检索结果-内蒙古大学图书馆

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

作者： Neeraj Nandal, Poonam Department of Computer Science & Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad India

ISBN: (纸本)9798331530389

A key aspect of artificial intelligence is continual learning. The capacity of a model to incrementally learn from a new task and adapt to it without losing the previous knowledge. A fundamental challenge that comes to successful continual learning is catastrophic forgetting;while learning a new task the model forgets the previously learned tasks. Various approaches to mitigate forgetting and enhance continual learning have been discussed across benchmark datasets such as MNIST, CIFAR-10, and Permuted MNIST. we focus mainly on replay, regularization, and modular architecture-based methods to prevent forgetting. Regularization methods penalize the significant change in parameters during the learning of new tasks while maintaining crucial parameters of previously completed tasks. Replay-based methods store samples of earlier tasks in explicit memory or generate pseudo-samples with the help of generative models. Modular architecture-based methods partition the neural architecture into task-specific modules to prevent interference between tasks, to effectively address catastrophic forgetting. This paper presents a comparative study of the key continual learning methods that reduce catastrophic forgetting. The findings demonstrate the trade-offs between different methods. We examine the efficiency and effectiveness of each method and propose a hybrid technique to prevent catastrophic forgetting. Our comparative analysis emphasizes the significance of choosing the best method depending on the specific requirement of the learning environment, the task complexity, and resource constraints. © 2025 IEEE.

关键词： artificial intelligence catastrophic forgetting continual learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of YOLO versions for Real-time Pothole Detection 16

Performance Analysis of YOLO versions for Real-time Pothole ...

引用

16th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Fortin, Leonhel V. Llantos, Orven E. Department of Computer Applications Philippines Department of Computer Science Philippines College of Computer Studies MSU-Iligan Institute of Technology Tibanga Iligan City9200 Philippines

The integration of lightweight computer vision models emerges as a promising solution for automating road inspection processes. The evolution of YOLO architectures, particularly their lightweight variants, enables significant improvements in both detection accuracy and computational efficiency. Recent iterations through YOLOv9-tiny, YOLOv10-nano, and YOLOv11-nano enhance real-time performance capabilities while maintaining acceptable accuracy through optimized network architectures. The implementation of these lightweight YOLO variants presents a compelling approach to automated pothole detection. Previous studies utilizing limited datasets of approximately 1,388 images established initial feasibility but left significant room for improvement in model robustness and generalization. This research addresses these limitations by employing an expanded dataset of 16,054 images, encompassing diverse environmental conditions and road surface characteristics. The comparative analysis establishes new benchmarks for pothole detection in resource-constrained environments, demonstrating the viability of nano/tiny models for practical applications. © 2025 Elsevier B.V.. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Age-of-Information-Aware Federated Learning

引用

Journal of computer science & Technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of Information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Depression Detection System: Integrating Multimodal Analysis for Early Diagnosis

AI-Enhanced Depression Detection System: Integrating Multimo...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Patidar, Aditya Gore, Dhruv Inje, Bhushan Alhat, Apurva Department of Computer Science SVKM's Narsee Monjee Institute of Management Studies Maharashtra Shirpur India

ISBN: (纸本)9798331512965

Depression is a prevalent mental health condition affecting millions globally, often going undiagnosed due to social stigma and limited accessibility to healthcare. This study presents an innovative AI-enhanced system for early depression detection, utilizing multimodal analysis integrating natural language processing (NLP) and patient health metrics. Two machine learning models form the system's core: a text classification model leveraging logistic regression to analyze user inputs and predict emotional tone and a health-data-based model that incorporates factors such as BMI, blood features, and comorbid conditions for comprehensive evaluation. The models were integrated into a web application offering a dual advantage of accurate screening and accessible mental health recommendations. Results demonstrated high efficacy with classification accuracy exceeding 91% across models, underscoring its potential to transform early-stage mental health interventions. Future enhancements include adopting advanced deep learning frameworks and expanding multilingual capabilities to broaden accessibility. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Empowering Equality: Sparking Brilliance in Stem 1

Empowering Equality: Sparking Brilliance in Stem

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Puri, Vaibhav Singh, Tushar Kumar Gupta, Avni Singh, Meeta Manav Rachna International Institute of Reasearch & Studies Department of Computer Science & Engineering Faridabad India

ISBN: (纸本)9798350356816

An online education-based platform providing free courses, community support and mentoring facilities for women and girls to deal with the gap in STEM. It deals with empowering women and girls by introducing the platform that helps them gain confidence, self-esteem and opportunities in STEM careers. It motivates inclusive education, which is in accordance with SDG 4: quality education. By addressing the gender gap in STEM through education and mentoring programs, it is also related with SDG 5: Gender equality, which helps to eliminate gender disparities. The Platform supports not only empowering women, but also improving the society. A brighter and a more beautiful future is continued by reducing the gender gap issues in STEM for all. © 2024 IEEE.

关键词： Mentorship programs SDG4 SDG5 STEM careers Women and Girls

来源：评论

学校读者我要写书评

暂无评论

A Survey and Experimental Review on Data Distribution Strategies for Parallel Spatial Clustering Algorithms

引用

Journal of computer science & Technology 2024年第3期39卷 610-636页

作者： Jagat Sesh Challa Navneet Goyal Amogh Sharma Nikhil Sreekumar Sundar Balasubramaniam Poonam Goyal Advanced Data Analytics and Parallel Technologies Laboratory Birla Institute of Technology and Science Pilani 333031India Uber New York 11101U.S.A. Computer Science and Engineering Department University of MinnesotaMinneapolis 55455U.S.A.

The advent of Big Data has led to the rapid growth in the usage of parallel clustering algorithms that work over distributed computing frameworks such as MPI,MapReduce,and *** important step for any parallel clustering algorithm is the distribution of data amongst the cluster *** step governs the methodology and performance of the entire *** typically use random,or a spatial/geometric distribution strategy like kd-tree based partitioning and grid-based partitioning,as per the requirements of the ***,these strategies are generic and are not tailor-made for any specific parallel clustering *** this paper,we give a very comprehensive literature survey of MPI-based parallel clustering algorithms with special reference to the specific data distribution strategies they *** also propose three new data distribution strategies namely Parameterized Dimensional Split for parallel density-based clustering algorithms like DBSCAN and OPTICS,Cell-Based Dimensional Split for dGridSLINK,which is a grid-based hierarchical clustering algorithm that exhibits efficiency for disjoint spatial distribution,and Projection-Based Split,which is a generic distribution *** of these preserve spatial locality,achieve disjoint partitioning,and ensure good data load *** experimental analysis shows the benefits of using the proposed data distribution strategies for algorithms they are designed for,based on which we give appropriate recommendations for their usage.

关键词： parallel data mining data distribution parallel clustering spatial locality preservation

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Challenges in Information Retrieval from Online Social Networking Platforms 3rd

A Systematic Review of Challenges in Information Retrieval f...

引用

3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023

作者： Chowdhary, Mohit Chahal, Poonam Department of Computer Science and Engineering Manav Rachna International Institute of Research & Studies Faridabad India

ISBN: (纸本)9789819725076

With evolution of massive advancements in technology the World Wide Web (WWW) has become the significant source of short and crisp textual messages. The emergence of short textual messages in internet are called as micro-text are due to existence of various blogging and social networking sites like Facebook, twitter, Instagram etc. These micro texts are highly important as they contain an opinion on a wide range of events pertaining to social issues, individual, products, organisations etc. The quality of text available online is highly variable as it includes the semantic information context and temporal words. Due to this there exist many inconsistencies in the text available online and further poses numerous challenges in sentiment analysis. The online text is the kind of unstructured data. In this paper various challenges and issues for sentiment analysis for online text are discussed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Detection analysis of malicious cyber attacks using machine learning algorithms

引用

Materials Today: Proceedings 2022年 68卷 26-34页

作者： Karthika, R.A. Maheswari, M. Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai India Department of Computational Intelligence SRM Institute of Science and Technology KTR Chennai 603203 India

Cybersecurity is the practice of safeguarding information and the systems that store or process information. Cybersecurity violations are the foremost persecution instigated by cyber attackers through one or more systems on single or several networks or systems. This kind of cyber threats can ruthlessly trigger data loss or theft besides halting the network systems partially or fully. Among various cybersecurity attacks, the Denial of Service (DoS) attack is one of the most dominant hacking modus operandi over the internet. The hackers use the weapons at their disposal to disrupt traffic in and around the network surroundings or the target system by bombarding it with a lot of malicious requests. This paper introduced machine learning algorithms such as Gaussian Naïve Bayes and Nearest Centroid to identify the attacks via classifying the given dataset into normal and malicious traffic. Furthermore, metrics such as accuracy, f-score, FNR, precision, and prediction time etc., were calculated to identify the best performing model. © 2022

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wildlife Monitoring Through Infrared Imaging: A Deep Learning Approach for Improved Animal Region Segmentation and Species Identification

引用

Journal of Harbin institute of Technology(New series) 2024年

作者： V Janani C Shanthi Department of Computer Science， School of Computing Sciences， Vels Institute of Science Technology and Advanced Studies

Infrared imaging has proven to be a powerful tool in various fields， with particular significance in wildlife monitoring. In this paper， we present an extension of our previous research， focusing on advancing the segmentation of animal regions in enhanced infrared images and expanding the scope to include species identification. Our proposed methodology builds upon the success of the R-CNN (Region-based Convolutional Neural Network) object detection to improve the accuracy and robustness of animal region segmentation， while simultaneously extending our model’s capabilities to identify and classify the species within those regions. By fine-tuning the R-CNN model on a larger dataset that includes annotated infrared images and species labels， we enhance its capacity to not only accurately segment animal regions but also classify them into specific species categories. To assess the performance of our extended model， we employ a comprehensive set of evaluation metrics， including pixel-based metrics like Intersection over Union (IoU)， as well as species classification accuracy. Our results demonstrate significant improvements in both region segmentation accuracy and species identification compared to our previous work and existing methods. This research showcases the potential of deep learning techniques， combined with transfer learning， to advance wildlife monitoring applications using infrared imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Models for Machine-Generated Text Detection Using Transformer-Based Models

Leveraging Deep Learning Models for Machine-Generated Text D...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Suthanthiradevi, P. Revathy, G. Rejini, K. Muthu Lakshmi, V. School of Computing Srm institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering Chennai117 India Amrita college of Engineering and Technology Department of Computer Science Engineering Nagercoil India St. Joseph's College of Engineering Department of Computer Science and Engineering OMR Chennai India

ISBN: (纸本)9798331543617

GPT is a large language model (LLM) derived from natural language processing that can generate a human-like text using machine learning. However, these models raise questions about authenticity and reliability of material, particularly in fields such as journalism, social media, and academia, despite their usefulness for automating text-based tasks. Detecting machine-generated text is thus an important difficulty in ensuring content integrity. This study investigates the use of huge language models as a technique for recognizing machine-generated material. The author proposes a comprehensive detection model by evaluating the language patterns, syntactic structures, and stylistic traits that separate AI-generated literature from human writing. In addition, this research investigate the possibilities of fine-tuning models designed expressly for text identification tasks and evaluate their performance using LLM - Detect AI Generated Text datasets. In digital ecosystems, LLMs are effective at detecting AI-generated text, providing a novel approach for content moderation, academic integrity checks, and synthetic media detection. An increasingly AI-powered future will require a model that can discriminate between human and machine-generated writing in real-time. According to experimental findings, the CNN architecture's design combined with the use of DistilBERT embeddings allows for the effective and efficient classification of AI generated text data, achieving an exceptional 98% accuracy rate. © 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

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：