检索结果-内蒙古大学图书馆

1st Workshop on GenAI Content Detection, GenAIDetect 2025

作者： Agrahari, Shifali Singh, Sanasam Ranbir Department of Computer Science and Engineering Indian Institute of Technology Guwahati India

ISBN: (纸本)9798891762053

Detecting AI-generated text has become increasingly prominent. This paper presents our solution for the DAIGenC Task 1 Subtask 2, where we address the challenge of distinguishing human-authored text from machine-generated content, especially in multilingual contexts. We introduce Multi-Task Detection (MLDet), a model that leverages Cross-Lingual Adaptation and Model Generalization strategies for Multilingual Machine-Generated Text (MGT) detection. By combining language-specific embeddings with fusion techniques, MLDet creates a unified, language-agnostic feature representation, enhancing its ability to generalize across diverse languages and models. Our approach demonstrates strong performance, achieving macro and micro F1 scores of 0.7067 and 0.7187, respectively, and ranking 15th in the competition1. We also evaluate our model across datasets generated by different distinct models in many languages, showcasing its robustness in multilingual and cross-model scenarios. © 2025 International Conference on 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 Scalable and Fault-Tolerant 5G Core on Kubernetes 17

A Scalable and Fault-Tolerant 5G Core on Kubernetes

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Paul, Sourav Keluskar, Tanvi Vutukuru, Mythili Indian Institute of Technology Department of Computer Science and Engineering Bombay India

ISBN: (纸本)9798331531195

The 5G core is an important part of a 5G network, and with the exponential growth of connected devices and dynamic traffic conditions, it is essential for the 5G core to be scalable and fault-tolerant. This requirement is even more important with the softwarization of the packet core and cloud-based deployments. This paper presents a comparison of design choices when building a scalable and fault-tolerant 5G core on a Kubernetes-orchestrated cloud platform. Prior work in this direction does not fully explore all design choices, or is not compliant with 3GPP standards. In contrast, we start with a 3GPP-compliant production-grade 5G core, and build multiple variants of cloud-native 5G core components. We leverage Kubernetes' automatic failover, and auto-scaling capabilities in different ways to make the 5G core scalable and fault-tolerant. We conduct extensive experiments to evaluate the scalability and resilience of various design choices, and to quantify the overheads of cloud deployments. Our work exposes tradeoffs between performance and fault tolerance, and provides insights on how best to design a scalable and fault-tolerant 5G core on Kubernetes. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing DNA Sequence Analysis for Disease Diagnosis and Prediction Using Parallelised Hash-Based Approach 2

Enhancing DNA Sequence Analysis for Disease Diagnosis and Pr...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Sreeram, Anusha Bhukya, Raju Department of Computer Science and Engineering National Institute of Technology Warangal India

ISBN: (纸本)9798331530389

DNA sequencing is a critical tool in genetics, helping to identify disease-causing mutations, predict disease risks, screen for genetic diseases, and monitor disease progression. By determining the order of nucleotides that make up DNA, DNA sequencing allows for the identification of genetic information in specific DNA fragments, entire genomes, or complex microbiomes. It has transformed disease diagnosis and treatment and has applications in biotechnology, forensic science, and evolutionary biology. Comparing DNA sequences helps researchers identify genetic disorders, cancers, and antibody repertoires, leading to tailored treatments for individual patients. However, the diagnosis of diseases using DNA requires an efficient algorithm due to the large number of nucleotides in DNA sequences. The hash-based approach, an optimal string pattern-matching algorithm, is used to identify relevant patterns in DNA sequences. This approach has shown significant improvement in speed compared to the single pattern matching approach for finding multiple string patterns and a parallelized approach for hash based using GPU is also proposed. © 2025 IEEE.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation Using Web Crawling 2nd

Movie Recommendation Using Web Crawling

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Raj, Pronit Kumar, Chandrashekhar Shekhar, Harshit Kumar, Amit Paul, Kritibas Jana, Debasish Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India

ISBN: (纸本)9783031845420

In today’s digital world, streaming platforms offer a vast array of movies, making it hard for users to find content matching their preferences. This paper explores integrating real-time data from popular movie websites using advanced HTML scraping techniques and APIs. It also incorporates a recommendation system trained on a static Kaggle dataset, enhancing the relevance and freshness of suggestions. By combining content-based filtering, collaborative filtering, and a hybrid model, we create a system that utilizes both historical and real-time data for more personalized suggestions. Our methodology shows that incorporating dynamic data not only boosts user satisfaction but also aligns recommendations with current viewing trends. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

Enhancing aviation safety: Machine learning for real-time ADS-B injection detection through advanced data analysis

引用

Alexandria engineering Journal 2025年 126卷 262-276页

作者： Rahman, Md. Atiqur Bhuiyan, Touhid Ali, M. Ameer Department of Computer Science and Engineering East West university Dhaka Bangladesh School of Information Technology Washington University of Science and Technology Alexandria United States Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh

Airplanes play a critical role in global transportation, ensuring the efficient movement of people and goods. Although generally safe, aviation systems occasionally encounter incidents and accidents that underscore the need for proactive risk management. This study employs machine learning to detect abnormalities in commercial aircraft operations using Automatic Dependent Surveillance–Broadcast (ADS-B) data. Given the growing reliance on ADS-B technology, concerns regarding its susceptibility to security breaches, such as injection attacks, have intensified. To address these vulnerabilities, we propose a robust ADS-B injection detection system. Employing GridSearchCV for model optimization, it effectively identifies and categorizes injection risks. The system's performance, evaluated using the ADS-B Message Injection Attacks Dataset, achieves outstanding results, including a value of 0.9970 for the accuracy, precision, recall, and F1 score. The proposed classifier also demonstrates a higher area under the curve (0.9999), specificity (0.9956), and Cohen's kappa (0.9954) than existing approaches, while achieving a lower log loss (0.0107). This research significantly enhances aviation security by introducing a highly accurate, computationally efficient, and reliable real-time detection model for ADS-B injection attacks, ensuring the integrity and resilience of modern flight control systems. © 2025 The Authors

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Indian sign language recognition using TensorFlow and MediaPipe 1st

Indian sign language recognition using TensorFlow and MediaP...

引用

1st International Conference on Applications of AI in 5G and IOT, ICAAI5GI 2024

作者： Kanyal, Hoshiyar Singh Gupta, Shubham Singh, Smriti Kumari, Sarita Department of Computer Science and Engineering ABES Institute of Technology Ghaziabad India

ISBN: (纸本)9781032874036

With this work, a technical method for identifying Indian Sign Language is attempted to be developed. This work attempted to create a system for recognizing the hand movements from Indian Sign Language using machine learning techniques. An amalgamation of two- and three-dimensional illustrations of Indian Sign Language motions has been employed. The dataset was manually assembled. To identify landmarks in the pictures, the Media Pipe framework has been used. The findings show that the approach used in this study is successful in identifying the other Sign Language alphabets and gestures. The signs and gestures recognition for several more Indian regional languages could also be investigated and explored using this method. © 2025 the Author(s).

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Advancing Software-Defined Vehicles: An End-to-End Framework with Digital Twin Based Attestation for OTA Updates 17

Advancing Software-Defined Vehicles: An End-to-End Framework...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Agrawal, Krish Rohan, Jha Luthra, Nishkarsh Sekhar, Pilla Venkata Sharma, Hrishesh Banda, Gourinath Indian Institute of Technology Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798331531195

Software-defined vehicles (SDVs) are an emerging paradigm in the automotive industry where vehicles' functionality, performance, and safety can be enhanced and updated through software, even after production. Unlike traditional vehicles, which rely primarily on physical components, SDVs leverage advanced connectivity, real-time data analytics, and cloud integration to adapt to changing regulations, driver preferences, and environmental conditions. This shift enables vehicles to evolve continuously, responding to new technological advances and customer needs. In this paper, we propose an end-to-end framework to demonstrate and realize the full benefits of SDVs. We incorporate the concept of digital twin (of the vehicle) driven software update authorization to download or update an application on the vehicle. In our framework, attestation refers to the verification of each software update's compatibility and functionality with the vehicle's current ECUs before deployment. Any impending/requested update is first verified for its compatibility with the vehicle's architecture (as per the twin) on the cloud. The idea is via the SDVs' digital twin - since each and every ECU is virtualized - the simulation and testing of the actual hardware setup with the new application software can be done without direct impact on the physical vehicle. Once the application is installed across all relevant virtualized ECUs, the framework confirms compatibility, ensuring smooth deployment and functionality in the real-world vehicle. Post this successful attestation, the installation will be done on the real vehicle corresponding to that digital twin. Through this proposed framework, we intend to ensure the safety of the updation, while the new updates contribute to the functionality and performance improvements. © 2025 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Dynamic Emotion-Adaptive Attention Mechanism (DEAAM) 5th

Dynamic Emotion-Adaptive Attention Mechanism (DEAAM)

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Garugu, Suresh Kumar Madhuri, P. Shyamala Atchana, Venu Gopal Penmetsa, Gopala Krishnam Raju Bandaru, Venkata Naga Rani Sastry Eemani, V.R.J. Department of Computer Science and Engineering Vishnu Institute of Technology Bhimavaram India

ISBN: (纸本)9783031770807

The Dynamic Emotion-Adaptive Attention Mechanism (DEAAM) offers a groundbreaking framework for analyzing emotions in real-time video streams, leveraging a state-of-the-art convolution neural network (CNN) for rapid and accurate emotion detection. By integrating an adaptive attention mechanism, DEAAM dynamically adjusts video sampling rates and focuses on areas of emotional intensity, optimizing computational resources for the most expressive moments. This system intricately combines facial landmark detection with saliency mapping to pinpoint critical expressive features, enhancing the depth and precision of the analysis. Furthermore, DEAAM incorporates temporal emotional coherence tracking, utilizing advanced recurrent neural networks to capture the evolution of emotional states, adding a rich contextual layer to the emotion recognition process. This comprehensive approach not only increases the accuracy of emotion analysis but also ensures efficiency by focusing on key emotional expressions. Ideal for applications in virtual communication, mental health assessment, and any domain requiring nuanced emotion recognition, DEAAM sets a new standard in empathetic technology, offering a sophisticated, contextually aware system for extracting real-time emotional insights from video feeds. © ICST institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Driven Academic Learning Record Management in Higher Education: A Comprehensive Review of Methodologies, Applications, Benefits, and Challenges

引用

SN computer Science 2025年第5期6卷 1-33页

作者： Chaudhari, Sheetal Shirole, Mahesh Computer Science and Engineering Department Sardar Patel Institute of Technology Andheri Maharashtra Mumbai 400058 India Computer Engineering and Information Technology Department Veermata Jijabai Technological Institute Matunga Maharashtra Mumbai 400031 India

Blockchain technology has the potential to revolutionize the education sector by improving the legitimacy and security of academic procedures. The academic learning record management records the learner’s academic qualifications and achievements. Keeping track of higher education academic learning records is essential to assess students’ credentials and advance their careers. The COVID-19 outbreak highlighted the need for flexible and collaborative learning systems. However, the processes of recording credit accumulation, verification, and transfer are complicated by the disparate credit schemes found in different universities. This creates the need for an academic credit management system. Secure learning record management is necessary because validating the professional and academic accomplishments listed on the resumé currently poses a challenge. Blockchain can remedy this scenario by guaranteeing data privacy, reducing the possibility of hacking, and offering transparent, traceable academic credentials as well as verification of other achievements. Despite these benefits, challenges are still associated with implementing blockchain in academic learning record management. These include handling multiple credentials with a unique identity, absence of smart contracts, on-chain and centralized storage, scalability problems, transaction costs, restricted control over student data, and inadequate student data recording standards. The main objective of this review is to examine recent studies on blockchain-driven academic learning record management by categorizing them into learning record management and academic credit management. This paper identifies research gaps and suggests further studies and practical applications to enhance transparency, efficiency, and trust in the education system. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Academic bank of credits Academic credit management Blockchain Education Learning record management NEP 2020

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Air Pollution Monitoring and Forecasting

Machine Learning-Based Air Pollution Monitoring and Forecast...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： M, Naga Ravindra Babu Durga Satish, M. Prasanthi, B.V. Jagadeesh, S.V.V.D. Janardhana Naidu, J.N.S.S. Pradeep, Immidi Kali Department of Computer Science & Engineering Vishnu Institute of Technology Bhimavaram India

ISBN: (纸本)9783031513374

Today, the governments of developing countries are focusing more on air pollution. Air pollution occurs because of factors like fuel use in vehicles such as private transport, industries, and, more importantly, the burning of waste like plastic and grass. These are a few of the elements that contribute to air pollution. All of these factors have an impact on air quality. It can be calculated or determined by using PM2.5 and other variables. If this level is high, then it may be a serious problem for people’s health. To control air pollution, continuous pollution monitoring is required. Here, different machine learning models like linear regression, decision tree classifiers, random forest classifiers, and KNN classifiers are used to detect whether the sample of air is polluted or not. On the basis of previous readings of PM2.5, NH3, CO, NO, NOx, and NO2, SO2 is used to predict the future values of the AQI. By collecting datasets of the daily atmospheric conditions of a specific city or town, this system is able to predict the PM2.5 level and also detect the air pollution status. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Air quality

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：