检索结果-内蒙古大学图书馆

Integrating V2X solutions in intelligent green cities: an AI-driven point exchange system approach

Neural Computing and Applications 2025年

作者： Talaat, Fatma M. Shaban, Warda M. ZainEldin, Hanaa Badawy, Mahmoud Elhosseini, Mostafa Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Faculty of Computer Science & Engineering New Mansoura University Gamasa35712 Egypt Department of Communication and Electronics Engineering Nile Higher Institute for Engineering and Technology Mansoura Egypt Faculty of Artificial Intelligence and informatics Horus University New Damietta Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Computer Science and Information Department Applied College Taibah University Madinah42353 Saudi Arabia College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia

With rapid urbanization, smart cities have become essential for enhancing urban management and sustainability by integrating technological, social, and institutional innovations. Among these innovations, vehicle-to-everything (V2X) communications and electric vehicles (EVs) play a critical role in reducing carbon emissions and optimizing urban mobility. To address the existing gaps in holistic V2X integration, this paper presents a novel eco-assistive fog-based traffic management system (EAFTMS) that leverages a four-tier architecture (IoT, fog, cloud, and application) for scalable, real-time traffic optimization. A key innovation of this system is the AI-driven point exchange system (PES), designed to incentivize sustainable behaviors such as reducing unnecessary vehicle usage and promoting green lifestyle choices. Unlike conventional models, the proposed framework incorporates real-time behavioral monitoring, rewards-based sustainability programs, and V2X-enabled dynamic traffic control. Empirical validation demonstrates that EAFTMS outperforms existing models, including support vector regression (SVR), achieving a 30% reduction in latency, a 40% improvement in response time, a 25% increase in traffic flow efficiency, and a 35% reduction in CO2 emissions. These results highlight the framework’s potential to set new standards in intelligent green cities by offering scalable, practical, and environmentally impactful solutions to urban transportation challenges. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Vehicles with Yolo 22

Object Detection for Vehicles with Yolo

引用

2024 IEEE 22nd World Symposium on Applied Machine Intelligence and informatics, SAMI 2024

作者： Maleki, Pouria Ramazani, Abbas Khotanlou, Hassan Ojaghi, Sina Mousavi, Milad Kalinin, Alexey Mosavi, Amir Bu-Ali Sina University Department of Electrical Engineering Hamedan Iran Bu-Ali Sina University Department of Computer Engineering Hamedan Iran University of Tehran School of Computer and Electrical Engineering Tehran Iran K. N. Toosi University of Technology Tehran Iran Abylkas Saginov Karaganda Technical University Kazakhstan Obuda University John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

ISBN: (纸本)9798350317206

The rapid urban population growth has intensified the challenges associated with urban and suburban traffic, necessitating effective traffic control and management. The efficient movement of emergency vehicles, particularly ambulances and fire trucks, has emerged as a critical concern. This article presents the Vehicle Dataset, a comprehensive benchmark for object detection, encompassing seven vehicle classes, including cars, motorcycles, buses, trucks, vans, ambulances, and fire trucks. The dataset, includes 29,759 meticulously labeled images obtained from freely available online sources, enables the identification of traffic patterns through deep neural networks. Notably, the dataset emphasizes the facilitation of emergency vehicle movement. The Vehicle Dataset in this study is divided into three subsets, with 25,369 images assigned for training, 2,896 for validation, and 1,494 for testing. Through the utilization of the dataset, object detection algorithms based on YOLO versions 5, 6, and 7 have been trained. Remarkably, YOLO version 7 has yielded outstanding results, achieving a final precision of 85% and a mAP of 85% at an IoU threshold of 0.5. Moreover, at IoU thresholds ranging from 0.5 to 0.9, a mAP of 64% has been attained. The Vehicle Dataset represents significant resource for researchers and practitioners in the transportation and traffic management field. Its inclusion of emergency vehicles such as ambulances and fire trucks contribute to its unique value. This article presents a detailed exploration of the dataset, underscoring its significance in advancing object detection methodologies. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Study of the Relation Between Discharges, Froude Number, Bed Width in Dividing Open Channel Flows 5th

A Mathematical Study of the Relation Between Discharges, Fro...

引用

5th International Conference on Water Resources, ICWR 2021

作者： Harmizi, Puteri Nadia Shafiqah Zawawi, Iskandar Shah Mohd Haniffah, Mohd Ridza Mohd Khairudin, Taufiq Khairi Ahmad Aris, Hazleen Faculty of Computer and Mathematical Sciences Kompleks Al-Khawarizmi Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Department of Water and Environment Engineering School of Civil Engineering Faculty of Engineering Universiti Teknologi Malaysia Johor Johor Bahru81310 Malaysia Faculty of Science Universiti Teknologi Malaysia Johor Johor Bahru81310 Malaysia Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Selangor Kajang43000 Malaysia

ISBN: (纸本)9789811959462

Open-channel with branches makes the channel flow more complex and difficult to analyse due to the complex variables and a large number of geometric properties related to the junction. The aim of this paper is to employ the mathematical model to investigate the relationship between discharge, Froude number and bed width in the dividing open-channel flow. Several assumptions have been made and input values are taken from the literature to solve the proposed model. Results indicated that the highest discharge ratio is obtained when the dividing angle at channel 2 is The discharge ratio slightly increases as the Froude number decreases for all angles. However, the Froude number of subcritical flows had a significant effect on the bed width ratio. For angles 30°, 45°, 60° and 75°, the discharge ratio decreases when the bed width ratio increases, but it remains unchanged when the angle is 90°. In conclusion, there is a linear relationship between discharges, Froude number and bed width ratio at certain dividing angles. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Froude number

来源：评论

学校读者我要写书评

暂无评论

Towards Swarm Intelligence Ontology for Formal Description of Metaheuristics Algorithms 4

Towards Swarm Intelligence Ontology for Formal Description o...

引用

4th International Conference on Computing, Networking, Telecommunications and engineering Sciences Applications, CoNTESA 2023

作者： Tulicic, Domagoj Horvat, Marko Lovrencic, Sandra University of Applied Science in Information Technology Department of Computer System and Networks Zagreb Croatia University of Zagreb Faculty of Electrical Engineering and Computing Department of Applied Computing Zagreb Croatia University of Zagreb Faculty of Organization and Informatics Foundations of Information Sciences Department of Theoretical and Applied Varaždin Croatia

ISBN: (纸本)9798350382754

Swarm intelligence is a class of nature-inspired metaheuristic algorithms, that is specifically derived from biological systems in nature with an emphasis on their social interactions. These algorithms have been primarily developed to solve complex combinatorial optimization problems and are extremely popular among researchers in metaheuristic algorithms. This is evident from the numerous published scientific papers describing algorithms inspired by biological systems, ranging from insects such as ants and bees to the largest animals on the planet like whales. All these algorithms share some common concepts and relationships that can be explicitly identified, named, and formalized. These shared concepts and relationships can be organized and represented through the construction of an ontology. The goal of this paper is to present a formal ontology that standardizes vocabulary, as well as a set of rules enabling precise communication and reasoning about these algorithms. Ultimately, this will improve our understanding, analysis, research processes, and utilization of these computational approaches. © 2023 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Forwarding Strategy Performance using Interest Variation Scheme in Named Data Networking 8

Forwarding Strategy Performance using Interest Variation Sch...

引用

8th International Conference on Wireless and Telematics, ICWT 2022

作者： Ahdan, Syaiful Nurkahfi, Galih Nugraha Nurhayati, Ade Mayasari, Ratna Negara, Ridha Muldina Syambas, Nana Rachmana School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung40132 Indonesia Faculty of Engineering and Computer Science Universitas Teknokrat Indonesia Lampung35132 Indonesia Faculty of Engineering Institut Teknologi Telkom Jakarta Jakarta11710 Indonesia School of Electrical Engineering Telkom University Bandung Indonesia

ISBN: (数字)9781665451222

ISBN: (纸本)9781665451222

Named Data Networking (NDN) is a new paradigm for the future internet architecture where the NDN communication process is based on the name of the content, two types of packets in NDN namely Interest and data controlled by the recipient. Forwarding strategy is responsible for determining where the interest will be forwarded, because each different application will require different forwarding behavior, this study aims to determine the performance of the forwarding strategy in accordance with the required application, This study uses a broadcast forwarding and bestroute strategy approach with the study parameters of the cumulative delay distribution in the observation time interval based on the number of variations of interest, whether the difference between the forwarding strategy and the amount of interest can affect the delay, this study uses the NDNSim simulator to test and make several scenarios with changes in interest, the results obtained after analyzing the two strategies are that the broadcast strategy has a higher delay than the bestroute strategy, to find out the results in detail, this study also displays the output in graph. © 2022 IEEE.

关键词： Wireless communication Process control Telematics Delays Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

ChatGPT Code Detection: Techniques for Uncovering the Source of Code

arXiv

引用

arXiv 2024年

作者： Oedingen, Marc Engelhardt, Raphael C. Denz, Robin Hammer, Maximilian Konen, Wolfgang Cologne Institute of Computer Science Faculty of Computer Science and Engineering Science TH Köln Gummersbach Germany Department of Medical Informatics Biometry and Epidemiology Faculty of Medicine Ruhr-University Bochum Bochum Germany

In recent times, large language models (LLMs) have made significant strides in generating computer code, blurring the lines between code created by humans and code produced by artificial intelligence (AI). As these technologies evolve rapidly, it is crucial to explore how they influence code generation, especially given the risk of misuse in areas like higher education. This paper explores this issue by using advanced classification techniques to differentiate between code written by humans and that generated by ChatGPT, a type of LLM. We employ a new approach that combines powerful embedding features (black-box) with supervised learning algorithms – including Deep Neural Networks, Random Forests, and Extreme Gradient Boosting – to achieve this differentiation with an impressive accuracy of 98%. For the successful combinations, we also examine their model calibration, showing that some of the models are extremely well calibrated. Additionally, we present white-box features and an interpretable Bayes classifier to elucidate critical differences between the code sources, enhancing the explainability and transparency of our approach. Both approaches work well but provide at most 85 − 88% accuracy. We also show that untrained humans solve the same task not better than random guessing. This study is crucial in understanding and mitigating the potential risks associated with using AI in code generation, particularly in the context of higher education, software development, and competitive programming. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Transformer Model with Pre-Layer Normalization for COVID-19 Growth Prediction

arXiv

引用

arXiv 2022年

作者： Fitra, Rizki Ramadhan Yudistira, Novanto Mahmudy, Wayan Firdaus Informatics Engineering Faculty of Computer Science Brawijaya University Indonesia

Coronavirus disease or COVID-19 is an infectious disease caused by the SARS-CoV-2 virus. The first confirmed case caused by this virus was found at the end of December 2019 in Wuhan City, China. This case then spread throughout the world, including Indonesia. Therefore, the COVID-19 case was designated as a global pandemic by WHO. The growth of COVID-19 cases, especially in Indonesia, can be predicted using several approaches, such as the Deep Neural Network (DNN). One of the DNN models that can be used is Deep Transformer which can predict time series. The model is trained with several test scenarios to get the best model. The evaluation is finding the best hyperparameters. Then, further evaluation was carried out using the best hyperparameters setting of the number of prediction days, the optimizer, the number of features, and comparison with the former models of the Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN). All evaluations used metric of the Mean Absolute Percentage Error (MAPE). Based on the results of the evaluations, Deep Transformer produces the best results when using the Pre-Layer Normalization and predicting one day ahead with a MAPE value of 18.83. Furthermore, the model trained with the Adamax optimizer obtains the best performance among other tested optimizers. The performance of the Deep Transformer also exceeds other test models, which are LSTM and RNN. © 2022, CC BY.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Load Balancing on Named Data Networking, Case Study: UIN Topology in Indonesia 16

Load Balancing on Named Data Networking, Case Study: UIN Top...

引用

16th International Conference on Telecommunication Systems Services and Applications, TSSA 2022

作者： Zaki Hamidi, Eki Ahmad Ahdan, Syaiful Jupriyadi Sucinto, Adi Arifin, Hasan Nur Syambas, Nana Rachmana School of Electrical Engineering and Informatics Instsitut Teknologi Bandung Bandung Indonesia Uin Sunan Gunung Djati Bandung Electrical Engineering Department Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia

ISBN: (纸本)9781665455947

Named Data Networking (NDN) is a network with a future internet architecture that changes the point of view in networking from host-centric to data-centric. Named data networking provides a network system where the routing system is no longer dependent on traditional IP. Network packets are routed through nodes by name. When many manufacturers produce packages with different names for several consumers, routing with load balancing is necessary. The case study carried out is to conduct a simulation by connecting all UIN campuses into a topology with the name UIN Topology in Indonesia, using several scenarios to describe the effectiveness of the load balancer on the UIN topology in Indonesia. This study focuses on load balancer applications to reduce delays in Named Data Networking (NDN), the topology of UIN in Indonesia. © 2022 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Seeing The Invisible in Arts ‐ From the Wane of axiality and Symmetry To the Wax of Invisibility and Emptiness

Artificial Intelligence and Seeing The Invisible in Arts ‐ ...

引用

International Conference on computer and Applications (ICCA)

作者： Rasha Said Abdel Latif M. Samir Abou El-Seoud Khaled Mohamed Dewidar Faculty of Energy and Environmental Engineering The British University in Egypt (BUE) Cairo Egypt Faculty of Informatics and Computer Science The British University in Egypt (BUE) Cairo Egypt Faculty Engineering The British University in Egypt (BUE) Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

Function has been always an important driver in architectural design. It is the request to generate form directly from purpose and utility. In 1896, Louis Sullivan projected that ‘form follows function’ and that the beauty of a building derives directly from its function and not from references of the built heritage. The assumption was that beauty would naturally derive from design once functional requirements are met. Thus, fitness for purpose equals beauty. In 1908, Adolf Loos even went so far as to ask for the total abandonment of decoration. In 1947, Mies van der Rohe made his paradigm shift, function is the main language for design in Europe, creating a new built environment. However, with the advent of machine learning systems, and as seen in our deep learning approach, form indeed can literally follow function. In this paper, we presented a new design approach where we can interpret the unseen in visualizing the future. This can decompose the final design to its essentials to finally generate a conceptual new futuristic design. Using multiple types of tools, we showed how to merge art, sculpture and architecture in a principled manner to yield new compositions and how to generate interesting design variations thus reaching novel conceptual designs. Architecture is a complex spatial organization field, and one must consider it in its totality. There are not only functional considerations but also aesthetical and structural ones. Artificial intelligence is an exciting field of investigation that not only has the potential to fill the gap of computational resources for the conceptual design phases of architectural projects but also the capacity to address the wider needs of the profession for futuristic designs. It answers the ideas of the volume of space, and how space be visualized and built. Finally, architecture does not only deal with functional perfection but also need to respond to immaterial and contextual conditions and inevitably responding to aestheti

关键词： Economics Deep learning Visualization Art Reviews Buildings Europe computer architecture Organizations Reflection

来源：评论

学校读者我要写书评

暂无评论

Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

arXiv

引用

arXiv 2025年

作者： Oliynyk, Daryna Mayer, Rudolf Rauber, Andreas CDL AsTra Faculty of Computer Science University of Vienna Vienna Austria SBA Research Vienna Austria Institute of Information Systems Engineering Faculty of Informatics TU Wien Vienna Austria

Machine learning (ML) models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other attack methods, substitute model training is an all-encompassing attack applicable to any machine learning model whose behaviour can be approximated from input-output queries. Whereas previous works mainly focused on improving the performance of substitute models by, e.g. developing a new substitute training method, there have been only limited ablation studies that try to understand the impact the strength of an attacker has on the substitute model’s performance. As a result, different authors came to diverse, sometimes contradicting, conclusions. In this work, we exhaustively examine the ambivalent influence of different factors resulting from varying the attacker’s capabilities and knowledge on a substitute training attack. Our findings suggest that some of the factors that have been considered important in the past are, in fact, not that influential;instead, we discover new correlations between attack conditions and success rate. In particular, we demonstrate that better-performing target models enable higher-fidelity attacks and explain the intuition behind this phenomenon. Further, we propose to shift the focus from the complexity of target models toward the complexity of their learning tasks. Therefore, for the substitute model, rather than aiming for a higher architecture complexity, we suggest focusing on getting data of higher complexity and an appropriate architecture. Finally, we demonstrate that even in the most limited data-free scenario, there is no need to overcompensate weak knowledge with unrealistic capabilities in the form of millions of queries. Our results often exceed or match the performance of previous attacks that assume a stronger attacker, suggesting that these stronger attacks are likely endangering a model owner’s intellectual property to a significantly higher degree than shown until now. Cop

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：