检索结果-内蒙古大学图书馆

6th Natural Legal Language Processing Workshop 2024, NLLP 2024, co-located with the 2024 Conference on Empirical Methods in Natural Language Processing

作者： Redelaar, Felicia Van Drie, Romy Verberne, Suzan De Boer, Maaike Leiden Institute of Advanced Computer Science Einsteinweg 55 Leiden Netherlands Dep. Data Science TNO Anna van Buerenplein 1 The Hague Netherlands

ISBN: (纸本)9798891761834

In this paper, we address the problem of answering questions about preconditions in the law, e.g. "When can the court terminate the guardianship of a natural person?". When answering legal questions, it is important to attribute the relevant part of the law;we therefore not only generate answers but also references to law articles. We implement a retrieval augmented generation (RAG) pipeline for longform answers based on the Dutch law, using several state-of-the-art retrievers and generators. For evaluating our pipeline, we create a dataset containing 102 legal QA pairs with attributions. Our experiments show promising results on our extended version for the automatic evaluation metrics from the Automatic LLMs' Citation Evaluation (ALCE) Framework and the G-EVAL Framework. Our findings indicate that RAG has significant potential in complex, citation-heavy domains like law, as it helps laymen understand legal preconditions and rights by generating high-quality answers with accurate attributions. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Survey on Event Extraction from Webpage 8

A Survey on Event Extraction from Webpage

引用

8th International Conference on Contemporary information technology and Mathematics, ICCITM 2022

作者： Ali, Rasha Mustafa, Ban Sharief Mosul University Computer Science Dep. Mosul Iraq

ISBN: (纸本)9798350334869

Event extraction (EE) is one of most important researches in the field of Natural Language Processing (NLP). Numerous significant events occur every day all over the world, and it published in various media outlets with varying narrative styles. A primary job in EE is to determine if events in the real world have been reported in articles and posts driven by the 4Ws' (what, who, when, and where). A complex relationship between people can be explained by an event, place, actions, and objects. An event-centered model captures the dynamic and semantic aspects of an event representation of event facts. An updated and comprehensive survey is needed due to the proliferation of methods, datasets, and evaluation metrics in the literature. In this paper, a survey on extracting events from websites and defining their types and applications in several different fields has been discussed. In addition, the study presents the strengths and weaknesses of event extraction systems for different types of models © 2022 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

A Jaccard Factor-Based Heuristic for the Set k-Cover Problem in Wireless Sensor Networks 3

A Jaccard Factor-Based Heuristic for the Set k-Cover Problem...

引用

3rd International Conference on Computing and information technology, ICCIT 2023

作者： Balamane, Salah Eddine Bouamama, Salim Mouhoub, Nasser Eddine Mohamed Boudiaf University Informatics Dep. M'sila Algeria Ferhat Abbas University Dep of Computer Science Setif19000 Algeria

ISBN: (纸本)9798350321487

The applications of a wireless sensor network rely heavily on the network's ability to function for an extended period. By separating the sensors into groups, each of which may keep an eye on the entire area of interest and be activated alternately, the system's lifetime can be maximized. However, determining the most significant number of different sensor covers necessitates solving the NP-complete set k-cover issue. This work presents an improved greedy approach to the set k-cover problem based on the Jaccard Similarity Coefficient. The latter is a statistical method used to understand the similarity and diversity between sample sets. Moreover, the quality of the produced solution is improved by removing duplicate sensors for each set cover. The effectiveness of the proposed approach was compared to some greedy-based methods from the literature based on 1000 widely used benchmark instances. Computational results demonstrate its efficacy in producing high-quality solutions within acceptable computational time, especially when the problem scale increases. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Sorting Red and Green Chilies by Digital Image Processing 2

Sorting Red and Green Chilies by Digital Image Processing

引用

2nd International Conference on Cybernetics and Innovations, ICCI 2023

作者： Chumuang, Narumol Ketcham, Mahasak Ganokratanaa, Thittaporn Pramkeaw, Patiyuth Chongsri, Jiratha Yimyam, Worawut Dep. of Digital Media Technology Thailand King Mongkut's University of Technology North Bangkok Dep. of Information Technology Management Thailand King Mongkut's University of Technology Thonburi Applied Computer Science Program Bangkok Thailand King Mongkut's University of Technology Thonburi Media Technology Program Bangkok Thailand Phetchaburi Rajabhat University Dep. of Business Information Management Thailand

ISBN: (纸本)9798350336573

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. This work has developed an automatic computer shutdown system. with image processing via a webcam by using image processing techniques (image processing) applied to a webcam by using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the face detection technique using the algorithm of Haar -like features to detect human faces and ROI. define a specific area of interest. The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing. This work can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification System Using Decision Tree Algorithm

Brain Tumor Classification System Using Decision Tree Algori...

引用

2025 IEEE International Conference on Cybernetics and Innovations, ICCI 2025

作者： Thaiparnit, Sattarpoom Janchidfah, Thanakrit Farooq, Adil Rajamangala University of Technology Suvarnabhumi Faculty of Business Administration Dep. Of Information System and Computer Business Suphan Buri72130 Thailand Muban Chombueng Rajabhat University dep. Of Digital Media Technology Ratchaburi70150 Thailand Maynooth University Department of Electronic Engineering Ireland

ISBN: (纸本)9798331533267

This research aims to study, design, and develop a brain tumor classification system using artificial intelligence, specifically decision tree algorithms. The system's primary objective is to assist medical personnel in making decisions, as distinguishing between two types of brain tumors-benign and malignant (cancerous)-can be challenging, especially for less experienced medical staff. Due to the similarities between these two types of tumors, it may be difficult for medical practitioners with limited expertise to differentiate between them in a timely manner. The proposed brain tumor classification system is designed to address this challenge. The research team conducted the study over approximately seven months, starting from the second semester of the 2023 academic year through the first semester of the 2024 academic year. Experimental results revealed that among the tree-based algorithms, Random Forest achieved the highest accuracy, followed by M5P. The best average accuracy from the experiments was obtained using a 70% training and 30% testing split, yielding an accuracy of 96.83%. Therefore, the research team selected the 70% training and 30% testing split for model development, as it provided the highest accuracy compared to the 60% training and 40% testing split, and the 80% training and 20% testing split, which showed lower accuracy. The results demonstrate that the 70% training and 30% testing approach is optimal for the brain tumor classification system, ensuring high accuracy in classifying brain tumors. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers Using Spectrograms with Supervised and Unsupervised Learning

arXiv

引用

arXiv 2024年

作者： Varotto, Matteo Valentin, Stefan Tomasin, Stefano Dep. of Computer Science Darmstadt University of Applied Sciences Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Italy

Cellular networks are potential targets of jamming attacks to disrupt wireless communications. Since the fifth generation (5G) of cellular networks enables mission-critical applications, such as autonomous driving or smart manufacturing, the resulting malfunctions can cause serious damage. This paper proposes to detect broadband jammers by an online classification of spectrograms. These spectrograms are computed from a stream of in-phase and quadrature (IQ) samples of 5G radio signals. We obtain these signals experimentally and describe how to design a suitable dataset for training. Based on this data, we compare two classification methods: a supervised learning model built on a basic convolutional neural network (CNN) and an unsupervised learning model based on a convolutional autoencoder (CAE). After comparing the structure of these models, their performance is assessed in terms of accuracy and computational complexity. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Standardization Review on Non-Terrestrial Networks 39

Standardization Review on Non-Terrestrial Networks

引用

39th International Conference on information Networking, ICOIN 2025

作者： Kyung, Yeunwoong Lee, Jaewook Ko, Haneul Oh, Seungmin Lee, Jaehwan Kim, Youngjun Kongju National University Div. of Info. & Comm. Eng Cheonan Korea Republic of Pukyong National University Dep. of Info. and Comm. Engineering Busan Korea Republic of Kyung Hee University Dep. of Electronic Eng Yongin-si Korea Republic of Kongju National University Dep. of Computer Science and Eng Cheonan Korea Republic of Kyungnam University School of Computer Science and Eng Changwon Korea Republic of

ISBN: (纸本)9798331506940

As the demand for global connectivity increases, non-terrestrial networks (NTNs), particularly satellite-based systems, have gained significant attention in communication network standardization. The 3rd Generation Partnership Project (3GPP) has been at the forefront of developing standards that incorporate satellite communications into the broader terrestrial network framework. This paper reviews the progression of NTN standardization, focusing on three key stages: (1) the use of satellites as relays or the next generation NodeBs (gNBs), (2) the integration of user plane functions (UPF) within satellites, and (3) the inclusion of control plane network functions (NFs) within satellites. These developments in standardizations reflect a shift from basic relay functions to fully integrated satellite networks. © 2025 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers Using Spectrograms with Supervised and Unsupervised Learning

Detecting 5G Signal Jammers Using Spectrograms with Supervis...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Matteo Varotto Stefan Valentin Stefano Tomasin Dep. of Computer Science Darmstadt University of Applied Sciences Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Italy

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

关键词： Wireless communication 5G mobile communication Computational modeling Data models Convolutional neural networks Synchronization Jamming

来源：评论

学校读者我要写书评

暂无评论

Automatic computer Shutdown with Image Processing via Webcam to Save Energy 2

Automatic Computer Shutdown with Image Processing via Webcam...

引用

2nd International Conference on Cybernetics and Innovations, ICCI 2023

作者： Chumuang, Narumol Ketcham, Mahasak Ganokratanaa, Thittaporn Pramkeaw, Patiyuth Yimyam, Worawut Chuamoo Dep. of Digital Media Technology Thailand King Mongkut's University of Technology North Bangkok Dep. of Information Technology Management Thailand King Mongkut's University of Technology Thonburi Applied Computer Science Program Bangkok Thailand King Mongkut's University of Technology Thonburi Media Technology Program Bangkok Thailand Phetchaburi Rajabhat University Dep. of Business Information Management Thailand

ISBN: (纸本)9798350336573

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. The researcher has developed an automatic computer shutdown system. with image processing via a webcam By using image processing techniques (Image Processing) applied to a webcam. By using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the Face Detection technique using the algorithm of Haar-like Features to detect human faces and ROI. Define a specific area of interest The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing This research can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Federated Aggregation Strategies and Architectures for Next-word Prediction

A Comparison of Federated Aggregation Strategies and Archite...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Sakhnovych, Yana Rottger, Richard Mayer, Rudolf Sba Research Vienna Austria University of Southern Denmark Dep. of Mathematics and Computer Science Odense Denmark

ISBN: (纸本)9798350324457

Federated learning is an important technique for training language models, which are frequently used for next-word prediction since federated learning allows utilising large quantities of real-life data without compromising the privacy of the data owners. Training a model that generalises well in this setting is a challenging task due to the inherent statistical heterogeneity of the training data, and due to the hardware limitations of private mobile devices. There are different approaches that address these issues, e.g. through model selection, different aggregation and learning strategies, and update compression. In this paper, two popular model architectures, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), are evaluated in centralised and federated settings. For federated learning, the vanilla Federated Averaging algorithm and two alternatives that try to address statistical heterogeneity, namely FedProx, which uses a proximal term to restrict the divergence from the global model during local model training, and Federated Attention, which has similar aims of reducing the distance between models as well to ensure faster convergence and improve generalisation, but is performing this during the aggregation station, are evaluated for their achieved perplexity and accuracy in various settings on two datasets. Based on these results, we provide guidelines on which methods to use, dep.nding on the scenario. © 2023 IEEE.

关键词： Federated Learning Federated Averaging Language Models Next-word Prediction

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：