检索结果-内蒙古大学图书馆

2024 International Conference on Image Processing and Artificial Intelligence, ICIPAl 2024

作者： Zhu, Xuhui Han, Bo Li, Dongliang School of Computer and Information Engineering Key Laboratory of Functional Materials and Devices for Informatics of Anhui Higher Education Institutes Fuyang Normal University Fuyang China

ISBN: (纸本)9781510681514

This paper proposes a new neural network model, series connection UNet (SC-UNet). The network model is composed of two series of UNet modules. The residual module and the attention mechanism gate are added to the model to make the back-propagation faster and focus the model's attention on the target region. In the medical image segmentation task of lung X-ray pictures, compared with the single UNet model, the average crossover ratio, mean pixel accuracy, average accuracy rate, and mean recall rate of the model structure increased by 4.51%, 3.98%, 0.45%, and 4.00% respectively. Experiments show that the SC-UNet model has significant advantages over the UNet model in medical image segmentation. © 2024 SPIE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A TOPOLOGICAL CHARACTERIZATION OF THE EXISTENCE OF w-STABLE SETS

arXiv

引用

arXiv 2024年

作者： Andrikopoulos, Athanasios Sampanis, Nikolaos Dept. of Computer Engineering and Informatics University of Patras Patras26504 Greece Department of Computer Engineering & Informatics University of Patras Greece

The theory of optimal choice sets is a solution theory that has a long and well-established tradition in social choice and game theories. Some of important general solution concepts of choice problems when the set of best alternatives does not exist (this problem occurs when the preferences yielded by an economic process are cyclic) is the Stable Set (Von Neumann-Morgenstern set) and its variants (Generalized Stable set, Extended Stable set, m-Stable set and w-Stable set). The theory of w-stable sets solution is more realistic because: (1) It solves the existence problem of solution;(2) It expands the notions of maximal alternative set and (3) The concept of stability is defined in such a way as to prevent a chosen alternative from being dominated by another alternative and sets this stability within the solution. In this paper, we present a topological characterization of the existence of w-Stable sets solution of arbitrary binary relations over non-finite sets of alternatives. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Clustering High-Dimensional Social Media Datasets sutilizing Graph Mining

Clustering High-Dimensional Social Media Datasets sutilizing...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Kanavos, Andreas Vonitsanos, Gerasimos Mylonas, Phivos Ionian University Department of Informatics Corfu Greece University of Patras Computer Engineering and Informatics Department Patras Greece

ISBN: (纸本)9781665480451

Social networks are an essential component of people' daily lives, and as a result, much academic attention has been focused on them. The rapid adoption of machine learning as a problem-solving tool, which simplifies and accelerates numerous tasks while enabling the processing of large volumes of data, has played a significant role in this field of research. This is in contrast to the more traditional approaches that lacked this momentum. Characterization of linkages and cluster identification i n social networks are two of the research community's most well-known issues. The goal of this study is to gather data for a set of users who are then divided into groups based on the hashtags they used in their Twitter postings. The procedure performed generates the numerical data, in following reduces the dimensions, and finally performs the clustering. © 2022 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Architecture of Convolutional Neural Network (CNN) for Intracranial Hemorrhage Prediction from CT-Scan Images 27

Enhanced Architecture of Convolutional Neural Network (CNN) ...

引用

27th International computer Science and engineering Conference, ICSEC 2023

作者： Badriyah, Tessy Luhukay, Sherly Febrina Syarif, Iwan Faradisa, Rosiyah Informatics and Computer Engineering Department Kampus PENS JL. Arief Rahman Hakim Sukolilo Surabaya60111 Indonesia

ISBN: (纸本)9798350342109

Head injury is the leading cause of mortality and morbidity and often results in pathological bleeding inside the skull, known as Intracranial Hemorrhage (ICH). Currently, the diagnosis of ICH and its type is still manually performed by taking brain images, commonly known as CT scans, which are then analyzed by experienced radiology specialists. In this study, a Convolutional Neural Network (CNN) modeling was conducted as a tool for doctors to detect ICH based on CT scans images. The CNN architecture used to build the classification model underwent four variations of adjustments until the recommended CNN architecture was obtained. With enhanced architecture, the classification achieved an average accuracy of 80% for each type of brain hemorrhage. The study shows that modifying the CNN architecture leads to obtaining a recommended architecture, which ultimately yields a more precise model compared to the initial architecture. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Mobility-Aware Workload Distribution and Task Allocation for Mobile Edge Computing Networks 1st

Mobility-Aware Workload Distribution and Task Allocation fo...

引用

1st International Conference on Advances in Computing Research, ACR’23

作者： Karras, Aristeidis Karras, Christos Giannaros, Anastasios Tsolis, Dimitrios Sioutas, Spyros Computer Engineering and Informatics Department University of Patras Patras Greece Department of History and Archaeology University of Patras Patras Greece

ISBN: (纸本)9783031337420

Mobile Edge Computing (MEC) is a promising computing paradigm that provides computing and storage services for mobile and big data applications. MEC servers are deployed at base stations to establish a mobile edge network (MEN) where mobile users can offload tasks to nearby servers to speed up their mobile applications. However, challenges such as the quality of workload distribution in edge computing environments still need to be tackled. Most studies and offloading strategies assume mobile users are stationary, but in reality, users move and this affects workload distribution and response time of mobile applications. In this work, we propose a solution that addresses these challenges by reducing energy consumption and enhancing QoS by assigning mobile tasks to MEC servers in the users’ predicted trajectories using a Random waypoint Model. We propose OptiMEC for scheduling mobile tasks in a Mobile Edge Computing (MEC) environment in 5G networks that utilize central-base stations. We consider the task properties, user mobility, and delay constraints in our proposed algorithmic scheme and we also propose an energy-load balancing heuristic. The problem is formulated as an optimization and constraint satisfaction problem and we propose a near-optimal solution for scheduling mobile tasks to MEC servers. The results of our simulation experiments show that our proposed solution can significantly reduce energy consumption in Mobile Edge Networks (MENs) and improve QoS by executing tasks under constrained time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Reservoir Permeability Prediction Using GPR with Grey Relational Grades and Uncertainty Quantification 7

A Novel Framework for Reservoir Permeability Prediction Usin...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Lawal, Ahmad Yang, Yingjie Baisa, Nathanael L. He, Hongmei De Montfort University School of Computer Science and Informatics Leicester United Kingdom University of Salford School of Science Engineering and Environment Manchester United Kingdom

ISBN: (纸本)9798350350890

Reservoir permeability prediction is crucial for hydrocarbon exploration and production. Traditional methods have limitations, and Gaussian Process Regression (GPR) offers a powerful alternative. However, GPR can be sensitive to kernel parameters. This paper proposes a novel framework, GPR with Grey Relational Lengthscale Adaptation (GRLA-GPR), that incorporates Grey Relational Grades (GRG) from NMR log data into GPR lengthscale updates to improve permeability prediction with a focus on uncertainty quantification. The framework utilizes a Radial Basis Function (RBF) and Matern kernels' GPR model and calculates GRG to capture relationships between NMR data sequences. The calculated GRG values are then used to update the GPR lengthscale during training. A validation strategy is employed to evaluate the performance. The effectiveness of the framework is assessed using accuracy metrics (mean absolute error, mean squared error and R^2) and uncertainty quantification metrics (variance and prediction interval normalized average width). The results are compared to a baseline GPR model without GRG-based updates. The proposed framework achieved a better performance in terms of accuracy and uncertainty quantification, providing more reliable permeability estimates for informed decision-making in reservoir characterization. © 2024 IEEE.

关键词： Nuclear magnetic logging

来源：评论

学校读者我要写书评

暂无评论

DocFlow: A Visual Analytics System for Question-Based Document Retrieval and Categorization

引用

IEEE Transactions on Visualization and computer Graphics 2024年第2期30卷 1533-1548页

作者： Qiu, Rui Tu, Yamei Wang, Yu-Shuen Yen, Po-Yin Shen, Han-Wei The Ohio State University Department of Computer Science and Engineering ColumbusOH43210-1132 United States National Yang Ming Chiao Tung University Department of Computer Science HsinChu300 Taiwan Washington University School of Medicine Institute for Informatics St. LouisMO63110 United States

A systematic review (SR) is essential with up-to-date research evidence to support clinical decisions and practices. However, the growing literature volume makes it challenging for SR reviewers and clinicians to discover useful information efficiently. Many human-in-the-loop information retrieval approaches (HIR) have been proposed to rank documents semantically similar to users' queries and provide interactive visualizations to facilitate document retrieval. Given that the queries are mainly composed of keywords and keyphrases retrieving documents that are semantically similar to a query does not necessarily respond to the clinician's need. Clinicians still have to review many documents to find the solution. The problem motivates us to develop a visual analytics system, DocFlow, to facilitate information-seeking. One of the features of our DocFlow is accepting natural language questions. The detailed description enables retrieving documents that can answer users' questions. Additionally, clinicians often categorize documents based on their backgrounds and with different purposes (e.g., populations, treatments). Since the criteria are unknown and cannot be pre-defined in advance, existing methods can only achieve categorization by considering the entire information in documents. In contrast, by locating answers in each document, our DocFlow can intelligently categorize documents based on users' questions. The second feature of our DocFlow is a flexible interface where users can arrange a sequence of questions to customize their rules for document retrieval and categorization. The two features of this visual analytics system support a flexible information-seeking process. The case studies and the feedback from domain experts demonstrate the usefulness and effectiveness of our DocFlow. © 1995-2012 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Combining TL and KD for Object Detection Model Compression 13

Combining TL and KD for Object Detection Model Compression

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Peng, Yuhan Lyu, Yan Zhao, Qiangfu The University of Aizu Computer Science and Engineering Aizuwakamatsu965-8580 Japan Muroran Institute of Technology Sciences and Informatics Muroran050a-8585 Japan

ISBN: (纸本)9798350373332

In modern society, object detection tasks have become extremely important due to their numerous applications in fields such as autonomous driving, surveillance, and healthcare. Real-time detection is particularly crucial for many applications. However, with the advancements in deep learning-based object detection methods, high performance often comes with high computational resource requirements, posing challenges for real-time monitoring, especially on resource-constrained devices. To address this issue, we study model compression using both transfer learning (TL) and knowledge distillation (KD). Specifically, we use the YOLOv5n model as a test case to show the basic idea for improving the performance of a small student model using a larger dataset for TL and a larger model for KD. As for KD, we further investigate feature-based and output-based KD. Experimental results show that the small student model can be improved significantly using TL and KD, with the mean Average Precision (mAP0.5) being increased by 13.28% compared to the baseline model. These results demonstrate the effectiveness of TL and KD in achieving high detection performance while reducing computational demands, making them suitable for various real-world applications. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Base and Stitch: Evaluating eTextile Interfaces from a Material-Centric View 24

Base and Stitch: Evaluating eTextile Interfaces from a Mater...

引用

18th International Conference on Tangible, Embedded, and Embodied Interaction, TEI 2024

作者： Rallabandi, Vineetha Haynes, Alice C. Reed, Courtney N. Strohmeier, Paul Sensorimotor Interaction Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany Human Computer Interaction Lab Saarland University Saarland Informatics Campus Saarbrücken Germany Biomedical Engineering and Imaging Sciences King's College London London United Kingdom

ISBN: (纸本)9798400704024

Fabrics are seen as the foundation for e-textile interfaces but contribute their own tactile properties to interaction. We examine the role of fabrics in gestural interaction from a novel, textile-focused view. We replicated an eTextile sensor and interface for rolling and pinching gestures on four different fabric swatches and invited 6 participants, including both designers and lay-users, to interact with them. Using a semi-structured interview, we examined their interaction with the materials and how they perceived movement and feedback from the textile sensor and a visual GUI. We analyzed participants' responses using a joint, reflexive thematic analysis and propose two key considerations for research in e-textile design: 1) Both sensor and fabric contribute their own, inseparable materiality and 2) Wearable sensing must be evaluated with respect to culturally situated bodies and orientation. Expanding on material-oriented design research, we proffer that the evaluation of eTextiles must also be material-led and cannot be decontextualized and must be grounded within a soma-aware and situated context. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Smart textiles

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Utilization of Grammatical Structures of Arabic Language in Hiding Bits

Evaluating the Utilization of Grammatical Structures of Arab...

引用

2024 Advances in Science and engineering Technology International Conferences, ASET 2024

作者： Rihan, Yazen Altaweel, Ala Khattab, Khattab Kamel, Ibrahim University of Sharjah College of Computing and Informatics Department of Computer Engineering Sharjah United Arab Emirates Ondokuz Mayis University Faculty of Ilahiyat Samsun Turkey

ISBN: (纸本)9798350344134

Nowadays, there is massive volume of data transmitted constantly through digital mediums. This data faces the risks of various cyber-attacks like eavesdropping, traffic analysis, packet injection, and packet dropping. There has been several security mechanisms to secure sensitive data and ensure their confidentiality, integrity, and availability. Indeed, Encryption, which is the process of converting the plain-text data into a non-understandable form known as the cipher-text, can secure the sensitive data. However, Encryption techniques are costly in terms of computational resources. Steganography, on the other hand, attempts to exploit the redundancy in data representation and structure to hide secret information within the data. Text steganography refers to the art of hiding secret information inside long passages of text. This paper proposes a new text steganography technique that exploits grammatical structures of Arabic language. Specifically, the paper exploits the redundancy in the language structure of Arabic grammar. The paper also presents the results of applying the proposed technique on a large dataset of articles from different categories such as politics, sports, and religion. The conducted experiments measure the number of secret bits that can be hidden in 1000 words for each category. The results show that some steganography rules can perform differently when annlied to different categories of text. © 2024 IEEE.

关键词： Data integrity

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：