forest burned annually in the United States alone. To overcome this, in this paper proposed a cutting-edge solution that integrates Internet of Things (IoT), remote sensing, and machine learning technology. By deploying a network of sensors throughout a certain forest area to monitor temperature, humidity, and smoke levels, we can collect real-time data on forest conditions. This data is transmitted to a centralized system with an accuracy rate of 92% in predicting potential fire outbreaks. This approach provides early detection of forest fires, allowing for rapid response and mitigation efforts. Proposed system ensures swift communication between the monitoring station, authorities, and firefighting teams, reducing response times. Rigorous testing, including over multiple simulations, has validated the system's effectiveness, positioning it as a major tool in forest fire management and potentially reducing fire damage by 30%.

关键词： Temperature sensors Vibrations Wildlife Forestry Machine learning Real-time systems Sensor systems Internet of Things Time factors Monitoring

来源：评论

学校读者我要写书评

暂无评论

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

VHASR: A Multimodal Speech Recognition System With Vision Ho...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Hu, Jiliang Li, Zuchao Wang, Ping Ai, Haojun Zhang, Lefei Zhao, Hai Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science Wuhan University Wuhan China School of Information Management Wuhan University Wuhan China Department of Computer Science and Engineering Shanghai Jiao Tong University China

ISBN: (纸本)9798891761643

The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approach effectively utilizing audio-related image information and set up VHASR, a multimodal speech recognition system that uses vision as hotwords to strengthen the model's speech recognition capability. Our system utilizes a dual-stream architecture, which firstly transcribes the text on the two streams separately, and then combines the outputs. We evaluate the proposed model on four datasets: Flickr8k, ADE20k, COCO, and OpenImages. The experimental results show that VHASR can effectively utilize key information in images to enhance the model's speech recognition ability. Its performance not only surpasses unimodal ASR, but also achieves SOTA among existing image-based multimodal ASR. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Scalable Video Transmission Based on the Outage Probability Analysis of MIMO Coding 4

A Novel Framework for Scalable Video Transmission Based on t...

引用

4th Information Communication Technologies Conference, ICTC 2023

作者： Zhang, Yongjian Wang, Dongyu Zhang, Zhiqiang Wang, Shiguo University of International Relations School of Cyber Science and Engineering Beijing China North China University of Technology Department of Electronic Engineering Beijing China Shanxi Police College Department of Cyber Security Taiyuan China University of Science and Technology Computer and Communication Engineering Institute Changsha Changsha China

ISBN: (纸本)9781665462587

This work presents a radical approach for space-time codings, which could realize the goal of unequal error protection (UEP) transmitting for scalable video. This analysis leads us to develop a hybrid coding framework that combines vertical bell-labs layered space-time (V-BLAST) to ensure high-data-rate for the less crucial enhancement layer (EL) and Alamouti coding to ensure high reliability for the base layer (BL). According to those simulation findings, the suggested hybrid delivery method performs substantially better based on peak signal-to-noise ratio than either a pure special multiplexing or a pure spatial diversity delivery scheme. © 2023 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Forensic Analysis of I2P Communication Network in Android and macOS Environments 18

Forensic Analysis of I2P Communication Network in Android an...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Wangchuk, Tashi Mandela, Ngaira Mbinda, Tumaini Damedjate, Kamboisssoi Etyang, Felix Makopa, Joel Royal University of Bhutan Department of Information Technology Dewathang Bhutan National Forensic Sciences University School of Cyber Security and Digital Forensics Gandhinagar India Cochin University of Science and Technology School of Computer Science and Engineering Kochi India

ISBN: (纸本)9789380544519

The Invisible Internet Project (I2P) has emerged as a crucial privacy-centric communication network, offering users a secure and anonymous online environment. As the utilization of I2P continues to expand, the demand for specialized forensic techniques tailored to this network becomes imperative. This paper comprehensively investigates I2P forensics within Android and macOS environments, addressing the unique challenges inherent in extracting and scrutinizing digital evidence from I2P applications. The research explores various artifacts and techniques to aid in reconstructing user activities within the I2P network, including analyzing storage files, configuration data, logs, and cache files. Additionally, the study investigates memory forensics as a complementary approach to I2P forensics. The outcomes of this research contribute to advancing forensic analysis techniques in privacy-centric networks, facilitating the efficient investigation of I2P-related crimes. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Android forensics dark web digital evidence digital forensics eepsite, Anti-forensics I2P forensics macOS forensics memory forensics privacy-centric networks

来源：评论

学校读者我要写书评

暂无评论

Multiclass Brain Tumor Detection using Convolutional Neural Network and Conventional Machine Learning 2

Multiclass Brain Tumor Detection using Convolutional Neural ...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Vidhya, K. Vamsi Krishna, B. Haritha, M. Rajasekaran, Arun Sekar Roopa Chandrika, R. Velusamy, Jayaraj Karunya Institute of Technology and Sciences Division of Data Science and Cyber Security School of Computer Science and Technology Coimbatore India QIS College of Engineering and Technology Department of AIMLDS Andhra Pradesh India QIS College of Engineering and Technology Department of Mechanical Engineering Andhra Pradesh India SR University Department of Electronics and Communication Engineering Telangana India Karpagam Academy of Higher Education Department of Cyber Security Coimbatore India Nehru Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331534950

Brain tumor (BT) affect the brain and reduce the lifespan of humans. Therefore, diagnosis and treatment of illnesses in its early stage is required. The objective of this paper is to evaluate the effectiveness of the Convolutional Neural Network (CNN) and Conventional Machine Learning (CML) strategies for identifying multiple classes of brain tumor. In the research, a comparison is made between these two systems for the picture classification of brain tumor. The first step is the collection and preprocessing of images of several classes of brain tumor. The CNN and CML models are trained using the preprocessed dataset. CML makes use of traditional machine learning (ML) algorithms for the purpose of feature extraction and classification, whereas CNN relies on convolutional layers to automatically extract significant features from the images it is fed as input. Precision, accuracy, F1 score, and recall are the criteria that are utilized to evaluate methods. In terms of accuracy and overall performance, CNN is superior to CML. CNN provides a more precise classification of a variety of tumor classifications. Based on these findings, convolutional neural networks (CNN) are likely superior than machine learning for the identification of multiclass brain tumor. CNNs are superior because of their ability to directly understand intricate patterns and characteristics from photographs. This work demonstrates the usefulness of CNNs for multiclass classification in brain tumor detection systems because of their high accuracy and efficiency. © 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

Comparative Analysis of Machine Learning Algorithms and Datasets for Detecting cyberbullying on Social Media Platforms

Comparative Analysis of Machine Learning Algorithms and Data...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Palagati, Anusha Balan, Santhosh Kumar Arun Joe Babulo, S. Raja, Laxmi Natarajan, K.K. Kalimuthu, Rajkumar Dept. of Computer Science and Engineering Guru Nanak Institute of Technology Ibrahimpatnam Hyderabad India Department of Computer Applications K.S.R College of Arts and Science for Women Tamilnadu Tiruchengode India Department of Cyber Security Karpagam Academy of Higher Education Tamilnadu Coimbatore India College of Engineering and Technology University of Technology and Applied Sciences Al Mussanah Oman Department of Cyber Security Guru Nanak Institute of Technology Ibrahimpatnam Hyderabad India

ISBN: (纸本)9798331510299

cyberbullying is defined as sharing of undesirable material in the cyberspace, primarily- the use of the social sites that instigate hostility and create feelings of hatred among the individuals. Another increasing threat due to increase use of internet-based communication is cyberbullying especially on the site such as Twitter. Different ML and NLP approaches including support vector machine (SVM), Naïve bayes, Random Forest, and logistic regression is employed to detect cyberbul Bullivating. These methods for supervised learning mine patterns in text and image, allowing computers to promptly flag risky interactions. Some of these approaches also utilizes OCR for the identification of image-based bullying. Consequently, the objective of this research is to identify the correct algorithm and dataset for improving the identification of cyberbullying and solving the problem that manifests itself in the steady increase in cases of this type of bullying. © 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

An Effective Span-based Multimodal Named Entity Recognition with Consistent Cross-Modal Alignment 30

An Effective Span-based Multimodal Named Entity Recognition ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Xu, Yongxiu Xu, Hao Huang, Heyan Cui, Shiyao Tang, Minghao Wang, Longzheng Xu, Hongbo Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9782493814104

With the increasing availability of multimodal content on social media, consisting primarily of text and images, multimodal named entity recognition (MNER) has gained a wide-spread attention. A fundamental challenge of MNER lies in effectively aligning different modalities. However, the majority of current approaches rely on word-based sequence labeling framework and align the image and text at inconsistent semantic levels (whole image-words or regions-words). This misalignment may lead to inferior entity recognition performance. To address this issue, we propose an effective span-based method, named SMNER, which achieves a more consistent multimodal alignment from the perspectives of information-theoretic and cross-modal interaction, respectively. Specifically, we first introduce a cross-modal information bottleneck module for the global-level multimodal alignment (whole image-whole text). This module aims to encourage the semantic distribution of the image to be closer to the semantic distribution of the text, which can enable the filtering out of visual noise. Next, we introduce a cross-modal attention module for the local-level multimodal alignment (regions-spans), which captures the correlations between regions in the image and spans in the text, enabling a more precise alignment of the two modalities. Extensive experiments conducted on two benchmark datasets demonstrate that SMNER outperforms the state-of-the-art baselines. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A stacked ensemble approach to detect cyber attacks based on feature selection techniques

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 316-331页

作者： Urmi, Wahida Ferdose Uddin, Mohammed Nasir Uddin, Md Ashraf Talukder, Md. Alamin Hasan, Md. Rahat Paul, Souvik Chanda, Moumita Ayoade, John Khraisat, Ansam Hossen, Rakib Imran, Faisal Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh School of Information Technology Deakin University Waurn Ponds Campus Geelong Australia School of Information Technology Crown Institute of Higher Education 116 Pacific Highway North SydneyNSW2060 Australia Department of Cyber Security Bangabandhu Sheikh Mujibur Rahman Digital University Kaliakoir Gazipur1750 Bangladesh Department of Electrical and Computer Engineering University of Ottawa Canada

The exponential growth of data and increased reliance on interconnected systems have heightened the need for robust network security. cyber-Attack Detection Systems (CADS) are essential for identifying and mitigating threats through network traffic analysis. However, the effectiveness of CADS is highly dependent on selecting pertinent features. This research evaluates the impact of three feature selection techniques—Recursive Feature Elimination (RFE), Mutual Information (MI), and Lasso Feature Selection (LFS)—on CADS performance. We propose a novel stacked ensemble classification approach, combining Random Forest, XGBoost, and Extra-Trees classifiers with a Logistic Regression meta-model. Performance is assessed using CICIDS2017 and NSL-KDD datasets. Results show that RFE achieves 100% accuracy for Brute Force attacks, 99.99% for Infiltration and Web Attacks on CICIDS2017, and 99.95% accuracy for all attacks on NSL-KDD, marking a significant improvement over traditional methods. This study demonstrates that optimizing feature selection and leveraging diverse classifiers can substantially enhance the accuracy of CADS, providing stronger protection against evolving cyber threats. © 2024 The Authors

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

PRESS: Defending Privacy in Retrieval-Augmented Generation via Embedding Space Shifting

PRESS: Defending Privacy in Retrieval-Augmented Generation v...

引用

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

作者： He, Jiaming Liu, Cheng Hou, Guanyu Jiang, Wenbo Li, Jiachen School of Computer Science and Engineering University of Electronic Science and Technology of China China College of Computer Science and Cyber Security Oxford Brookes College Chengdu University of Technology China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350368741

Retrieval-augmented generation (RAG) expands the capabilities of large language models (LLMs) in various applications by integrating relevant information retrieved from external data sources. However, the RAG systems are exposed to substantial privacy risks during the information retrieval process, leading to potential data leakage of private information. In this work, we present a Privacy-preserving Retrieval-augmented generation via Embedding Space Shifting (PRESS), systematically exploring how to protect privacy in RAG systems. Specifically, we first conduct proximal policy optimization (PPO) based training on pre-trained language models to generate target training samples. Then we employ a purposive shift fine-tuning on the text embedding model with the generated samples for guiding the RAG system to map potential privacy leaking queries to safe target in embedding space. Extensive experimental results on representative models and datasets demonstrate that our protection method achieves high defense performance with high efficiency while keeping the normal functionality of the RAG system. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advance Public Bus Transport Management System: An Innovative Smart Bus Concept

Advance Public Bus Transport Management System: An Innovativ...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Patel, Keyurkumar Patel, Divya Chaudhary, Nishit Thakkar, Darsh Savaliya, Pratham Mistry, Armaan Rashtriya Raksha University Artificial Intelligence and Cyber Security Department of IT Gujarat Gandhinagar382305 India Karnavati University Unitedworld School of Computational Intelligence Department of Computer Science and Engineering Gujarat Gandhinagar382422 India

ISBN: (纸本)9798350324136

In the present era, public bus transportation services often lag behind in adopting modern technologies, resulting in numerous operational complexities. These issues encompass challenges such as poor passenger density control, operational inefficiencies, inadequate live tracking, limited real-Time capabilities, suboptimal resource management, route ambiguities, safety concerns, and more. This research paper introduces a comprehensive solution an Advance Public Bus Transport Management System (APBTMS) that aims to address these challenges for the benefit of both passengers and transport management authority. Our proposed system leverages various sensors and IoT (Internet of Things) modules deployed within buses to monitor various onboard activities and physical environmental factors. These enable the making of data-driven decisions in real-Time, Facilitating improved operational control. Key components of the system include GPS (Global Positioning System) tracking for real-Time bus location updates, passenger density/count through CV (computer Vision), and continuous monitoring of physical environmental factors such as temperature, humidity, sound magnitude, and vibration magnitude which facilitate accident/abnormalities detection, Fire detection and helps in continuously monitoring road quality. The application of CV technology, along with passenger count, can detect harm-causing objects inside a bus and can compare the faces of passengers with black-listed passengers (involved in previously reported crimes such as theft, and nuisance). Passengers benefit from these advancements through a dedicated mobile application. A User-friendly website is also offered to public bus transport management authority providing various useful functionalities. With the addition of safety features like real-Time speed detection and many other capabilities in the future, our proposed system can expand its benefits to school bus services and other public transportation services. © 2024

关键词： API (Application Programming Interface) AWS (Amazon Web Services) Cloud Computing CV (computer Vision) GPS (Global Positioning System) GSM (Global System for Mobile communication) IoT (Internet of Things) ML (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：