检索结果-内蒙古大学图书馆

Location embedding based pairwise distance learning for fine-grained diagnosis of urinary stones

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Qiangguo Huang, Jiapeng Sun, Changming Cui, Hui Xuan, Ping Su, Ran Wei, Leyi Wu, Yu-Jie Wu, Chia-An Duh, Henry B.L. Lu, Yueh-Hsun School of Software Northwestern Polytechnical University Shaanxi China Yangtze River Delta Research Institute of NPU Suzhou China CSIRO Data61 Sydney Australia Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Engineering Shantou University Guangdong China College of Intelligence and Computing Tianjin University Tianjin China School of Information Xiamen University Xiamen China AIDD Faculty of Applied Science Macao Polytechnic University China Department of Radiology Shuang-Ho Hospital Taipei Medical University Taipei Taiwan Master of Public Health Program National Yang Ming Chiao Tung University Taipei Taiwan School of Design The Hong Kong Polytechnic University Hong Kong Department of Radiology School of Medicine College of Medicine Taipei Medical University Taipei Taiwan

The precise diagnosis of urinary stones is crucial for devising effective treatment strategies. The diagnostic process, however, is often complicated by the low contrast between stones and surrounding tissues, as well as the variability in stone locations across different patients. To address this issue, we propose a novel location embedding based pairwise distance learning network (LEPD-Net) that leverages low-dose abdominal X-ray imaging combined with location information for the fine-grained diagnosis of urinary stones. LEPD-Net enhances the representation of stone-related features through context-aware region enhancement, incorporates critical location knowledge via stone location embedding, and achieves recognition of fine-grained objects with our innovative fine-grained pairwise distance learning. Additionally, we have established an in-house dataset on urinary tract stones to demonstrate the effectiveness of our proposed approach. Comprehensive experiments conducted on this dataset reveal that our framework significantly surpasses existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jiahao Yang, Liutao Wang, Fanwen Nan, Yang Wu, Weiwen Wang, Chengyan Shi, Kuangyu Aviles-Rivero, Angelica I. Schönlieb, Carola-Bibiane Zhang, Daoqiang Yang, Guang Department of Bioengineering and Imperial-X Imperial College London London United Kingdom National Heart and Lung Institute Imperial College London London United Kingdom Cardiovascular Research Centre Royal Brompton Hospital London United Kingdom College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Biomedical Engineering Shenzhen Campus of Sun Yat-sen University Guangdong China Human Phenome Institute Fudan University Shanghai China Department of Nuclear Medicine Inselspital University of Bern Bern Switzerland Department of Informatics Technical University of Munich Munich Germany Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom

Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism "masks out" redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

Predicting construction time and cost of tunnels using Markov chain model considering opinions of experts

学校读者我要写书评

暂无评论

Tunnelling and Underground Space technology 2021年 116卷 104109-104109页

作者： Mahmoodzadeh, Arsalan Mohammadi, Mokhtar Nariman Abdulhamid, Sazan Nejati, Hamid Reza M Gharrib Noori, Krikar Hashim Ibrahim, Hawkar Farid Hama Ali, Hunar Department of Civil Engineering University of Halabja HalabjaKurdistan Region Iraq Department of Information Technology College of Engineering and Computer Science Lebanese French University KR Iraq Civil Engineering Department College of Engineering Salahaddin University-Erbil ErbilKurdistan Region44002 Iraq Rock Mechanics Division School of Engineering Tarbiat Modares University Tehran Iran Petroleum Technology Department/Control and Operation Koya Technical Institute Erbil Polytechnic University ErbilKurdistan Region Iraq

The impact of uncertainty on decision-making is increasingly prioritized, especially for large geotechnical projects such as tunnels. In this article, the effects of geological/geotechnical uncertainties in tunnel construction time and costs were reduced. The forecasting of geological/geotechnical conditions in a tunnel project was based on the Markov chain. To accessing the more accurate input data of the Markov chain and estimate the construction time and cost required for tunnel construction, tunneling experts were interviewed through a questionnaire. Also, to assess the updating effect on obtained outcomes during the tunnel construction, the model was updated for one time. Finally, comparing the predicted results with the actual results, the effects of the interviewing and updating process were investigated. According to the results, the uncertainties in the predictions were found to be reduced significantly. Lastly, this research can provide guidance or reference for the evaluation and decision-making of complex systems engineering problems, and indicate a direction for further research of risk assessment and decision-making issues. © 2021 Elsevier Ltd

关键词： Decision making

Application of face recognition based on CNN in fatigue driving detection 2019

学校读者我要写书评

暂无评论

Application of face recognition based on CNN in fatigue driv...

2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019

作者： Xing, Jianju Fang, Guoxin Zhong, Juping Li, Jun Department of Computer Meizhou Vocational Technical School Meizhou China Guangdong Hengdian Information Technology Co. Ltd Guangzhou China College of Computer Science Guangdong Polytechnic Normal University Guangzhou China

ISBN: (纸本)9781450372022

Fatigue driving detection technology based on the external characteristics of the driver has made some progress in many aspects, but the method of driver facial feature extraction needs to be further improved, and the driver's eye location takes a long time, which affects the system recognition rate. The paper uses the fatigue driving detection method to achieve better results than the traditional detection method. The authors applied the convolutional neural network to face recognition, and improve the pupil localization algorithm, effectively overcoming the problem of large calculation of the original algorithm. According to the characteristics of driver's eyes with different width and height ratios in different states, a simple and feasible method of eye state judgment is realized, and the driver's fatigue state is judged by PERCLOS algorithm. The convolutional neural network model is applied to ORL face database, and the face recognition rate is 85%. The improved Hough transform method has a positioning accuracy of 92% for the driver's eyes, respectively, and the recognition rate for the driver's eye state is 83.9%. The authors designed the prototype system of fatigue driving detection based on face recognition which realizes the functions of driver's face feature detection, eye location, eye state judgment and fatigue judgment. The experimental results show that the recognition rate of fatigue is 87.5%. © 2019 Association for Computing Machinery.

关键词： Face recognition

Thresholding-based approach for segmentation of melanocytic skin lesion in dermoscopic images

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2024年第1期2991卷

作者： Dilovan Asaad Zebari Yusliza Yusoff Adel Al-Zebari Habibollah Haron Nechirvan Asaad Zebari Department of Computer Science College of Science Nawroz University Duhok 42001 Kurdistan Region Iraq Faculty of Computing Universiti Teknologi Malaysia Johor Bahru 81310 Johor Malaysia Department of Information Technology Technical College of Informatics Akre Duhok Polytechnic University Duhok 42001 Kurdistan Region Iraq Department of Computer Engineering Harran University 63300 Sanliurafa Turkey

The early and effective identification of skin lesion relies heavily on skin lesion segmentation. In contrast, automatic lesion segmentation in dermoscopic images is a difficult task due to several issues such as artifacts (hairs, gel bubbles, and ruler markers), indistinct boundaries, low contrast, and differences in sizes and lesion shapes. Nevertheless, this task can be accomplished. This work attempts to segment skin lesions from normal lesions based on the thresholding technique. The proposed work improved the segmented lesion by removing unwanted objects from an image using morphological operation. This work can effectively segment the lesion region from the normal skin. The segmentation accuracy provided by the system is 91.21%, and comparative analysis has been carried out with thresholding techniques. Based on the findings of the investigation, it has been determined that this work can segment lesions effectively.

关键词：

Elevator exhaustion time reduction by eliminating fake demands

学校读者我要写书评

暂无评论

Elevator exhaustion time reduction by eliminating fake deman...

1st International Multi-Disciplinary Conference Theme: Sustainable Development and Smart Planning, IMDC-SDSP 2020

作者： Hamad, Qusay Shihab Ali, Yasir Hassan Ahmed, Falah Y.H. Borhana, Abdoulhdi. A. Ahmed, M. Ali, Abdelrhman Salah M. Fadhil, Hilal A. Croock, Muayad Sadik Baghdad Iraq Technical Collage Mosul Mosul Iraq Management and Science University Shah Alam Selangor40100 Malaysia Department of Mechanical Engineering College of Engineering Universiti Tenaga Nasional BN – 03-33 Jalan IKRAM-UNITEN KajangSelangor Darul Ehsan43000 Malaysia Department of Mechanical Engineering College of Engineering Science & Technology Sebha University Sebha Libya Department of Mechanical Engineering School of Engineering Bahrain Polytechnic Isa Town33349 Bahrain Institute of Noise and Vibration Universiti Teknologi Malaysia Jalan Sultan Yahya Petra Kuala Lumpur54100 Malaysia Al-Farabi University College-Computer Engineering Dep University of Technology Baghdad Iraq Department of Computer Engineering University of Technology Baghdad Iraq

ISBN: (纸本)9781631902611

achieving the highest performance and efficiency of elevators have become an important area of research in the world of elevators. Because of the accelerating nature of the world, the interest in time and the rush to accomplish business became a major need for mankind. And that high buildings rely mainly on elevators, reducing the response time of the elevator is the most important research areas, so in this research, we propose an idea to provide the elevator to the person and not to false demand and this requires detection the presence of someone waiting for the elevator to the proposed system provides an algorithm based on the sensor PIR (passive infrared sensor). The results showed the size of profit achieved by the system and the profit is divided into profit times (reduce response time which leads to increase comfort for the rest of the people) and profit in reducing the energy consumed by the elevator. © 2020 EAI.

关键词： Elevators

PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Jiatai Han, Guoqiang Pan, Xipeng Chen, Hao Li, Danyi Jia, Xiping Shi, Zhenwei Wang, Zhizhen Cui, Yanfen Li, Haiming Liang, Changhong Liang, Li Liu, Zaiyi Han, Chu School of Computer Science and Engineering South China University of Technology Guangzhou China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Guangdong Guangzhou510080 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Guangdong Polytechnic Normal University School of Computer Science Guangzhou510665 China Department of Pathology Nanfang Hospital Basic Medical College Southern Medical University Guangdong Guangzhou510515 China Guangdong Province Key Laboratory of Molecular Tumor Pathology Guangdong Guangzhou510515 China Department of Radiology Fudan University Shanghai Cancer Center Shanghai200032 China Department of Oncology Shanghai Medical College Fudan University Shanghai200032 China Department of Radiology Shanxi Province Cancer Hospital Shanxi Taiyuan030013 China

Histopathological tissue classification is a fundamental task in pathomics cancer research. Precisely differentiating different tissue types is a benefit for the downstream researches, like cancer diagnosis, prognosis and etc. Existing works mostly leverage the popular classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we proposed a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to further improve the classification performance without a re-training burden. We mimic how pathologists observe pathology slides in different magnifications and construct an image pyramid for the input image in order to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equipped PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%), which greatly saves the computational time and annotation efforts. © 2021, CC BY.

关键词： Classification (of information)

Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jiahao Wu, Yinzhe Wang, Fanwen Fang, Yingying Nan, Yang Alkan, Cagan Abraham, Daniel Liao, Congyu Xu, Lei Gao, Zhifan Wu, Weiwen Zhu, Lei Chen, Zhaolin Lally, Peter Bangerter, Neal Setsompop, Kawin Guo, Yike Rueckert, Daniel Wang, Ge Yang, Guang Department of Bioengineering Faculty of Engineering Imperial College London Exhibition Road LondonSW7 2AZ United Kingdom Imperial-X and School of Biomedical Engineering & Imaging Sciences King's College London United Kingdom Department of Electrical Engineering Stanford University CA94305 United States Department of Radiology Beijing Anzhen Hospital Capital Medical University 2nd Anzhen Road Chaoyang District Beijing100029 China School of Biomedical Engineering Sun Yat-sen University Guangdong Guangzhou510006 China Hong Kong University of Science and Technology Hongkong Hong Kong Department of Data Science and AI Faculty of Information Technology Monash University Wellington Rd ClaytonVIC3800 Australia Electrical and Computer Engineering Department Boise State University ID83725 United States Department of Radiology Stanford University CA94305 United States Department of Computing Imperial College London South Kensington Campus LondonSW7 2AZ United Kingdom Technical University of Munich Munich80333 Germany New York United States

Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans. This review elucidates recent advances in MRI acceleration via data and physics-driven models, leveraging techniques from algorithm unrolling models, enhancement-based methods, and plug-and-play models to the emerging full spectrum of generative model-based methods. We also explore the synergistic integration of data models with physics-based insights, encompassing the advancements in multi-coil hardware accelerations like parallel imaging and simultaneous multi-slice imaging, and the optimization of sampling patterns. We then focus on domain-specific challenges and opportunities, including image redundancy exploitation, image integrity, evaluation metrics, data heterogeneity, and model generalization. This work also discusses potential solutions and future research directions, with an emphasis on the role of data harmonization and federated learning for further improving the general applicability and performance of these methods in MRI reconstruction. © 2024, CC BY.

关键词： Magnetic resonance imaging

Security enhancement of big data in cloud application using block-chain

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2587卷

作者： Avein Jabar Al-Asadi J. V. S. Arundathi Omdev Dahiya Abdul Wahab Hashmi Ankur Gupta Malik Bader Alazzam Dept. of Information Technology Technical College of Informatics TCI Sulaimani Polytechnic University Sulaymaniyah Iraq Dept. of Computer Science SR & BGNR Government Arts and Science Degree & PG College (Autonomous) Khammam Telangana India School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Advanced Manufacturing and Mechatronics Lab Mechanical Engineering Department Malaviya National Institute of Technology Jaipur India Dept. of Computer Science and Engineering Vaish College of Engineering Rohtak Haryana India Faculty of Computer Science and Informatics Amman Arab University Amman Jordan

Organizations are inundated on a daily basis with vast, difficult-to-manage volumes of structured and unstructured data, which is known as “big data.” Analysis of large amounts of data may provide useful information that can be used to improve decision-making and boost employee morale. This kind of data storage makes it almost hard to change, hack, or otherwise deceive. Every computer in a block-chain network has a copy of the block-transaction chain’s log, which is called a “block-chain.” In previous researches it has been observed that security of big data is a major issue. Block chain has been found suitable mechanism to deal with such issues. Block-chain has also been considered a service in the context of cloud computing, termed Block-chain as a Service (BaaS). By using virtual storage nodes, block-chain technology may create whole new cloud storage services that are very resistant to data tampering. The proposed research has focused on the enhancement of security of big data from SQL injection attack that is transferred over cloud application. Research is making use of block chain technology in order to resolve the issue of security. The major objective of research is to propose block chain based security model for big data that should be more secure and efficient in case of SQL injection attack. Research work has proposed modified algorithm enhances the security of big data in cloud application against SQL injection, cross script.

关键词：