检索结果-内蒙古大学图书馆

WU-Net++: A novel enhanced Weighted U-Net++ model for brain tumor detection and segmentation from multi-parametric magnetic resonance scans

引用

Multimedia Tools and Applications 2024年第28期83卷 71885-71908页

作者： Das, Suchismita Dubey, Rajni Jena, Biswajit Tsai, Lung-Wen Saxena, Sanjay Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar India School of Computer Engineering KIIT Deemed to Be University Bhubaneswar India Division of Cardiology Department of Internal Medicine Taipei Medical University Hospital Taipei111031 Taiwan Department of Computer Science and Engineering Institute of Technical Education and Research SOA Deemed to Be University Bhubaneswar India Department of Medicine Research Taipei Medical University Hospital Taipei111031 Taiwan Department of Information Technology Office Taipei Medical University Hospital Taipei11031 Taiwan Graduate Institute of Data Science College of Management Taipei Medical University Taipei11031 Taiwan

Brain tumor detection and segmentation from multi-parametric magnetic resonance (MR) scans are crucial for the prognosis and treatment planning of brain tumor patients in current clinical practice. With recent technological advancements, artificial intelligence-based deep learning has proven its indispensable image analysis capability in the most challenging tasks. This study proposes an automated WU-Net + + deep learning model for brain tumor segmentation using multiparametric structural MR scans obtained from the BraTS 2018 dataset. The model was validated through cross-dataset testing for intracranial hemorrhage (ICH) classification (ATLAS V2.1 dataset) and multi-organ segmentation from abdominal images of TCIA and BTCV datasets. The WU-Net++ model, a novel version of U-Net, was developed by adjusting its pooling operation as a weighted function of max and average pooling for brain tumor segmentation. The proposed model (WU-Net + +) achieved an F1 score of 0.94 ± 0.124, a dice score of 0.91 ± 0.132, and an AUC value of 0.915 for whole tumor segmentation. The model also achieved a high accuracy of 0.9949 ± 0.121 in ICH classification and dice scores of 0.912 ± 0.21, 0.844 ± 0.25, and 0.893 ± 0.17 for spleen, esophagus, and portal and splenic vein segmentation, respectively. Our study revealed that WU-Net + + has significant potential to improve the accuracy of segmentation and could be an effective method in the era of precision medicine. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Fatigue detection for public transport drivers under the normalization of epidemic prevention 21

Fatigue detection for public transport drivers under the nor...

引用

21st International Symposium on Distributed Computing and Applications for Business engineering and science, DCABES 2022

作者： Yu, Zhe Li, Lei Xu, Lijun Chen, Kansong School of Computer Science and Information Engineering Hubei University Wuhan430062 China

ISBN: (纸本)9781665454629

Several studies have shown that fatigue driving is one of the important causes of public transport safety accidents. With the outbreak of the COVID-19, the wearing of masks by public transport drivers presents new challenges for computer-based visual fatigue detection. In order to achieve the goal of accurately capturing the landmark information of the face even when the face is occluded by a large area, we adopt the DNN-based face detection method which has the highest accuracy and the best occlusion resistance. When the driver's face is blocked, the landmark information of the blocked face can be accurately detected by using our optimized face landmark detector. The accuracy rate of landmark recognition can reach 97.80%. On this basis, we calculate the driver's eye information, mouth information and the driver's head deflection angle information in real time as the judgment indicators of the degree of fatigue to comprehensively evaluate the driver's fatigue state. And use mathematical methods to fuse indicators in real time, classify the driver's fatigue state according to the value of the fusion indicators, and adopt different early warning methods for different levels of fatigue. In addition, in order to further improve the accuracy of the detection results and exclude the influence of other facial behaviors on our fatigue judgment indicators, we propose a kinetic energy calculation formula for facial organs based on the improved optical flow method. According to the different kinetic energy of facial organs in different states, which can accurately distinguish the different behaviors of the same facial organs such as blinking and closing eyes, yawning and speaking, which significantly increases the robustness and generalization ability of the detection program. The final experimental results show that the correct rate of the method for determining the degree of fatigue of the driver and passengers can reach 98.40% and 92.30% respectively when the driver does no

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Design and Architectural Implementation of Consortium Blockchain Based Framework for Open Banking Customer Consent and Data Handling

引用

SN computer science 2024年第2期5卷 271页

作者： Ghosh, Abir Mukhopadhyay, Indraneel Chakraborty, Subhalaxmi University of Engineering and Management West Bengal Kolkata India Amity School of Information Technology Amity University West Bengal Kolkata India Department of Computer Science University of Engineering and Management West Bengal Kolkata India

Presently blockchain-based open banking approaches have gained immense popularity in financial sector. In open banking, customer consent is mandatory by regulation before any customer data can be shared by bank with Third Party Providers (TPP) following strict security protocols. Recent study shows that customer remains unaware about private data leakages where data is shared by bank not adhering agreement between bank and customer. To mitigate such type of problem, an innovative consortium permissioned blockchain-based structure comprising banks, regulators, Third Party Providers, and customers is addressed in this proposed work. The implemented framework manages consent handling and data sharing under the gamut of blockchain security. Security analysis of the framework proves it to be secure from threats and performance evaluation of the framework is satisfactory with more than fifty customer data parameters and ten nodes of blockchain. This blockchain based framework traces data sharing non-compliances and reports it real-time basis to customer. Thus it enhances the transparency in the whole open banking data sharing process and boosts customer confidence to adopt open banking practices. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Bank Blockchain Consent management Customer trust Data violation Open banking Regulator Third party providers

来源：评论

学校读者我要写书评

暂无评论

PromptLink: Multi-template prompt learning with adversarial training for issue-commit link recovery 24

PromptLink: Multi-template prompt learning with adversarial ...

引用

18th ACM/IEEE International Symposium on Empirical Software engineering and Measurement, ESEM 2024

作者： Deng, Yang Wang, Bangchao Zou, Zhiyuan Ye, Luyao School of Computer Science and Artificial Intelligence Wuhan Textile University China Engineering Research Center of Hubei Province for Clothing Information Wuhan Textile University China

ISBN: (纸本)9798400710476

In recent years, Prompt Learning, based on pre-training, prompting, and prediction, has achieved significant success in natural language processing (NLP). The current issue-commit link recovery (ILR) method converts the ILR into a classification task using pre-trained language models (PLMs) and dedicated neural networks. However, due to inconsistencies between the ILR task and PLMs, these methods not fully leverage the semantic information in PLMs. To imitate the above problem, we make the first trial of the new paradigm to propose a Multi-template prompt learning method with adversarial training for issue-commit link recovery (PromptLink), which transforms the ILR task into a cloze task through the template. Specifically, a Multi-template PromptLink is designed to enhance the generalisation capability by integrating various templates and adopting adversarial training to mitigate the model overfitting. Experiments are conducted on six open-source projects and comprehensively evaluated across six commonly measures. The results show that PromptLink achieves an average F1 of 96.10%, Precision of 96.49%, Recall of 95.92%, MCC of 94.04%, AUC of 96.05%, and ACC of 98.15%, significantly outperforming existing state-of-the-art methods on all measures. Overall, PromptLink not only enhances performance and generalisation but also emerges new ideas and methods for future research. The source code of PromptLink is available at https://***/s/6130d42ff464c579cdec. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Model for Predicting Chronic Kidney Diseases Based on Medical Data Using Reinforcement Learning

引用

SN computer science 2024年第4期5卷 353页

作者： Nramban Kannan, Senthil Kumar Aseervatham, Joshi Moholkar, Kavita Palanimuthu, Mithun Marappan, Saranya Narendran, Muthusamy Sathar, Banu Sengan, Sudhakar Department of Computer Science & amp Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamil Nadu Chennai 600123 India Department of Computer Science and Business Systems Engineering JSPM’S Rajarshi Shahu College of Engineering Savitribai Phule Pune University Pune 411033 India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Tamil Nadu Chennai 600119 India Department of Information Technology Paavai Engineering College Tamil Nadu Namakkal 637018 India Department Information Technology KCG College of Technology Tamil Nadu Chennai 600097 India Department of Master of Computer Application T. J. Institute of Technology Chennai 600100 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627451 India

Kidney diseases (KD) are a global public health concern affecting millions. Early detection and prediction are crucial for effective treatment. Artificial intelligence (AI) techniques have been used in KDP to analyze past medical records, applying patients’ Electronic Medical Record (EHR) data. However, conventional statistical analysis methods conflict with fully comprehending the complexity of EHR data. AI algorithms have helped early KDP learn and identify complex data patterns. However, challenges include training heterogeneous historical data, protecting privacy and security, and developing monitoring system regulations. This study addresses the primary challenge of training heterogeneous datasets for real-world evaluation. Early detection and diagnosis of chronic kidney disease (CKD) is crucial for improved outcomes, reduced healthcare costs, and reliable treatment. Early treatments are crucial for CKD, as it often develops without apparent symptoms. Predictive models, particularly those using reinforcement learning (RL), can identify significant trends in complex healthcare information, which standard techniques may struggle with. The study makes KDP more accurate and reliable using RL methods on clinical data. This lets doctors find diseases earlier and treat them better by looking at static and changing health measurements. Machine learning (ML) algorithms can enhance the accuracy of AI systems over time, enhancing their effectiveness in detecting and diagnosing diseases. In the current investigation, the RL-ANN model is implemented for performing enforceable CKD by assessing the outcomes of multiple neural networks, which include FNN, RNN, and CNN, according to parameters such as accuracy, sensitivity, specificity, prediction error, prediction rate, and kidney failure rate (KFR). The recommended RL-ANN method has a lower failure rate of 70% based on the KFR data. Further, the proposed approach earned 95% in PR and 70% in analysis of errors. However, the RL

关键词： Alerting systems and diagnostic assistance Chronic kidney disease Machine learning Medical history RL-ANN

来源：评论

学校读者我要写书评

暂无评论

引用

7th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2022

作者： Yang, Hui Yu, Wanjun Shanghai Institute of Technology School of Computer Science and Information Engineering ShangHai China

ISBN: (数字)9781665482295

ISBN: (纸本)9781665482295

The user and item features extracted by the traditional recommendation system are relatively simple, and at the same time, the mining of the internal relationship between users and products is not sufficient, resulting in unsatisfactory recommendation effect. Based on the research of the existing recommendation system, aiming at the problem of insufficient user and item information extraction, this paper realizes the screening and classification of items and users through algorithms, and performs shallow semantic information and deep semantic information on the information of users and items. Divide and process them separately to achieve the purpose of fully extracting shallow semantic features and deep semantic features, and recommend different items to different users according to users' ratings and interests. A recommendation method based on deep noise reduction autoencoder proposed in this paper firstly needs to divide the information of users and items into shallow semantic information and deep semantic information, and process them separately. The autoencoders are trained separately to realize the recommendation of different items for users with different interests. Through the above methods, this paper mainly improves the recommendation accuracy of the current recommendation system and reduces the adverse effects of matrix sparsity. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Temporal Refinement Graph Convolutional Network for Skeleton-Based Action Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1586-1598页

作者： Zhuang, Tianming Qin, Zhen Ding, Yi Deng, Fuhu Chen, Leduo Qin, Zhiguang Raymond Choo, Kim-Kwang University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province Chengdu Sichuan610054 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu Sichuan610054 China School of Advanced Technology Suzhou Jiangsu215123 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

Human skeleton data, which has served in the aspect of human activity recognition, ought to be the most representative biometric characteristics due to its intuitivity and visuality. The state-of-the-art approaches mainly focus on improving modeling spatial correlations within graph topologies. However, the interframes motional representations are also of vital importance, and we argue that they are worth paying attention to and exploring. Therefore, a temporal refinement module with contrastive learning mechanism is proposed, fuzing as a complementary to the conventional spatial graph convolution layer. In addition, in order to further exploiting the interframe variances and generalizing graph convolutional network (GCN) operation to temporal dimension, a temporal-correlation matrix is introduced to effectively capture dynamic dependencies within frame-pairs, enhancing semantic feature representation. Moreover, since GCN is a typical local operator which lacks of capability to fully model the long-term relations along spatial and temporal variation, to move beyond the limitation, a spatial-temporal cascaded aggregation (STCA) module is designed to enlarge the receptive filter scale. The overall recognition framework consists of three above novelties, which is capable of achieving remarkable performance by evaluating on benchmark datasets (i.e., NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, and Kinetics Skeleton 400). Extensive experiments demonstrate the effectiveness of the proposed framework, e.g., performing recognition accuracy rate of 90.9% and 96.8% on NTU RGB+D 60, 87.9% and 88.9% on NTU RGB+D 120. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Post-quantum Dropout-Resilient Aggregation for Federated Learning via Lattice-Based PRF 1st

Post-quantum Dropout-Resilient Aggregation for Federated Le...

引用

1st International Conference on Artificial Intelligence Security and Privacy, AIS and P 2023

作者： Zuo, Ruozhou Tian, Haibo Zhang, Fangguo School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9789819997848

Machine learning has greatly improved the convenience of modern life. As the deployment scale of machine learning grows larger, the corresponding data scale also increases, leading to a large number of small and medium-sized organizations wishing to use their respective data to train models together, even though this may bring risks of violating data privacy regulations and privacy leakage. To meet this demand, federated learning was proposed, which can satisfy the needs of various organizations to expand the training data scale without directly sharing data, while avoiding violations of data privacy regulations and privacy leakage. General federated learning usually allows clients to train local models independently, and then aggregate them on a central server to build a global model in a privacy-preserving manner. There are various ways to protect privacy, such as homomorphic encryption, differential privacy, etc. Among these methods, one type of federated learning scheme is based on homomorphic pseudorandom functions. This type of scheme is relatively simple to construct, has a smaller communication scale, is more resilient to disconnections, and has high scalability. However, the security aggregation with cryptographic primitives based on classic assumptions such as DDH cannot resist quantum attacks, and since the protected gradient vectors are usually tens of thousands of dimensions, obtaining the aggregation results requires solving tens of thousands of discrete logarithms, which leads to some loss of efficiency. In this paper, we proposed a secure aggregation scheme based on HPRG over lattice, which has practical efficiency and resilience to dropout and can resist quantum attacks due to the hardness of the RLWE assumption. Moreover, our scheme only requires polynomial multiplication and addition (usually treated as vectors in implements), thus significantly improving computational efficiency. © The Author(s), under exclusive license to Springer Nature Singapo

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Energy Optimization Strategy for the Multi-Energy Microgrid with the Carbon Trading under the Step Price 7

An Intelligent Energy Optimization Strategy for the Multi-En...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Liu, Weirong Tang, Nvzhi Rong, Jieqi He, Hongjiang Chen, Bin School of Computer Science and Engineering Central South University Changsha China School of Electronic Information Central South University Changsha China School of Automation Central South University Changsha China College of Automotive and Mechanical Engineering Changsha University of Science and Technology Changsha China

ISBN: (纸本)9798350359558

It is promising to reduce carbon emission by incor-porating carbon trading into the multi-energy microgrid which can exploit the complementary advantages among various energies. Currently, most carbon trading uses the fixed price, limiting the prohibition effect on carbon emission. Introducing the step price can bring the indifferentiable characteristic of the cost function, which is difficult to solve. To address the issue, in this paper, an energy optimization strategy is proposed for the multi-energy microgrid based on the intelligent meta-heuristic algorithm. Firstly, the models of the electric, heat, gas devices, and energy converters are constructed. Then the energy optimization problem for multiple energies with the carbon trading under step price is formulated. Afterward, an improved grey wolf optimization algorithm with fast convergence is utilized to reduce the operation cost under the lowest carbon emission. The Simulations conducted on the real-world data verify the effectiveness of the proposed strategy. © 2024 IEEE.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild 38

Locating What You Need: Towards Adapting Diffusion Models to...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 2024 Neural information processing systems foundation. All rights reserved.

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：