检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Danquah, Wiseborn Manfe Altilar, D. Turgay Faculty of Computer Engineering & Informatics Istanbul Technical University Istanbul34469 Turkey

The organization of vehicles into platoons, a convoy of vehicles with the same relative distance between them in a given road lane, is very promising due to its contributions to intelligent transportation systems. A significant reduction in traffic congestion, fuel consumption, and pollution can be achieved by forming platoons on the road. Furthermore, as powerful processing units and other resources embedded in platoon vehicles may not be fully utilized during the entire travel period, the vehicles in the platoon can collaborate to form a federated platoon-based vehicular cloud to meet the high demand for computing resources and services in vehicular environments. In order to make advancements in the deployment of federated platoon-based vehicular cloud, two key contributions are made in this study. Firstly, the concept of federated platoon-based vehicular cloud computing for task execution in a vehicular environment is highlighted. Secondly, data partitioning and scheduling schemes that distribute data chunks of large and divisible application data among platoon vehicles are proposed considering the characteristics of vehicular resources, network parameters, and the position of vehicles in the platoon. The data partitioning and scheduling schemes, which are modeled based on the different information flow typologies of vehicular platoon, consist of the Bi-Directional Recursive (BD-R), Bi-Directional Interlaced (BD-I), Bi-Directional Lead Recursive (BDL-R), Bi-Directional Lead Interlaced (BDL-I), Bi-Directional Lead Aggregate Recursive (BDLA-R) and the Bi-Directional Lead Aggregate Interlaced (BDLA-I). Performance analysis carried out through realistic simulations showed that while the BDL-R and BDL-I schemes have the best performance in terms of task execution time, the other schemes have the advantage of enforcing priority in unprocessed data transmission and dependency in the aggregation of processed data chunks by each platoon member. © 2022, The Authors. All ri

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

ANEC: An Amharic Named Entity Corpus and Transformer Based Recognizer

arXiv

引用

arXiv 2022年

作者： Jibril, Ebrahim Chekol Tantuǧ, A. Cüneyd Faculty of Computer Engineering and Informatics Istanbul Technical University Istanbul34469 Turkey

Named Entity Recognition is an information extraction task that serves as a preprocessing step for other natural language processing tasks, such as machine translation, information retrieval, and question answering. Named entity recognition enables the identification of proper names as well as temporal and numeric expressions in an open domain text. For Semitic languages such as Arabic, Amharic, and Hebrew, the named entity recognition task is more challenging due to the heavily inflected structure of these languages. In this paper, we present an Amharic named entity recognition system based on bidirectional long short-term memory with a conditional random fields layer. We annotate a new Amharic named entity recognition dataset (8,070 sentences, which has 182,691 tokens) and apply Synthetic Minority Over-sampling Technique to our dataset to mitigate the imbalanced classification problem. Our named entity recognition system achieves an F-1 score of 93%, which is the new state-of-the-art result for Amharic named entity recognition. We will release the dataset after acceptance. © 2022, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Does Twinning Vehicular Networks Enhance Their Performance in Dense Areas

arXiv

引用

arXiv 2024年

作者： Al-Shareeda, Sarah Oktug, Sema F. Yaslan, Yusuf Yurdakul, Gokhan Canberk, Berk Faculty of Computer Engineering and Informatics Istanbul Technical University Turkey BTS Group Turkey School of Computing Engineering and The Built Environment Edinburgh Napier University United Kingdom

This paper investigates the potential of Digital Twins (DTs) to enhance network performance in densely populated urban areas, specifically focusing on vehicular networks. The study comprises two phases. In Phase I, we utilize traffic data and AI clustering to identify critical locations, particularly in crowded urban areas with high accident rates. In Phase II, we evaluate the advantages of twinning vehicular networks through three deployment scenarios: edge-based twin, cloud-based twin, and hybrid-based twin. Our analysis demonstrates that twinning significantly reduces network delays, with virtual twins outperforming physical networks. Virtual twins maintain low delays even with increased vehicle density, such as 15.05 seconds for 300 vehicles. Moreover, they exhibit faster computational speeds, with cloud-based twins being 1.7 times faster than edge twins in certain scenarios. These findings provide insights for efficient vehicular communication and underscore the potential of virtual twins in enhancing vehicular networks in crowded areas while emphasizing the importance of considering real-world factors when making deployment decisions. © 2024, CC BY.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Interval Partitioning for Packet Classification in OpenFlow vSwitch

IEEE Networking Letters

引用

IEEE Networking Letters 2020年第3期2卷 128-131页

作者： Akkoc, Mertkan Canberk, Berk Department of Computer Engineering Faculty of Computer and Informatics Istanbul Technical University İstanbul34469 Turkey

Packet classification is a key factor for choosing proper action for incoming packet and has to be done fast and effectively, especially in OpenFlow. But OpenFlow vSwitch technology doesn't always allow to use some fast hardware technology for packet classification like TCAM (Ternary Content Addressable Memory). Instead of TCAM, decision tree methods are preferred solutions for fast classification in OpenFlow vSwitch in the literature. But most of these methods can cause the rule replication problem. As a result, while the duration of packet classification decreases, rule update duration increases. There are also rule partitioning methods in the literature to solve this problem, but the running time of these methods mostly depends on the number of rule fields. Also, some of these solutions don't overcome the rule replication problem. At that point, the main question of this letter is that how can we make the rule partitioning fast by both preventing the rule replication and allowing fast packet classification and rule update in OpenFlow vSwitch? To solve the rule partitioning problem, we propose a greedy based interval partitioning strategy. Here, the running time of the partitioning algorithm only depends on the rule number. After partitioning, we propose to use HyperCuts to construct decision trees for fast packet classification and rule update. According to performance evaluation results, we do the rule partitioning and rule updates faster than the PartitonSort method with the percentage of 88, 15, respectively. Also, we classify packet faster than the TupleMerge method with the percentage of 40 for online and 50 for offline scenarios. © 2019 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

DTWN: Q-learning-based Transmit Power Control for Digital Twin WiFi Networks

EAI Endorsed Transactions on Industrial Networks and Intelli...

引用

EAI Endorsed Transactions on Industrial Networks and Intelligent Systems 2022年第31期9卷

作者： Cakir, Lal Verda Huseynov, Khayal Ak, Elif Canberk, Berk Computer Engineering Department India Artificial Intelligence and Data Engineering Department Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey BTS Group Istanbul Turkey

Interference has always been the main threat to the performance of traditional WiFi networks and next-generation moving forward. The problem can be solved with transmit power control(TPC). However, to accomplish this, an information-gathering process is required. But this brings overhead concerns that decrease the throughput. Moreover, mitigation of interference relies on the selection of transmit powers. In other words, the control scheme should select the optimum configuration relative to other possibilities based on the total interference, and this requires an extensive search. Furthermore, bidirectional communication in real-time needs to exist to control the transmit powers based on the current situation. Based on these challenges, we propose a complete solution with Digital Twin WiFi Networks (DTWN). Contrarily to other studies, with the agent programs installed on the APs in the physical layer of this architecture, we enable information-gathering without causing overhead to the wireless medium. Additionally, we employ Q-learning-based TPC in the Brain Layer to find the best configuration given the current situation. Consequently, we accomplish real-time monitoring and management thanks to the digital twin. Then, we evaluate the performance of the proposed approach through total interference and throughput metrics over the increasing number of users. Furthermore, we show that the proposed DTWN model outperforms existing schemes. © 2022. L. V. Cakir et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Brain Multigraph Population From a Single Graph Template for Boosting One-Shot Classification

arXiv

引用

arXiv 2022年

作者： Pala, Furkan Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

A central challenge in training one-shot learning models is the limited representativeness of the available shots of the data space. Particularly in the field of network neuroscience where the brain is represented as a graph, such models may lead to low performance when classifying brain states (e.g., typical vs. autistic). To cope with this, most of the existing works involve a data augmentation step to increase the size of the training set, its diversity and representativeness. Though effective, such augmentation methods are limited to generating samples with the same size as the input shots (e.g., generating brain connectivity matrices from a single shot matrix). To the best of our knowledge, the problem of generating brain multigraphs capturing multiple types of connectivity between pairs of nodes (i.e., anatomical regions) from a single brain graph remains unsolved. In this paper, we unprecedentedly propose a hybrid graph neural network (GNN) architecture, namely Multigraph Generator Network or briefly MultigraphGNet, comprising two subnetworks: (1) a many-to-one GNN which integrates an input population of brain multigraphs into a single template graph, namely a connectional brain temple (CBT), and (2) a reverse one-to-many U-Net network which takes the learned CBT in each training step and outputs the reconstructed input multigraph population. Both networks are trained in an end-to-end way using a cyclic loss. Experimental results demonstrate that our MultigraphGNet boosts the performance of an independent classifier when trained on the augmented brain multigraphs in comparison with training on a single CBT from each class. We hope that our framework can shed some light on the future research of multigraph augmentation from a single graph. Our MultigraphGNet source code is available at https://***/basiralab/MultigraphGNet. © 2022, CC BY-NC-ND.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Obstacle Identification and Ellipsoidal Decomposition for Fast Motion Planning in Unknown Dynamic Environments

arXiv

引用

arXiv 2022年

作者： Kaymaz, Mehmetcan Ure, Nazım Kemal The Faculty of Aeronautics and Astronautics Istanbul Technical University Istanbul Turkey The Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

Collision avoidance in the presence of dynamic obstacles in unknown environments is one of the most critical challenges for unmanned systems. In this paper, we present a method that identifies obstacles in terms of ellipsoids to estimate linear and angular obstacle velocities. Our proposed method is based on the idea of any object can be approximately expressed by ellipsoids. To achieve this, we propose a method based on variational Bayesian estimation of Gaussian mixture model, the Kyachiyan algorithm, and a refinement algorithm. Our proposed method does not require knowledge of the number of clusters and can operate in real-time, unlike existing optimization-based methods. In addition, we define an ellipsoid-based feature vector to match obstacles given two timely close point frames. Our method can be applied to any environment with static and dynamic obstacles, including ones with rotating obstacles. We compare our algorithm with other clustering methods and show that when coupled with a trajectory planner, the overall system can efficiently traverse unknown environments in the presence of dynamic obstacles. © 2022, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Deep Cross-Modality and Resolution Graph Integration for Universal Brain Connectivity Mapping and Augmentation

arXiv

引用

arXiv 2022年

作者： Cinar, Ece Haseki, Sinem Elif Bessadok, Alaa Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

The connectional brain template (CBT) captures the shared traits across all individuals of a given population of brain connectomes, thereby acting as a fingerprint. Estimating a CBT from a population where brain graphs are derived from diverse neuroimaging modalities (e.g., functional and structural) and at different resolutions (i.e., number of nodes) remains a formidable challenge to solve. Such network integration task allows for learning a rich and universal representation of the brain connectivity across varying modalities and resolutions. The resulting CBT can be substantially used to generate entirely new multimodal brain connectomes, which can boost the learning of the downs-stream tasks such as brain state classification. Here, we propose the Multimodal Multiresolution Brain Graph Integrator Network (i.e., M2GraphIntegrator), the first multimodal multiresolution graph integration framework that maps a given connectomic population into a well-centered CBT. M2GraphIntegrator first unifies brain graph resolutions by utilizing resolution-specific graph autoencoders. Next, it integrates the resulting fixed-size brain graphs into a universal CBT lying at the center of its population. To preserve the population diversity, we further design a novel clustering-based training sample selection strategy which leverages the most heterogeneous training samples. To ensure the biological soundness of the learned CBT, we propose a topological loss that minimizes the topological gap between the ground-truth brain graphs and the learned CBT. Our experiments show that from a single CBT, one can generate realistic connectomic datasets including brain graphs of varying resolutions and modalities. We further demonstrate that our framework significantly outperforms benchmarks in reconstruction quality, augmentation task, centeredness and topological soundness. © 2022, CC BY-NC-ND.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Linkedin Profiles

Risk Assessment of Linkedin Profiles

引用

International Conference on computer Science and engineering (UBMK)

作者： Arzum Aydın Şerif Bahtiyar Cyber Security and Privacy Research Lab SPFLab. Faculty of Computer and Informatics Engineering Istanbul Technical University Maslak Istanbul Türkiye

Fake or fraudulent accounts are a significant problem in social networking that is often addressed by the users of various social networking platforms involving Linkedin. Fraudulent accounts generally try to convince people about their identity that they are authentic. Adversaries use fake profiles or they impersonate a real identity on social networks to obtain more privileges. Therefore, it is critical to understand problems regarding fraudulent profiles. In this paper, we propose new sustainable framework to assess risks about profiles in social networking platforms. The framework is implemented as a web extension and it is analyzed with ITU alumni profiles in Linkedin. The analyses results show that there are different profiles within one community in Linkedin that may be significant threat for social network users.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chaotic American zebra search optimization algorithm for benchmark challenges 15

Chaotic American zebra search optimization algorithm for ben...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Kamboj, Vikram Kumar Krishna, Ardhala Bala Verma, Chaman Raboaca, Maria Simona Filote, Constantin Stepanova, Maria Schulich School of Engineering University of Calgary AB Canada Malla Reddy Engineering College for Women Dept. of Electrcical and Electronics Engineering Hyderabad India Eötvös Loránd University Faculty of Informatics Dept. of Media and Edu. Informatics Budapest Hungary National Research and Development Institute for Cryogenics and Isotopic Technologies Icsi Energy Department Ramnicu Valcea240050 Romania Stefan Cel Mare University of Suceava Faculty of Electrical Engineering and Computer Science Suceava720229 Romania Bauman Moscow State Technical University Engineering Business and Management Faculty Russia

ISBN: (纸本)9798350321388

In this research, we presented a modification to the recently developed swarm premised American zebra search optimization algorithm (AZOA) using chaos. The particular Singer mapping was proposed by the so-called chaotic AZOA and was already known to perform better in optimization. Twelve uni, multi modal benchmark functions, three-bar truss and ten bar truss optimal structural designs were tested. The chaotic AZOA with Singer map would perform more effectively, more consistently, and quicker than the classical AZOA and other recent metaheuristics in optimization, according to the results, which also supported the viability of the modifications. It was discussed if the chaotic AZAO could be optimized with the original AZOA, and the chaotic AZOA was suggested for use in applications for actual engineering challenges. © 2023 IEEE.

关键词： Mapping

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：