检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Lee, Pilhyeon Hwang, Sunhee Jeon, Seogkyu Byun, Hyeran Department of Computer Science Yonsei University Graduate School of Artificial Intelligence Yonsei University Graduate Program of Cognitive Science Yonsei University AI Imaging Tech. Team LG Uplus

This paper focuses on EEG-based visual recognition, aiming to predict the visual object class observed by a subject based on his/her EEG signals. One of the main challenges is the large variation between signals from different subjects. It limits recognition systems to work only for the subjects involved in model training, which is undesirable for real-world scenarios where new subjects are frequently added. This limitation can be alleviated by collecting a large amount of data for each new user, yet it is costly and sometimes infeasible. To make the task more practical, we introduce a novel problem setting, namely subject adaptive EEG-based visual recognition. In this setting, a bunch of pre-recorded data of existing users (source) is available, while only a little training data from a new user (target) are provided. At inference time, the model is evaluated solely on the signals from the target user. This setting is challenging, especially because training samples from source subjects may not be helpful when evaluating the model on the data from the target subject. To tackle the new problem, we design a simple yet effective baseline that minimizes the discrepancy between feature distributions from different subjects, which allows the model to extract subject-independent features. Consequently, our model can learn the common knowledge shared among subjects, thereby significantly improving the recognition performance for the target subject. In the experiments, we demonstrate the effectiveness of our method under various settings. Our code is available at here. Copyright © 2021, The Authors. All rights reserved.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Implementing the Haversine Formula for Detecting Societal Issues and Delivering Relevant Preaching Content

Implementing the Haversine Formula for Detecting Societal Is...

引用

International Conference on Electrical Engineering and Informatics (ICon EEI)

作者： Rahmad Kurniawan Fatayat Tisha Melia Evfi Mahdiyah Abdul Somad Batubara Imam Ghozali Ilyas Husti Department of Computer Science Faculty of Mathematics and Natural Sciences Universitas Riau Pekanbaru Indonesia Bandar Seri Begawan Brunei Darussalam Universiti Islam Sultan Sharif Ali Brunei Darussalam Sekolah Tinggi Agama Islam Negeri (STAIN) Bengkalis Bengkalis Indonesia Graduate Program Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331540791

ISBN: (纸本)9798331540807

The effectiveness of Islamic preaching is often hindered by the need for localized data on societal issues, which leads to lectures that may not address the community’s specific needs. This study seeks to bridge this gap by developing a system that provides relevant preaching outlines tailored to issues detected within a 1 km radius of a mosque. The system incorporates data from 185 mosques and is enhanced by integrating societal issues as a feature. The Haversine formula was employed for precise distance calculations to identify nearby issues accurately. Blackbox testing verified that the system functions correctly. In addition, response time experiments showed an average time of 0.17 seconds. This result highlights the system's overall efficiency in delivering quick responses. Furthermore, a user acceptance test involving eight Islamic preachers revealed high satisfaction with the system’s ease of understanding, as indicated by a mean score of 4.75. These findings suggest that the system effectively supports preachers in delivering contextually relevant preaching and enhances the impact of their preaching efforts by aligning them with the specific concerns of the communities. This innovative approach marks a significant step forward in using geospatial intelligence for religious outreach, with future developments planned to integrate AI to generate dynamic content for various Islamic occasions.

关键词： Electrical engineering Bridges Closed box Geospatial analysis Time factors Artificial intelligence Informatics Testing

来源：评论

学校读者我要写书评

暂无评论

Assistive technology with device for self-inflating bag in neonatology

引用

Research on Biomedical Engineering 2025年第2期41卷

作者： Marcelino, Ana Carolina Rodovanski, Giovana Pascoali Bonetti, Karoline Panes, Caio Rabinovich de Almeida Martins, Fernando Moran, Cristiane Aparecida Araranguá Brazil Graduate Program in Neurosciences and Behavior Department of Experimental Psychology of the Institute of Psychology-University of São Paulo Sao Paulo Brazil Araranguá Brazil Computer Engineering Instituto Mauá de Tecnologia São Caetano do Sul Brazil Electronic Engineering and Computing with Emphasis on Electronic Devices and Systems at Instituto Tecnológico de Aeronáutica–ITA São Caetano do Sul Brazil Department of Physiotheraphy and at the Postgraduate Program in Rehabilitation Science of the Federal University of Santa Catarina-UFCS Ararangua Brazil

Purpose: The objectives of this study were to create a device with technological development of the self-inflating bag (SIB) equipment to measure the variables tidal volume, peak inspiratory pressure, and inspiratory flow and to evaluate the knowledge of undergraduate students in handling the SIB. To reduce the risks of mortality, length of hospital stay, and infections, SIB is a resource used to ventilate the patient through the inflation of the device, but it is not capable of measuring the ventilatory parameters. Excess ventilation and incorrect handling of the bag can cause lung injury in newborns. Therefore, measuring these parameters can prevent lung injury resulting from inadequate ventilation. Method: This is a cross-sectional and experimental study, with the development of a device SIB that allows the evaluation of variables of neonatal respiratory mechanics that were tested with an artificial lung. It was approved by the Research Ethics Committee and the research was developed in three stages: the first represents the search for scientific articles for the consensus of neonatal ventilatory variables for the construction of the SIB parameters;the second stage depicts the technological development of a device capable of monitoring such variables through the SIB. In the third stage, the content validation of the device with the handling of the SIB was carried out by students of medicine and physiotherapy courses of Brazil. Results: In this work, a device that analyzes the values of the main ventilatory parameters in neonatology was developed and to generate a safety range for the use of the device, curves with a tolerance of 10% up and down were created. All electronic components were coupled to the equipment, with a display that transmits the parameter values. The web page can be used on a cell phone, tablet, computer, or SmartTv, as long as it is connected to the "RespiratorIoT_AP" network. Among the 29 participants in the study, 8 said they were familiar w

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Based Augmentation for Lung Cancer Risk Prediction from Temporal CT Images

Diffusion-Based Augmentation for Lung Cancer Risk Prediction...

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Hsing-Chen Meng Yi-Hui Lin Chun-Rong Huang Nai-Wen Shih Shawn Wu Yen-Yu Lin Graduate Degree Program of AI National Yang Ming Chiao Tung University Hsinchu Taiwan Dept. of Radiation Oncology Taichung Veterans General Hospital Taichung Taiwan Dept. of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Dept. of Diagnostic Imaging SY Research Institute NY USA

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Cancer risk prediction based on CT images of a patient taken at multiple time points in the past has become an emerging research topic. While deep learning methods yield promising results, they require a large amount of temporally sequenced data for reliable performance. Acquiring such time-series data is expensive and time-consuming. Hence, data aug-mentation based on a small, annotated, and temporally sequenced medical image dataset is essential to cancer risk prediction. This paper introduces a novel diffusion-based method for augmenting temporal medical images with an application to lung cancer risk prediction. Specifically, we develop our approach based on a conditional diffusion model owing to its high flexibility of condition design. We generate target images of a patient for training by overlaying tumors recently detected and masked by eroded segmentation maps onto CT images taken earlier to simulate tumor growth. Specifically, our conditional diffusion model is trained by using CT images taken in the first or second year, along with tumor segmentation maps in the third year, as well as the generated target images. Three distinct generation strategies are designed by using different combinations of CT images and eroded segmentation maps as conditions to synthesize lung CT images, hence diversifying and enriching the training set. Experimental results demonstrate that learning using 25 % of training data together with our augmented data achieves comparable performance to that using 100% of training data.

关键词： Training Image segmentation Computed tomography Lungs Lung cancer Training data Diffusion models Reliability Tumors Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

5-Fold Cross Validation on Supporting K-Nearest Neighbour Accuration of Making Consimilar Symptoms Disease Classification

5-Fold Cross Validation on Supporting K-Nearest Neighbour Ac...

引用

computer science and Engineering (IC2SE), International Conference on

作者： Andy Satria Opim Salim Sitompul Herman Mawengkang Graduate Program of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Universitas Sumatera Utara Medan Indonesia

ISBN: (纸本)9781665400473

Classification is a technique in machine learning that is used to built the group of data. The data that consist of class and target are grouped based on the data attachment to the sample data, so that the data group can be used as a basis for making decisions at a later stage. This study aims to find a classification of two diseases, dengue fever and typhus which have similar symptoms using a combination of two techniques, 5-Fold Cross Validation and K-Nearest Neighbor. The combination of these techniques is done to improve the accuracy of the classification, feature selection is done in preprocessing phase to collect verified feature to get information gain to measure which feature is kept and continue to next stage of classification process. A confusion matrix will be applied to test the performance in terms of the accuracy of the constructed classification. K-Nearest Neighbor (KNN) is a classification method that applies a supervised algorithm, while 5-Fold Cross Validation is a statistical method that is applied to test the performance of a method or technique. This investigation resulted in an increase in the value of accuracy and recall, with a score of 1.79 points and a recall value of 96.43%.

关键词： computer science Phase measurement Statistical analysis Machine learning Gain measurement Feature extraction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Digital art technology publication in indonesia: A bibliometric analysis (2011-2020) technology 6

Digital art technology publication in indonesia: A bibliomet...

引用

6th International Conference on Information Management and Technology, ICIMTech 2021

作者： Maulana, Fairuz Iqbal Audia Agustina, Ira Gasa, Frederik Masri Rahmadika, Sandi Ramdania, Diena Rauda Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Design Interior Design Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Economics Communication Communication Science Department Jakarta11480 Indonesia National University Busan Interdisciplinary Program of Information Security Graduate School Pukyong Korea Republic of UIN Sunan Gunung Djati Department of Informatics Bandung Indonesia

ISBN: (纸本)9781665449373

Digital art technology is a form of technology in the form of hardware or software that can produce artistic works or practices as part of the creative process. This research is an idea about the publication of digital art technology, which shows its widespread use based on data from publications in Indonesia. This study visually maps scientific publications in digital techniques indexed with bibliometric analysis at the Indonesian state level. This study collected data from the Scopus database, used the Scopus website analysis feature, and visualized the bibliometric network using Vosviewer. The method used consists of five phases: search keyword determination, initial search results, search results refinement, preliminary compilation and data analysis. 57 academic documents published in Indonesia between 2011 and 2020 were obtained in the search for data based on the Scopus database. The processed data show patterns and trends in the increasing number of international publications in digital art technology indexed by Scopus. This study proposes a classification of the convergence axis. © 2021 IEEE.

关键词： Arts computing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Improving Multiclass Anomaly Detection on Conveyor Belts

Machine Learning Techniques for Improving Multiclass Anomaly...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Saulo N. Matos Otávio F. Coletti Rafael Zimmer Fernando U. Filho Ricardo C.C. L. de Carvalho Victor R. da Silva Jorge L. Franco Thomas V. B. Pinto Luiz G. D. de Barros Caetano M. Ranieri Bruno E. Lopes Diego F. Silva Jó Ueyama Gustavo Pessin Institute of Mathematics and Computer Science University of Sã o Paulo Brazil São Carlos School of Engineering University of São Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Graduate Program in Electrical Engineering Universidade Federal of Minas Gerais Belo Horizonte MG Brazil Vale SA Vitória Brazil

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Industrial conveyor belt systems are an efficient means of transport due to their adaptability and extension. Nonetheless, such systems are prone to various failures, including but not limited to: idler anomalies; belt tears; and pin misalignment which can cause significant disruptions in the production process. Preemptive maintenance and health monitoring of these conveyor belts is a common practice for avoiding these failures, but a challenging task due to the rarity of comprehensive anomaly detection datasets in the area, with current works aimed at evaluating the belt's immediate condition at fixed points. This study addresses this research gap by comparing multiple machine learning techniques, such as a proposed Hybrid Neural Network (HNN) tailored for classification of multiple anomaly classes, as well as machine learning approaches for time series based on feature extraction, Catch22, Minirocket Arsenal, and Time Series Forest. Our proposed HNN architecture performed better in classifying and distinguishing between different types of anomalies, with an accuracy of 95.55%. The obtained results suggest a promising approach for the area of predictive maintenance for industrial conveyor systems, as well as gives insights on possible improvements on the model and future research.

关键词： Machine learning algorithms Accuracy Time series analysis Machine learning Belts Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Nanoslot-Induced Ultrastrong Phonon-Photon and Phonon-Phonon Coupling in Hybrid Organic-Inorganic Perovskites 16

Nanoslot-Induced Ultrastrong Phonon-Photon and Phonon-Phonon...

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Kim, Dasom Hou, Jin Lee, Geon Agrawal, Ayush Kim, Sunghwan Zhang, Hao Bao, Di Baydin, Andrey Wu, Wenjing Tay, Fuyang Huang, Shengxi Hagenmüller, Daivd Chia, Elbert E. M. Kim, Dai-Sik Seo, Minah Mohite, Aditya D. Kono, Junichiro Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States Sensor System Research Center Korea Institute of Science and Technology Seoul02792 Korea Republic of Department of Physics and Astronomy Seoul National University Seoul08826 Korea Republic of Department of Chemical and Biomolecular Engineering Rice University HoustonTX77005 United States Ulsan44919 Korea Republic of Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 637371 Singapore Smalley-Curl Institute Rice University HoustonTX77005 United States Université de Strasbourg Cnrs Strasbourg67000 France KU-KIST Graduate School of Converging Science and Technology Korea University Seoul02841 Korea Republic of Department of Physics and Astronomy Rice University HoustonTX77005 United States

Methods for harnessing vibrational states are desired for phonon-based technologies. We realized ultrastrong coupling of two phonon modes in perovskite materials induced by ultrastrong coupling with a common photonic ... 详细信息

ISBN: (纸本)9798350372076

关键词： Organic-inorganic materials

来源：评论

学校读者我要写书评

暂无评论

Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In Shen, Xuemin Poor, H. Vincent The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Driven by advances in generative artificial intelligence (AI) techniques and algorithms, the widespread adoption of AI-generated content (AIGC) has emerged, allowing for the generation of diverse and high-quality content. Especially, the diffusion model-based AIGC technique has been widely used to generate content in a variety of modalities. However, the real-world implementation of AIGC models, particularly on resource-constrained devices such as mobile phones, introduces significant challenges related to energy consumption and privacy concerns. To further promote the realization of ubiquitous AIGC services, we propose a novel collaborative distributed diffusion-based AIGC framework. By capitalizing on collaboration among devices in wireless networks, the proposed framework facilitates the efficient execution of AIGC tasks, optimizing edge computation resource utilization. Furthermore, we examine the practical implementation of the denoising steps on mobile phones, the impact of the proposed approach on the wireless network-aided AIGC landscape, and the future opportunities associated with its real-world integration. The contributions of this paper not only offer a promising solution to the existing limitations of AIGC services but also pave the way for future research in device collaboration, resource optimization, and the seamless delivery of AIGC services across various devices. Our code is available at https://***/HongyangDu/DistributedDiffusion. © 2023, CC BY.

关键词： Wireless networks

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：