检索结果-内蒙古大学图书馆

London Imaging Meeting, LIM 2023

作者： Kadyrova, Altynay Pedersen, Marius Westland, Stephen Weijkamp, Clemens Horiuchi, Takahiko Department of Computer Science Norwegian University of Science and Technology Gjøvik Norway School of Design University of Leeds LeedsLS2 9JT United Kingdom Canon Production Printing Netherlands B.V Venlo5914 HH Netherlands Graduate School of Engineering Chiba University Chiba Japan

ISBN: (纸本)9780892083633

Naturalness is a complex concept and a number of parameters might impact naturalness perception. In this work, we addressed how the combination of differ ent elevation levels and size of prints impacts natural ness perception of 2.5D prints. The results of a sub jective ranking experiment showed that observers per ceived 2.5D prints as more natural at higher elevation with larger size of print. Moreover, we observed that elevation seems to be a more dominant parameter than size of the print for observers when evaluating natural ness. © 2023 Society for Imaging science and Technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of deep learning models for detecting face mask 7

Comparative analysis of deep learning models for detecting f...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Ramadhan, M. Vickya Muchtar, Kahlil Nurdin, Yudha Oktiana, Maulisa Fitria, Maya Maulina, Novi Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-The-Art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-Trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification. © 2022 Elsevier B.V.. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Constructing Coronary Artery Vessel Segmentation Based on Deep Learning Models and Image Processing 24

Constructing Coronary Artery Vessel Segmentation Based on De...

引用

8th International Conference on Medical and Health Informatics, ICMHI 2024

作者： Peng, Kang-Syuan Chang, Hsiao-Huang Hsu, Ying-Kai Chien, Ting-Ying Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Cardiovascular Surgery Department Taipei Veterans General Hospital Taipei City TaiwanTaipei Medical University Taipei City Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan TaiwanInnovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan

ISBN: (纸本)9798400716874

Narrowing of the coronary arteries is an important indicator of the severity of coronary artery disease (CAD) in patients. Previous research using deep learning to identify narrowed vessels has primarily been based on object detection, but this approach has several problems, such as the inability to detect multivessel narrowing, calculate the actual rate of narrowing, and determine the exact location of occurrence. Therefore, we believe that the determination of narrowing should return to the original method, namely, calculating the maximum and minimum diameters around the vessel. However, to automate this task, a preprocessing step for separating each vessel is needed, especially for the complex structure of the left coronary artery. We designed a deep learning model capable of analyzing an entire coronary angiography (CAG) image for the separation and tracking of vessels. This not only serves as a preprocessing step for calculating narrowing but also allows for the analysis of different vessel flow directions, providing doctors with comprehensive assessment indicators. © 2024 Copyright ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Smart cities and electrical and electronic waste management: a review of challenges and opportunities

Urbanization, Sustainability and Society

引用

Urbanization, Sustainability and Society 2025年第1期2卷 282-307页

作者： Deividson Sá Fernandes de Souza Simone Sehnem Patricia Guarnieri Thyago Celso Cavalcante Nepomuceno Fernando Henrique Taques Lucio Camara e Silva Post-Graduate Program in Production Engineering – CAA Federal University of Pernambuco Recife Brazil Department of Management Unoesc Chapecó Brazil and Department of Management Unisul Florianópolis Brazil Faculty of Economics Business Accounting and Public Policies Universidade de Brasília Brasília Brazil Technology Center Universidade Federal de Pernambuco Recife Brazil and Department of Computer Control and Management Engineering Antonio Ruberti University of Rome La Sapienza Rome Italy Post-Graduate Program in Production Engineering – CAA Federal University of Pernambuco Recife Brazil and Department of Applied Economics – ECONRES Research Group Universidad Autónoma de Madrid Madrid Spain

Purpose This paper aims to provide a comprehensive literature review on the practices and challenges in managing waste electrical and electronic equipment (WEEE) in smart cities. Design/methodology/approach A systematic literature review was conducted using the Methodi Ordinatio. Articles published between 2012 and 2022 were analyzed, totaling 149 references, of which 30 were included in the final review. Findings Emerging technologies such as the Internet of Things (IoT), big data and artificial intelligence (AI) are frequently highlighted as promising solutions for efficient e-waste management. Governance models and public policies are widely recognized as crucial for the successful implementation of WEEE management practices in smart cities. Originality/value This study underscores the role of advanced technologies, such as IoT and AI, in enhancing urban mobility and WEEE management. Key challenges include information security, privacy, interoperability, costs and sustainability. The findings reveal a convergence between smart cities and WEEE management, fostering the circular economy and the recovery of valuable materials.

关键词： Smart cities WEEE Systematic literature review Methodi Ordinatio

来源：评论

学校读者我要写书评

暂无评论

The Impact of Different Modes of Augmented Reality Information in Assisted Aircraft Cable Assembly 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Ariansyah, Dedy Xi, Khaizuo Erkoyuncu, John Ahmet Pardamean, Bens Bioinformatics and Data Science Research Centre Bina Nusantara University Jakarta11480 Indonesia School of Aerospace Transport and Manufacturing Cranfield University BedfordMK43 0AL United Kingdom Centre of Digital Engineering and Manufacturing School of Aerospace Transport and Manufacturing Cranfield University BedfordMK43 0AL United Kingdom Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Aircraft avionics systems are complicated systems which involves high number of components and complex cable assembly procedure. To deal with this challenge, Augmented Reality (AR) has been proposed to be an effective method to improve assembly efficiency and to reduce error rates. In this paper, the authors developed AR-based guidance cable assembly and compare the impact of different modes of AR information. The results show that although AR outperformed the paper document assembly guidance, the design of AR information has distinct influence on the successful completion of the cables assembly process. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Brazilian Climate Data Influence on Soybean Pricing by Using Long Short-Term Memory Models

SSRN

引用

SSRN 2024年

作者： Oliva, Jefferson Tales Martelli, Otávio Pigozzo de Castro Barbosa, Marco Antônio Dal Molin, Viviane Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical and Computer Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Department of Academic Informatics Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Graduate Program in Production and Systems Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil

This work uses machine learning to verify whether the Brazilian climate influences international soybean price prediction. For this, climatic data, dollar quotes, inflation, and annual soybean production were collected from different data sources. Then, the collected data were pre-processed and grouped by Brazilian state. Afterward, data from the five most productive Brazilian states are chosen, such as Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS). Afterward, predictive models are built using the long short-term memory (LSTM) method, which is applied in each chosen state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest values of root mean squared error (RMSE) and mean absolute error (MAE). Regarding predictors trained without climate data, the RS and PR obtained the lowest values of RMSE and MAE, respectively. After conducting statistical hypothesis tests, no significant difference was found among models, stating, with 95% certainty, that, in this study, the Brazilian climatic data did not influence the model performance for predicting soybean prices. On the other hand, one of the main contributions of work is conducting an unprecedented study about soybean price prediction using Brazilian climatic data. © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Towards Precision Cancer Therapy: Prottrans and Multi-Window Scanning Convolutional Neural Networks Transforming Protein-Peptide Interaction Predictions

SSRN

引用

SSRN 2024年

作者： Van Le, The Zi Zhan, Jun Yu Ou, Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

This study delves into the prediction of protein-peptide interactions using advanced machine learning techniques, comparing models such as sequence-based, standard CNNs, and traditional classifiers. Leveraging pre-trained language models and multi-view window scanning CNNs, our approach yields significant improvements, with ProtTrans standing out based on 2.1 billion protein sequences and 393 billion amino acids. The integrated model achieves an impressive AUC of 0.855 and 0.822 on Set_1 and Set_2 datasets, outperforming previous methods. Beyond this, we explore the application of this model in cancer therapy, particularly in identifying peptide interactions for selective targeting of cancer cells. The findings of this study contribute to bioinformatics, providing valuable insights for drug discovery and therapeutic development. © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deepepiil13: Deep Learning for Prediction of Il-13 Inducing Epitopes Using Pre-Trained Language Models and Multi-Window Convolutional Neural Networks

SSRN

引用

SSRN 2024年

作者： Chuang, Cheng-Che Ou, Yu-Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

Interleukin-13 (IL-13) is a key cytokine involved in allergic inflammation and the cytokine storm associated with severe COVID-19. Identifying antigenic epitopes capable of inducing IL-13 holds therapeutic potential for developing epitope-based vaccines and immunomodulatory treatments. However, conventional methods for epitope prediction are often inefficient and inaccurate. This study presents DeepEpiIL13, a novel deep learning framework that integrates pre-trained language models and multi-window convolutional neural networks (CNNs) to rapidly and accurately predict IL-13-inducing epitopes from protein sequences. The ProtTrans pre-trained language model was employed to generate high-dimensional embeddings that capture rich contextual information from protein sequences. These embeddings were then inputted into a multi-window CNN architecture, enabling the efficient exploration of local and global sequence patterns associated with IL-13 induction. The proposed approach was rigorously evaluated using benchmark datasets and an independent SARS-CoV-2 dataset. DeepEpiIL13 achieved superior performance compared to traditional methods, with an impressive Matthews correlation coefficient (MCC) of 0.52 and an area under the receiver operating characteristic curve (AUC) of 0.86 on the benchmark dataset. On the independent SARS-CoV-2 dataset, DeepEpiIL13 demonstrated remarkable robustness, attaining an MCC of 0.63 and an AUC of 0.92, highlighting its potential applicability in the context of COVID-19 research. This study introduces a powerful deep learning framework for accurate epitope prediction, offering new avenues for the development of epitope-based vaccines and immunotherapies targeting IL-13-mediated disorders. The successful identification of IL-13-inducing epitopes paves the way for novel therapeutic interventions against allergic diseases, inflammatory conditions, and potentially severe viral infections like COVID-19. © 2024, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

FDAM: Filter-Dedicated Approximate Multiplier Design for Real-Time CNN Acceleration

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Nguyen, Kihwan Kim Xuan Truong Jeon, Dongsuk Lee, Hyuk-Jae Korea Republic of program Department of Electrical Engineering Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Graduate School of Convergence Science and Technology Research Institute for Convergence Science Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Video super-resolution (VSR) is widely used in various high-definition applications, such as HDTVs and smartphones, requiring a dedicated upscaling technique for realtime full-HD generation. To reduce on-chip buffers for largesize output feature maps, a streaming VSR accelerator may employ an output stationary dataflow, leading to a large energy consumption caused by frequent filter switching. To mitigate this, we introduce a new filter-dedicated multiplier design for realtime VSR acceleration. We replace costly multipliers with adders, shifters, and multiplexers (MUXes), referred to as unified multiple constant multiplications (UMCM). The conventional UMCM, however, may incur considerable area/power overhead due to the unified topology constraint among different filter sets. To address this problem, we propose a new approximated MCM (AMCM) problem to relax the constraint and an approximate compatible graph synthesis (A-CGS) framework to efficiently solve AMCM by jointly searching for approximated filters and constructing a unified graph. Additionally, we suggest a lightweight finetuning method by freezing approximated filters and only finetuning biases, which can recover the original model’s accuracy within a few epochs. Experimental results with synthetic data demonstrate that AMCM reduces the area by up to 49.8%, 44.8%, and 40.3% when considering constant sets of 2, 4, and 8, respectively. Our designs with SR application achieve up to a 73.3% reduction in energy consumption. Experiments with the Set5 and Set14 datasets show that our model with bias correction achieves similar restoration performance compared to the eightbit models. © 1982-2012 IEEE.

关键词： Acceleration

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：