检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Belem, Catarina Kelly, Markelle Steyvers, Mark Singh, Sameer Smyth, Padhraic Department of Computer Science University of California Irvine United States Department of Cognitive Sciences University of California Irvine United States

ISBN: (纸本)9798891761643

Uncertainty expressions such as "probably" or "highly unlikely" are pervasive in human language. While prior work has established that there is population-level agreement in terms of how humans quantitatively interpret these expressions, there has been little inquiry into the abilities of language models in the same context. In this paper, we investigate how language models map linguistic expressions of uncertainty to numerical responses. Our approach assesses whether language models can employ theory of mind in this setting: understanding the uncertainty of another agent about a particular statement, independently of the model's own certainty about that statement. We find that 7 out of 10 models are able to map uncertainty expressions to probabilistic responses in a human-like manner. However, we observe systematically different behavior depending on whether a statement is actually true or false. This sensitivity indicates that language models are substantially more susceptible to bias based on their prior knowledge (as compared to humans). These findings raise important questions and have broad implications for human-AI and AI-AI communication. © 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

Color image restoration by filtering methods: a review

引用

Soft Computing 2024年第13-14期28卷 7755-7782页

作者： Salamat, Nadeem Missen, Malik Muhammad Saad Akhtar, Nadeem Mustahsan, Muhammad Surya Prasath, V.B. Department of Mathematics Khawaja Fareed University of Engineering and Information Technology Rahim Yar Khan64200 Pakistan Department of Computer Science and IT The Islamia University of Bahawalpur Bahawalpur63100 Pakistan Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Center CincinnatiOH45229 United States Department of Computer Science Pediatrics and Biomedical Informatics University of Cincinnati CincinnatiOH45221 United States

Digital images are corrupted with noise, and image denoising is an important step in image processing modules. In this review, the latest developments in filtering methods for color image restoration are analyzed. These algorithms are compared in terms of objective image quality measures and divided into major classes, such as spatial domain, switching and wavelet filtering methods. These classes are based on the particular methodology used in image denoising algorithms and further subdivided to show their classification in terms of noise models utilized, application style, and stages the filters applied in images. In particular, we present a review of filtering methods in color image denoising, published over the past two decades. Our classification and succinct descriptions of color image restoration by these mathematical filtering techniques and their characterizations can help choose the appropriate ones for various downstream image processing tasks. © The Author(s) 2024.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

CASPER: Context-Aware Anomaly Detection System for Industrial Robotic Arms

CASPER: Context-Aware Anomaly Detection System for Industria...

引用

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Kayan, Hakan Rana, Omer Burnap, Pete Perera, Charith Cardiff University Department of Computer Science and Informatics Cardiff United Kingdom

ISBN: (纸本)9781665453813

With the arrival of industry 4.0, industrial control systems are converted into 'smart' industrial cyber-physical systems that depend on high interconnectivity enabled by ubiquitous applications. As these applications can significantly reduce maintenance and supervision costs, the integration of these applications is done with the 'cost' being the focus overlooking the security aspect that suffers from the vulnerabilities that occurred due to increased attack surface. The adversaries aim to create physical alterations by exploiting these cyber vulnerabilities via so-called 'cyber-physical' attacks. In this work, we introduce CASPER, a context-aware ubiquitous machine learning-based anomaly detection infrastructure that utilizes ubiquitous computing to detect anomalies of an industrial robotic arm. CASPER monitors the robotic arm's movements to ensure the arm follows a predetermined trajectory. The CASPER can reach an accuracy and F1 score of 97% which is promising for an industrial domain. We modify the joint velocity of an industrial robotic arm to create anomalies which we detect via CASPER.(Demo Video) © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Rethinking (Human) Bodies in HRI: Embodied Interactions Every Day 6

Rethinking (Human) Bodies in HRI: Embodied Interactions Ever...

引用

6th Social Robots with AI: Prospects, Risks, and Responsible Methods Robophilosophy, RP 2024

作者： Fantasia, Valentina Winkle, Katie Harrison, Katherine Ziemke, Tom Lisy, Dominika Dobrosovestnova, Anna Department of Philosophy and Cognitive Science Lund University Sweden Department of Information Technology Uppsala University Sweden Department of Thematic Studies Linköping University Sweden Department of Cognitive Science Linköping University Sweden Human Computer Interaction Group TU Wien Austria

ISBN: (纸本)9781643685670

Significant amounts of HRI research effort are spent on the design/evaluation of robot bodies. Critical discussion and debates concerning the way bodies are treated and considered within HRI have tended to focus on the implications of designing/interacting with highly anthropomorphic robots, yet drawing attention away from the human body in HRI, particularly in the context of everyday interactions with "unexpectedly" social robots, i.e. those non-humanoid robots that human users interact with in a somewhat "social" way. These kind of robots crystallise particular aspects of (and tensions between) the different ways in which bodies are understood across disciplines. At the same time, a fundamental, and largely neglected tool for HRI research is the researchers' own embodied experience of the intersubjective role. This workshop has invited speakers and audience to engage in cross-disciplinary conversations on embodiment in HRI, highlighting the different ways in which "the body" is or can be variously conceptualised and researched. © 2025 IOS Press. All rights reserved.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Quantitative Susceptibility Mapping With Reduced Training Time Based on Local Field Transformation

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年第2期9卷 1527-1538页

作者： Wu, Ming-Long Huang, De-Rong Cheng, Jhih-Shan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan National Cheng Kung University Institute of Medical Informatics Tainan701 Taiwan

A quantitative susceptibility mapping (QSM) approach using single-orientation imaging data is proposed in this study. The proposed method generates local field maps at five predefined orientations via deep learning from single-orientation local field maps, followed by physical dipole inversion using the analytical Calculation of Susceptibility through Multiple Orientation Sampling (COSMOS) algorithm. We termed the method pseudo COSMOS (pCOSMOS). By isolating the physical dipole inversion process from deep learning, training of the neural network model becomes greatly accelerated. Brain imaging data from 10 healthy subjects (7 training and 3 testing) acquired at 3T with five different orientations relative to the main magnetic field were included to evaluate the reconstruction quality. Results compared against two iterative (Morphology Enabled Dipole Inversion or MEDI, and Structural Feature-based Collaborative Reconstruction or SFCR) and two deep learning QSM approaches (QSMnet and Learned Proximal Convolutional Neural Network or LPCNN) using COSMOS as the reference standard revealed that the susceptibility maps obtained from pCOSMOS yielded global quantitative performance comparable to QSMnet and LPCNN, while being prominently superior to MEDI and SFCR. Estimation errors in magnetic susceptibility were between 0.01 and 0.02 ppm voxel-wise, and 0.006 ± 0.004 ppm for five selected gray matter areas. Visual inspection further suggested better preserved tissue boundaries in pCOSMOS than QSMnet and LPCNN. Training time was reduced from 2 days for LPCNN and 12 hours for QSMnet to 3.2 hours for pCOSMOS. It is concluded that the proposed pCOSMOS method is an alternative deep learning QSM approach when computational efficiency is essential. © 2017 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Design Face Spoof Detection using Deep Learning

Design Face Spoof Detection using Deep Learning

引用

2023 International Conference on Energy, Power, Environment, Control, and Computing, ICEPECC 2023

作者： Thiruchelvam, Pranavi Sathiyarasah, Sayanthan Paranthaman, Thushaliny Thaneeshan, Rajeetha Uva Wellassa University Department of Computer Science and Informatics Sri Lanka

ISBN: (纸本)9781665476010

The recognition of facial patterns has grown in popularity among the various biometric systems in recent years. As a result, there has been a significant advancement in this field. The security of such systems, however, may be of paramount concern given that numerous studies have shown that face recognition systems are susceptible to a number of threats, including spoofing attacks. When a biometric system is used to identify unauthorized users, spoofing refers to the capacity to trick the system into thinking the unauthorized user is the real deal by using a variety of methods to show a fake version of the original biometric attribute to sensing objects. A number of anti-spoofing techniques that do exist protects face spoofing. This study presents a simple and efficient Resnet18 Convolutional Neural Network (CNN) model architecture, which is more beneficial and produces greater accuracy than other handcrafted, machine learning and pre trained Models. This proposed system has three steps such as analyzing possible enhancements to features, loading photographs and their predictions, and face verification of real or spoofs in an image. We have proposed the model using publicly available challenging CASIA dataset. Wrap photo, cut photo, and electronic screen are three numerous varieties of images that capture real people's faces. The input video split into picture frames in this step. Experimental results demonstrated that proposed approached outperforms similar approaches by showed a 99.12 percentage of real detection accuracy and a 98.20 percentage of spoof detection accuracy. The results of the experiments demonstrate that our proposed detection system indicates a higher results of detection rate rather than earlier used techniques. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Cultural Heritage 3D Models from Sparse Point Clouds Using Implicit Neural Representations 1

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Triantafyllou, Georgios Dimas, George Kalozoumis, Panagiotis G. Iakovidis, Dimitris K. Department Computer Science and Biomedical Informatics University of Thessaly Lamia Greece

ISBN: (数字)9783031377310

ISBN: (纸本)9783031377303

Creating accessible museums and exhibitions is a key factor to today’s society that strives for inclusivity. Visually-impaired people can benefit from manually examining pieces of an exhibition to better understand the features and shapes of these objects. Unfortunately, this is rarely possible, since such items are usually behind protective barriers due to their rarity, worn condition, and/or antiquity. Nevertheless, this can be achieved by 3D printed replicas of these collections. The fabrication of copies through 3D printing is much easier and less time-consuming compared to the manual replication of such items, which enables museums to acquire copies of other exhibitions more efficiently. In this paper, an accessibility-oriented methodology for reconstructing exhibits from sparse 3D models is presented. The proposed methodology introduces a novel periodic and parametric activation function, named WaveShaping (WS), which is utilized by a multi-layer perceptron (MLP) to reconstruct 3D models from coarsely retrieved 3D point clouds. The MLP is trained to learn a continuous function that describes the coarse representation of a 3D model. Then, the MLP is regarded as a continuous implicit representation of the model;hence, it can interpolate data points to refine and restore regions of the model. The experimental evaluation on 3D models taken from the ShapeNet dataset indicates that the novel WS activation function can improve the 3D reconstruction performance for given coarse point cloud model representations. © 2023, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of O...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lu, Xiaotian Li, Jiyi Takeuchi, Koh Kashima, Hisashi Department of Intelligence Science and Technology Graduate School of Informatics Kyoto University Kyoto Japan Department of Computer Science and Engineering University of Yamanashi Kofu Japan

ISBN: (纸本)9798891761681

Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results. © 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

Energy Detection in cognitive Radio Networks to Optimize the Spectrum Utilization Through Cooperative Spectrum Sensing Using Weights

Energy Detection in Cognitive Radio Networks to Optimize the...

引用

International Conference on Modern Electronics Devices and Communication Systems, MEDCOM 2021

作者： Gupta, Rahul Gupta, P.C. Department of Computer Science and Informatics University of Kota Rajasthan Kota India

ISBN: (纸本)9789811963827

cognitive radio network provides an efficient solution for spectrum utilization. The cooperative spectrum sensing is one of the sensing techniques with which the secondary users of cognitive radio network (CRN) could learn about the availability of the spectrum. In this article, authors had designed and developed their own CRN simulation model in which the RF spectrum range of 54 MHz to 648 MHz is divided into various channels. Secondary users are kept moving in these various channels along with the primary user. The presence of primary user is detected by applying weights on the energy received by local secondary users. The information about the energy of primary user is collected locally by SU and provided to the fusion center for PU detection. This article discusses how the secondary user detects the energy of primary user using weights. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Sentiment Polarity Analysis of Bangla Food Reviews Using Machine and Deep Learning Algorithms 3

Sentiment Polarity Analysis of Bangla Food Reviews Using Mac...

引用

3rd International Conference on Advancement in Electrical and Electronic Engineering, ICAEEE 2024

作者： Amin, Al Sarkar, Anik Islam, Md Mahamodul Miazee, Asif Ahammad Islam, Md Robiul Hoque, Md Mahmudul Uttara University Department of Computer Science and Engineering Dhaka Bangladesh National Institute of Technology Silchar India University of Oslo Department of Informatics Oslo Norway Maharishi International University Department of Computer Science Iowa United States CCN University of Science & Technology Department of Computer Science and Engineering Comilla Bangladesh

ISBN: (纸本)9798350388282

The Internet has become an essential tool for people in the modern world. Humans, like all living organisms, have essential requirements for survival. These include access to atmospheric oxygen, potable water, protective shelter, and sustenance. The constant flux of the world is making our existence less complicated. A significant portion of the population utilizes online food ordering services to have meals delivered to their residences. Although there are numerous methods for ordering food, customers sometimes experience disappointment with the food they receive. Our endeavor was to establish a model that could determine if food is of good or poor quality. We compiled an extensive dataset of over 1484 online reviews from prominent food ordering platforms, including Food Panda and HungryNaki. Leveraging the collected data, a rigorous assessment of various deep learning and machine learning techniques was performed to determine the most accurate approach for predicting food quality. Out of all the algorithms evaluated, logistic regression emerged as the most accurate, achieving an impressive 90.91% accuracy. The review offers valuable insights that will guide the user in deciding whether or not to order the food. © 2024 IEEE.

关键词： Sentiment analysis

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：