检索结果-内蒙古大学图书馆

Towards Automatic Dataset Discovery From Scientific Publications

IEEE Access 2025年

作者： Kumar, Sandeep Ghosal, Tirthankar Ekbal, Asif Indian Institute of Technology Department of Computer Science and Engineering Patna India Oak Ridge National Laboratory National Center for Computational Sciences United States

Datasets are a crucial artifact in research, and there is always a high demand for good datasets. Due to rapid scientific progress and exponential growth in the scientific literature, there has been a proportionate increase in the number of datasets. However, many datasets and research studies are left unexplored and under-utilized as these are not discoverable easily, leading to duplicate efforts. Building good datasets is costly in terms of time, money, and human effort. Hence, automated tools to facilitate the search and discovery of datasets are crucial to the scientific community. In this work, we investigate a deep neural network-based architecture to automate the dataset discovery from scientific publications. In this paper, we perform two tasks namely dataset mention extraction and entity linking. Our method outperforms the earlier ones and achieves an F1 score of 56.24 in extracting dataset mentions from research papers on a popular corpus of social science publications. Our approach also outperforms the prior research and achieves a precision score of 88.63 in linking research papers to a dataset knowledge base for another popular corpus of social science publications. We hope that this system will further promote data sharing, offset the researchers' workload in identifying the right dataset and increase the reusability of datasets. © 2013 IEEE.

关键词： Discovering Datasets Extracting Dataset References Mining Publications Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

Automatic Diagnosis of Polycystic Ovarian Syndrome Using Wrapper Methodology with Deep Learning Techniques

引用

computer Systems science & engineering 2023年第10期47卷 239-253页

作者： Mohamed Abouhawwash S.Sridevi Suma Christal Mary Sundararajan Rohit Pachlor Faten Khalid Karim Doaa Sami Khafaga Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)College of EngineeringMichigan State UniversityEast LansingMI48824USA Sri Ramachandra Faculty of Engineering&Technology Sri Ramachandra Institute of Higher Education and ResearchPorurChennai600116India Department of Information Technology Panimalar Institute of TechnologyChennai600123India Department of Computer Science and Engineering School of EngineeringMIT ArtDesign and Technology UniversityPune412201India Department of Computer Sciences College of Computer and Information SciencesPrincess Nourahbint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

One of the significant health issues affecting women that impacts their fertility and results in serious health concerns is Polycystic ovarian syndrome(PCOS).Consequently,timely screening of polycystic ovarian syndrome can help in the process of *** a method to aid doctors in this procedure was crucial due to the difficulties in detecting this *** research aimed to determine whether it is possible to optimize the detection of PCOS utilizing Deep Learning algorithms and ***,feature selection methods that produce the most important subset of features can speed up calculation and enhance the effectiveness of *** this research,the tri-stage wrapper method is used because it reduces the computation *** proposed study for the Automatic diagnosis of PCOS contains preprocessing,data normalization,feature selection,and classification.A dataset with 39 characteristics,including metabolism,neuroimaging,hormones,and biochemical information for 541 subjects,was employed in this *** start,this research pre-processed the *** for feature selection,a tri-stage wrapper method such as Mutual Information,ReliefF,Chi-Square,and Xvariance is ***,various classification methods are tested and *** learning techniques including convolutional neural network(CNN),multi-layer perceptron(MLP),Recurrent neural network(RNN),and Bi long short-term memory(Bi-LSTM)are utilized for *** experimental finding demonstrates that with effective feature extraction process using tri stage wrapper method+CNN delivers the highest precision(97%),high accuracy(98.67%),and recall(89%)when compared with other machine learning algorithms.

关键词： Deep learning automatic detection polycystic ovarian syndrome tri-stage wrapper method mutual information relief Chi-Square

来源：评论

学校读者我要写书评

暂无评论

A Scalable Real-Time Data Assimilation Framework for Predicting Turbulent Atmosphere Dynamics

A Scalable Real-Time Data Assimilation Framework for Predict...

引用

2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Yin, Junqi Liang, Siming Liu, Siyan Bao, Feng Chipilski, Hristo G. Lu, Dan Zhang, Guannan Oak Ridge National Laboratory National Center for Computational Science Oak RidgeTN United States Florida State University Department of Mathematics TallahasseeFL United States Oak Ridge National Laboratory Computational Science and Engineering Division Oak RidgeTN United States Florida State University Department of Scientific Computing TallahasseeFL United States Oak Ridge National Laboratory Computer Science and Mathematics Division Oak RidgeTN United States

ISBN: (纸本)9798350355543

AI-based foundation models like FourCastNet, GraphCast, ClimaX, and Pangu-Weather are revolutionizing weather and climate predictions but are not yet ready for operational use. Their limitation lies in the absence of a data assimilation system to incorporate real-time Earth system observations, crucial for accurately forecasting events like tropical cyclones and atmospheric rivers. To overcome these obstacles, we introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF), which significantly outperforms the state-of-the-art data assimilation method, e.g., the Local Ensemble Transform Kalman Filter (LETKF);and a vision transformer-based surrogate capable of real-time adaptation through the integration of observational data. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier. Our results not only illustrate the framework's exceptional scalability on high-performance computing systems, but also demonstrate the importance of supercomputers in real-time data assimilation for weather and climate predictions. Even though the proposed framework is tested only on a benchmark surface quasi-geostrophic (SQG) turbulence system, it has the potential to be combined with existing AI-based foundation models, making it suitable for future operational implementations. © 2024 IEEE.

关键词： data assimilation Diffusion models foundation models generative AI high-performance computing uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

-Type inequalities for subsequences of Nörlund means of Walsh–Fourier series

引用

Journal of Inequalities and Applications 2023年第1期2023卷 1-13页

作者： Baramidze, David Persson, Lars-Erik Tangrand, Kristoffer Tephnadze, George School of Science and Technology The University of Georgia Tbilisi Georgia Department of Computer Science and Computational Engineering UiT The Arctic University of Norway Narvik Norway Department of Mathematics and Computer Science Karlstad University Karlstad Sweden

We investigate the subsequence $\{t_{2^{n}}f \}$ of Nörlund means with respect to the Walsh system generated by nonincreasing and convex sequences. In particular, we prove that a large class of such summability methods are not bounded from the martingale Hardy spaces $H_{p}$ to the space $\mathit{weak-}L_{p} $ for $0< p<1/(1+\alpha ) $ , where $0<\alpha <1$ . Moreover, some new related inequalities are derived. As applications, some well-known and new results are pointed out for well-known summability methods, especially for Nörlund logarithmic means and Cesàro means.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation

Generalizable Audio Deepfake Detection via Latent Space Refi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Wen Gu, Yanmei Wang, Zhiming Zhu, Huijia Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology Shanghai China Ant Group Shanghai China

ISBN: (纸本)9798350368741

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a novel strategy that integrates Latent Space Refinement (LSR) and Latent Space Augmentation (LSA) to improve the generalization of deepfake detection systems. LSR introduces multiple learnable prototypes for the spoof class, refining the latent space to better capture the intricate variations within spoofed data. LSA further diversifies spoofed data representations by applying augmentation techniques directly in the latent space, enabling the model to learn a broader range of spoofing patterns. We evaluated our approach on four representative datasets, i.e. ASVspoof 2019 LA, ASVspoof 2021 LA and DF, and In-The-Wild. The results show that LSR and LSA perform well individually, and their integration achieves competitive results, matching or surpassing current state-of-the-art methods. © 2025 IEEE.

关键词： anti-spoofing audio deepfake detection generalization

来源：评论

学校读者我要写书评

暂无评论

Sclera Vessel Analysis for Biometric System on Real Time Security Application

Sclera Vessel Analysis for Biometric System on Real Time Sec...

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Divya Anantharajan M. Saravanakumar B. Bharathi Kannan S. Ponmaniraj Department of Computer Science and Engineering Vandayar Engineering College Thanjavur Department of computer science and Engineering Hindusthan College of Engineering and Technology Coimbatore Department of computational Intelligence SIMATS Saveetha school of Engineering Thandalam

Biometrics has an unavoidable space in the era of security in terms of identifying the Individuals. There are many biometrics which are providing more prominent result, but all these biometrics needs the user cooperation in acquisition. The sclera, white portion of the eye, vessel patterns are holding the uniqueness to identify the individuals. This becomes the root of many researchers to recognize the individual with non-co-operative user images. Sclera recognitions are beginning of the new era which is to leads the recognition on the surveillance camera. Since the Image quality is less in the surveillance camera images and the segmentation of sclera is more challenging which has more impact on the accuracy of the recognition. To improve the accuracy of the segmentation Convolutional Neural Network has been used which has increase the time complexity of the system. Since the accuracy of the segmentation has increased and to optimize the time integro Differential Operator is utilized which reduces the searching area of the iris so the time taken will be reduced. The combination of CNN and DIO will increase the accuracy and complexity of the Segmentation Process. The experiments are carried out on the UBIRIS Dataset V2.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Wildlife Tracking with Fine-Tuned YOLOv11

Real-Time Wildlife Tracking with Fine-Tuned YOLOv11

引用

Trends in engineering Systems and Technologies (ICTEST), International Conference on

作者： Abdul Basit Mughal Javiriya Hameed Arian Syed Mohsin Shah Syed Mujtaba Haider Rafi Ullah Khan Department of Computer Science Bahria University Islamabad Pakistan Department of Computer Science COMSATS University Islamabad Pakistan Faculty of Engineering University of Deusto Bilbao Spain Department of Computational Mathematics University of Pavia Italy Department of Electrical & Computer Engineering PAF-IAST Haripur Pakistan

ISBN: (数字)9798331505370

ISBN: (纸本)9798331505387

Wildlife monitoring is an important task in computer vision to preserve biodiversity, maintain ecosystem balance and stability, and promote sustainable development. Monitoring wild animals is important for people living near forests, as conflicts between humans and wildlife often result in the loss of precious human lives and livestock. Low-Light images, diverse animal poses, complex environments, and varied terrain structures present significant challenges in wildlife monitoring. This paper introduces a novel wildlife monitoring technique utilizing a fine-tuned YOLOv11 model to effectively monitor animals in low lighting conditions, challenging environments and diverse poses. The dataset is constructed from CCTV video footage captured at night and includes frames featuring 17 wild animal species. The mAP of our fine-tuned YOLOv11 is 97.2%.

关键词： computer vision Animals Wildlife Object detection Streaming media Market research Stability analysis Real-time systems Sustainable development Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Trusted Lesion-assessment Network for Interpretable Diagnosis of Coronary Artery Disease in Coronary CT Angiography 39

A Trusted Lesion-assessment Network for Interpretable Diagno...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ma, Xinghua Fang, Xinyan Zou, Mingye Luo, Gongning Wang, Wei Wang, Kuanquan Qiu, Zhaowen Gao, Xin Li, Shuo Faculty of Computing Harbin Institute of Technology Harbin China Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal Saudi Arabia Faculty of Computing Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China Department of Computer and Data Science Case Western Reserve University Cleveland United States Department of Biomedical Engineering Case Western Reserve University Cleveland United States

ISBN: (纸本)157735897X

Coronary Artery Disease (CAD) poses a significant threat to cardiovascular patients worldwide, underscoring the critical importance of automated CAD diagnostic technologies in clinical practice. Previous technologies for lesion assessment in Coronary CT Angiography (CCTA) images have been insufficient in terms of interpretability, resulting in solutions that lack clinical reliability in both network architecture and prediction outcomes, even when diagnoses are accurate. To address the limitation of interpretability, we introduce the Trusted Lesion-Assessment Network (TLA-Net), which provides a clinically reliable solution for multi-view CAD diagnosis: (1) The causality-informed evidence collection constructs a causal graph for the diagnostic process and implements causal interventions, preventing confounders’ interference and enhancing the transparency of the network architecture. (2) The clinically-aligned uncertainty integration hierarchically combines Dirichlet distributions from various views based on clinical priors, offering confidence coefficients for prediction outcomes that align with physicians’ image analysis procedures. Experimental results on a dataset of 2,618 lesions demonstrate that TLA-Net, supported by its interpretable methodological design, exhibits superior performance with outstanding generalization, domain adaptability, and robustness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-LSTM Based on Crow Search Optimization Algorithm for Product Review Classification

CNN-LSTM Based on Crow Search Optimization Algorithm for Pro...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Yamsani, Nagendar Jothi, B. Srinivasan, N. Dineshkumar, R. Ramachandra, A.C. Sr University School of Computer Science and Artificial Intelligence Warangal India Srm Institute of Science and Technology Kattankulathur Department of Computational Intelligence Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Cse Chennai India Saveetha School of Engineering Sriperumbudur Department of Ece Thandalam India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350313413

Product reviews means an everyone's opinion or views towards particular products or services that delivered to a specific company. In modern global, reviews of online product play a vital part in the estimation process of product in a company and their customers. The extracted features are selected by using the Chi-Squared technique and for the classification of product review proposed a model by utilizing the combined deep learning techniques like Convolutional Neural Network (CNN) and Long- Short Term Memory (LSTM) and it optimized by Crow Search Algorithm (CSA). CNN is used for capturing the local information and LSTM neural network is used for the long-distance dependencies. By utilizing the benefits of CNN and LSTM and it is optimized by CSA for the effective classification of product review. The proposed model performance is estimated by using the performance metrics like Accuracy, Recall, Specificity, Sensitivity and F1-score are 98.35%, 93.20%, 97.57%, 94.82% and 95.78% respectively. The proposed model is compared with other existing model in terms of performance metrics which shows the better performance results. © 2023 IEEE.

关键词： Chi-Squared Convolutional Neural Network Crow Search Algorithm Long-Short Term Memory and Product Review

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Based Long Short-Term Memory for Android Malware Detection

Hybrid Optimization Based Long Short-Term Memory for Android...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Lande, Jayapal Maheswari, M. Kamali, S.M. Dineshkumar, R. Priyanka, M.S. Sr University School of Computer Science & Artificial Intelligence Warangal India Srm Institue of Science and Technology School of Computing Department of Computational Intelligence Chennai India Annapoorana Engineering College Department of Electrical and Electronics Engineering Salem India Saveetha School of Engineering Department of Ece Sriperumbudur Thandalam India Nitte Meenakshi Institute of Technology Department of Ai and Ml Yelahanka Bengaluru India

ISBN: (纸本)9798350313413

Malware detection is process of detecting the suspicious files and activities, that can classify as benign and malicious depends on different characters like capability of infection, structure of malware and speed rate. In this paper, proposed a Particle Swarm Optimization and Ant Colony Optimization (HPSALO) based Long Short-Term Memory (LSTM) model for malware detection and classification. The combination of these two algorithms that leads to the balance between exploration and exploitation. The dataset utilized for the research is DREBIN dataset and process of data cleaning is performed by NumPy library. The feature selection is performed by combination of hybrid PSALO algorithms and selected features are given to Long Short-Term Memory (LSTM) classifier that classifies as benign and malware files. The performance of proposed method is estimated by performance metrics of accuracy, precision, recall and f1-score. The proposed method attained accuracy of 99.38%, precision of 99.30%, recall of 99.08% and f1-score of 99.42% which is comparatively higher than other existing methods like Whale Optimization Algorithm-LSTM (WOA-LSTM), Cat Swarm Optimization-LSTM (CSO-LSTM), Particle Swarm Optimization-LSTM and Ant Lion Optimization-LSTM. © 2023 IEEE.

关键词： Ant Lion Optimization Long Short-Term Memory Malware Detection NumPy and Particle Swarm Optimization

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：