检索结果-内蒙古大学图书馆

20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, ISA 2024

作者： Petliak, Nataliia Alcaina, Cristina F. Fučíková, Eva Hajič, Jan Urešová, Zdeňka ÚFAL MFF UK Charles University Faculty of Mathematics and Physics Computer Science School Malostranské nám. 25 Prague 1 Czech Republic

ISBN: (纸本)9782493814326

This short demo description paper presents a new tool designed for searching an event-type ontology with rich information, demonstrated on the SynSemClass (Urešová et al., 2022) ontology resource (version 5.0, (Urešová et al., 2023)). The tool complements a web browser, created by the authors of the SynSemClass ontology previously. Due to the complexity of the resource, the search tool offers possibilities both for a linguistically-oriented researcher as well as teams working with the resource from a technical point of view, such as building role labeling tools, automatic annotation tools, etc. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Advanced brain tumor segmentation using DeepLabV3Plus with Xception encoder on a multi-class MR image dataset

引用

Multimedia Tools and Applications 2025年 1-22页

作者： Saifullah, Shoffan Dreżewski, Rafal Yudhana, Anton Faculty of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia

Accurate segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans presents notable challenges. This particularly in differentiating tumors from surrounding tissues with similar intensity. This study utilizes the DeepLabV3Plus model with an Xception encoder to address these challenges. We evaluated the model on a dataset of 3064 MR images, which included meningioma, glioma, and pituitary tumors. The model achieved high segmentation performance, with an accuracy of 0.9991, Dice Similarity Coefficient (DSC) of 0.9529, and Jaccard Index (JI) of 0.9133. It also demonstrated substantial boundary precision, recording an Average Symmetric Surface Distance (ASSD) of 0.84 mm and a Hausdorff Distance (HD) of 2.3 mm. These metrics surpass those of existing state-of-the-art models. While the model performed well with well-defined tumor boundaries, it faced challenges segmenting tumors with ambiuous edges. These findings suggest significant potential for enhancing diagnostic accuracy in neuro-oncology. Future work will focus on enhancing the model’s sensitivity to subtle tumor features and expanding the dataset to include a broader range of tumor characteristics. Additionally, incorporating multimodal imaging data could further improve segmentation precision. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Fine-Tuning For Low-resource Englishbased Creole with Pre-Trained LLMs

Two-Stage Fine-Tuning For Low-resource Englishbased Creole w...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data Engineering, CSDE 2023

作者： Amanda Tan, Shu Hui Aung, Eint Sandi Yamana, Hayato Department of Computer Science and Communications Engineering Waseda University Tokyo Japan Waseda University Faculty of Science and Engineering Tokyo Japan

ISBN: (纸本)9798350341072

Sentiment analysis adopts natural language processing (NLP) techniques to determine the emotional tone of the text. Sentiment analysis research has predominantly been conducted on commonly spoken languages, such as English and Mandarin Chinese. However, less widely spoken languages, such as Englishbased Creoles, have received limited attention due to the need for large-scale labeled datasets. English-based Creoles are derived from English, resulting in many similarities with English. However, English-based Creoles differ from English in some aspects, making the Creole unintelligible to other English speakers. In sentiment analysis research conducted on Singapore English-based Creole (Singlish), most existing research does not leverage the capabilities of large-language models, such as pretrained BERT. To our knowledge, only Gotera et al.'s work relates to a large-language model;however, their contribution is creating a new pre-trained model for Singlish. However, creating a new pre-trained model is computationally expensive, and pre-training a less widely spoken language will result in ineffective because of the small dataset. Hence, we propose a new two-stage fine-tuning framework for pre-trained models, targeting a low-resource English-based Creole, Singlish. Our proposed framework initially clusters the dataset into two based on each data point's percentage of English words. Then, two-stage fine-tuning is performed by transferring the pre-trained BERT model onto the clustered dataset with the higher English percentage in the first stage. The model is further transferred onto the clustered dataset with the lower English percentage in the second stage. Our proposed framework outperforms the traditional fine-tuning framework, achieving a weighted F1 score of 0.8344 for sentiment analysis. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hybrid Genetic-Ant Colony Optimization for Dynamic Self-Healing and Network Performance Optimization in 5G/6G Networks

引用

Procedia computer science 2025年 252卷 404-413页

作者： Aanchal Agrawal A.K. Pal Department of Mathematics Statistics & Computer Science GBPUAT Pantnagar Uttarakhand 263145 India

The rapid growth of 5G/6G networks requires resilient solutions to optimize network performance while ensuring adaptability against failures. This paper introduces a novel Adaptive Hybrid Genetic-Ant Colony Optimization (GA-ACO) framework, designed for dynamic self-healing and multi-objective performance optimization in next-generation mobile networks. The developed method combines the global optimization competencies of a Genetic Algorithm (GA) with the local rerouting performance of Ant Colony Optimization (ACO), developing a dynamic switching mechanism. When no faults are detected, GA optimizes critical objectives such as latency minimization, bandwidth utilization, and energy efficiency. After identifying network faults, such as base station failures, ACO quickly reroutes impacted devices to preserve fault tolerance and minimize downtime. Main network metrics, including latency, bandwidth utilization, energy efficiency, and fault tolerance, are optimized at the same time utilizing a weighted-sum fitness function. The model adjusts dynamically to changing network situations, making it perfectly appropriate for real-time applications in 5G/6G networks, such as smart cities and mission-critical communications. Simulation results show the efficiency of the GA-ACO hybrid, demonstrating improved network efficiency and rapid recovery during failures. This innovative adaptive approach guarantees a more effective, efficient, and sustainable mobile communication network, competent of facing the complex needs of future 5G/6G technologies.

关键词： Sustainable mobile communication Dynamic self-healing network performance optimization ant colony optimization bandwidth utilization

来源：评论

学校读者我要写书评

暂无评论

引用

12th Italian Information Retrieval Workshop, IIR 2022

作者： Balloccu, Giacomo Boratto, Ludovico Fenu, Gianni Marras, Mirko Department of Mathematics and Computer Science University of Cagliari Cagliari Italy

Modern knowledge-based recommender systems enable the end-to-end generation of textual explanations. These explanations are created from learnt paths between an already experience product and a recommended product in a knowledge graph, for a given user. However, none of the existing studies has investigated the extent to which properties of a single explanation (e.g., the recency of interaction with the already experience product) and of a group of explanations for a recommended list (e.g., the diversity of the explanation types) can influence the perceived explanation quality. In this paper, we summarize our previous work on conceptualizing three novel properties that model the quality of the explanations (linking interaction recency, shared entity popularity, and explanation type diversity) and proposing re-ranking approaches able to optimize for these properties. Experiments on two public data sets showed that our approaches can increase explanation quality according to the proposed properties, while preserving recommendation utility. Source code and data: https://***/giacoballoccu/explanation-quality-recsys. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Distance Awareness Using Deep Learning Method 7th

Deep Learning in Distance Awareness Using Deep Learning Meth...

引用

7th International Conference on Microelectronics and Telecommunication Engineering, ICMETE 2023

作者： Hussein, Raghad I. Onaizah, Ameer N. Faculty of Pharmacy University of Kufa Najaf Iraq School of Automation Beijing Institute of Technology Zhongguancun Beijing100811 China Faculty of Computer Science and Mathematics University of Kufa Kufa Iraq

ISBN: (纸本)9789819995615

Recent studies have shown that deep learning does pretty well at reproducing 3D scenes using multiple-view images or videos. Nevertheless, these restorations do not expose the personalities of the items, and item identification is necessary for such a scene to work in augmented worlds or interactive features. The objects in a picture that have been reconstructed as a unified mesh are handled as a singular body rather than being seen as independent categories that can be engaged with or changed. Reconstructing an entity three-dimensional image from a two-dimensional image is challenging since the transformation from a visual scene to a picture is permanent and reduces a dimensionality. In addition to creating more exact shapes when compared with previous methodologies for mesh rebuilding from individual images, our approach exhibited improved achievement in initiating comprehensive meshes when compared to strategies using only inherent portrayal mesh rebuilding networks (for instance, neighborhood deep implicit functions). By applying the multi-modal instructional methods, this was done. Real-world facts were utilized to assess the effectiveness of the suggested method. The results showed that it might perform noticeably better than earlier methods for entity 3D scene rebuilding. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Fused Transformers: Fused Information of Arabic long Article for Summarization 6

Fused Transformers: Fused Information of Arabic long Article...

引用

6th International Conference on AI in Computational Linguistics, ACLing 2024

作者： Ezzat, Zeyad Khalfallah, Ayman Khoriba, Ghadad Center for Informatics Science Information Technology and Computer Science School Nile University Giza Egypt Computer and Systems Department Faculty of Engineering Alexandria University Alexandria Egypt Applied Innovation Centre Egypt Faculty of Computers and Artificial Intelligence Helwan University Cairo Egypt

This paper introduces a novel approach for extending the applicability of pre-trained models to accommodate longer texts. Addressing the inherent limitation of quadratic performance in attention models within transformers, we propose the concept of fused transformers. By integrating new adaptor techniques, we enhance the encoding of lengthy text segments by breaking them into shorter spans. Subsequently, these segments are fused to increase the model's effectiveness in processing extended texts. This fusion mechanism serves to fortify the model's capacity for fine-tuning. Furthermore, we implement a length-based curriculum for expedited training Our experiments yielded 16 Rouge-2 points, representing a doubling of the score achieved by the vanilla fine-tuning method on the newly introduced "Mukhtasar" dataset for summarization. This highlights the effectiveness of managing complex relations among text segments and confirms that our method can outperform conventional training approaches. © 2024 Elsevier B.V.. All rights reserved.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

A 32-bit efficient subpipelined architecture for AES encryption and decryption 18

A 32-bit efficient subpipelined architecture for AES encrypt...

引用

18th International Conference on Computational Intelligence and Security, CIS 2022

作者： Li, Ke Li, Hua Mund, Graeme University of Lethbridge Department of Mathematics and Computer Science Lethbridge Canada

ISBN: (纸本)9798350346275

A new 32-bit sub-pipelined compact architecture for fast AES encryption and decryption is presented in this paper. The proposed fully composite field GF((24)2) based subpipelined encryption/decryption and keyschedule lead to the lower hardware complexity. The design has higher throughput and lower hardware cost and can be efficiently applied in computing restricted environments. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effectiveness of Machine Learning Algorithms in Vehicle Insurance Fraud Prediction: A Comparative Approach 3

Assessing the Effectiveness of Machine Learning Algorithms i...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Satone, Aditya P. Daronde, Subodh Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Due to the wealth of information accessible on many insurance issues, including travel and auto insurance, individuals are becoming more and more impacted by these kinds of insurance in today's society. But this tendency also makes room for dishonest practices. Insurance fraud is harmful and unlawful, regardless of who commits it - the vendor or the customer. Fraud can come from both the customer and the vendor. The consumer may commit fraud by filing exaggerated claims or using out-of-date policies, while the vendor may market insurance from phoney firms or neglect to submit premiums. This paper presents a comparative analysis of various classification algorithms, including Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Linear Regression (LR), and Polynomial Regression, for detecting insurance fraud. The performance of these algorithms is evaluated using key metrics such as Precision, Recall, and F1-Score. The analysis reveals that the bestperforming model is the Random Forest, with a Mean Squared Error (MSE) of 6.50, outperforming the other techniques. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhanced Keystroke Dynamics Authentication Using Keystroke Vector Dissimilarity 15

Enhanced Keystroke Dynamics Authentication Using Keystroke V...

引用

15th International Conference on Information Technology and Electrical Engineering, ICITEE 2023

作者： Bussabong, Naphat Anusas-Amornkul, Tanapat King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Computer and Information Science Bangkok Thailand

ISBN: (纸本)9798350304466

A keystroke dynamics is a simple example of a biometric authentication by using a typing rhythm on a keyboard without any special device. Previous research used Euclidean distance to distinguish between an authentic user and an imposter [1]. However, the Euclidean distance has a flaw in that a distance could be the same even though the keystroke rhythms are different. Therefore, this paper proposed to enhance the keystroke dynamics authentication by using a keystroke vector and calculating a standard deviation for each key to give different weights such that the variations of each keystroke is taking into account. A dataset is similar in [1] but some data is different. The performance was measured using Equal Error Rate (EER) and the result showed that the EER was 3.33%, compared to 4% in [1]. © 2023 IEEE.

关键词： Authentication

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：