检索结果-内蒙古大学图书馆

2024 International Conference on Smart Systems for Applications in Electrical sciences, ICSSES 2024

作者： Bharathi, P.T. Bindu, S.N. Deepthi, S.G. Gunakeerthi, H.U. Harshitha, K.U. Siddaganga Institute of Technology Department of Computer Science & Engineering Karnataka India

ISBN: (纸本)9798350364040

Hepatitis - C Virus (HCV) infection stands as a prominent cause of chronic liver disease on a global scale. Predicting HCV poses a significant challenge in the medical field, as the abundance of healthcare data remains underutilized. To tackle this issue, it is imperative to collect relevant data, extract valuable insights and employ them effectively. Consequently data mining holds immense potential across various industries and scientific domains. The objective of this research work is to meticulously analyze and visualize the dataset's variables aiming to identify essential factors related with HCV. Given the substantial prevalence of HCV, its impact on liver health and potential fatality emphasize the urgent and potential need to develop an accurate prediction models. However, the classification modelling like Support Vector Machine, Decision Tree, Logistic Regression & Random Forest were implemented with the help of feature selection and without feature selection. From the results, it is observed Random Forest with feature selection out performed with an accuracy of 89% and without feature selection with an accuracy of 88.33%. These models are indispensable in contemporary society. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

SPVPC: Smart Contract Based Publicly Verifiable Polynomial Computations 18th

SPVPC: Smart Contract Based Publicly Verifiable Polynomial C...

引用

18th International Conference on Network and System Security, NSS 2024

作者： Chakraborty, Partha Sarathi Tripathy, Somanath Department of Computer Science and Engineering Indian Institute of Technology Patna Patna India

ISBN: (纸本)9789819635306

The desire to delegate computation to the cloud arises from the proliferation of small, computational restrained devices. However, to ensure the security and privacy of the stored data in the cloud, data owners always encrypt their sensitive data before outsourcing it. Nonetheless, computation outsourcing proves beneficial only when the returned result is trustworthy. Moreover, it must ensure the security and confidentiality of the computation and data during execution. Thus, the challenge lies in efficiently verifying the correctness of computation results generated over encrypted data and maintaining practical computational time for verifying results. Blockchain emerges as a trustworthy entity, enabling fairness and transparency in the scheme. We propose a secure and efficient smart contract based publicly verifiable polynomial computation with an incentive mechanism to protect confidentiality. In the proposed scheme, the smart contract is a verifier that ensures trusted verification and manages incentive transfer. We demonstrate the proposed scheme’s effectiveness through security proofs and performance analysis, significantly reducing verifier computational costs and enhancing overall efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing in Geographic Information Systems 3

Natural Language Processing in Geographic Information System...

引用

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

作者： Kushmitha, S. Kathrine, Jaspher W. Abisha, M.B. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798331527549

The integration of Geographic Information Systems (GIS) with Natural Language Processing (NLP) has transformed how spatial data is accessed and utilized. By enabling GIS interfaces to interpret natural language queries, NLP enhances user experience, democratizes geospatial data, and improves query accuracy. This paper reviews state-of-the-art methodologies for geo-parsing, geo-coding, and spatial query interpretation, addressing challenges like geographic ambiguity, imprecise spatial relationships, and scalability limitations. Key contributions include a systematic literature review identifying research gaps such as insufficient context-awareness and a lack of annotated datasets, alongside case studies demonstrating the benefits of NLP integration in applications like disaster management and urban planning. Future opportunities are explored in leveraging deep learning, multimodal data integration, and adaptive user interfaces to further enhance GIS accessibility and usability. Future opportunities are explored in leveraging deep learning for spatial reasoning, integrating multimodal data sources for enhanced decision-making, and developing adaptive user interfaces tailored for diverse audiences. Furthermore, the paper highlights the potential of NLP in generating geo-descriptions for distributed sensor networks, supporting accessibility for impaired users, and enhancing real-time data analysis in smart city initiatives. Addressing these gaps and building scalable frameworks will pave the way for GIS systems that are not only powerful but also inclusive, fostering global accessibility and broader adoption of geospatial technologies. © 2025 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Improving Students' Understanding of Education Using Generative Adversarial Networks: Bridging Text and Visuals 8

Improving Students' Understanding of Education Using Generat...

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Shidhaganti, Ganeshayya I. Kavyashree, K.N. Vishwachetan, D. Ramaiah Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

Utilizing technology in the classroom is essential in today's environment to enhance students' learning. The background problem revolves around the necessity to adapt traditional educational methods to meet the evolving needs of students in today's digital age. With rapid technological advancements, classrooms face the challenge of effectively integrating technology to enhance learning experiences and outcomes. This includes addressing issues such as access to technology, digital literacy among students and educators, and the effective utilization of technology to facilitate interactive and engaging learning environments. The need to employ Generative Model to link school students descriptive 'Poem' statements with relevant visual imagery, accommodating diverse learning preferences. Through pre-trained VQGAN and CLIP models, this research work seamlessly integrates textual description with visually captivating images, employing iterative optimization methods to align image representations with textual descriptions. By incorporating advanced technique such as cutout augmentation the project ensures the quality and variety of generated images, catering to the diverse learning needs of school students. The outcome is successfully produced and an image is generated matching the 'Poem' description, where the average approximate percentage of accuracy is approximately 77.80% and the average approximate percentage of loss is approximately 22.89%. Additionally, a video documenting the iterative image synthesis process was created, providing insights into the image's evolution and highlighting the effective integration of technology to enhance educational experiences. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Weighted Ensemble Learning for Accident Severity Classification Using Social Media Data

引用

SN computer science 2024年第5期5卷 528页

作者： Raul, Sanjib Kumar Rout, Rashmi Ranjan Somayajulu, D.V.L.N. Department of Computer Science and Engineering National Institute of Technology Telangana Warangal 506004 India Department of Computer Science and Engineering Indian Institute of Information Technology Design and Manufacturing (IIITDM) Andhra Pradesh Kurnool 518002 India

Due to the heavy increase in social media usage, like Twitter, there is a growing interest in the research community in developing automation tools like accident severity-based tweet classification models. These tools aid in automatically extracting severity information from the accident tweet content. Moreover, prediction models are essential for predicting the severity of an accident to increase the safety efficacy of the road traffic system. However, the difficulty lies in the collection of sufficient labeled data. We propose a model called weighted ensemble-based self-training with decision tree (WESTDT), a semi-supervised methodology with a dynamic data labeling strategy. The base classifier in this model is a homogeneous weighted ensemble of decision tree classifiers for better prediction of pseudo labels. We also propose a novel performance measure called risk factor to estimate the amount of risk present in the application using the prediction model. The proposed model outperformed the state-of-the-art model, namely reliable semi-supervised ensemble learning (RESSEL), and the baseline models, namely decision tree (DT) and self-training with decision tree (STDT), in terms of both the traditional and the proposed measures. The results indicate that the proposed framework outperforms all other models on all datasets in terms of precision, recall, and accuracy by a range of 5–18.3%, 3.9–9.3%, and 6.6%, respectively. These findings can be helpful for the development of efficient and sustainable systems for traffic management and safety. It is also crucial for assisting government authorities in devising prompt, proactive strategies to prevent traffic accidents and enhance road safety. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Accident severity classification Decision tree Self-training Semi-supervised learning Weighted ensemble learning

来源：评论

学校读者我要写书评

暂无评论

MediMind: A Comprehensive Health Prediction and Record-Keeping Platform 6th

MediMind: A Comprehensive Health Prediction and Record-Keep...

引用

6th International Conference on Information Systems and Management science, ISMS 2023

作者： Naik, Darshana A. Sharma, Aditya Mahajan, Danish Khandelwal, Dhruv Gajya, Arpit Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9783031707889

The "MediMind" project signifies a revolutionary fusion of predictive analytics, centered on diabetes and heart disease risk assessment, coupled with state-of-the-art skin disease prediction and robust Electronic Health Record (EHR) management. By employing advanced machine learning models like Logistic Regression and Support Vector Machines (SVM) for diabetes and heart disease predictions, alongside the cutting-edge Convolutional Neural Network (ResNet-50) for precise skin disease classification, "MediMind" achieves unparalleled accuracy and applicability. The predictive models exhibit exceptional performance metrics, boasting high accuracy, precision, recall, and F1-score. Seamless integration into Electronic Health Records (EHR) ensures immediate implementation in clinical decision-making, providing healthcare professionals with precise insights into diabetes and heart disease risks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Priority-Based MPTCP Scheduler for 5G and Beyond Heterogeneous Links 16

Priority-Based MPTCP Scheduler for 5G and Beyond Heterogeneo...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Gumasthi, Nikhil B. Baswade, Anand M. Indian Institute of Technology Bhilai Department of Computer Science and Engineering India

ISBN: (纸本)9798350383119

Modern cellular devices often have dual interfaces for providing high-speed data transfer. This dual-interface design enhances versatility and user convenience. Dual interface technology allows 5G NR devices to connect to the 5G core using two separate base stations. One base station operates in the mmWave frequency range, and the other operates in the sub-6 GHz frequency range. However, millimeter-wave (mmWave) signals face challenges in terms of limited penetration through obstacles, such as buildings, and susceptibility to atmospheric absorption, leading to reduced coverage and potential signal degradation in adverse weather conditions. On the other hand, sub-6 GHz waves offer better penetration through obstacles and a broader scope compared to mmWave, making them suitable for providing reliable and expansive wireless connectivity in urban and indoor environments. Both mmWave and sub-6 GHz frequencies have distinct advantages and limitations;mmWave provides high data rates but has limited coverage, while sub-6 GHz offers a broader range but at lower data rates. However, in a heavy data transfer scenario, frequent loss in the mmWave link while transmitting packets can lead to packet drops (wireless medium), reducing the congestion window size and increasing the flow completion time. To mitigate this, we propose to use analytical hierarchy process (AHP) and grey rational analysis (GRA) based priority allocation mechanism to schedule packets on the most reliable link, thereby reducing the packet drops and flow completion time. © 2024 IEEE.

关键词： 5G NR Multipath TCP (MPTCP) network simulator-3 (NS-3) network simulator-3-mmWave priority scheduling

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Data Security using Edge-Preserving Image Interpolation for Reversible Data Hiding 2

Enhancement of Data Security using Edge-Preserving Image Int...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Pandey, Supriya Pandey, Shrawan Kumar Tripathi, Abhinandan Buddha Institute of Technology Department of Computer Science & Engineering Gorakhpur India

ISBN: (纸本)9798350368109

The proliferation of online data, video, and audio transfer over the internet has made Reversible Data Hiding (RDH) a significant area of research. However, embedding data into an image can be challenging as it can cause distortion and degrade image quality. To mitigate this issue, we have proposed edge-preserving image smoothing before data embedding to reduce distortion. The outcomes of proposed schemes are evaluated using metrics such as Peak Signal to Noise Ratio (PSNR), encoding capacity (EC) including incorporation time and embedding speed. The study reveals that the proposed technique surpasses existing state-of-the-art methods. © 2024 IEEE.

关键词： EC PSNR RDH

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning and Nature Inspired Algorithm Based Hybrid Approach for Detection of IoT Attacks 4

A Machine Learning and Nature Inspired Algorithm Based Hybri...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Sikdar, Subinoy Kule, Malay Indian Institute of Engineering Science and Technology Department of Computer Science and Technology Howrah Shibpur India

ISBN: (纸本)9798350389128

Internet of Things (IoT) is revolutionizing our daily life, shifting manual systems to computerized ones. With the proliferation of IoT devices connected via the internet, ensuring security against malicious attacks is critical. So, the security of information is the greatest concern in modern days as the IoT devices are attacked by various malicious services. In this paper, we have proposed a hybrid attack detection method using machine learning and nature inspired algorithm. The main objective of this paper is to find out the best feature(s) as well as the best algorithms, which detect the attack accurately. We have used CICIoT2023 dataset to classify the malicious attacks and benign traffic. Decision Tree and One Rule algorithm has been applied on the dataset and both the algorithms reached the accuracy up to 98.22% and 98.99% respectively. An ensemble learning method was also developed using Random Forest algorithm. Furthermore, a hybrid attack detection approach has been implemented using Decision Tree and Cuckoo Search Algorithm, which can perform better than Random Forest model. The hybrid classifier has obtained the accuracy up to 99.40%, whereas the Random Forest model reached the accuracy up to 99.28%. © 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

Evaluating Neural Network Parameter Obliteration in Catastrophic Forgetting

Evaluating Neural Network Parameter Obliteration in Catastro...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Sehra, Udit Dutta, Rishi Raj Pandit, Mohammad Khalid National Institute of Technology Hamirpur Department of Computer Science & Engineering India

ISBN: (纸本)9798350364866

One of the major weaknesses of Neural Networks is their inability to learn multiple functions (tasks) sequentially. This phenomenon is observed when a data distribution shift is encountered in continual learning, leading to catastrophic forgetting. Such ability is foremost important to develop models with general intelligence. In this paper, we evaluate how different parts of the neural network contribute to overall forgetting by investigating the training dynamics during different methods of continual learning. We evaluate and analyze the learning dynamics in catastrophic forgetting on frequently used classification models on CIFAR-10 and Fashion-MNIST datasets. Our findings reveal a consistent trend in continual learning scenarios, both in domain-incremental and class-incremental settings. Specifically, gamma means demonstrate stability in earlier layers but exhibit increased plasticity in later layers, indicating heightened adaptability to changes in data distributions. © 2024 IEEE.

关键词： Neural network models

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：