检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wehner, Jan Oliehoek, Frans Siebert, Luciano Cavalcante CISPA Helmholtz Center for Information Security Germany Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Learning rewards from human behavior or feedback is a promising approach to aligning AI systems with human values but fails to consistently extract correct reward functions. Interpretability tools could enable users to understand and evaluate possible flaws in learned reward functions. We propose Counterfactual Trajectory Explanations (CTEs) to interpret reward functions in Reinforcement Learning by contrasting an original and a counterfactual trajectory and the rewards they each receive. We derive six quality criteria for CTEs and propose a novel Monte-Carlo-based algorithm for generating CTEs that optimizes these quality criteria. To evaluate how informative the generated explanations are to a proxy-human model, we train it to predict rewards from CTEs. CTEs are demonstrably informative for the proxy-human model, increasing the similarity between its predictions and the reward function on unseen trajectories. Further, it learns to accurately judge differences in rewards between trajectories and generalizes to out-of-distribution examples. Although CTEs do not lead to a perfect prediction of the reward, our method, and more generally the adaptation of XAI methods, are presented as a fruitful approach for interpreting learned reward functions and thus enabling users to evaluate them. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Future of Online Shopping: Blockchain- Powered E-Commerce Platforms

The Future of Online Shopping: Blockchain- Powered E-Commerc...

引用

Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT), International Conference on

作者： Ajmeera Kiran Nemani Divya Sri Ramesh Kumar Ayyasamy P. Chinnasamy Sreelakshmi Vellanki Maddula Vujwala Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Malaysia Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540692

A cutting-edge online marketplace that uses blockchain technology to transform how we purchase and sell goods and services is known as a blockchain- powered e-commerce platform. This platform uses a decentralized network of computers, also known as nodes, to maintain a transparent and impenetrable record of all transactions instead of depending on a central authority like a bank or a company. A blockchain-based e-commerce platform is a secure, transparent, and trusted online marketplace. It does away with the need for intermediaries, improves security, and provides a world market where users can confidently conduct peer-to-peer transactions. This novel strategy could change how online commerce and shopping are performed.

关键词： Costs Transforms Signal processing Peer-to-peer computing Blockchains Safety Fraud

来源：评论

学校读者我要写书评

暂无评论

Malaysian Sign Language Recognition Using 3D Hand Pose Estimation

Malaysian Sign Language Recognition Using 3D Hand Pose Estim...

引用

Digital Transformation and Intelligence (ICDI), International Conference on

作者： Kavishaalini Padmanand Phei-Chin Lim Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Sarawak Malaysia

ISBN: (纸本)9798350397017

Sign languages are one of those mediums for hearing-impaired people. These languages transmit meaning by visual-manual treatment., or more simply, hand movement. Currently, there are only 95 sign language interpreters registered with the Malaysian Federation of the Deaf as of 2020, compared to 40,389 hearing-impaired individuals with disabilities registered with the welfare department which is a problem. Therefore, with the use of deep-learning technology., this paper proposes to alleviate the scarcity of Malaysian Sign Language interpreters for the benefit of hearing-impaired persons. The paper aims to test and report a sequenced 3D keypoint hand pose estimation model for Malaysian Sign Language Recognition and evaluate the implementation of action model in decoding basic poses of Malaysian Sign Language. According to the findings, the detecting of 3D keypoints and incorporating into LSTM models using deep learning machine learning platform and framework like TensorFlow and MediaPipe enables the detection of Malaysian sign language 3D hand posture estimation. The results demonstrated that 3D hand posture estimation may be utilised to estimate sign language in real time, providing for a better interpretation approach for the deaf community.

关键词： Deep learning Solid modeling Three-dimensional displays Digital transformation Pose estimation Gesture recognition Assistive technologies

来源：评论

学校读者我要写书评

暂无评论

Wav2Vn: Scalable Unsupervised Pre-training and Adaptation for Multi-Accent Vietnamese ASR

Wav2Vn: Scalable Unsupervised Pre-training and Adaptation fo...

引用

Green Buildings (ATiGB), Applying New technology in

作者： Viet Nguyen Kim Huyen Nguyen Thi Ngoc Hieu Dam Minh Nguyen Do Hoang Khoi Tien-Dung Do Cao Truong Dung Department of Information Technology Posts and Telecommunication Institute of Technology Ha Noi Vietnam Department of Computer Science Swinburne University Ha Noi Vietnam Department of Computer Science Posts and Telecommunication Institute of Technology Ha Noi Vietnam Faculty of Information Posts and Telecommunication Institute of Technology Ha Noi Vietnam Department of Electronic Engineering Posts and Telecommunication Institute of Technology Ha Noi Vietnam

ISBN: (数字)9798331505042

ISBN: (纸本)9798331505059

Automatic speech recognition (ASR) systems have seen significant advancements in recent years, driven by deep learning and large-scale pre-training methods. However, achieving high accuracy across multiple accents remains a challenging task, especially for languages with rich phonetic diversity like Vietnamese. The Vietnamese language encompasses a wide range of regional accents, each with unique phonetic characteristics that can hinder the performance of conventional ASR. To address this issue, we present a Vietnamese language processing model called Wav2Vn as a novel approach to scalable unsupervised pretraining and adaptation for ASR targeting multiple Vietnamese accents. Our method leverages the power of the Mixture of Experts (MoE) to effectively handle the diverse phonetic variations across different Vietnamese accents. Our results demonstrate a significant performance improvement in terms of word error rate (WER) and robustness to accent variability compared to the current state-of-the-art PhoWhisper.

关键词： Adaptation models Error analysis Green buildings Scalability Diversity reception Self-supervised learning Phonetics Robustness Computational efficiency Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

MOB-GCN: A Novel Multiscale Object-Based Graph Neural Network for Hyperspectral Image Classification

arXiv

引用

arXiv 2025年

作者： Yang, Tuan-Anh Hy, Truong-Son Dao, Phuong D. Faculty of Information Technology University of Science VNU-HCM Viet Nam Department of Computer Science Univerity of Alabama Birmingham United States Department of Agricultural Biology Colorado State University United States

This paper introduces a novel multiscale object-based graph neural network called MOB-GCN for hyperspectral image (HSI) classification. The central aim of this study is to enhance feature extraction and classification performance by utilizing multiscale object-based image analysis (OBIA). Traditional pixel-based methods often suffer from low accuracy and speckle noise, while single-scale OBIA approaches may overlook crucial information of image objects at different levels of detail. MOB-GCN addresses this issue by extracting and integrating features from multiple segmentation scales to improve classification results using the Multiresolution Graph Network (MGN) architecture that can model fine-grained and global spatial patterns. By constructing a dynamic multiscale graph hierarchy, MOB-GCN offers a more comprehensive understanding of the intricate details and global context of HSIs. Experimental results demonstrate that MOB-GCN consistently outperforms single-scale graph convolutional networks (GCNs) in terms of classification accuracy, computational efficiency, and noise reduction, particularly when labeled data is limited. The implementation of MOB-GCN is publicly available at https://***/HySonLab/MultiscaleHSI. © 2025, CC BY.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Soil and Climate Parameters Based Crop Recommendation Model for Yandev, Gboko Local Government Area of Benue State

Soil and Climate Parameters Based Crop Recommendation Model ...

引用

International Conference on Ubiquitous information Management and Communication (IMCOM)

作者： Dekera Kenneth Kwaghtyo Christopher Ifeanyi Eke Joshua Abah Timothy Moses Jeffery Agushaka Faith B Fatokun Department of Computer Science Faculty of Computing Federal University of Lafia Lafia Nigeria Malaysian Institute of Information Technology University of Kuala Lumpur Kuala Lumpur Malaysia

The increase in human population on fixed landmarks brings about recurrent cultivation of farmlands, which degrades the soil. The varied nature of the soil and climate escalates this situation. Making farming decisions based on human experience is misleading, especially in the everchanging climates. Farmers now experience low agricultural output in the Yandev District of Benue State, Nigeria. Hence, proper management of farming resources with the aid of artificial intelligence has become pertinent. Existing solutions may not be effective in the Yandev axis due to the geographic disparity of the datasets used to train the models. This study leveraged soil and climate parameters in the Yandev district to develop a crop recommendation model. Five machine learning models, including decision trees, naive Bayes, logistic regression, random forest, and extreme gradient boosting, were utilized. The models were experimented with the Yandev dataset and evaluated using accuracy, $\mathbf{F}1$ -score, precision and recall metrics. The evaluation shows that the naive Bayes algorithm outclassed the other learning models with a performance of $99.85\%$ accuracy. This experimental result also outperformed other existing methods, indicating the significance of the model in the area. The goal of recommending what crop to grow in the Yandev axis was achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Modeling Elements of Luoshan Shadow Puppets Creative Goods Based on Deep Learning

Design of Modeling Elements of Luoshan Shadow Puppets Creati...

引用

International Conference on Applied Machine Learning (ICAML)

作者： Taotao Xu Musdi bin Hj. Shanat Brendan Chan Kah Le Wei Zhang Faculty of Applied and Creative Arts University Malaysia Sarawak Sarawak Malaysia Faculty Of Computer Science And Information Technology University Malaysia Sarawak Sarawak Malaysia

The application of Luoshan shadow puppet elements in creative goods can break through the single communication path of shadow play and make the communication process of Luoshan shadow play art more vivid and 3D. In this paper, based on the design of modeling elements of mountain shadow puppets, the characteristics of visual elements of shadow puppets creative goods are analyzed, and an intelligent design algorithm of shadow puppets creative goods based on deep learning (DL) is innovatively proposed. Based on the design of modeling elements of Luoshan shadow puppets, this paper analyzes the characteristics of visual elements of shadow puppet creative goods, puts forward an intelligent design algorithm of shadow puppet creative goods based on DL, and explores the computer-aided shadow puppets modeling design strategy driven by artificial intelligence. The results show that the F1 value of the algorithm is about 94%, and the efficiency of the algorithm is high. The validity and reliability of the method in this paper are effectively verified by the test, which provides a reliable and efficient method for the design of modeling elements of Luoshan shadow puppet creative goods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Sound and Data Steganography Based Secure Authentication System

引用

computers, Materials & Continua 2021年第4期67卷 723-751页

作者： Debajit Datta Lalit Garg Kathiravan Srinivasan Atsushi Inoue G.Thippa Reddy M.Praveen Kumar Reddy K.Ramesh Nidal Nasser School of Computer Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India Faculty of Information and Communication Technology University of MaltaMsidaMSD2080Malta School of Information Technology and Engineering Vellore Institute of Technology(VIT)Vellore632014India Department of Information Systems&Business Analytics Eastern Washington UniversitySpokaneWA99202USA Department of Computer Science Karnataka State Akkamahadevi Women’s UniversityVijayapuraIndia College of Engineering Alfaisal UniversityRiyadh1153Saudi Arabia

The prodigious advancements in contemporary technologies have also brought in the situation of unprecedented ***,the pin-based security system is an inadequate mechanism for handling such a *** reason is that hackers use multiple strategies for evading security systems and thereby gaining access to private *** research proposes to deploy diverse approaches for authenticating and securing a connection amongst two devices/gadgets via sound,thereby disregarding the pins’manual ***,the results demonstrate that the proposed approaches outperform conventional pin-based authentication or QR authentication ***,a random signal is encrypted,and then it is transformed into a wave file,after which it gets transmitted in a short burst via the device’s ***,the other device/gadget captures these audio bursts through its microphone and decrypts the audio signal for getting the essential data for ***,this model requires two devices/gadgets with speakers and a microphone,and no extra hardware such as a camera,for reading the QR code is *** first module is tested with realtime data and generates high scores for the widely accepted accuracy metrics,including precision,Recall,F1 score,entropy,and mutual information(MI).Additionally,this work also proposes a module helps in a secured transmission of sensitive data by encrypting it over images and other *** steganographic module includes two-stage encryption with two different encryption algorithms to transmit data by embedding inside a *** encryption algorithms and their combinations are taken for this system to compare the resultant file *** these systems engender high accuracies and provide secure connectivity,leading to a sustainable communication ecosystem.

关键词： Cyber-attacks signals privacy security organization encryption decryption authentication effective communication steganography

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Graph Edit Distance-Based Approach for Finding Business Process Similarities

引用

computers, Materials & Continua 2021年第12期69卷 3603-3618页

作者： Abid Sohail Ammar Haseeb Mobashar Rehman Dhanapal Durai Dominic Muhammad Arif Butt Department of Computer Science COMSATS University IslamabadLahorePakistan Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKamparPerakMalaysia Universiti Teknologi PETRONAS Bandar Seri IskandarTronoh PerakMalaysia Punjab University College of Information Technology University of the PunjabLahorePakistan

There are numerous application areas of computing similarity between process *** includes finding similar models from a repository,controlling redundancy of process models,and finding corresponding activities between a pair of process *** similarity between two process models is computed based on their similarity between labels,structures,and execution *** attempts have been made to develop similarity techniques between activity labels,as well as their execution ***,a notable problem with the process model similarity is that two process models can also be similar if there is a structural variation between ***,neither a benchmark dataset exists for the structural similarity between process models nor there exist an effective technique to compute structural *** that end,we have developed a large collection of process models in which structural changes are handcrafted while preserving the semantics of the ***,we have used a machine learning-based approach to compute the similarity between a pair of process models having structural and label ***,we have evaluated the proposed approach using our generated collection of process models.

关键词： Machine learning intelligent data management similarities of process models structural metrics dataset graph edit distance process matching artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Denoising Medical Images Using Deep Learning in IoT Environment

引用

computers, Materials & Continua 2021年第12期69卷 3127-3143页

作者： Sujeet More Jimmy Singla Oh-Young Song Usman Tariq Sharaf Malebary School of Computer Science and Engineering Lovely Professional UniversityJalandharIndia Software Department Sejong UniversitySeoulKorea College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology in RabighKing Abdulaziz UniversityJeddah21911Saudi Arabia

Medical Resonance Imaging(MRI)is a noninvasive,nonradioactive,and meticulous diagnostic modality capability in the field of medical ***,the efficiency of MR image reconstruction is affected by its bulky image sets and slow process ***,to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network(SANR_CNN)for eliminating noise and improving the MR image reconstruction *** proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality,and SARN algorithm is used for building a dictionary learning technique for denoising large image *** proposed SANR_CNN model also preserves the details and edges in the image during *** experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio(PSNR),structural similarity index(SSIM),and mean squared error(MSE).The proposed SANR_CNN model achieved higher PSNR,SSIM,and MSE efficiency than the other noise removal *** proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.

关键词： Medical resonance imaging convolutional neural network denoising contrast enhancement internet of things rheumatoid arthritis

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：