检索结果-内蒙古大学图书馆

Renal calculus composition assessment from radiographic images using machine learning technique

Research on Biomedical engineering 2025年第2期41卷

作者： K, Prakashini Pal, Basudha Thalengala, Ananthakrishna H, Anitha Chawla, Arun Department of Radio Diagnosis and Imaging Kasturba Medical College Manipal Academy of Higher Education Manipal Karnataka Udupi576104 India Karnataka State Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka Udupi576104 India Department of Urology and Renal Transplant Kasturba Medical College Manipal Academy of Higher Education Manipal Karnataka Udupi576104 India

Purpose: In urolithiasis, hard deposits of minerals or salts are formed in the kidneys or urinary tract which may be of pure or mixed composition. It is important to know the composition of stone(s) to decide the kind of treatment and help in post-operative care to reduce re-occurrence. This study has a novel aim of selecting the best model for predicting the extent of each chemical present in the stone(s) of a patient from radiographic images (in vivo analysis). Methods: For the stone composition analysis from images, five supervised learning models were used for multi-class-multi-output classification or multi-task classification. Multi-task classification was best suited in this case as there were seven target chemicals—calcium, magnesium, uric acid, ammonia, oxalate, phosphate, and carbonate;each of which was classified as absent, low, moderate, or high simultaneously. The metrics for such classifications are not defined in general because multiple criteria cause anomalies. Results: In the present work, the F1 score with which each model classifies each chemical was computed, and a multi-criteria decision-making algorithm called Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was used to find the best model. The k-nearest neighbour classifier has given the best TOPSIS performance score of 0.9034. Conclusion: There are five different machine learning (ML) models considered in the study and were evaluated on their F1 score for each target chemical. Each of the ML classifiers was multi-class multi-output (MCMO) model, and the ultimate choice was made based on the outcome of the TOPSIS algorithm. The KNN model has found to outperform the others. This study has significance in identification and classification of stone composition from DECT images of renal calculus. © The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering 2025.

关键词： Multi-criteria decision-making Multi-task classification Supervised machine learning TOPSIS Urolithiasis

来源：评论

学校读者我要写书评

暂无评论

Achieving Personalized Federated Learning with Sparse Local Models

arXiv

引用

arXiv 2022年

作者： Huang, Tiansheng Liu, Shiwei Shen, Li He, Fengxiang Lin, Weiwei Tao, Dacheng The Department of Computer Science and Engineering South China University of Technology Guangzhou China Eindhoven University of Technology Netherlands Netherlands JD Explore Academy Beijing China

Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. However, PFL is far from its maturity, because existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. In this work, we propose federated learning with personalized sparse mask (FedSpa), a novel PFL scheme that employs personalized sparse masks to customize sparse local models on the edge. Instead of training an intact (or dense) PFL model, FedSpa only maintains a fixed number of active parameters throughout training (aka sparse-to-sparse training), which enables users' models to achieve personalization with cheap communication, computation, and memory cost. We theoretically show that the iterates obtained by FedSpa converge to the local minimizer of the formulated SPFL problem at the rate of O(√1/T ). Comprehensive experiments demonstrate that FedSpa significantly saves communication and computation costs, while simultaneously achieves higher model accuracy and faster convergence speed against several state-of-the-art PFL methods. Copyright © 2022, 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

Staging of clear cell renal cell carcinoma using random forest and support vector machine 4

Staging of clear cell renal cell carcinoma using random fore...

引用

4th International Conference on Advanced technology and Applied sciences, ICaTAS 2019

作者： Talaat, D. Zada, F. Kadry, R. Computer Department Faculty of Engineering and Technology Arab Academy for Science and Technology Abou Keer Alexandria Egypt

Kidney cancer is one of the deadliest types of cancer affecting the human body. It's regarded as the seventh most common type of cancer affecting men and the ninth affecting women. Early diagnosis of kidney cancer can improve the survival rates for many patients. Clear cell renal cell carcinoma (ccRCC) accounts for 90% of renal cancers. Although the exact cause of the kidney cancer is still unknown, early diagnosis can help patients get the proper treatment at the proper time. In this paper, a novel semi-automated model is proposed for early detection and staging of clear cell renal cell carcinoma. The proposed model consists of three phases: segmentation, feature extraction, and classification. The first phase is image segmentation phase where images were masked to segment the kidney lobes. Then the masked images were fed into watershed algorithm to extract tumor from the kidney. The second phase is feature extraction phase where gray level co-occurrence matrix (GLCM) method was integrated with normal statistical method to extract the feature vectors from the segmented images. The last phase is the classification phase where the resulted feature vectors were introduced to random forest (RF) and support vector machine (SVM) classifiers. Experiments have been carried out to validate the effectiveness of the proposed model using TCGA-KRIC dataset which contains 228 CT scans of ccRCC patients where 150 scans were used for learning and 78 for validation. The proposed model showed an outstanding improvement of 15.12% for accuracy from the previous work. © Published under licence by IOP Publishing Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Advancements in Medical Imaging: Detecting Kidney Stones in CT Scans using a ELM-I AdaBoost-RT Model

Advancements in Medical Imaging: Detecting Kidney Stones in ...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Sudarsan, M.S.V.D. Sapra, Puneet Suganthi, D. Jeevitha, S. Ankit, R. Chauhan, Amit Department of Mathematics V.R. Siddhartha Engineering Vijayawada India Rayat Bahra University Department of Cse Punjab Mohali India Saveetha University Saveetha College of Arts and Sciences Department of Computational Intelligence Chennai India Kalasalingam Academy of Research and Education Department of Computer Science and Information Technology Krishnankoil India Lovely Professional University School of Physical Education Punjab Phagwara India Christ University Department of Life Sciences Bengaluru India

ISBN: (纸本)9798350360660

Kidney stones have been more common in recent years, leading many to believe that the condition is common. The condition's strong relationship with other terrible diseases makes it a major threat to public health. The development of instruments and procedures that facilitate the diagnosis and treatment of this ailment has the potential to enhance the effectiveness and efficiency of health care. Preprocessing, feature extraction, level set segmentation, and model training are the four steps that make up this approach. Part of the preprocessing includes eliminating the skeletal skeleton and soft-organs. Level set segmentation is commonly used for object tracking, motion segmentation, and image segmentation. An extremely effective feature extraction method called Gray level co-occurrence matrix (GLCM) is suggested for extracting the necessary characteristics from the segmented image. That ELM-I-AdaBoost-RT was used all during training. This cutting-edge technique achieves an average accuracy of 95.83%, surpassing both ELM and AdaBoost. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Suppress content shift: better diffusion features via off-the-shelf generation techniques 24

Suppress content shift: better diffusion features via off-th...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Zhiyong Yang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://***/Darkbblue/diffusion-content-shift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preliminary comparisons among the Gaofen-1 wide field of view sensors 29

Preliminary comparisons among the Gaofen-1 wide field of vie...

引用

29th International Conference on Geoinformatics, Geoinformatics 2022

作者： Chen, Feng Zhang, Wenhao Hu, Jing Zhao, Baisong Wang, Chenxing Song, Yuejun Jiangxi Academy of Water Science and Engineering Jiangxi Provincial Key Laboratory of Soil Erosion and Prevention Nanchang China College of Computer and Information Engineering Xiamen University of Technology Xiamen China Shandong Tongsheng Surveying and Mapping Geographic Information Co. Ltd Zibo China Research Center for Eco-Environmental Sciences State Key Laboratory of Urban and Regional Ecology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350309881

ISBN: (纸本)9798350309881

The wide field of view (WFV) sensor as one of the imaging systems onboard Gaofen-l (GF-1) satellite acquires multispectral imagery with a spatial resolution of 16 m. The medium spatial resolution as well as high temporal resolution and wide swath makes the GF-1 WFV multispectral imagery more suitable for monitoring over large-scale surface. Currently, investigations mainly focusing on processing and application of the GF-1 WFV data have been widely reported. There are four GF-1 WFV sensors (namely including WFV1, WFV2, WFV3, and WFV4) designed with similar characterization, but having discrepancies among them. However, comparability among the four WFV sensors has not been discussed fully. In this paper, preliminary findings on comparison of the GF-1 WFV sensors are presented. Relatively significant discrepancies among the GF-1 WFV sensors are observed in spectral response function and the derived indicators (i.e. channel effective wavelength and the percentage of overlap) for the red and green channels, whereas the differences are less obvious for the blue channel. The between-sensor differences generally vary with the channel, which are also associated with the sensors in comparison. Overall, the WFV1 and the WFV2 show comparability in all channels (i.e. the blue, green, red, and near-infrared channels). Furthermore, the findings based on a collection of synthesized GF-1 WFV data suggest that a general linear model may not be sufficient to improve between-sensor comparability for all individual land use/cover classes, although it is effective to reduce the overall between-sensor difference. Potential uncertainty in channel reflectance introduced through transformation model should be taken into account for the applications followed by. © 2022 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Monitoring Urban Expansion of Huizhou from 2000 to 2020 Using the Google Earth Engine

Dynamic Monitoring Urban Expansion of Huizhou from 2000 to 2...

引用

2021 IEEE International Conference on Space-Air-Ground Computing, SAGC 2021

作者： Peng, Shuhong Qian, Jing Wang, Zhen Liu, Haibin Wei, Shujie Sun, Jiayu Wu, Zhipan School of Computer Science and Engineering Huizhou University Huizhou China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Management University of Montpellier Montpellier France

ISBN: (纸本)9781665400114

Huizhou is located in the Pearl River Delta of Guangdong Province, bordering Shenzhen and Hong Kong. It is one of the rapidly developing cities in the Guangdong-Hong Kong-Macao Greater Bay Area. With the accelerating process of urbanization, the land use change of built-up areas in Huizhou is also increasing. This paper uses Google Earth engine (GEE) cloud computing platform, selects multiple periods Landsat remote sensing data, uses CART data classifier to discriminate urban land, vegetation land and water body, and implements dynamic monitoring of Huizhou urban expansion from 2000 to 2020. The results show that the urban area changes to an increasing trend from 2000 to 2020, with a total increased area of 350.13 km2. Based on the extracted urban built-up area of Huizhou in 2000, 2005, 2010, 2015 and 2020, the growth rates of urban area in recent years are: 10.63% in 2000-2005, 3.84% in 2005-2010, 5.82% in 2010-2015 and 8.24%in 2015-2020, respectively. This study will provide a data basis for the analysis of urban future planning in Huizhou. © 2021 IEEE.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Pseudo complementary measurement for traditional single-pixel cameras

引用

Chinese Physics B 2020年第11期29卷 315-322页

作者： Qian Dong Xu-Ri Yao Xin Liu Bing Liu Guang-Jie Zhai State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China Key Laboratory of Electronics and Information Technology for Space Systems National Space Science CenterChinese Academy of SciencesBeijing 100190China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

A traditional single-pixel camera needs a large number of measurements to reconstruct the object with compressive sensing *** with the 1/0 matrices in classical measurement,the 1/-1 matrices in the complementary measurement has better property for reconstruction computation and returns better reconstruction ***,each row of the 1/-1 matrices needs two measurements with the traditional single-pixel camera which results into double measurements compared with the 1/0 *** this paper,we consider the pseudo complementary measurement which only takes the same amount of measurements with the row number of some properly designed 1/0 matrix to compute the total luminous flux of the objective and derives the measurement data of the corresponding 1/-1 matrix in a mathematical *** numerical simulation and experimental result show that the pseudo complementary measurement is an efficient tool for the traditional single-pixel camera imaging under low measurement rate,which can combine the advantages of the classical and complementary measurements and significantly improve the peak signal-to-noise ratio.

关键词： computational imaging single-pixel camera

来源：评论

学校读者我要写书评

暂无评论

Simulation of Industrial Economic Development Model Based on Fuzzy Clustering Algorithm

Simulation of Industrial Economic Development Model Based on...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： N. Prakash Samson Isaac. J A. Arun Kumar Ramaganesh M B. Prasad P. Uthayakumar Department of Electrical and Electronics Engineering Kumaraguru College of Technology Saravanampatti Coimbatore Department of Electronics and Communication Engineering Sona College of Technology Department of Computer Science & Engineering Autonomous Institute Marri Laxman Reddy Institute of Technology and Management Dundigal Hyderabad Telangana Department of Mechanical Engineering Kalasalingam Academy of Research and Education Department of Mathematics PSNA College of Engineering and Technology (Autonomous) Dindigul Tamilnadu India

As human society enters the era of the knowledge economy, the "industrial economic development of Fuzzy Clustering Algorithm (FCM), which promotes the development of science and technology and social progress, has undergone profound changes in both connotation and form, and has gradually become an important part of the national development strategy." In order to investigate the effects of various policy alternatives on the energy industry, a system simulation model of the expansion of the energy industry from the position of a low-carbon economy is created based on DPSIR theory from the perspectives of energy, economy, environment, policy, and society. There are other clustering algorithms available today, but the fuzzy c-means clustering algorithm is the most widely used. Many improved techniques are presented based on this algorithm to produce a better clustering effect. The clustering effectiveness index must be evaluated for the effect after clustering. Clustering analysis is a critical component of unsupervised pattern recognition. Fuzzy clustering has become the industry standard for clustering analysis because it establishes the ambiguous description of the sample for the category and can more precisely reflect reality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation

arXiv

引用

arXiv 2024年

作者： Tao, Wei Zhou, Yucheng Wang, Yanlin Zhang, Hongyu Wang, Haofen Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Software Engineering Sun Yat-sen University Guangdong Zhuhai519082 China School of Big Data and Software Engineering Chongqing University Chongqing China College of Design and Innovation Tongji University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 220 Handan Road Shanghai200433 China

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. © 2024, CC BY.

关键词： Sampling

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：