检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Usman, Fouzia Anwar, Syed M. Rauf, Usman University of Engineering & Technology Software Engineering Department Taxila Pakistan University of Engineering & Technology Computer Engineering Department Taxila Pakistan

ISBN: (纸本)9798350322125

In video games, procedural content generation has a strong history. Current procedural content generation strategies, such as search-based, solver-based, rule-based, and language-based techniques, have been used to create levels, maps, character models, and surfaces in games. There has been a research area dedicated to game content generation. More recently, Generative tasks have been in charge of a wide range of content creations that are relevant to games. Although some front-line Generative Adversarial Networks (GANs) are used independently, others are used in conjunction with more traditional techniques or an intel-ligent environment. GANs model suffers from a problem known as mode collapse where duplicate content is generated. In this ar-ticle, we have applied a simple Generative Adversarial Network, Deep convolutional Generative Adversarial Network(DCGAN), and Wasserstein Generative Adversarial Network(WGAN) to the ZELDA data set for levels of content generation and conclude the results of the basis of visual recognition. Results show that WGAN generates visually good content. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Regularized forensic efficient net: a game theory based generalized approach for video deepfakes detection

引用

Multimedia Tools and Applications 2024年 1-44页

作者： Ain, Qurat Ul Javed, Ali Malik, Khalid Mahmood Irtaza, Aun Department of Computer Science University of Engineering and Technology-Taxila Punjab Taxila47050 Pakistan Department of Software Engineering University of Engineering and Technology-Taxila Punjab Taxila47050 Pakistan College of Innovation and Technology University of Michigan-Flint FlintMI48502 United States

Due to the advancements in cutting-edge generative AI algorithms, generating hyper realistic deepfake videos has become easier for the public. This hyperrealism consequently fails contemporary methods to reliably discriminate between original and fake videos. Therefore, to counter any threat caused by these next-generation artificially generated videos, dependable approaches are required to address this classification challenge. To achieve this objective this paper presents an interdisciplinary approach that integrates game theory with deep learning to bring a novel solution to the problem of deepfake detection and protect the detectors against anti-forensics attack. To the best of our knowledge, there does not exist any other work dedicated to video deepfake detection using the integrated approach of game theory and deep learning. The game is designed for two players to distinguish between pristine and deepfake videos. The game utilizes different strategies for the data manipulator as a player P1 and the deepfake detector as P2. Strategies used for P1 involve the formation of the subsets like open and close-set, combined subsets, imbalanced dataset, and post-processing attacks to create challenging strategies for P2. To counter the strategies of P1,we propose a novel Regularized Forensic Efficient Net (RFE Net) that employs regularization techniques, such as batch normalization, dropout, augmentation, and early stopping. Based on the P1 move, the detector chooses the regularization techniques by considering factors such as generalizability and efficiency. Regularization-based strategies improve the performance of our model when compared to contemporary methods. Computation of the Nash equilibrium with the proposed zero-sum game helps to effectively detect deepfakes and leads the game to maximum payoff. Performance of the proposed game theory-based RFE Net was measured on standard and diverse datasets of FaceForensic++, DFDC preview, CelebDF, DFFD, and the World lea

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

NNC: A Nearest Neighbors Constraint-based Metric Learning for Multivariate Time Series Classification 2

NNC: A Nearest Neighbors Constraint-based Metric Learning fo...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Chen, Zhi Zhang, Fengli Zhu, Jiajing Zhang, Yun Li, Qiaoqin Liu, Yongguo University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798331515669

Multivariate time series (MTS) classification has gained significant attention as a prominent research area in recent years. Studies using Mahalanobis distance-based dynamic time warping along with metric learning algorithms have reported significant results. Existing metric learning approaches, such as large margin nearest neighbor, seek to optimize a loss function with two components: one that reduces the distance between samples with the same label and another that increases the distance between samples with different labels. However, these two terms play an opposite role in some situations and it is difficult to explore a way to balance such two competitive terms. In this paper, we introduce a nearest neighbors constraint (NNC) model designed for MTS classification. In NNC, a data-adaptive Mahalanobis distance-based dynamic time warping distance metric is designed to compute the distance between two MTS. To learn the Mahalanobis distance, a concise and effective loss function is developed. Instead of scanning all triplets, NNC only employs the triplets which violate the rule that an MTS's k nearest neighbors should share the same label with it to learn the Mahalanobis distance. Experiments on 9 public MTS datasets demonstrate that the proposed model achieves competitive performance. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Triple Diseases Prediction System using Deep Learning Techniques 2

Triple Diseases Prediction System using Deep Learning Techni...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Vijayan, R. Mareeswari, V. Jaswanth, A.B. Department of Information Technology Tamilnadu Vellore India Department of Software and Systems Tamilnadu Vellore India Software Engineering Tamilnadu Vellore India

ISBN: (纸本)9798350328202

With the existing deep learning models in predicting multiple diseases primarily focus on analyzing individual diseases in isolation, lacking a unified system for multi-disease prediction. This project presents an approach to predict multiple diseases using Flask API, with a specific focus on brain tumors, COVID-19 and pneumonia. The proposed work represents a significant contribution to the field of disease prediction, harnessing the power of deep learning algorithms and modern web application development. The primary focus is on disease prediction, with a particular emphasis on ensuring accuracy and accessibility for end-users. The initial phase of this research involves data collection, where relevant datasets of various diseases are gathered. These datasets serve as the foundation for training and validating the deep learning models. Two prominent deep learning algorithms, Sequential CNN and VGG16, are employed for this purpose. These algorithms are chosen for their ability to handle complex data and recognize patterns within medical images and other health-related data. The core of the research involves training the deep learning models using the collected datasets. This step is crucial in enabling the models to learn and generalize from the provided data, ultimately enhancing their predictive capabilities. The models are modified to elevate their performance and accuracy. Following the training phase, the models are rigorously tested to evaluate their predictive accuracy. This assessment is vital in gauging the real-world applicability of the models in medical diagnosis. To make these powerful disease prediction models accessible to a wider audience, a front-end web application is developed. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Simulation of unmanned survey path planning in debris flow gully based on GRE-Bat algorithm

引用

Journal of Mountain Science 2024年第12期21卷 4062-4082页

作者： LIU Dunlong FENG Duanguo SANG Xuejia ZHANG Shaojie YANG Hongjuan College of Software Engineering Chengdu University of Information TechnologyChengdu 610225China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China

Unmanned aerial vehicle(UAV)paths in the field directly affect the efficiency and accuracy of payload data *** planning of UAV advancing along river valleys in wild environments is one of the first and most difficult problems faced by unmanned surveys of debris flow *** study proposes a new hybrid bat optimization algorithm,GRE-Bat(Good point set,Reverse learning,Elite Pool-Bat algorithm),for unmanned exploration path planning of debris flow sources in outdoor *** the GRE-Bat algorithm,the good point set strategy is adopted to evenly distribute the population,ensure sufficient coverage of the search space,and improve the stability of the convergence accuracy of the ***,a reverse learning strategy is introduced to increase the diversity of the population and improve the local stagnation problem of the *** addition,an Elite pool strategy is added to balance the replacement and learning behaviors of particles within the population based on elimination and local perturbation *** demonstrate the effectiveness of the GRE-Bat algorithm,we conducted multiple simulation experiments using benchmark test functions and digital terrain *** to commonly used path planning algorithms such as the Bat Algorithm(BA)and the Improved Sparrow Search Algorithm(ISSA),the GRE-Bat algorithm can converge to the optimal value in different types of test functions and obtains a near-optimal solution after an average of 60 *** GRE-Bat algorithm can obtain higher quality flight routes in the designated environment of unmanned investigation in the debris flow gully basin,demonstrating its potential for practical application.

关键词： Bat algorithm Unmanned surveys Debris flow gully Path planning Unmanned aerial vehicle Reverse learning

来源：评论

学校读者我要写书评

暂无评论

Research on teaching model of secondary school students' abstract ability in mathematics based on NetPad and problem chain 23

Research on teaching model of secondary school students' abs...

引用

7th International Conference on Education and Multimedia technology, ICEMT 2023

作者： Yin, Ruiyao Chen, Ruxian Xu, Ruixi Li, Jing Zhao, Jietong Institute of Computing Science and Technology Guangzhou University China Software Engineering Institute of Guangzhou Software Engineering Institute of Guangzhou China

ISBN: (纸本)9798400709142

The cultivation of core subject literacy is the central embodiment of the curriculum objectives. In the core literacy of mathematics, mathematical abstraction is the basic idea of mathematics and an important foundation for the formation of rational thought. The NetPad is a dynamic mathematical education software based on the Internet platform, its dynamic visualization feature allows the abstraction of general laws by constantly changing the geometric relationships between shapes. Unlike the traditional mathematics teaching, the use of problem chains in NetPad-based mathematics classrooms allows teachers to grasp the rhythm of the classroom through problems and dismantle complex mathematical problems, which helps students understand and think. This paper proposes a teaching model based on NetPad and problem chains, which contains teaching objectives, teaching processes, and types of problem chains corresponding to the processes. Among them, the six goals of Bloom's Taxonomy of Educational Objectives are reconstructed based on the connotation level of mathematical abstraction to form new teaching objectives, making them more suitable for teaching mathematical abstraction, and the teaching process is formed in accordance with the new teaching objectives, the process including environment construction, definition of concept, exploration of meaning, testing and application, and transfer and enhancement;each teaching process is matched with a corresponding type of question chain. In the paper, the teaching cases are practiced under the guidance of this model, and good teaching effects are achieved. CCS CONCEPTS •Applied computing •Education •Computer-assisted instruction © 2023 ACM.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Cleaning of Multi-Source Uncertain Time Series Data Based on PageRank

引用

Journal of Donghua University(English Edition) 2023年第6期40卷 695-700页

作者：高嘉伟孙纪舟 Faculty of Computer and Software Engineering Huaiyin Institute of TechnologyHuai’an 223003China

There are errors in multi-source uncertain time series *** discovery methods for time series data are effective in finding more accurate values,but some have limitations in their *** tackle this challenge,we propose a new and convenient truth discovery method to handle time series data.A more accurate sample is closer to the truth and,consequently,to other accurate *** the mutual-confirm relationship between sensors is very similar to the mutual-quote relationship between web pages,we evaluate sensor reliability based on PageRank and then estimate the truth by sensor ***,this method does not rely on smoothness assumptions or prior knowledge of the ***,we validate the effectiveness and efficiency of the proposed method on real-world and synthetic data sets,respectively.

关键词： big data data cleaning time series truth discovery PageRank

来源：评论

学校读者我要写书评

暂无评论

Improving the Inference Efficiency of Transformer Models in Machine Translation Tasks by Low-rank Decomposition Methods

Improving the Inference Efficiency of Transformer Models in ...

引用

2024 International Conference on Electronics and Devices, Computational Science, ICEDCS 2024

作者： Liu, Zhijia University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798331527624

In recent years, Transformer model has made remarkable progress in machine translation tasks and has become the mainstream translation model. However, the calculation complexity of Transformer model is high, especially when dealing with long sequences, the inference efficiency becomes a key issue. In order to improve the inference efficiency of Transformer model, a method based on low-rank decomposition is adopted, and the calculation amount is significantly reduced by optimizing the key modules of the model. Firstly, this paper decomposes the self-attention mechanism in the Transformer model into low-rank, and decomposes the high-dimensional matrix into the product of several low-dimensional matrices by using matrix decomposition technology, thus reducing the computational complexity. Secondly, in the process of model training, pruning technology is combined to remove redundant parameters, so as to further reduce the calculation amount and model scale. On the premise of ensuring the translation quality, this paper carries out experimental verification on large-scale data sets, and the results show that this method can greatly improve the inference speed of the model while maintaining the translation performance. For short sentences with less than 100 words, the inference time of the original model is from 50 milliseconds to 140 milliseconds, and the inference time of the low-rank decomposition model is shortened to 40-100 milliseconds, which is a significant improvement for the real-time translation system. The experimental results show that the low-rank decomposition method not only significantly improves the inference efficiency of the model, but also effectively reduces the consumption of computing resources, which provides a more economical and efficient choice for practical application. © 2024 IEEE.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

AOA Based Localization and orientation estimation of UWB via Weighted Least Squares 24

AOA Based Localization and orientation estimation of UWB via...

引用

24th IEEE International Conference on Communication technology, ICCT 2024

作者： Zhang, Di Li, Ye Yin, Guangqiang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798350363760

In the Internet of Things (IoT), robot localization using ultra-wideband (UWB) technology requires estimating both the position and orientation of the robot. However, current localization and orientation estimation methods often rely on rigid body models, which require multiple anchors, leading to high system costs. To address this limitation, this paper focuses a self-localization approach based on the angle of arrival (AOA), which reduces complexity with only a single anchor. We propose an enhanced algorithm that employs weighted least squares (WLS) to improve estimation accuracy. Additionally, we derive the closed-form Cramér-Rao lower bound (CRLB) as a theoretical benchmark to evaluate the performance of the proposed algorithm. Both simulation results and real-world experiments demonstrate that the proposed algorithm achieves high localization accuracy, providing a cost-effective and efficient solution for IoT applications. © 2024 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

LSRN-AED: lightweight super-resolution network based on asymmetric encoder–decoder

引用

Soft Computing 2024年第13-14期28卷 8513-8525页

作者： Huang, Shuying Li, Wei Yang, Yong Wan, Weiguo Lai, Houzeng School of Software Tiangong University Tianjin300387 China School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang330032 China School of Computer Science and Technology Tiangong University Tianjin300387 China

Due to limited memory and computing resources, the application of deep neural networks on embedded and mobile devices is still a great challenge. To tackle this problem, this paper proposes a lightweight super-resolution network based on asymmetric encoder–decoder (LSRN-AED), which achieves better performance while reducing model parameters and computation. On the basis of rethinking the roles of encoder and decoder, an asymmetric encoder–decoder (AED) composed of complex encoders and simple decoders is designed to achieve feature extraction and reconstruction. Here, the decoder only adopts one inverted residual block, which can reduce the computational cost of the model and the redundancy of mapping features. For the encoder, inspired by the Transformer structure, an epiphany encoder is designed to realize the feature extraction and representation. In the encoder, a multi-way epiphany attention module (MEAM) is constructed, in which inverted residual blocks are used to replace traditional residual blocks to extract features and reduce model complexity. To realize the selection and enhancement of spatial features, an epiphany attention block (EAB) is designed by exploiting depth-wise convolutions which can learn the significant spatial information of the feature maps. Experimental results demonstrate that the proposed LSRN-AED can achieve better performance at lower parameter cost and outperform some existing state-of-the-art lightweight models. For example, compared to the advanced SMSR method, the proposed LSRN-AED has better evaluation metrics while reducing the number of parameters by 45%, 44%, and 44%, and FLOPs by 44%, 42%, and 41% on the × 2/3/4 SR tasks, respectively. The code will be published on GitHub after our paper is accepted for publication. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Feature extraction

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：