检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Khowaja, Sunder Ali Nkenyereye, Lewis Mujtaba, Ghulam Lee, Ik Hyun Fortino, Giancarlo Dev, Kapal Faculty of Engineering and Technology University of Sindh Sindh Jamshoro76080 Pakistan Department of Computer Science and Information Security Seoul05006 Korea Republic of Department of Computer Science West Virginia University MorgantownWV26506 United States IKLab Inc. Gyeonggi-do Siheung15073 Korea Republic of Department of Mechatronics Tech University of Korea Gyeonggi-do Siheung15073 Korea Republic of Department of Informatics Modeling Electronics and Systems University of Calabria Calabria Italy Department of Computer Science ADAPT Centre Munster Technological University Cork Ireland

With the surge in emerging technologies such as Metaverse, spatial computing, and generative AI, the application of facial style transfer has gained a lot of interest from researchers as well as startups enthusiasts alike. StyleGAN methods have paved the way for transfer-learning strategies that could reduce the dependency on the huge volume of data that is available for the training process. However, StyleGAN methods have the tendency of overfitting that results in the introduction of artifacts in the facial images. Studies, such as DualStyleGAN, proposed the use of multipath networks but they require the networks to be trained for a specific style rather than generating a fusion of facial styles at once. In this paper, we propose a FusIon of STyles (FIST) network for facial images that leverages pre-trained multipath style transfer networks to eliminate the problem associated with lack of huge data volume in the training phase along with the fusion of multiple styles at the output. We leverage pre-trained styleGAN networks with an external style pass that use residual modulation block instead of a transform coding block. The method also preserves facial structure, identity, and details via the gated mapping unit introduced in this study. The aforementioned components enable us to train the network with very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient, flexible style and model fusion in the generative space. We perform extensive experiments to show the superiority of FISTNet in comparison to existing state-of-the-art methods. © 2023, CC BY-NC-ND.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Darloc: Deep Learning and Augmentation Based Robust Magnetic Indoor Localization

SSRN

引用

SSRN 2022年

作者： Wang, Qinghu Jia, Jie Deng, Yansha Chen, Jian Wang, Xingwei Huang, Min Aghvami, Abdol Hamid School of Computer Science and Engineering Northeastern University Shenyang110819 China School of Computer Science and Technology Institute of Computer Engineering Inner Mongolia Minzu University Tongliao028000 China Department of Informatics King’s College London LondonWC2R 2LS United Kingdom School of Information Science and Engineering Northeastern University Shenyang110819 China

Magnetic-based indoor localization has attracted considerable attention due to the pervasiveness of geomagnetic fields and is free of extra infrastructures. However, existing approaches still face heterogeneity problems caused by the type of devices, the holding attitudes, and the moving speeds of pedestrians. To cope with it, we propose a novel deep learning and augmentation-based magnetic localization framework (DarLoc). First, we invoke orientation-insensitive magnetic signal extraction to remove the Direct Current (DC) component of the sequence and to eliminate the impact caused by different holding attitudes and various mobile devices. Second, we propose novel data augmentation and feature augmentation methods to extract features of speed information, thus tackling the multi-scale sequence problem caused by different moving speeds. Finally, we propose a deep multi-scale spatial-temporal learning model to extract both spatial and temporal features of the augmented sequences and to provide a robust localization for people with various moving speeds and attitudes. Extensive experiments, including a total of 189 volunteers with 4 different mobile devices and multiple moving speeds, are employed to evaluate the performance of DarLoc over 14 months. Experiment results reveal that: 1) DarLoc obtains an average localization accuracy of 0.47 m and 0.56 m under constant and variable moving speeds scenarios, respectively;2) DarLoc obtains about 41% and 60% localization accuracy improvement compared with the state-of-the-art localization methods. © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics

arXiv

引用

arXiv 2022年

作者： Guo, Xiaoyuan Duan, Jiali Kuo, C.-C. Jay Gichoya, Judy Wawira Banerjee, Imon Department of Computer Science Emory University GA United States Ming Hsieh Department of Electrical and Computer Engineering University of Southern California CA United States Department of Radiology and Imaging Sciences Emory University GA United States School of Computing Informatics Decision Systems Engineering Arizona State University AZ United States Department of Radiology Mayo Clinic AZ United States

Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual modality is inherently continuous and high-dimensional, which potentially prohibits the alignment as well as fusion between vision and language modalities. We therefore propose to "discretize" the visual representation by joint learning a codebook that imbues each visual token a semantic. We then utilize these discretized visual semantics as self-supervised ground-truths for building our Masked Image Modeling objective, a counterpart of Masked Language Modeling which proves successful for language models. To optimize the codebook, we extend the formulation of VQ-VAE which gives a theoretic guarantee. Experiments validate the effectiveness of our approach across common vision-language benchmarks. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Indonesian Language Model for Emotion Classification and Sentiment Analysis

Transformer-Based Indonesian Language Model for Emotion Clas...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Hendri Ahmadian Taufik Fuadi Abidin Hammam Riza Kahlil Muchtar Graduate School of Mathematics and Applied Sciences Universitas Syiah Kuala Banda Aceh Indonesia Department of Informatics Faculty of Mathematics and Natural Sciences Universitas Syiah Kuala Banda Aceh Indonesia Research Center for Artificial Intelligence and Cyber Security National Research and Innovation Agency Jakarta Indonesia Department of Electrical and Computer Engineering Faculty of Engineering Universitas Syiah Kuala Banda Aceh Indonesia

The rapid development of social networks has made much user-generated data accessible for public evaluation. These data can be used for multiple purposes, such as textual analysis of comments and reviews. This article employs a variant of the bidirectional encoder representations from Transformer (BERT) model designed explicitly for Bahasa Indonesia (called IndoBERT model) to enhance the performance of the Indonesian natural language understanding benchmark in tasks, such as sentiment analysis and emotion classification. The two tasks were tested using a hybrid method, combining the IndoBERT model's last hidden layer summation with a neural network model. The performance of the resulting model was assessed using the F1-score metric. The experimental results show that the proposed model attains an accuracy of 0.92 and 0.76 for sentiment analysis and emotion classification, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy Protection with Group Onion Routing based on AI-based URL Classification

Differential Privacy Protection with Group Onion Routing bas...

引用

2020 ACM International Conference on Intelligent Computing and its Emerging Applications, ICEA 2020

作者： Liu, I-Hsien Chang, Yung-Lin Li, Jung-Shian Liu, Chuan-Gang Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Tainan Taiwan Department of Applied Informatics and Multimedia Chia-Nan University of Pharmacy and Science Tainan Taiwan

ISBN: (纸本)9781450383042

Due to the rapid spread of tablet computers, smartphones, and other mobile information devices, wireless communication technology is fully developed and deployed widely. Mobile Internet access has been a main and important way to communicate the world in daily and it privacy protection also catches much attentions. The Onion Router, better known as Tor, is a technique for anonymous communication over internet without regional restrictions for privacy protection. Apart from this, Tor can reach sites that normal search engine cannot search. As the opinion of Tor, the transmitted data has been encrypted layer by layer, just like onion, before it reaching server. Our research proposed a system predicting URL's category with the use of machine learning technique before visiting. According to the category prediction, we represent different privacy level with three kinds of RSA key lengths on onion routing. Depending on various situations, our system can obtain the balance between security and time cost. Hence, our proposed scheme can make onion routing more flexible and efficiently. © 2020 ACM.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and CNN-Based Approach for Efficient Detection of Potato Leaf Diseases

Deep Learning and CNN-Based Approach for Efficient Detection...

引用

IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)

作者： Taher M. Ghazal Jamshaid Iqbal Janjua Walid Abushiba Muhammad Salah-ud-Din Iqbal Waqas Iqbal Munir Ahmad Muhammad Saleem Faculty of Information Science and Technology College of Arts & Science Applied Science University Manama Bahrain & Center for Cyber Security Universiti Kebangsaan Malaysia Selangor Malaysia Al-Khawarizimi Institute of Computer Science (KICS) University of Engineering & Technology (UET) Lahore Pakistan College of Engineering Applied Science University Bahrain School of Computer Science Minhaj University Lahore Pakistan Department of forestry and Range Management University of Agriculture Faisalabad Pakistan College of Informatics Korea University Seoul Republic of Korea

ISBN: (数字)9798331543105

ISBN: (纸本)9798331543112

Potato is a maj or food crop worldwide, providing essential nutrients to millions. However, various diseases can severely affect potato crops, leading to reduced yield and quality. Early disease detection is crucial for effective disease management and control. This study presents a deep learning-based approach using CNN to autonomously diagnose potato leaf diseases. The model leverages the Plant Village dataset, which contains images of potato leaves in both healthy and diseased states. The proposed method demonstrates high accuracy in identifying multiple potato leaf diseases, offering promising results for application in precision agriculture. By utilizing CNN s, the model effectively detects and classifies disease symptoms, providing a reliable tool for early intervention in agricultural practices. The approach's potential impact on improving crop yield and minimizing losses due to diseases is highlighted, making it a significant contribution to smart farming techniques. The study underscores the importance of deep learning in modern agricultural practices and its role in enhancing disease management strategies.

关键词： Deep learning Precision agriculture Smart agriculture Plants (biology) Geoscience Nutrients Reliability Remote sensing Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Konstantina-Helen Tsarapatsani Vasilios D. Tsakanikas Antonis Sakellarios Hans J. Trampisch Efterpi Karapintzou Henrik Rudolf George K. Matsopoulos Dimitrios I. Fotiadis Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Department of Medical Informatics Biometry and Epidemiology Ruhr University Bochum Bochum Germany Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greeece Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina and Biomedical Research Institute-FORTH Ioannina Greece

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction.

关键词： Accuracy Sensitivity Explainable AI Biological system modeling Peptides Receivers Predictive models Indexes Cardiovascular diseases Random forests

来源：评论

学校读者我要写书评

暂无评论

Cooperative multi-modal localization in connected and autonomous vehicles

arXiv

引用

arXiv 2021年

作者： Piperigkos, Nikos Lalos, Aris S. Berberidis, Kostas Anagnostopoulos, Christos Computer Engineering & Informatics Department University of Patras Greece Industrial Systems Institute Athena Research Center Patras Greece

Cooperative Localization is expected to play a crucial role in various applications in the field of Connected and Autonomous vehicles (CAVs). Future 5G wireless systems are expected to enable cost-effective Vehicle-to-Everything (V2X) systems, allowing CAVs to share with the other entities of the network the data they collect and measure. Typical measurement models usually deployed for this problem, are absolute position from Global Positioning System (GPS), relative distance and azimuth angle to neighbouring vehicles, extracted from Light Detection and Ranging (LIDAR) or Radio Detection and Ranging (RADAR) sensors. In this paper, we provide a cooperative localization approach that performs multi modal-fusion between the interconnected vehicles, by representing a fleet of connected cars as an undirected graph, encoding each vehicle position relative to its neighbouring vehicles. This method is based on: i) the Laplacian Processing, a Graph Signal Processing tool that allows to capture intrinsic geometry of the undirected graph of vehicles rather than their absolute position on global coordinate system and ii) the temporal coherence due to motion patterns of the moving vehicles. © 2021, CC BY-NC-ND.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Construction of Ternary Bent Functions From Ternary Linear Functions

Construction of Ternary Bent Functions From Ternary Linear F...

引用

International Symposium on Multiple-Valued Logic

作者： Milena Stanković Radomir S. Stanković Claudio Moraga Jaakko T. Astola Faculty of Electronic Engineering Department of Computer ScienceNi&#x0161 Serbia Mathematical Institute of SASA Belgrade Serbia Faculty of Computer Science Technical University of Dortmund Dortmund Germany Department of Informatics Technical University &#x201C Federico Santa Mar&#x00ED a&#x201D Valpara&#x00ED so Chile Department of Signal Processing Tampere University of Technology Tampere Finland

ISBN: (数字)9781665423953

ISBN: (纸本)9781665423960

As in the binary case, ternary bent functions are defined as most non-linear ternary functions meaning that they are at the largest possible Hamming distance from affine ternary functions. It is therefore interesting to observe that some ternary bent functions can be constructed as various combinations of linear ternary functions. By starting from the combination of linear functions corresponding to the basic ternary bent functions the construction of different other ternary bent functions can be performed by the application of different combinations of FFT-like permutation matrices for ternary functions.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Outcomes of combined mitochondria and mesenchymal stem cellsderived exosome therapy in rat acute respiratory distress syndrome and sepsis

引用

World Journal of Stem Cells 2024年第6期16卷 690-707页

作者： Kun-Chen Lin Wen-Feng Fang Jui-Ning Yeh John Y Chiang Hsin-Ju Chiang Pei-Lin Shao Pei-Hsun Sung Hon-Kan Yip Department of Anesthesiology Kaohsiung Chang Gung Memorial HospitalKaohsiung 83301TaiwanChina Division of Pulmonary and Critical Care Medicine Department of Internal MedicineKaohsiung Chang Gung Memorial HospitalChang Gung University College of MedicineKaohsiung 83301TaiwanChina Department of Cardiology The First Affiliated Hospital of Jinan UniversityGuangzhou 510630Guangdong ProvinceChina Department of Computer Science and Engineering National Sun Yat-sen UniversityKaohsiung 804201TaiwanChina Department of Healthcare Administration and Medical Informatics Kaohsiung Medical UniversityKaohsiung 80708TaiwanChina School of Medicine Chung Shan Medical UniversityTaichung 40201TaiwanChina Department of Nursing Asia UniversityTaichung 41354TaiwanChina Division of Cardiology Department of Internal MedicineKaohsiung Chang Gung Memorial Hospital and Chang Gung University College of MedicineKaohsiung 83301TaiwanChina Institute for Translational Research in Biomedicine Kaohsiung Chang Gung Memorial HospitalKaohsiung 83301TaiwanChina Center for Shockwave Medicine and Tissue Engineering Kaohsiung Chang Gung Memorial HospitalKaohsiung 83301TaiwanChina Department of Medical Research China Medical University HospitalChina Medical UniversityTaichung 40402TaiwanChina School of Medicine College of MedicineChang Gung UniversityTaoyuan 33302TaiwanChina

BACKGROUND The treatment of acute respiratory distress syndrome(ARDS)complicated by sepsis syndrome(SS)remains *** To investigate whether combined adipose-derived mesenchymal-stem-cells(ADMSCs)-derived exosome(EXAD)and exogenous mitochondria(mitoEx)protect the lung from ARDS complicated by *** In vitro study,including L2 cells treated with lipopolysaccharide(LPS)and in vivo study including male-adult-SD rats categorized into groups 1(sham-operated-control),2(ARDS-SS),3(ARDS-SS+EXAD),4(ARDS-SS+mitoEx),and 5(ARDS-SS+EXAD+mitoEx),were included in the present *** In vitro study showed an abundance of mitoEx found in recipient-L2 cells,resulting in significantly higher mitochondrial-cytochrome-C,adenosine triphosphate and relative mitochondrial DNA levels(P<0.001).The protein levels of inflammation[interleukin(IL)-1β/tumor necrosis factor(TNF)-α/nuclear factor-κB/toll-like receptor(TLR)-4/matrix-metalloproteinase(MMP)-9/oxidative-stress(NOX-1/NOX-2)/apoptosis(cleaved-caspase3/cleaved-poly(ADP-ribose)polymerase)]were significantly attenuated in lipopolysaccharide(LPS)-treated L2 cells with EXAD treatment than without EXAD treatment,whereas the protein expressions of cellular junctions[occluding/β-catenin/zonula occludens(ZO)-1/E-cadherin]exhibited an opposite pattern of inflam-mation(all P<0.001).Animals were euthanized by 72 h post-48 h-ARDS induction,and lung tissues were *** 72 h,flow cytometric analysis of bronchoalveolar lavage fluid demonstrated that the levels of inflam-matory cells(Ly6G+/CD14+/CD68+/CD11b/c+/myeloperoxidase+)and albumin were lowest in group 1,highest in group 2,and significantly higher in groups 3 and 4 than in group 5(all P<0.0001),whereas arterial oxygen-saturation(SaO2%)displayed an opposite pattern of albumin among the *** findings of lung injury/fibrosis area and inflammatory/DNA-damaged markers(CD68+/γ-H2AX)displayed an identical pattern of SaO2%among the groups(all P<0.0001).The pro

关键词： Acute respiratory distress syndrome Sepsis syndrome Exosomes Mitochondria Adipose tissue-derived mesenchymal stem cells Inflammation

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：