检索结果-内蒙古大学图书馆

Character Recognition from Handwritten Image Using Convolutional Neural Networks 1

2nd International Symposium on Signal and Image Processing, ISSIP 2018

作者： Jana, Ranjan Bhattacharyya, Siddhartha Department of Information Technology RCC Institute of Information Technology KolkataWest Bengal India Department of Computer Application RCC Institute of Information Technology KolkataWest Bengal India Faculty of Electrical Engineering and Computer Science VSB Technical University of Ostrava Ostrava Czech Republic

ISBN: (数字)9789811367830

ISBN: (纸本)9789811367823

Character recognition from handwritten images is of great interest in the pattern recognition research community for their good application in many areas. To implement the system, it requires two steps, viz., feature extraction followed by character recognition based on any classification algorithm. Convolutional neural network (CNN) is an excellent feature extractor and classifier. The performance of a CNN for a particular application depends on the parameters used in the network. In this article, a CNN is implemented for the MNIST dataset with appropriate parameters for training and testing the system. The system provides accuracy up to 98.85%, which is better with respect to others. It also takes very low amount of time for training the system. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Correction to: LTE-NBP with holistic UWB-WBAN approach for the energy efficient biomedical application

引用

Multimedia Tools and applications 2023年第25期82卷 39813-39813页

作者： Kumar, Abhishek Rathore, Pramod Sing Dubey, Ashutosh Kumar Agrawal, Rashmi Sharma, Kanta Prasad Department of CSE Chandigarh University Mohali India Aryabhatta College of Engineering & Research Center Ajmer India Chitkara University School of Engineering and Technology Solan India Faculty of Computer Applications Manav Rachna International Institute of Research and Studies Faridabad India Computer Engineering and Application GLA University Mathura India

来源：评论

学校读者我要写书评

暂无评论

Response to Comment on (Novel two-dimensional porous graphitic carbon nitride C6N7 monolayer: A First-principle calculations [Appl. Phys. Lett. 2021, 119, 142102])

arXiv

引用

arXiv 2022年

作者： Bafekry, Asadollah Faraji, Mehrdad Fadlallah, Mohamed M. Sarsari, I. Abdolhosseini Jappor, Hamad R. Fazeli, Sara Ghergherehchi, Mitra Department of Radiation Application Shahid Beheshti University Tehran Iran Micro and Nanotechnology Graduate Program TOBB University of Economics and Technology Sogutozu Caddesi No 43 Sogutozu Ankara06560 Turkey Department of Physics Faculty of Science Benha University Benha13518 Egypt Department of Physics Isfahan University of Technology Isfahan84156-83111 Iran Department of Physics College of Education for Pure Sciences University of Babylon Hilla Iraq Department of Material Science and Engineering Sharif University of Technology PO Box 11155-9466 Tehran Iran Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Recently, reported a comments on the our paper [Appl. Phys. Lett. 119, 142102(2021)]. With our response, the APL journal rejected their non scientificcomments. There are some ambiguities about their claim: 1-They can check thephonon dispersion of their structure to see ZA out-of-plane mode. 2-They reportthe uniaxial stress-strain responses in Fig 2., which is unrelated to ourpaper. For a more helpful understanding of the mechanical properties of thenovel C6N7 monolayer, they can publish a paper. 3-They mentioned: Using the DFTmethod and with assuming a thickness of 3.35 A for the C6N7 monolayer based ongraphene thickness. Why did they choose this thickness while we know our C6N7monolayer is at without buckling? The distance of ZA out-of-plane movement ofions in C6N7 is different from Graphene. © 2022, CC BY.

关键词： Monolayers

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient Federated Semi-Supervised Learning Framework Via Pseudo Supervision Refinement Strategy for Lung Tumor Segmentation

SSRN

引用

SSRN 2024年

作者： Shi, Zhenwei Li, Weixing Pan, Xipeng Zhang, Zhen Wu, Guangyao Ye, Guanchao Wee, Leonard Dekker, Andre Han, Chu Shi, Lei Liu, Zaiyi Liu, Zhenbing School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Department of Radiology Huazhong University of Science and Technology Tongji Medical College Union Hospital Hubei Wuhan430021 China Clinical Data Science Faculty of Health Medicine Life Sciences Maastricht University Maastricht6229 ET Netherlands GROW School of Oncology and Reproduction Maastricht University Medical Centre+ Maastricht6229 ET Netherlands Guangdong Provincial People's Hospital China

Background and Objective: Accurate lung tumor segmentation is crucial for early clinical diagnosis and subsequent treatment planning for patients. Conducting centralized training to enhance model performance is impractical in real-world scenarios. Although federated learning offers a promising solution to this issue, effectively and efficiently utilizing unlabeled data remains a challenge. Methods: In this work, we propose a novel federated semi-supervised learning framework (FSSL) for complex and realistic scenario, which can efficiently leverage the limited labeled data and abundant unlabeled data from multiple clinical sites. Specifically, we initially conduct federated self-supervised pre-training at completely unlabeled sites using masked image modeling strategy. Subsequently, in the fine-tuning stage, we propose a pseudo supervision refinement strategy to leverage the unlabeled data from partially labeled sites, which not only reduces pseudo label noise but also helps stabilize the training process. Moreover, we propose a dynamic model aggregation strategy to assist the server in dynamically combining all local models during communication round. Results: We conducted extensive comparative and ablation experiments to validate the effectiveness of our proposed method. When only a limited amount of labeled data is available in the partially labeled sites, even without loading the pre-trained model, our approach consistently achieves the highest average Dice scores of 0.7383, 0.4768, and 0.6629 on the internal test sets, external unseen test sets, and pre-training test sets, respectively. Upon loading the pre-trained model, the scores on the three test sets further improve to 0.8205, 0.6185, and 0.7334, respectively. Conclusion: Our proposed method is capable of collaboratively training a global model with robust segmentation performance and generalizability by efficiently utilizing unlabeled data from different sites, even when only a limited amount of labeled da

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

applications of Raman Spectroscopy in Clinical Medicine

arXiv

引用

arXiv 2023年

作者： Qi, Yaping Chen, Esther Xinyi Hu, Dan Yang, Ying Wu, Zhenping Zheng, Ming Sadi, Mohammad A. Jiang, Yucheng Zhang, Kang Chen, Zi Chen, Yong P. Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Av. Wai Long China Tohoku University Sendai980-8577 Japan Faculty of Medicine Macau University of Science and Technology Av. Wai Long China State Key Laboratory of Information Photonics and Optical Communications School of Science Beijing University of Posts and Telecommunications Beijing100876 China School of Materials Science and Physics China University of Mining and Technology Xuzhou221116 China Department of Physics and Astronomy Elmore Family School of Electrical and Computer Engineering Birck Nanotechnology Center Purdue Quantum Science and Engineering Institute Purdue University West LafayetteIN47907 United States Jiangsu Key Laboratory of Micro and Nano Heat Fluid Flow Technology and Energy Application School of Physical Science and Technology Suzhou University of Science and Technology Jiangsu Suzhou215009 China Division of Thoracic Surgery Brigham and Women's Hospital Harvard Medical School 75 Francis Street BostonMA02115 United States Institute of Physics and Astronomy Villum Center for Hybrid Quantum Materials and Devices Aarhus University AarhusC 8000 Denmark

Raman spectroscopy provides spectral information related to the specific molecular structures of substances and has been well established as a powerful tool for studying biological tissues and diagnosing diseases. This article reviews recent advances in Raman spectroscopy and its applications in diagnosing various critical diseases, including cancers, infections, and neurodegenerative diseases, and in predicting surgical outcomes. These advances are explored through discussion of state-of-the-art forms of Raman spectroscopy, such as surface-enhanced Raman spectroscopy, resonance Raman spectroscopy, and tip-enhanced Raman spectroscopy employed in biomedical sciences. We discuss biomedical applications, including various aspects and methods of ex vivo and in vivo medical diagnosis, sample collection, data processing, and achievements in realizing the correlation between Raman spectra and biochemical information in certain diseases. Finally, we present the limitations of the current study and provide perspectives for future research. © 2023, CC BY.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient Federated Semi-Supervised Learning Framework Via Pseudo Supervision Refinement Strategy for Lung Tumor Segmentation

SSRN

引用

SSRN 2024年

作者： Shi, Zhenwei Li, Weixing Pan, Xipeng Zhang, Zhen Wu, Guangyao Ye, Guanchao Wee, Leonard Andre, Dekker Han, Chu Shi, Lei Liu, Zaiyi Liu, Zhenbing School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Department of Radiology Huazhong University of Science and Technology Tongji Medical College Union Hospital Hubei Wuhan430021 China Clinical Data Science Faculty of Health Medicine Life Sciences Maastricht University Maastricht6229 ET Netherlands GROW School of Oncology and Reproduction Maastricht University Medical Centre+ Maastricht6229 ET Netherlands Guangdong Provincial People's Hospital China

Accurate lung tumor segmentation is crucial for early clinical diagnosis and subsequent treatment planning for patients. Centralized model training faces privacy constraints, although federated learning offers a promising solution to this issue, effectively and efficiently utilizing unlabeled data remains a challenge. In this work, we propose a novel federated semi-supervised learning framework for complex and realistic scenario, which can efficiently leverage the limited labeled data and more homogeneous unlabeled data from multiple clinical sites for collaborative model training. Specifically, we initially conduct federated self-supervised pre-training at completely unlabeled sites using masked image modeling strategy. Subsequently, in the fine-tuning stage, we propose a pseudo supervision refinement strategy to leverage the unlabeled data from partially labeled sites, which not only reduces pseudo label noise but also helps stabilize the training process. Moreover, we propose a dynamic model aggregation strategy to assist the server in dynamically combining local models during each communication round to enhance the robustness and generalizability of the global model. Extensive comparative and ablation experiments confirm the efficacy of our proposed methodology, demonstrating improvement over recent state-of-the-art federated semi-supervised segmentation methods in scenarios with only a small amount of labeled data. This approach highlights the significant potential of multi-source and heterogeneous unlabeled data in facilitating the training of federated deep learning models and promotes clinical applications, assists radiologists in diagnosis and improves patient outcomes. The source code will be released on https://***/zhenweishi/FedPSR © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired Bat Optimization Algorithm for Automatic Clustering of Grayscale Images 1

引用

2nd International Symposium on Signal and Image Processing, ISSIP 2018

作者： Dey, Alokananda Bhattacharyya, Siddhartha Dey, Sandip Platos, Jan Snasel, Vaclav Department of Computer Application RCC Institute of Information Technology KolkataWest Bengal India Faculty of Electrical Engineering and Computer Science VSB Technical University of Ostrava Ostrava Czech Republic Department of Computer Science and Engineering OmDayal Group of Institutions Howrah India

ISBN: (数字)9789811367830

ISBN: (纸本)9789811367823

This paper introduces a quantum-inspired framework with the bat optimization algorithm for automatic clustering of image datasets. The aim of this work is to find out the optimal number of clusters from an image dataset on a run. A comparison has been produced between the quantum-inspired bat optimization algorithm and its classical counterpart. As a result, it is seen that the quantum-inspired version outperforms its classical counterpart. Computational experiments have been conducted on four Berkeley image datasets. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

International Conference on Innovative Computing and Communications 1

引用

丛书名： Lecture Notes in Networks and Systems

2019年

作者： Siddhartha Bhattacharyya Aboul Ella Hassanien Deepak Gupta Ashish Khanna Indrajit Pan

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Advanced artificial intelligence in heart rate and blood pressure monitoring for stress management

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 255-255页

作者： Lin, Qiang Li, Tongtong Shakeel, P. Mohamed Samuel, R. Dinesh Jackson School of Mathematics and Computer Science Northwest Minzu University LanzhouGansu China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University LanzhouGansu China Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University LanzhouGansu China Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka (UTeM) Durian Tunggal Malaysia Faculty of Technology Design and Environment Visual Artificial Intelligence Lab Oxford Brookes University Oxford UK

来源：评论

学校读者我要写书评

暂无评论

A Novel Strategy for Prediction of Cellular Cholesterol Signature Motif from G Protein-Coupled Receptors based on Rough Set and FCM Algorithm

A Novel Strategy for Prediction of Cellular Cholesterol Sign...

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： Rudra Kalyan Nayak Ramamani Tripathy V. Saravanan Siva Shankar S. Priti Das Dinesh Kumar Anguraj Faculty of Computer Science & Engineering Koneru Lakshmaiah Education Foundation (Deemed to be University) Green Fields Vaddeswaram Andhra Pradesh India Faculty of Master in Computer Application United School of Business Management Bhubaneswar Odisha India Faculty of Computer Science & Engineering KG Reddy College of Engineering and Technology Hyderabad Telengana India SCB Medical College and Hospital Cuttack Odisha India

ISBN: (数字)9781728148892

ISBN: (纸本)9781728148908

In present era, both soft computing and artificial intelligence techniques have been implemented as problem solver in bioinformatics, as conventional methods are not sufficient for handling huge amount of data. The principal focus of research in all pharmaceutical industries is on human proteins like G protein-coupled receptors (GPCRs), ATP-binding cassette (ABC) transporter etc. Membrane protein plays a significant role for every human being and all drug targets have been considered using this protein. In this manuscript, our focal point of research is on membrane protein that is GPCR family and cholesterol target process on the transmembrane region. Among all living organisms, GPCR acts as the largest superfamily and it includes numerous classes. From the last decades to till date GPCR sequence prediction and classification have been a challenging factor for all biomedicine scientists. GPCR family is also known as 7-pass transmembrane protein receptors. Every time membrane cholesterol has targets for the binding sites of membrane protein in both N terminus and C terminus of the cell membrane. For this purpose, a computational Rough-Fuzzy C-Means (FCM) based approach is implemented for prediction and this method helps to find out valid amino acid sequence which has biological relevance for clinical drug discovery.

关键词：

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：