检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Agrawal, Akanksha Lokshtanov, Daniel Panolan, Fahad Saurabh, Saket Verma, Shaily Department of Computer Science and Engineering Indian Institute of Technology Madras India Department of Computer Science University of California Santa Barbara United States School of Computing University of Leeds United Kingdom Theoretical Computer Science The Institute of Mathematical Sciences HBNI India Department of Informatics University of Bergen Norway Algorithm Engineering Group Hasso Plattner Institute Germany

The classic greedy coloring (first-fit) algorithm considers the vertices of an input graph G in a given order and assigns the first available color to each vertex v in G. In the Grundy Coloring problem, the task is to find an ordering of the vertices that will force the greedy algorithm to use as many colors as possible. In the Partial Grundy Coloring, the task is also to color the graph using as many colors as possible. This time, however, we may select both the ordering in which the vertices are considered and which color to assign the vertex. The only constraint is that the color assigned to a vertex v is a color previously used for another vertex if such a color is available. Partial Grundy coloring of a graph corresponds to the vertex coloring produced by the greedy coloring heuristics called last-fit coloring, which assigns the last available color to each vertex in the given order. Whether Grundy Coloring and Partial Grundy Coloring admit fixed-parameter tractable (FPT) algorithms, algorithms with running time f(k)nO(1), where k is the number of colors, was posed as an open problem by Zaker and by Effantin et al., respectively. Recently, Aboulker et al. (STACS 2020 and Algorithmica 2022) resolved the question for Grundy Coloring in the negative by showing that the problem is W[1]-hard. For Partial Grundy Coloring, they obtain an FPT algorithm on graphs that do not contain Ki,j as a subgraph (a.k.a. Ki,j-free graphs). Aboulker et al. re-iterate the question of whether there exists an FPT algorithm for Partial Grundy Coloring on general graphs and also asks whether Grundy Coloring admits an FPT algorithm on Ki,j-free graphs. We give FPT algorithms for Partial Grundy Coloring on general graphs and for Grundy Coloring on Ki,j-free graphs, resolving both the questions in the affirmative. We believe that our new structural theorems for partial Grundy coloring and "representative-family" like sets for Ki,j-free graphs that we use in obtaining our results may have wi

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Clustering Based User Allocation in 5G Networks∗

Clustering Based User Allocation in 5G Networks∗

引用

2021 International Symposium on Networks, computers and Communications, ISNCC 2021

作者： Bouras, Christos Kalogeropoulos, Rafail Sina, Ioannis Computer Technology Institute Press 'Diophantus201D Univ. Of Patras Greece Patras Greece Computer Engineering And Informatics Dept.

ISBN: (纸本)9780738113166

Machine learning is an extremely efficient technique for solving complex problems without the use of traditional programming but rather enabling machines to learn from an input of data and train them to cope with various problems. The rapid growth in the number of active mobile devices, mobile applications and services dictates an efficient utilization of mobile and wireless networking infrastructure. Communication networks need to evolve and valorize machine learning methods in order to process large volumes of data without introducing excessive time delay in these computations. Upcoming 5G systems are expected to be the first network infrastructure to support exploding mobile traffic volumes and machine learning techniques can be used in order to help manage the rise in data volumes. We present a mechanism for resource allocation in mobile and wireless networks, that effectively utilizes machine learning techniques. © 2021 IEEE.

关键词： Wireless networks

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

Enhancing UAV Autonomous Navigation in Indoor Environments Using Reinforcement Learning and Convolutional Neural Networks 22

Enhancing UAV Autonomous Navigation in Indoor Environments U...

引用

22nd IEEE International Symposium on Intelligent Systems and informatics, SISY 2024

作者： Safarpour Motealegh Mahalegi, Homayoun Farhadi, Amirfarhad Molnar, Gyorgy Nagy, Eniko Obuda University Institute of Mechatronics and Vehicle Engineering Budapest Hungary Islamic Azad University Department of Computer Engineering Science and Research Branch Tehran Iran Obuda University Hungary Szechenyi University Apaczai Csere János Faculty of Humanities Education and Social Sciences Kando Kalman Faculty of Electrical Engineering Budapest Gyor Hungary Obuda University Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350385601

In recent years, the number of unmanned aerial vehicle (UAV) applications has increased. However, navigating them indoors is still tricky because no GPS signals are available, and the obstacles constantly change. This study exploits the collaboration between convolutional neural networks (CNNs) and reinforcement learning (RL) to overcome these challenges, improving the level of independence of UAVs in indoor settings. We present a new technique known as potential-based reward shaping, which directly incorporates expert knowledge into the reinforcement learning framework. This technique efficiently addresses the problem of sparse rewards that often hinder learning in conventional RL configurations. In addition, we have created a reflective reinforcement learning agent that systematically assesses its actions to prioritize those that result in the most substantial enhancements. We have extensively evaluated the performance of our method with the High-Definition Indoor Navigation (HDIN) dataset to show that our method continuously outperformed current non-introspective RL techniques in terms of decision-making speed and navigation accuracy in this evaluation. The results show that this new CNN-RL combination is feasible and suggests a scalable method for complex indoor navigation problems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EEG Analysis of Human Perception based on Video-Audio Stimuli 1

EEG Analysis of Human Perception based on Video-Audio Stimul...

引用

1st International Conference on Smart Technologies Communication and Robotics, STCR 2021

作者： Manochitra, S. Partheepan, Ravinthiran Kalasalingam Institute of Technology Faculty of Computer Science and Engineering Tamilnadu Virudhunagar India Vytautas Magnus University Faculty of Informatics Master Programme - Applied Informatics Kaunas Lithuania

ISBN: (纸本)9781665418065

Emotions plays a potential role in human computer interaction which are having an obligatory models of cognitive measures. The emotions are dominated by the human physiological communication channels. Those emotions could affect several human activities like learning, decision making, communication, perception, cognitive and so on. Also, some of the emotions are quite difficult to measure and interpret and having difficulty in incorporating them into a technology and design. On the other hand, state of the technologies has enabled us to capture the emotions and integrate them for the use of human computer interaction contexts. This paper delivers an attempt to model the emotions using electroencephalography (EEG). The video stimuli for the two representatives are based on a few negative, positive and neutral contents were shown to volunteers and EEG data was obtained. Further, EEG analysis were experimented and collected about their emotional states with subject's self reports. This study determines that the human emotions could be modelled for affect assessment module or for the usage in human computer interaction and affect based intelligent interactions. © 2021 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

DEPTH-GUIDED FREE-SPACE SEGMENTATION FOR A MOBILE ROBOT

arXiv

引用

arXiv 2023年

作者： Sevastopoulos, Christos Hussain, Joey Konstantopoulos, Stasinos Karkaletsis, Vangelis Makedon, Fillia Department of Computer Science & Computer Engineering University of Texas at Arlington ArlingtonTX United States Institute of Informatics and Telecommunications NCSR'Demokritos' Agia Paraskevi Attica Greece

Accurate indoor free-space segmentation is a challenging task due to the complexity and the dynamic nature that indoor environments exhibit. We propose an indoors free-space segmentation method that associates large depth values with navigable regions. Our method leverages an unsupervised masking technique that, using positive instances, generates segmentation labels based on textural homogeneity and depth uniformity. Moreover, we generate superpixels corresponding to areas of higher depth and align them with features extracted from a Dense Prediction Transformer (DPT). Using the estimated free-space masks and the DPT feature representation, a SegFormer model is fine-tuned on our custom-collected indoor dataset. Our experiments demonstrate sufficient performance in intricate scenarios characterized by cluttered obstacles and challenging identification of free space. © 2023, CC BY.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A survey and recent advances in black widow optimization: variants and applications

引用

Neural Computing and Applications 2024年 1-21页

作者： Shehab, Mohammad Shambour, Mohd Khaled Yousef Abu Hashem, Muhannad A. Al Hamad, Husam Ahmad Shannaq, Fatima Mizher, Manar Jaradat, Ghaith Sh. Daoud, Mohammad Abualigah, Laith College of Computer Sciences and Informatics Amman Arab University Amman11953 Jordan The Custodian of the Two Holy Mosques Institute for Hajj and Umrah Research Umm Al-Qura University Makkah Saudi Arabia Department of Geomatics Architecture and Planning Faculty King Abdulaziz University Jeddah Saudi Arabia College of Engineering Al Ain University Abu Dhabi United Arab Emirates Research Center University of Tabuk Tabuk71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Applied science research center Applied science private university Amman11931 Jordan College of Engineering Yuan Ze University Taoyuan32003 Taiwan

Artificial Intelligence techniques, such as optimization algorithms, have become essential for success in many fields. Therefore, most researchers, especially in computer and engineering sciences, focused their efforts and abilities on adapting the optimization algorithms for solving various problems. This review introduces one of the recent nature-inspired optimization algorithms, called black widow optimization (BWO). This review highlights the main procedures of BWO, its strengths and weaknesses, the growth of BWO, the variants of BWO (i.e., binary, modification, and hybridization), and the efficiency of BWO in different fields and applications (i.e., feature selection, medical, image processing, engineering, IoT, power and energy, and networks). As a result, the review seeks to assist researchers who are interested in using the BWO to address their challenges. For instance, it could help manage large pilgrim crowds, enabling smoother ritual performances and overcoming potential difficulties they encounter. Also, it suggests new possible ways of enhancing the efficiency of the basic BWO. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Causal Prompting: Debiasing Large Language Model Prompting Based on Front-Door Adjustment 39

Causal Prompting: Debiasing Large Language Model Prompting B...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Congzhi Zhang, Linhai Wu, Jialong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)157735897X

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily focus on the model training stage, including approaches based on data augmentation and reweighting, yet they struggle with the complex biases inherent in LLMs. To address such limitations, the causal relationship behind the prompting methods is uncovered using a structural causal model, and a novel causal prompting method based on front-door adjustment is proposed to effectively mitigate LLMs biases. In specific, causal intervention is achieved by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thought generated by LLM is employed as the mediator variable and the causal effect between input prompts and output answers is calculated through front-door adjustment to mitigate model biases. Moreover, to accurately represent the chain-of-thoughts and estimate the causal effects, contrastive learning is used to fine-tune the encoder of chain-of-thought by aligning its space with that of the LLM. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets on both open-source and closed-source LLMs. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Cultivate Smart and Healthy Ageing 9th

Cultivate Smart and Healthy Ageing

引用

9th EAI International Conference on IoT Technologies for HealthCare, HealthyIoT 2022

作者： Andreou, Andreas Mavromoustakis, Constandinos X. Markakis, Evangelos Mastorakis, George Batalla, Jordi Mongay Pallis, Evangelos Dobre, Ciprian Department of Computer Science University of Nicosia and University of Nicosia Research Foundation Nicosia Cyprus Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Crete Greece Department of Management Science and Technology Hellenic Mediterranean University Agios Nikolaos Crete Greece Warsaw University of Technology Warsaw Poland Department of Industrial Design and Production Engineering School of Engineering University of West Attica Athens Greece National Institute for Research and Development in Informatics Bucharest Romania

ISBN: (纸本)9783031286629

The essential criterion for developing an intelligent age-friendly environment is evaluating and monitoring the provision of services. Our research aims to allow the deployment of a broad range of digital healthcare solutions interconnected in an IoT network ecosystem. Through their interoperability, we will be able to cultivate age-friendly smart homes for older adults. Thus, we will enable interpreted living and wellbeing. The intelligent integrations of digital solutions will allow the acquisition and evaluation of health-related data. Standardization, interoperability and scalability of the integration will increase efficiency in healthcare, improving older adults’ Quality of Life (QoL). Also, interpreting their needs will allow key stakeholders to optimize the Quality of Service (QoS). The proposed Internet of Health (IoH) framework will encapsulate sustainable and affordable innovative solutions and their benefits for a comfortable, meaningful, and independent life in an intelligent environment. Therefore, the frame mediated by edge computing, in-home and community settings will be able to interact with healthcare networks contributing to hospitalizations and institutional care. © 2023, ICST institute for computer Sciences, Social informatics and Telecommunications engineering.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Talking Face Generation with Diverse yet Realistic Facial Animations

arXiv

引用

arXiv 2023年

作者： Wu, Rongliang Yu, Yingchen Zhan, Fangneng Zhang, Jiahui Zhang, Xiaoqin Lu, Shijian School of Computer Science and Engineering Nanyang Technological University Singapore Max Planck Institute for Informatics Germany College of Computer Science and Artifcial Intelligence Wenzhou University China

Audio-driven talking face generation, which aims to synthesize talking faces with realistic facial animations (including accurate lip movements, vivid facial expression details and natural head poses) corresponding to the audio, has achieved rapid progress in recent years. However, most existing work focuses on generating lip movements only without handling the closely correlated facial expressions, which degrades the realism of the generated faces greatly. This paper presents DIRFA, a novel method that can generate talking faces with diverse yet realistic facial animations from the same driving audio. To accommodate fair variation of plausible facial animations for the same audio, we design a transformer-based probabilistic mapping network that can model the variational facial animation distribution conditioned upon the input audio and autoregressively convert the audio signals into a facial animation sequence. In addition, we introduce a temporally-biased mask into the mapping network, which allows to model the temporal dependency of facial animations and produce temporally smooth facial animation sequence. With the generated facial animation sequence and a source image, photo-realistic talking faces can be synthesized with a generic generation network. Extensive experiments show that DIRFA can generate talking faces with realistic facial animations effectively. Copyright © 2023, The Authors. All rights reserved.

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：