检索结果-内蒙古大学图书馆

Drawing Order Diagrams Through Two-Dimension Extension

Journal of Graph Algorithms and Applications 2023年第9期27卷 783-802页

作者： Dürrschnabel, Dominik Hanika, Tom Stumme, Gerd Knowledge & Data Engineering Group Research Center for Information System Design & Department of Electrical Engineering and Computer Science University of Kassel Germany Institute of Computer Science University of Hildesheim Germany Berlin School of Library and Information Science Humboldt-Universität zu Berlin Germany

Ordinal real-world data such as concept hierarchies, ontologies, genealogies, or task dependencies in scheduling often has the property to not only contain pairwise comparable, but also incomparable elements. Order diagrams provide an important tool for understanding and thus discovering knowledge in such data. Easily readable drawings of such order diagrams are hard to come by, even for small ordered sets. Many attempts were made to transfer classical graph drawing approaches to order diagrams. Although these methods produce satisfying results for some ordered sets, they unfortunately perform poorly in general. In this work, we present the novel algorithm DimDraw to decompose an ordered set (e.g., a concept hierarchy) in linear orders and to produce a corresponding order diagram. This algorithm is based on a relation between the dimension of an ordered set and the bipartiteness of its transitive incompatibility graph. To evaluate the quality of the algorithm, a user study was conducted where generated drawings were compared with ones from state-of-the-art drawing algorithms. © 2023 Brown University. All rights reserved.

关键词： Set theory

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Transfer Learning for Enhanced Brain Tumor Detection through the Integration of MobileNetV2 and InceptionV3 3

Hybrid Deep Transfer Learning for Enhanced Brain Tumor Detec...

引用

3rd International Conference on Machine Learning and data Engineering, ICMLDE 2024

作者： Ogundokun, Roseline Oluwaseun Awoniyi, Charles Adebola, Nabeela T. Akinyemi, Akinrotimi Akinpelu, Samson Adebisi Adigun, Matthew O. Department of Centre of Real Time Computer Sciences Kaunas University of Technology Kaunas44249 Lithuania Department of Computer Science Landmark University Omu Aran Nigeria Bupa Insurance United Kingdom Data Science Department University of Salford United Kingdom Department of Computer Science Caleb University Lagos Imota Nigeria School of Mathematics Statistics and Computer Science University of Kwazulu Natal Durban South Africa Department of Computer Science University of Zululand Kwadlangezwa South Africa

Brain Tumors (BT) are one of the most hazardous diseases in the world, primarily because of the speed at which they spread and high mortality rates. Hence, diagnosing BT at an early stage with higher accuracy is necessary. Recent breakthroughs in deep transfer learning have achieved great performances in identifying common types of BT, such as glioma, meningioma, and pituitary tumors. In this paper, we will propose a novel hybrid deep transfer learning architecture by combining the strengths of two state-of-the-art pre-trained deep convolutional neural networks: MobileNetV2 and InceptionV3. We implement a parallel feature extraction process, reduce dimensionality in the extracted features using dropout techniques, and pass the refined data through fully connected layers for accurate classification. In this context, our two-step methodology of sub-image classification and final image categorisation with the help of majority voting and maximum probability principles shows much-improved results. Validated on a comprehensive BT dataset, our approach achieves 98.68% accuracy, 97% precision, 97.25% recall, and 97% F-measure with 0.9975 AUC and average precision of 99.50%. The outcomes surpass the performance of existing models on precision, sensitivity, and generalization, thus revealing the value that this technique may hold in whole-slide MRI image classification and clinical practice. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design Principle Transfer in Neural Architecture Search via Large Language Models 39

Design Principle Transfer in Neural Architecture Search via ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Xun Wu, Xingyu Feng, Liang Lu, Zhichao Tan, Kay Chen Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge accumulated in previous search processes is reused to warm up the architecture search for new tasks. However, existing TNAS methods still search in an extensive search space, necessitating the evaluation of numerous architectures. To overcome this challenge, this work proposes a novel transfer paradigm, i.e., design principle transfer. In this work, the linguistic description of various structural components’ effects on architectural performance is termed design principles. They are learned from established architectures and then can be reused to reduce the search space by discarding unpromising architectures. Searching in the refined search space can boost both the search performance and efficiency for new NAS tasks. To this end, a large language model (LLM)-assisted design principle transfer (LAPT) framework is devised. In LAPT, LLM is applied to automatically reason the design principles from a set of given architectures, and then a principle adaptation method is applied to refine these principles progressively based on the new search results. Experimental results show that LAPT can beat the state-of-the-art TNAS methods on most tasks and achieve comparable performance on others. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Design for testability

来源：评论

学校读者我要写书评

暂无评论

Public Awareness of Phishing in Indonesia: System Literature Review

Public Awareness of Phishing in Indonesia: System Literature...

引用

2023 International Conference on data science and Its Applications, ICoDSA 2023

作者： Chandra, Anthony William Chandiarta, Zefanya Setiyawan, Lutfi Gunawan, Alexander Agung Santoso Edbert, Ivan Sebastian Bina Nusantara University Cyber Security Program School of Computer Science Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350305197

In an era where technology is advancing at an unprecedented rate, the internet has become an indispensable tool for everyday life, offering both convenience and efficiency. While the internet has simplified tasks ranging from communication to information retrieval, it also poses significant challenges in the realm of cyber security. Users are not just potential victims but can also become unwitting perpetrators of cybercrimes. This highlights the urgent need for cyber security awareness among the general populace. Focusing on Indonesia, a nation where cyber security education is still in its infancy, this study aims to assess the level of public awareness regarding the specific threat of phishing. Employing the Systematic Literature Review (SLR) methodology, this research analyzes a comprehensive range of literature encompassing subjects such as phishing, data leakage, broader cyber security threats, and the current state of public awareness about phishing. The objective is to provide a detailed overview of existing knowledge and identify areas where educational efforts should be concentrated. The results indicate a considerable gap in the understanding of phishing among Indonesians. Many studies reviewed did not offer a clear definition or explanation of phishing, creating an environment where individuals are more susceptible to these cyber-attacks. This research underscores the urgent need for targeted educational initiatives aimed at increasing public awareness and understanding of phishing and other cyber threats. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Dysgraphia Disorder Detection and Classification Using Deep Learning Technique

引用

SN computer science 2025年第3期6卷 1-11页

作者： Manimekala, B. Umamaheswari, D. Rozario, Juliet Kannan, M. Savitha, P. Margaret Department of Computer Science School of Sciences Christ University Karnataka Bangalore India

Dysgraphia, a neurological condition, impedes children’s acquisition of standard writing abilities, leading to subpar written expression. Inadequate or underdeveloped writing proficiency can adversely affect a child’s educational progress and self-esteem. To address this issue, our study involved compiling a novel dataset of handwritten operations and extracting an array of features to encapsulate the various dimensions of handwriting characteristics. This research presents the Rotational Region Convolutional Neural Network (R2CNN) as a novel approach to tackle this issue. The R2CNN framework integrates a multitask refinement network for accurate tilted box detection and a text region proposal network (Text RPN) to identify potential text areas. To address the imbalance in the training categories and mitigate the overpopulation problem through feature elimination, a balance parameter is incorporated into the loss function. This research focused on identifying dysgraphia by analyzing these extracted features, which included both handwriting and geometric elements. The feature-learning stage of deep transfer learning effectively extracts and applies characteristics to identify dysgraphia. Research findings indicate that this study can use handwritten images to detect dysgraphia in children. The results of the data-gathering process show that this investigation can leverage samples of handwritten text to recognize dysgraphia among young individuals. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning Dysgraphia detection Handwriting diagnosis Rotating region CNN Text-RPN

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authenticated Key Agreement Protocol for Smart Power Grid Systems Using PUF

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2024年 5卷 3568-3580页

作者： Zahoor, Amina Mahmood, Khalid Saleem, Muhammad Asad Badar, Hafiz Muhammad Sanaullah Le, Tuan-Vinh Das, Ashok Kumar Department of Computer Science Sahiwal57000 Pakistan National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Emerson University Multan Department of Emerging Computing Technologies Multan61000 Pakistan Fu Jen Catholic University Bachelor's Program of Artificial Intelligence and Information Security New Taipei City24206 Taiwan International Institute of Information Technology Hyderabad Center for Security Theory and Algorithmic Research Hyderabad500032 India

The Smart Power Grid (SPG) is pivotal in orchestrating and managing demand response in contemporary smart cities, leveraging the prowess of Information and Communication Technologies (ICTs). Within the immersive SPG environment, the ubiquitous deployment of smart meters stands as a testament to their paramount importance in the realm of vigilant monitoring and oversight. These smart meters are installed on high-tension electricity lines and transmit information about electricity outages and other issues to the utility center. To access services from utility centers, smart meters need to communicate securely over a public channel, even though the network itself is insecure. However, potential attacks from adversaries ( Ad) can exploit this communication. Therefore, protecting this communication is of utmost importance. Several privacy-preserving authentication protocols designed for SPG have been introduced in the literature. Nevertheless, a significant number of these protocols exhibit vulnerabilities to diverse security attacks. This article introduces a lightweight and anonymous authentication protocol specifically designed to address these concerns in the SPG environment. Our protocol ensures both security and efficiency, surpassing other comparable protocols in terms of its lightweight nature. By employing both formal and informal analysis, we showcase the robustness of our protocol against significant attacks while remaining lightweight. The proposed protocol provides added security features and incurs 23.8879% lower computation cost than related protocols. Consequently, our protocol is highly suitable for implementation in the SPG system. © 2020 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Reinforcing Artificial Neural Networks through Traditional Machine Learning Algorithms for Robust Classification of Cancer

引用

computers, Materials & Continua 2023年第5期75卷 4293-4315页

作者： Muhammad Hammad Waseem Malik Sajjad Ahmed Nadeem Ishtiaq Rasool Khan Seong-O-Shim Wajid Aziz Usman Habib Department of Computer Sciences and Information Technology University of Azad Jammu and KashmirMuzaffarabad13100Pakistan Department of Computer Science and AI College of Computer Science and EngineeringUniversity of JeddahJeddah23890Saudi Arabia Department of Computer and Network Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah23890Saudi Arabia Department of AI&DS School of ComputingNational University of Computer and Emerging SciencesIslamabad44000Pakistan

Machine Learning(ML)-based prediction and classification systems employ data and learning algorithms to forecast target ***,improving predictive accuracy is a crucial step for informed *** the healthcare domain,data are available in the form of genetic profiles and clinical characteristics to build prediction models for complex tasks like cancer detection or *** ML algorithms,Artificial Neural Networks(ANNs)are considered the most suitable framework for many classification *** network weights and the activation functions are the two crucial elements in the learning process of an *** weights affect the prediction ability and the convergence efficiency of the *** traditional settings,ANNs assign random weights to the *** research aims to develop a learning system for reliable cancer prediction by initializing more realistic weights computed using a supervised setting instead of random *** proposed learning system uses hybrid and traditional machine learning techniques such as Support Vector Machine(SVM),Linear Discriminant Analysis(LDA),Random Forest(RF),k-Nearest Neighbour(kNN),and ANN to achieve better accuracy in colon and breast cancer *** system computes the confusion matrix-based metrics for traditional and proposed *** proposed framework attains the highest accuracy of 89.24 percent using the colon cancer dataset and 72.20 percent using the breast cancer dataset,which outperforms the other *** results show that the proposed learning system has higher predictive accuracies than conventional classifiers for each dataset,overcoming previous research ***,the proposed framework is of use to predict and classify cancer patients ***,this will facilitate the effective management of cancer patients.

关键词： ANN decision support systems gene-expression data hybrid classification machine learning predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Multimodal data Fusion Based on Generative Adversarial Network in University Teaching Evaluation

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第2期10卷 845-858页

作者： Liu, Min Teng, Hua Zhang, Hong Li, Hao School of Computer Science and Software Engineering Southwest Petroleum University Nanchong637001 China Department of Computer China West Normal University Nanchong637009 China Faculty of Computer and Information Science SouthWest University Chongqing400700 China Krirk University Bangkok10220 Thailand

With the advancement of educational evaluation reform and the popularization of higher education, university teaching quality evaluation has been a research hotspot in the field of educational evaluation. In response to the issue of multimodal heterogene-ity gap in current university education evaluation data, which makes it tough to integrate evaluation data, this article suggests a Multimodal data Fusion (MDF) method for university teaching evaluation relied on Generative Adversarial Network (GAN). Firstly, the MDF model is constructed from two aspects: establishing similarity network and designing regularization terms. By designing sparse regularization terms, the feature selection of multimodal samples is carried out to address the issue of large deviation of fusion data. Secondly, BERT pre-training model is adopted to extract the modal embedding features of teaching evaluation text, and Bi-LSTM is adopted to extract the audio and visual modal embedding features of teaching evaluation. Then, on the ground of the constructed MDF model, combined with the GAN and autoencoder, a multi-modal adversarial autoencoder learning model is established to reduce the heterogeneous gap between modes and form a unified representation. At last, the self-attention pretest network is established to achieve the automatic classification of multi-modal university teaching evaluation data. The experimental outcome implies that the accuracy, F1 value and determination coefficient R2 of the suggested method are 92.18%, 93.72% and 90.5%, respectively, which are superior to the comparison method, showing good classification performance. © 2025, J. Network Intell. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

sEMG-based Sarcopenia risk classification using empirical mode decomposition and machine learning algorithms

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 2901-2921页

作者： Kumar, Konki Sravan Lee, Daehyun Jamsrandoj, Ankhzaya Soylu, Necla Nisa Jung, Dawoon Kim, Jinwook Mun, Kyung Ryoul Center for Artificial Intelligence Korea Institute of Science and Technology Seoul Korea Republic of KHU-KIST Department of Converging Science and Technology Graduate School Kyung Hee University Seoul Korea Republic of Department of Human Computer Interface and Robotics Engineering University of Science and Technology Daejeon Korea Republic of Department of Computer Science Ozyegin University Istanbul Turkey

Early detection of the risk of sarcopenia at younger ages is crucial for implementing preventive strategies, fostering healthy muscle development, and minimizing the negative impact of sarcopenia on health and aging. In this study, we propose a novel sarcopenia risk detection technique that combines surface electromyography (sEMG) signals and empirical mode decomposition (EMD) with machine learning algorithms. First, we recorded and preprocessed sEMG data from both healthy and at-risk individuals during various physical activities, including normal walking, fast walking, performing a standard squat, and performing a wide squat. Next, electromyography (EMG) features were extracted from a normalized EMG and its intrinsic mode functions (IMFs) were obtained through EMD. Subsequently, a minimum redundancy maximum relevance (mRMR) feature selection method was employed to identify the most influential subset of features. Finally, the performances of state-of-the-art machine learning (ML) classifiers were evaluated using a leave-one-subject-out cross-validation technique, and the effectiveness of the classifiers for sarcopenia risk classification was assessed through various performance metrics. The proposed method shows a high accuracy, with accuracy rates of 0.88 for normal walking, 0.89 for fast walking, 0.81 for a standard squat, and 0.80 for a wide squat, providing reliable identification of sarcopenia risk during physical activities. Beyond early sarcopenia risk detection, this sEMG-EMD-ML system offers practical values for assessing muscle function, muscle health monitoring, and managing muscle quality for an improved daily life and well-being. © 2024 American Institute of Mathematical sciences. All rights reserved.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Leveraging MobileNet V2 for swift and precise identification of lung and colon cancers

Leveraging MobileNet V2 for swift and precise identification...

引用

2025 International Conference on Artificial Intelligence and data Engineering, AIDE 2025

作者： Pooja, H. Shivakumar, C. Varun, V. Renganayaki, S. Adithya, M. Sanjay Kumar, N.R. School of Computer Science and Engineering Ramanagara India Department of Information Science and Engineering Ramanagara India

ISBN: (纸本)9798331527518

Lung and colon cancers pose a significant global health challenge. Early detection is crucial for improved patient outcomes. This study investigates Applying deep learning to differentiate lung and colon cancer subtypes using the LC25000 dataset. The MobileNetV2 architecture was selected due to its efficiency and accuracy. The dataset was divided into five categories: Colon adenocarcinoma, non-neoplastic colon tissue, Malignant lung adenocarcinoma, Malignant lung squamous cell carcinoma, and non-neoplastic lung tissue. data augmentation techniques were applied to enhance model performance. The model achieved impressive accuracies of 97.57%, 98.00%, and 98.3% on the training, validation, and testing sets, respectively. These results highlight the potential of deep learning for rapid, accurate, and minimally invasive cancer detection, surpassing traditional methods. Our findings contribute to the development of more efficient and accessible cancer screening approaches. © 2025 IEEE.

关键词： Diseases

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

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

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：