检索结果-内蒙古大学图书馆

Combining permuted language model and adversarial training for Chinese machine reading comprehension

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10059-10073页

作者： Liu, Jianping Chu, Xintao Wang, Jian Wang, Meng Wang, Yingfei College of Computer Science and Engineering North Minzu University Yinchuan China The Key Laboratory of Images Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan China Agricultural Information Institute Chinese Academy of Agricultural Sciences Beijing China

Due to the polysemy and complexity of the Chinese language, Chinese machine reading comprehension has always been a challenging task. To improve the semantic understanding and robustness of Chinese machine reading comprehension models, we propose a model that utilizes adversarial training algorithms and Permuted Language Model (PERT). Firstly, we employ the PERT pre-training model to embed paragraphs and questions into vector space to obtain corresponding sequential representations. Secondly, we use a multi-head self-attention mechanism to extract key textual information from the sequence and employ a Bi-GRU network to semantically fuse the output feature vectors, aiming to learn deep semantic representations in the text. Finally, we introduce perturbations into the model training process. We achieve this by utilizing adversarial training algorithms such as Fast Gradient Method (FGM) and Projected Gradient Descent (PGD). These algorithms generate adversarial samples to enhance the model’s robustness and stability when facing diverse inputs. We conducted comparative experiments on the publicly available Chinese reading comprehension datasets CMRC2018 and DRCD. The experimental results show that our proposed model has achieved significant improvements in both EM and F1-Score compared to the baseline model. To validate the model’s generalization and robustness, we utilized ChatGPT to construct a scientific dataset that includes a large number of domain-specific terms, sentences with mixed Chinese and English, and complex comprehension tasks. Our model also performed remarkably well on the self-built dataset. In conclusion, the proposed model not only effectively enhances the understanding of semantic information in Chinese text but also demonstrates a certain level of generalization capability. © 2024 – IOS Press. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Equivalence Principle and Machian origin of extended gravity

arXiv

引用

arXiv 2024年

作者： Benedetto, Elmo Corda, Christian Licata, Ignazio Department of Computer Science University of Salerno Via Giovanni Paolo II 132 Sa Fisciano84084 Italy SUNY Polytechnic Institute UticaNY13502 United States Palermo Italy

Chae’s analyses on GAIA observations of wide binary stars have fortified the paradigm of extended gravity with particular attention to MOND-like theories. We recall that, starting from the origin of Einstein’s general relativity, the request of Mach on the structure of the theory has been the core of the foundational debate. This issue is strictly connected with the nature of the mass-energy equivalence. This was exactly the key point that Einstein used to derive the same general relativity. On the other hand, the current requirements of particle physics and the open questions within extended gravity theories, which have recently been further strengthened by analyses of GAIA observations, request a better understanding of the Equivalence Principle. By considering a direct coupling between the Ricci curvature scalar and the matter Lagrangian a non geodesic ratio between the inertial and the gravitational mass can be fixed and MOND-like theories are retrieved at low energies. Copyright © 2024, The Authors. All rights reserved.

关键词： Relativity

来源：评论

学校读者我要写书评

暂无评论

CLASSIFICATION OF LUNG CANCER SUBTYPES ON CT IMAGES WITH SYNTHETIC PATHOLOGICAL PRIORS

arXiv

引用

arXiv 2023年

作者： Zhu, Wentao Jin, Yuan Ma, Gege Chen, Geng Egger, Jan Zhang, Shaoting Metaxas, Dimitris N. Research Center for Healthcare Data Science Zhejiang Lab Hangzhou311121 China School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Shanghai Artificial Intelligence Laboratory Shanghai200120 China Department of Computer Science Rutgers University PiscatawayNJ08854 United States

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case’s CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score. © 2023, CC0.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Morocco's COVID-19 instance as a potential epidemiological scenario

Morocco's COVID-19 instance as a potential epidemiological s...

引用

Innovative Research in Applied science, Engineering and Technology (IRASET),Conference on

作者： El Mehdi Chouit Mohamed Rachdi Mostafa Bellafkih Brahim Raouyane Department of Mathematics and Computer Science RAISS Laboratory National Institute of Posts and Telecommunications (INPT) Rabat Morocco TIM Laboratory Faculty of sciences Ben M'sik ENSAD Hassan II University Casablanca Morocco Department of Mathematics and Computer Science Faculty of Sciences Ain Chock University Hassan II Casablanca Morocco

Machine learning is widely used in all industries. In order to speed up decision-making on the most likely course of action, machine learning have shown their effectiveness in analyzing perioperative effects. In several technological sectors, ML models have been utilized for a while to specify and rank dangerous threat variables. To handle forecasting problems, several different prediction approaches are regularly used. The work shows how ML models can forecast the frequency of COVID-19 instances in the future, which is now considered to be a serious threat to civilisation. In this study, we carried out a comparison analysis of two widely used machine learning models: SVM and linear regression. Each model projects three variables: the cumulative count of confirmed cases, the cumulative count of fatalities, and the cumulative count of recoveries over the next 30 days. The study's conclusions demonstrate that applying these tactics to the current COVID-19 pandemic scenario is a viable choice. To boost accuracy, we used two ML models. The results of the experiment indicate that when it comes to COVID-19 prediction, Linear Regression yields the best results, while SVM yields the worst.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing Deep Reinforcement Learning for Advanced Pattern Extraction in Big Data Analytics and Ontology Systems 2

Utilizing Deep Reinforcement Learning for Advanced Pattern E...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Karthik, A. Asha, V. Bhardwaj, Garima Nijhawan, Ginni Khan, Irfan Bader, Nabaa M. Institute of Aeronautical Engineering Dundigal Hyderabad India New Horizon College of Engineering Department of Computer Applications Bangalore India Amity University Amity Business School Uttar Pradesh Greater Noida India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Uttar PradeshKnowledge Park II Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350384277

The development of big data has provided unparalleled prospects for uncovering novel patterns and insights in several domains. However, the complex structure and volume of data need the use of advanced methods to successfully extract significant information. This research presents a new framework that utilizes Deep Reinforcement Learning (DRL) to improve pattern extraction in big data analytics and ontology systems. DRL, which combines deep learning with reinforcement learning, excels at dealing with data spaces that have a large number of dimensions. This makes it a good option for effectively exploring and analyzing complex datasets. The suggested framework effectively utilizes sophisticated ontological structures to integrate DRL, enabling it to accurately identify and extract complex patterns that may be overlooked by standard approaches. The study showcases the effectiveness of the framework by conducting extensive tests on diverse big datasets, demonstrating that the DRL-enhanced system surpasses previous methods in terms of both accuracy and speed. The study also addresses architectural design, the choice of reinforcement learning methods, and the found implementation issues. Moreover, it delves into the consequences of these discoveries for subsequent investigations and real-world implementations, emphasizing the capacity of DRL to transform the identification of patterns in large-scale data settings. This work enhances the area of big data analytics by offering a strong technique for extracting complex patterns, which in turn enables better informed decision-making and discovery in scientific and commercial sectors. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Smart Thermal Management and Control of Interleaved Boost Converters in High-Power Photovoltaic Systems

Smart Thermal Management and Control of Interleaved Boost Co...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Dasari, Kavitha Asha, V. Kansal, Lavish Praveen Parashar, Ashish Kumar Alwan, Adil Abbas Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Master of Computer Applications Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India Lloyd Institute of Management and Technology Plot No.-11 Knowledge Park-II Uttar Pradesh Greater Noida201306 India College of Engineering Technology National University of Science and Technology Dhi Qar Iraq

ISBN: (纸本)9798350357769

In the realm of high-power photovoltaic (PV) systems, ensuring efficient and reliable performance demands precise thermal management. This study delves into the intricacies of thermal management and control strategies for interleaved boost converters (IBC), pivotal components in these systems. Interleaved topology, though recognized for its capability to reduce ripple currents and enhance efficiency, presents unique thermal challenges due to uneven current distribution among the parallel converters. This research introduces a smart thermal control methodology that amalgamates real-time temperature monitoring with adaptive control strategies, ensuring optimal thermal performance and preventing hotspot formation. Employing a combination of advanced sensors and sophisticated algorithms, the proposed system autonomously adapts to varying solar irradiances and ambient conditions, thereby ensuring consistent thermal stability. Experimental results demonstrate a significant reduction in temperature deviations among parallel converters and an overall enhancement in system reliability and efficiency. The findings from this research set the groundwork for future designs of PV systems, ensuring their sustainable and efficient operation under diverse conditions. © 2023 IEEE.

关键词： Adaptive Control Strategies Hotspot Prevention. Top of Form Interleaved Boost Converters Photovoltaic Systems Thermal Management

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge Machine Learning Algorithms for In-Depth Characterization and Efficiency Improvement of Phase Change Heat Transfer Mechanisms

Cutting-Edge Machine Learning Algorithms for In-Depth Charac...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Khambra, Geetanjli Praveena, K. Manjunatha Dutt, Amit Khan, Irfan Issa, Ali Ashoor College Department of Computer Applications M.P Bhopal India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

This study introduces a sophisticated and holistic methodology for the enhanced understanding and optimization of phase change heat transfer mechanisms. The proposed framework integrates Deep Learning Neural Networks (DLNN), Random Forest (RF), Long Short-Term Memory (LSTM) Networks, Gaussian Processes (GP), and Reinforcement Learning (RL) in a synergistic manner, emphasizing the iterative and adaptive nature of each algorithm. A detailed flowchart for each algorithm delineates the process, showcasing their roles in refining predictions and optimizing models. An ablation study underscores the crucial contribution of each component, revealing their collective efficacy. Comparative analyses against existing algorithms highlight the proposed method's consistent superiority in accuracy, precision, recall, mean squared error, and Rsquared. Resource efficiency metrics further affirm its computational effectiveness. Visualizations provide a comprehensive and intuitive representation of the methodology's strengths. The proposed framework offers a promising avenue for characterizing and optimizing phase change heat transfer, contributing to advancements in thermal sciences and real-world applications. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Altered Cloud Service Composition Techniques for Enhanced Integration

Altered Cloud Service Composition Techniques for Enhanced In...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Nancy Arya Priyanka Gupta B Rajalakshmi Ginni Nijhawan Praveen Hareth A. Alrikabi Department of Computer Science and Engineering Shree Guru Gobind Singh Tricentenary University Gurugram Institute of Aeronautical Engineering Dundigal Hyderabad Department of Computer Science New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Lloyd Institute of Engineering & Technology Knowledge Park II Greater Noida Uttar Pradesh Collage of Dentist National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

Create dynamic, dependable, and cost-effective cloud service combinations using the Dynamic Cloud Service Composition (DCSC) approach. Service Ranking (SR), Adaptive Composition (AC), and Cost Optimization algorithm are used in this strategy. Their combined efforts classify services by QoS, generate flexible compositions, and minimize prices. The most important factors for ranking service quality can be found using weighted numbers. It is possible to achieve dynamic flexibility by keeping an eye on service traits and using Adaptive Composition to start reconfigurations. Cutting costs without lowering the standard of service is what cost optimization is all about. Economically beneficial compositions result. Performance Score (PS), Adaptation Rate (AR), Cost Efficiency (CE), Resilience Index (RI), Resource Utilization (RU), and (ACost) are evaluated.

关键词： Technological innovation Costs Quality of service Writing Resource management Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

From Non-Expert to Expert: Recurrent Refined Learning for Medical Image Segmentation

From Non-Expert to Expert: Recurrent Refined Learning for Me...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Ruohui Li, Changtai Ban, Xiaojuan Yin, Shihua Yao, Chao Guo, Yu Obaidat, Mohammad S. University of Science and Technology Beijing Beijing Advanced Innovation Center for Materials Genome Engineering Beijing China University of Science and Technology Beijing School of Intelligence Science and Technology Beijing China Liaoning Academy of Materials Institute of Materials Intelligent Technology Shenyang China Second Affiliated Hospital Guangxi Medical University Nanning China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China University of Jordan King Abdullah Ii School of Information Technology Amman Jordan Amity University UP Noida India

ISBN: (纸本)9798350386226

Precise lesion segmentation is essential in computer-aided diagnosis and treatment. Prevalent deep-learning-based approaches need high-quality annotations to achieve satisfying performance. However, blurring effects and infiltration hamper the accurate delineation of lesions. A common solution is to divide the annotation process into initial annotation by non-specialized personnel and subsequent modification by expert physicians, where the latent correction patterns and non-expert labels are seldom utilized effectively. To explore their helpfulness, we propose ReReNet, a recurrent refined network for lesion segmentation that learns from non-expert to expert. It achieves progressively refined segmentation results through multiple iterations with tailored discrepancy-aware supervision. During training, as the iterative process perceives discrepancies between refining and expert labels, the model gradually grasps the knowledge of turning the barely correct into the clinically accurate. We validate ReReNet's capability on three medical image segmentation (MIS) datasets, including magnetic resonance (MR) and computed tomography (CT) modalities. Comparison results indicate that the proposed approach achieves superior performance by introducing the designed recurrent mechanism and outperforms mainstream methods, demonstrating the effectiveness of mining hidden correction patterns by utilizing non-expert information. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Active Visible-Light Integrated Photonics Platform on 200-mm Si

An Active Visible-Light Integrated Photonics Platform on 200...

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Sacher, Wesley D. Lin, Yiding Chen, Hong Azadeh, Saeed S. Yong, Zheng Luo, Xianshu Chua, Hongyao Mak, Jason C. C. Govdeli, Alperen Sharma, Ankita Mikkelsen, Jared C. Mu, Xin Stalmashonak, Andrei Lo, Guo-Qiang Poon, Joyce K. S. Max Planck Institute of Microstructure Physics Weinberg 2 Halle06120 Germany Department of Electrical and Computer Engineering University of Toronto 10 King's College Road TorontoONM5S 3G4 Canada Advanced Micro Foundry Pte. Ltd 11 Science Park Road Science Park II Singapore117685 Singapore

We present a foundry-fabricated monolithically integrated photonics platform for the visible spectrum (λ=445-640nm) with two layers of silicon nitride waveguides, silicon photodiodes, efficient undercut thermo-optic ... 详细信息

ISBN: (纸本)9781957171180

关键词： Silicon nitride

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：