检索结果-内蒙古大学图书馆

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Singh, Damini Agarwal, Khyati Marwaha, Mansha Mishra, Neha Pathak, Disha Mohini Abes Engineering College Department of Computer Science India

ISBN: (纸本)9798350350357

The traditional system of issue reporting has heavily relied on manual processes that require users to register their complaints with the authorities. This method is time-consuming and often results in inefficiencies due to the lack of a centralized and transparent mechanism. Our idea revolutionizes the traditional approach by employing a cutting-edge solution that grants users the ability to report and track issues directly and effectively, paving the way for a new era of seamless and transparent issue reporting. The latest technological advancements encourage the convergence of various technologies, seamlessly integrating application development, machine learning features, and cloud computing. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Ingredient Recognition and Recipe Suggestion using computer Vision and Predictive Modeling 8

Cross-Modal Ingredient Recognition and Recipe Suggestion usi...

引用

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

作者： Sanin Zulphi, M. Muzzammil Razin, P.A. Rahul Krishna, K.R. Ramasamy, Gobi Department of Computer Science Karnataka Bengaluru560029 India

ISBN: (纸本)9798331505462

This paper is focused on the development of a novel system known as 'IngredEye.' It involves various approaches that can be grouped into categories, such as computer vision, including YOLOv8, a KNN prediction model, and a Flutter framework that hosts all of them in a mobile application environment. Previous studies have analyzed the application of computer vision and OpenCV recognition in cooking and proved that such approaches could enhance the level of convenience in the culinary field. This paper addresses issues like changes in lighting, occlusions, and other factors that have to be solved by the algorithms envisaged for real applications. The objective of this paper solely relies on integrating the OpenCV object detection method with comprehensive machine learning techniques specialized for the culinary field. Presenting the end-user with recipe recommendations based on the visual input they have given. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Bagging Classifiers Between Multi-Core And Single-Core Processors Using Python Multiprocessing 2

Performance Comparison of Bagging Classifiers Between Multi-...

引用

2nd IEEE International Conference on Advancements and Key Challenges in Green Energy and Computing, AKGEC 2024

作者： Rawat, Aman Krishna, Charu Kumar, Divya Mnnit Allahabad Computer Science Department Prayagraj India

ISBN: (纸本)9798350390179

In recent years, the demand for efficient and scalable machine learning algorithms has surged. Bagging (Bootstrap Aggregating) stands out as a widely used ensemble technique that combines multiple base classifiers to enhance predictive accuracy and mitigate over fitting. However, when implementing bagging classifiers in Python, a crucial consideration lies in their effective utilization of multi-core processors. Python, as a language, faces parallelism limitations due to the Global Interpreter Lock (GIL) present in its C implementation (cPython). The GIL restricts Python threads from fully exploiting multiple CPU cores, thereby limiting their concurrency. Consequently, relying solely on regular threads for concurrency would not fully harness the potential of multi-core processors. Python, as a language, faces parallelism limitations due to the Global Interpreter Lock (GIL) present in its C implementation (cPython). The GIL restricts Python threads from fully exploiting multiple CPU cores, thereby limiting their concurrency. Consequently, relying solely on regular threads for concurrency would not fully harness the potential of multi-core processors. To overcome this limitation, we recommend leveraging Python's multiprocessing module. Unlike threads, which share the same memory space and are subject to the GIL, multiprocessing creates separate processes, each with its own Python interpreter instance. As a result, these processes can run in parallel, effectively utilizing multiple CPU cores. Our study delves into the performance comparison of bagging classifiers on multi-core processors versus single-core using Python multiprocessing. Our experiments reveal that multiprocessing significantly improves execution time, particularly for CPU-bound tasks. By leveraging multiple cores, bagging classifiers can better generalize to unseen data and achieve enhanced predictive accuracy. © 2024 IEEE.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

Real-time violence detection and localization through subgroup analysis

引用

Multimedia Tools and Applications 2025年第7期84卷 3793-3807页

作者： Veltmeijer, Emmeke Franken, Morris Gerritsen, Charlotte Department of Computer Science Vrije Universiteit Amsterdam De Boelelaan 1111 Amsterdam1081 HV Netherlands Amsterdam Netherlands

In an era of rapid technological advancements, computer systems play a crucial role in early Violence Detection (VD) and localization, which is critical for timely human intervention. However, existing VD methods often fall short, lacking applicability to surveillance data, and failing to address the localization and social dimension of violent events. To address these shortcomings, we propose a novel approach to integrate subgroups into VD. Our method recognizes and tracks multiple subgroups across frames, providing an additional layer of information in VD. This enables the system to not only detect violence at video-level, but also to identify the groups involved. This adaptable add-on module can enhance the applicability of existing models and algorithms. Through extensive experiments on the SCFD and RWF-2000 surveillance datasets, we find that our approach improves social awareness in real-time VD by localizing the people involved in an act of violence. The system offers a small performance boost on the SCFD dataset and maintains performance on RWF-2000, reaching 91.3% and 87.2% accuracy respectively, demonstrating its practical utility while performing close to state-of-the-art methods. Furthermore, our efficient method generalizes well to unseen datasets, marking a promising advance in early VD. © The Author(s) 2024.

关键词： Localization Subgroup analysis Surveillance data Violence detection

来源：评论

学校读者我要写书评

暂无评论

Detection & Mitigation of DDoS Attacks Using Deep Learning Algorithms 1

Detection & Mitigation of DDoS Attacks Using Deep Learning A...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Sanjeev, Dyuthi Mokashi, Bhargavi PES University Department of Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350355611

This paper demonstrates how deep learning algorithms detect and mitigate distributed denial of service (DDoS) threats. DDoS attacks jeopardize network security, causing substantial disruptions and economic harm. A major focus of this project is to improve detection accuracy and efficiency by using advanced techniques and architectures within deep learning. By examining the specific properties of network traffic data, the system may more efficiently detect illegitimate activity. These are achieved through state-of-the-art, very complex neural network methods: Artificial Neural Networks and a hybrid model entailing Convolutional Neural Networks with Gated Recurrent Units. The system with anomalies detection method from unsupervised learning is more robust to zero-day attacks because it can discover even new attack patterns. As cyber-attacks and online risks are evolving with time, this approach will be a better way to implement network infrastructure. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Image Quality Improvement and Reduction of Parameters by Utilizing Learning-based Noise Reduction Method for Surveillance Camera Images 24

Image Quality Improvement and Reduction of Parameters by Uti...

引用

6th International Conference on Intelligent Medicine and Image Processing, IMIP 2024

作者： Goto, Tomio Department of Computer Science Nagoya Institute of Technology Japan

ISBN: (纸本)9798400710032

It is well known that video images captured by in-vehicle cameras and surveillance cameras are degraded due to noise introduced by their shooting environments. In this paper, we remove such noise using a learning method to improve the image quality. Furthermore, we propose a practical method for real-time processing by making the process lighter and faster. In order to make practical use of denoising techniques, it is necessary to develop lightweight models with high denoising performance. Experimental results show the effectiveness of our proposed method. © 2024 ACM.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy in Breast Ultrasound Imaging through Deep Learning and Image Augmentation Techniques 2

Enhancing Diagnostic Accuracy in Breast Ultrasound Imaging t...

引用

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

作者： Mahesh, R.T. Department of Computer Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798331534950

This study investigates the application of deep learning models, specifically EfficientNet-B7, combined with advanced image augmentation strategies to improve the diagnostic accuracy of breast ultrasound image classification. The research utilizes a comprehensive dataset of breast ultrasound images labelled as benign, malignant, and normal, supplemented by corresponding masks to highlight areas of interest. By applying image changes such as Random Horizontal Flip, Random Rotation, and Color Jitter, the study intends to address class imbalances and boost the model's generalizability. The EfficientNet-B7 model, fine-tuned on the expanded dataset, attained a classification accuracy of 99% with a precision of 99%, recall of 99%, and F1-score of 99%, demonstrating a considerable improvement in recognizing various circumstances. These metrics underscore the model's effectiveness in minimizing diagnostic errors, crucial for clinical applications. This research highlights the potential of combining high-capacity neural networks with targeted image augmentations to improve outcomes in medical imaging diagnostics. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

SAFLEX: SELF-ADAPTIVE AUGMENTATION VIA FEATURE LABEL EXTRAPOLATION 12

SAFLEX: SELF-ADAPTIVE AUGMENTATION VIA FEATURE LABEL EXTRAPO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ding, Mucong An, Bang Xu, Yuancheng Satheesh, Anirudh Huang, Furong Department of Computer Science University of Maryland United States

Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data. While traditional methods, such as hand-crafted augmentations, are effective but limited in scope, modern, adaptable techniques often come at the cost of computational complexity and are hard to fit into existing processes. In this work, we unveil an efficient approach that universally enhances existing data augmentation techniques by enabling their adaptation and refinement, thereby providing a significant and comprehensive improvement across all existing methods. We present SAFLEX (Self-Adaptive Augmentation via Feature Label EXtrapolation), an approach that utilizes an efficient bilevel optimization to learn the sample weights and soft labels of augmented samples. This is applicable to augmentations from any source, seamlessly integrating with existing upstream augmentation pipelines. Remarkably, SAFLEX effectively reduces the noise and label errors of the upstream augmentation pipeline with a marginal computational cost. As a versatile module, SAFLEX excels across diverse datasets, including natural, medical images, and tabular data, showcasing its prowess in few-shot learning and out-of-distribution generalization. SAFLEX seamlessly integrates with common augmentation strategies like RandAug and CutMix, as well as augmentations from large pre-trained generative models like stable diffusion. It is also compatible with contrastive learning frameworks, such as fine-tuning CLIP. Our findings highlight the potential to adapt existing augmentation pipelines for new data types and tasks, signaling a move towards more adaptable and resilient training frameworks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Prediction through ML And DL Models: A Survey 8

Epileptic Seizure Prediction through ML And DL Models: A Sur...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Viswanath, J. Annamalai, S. Ramesh, S. Department of Computer Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350367904

Epileptic seizures are unpredictable and pose significant risks to individuals affected by epilepsy. Electroencephalogram (EEG) signals offer a promising avenue for early seizure prediction, enabling timely intervention and improved quality of life for patients. This survey paper provides a comprehensive review of Deep learning (DL) and Machine learning (ML) learning techniques applied to EEG-based epileptic seizure prediction. It covers traditional ML models, advanced DL architectures, and optimization algorithms, highlighting their effectiveness and limitations. Additionally, the paper discusses feature extraction methods, signal processing techniques, and evaluation metrics used in this domain. Real-world applications, current challenges, and future research directions are explored to offer a holistic view of the field. By examining state-of-the-art methods, this survey aims to provide valuable insights into the development of robust, real-time seizure prediction systems, fostering advancements in clinical applications and patient care. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Learning from Streaming Data when Users Choose 41

Learning from Streaming Data when Users Choose

引用

41st International Conference on Machine Learning, ICML 2024

作者： Su, Jinyan Dean, Sarah Department of Computer Science Cornell University United States

In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers’ models influence which service the user will choose at the next time step, and the user’s choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data. Copyright 2024 by the author(s)

关键词：

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：