检索结果-内蒙古大学图书馆

4th international conference on Computational Methods in science and Technology, ICCMST 2024

作者： Dhiman, Pummy Kaur, Amandeep Sharma, Dilip Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Engineering and Application GLA University Mathura India

ISBN: (纸本)9781032911571

In today’s digital age, technology has advanced to the point where it is difficult to distinguish be-tween genuine and forged media content. It was intended to be used for entertainment, but it is now being used to deceive people and create biasness, which can lead to disastrous situations. The goal of this bibliometric study is to provide scientific mapping on the role of deep learning in deepfake detection published online. Scopus and VOSviewer are used to create a concept map of 128 articles. Additionally, future directions for research are suggested. © 2025 the Author(s).

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Selective sampling and temporal positional encoding for monocular video based 3D human pose and shape estimation 5

Selective sampling and temporal positional encoding for mono...

引用

5th international conference on Signal Processing and computer science, SPCS 2024

作者： Hou, Yupeng Wen, Han Zeng, Guangping School of Computer & Communication Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

This study introduces a novel framework for video-based 3D human pose and shape estimation, termed Selective sampling and Temporal Positional Encoding (STPE). Our method leverages selective sampling and advanced positional encoding to tackle the temporal complexities of video data and the high cost and scarcity of annotated datasets. Inspired by the Masked Autoencoder (MAE), our approach adopts a selective sampling strategy that efficiently captures the essential dynamics of human motion from partial views, significantly reducing reliance on continuous frames. The framework incorporates Rotary Position Embedding (RoPE), using rotational angles to simplify positional encoding. This innovation decreases model complexity and boosts learning effectiveness. We also introduce randomized index positions during training, introducing variability and enhancing generalization across various datasets and motion patterns. Our model, validated on standard datasets like 3DPW, MPI-INF-3DHP, and Human3.6M, shows enhanced performance in accurate and robust 3D pose and shape capture compared to existing methods. Our results demonstrate that strategic frame sampling and sophisticated positional encoding can significantly improve accuracy and robustness of video-based pose estimation systems. © 2025 SPIE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

research on Building K-Contents Specialized Text2Image Pipeline 27

Research on Building K-Contents Specialized Text2Image Pipel...

引用

27th international conference on advanced Communications Technology, ICACT 2025

作者： Kang, Seungeun Lee, Dahyun Han, Sangbum Lim, Seokjae Kim, Namgi Division of AI Computer Science and Engineering Kyonggi University Suwon154-42 Korea Republic of AI Tech Team LOTTE INNOVATE Seoul179 Korea Republic of

ISBN: (纸本)9791188428137

Recently, there has been a lot of research on the Text2Image generative model as social and technological interest in generative models has increased. In addition, the interest in Korean contents (K-Contnets) has increased. In this paper, we propose "K-Contents Specialized Text2Image Pipeline". "K-Contents Specialized Text2Image Pipelilne" is specialized for understanding Korean prompts and aims to generate images specialized for various K-Contents. To build the pipeline, we collect and preprocess text and image data. Then, we train the Korean Text Encoder on the text data and train three specialized K-Contents generation pipelines on the image data. We also propose to use the SDXL model’s Img2Img Refiner with the SD model for time-efficient image generation. After that, we use the learned pipelines to generate real images and analyze their performance. Finally, we discuss the utilization of the above pipelines, limitations, and future research. Copyright 2025 Global IT research Institute (GIRI). All rights reserved.

关键词： Image Generation K-Contents Korean text encoder Stable Diffusion

来源：评论

学校读者我要写书评

暂无评论

An electromagnetic leakage signal characterization method for multi-feature selection and fusion 24

An electromagnetic leakage signal characterization method fo...

引用

8th international conference on Electronic information Technology and computer engineering, EITCE 2024

作者： You, Xingye Huang, Xin Mao, Jian Huang, Kai Liu, Jinming Zhang, Jiemin College of Computer Engineering Jimei University Fujian Xiamen China College of Computer Engineering Jimei University Xiamen361021 China

ISBN: (纸本)9798400710094

Unintentional electromagnetic leakage is generated during the use of various components of computer equipment. These leaked electromagnetic signals contain a significant amount of useful information, which can be captured and recovered, potentially leading to security problems. However, characterizing these signals is challenging due to substantial environmental noise, making it impossible to extract effective information using a priori knowledge. To address this issue, this paper proposes a multi-feature filtering and fusion-oriented method for characterizing electromagnetic leakage information. This method calculates ten types of feature curves, such as peak-to-peak, variance, and mean, to highlight effective signals in the data. Additionally, it introduces the index based on Wasserstein distance for screening to retain effective features and eliminate irrelevant and redundant ones. A multi-feature fusion model, called the EFT model, is designed using the encoder of the transformer architecture to fuse and process complementary information from the features. Experimental results demonstrate that the proposed method effectively improves data characterization, fully exploits the complementarity between multiple features, and provides more accurate vector representations for tasks such as electromagnetic leakage source localization and leakage source analysis, thereby enhancing the final detection performance. © 2024 Copyright held by the owner/author(s).

关键词： information leakage

来源：评论

学校读者我要写书评

暂无评论

research on intelligent monitoring and quality control of BIM technology based on computer vision in the construction process of villages and towns 3

Research on intelligent monitoring and quality control of BI...

引用

3rd international conference on Algorithms, Network, and Communication Technology, ICANCT 2024

作者： Cao, Zhifang Guangdong Innovative Technical College Guangdong Dongguan523960 China

ISBN: (数字)9781510688902

ISBN: (纸本)9781510688896

In the field of construction, the application of Building information Modeling (BIM) technology combined with computer vision offers a promising avenue for enhancing the quality control and intelligent monitoring of village and township construction projects. This paper introduces a novel approach that integrates BIM with advanced computer vision algorithms to automatically detect construction anomalies and assess quality in real time. Through this integration, the research deploys an experimental system across various construction phases, employing it to monitor adherence to BIM models and identify deviations. The findings reveal a significant improvement in error detection accuracy, substantially reducing the reliance on manual inspections and associated costs. Moreover, the system effectively provides project managers with continuous feedback and insights, thereby streamlining decision-making processes and ensuring compliance with construction standards. Conclusively, this research demonstrates the potential of combining BIM and computer vision technologies to revolutionize construction management practices, marking a step forward in the pursuit of more efficient and high-quality construction processes. © 2025 SPIE.

关键词： Building information Model

来源：评论

学校读者我要写书评

暂无评论

Systematic comparison between a research-grade EEG device and a consumer-grade BCI device for predicting consumer preference using an ML framework

引用

Multimedia Tools and Applications 2025年 1-19页

作者： Ishtiaque, Farhan Miya, Mohammad Tohidul Islam Mashrur, Fazla Rabbi Rahman, Khandoker Mahmudur Vaidyanathan, Ravi Anwar, Syed Ferhat Sarker, Farhana Tat, Huam Hon Hamid, Abu Bakar Abdul Mamun, Khondaker A. AIMS Lab IIRIC UIU Dhaka Bangladesh School of Business and Economics United International University Dhaka Bangladesh Department of Biomedical Engineering University of Rochester RochesterNY United States Department of Mechanical Engineering Imperial College London London United Kingdom Office of the Vice Chancellor BRAC University Dhaka Bangladesh and Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh Faculty of Business City University of Macau Taipa China Faculty of Business Information & Human Sciences Infrastructure University Kuala Lumpur Kuala Lumpur Malaysia Department of CSE United International University Dhaka Bangladesh

Evaluation of marketing stimuli such as static advertisements, video advertisements, promotions, etc. is an important part of marketing research. Traditionally, the evaluation is done through large surveys, focus group discussions, questioner-based surveys, etc. However, these methods are time-consuming and expensive. Here, neuromarketing offers a solution that can improve marketing research. Recently, several EEG-based neuromarketing studies proved the potential of neuromarketing as a marketing research tool. However, most of these researchers used research-grade EEG devices. research-grade EEG devices are bulky and require high setup time. This is why, despite much successful research, the technology is yet to be implemented on a day-to-day basis. On the other hand, consumer-grade BCI devices are cheap, wearable, and offer little to no setup time. So, it is ideal for day-to-day implementation. However, consumer-grade BCI lacks in terms of signal quality and available channel number, and it has not been widely tested in neuromarketing. So, in this study, we compared a research-grade EEG device and a consumer-grade BCI device for consumers’ preference prediction using a machine learning framework. We designed an experiment to record participants' EEG data while they were shown marketing stimuli. Their response has been taken as affective attitude (AA) purchase intention (PI). After that, binary classification was performed. We achieved 80.71% and 82.07% accuracy for predicting purchase intention and affective attitude using the research-grade EEG device, whereas it was 78.31% and 81.23% using the consumer-grade BCI device. These findings prove that consumer-grade BCI can be a viable option for day-to-day usage in neuromarketing. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Analysis of CAD tools in VLSI Physical design

Analysis of CAD tools in VLSI Physical design

引用

2025 IEEE international Students' conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Bharath, Duttuluru Jagadeesh, A. Chaitanya M, Uday Jaya, T. Saveetha Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331529833

The increasing complexity of VLSI physical design has elevated the need for advanced CAD tools capable of efficiently managing tasks such as floor planning, placement, routing, and optimization. This study presents a detailed evaluation of prominent CAD tools, analyzing their effectiveness in addressing the critical demands of modern VLSI design, including power efficiency, performance, and scalability. By comparing the strengths and limitations of each tool, this work aims to guide practitioners in selecting optimal solutions for their specific design requirements. Additionally, emerging trends in CAD development, particularly the integration of AI and machine learning, are discussed as pathways to further enhance design automation. Our analysis provides insights that not only underscore the current capabilities of CAD tools but also suggest directions for future research to meet the evolving needs of the VLSI industry. © 2025 IEEE.

关键词： Power systems computer aided design

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity Threat Detection and Classification

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity T...

引用

2025 international conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Akilandeswari, S. Soumya, T.R. Sumathi, S. Sushith, Mishmala Brinda, V. Rajan, S. E.G.S. Pillay Engineering College Department of Artificial Intelligence & Data Science Nagapattinam611002 India Prathyusha Engineering College Department of Computer Science Engineering Tiruvallur602025 India Velammal Engineering College Department of Electronics and Communication Engineering Chennai600066 India Adithya institute of Technology Department of Information Technology Kurumbapalayam India K.Ramakrishnan College Of Engineering Department of Electronics and Communication Engineering Samayapuram621112 India Velalar College of Engineering and Technology Department of Electronics and Communication Engineering Erode638012 India

ISBN: (纸本)9798331509828

With the advancement of digital era comes an increased value for cybersecurity, and these need to be dealt with using advanced techniques. Deep learning - metaheuristic optimization hybrid model for advanced threat detection and mitigation is presented in this paper. With a Convolutional Neural Network (CNN) for feature extraction and Long Short-Term Memory (LSTM) for sequence analysis, the proposed framework integrates all the modules in order to provide robust cyber-attack detection. In order to optimize the parameters of the model, a Particle Swarm Optimization (PSO) algorithm is used in order to achieve better classification accuracy and faster computation. Benchmark datasets are used for extensive experiments, where existing methods outperformed in terms of precision, recall, and Fl-score. The results demonstrate that with detected flagged FPs and the hybrid model, the increased detection rates are achieved without the reduction in true negatives, rendering it a practical solution for real world applications. This research adds to the field by providing a solution to cybersecurity problems that is scalable and adaptable to the present and beyond. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Review of identification technologies for stray animal governance 5

Review of identification technologies for stray animal gover...

引用

5th international conference on Signal Processing and computer science, SPCS 2024

作者： Han, Puze College of Science and Engineering University of Minnesota Twin Cities Minneapolis55455 United States

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

In recent years, societal changes have led to a growing prominence of pets in people's lives. However, uncontrolled pet reproduction in urban areas has given rise to a significant issue of stray animals, posing serious threats to human health and the environment. Conventional manual methods for counting stray animals face challenges in terms of efficiency and the risk of disease transmission. With technological advancements, image recognition, and sound identification, among other techniques, have emerged as crucial tools to address this issue. Image recognition, leveraging intuitive statistics based on external features, combined with the low-power attributes of sound identification and the health assessment capabilities of thermal imaging, collectively provide comprehensive technological support for stray animal population statistics. In the realm of image algorithms, both traditional target detection algorithms and deep learning methods such as RCNN and Faster RCNN employ convolutional neural networks to accurately identify and locate stray animals. Regarding sound algorithms, traditional Gaussian mixture models and hidden Markov models, as well as deep learning techniques involving convolutional neural networks, have effectively enhanced the accuracy of stray animal sound recognition. The integration of image and audio in a hybrid method significantly enhances stray animal monitoring. Employing advanced techniques in video tracking and sound recognition, this approach offers an efficient and practical solution, crucial for wildlife ecosystem surveillance and conservation. research indicates that the application of deep learning methods in the domains of image and sound has significantly advanced compared to traditional approaches. In terms of image processing, I utilized the YOLO algorithm to perform grid division, feature extraction, and loss computation steps to achieve stray animal detection, demonstrating outstanding performance. Through the application of t

关键词： Animals Detection and tracking algorithms Object detection Animal model studies Image processing Education and training Diseases and disorders Positron emission tomography Deep learning Expectation maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

ESert: An Enhanced Span-Based Model for Measurable Quantitative information Extraction from Medical Texts 5th

ESert: An Enhanced Span-Based Model for Measurable Quantitat...

引用

5th international conference on Neural Computing for advanced Applications (NCAA)

作者： Zhang, Qixuan Chen, Jiale Wang, Haitao Cao, Xinyu Jie, Wei Hao, Tianyong South China Normal Univ Sch Comp Sci Guangzhou Peoples R China China Natl Inst Standardizat Beijing Peoples R China

ISBN: (纸本)9789819770069;9789819770076

Measurable quantitative information is one of typical quantitative information in unstructured texts. It consists of entities related to numerics, units and their relationships. How to accurately and efficiently extract measurable quantitative information from unstructured texts remains a challenge. This paper aims to propose an Enhanced span-based joint model named ESert, which uses an n-gram encoder to identify word boundaries with a positive and negative sampling mechanism to extract measurable quantitative information. The experiments evaluate the ESert based on a clinical quantification information dataset containing 1359 Chinese electronic medical records. The results show that our model achieves F1 scores of 97.97% and 97.28% in measurable quantitative information recognition and association, respectively, indicating the effectiveness of the proposed model.

关键词： Measurable quantitative information n-gram encoder positive and negative sampling mechanism

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：