检索结果-内蒙古大学图书馆

2024 International Research Conference on Smart computing and Systems engineering, SCSE 2024

作者： Mahinsa Athree, P. Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Faculty of Graduate Studies and Research Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Dept. of Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350375688

Usually, only time and distance are considered when choosing a route, not the risk involved. Due to not taking the danger into account before the trip, we might have to experience numerous problems and risks. As a result, there may be dangerous situations for the driver and passengers and time and fuel wastage. Thus, the issue is how to evaluate the road while choosing the route before using it and What elements are crucial to take into account while evaluating a route's issues. This project aims to develop a system to evaluate risk before a vehicle enters a dangerous area and predict the best path by evaluating aspects of roads including accidents, road repairs, and road blockers. Image Classification is used to detect road repairs and blockers. Federated Learning will be used to improve the accuracy of the Road blocker detector. Here, Clients will train locally using private data, send their optimized parameters to the central server, and then aggregate those trained parameters to produce a global model. This process will be continued until the system has a trained model that is ideal for predicting roadblocks. YOLOV7 object detector will be used to detect vehicle collisions and accidents in real-time. Finally, Federated Learning will be used to notify users about detected incidents and event details will be marked in a Google map which is running on a Flask application. Using the Blocker map, drivers can decide which route is more suitable based on the proposed system's detections and blocker details. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Phase-Only Synthesis of Pencil Beams via Sequential Quadratic Programming

Phase-Only Synthesis of Pencil Beams via Sequential Quadrati...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Mladen Vucic Katarina Vodvarka Maja Jurisic Bellotti Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

Phase-only adjustment of antenna arrays simplifies design of their feeding networks and maximizes energy efficiency. However, optimization-based synthesis of the corresponding beam patterns leads to nonconvex problems. Various techniques for solving these problems have been considered. In this paper, we present an approach based on sequential quadratic programming. We focus on phase-only design of pencil beams with the sidelobes optimum in minimax sense. In this context, we consider beampatterns without and with null regions, having specified coefficients' magnitudes and arbitrary, even-symmetric, or odd-symmetric phases.

关键词： Phased arrays Hands Europe Antennas and propagation Antenna feeds Energy efficiency Quadratic programming Optimization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Distributed Denial-of-Services Attacks Detection and Mitigation Testbed for SDN-Enabled IoT Devices 13

Machine Learning Based Distributed Denial-of-Services Attack...

引用

13th International Conference on computing Communication and Networking Technologies, ICCCNT 2022

作者： Sritharan, Kiruthikan Elagumeeharan, Rojeemeeharan Nakkeeran, Senthuran Mohamed, Agaar Ganegoda, Binura Yapa, Kanishka Department of Computer Systems Engineering Faculty of Computing SLIIT Colombo Sri Lanka

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

One of the most important innovations in contemporary technology since the 1980s is the Internet of Things [1]. One of the most popular current technologies today is the Internet of Things (IoT), which enables various devices to communicate with one another, exchange data, and be controlled by other devices that have been granted authentication. As these sophisticated technologies were created and developed, cyber threats against them also grew significantly. Since devices may be controlled if a network or a specific device is penetrated by an attacker, there are particularly significant hazards to the IoT environment. The downside is that because IoT devices are connected to local networks, if an attacker gained access to a weak device, the entire local network will be compromised, exposing important data and disrupting operations. One of the treatments for DDoS attacks on IoT devices is the topic of our research. To be more precise, our research suggests an Automated IoT Vulnerability Testbed for DDoS Attacks in an SDN environment, constructed using the Python programming language and numerous machine learning techniques. The network traffic that is coming to the IoT devices will be analyzed as part of our suggested solution, which will help to thwart successful DDoS attacks. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Exploring Pre-Trained Model Potential for Reflective Vest Real Time Detection With YOLOv8 Models 3

Exploring Pre-Trained Model Potential for Reflective Vest Re...

引用

3rd International Conference on Applied Artificial Intelligence and computing, ICAAIC 2024

作者： Milanovic, Aleksandar Jovanovic, Luka Zivkovic, Miodrag Bacanin, Nebojsa Cajic, Miroslav Antonijevic, Milos Singidunum University Department of Informatics and Computing Beograd Serbia Singidunum University Faculty of Technical Sciences Beograd Serbia University 'Union Nikola Tesla' Faculty of Information Technology and Engineering Cara Dusana Beograd Serbia

ISBN: (纸本)9798350375190

Workplace safety is crucial across all industries, particularly in dynamic environments like construction and road infrastructure. The application of computer vision holds promise in enhancing safety measures by automatically detecting hazards and identifying risks in real-time. Despite its potential, computer vision's role in workplace safety remains under-explored. This study investigates the effectiveness of three pre-trained versions of the YOLOv8 model in detecting reflective vests, a critical safety element, using real-world data. The YOLOv8 model offers fast and accurate recognition, enabling efficient monitoring of work activities and timely alerts for safety breaches. Results demonstrate the model's capability in improving workplace safety while maintaining manageable computational demands. This research underscores the significance of leveraging advanced technological solutions like CV to mitigate risks and ensure the well-being of employees in hazardous work environments. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

Enhancing Gaussian Splatting SLAM with Feature-Based Tracking

Enhancing Gaussian Splatting SLAM with Feature-Based Trackin...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Muhammad Awais Karlo Koledić Luka Petrović Ivan Marković Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

Accurate localization and scene reconstruction are essential for the autonomous navigation of mobile agents. Simultaneous Localization and Mapping (SLAM) algorithms address both challenges by formulating a unified optimization problem, offering an integrated solution to both objectives. Recent advances in learning-based scene understanding have significantly improved accuracy and robustness, particularly in adverse scenarios that are troublesome for traditional geometric methods. However, generating an accurate dense scene reconstruction remains an open challenge, largely due to the complexity of the optimization problem, making it unsuitable for real-time requirements on resource-constrained devices. Novel advances in 3D reconstruction such as implicit representations and Gaussian Splatting present an enticing formulation enabling offline reconstruction of large-scale scenes. While these approaches have been successfully adapted for online incremental reconstruction, particularly through Gaussian Splatting SLAM methods, they are hindered by significant computational complexity and convergence challenges due to the non-convex nature of photometric optimization. In this work we rethink this approach by combining the strengths of traditional feature-based methods with innovative reconstruction capability of Gaussian splatting. Specifically, we integrate feature-based pose estimation, relocalization and loop closure with 3D Gaussian-based scene reconstruction. This results in state-of-the-art tracking and mapping performance on the EuRoC and TUM datasets, while significantly reducing convergence iterations and improvina real-time performance.

关键词： Location awareness Simultaneous localization and mapping Three-dimensional displays Accuracy Pose estimation Mobile agents Real-time systems Robustness Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence to evaluate the impact of urban green and blue spaces on chlorophyll-a concentrations

引用

Environmental Science and Pollution Research 2025年 1-13页

作者： Fonseka, Panchali U. Mampitiya, Lakindu Rathnayake, Namal Zhang, Hongsheng Samarasuriya, Chaminda Premasiri, Ranjith Rathnayake, Upaka Department of Earth Resource Engineering Faculty of the Engineering University of Moratuwa Katubedda Moratuwa10400 Sri Lanka Arthur C Clarke Institute for Modern Technologies Katubedda Moratuwa10400 Sri Lanka Water Resources Management and Soft Computing Research Laboratory Athurugiriya Millennium City10150 Sri Lanka Department of Civil Engineering Faculty of Engineering The University of Tokyo 1 Chome-1-1 Yayoi Bunkyo City Tokyo113-8656 Japan Department of Geography Centennial Campus The University of Hong Kong Pokfulam Road Hong Kong Department of Civil Engineering and Construction Faculty of Engineering and Design Atlantic Technological University SligoF91 YW50 Ireland

Urbanization is accelerating rapidly, highlighting the critical role of aligning with sustainable development goals, urban green and blue spaces (UGS and UBS). These spaces play a crucial role in enhancing the health and well-being of city residents in terms of ecology. Acknowledging the importance of urban ecology, this study utilizes Sentinel-2A data and support vector machine classification, aimed to identify UGS and UBS. To examine the connections between UGS and UBS, specific indices, spectral bands, and textures were calculated. Additionally, the concentration of chlorophyll, a vital indicator of ecological health, was assessed using three indices. Structural equation modeling was employed to elucidate the relationship between UGS and UBS and their impact on chlorophyll concentration for the years 2017 and 2023. In the 2017 model, UGS exhibited a positive path coefficient (0.25) with chlorophyll-a, indicating that an increase in UGS is associated with an increase in chlorophyll levels. Conversely, in 2023, the path coefficient turned negative (− 0.83), presenting a stark contrast to the 2017 model. This shift suggests potential environmental or urban development changes, such as alterations in the quality or type of urban green spaces, potentially including more non-native or ornamental plants that contribute less to overall chlorophyll levels. UGS can be subjected to pollution, soil compaction, and other stressors that reduce plant health. Similarly, the UBS showed an increase in its path coefficient from − 0.99 in 2017 to − 1.8 in 2023, suggesting improvements such as cleaner water or urban planning strategies aimed at reducing water pollution. The consistent negative relationship across both years suggests that urban water bodies are not contributing to Chl levels due to complex interactions of water bodies with their urban surroundings. However, further research is essential to delve into these dynamics and comprehend the implications for urban ecological

关键词： Green development

来源：评论

学校读者我要写书评

暂无评论

Bidirectionalization For The Common People

arXiv

引用

arXiv 2025年

作者： Dončević, Juraj Brčić, Mario Mlinarić, Danijel University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

This paper presents an innovative approach to applying bidirectional transformations (BX) in practice. To introduce BX to a wider audience of technologists, engineers, and researchers, we have chosen to use C# to develop Bifrons - a library of BX lenses that replaces domain-specific programming languages (DSL) in practical use. The proposed approach simplifies the implementation effort for two-way transformations by using simple symmetric lenses as the initial design pattern. It ensures correctness within reason by providing a simple lens-testing framework. We demonstrate the usability of BX lenses in a realistic scenario by using Bifrons to perform a case study experiment synchronizing data from two structurally and technologically heterogeneous databases. Copyright © 2025, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Quantile-Based Maximum Likelihood Training for Outlier Detection 38

Quantile-Based Maximum Likelihood Training for Outlier Detec...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Taghikhah, Masoud Kumar, Nishant Šegvić, Siniša Eslami, Abouzar Gumhold, Stefan Faculty of Computer Science Technische Universität Dresden Dresden Germany Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Translational Research Lab Carl Zeiss Meditec AG Munich Germany

ISBN: (纸本)1577358872

Discriminative learning effectively predicts true object class for image classification. However, it often results in false positives for outliers, posing critical concerns in applications like autonomous driving and video surveillance systems. Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning. Furthermore, unsupervised generative modeling of inliers in pixel space has shown limited success for outlier detection. In this work, we introduce a quantile-based maximum likelihood objective for learning the inlier distribution to improve the outlier separation during inference. Our approach fits a normalizing flow to pre-trained discriminative features and detects the outliers according to the evaluated log-likelihood. The experimental evaluation demonstrates the effectiveness of our method as it surpasses the performance of the state-of-the-art unsupervised methods for outlier detection. The results are also competitive compared with a recent self-supervised approach for outlier detection. Our work allows to reduce dependency on well-sampled negative training data, which is especially important for domains like medical diagnostics or remote sensing. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Non-Foster Self-oscillating Single-loop Antenna - Experimental Investigation 16

Non-Foster Self-oscillating Single-loop Antenna - Experiment...

引用

16th International Congress on Artificial Materials for Novel Wave Phenomena, Metamaterials 2022

作者： Nozina, D. Cavlek, I. Zeljko, A. Krois, I. Hrabar, S. University of Zagreb Faculty of Electrical Engineering and Computing Unska 3 Zagreb Croatia

ISBN: (数字)9781665465847

ISBN: (纸本)9781665465847

Recent theoretical proposal of a self-oscillating single-loop non-Foster antenna is complemented by experimental verification. The measurements on scaled prototype (a loop smaller than λ/10, operating in 10-60 MHz RF regime) revealed self-oscillations tunable across 1:2.2 bandwidth. Such a loop is promising candidate for unit cell of future active metasurfaces. © 2022 IEEE.

关键词： Loop antennas

来源：评论

学校读者我要写书评

暂无评论

Enhancing Programming Education with Open-Source Generative AI Chatbots

Enhancing Programming Education with Open-Source Generative ...

引用

Proceedings of the International Convention MIPRO

作者： Antonia Šarčević Ivan Tomičić Andrija Merlin Marko Horvat Department of Applied Computing Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9798350382501

ISBN: (纸本)9798350382518

This paper describes the development of an Open-Source Generative AI Chatbot, utilizing free Large Language Models (LLM) to enrich the student learning experience for a university course in “Introduction to Programming”. The article aims to provide a step-by-step guide for selecting, fine-tuning, and evaluating available models. As a first step in choosing the appropriate LLM, which provides the most accurate responses while not requiring excessive computing power, the article will cover a discussion of the advantages and disadvantages of local vs. cloud-available models. After selecting a few promising models, the next stage includes fine-tuning LLMs to answer domain-specific questions using a dataset containing essential rules, guidelines, and explanatory content regarding the subject. The crucial aspect of selecting a model was evaluating answers, and in this context, both human and automatic evaluation techniques will be presented. Finally, it is possible to enhance the model performance and accuracy by incorporating Retrieval-Augmented Generation (RAG) techniques and exploring the influence of various factors, such as different vector databases, model temperatures, maximum token lengths, prompt templates, embeddings, repetition penalties, and chunking sizes. Our results show that chatbots have significant potential to improve academic support and learning efficiency, as well as personalized education in general.

关键词： Electric potential Accuracy Temperature Generative AI Computational modeling Education Chatbots

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：