检索结果-内蒙古大学图书馆

6th International Conference on Intelligent computing, Communication, and Devices, ICCD 2023

作者： Hu, Jieling Yang, Yufei Dai, Xianhua School of Electronics and Information Technology Sun Yat-sen University Guangzhou China School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Melbourne Australia

ISBN: (数字)9781510666269

ISBN: (纸本)9781510666252

This paper studies the static network community detection algorithm, improves the overlapping community detection algorithm LFM based on local expansion, and improves the randomness and redundancy of this algorithm in the process of seed selection and community expansion. Vertex influence and their similarity are used to select seeds, and the redundant steps in community expansion are optimized, and the SCF-LFM algorithm is proposed. The experimental results show that the algorithm has improved accuracy and modularity, and the result of the division has a high degree of community. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A survey on deep learning for polyp segmentation: techniques, challenges and future trends

引用

Visual Intelligence 2025年第1期3卷 1-20页

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. © The Author(s) 2025.

关键词： Comprehensive evaluation Deep learning Medical imaging Polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

Predicting Energy Consumption of Battery-Operated Electric Vehicles: A Comparative Performance Assessment

Predicting Energy Consumption of Battery-Operated Electric V...

引用

2023 IEEE International Conference on Industrial engineering and engineering Management, IEEM 2023

作者： Paul, Dyuti Mo, Huadong Elsayed, Saber Chakrabortty, Ripon K. School of Engineering and Technology University of New South Wales CanberraACT-2612 Australia School of Systems and Computing University of New South Wales CanberraACT2612 Australia

ISBN: (纸本)9798350323153

Predicting the real-time energy consumption of battery-operated electric vehicles (BEVs) remains criticalin identifying energy-efficient routes and charging stations. However, accurately predicting energy consumption depends on various environmental factors, such as wind speed, wind direction, temperature, humidity, and precipi-tation. Although the existing time series (TS) models offer valuable insights into energy consumption prediction and data trends, they need to generate more accurate outcomes, especially with real-time data. Moreover, obtaining comprehensive and accurate data pertaining to BEV energy consumption poses significant challenges. The scarcity of data can hinder the progress of research in this area. Therefore, this study aims to identify an efficient prediction model by comparing it with existing models, which will con-tribute to developing more accurate and efficient prediction models for BEV power consumption. We selected particular environmental factors that were expected to impact BEV energy consumption. These findings also involved acquiring BEV energy consumption data and integrating it with various environmental parameters. © 2023 IEEE.

关键词： BEV Deep Neural Network Energy Consumption Machine Learning Prediction Algorithm Regression Analysis Time Series

来源：评论

学校读者我要写书评

暂无评论

Profane Words on Twitter: An analysis of the use of swear words in different countries 2022

Profane Words on Twitter: An analysis of the use of swear wo...

引用

6th International Conference on Compute and Data Analysis, ICCDA 2022

作者： Phoey Lee, Teh Cheng, Chi-Bin Department of Computing and Information Systems School of Engineering and Computing Sunway University Malaysia Department of Information Management Tamkang University Tamsui Taiwan

ISBN: (纸本)9781450395472

Decreasing the usage of profanity terms can reduce a toxic environment, create a clean language culture towards the z-generation who is now exploring the online world. To understand how intensive is profanity usage in social media platforms, we collected a sample of tweets for the year 2020, from Jan 2020 to Dec 2020. A total of 4,175,516 tweets that contained the reference list of various profanity words is collected, with its geographical country compiled. Each of the tweets included at least a profanity term from the categories set of profanity. This study intends to visualise the profanity classes in text communication among users from different countries. This idea is to create awareness of language usage and suggest a possible mechanism to assist or investigate a potential crime, such as racism or cyberbully detection. © 2022 ACM.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Genetic Algorithm for 2D Path Planning of Unmanned Aerial Vehicles with Obstacle Avoidance 23

An Empirical Study on Genetic Algorithm for 2D Path Planning...

引用

2023 International Conference on Computer, Vision and Intelligent Technology, ICCVIT 2023

作者： Zhao, Ya-Hong Lan, Yu-Lin Li, Shang-Lin Zhang, Wen-Fen School of Computer and Artificial Intelligence Xiangnan University China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Chenzhou China

ISBN: (纸本)9798400708701

Unmanned aerial vehicle (UAV), with high efficiency, low manpower costs, and flexible convenience, has attracted widespread attention in logistics. UAV trajectory planning is an essential component in this context. Genetic algorithm(GA) is an effective tool for solving complex route optimization problems. However, selecting the optimal combination of parameters for UAV path planning remains a challenging problem, especially in complex urban environments with numerous obstacles. This paper proposes a genetic algorithm-based UAV path planning approach(UAV_GA) that considers obstacle avoidance on a two-dimensional grid-based map. Furthermore, to investigate the general patterns in selecting parameters for GA in such problems, a comprehensive empirical study is conducted. The study analyzes the effects of population size, number of iterations, crossover, and mutation probabilities on algorithm performance. It aims to identify universal patterns for optimal parameter combinations and provide guidance for parameter selection in GA for UAV trajectory planning with obstacle avoidance. © 2023 ACM.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Source-level reasoning for quantitative information flow

arXiv

引用

arXiv 2024年

作者： Chen, Chris McIver, Annabelle Morgan, Carroll School of Computing Macquarie University Australia School of Engineering and Trustworthy Systems UNSW Australia

We present a novel formal system for proving quantitative-leakage properties of programs. Based on a theory of Quantitative Information Flow (QIF) that models information leakage as a noisy communication channel, it uses "gain-functions" for the description and measurement of expected leaks. We use a small imperative programming language, augmented with leakage features, and with it express adversaries’ activities in the style of, but more generally than, the Hoare triples or expectation transformers that traditionally express deterministic or probabilistic correctness but without information flow. The programs are annotated with "gain-expressions" that capture simple adversarial settings such as "Guess the secret in one try." but also much more general ones;and our formal syntax+logic -based framework enables us to transform such gain-expressions that apply after a program has finished to ones that equivalently apply before the program has begun. In that way we enable a formal proof-based reasoning system for QIF at the source level. We apply it to the language we have chosen, and demonstrate its effectiveness in a number of small but sometimes intricate situations. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cirrhosis Prediction in Chronic Liver Disease Patients Using Machine Learning Techniques 3

Cirrhosis Prediction in Chronic Liver Disease Patients Using...

引用

3rd International Conference on Pervasive computing and Social Networking, ICPCSN 2023

作者： Athish, V.P. Sree Nandha, S.S. Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Dept. of Data Science and Business Systems Tamilnadu Kattankulathur603203 India

ISBN: (纸本)9798350322842

Liver failure is a serious medical condition that can have life-threatening consequences. The liver is responsible for filtering blood and performing many other important functions. With the rise of machine learning in healthcare, there is an opportunity to use past datasets to predict liver failure early on. The main focus of this research work is to explore the application of supervised machine learning algorithms in predicting liver failure. The study involved pre-processing techniques such as univariate and bivariate analysis, and data visualization to gain better insights into the features of the dataset. Using these techniques, a multi-class classification model was built with machine learning algorithms, and the performance metrics of accuracy, F1 score, and recall were used to compare the algorithms. The results show that machine learning algorithms can accurately predict liver failure and can be an effective tool in healthcare. This study demonstrates the potential of machine learning in predicting liver failure and can contribute to the development of future models in the field. The results of this research study indicates that the proposed algorithm achieved an accuracy of 94.48%. The proposed work will be beneficial to researchers in this field and inspire them to build more advanced and accurate models. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Provably Secure Post-Quantum Based EDHOC Protocol 22

A Provably Secure Post-Quantum Based EDHOC Protocol

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Yadav, Awaneesh Kumar Shojafar, Mohammad Braeken, An School of Computing and Electrical Engineering Indian Institute of Technology Mandi India Institute for Communication Systems University of Surrey 5G/6GIC Guildford United Kingdom Brussel Belgium

ISBN: (纸本)9798331508050

Transport Layer Security (TLS) is considered to be the most used standard security protocol for the Internet of Things (IoT). However, as TLS was originally designed for computer networks, it is not optimal with respect to efficiency. Therefore, a new protocol called Object Security for Constrained RESTful Environments (OSCORE) has been standardized for securing constrained devices. Currently, the Ephemeral-Diffie-Hellman-Over-COSE (EDHOC) protocol, which is a key exchange protocol to define a session key used in OSCORE, is also in the process of being standardized. EDHOC consists of four authentication modes, each offering different security strengths and performance. However, these modes are not yet secure against quantum attacks. Since we are in a transition period and do not yet possess deeply analyzed post-quantum algorithms, we propose a generic hybrid protocol. As such, the protocol can easily update from one post-quantum algorithm to the other and becomes secure against either a post-quantum attack or a potential attack against a newly defined post-quantum algorithm. The proposed mode does not require any changes to the original EDHOC protocol and offers perfect backward compatibility. The security is ensured using Real-Or-Random (ROR) logic, and additional performance costs are analyzed using different variants of post-quantum algorithms. © 2025 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

On Crop Canopy Scattering for Integrated mmWave Sensing and Communication in Agricultural Fields 20

On Crop Canopy Scattering for Integrated mmWave Sensing and ...

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart systems, MASS 2023

作者： Nie, Shuai Ge, Yufeng Vuran, Mehmet C. University of Nebraska-Lincoln School of Computing LincolnNE United States University of Nebraska-Lincoln Biological Systems Engineering LincolnNE United States

ISBN: (纸本)9798350324334

Millimeter-wave (mmWave) spectrum offers wide bandwidth resources that are promising to realize high-throughput wireless communications in agricultural fields. Due to the relatively small wavelength at this frequency band, mmWave signals tend to be scattered when the wireless link is established above the crop canopy. However, little is known about the scattering effect caused by crop canopy at mmWave. In this work, the scattering loss in the mmWave spectrum is quantified for different crop canopy states that are represented by the leaf area index. In particular, an approach based on a Rayleigh roughness criterion is utilized, coupled with canopy height statistics, to calculate the scattering loss. The results of the model agree well with empirical data collected from agricultural field experiments conducted in Summer 2021. The results demonstrate that as the leaf area index decreases with crop maturity, the scattering loss also decreases. This is the first work that illustrates the feasibility of using the mmWave communication links to perform sensing on the leaf area index, which is a critical metric in estimating crop conditions. © 2023 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Models in Power Generation for Energy Consumption Prediction

Artificial Intelligence Models in Power Generation for Energ...

引用

International Conference on Emerging Trends in Networks and Computer Communications (ETNCC)

作者： Lit Yang Tan Charis Shwu Chen Kwan Samuel-Soma M. Ajibade Athirah Mohd Ramly Department of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Malaysia Department of Computing School of Architecture Computing and Engineering University of East London London UK

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

The incorporation of artificial intelligence (AI) into power-related applications signifies a new and unexplored domain in machine learning for predicting power generation. This novel method utilizes prediction models, often used in different fields, to predict energy-related patterns, providing a unique and specialized viewpoint. The synergy of academicians, AI experts, and industry professionals in the energy sector has resulted in the creation of customized AI models to optimize operational efficiency. By customizing various AI models to suit the distinct attributes of energy scenarios and datasets, these models are positioned to transform energy management methods. This study examines the utilization of AI models to enhance energy efficiency in power generation in Malaysia. The project seeks to predict future power consumption in various sectors, analyze growth rates, and identify sectors with investment potential by developing a Linear Regression model. In addition, a thorough power plan is developed using the estimated energy usage. A comparative analysis is performed to determine the most appropriate model for this particular scenario, which will improve decision-making in the energy sector. The results of this study present promising opportunities for further investigation. By broadening the study's focus to encompass a broader array of AI models and their assessment of performance, it is possible to gain useful insights for predicting power generation. Furthermore, the integration of real-time data streams and the inclusion of feedback loops in the AI models could improve their ability to adapt and increase their accuracy as time progresses.

关键词： Adaptation models Energy consumption Analytical models Linear regression Artificial neural networks Predictive models Data models Artificial intelligence Power generation Streams

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：