检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Xing, Yuting Ye, Hangting Zhang, Xiaoyu Cao, Wei Zheng, Shun Bian, Jiang Guo, Yike Data Science Institute Imperial College London London United Kingdom Jilin University School of Artificial Intelligence Jilin China Microsoft Research Asia Beijing China Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9781665468190

Continuous glucose monitoring prediction is a crucial yet challenging task in precision medicine. This paper presents a novel neural ODE based approach for predicting continuous glucose monitoring (CGM) levels purely based on sporadic self-monitoring signals. We integrate the expert knowledge from physiological model into our model to improve the accuracy. Experiments on the real-world data demonstrate that our method outperforms other state-of-the-art methods on NRMSE metrics. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

CollageNoter: Real-Time and Adaptive Collage Layout Design for Screenshot-Based E-Note-Taking 39

CollageNoter: Real-Time and Adaptive Collage Layout Design f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Qiuyun Guo, Bin Yao, Lina Qiao, Xiaotian Zhang, Ying Yu, Zhiwen School of Computer Science Northwestern Polytechnical University China CSIRO’s Data61 Australia School of Computer Science and Technology Xidian University China Guangzhou Institute of Technology Xidian University China College of Computer Science and Technology Harbin Engineering University China

ISBN: (纸本)157735897X

To enhance the processing of complex multi-modal documents (e.g. e-books, long web pages, etc.), it is an efficient way for users to take digital screenshots of key parts and reorganize them into a new collage E-Note. Existing methods for assisting collage layout design primarily employ a semantic relevance-first strategy, with arranging related contents together. Though capable, it can not ensure the visual readability of screenshots and may conflict with human natural reading patterns. In this paper, we introduce CollageNoter for real-time collage layout design that adapts to various devices (e.g. laptop, tablet, phone, etc.), offering users visually and cognitively well-organized screenshot-based E-Notes. Specifically, we construct a novel two-stage pipeline for collage design, including 1) readability-first layout generation and 2) cognitive-driven layout adjustment. In addition, to achieve real-time response and adaptive model training, we propose a cascade transformer-based layout generator named CollageFormer and a size-aware collage layout builder for automatic dataset construction. Extensive experimental results have confirmed the effectiveness of our CollageNoter. 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

Virtual Palette: An Efficient Object Tracking Tool

Virtual Palette: An Efficient Object Tracking Tool

引用

Sustainable computing and Smart Systems (ICSCSS), International Conference on

作者： R. Madhura S. Nikkath Bushra Devi P. P Sasigresa P Department of Computing Technologies SRM Institute of Science and Technology Kattangulathur Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering (Data Science) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Virtual Palette is a cutting-edge tool designed to enhance audience participation by providing an alternative to conventional jamboards for educators. Leveraging object tracking, a fundamental component of computer vision, it facilitates seamless and intuitive interactions with the audience. The video analysis process comprises three primary steps: object detection, object tracking across frames, and object behavior analysis. This sophisticated approach necessitates meticulous consideration of elements such as accurate object representation, feature selection for tracking, object recognition, and object tracking. One of the primary advantages of Virtual Palette over traditional mouse or touchpad devices is its ability to support clear and legible drawing and effective interaction in virtual environments. This feature is particularly beneficial for individuals with hearing impairments, aiding in the identification of patterns and drawings. The development of Virtual Palette involves overcoming challenges such as precise three-dimensional finger movement tracking and optimizing the technology for virtual backgrounds. Overall, Virtual Palette offers a dynamic and interactive teaching experience, akin to the advantages provided by screen recording for creating tutorials and virtual documentation.

关键词： Fingers Virtual environments Tutorials Transforms Object detection Green computing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on optimization of emergency rescue plan based on risk measurement 3

Research on optimization of emergency rescue plan based on r...

引用

2023 3rd International Conference on Big data, Artificial Intelligence and Risk Management, ICBAR 2023

作者： Bu, Fanbiao Chen, Xuhao Lv, Ying Xu, Hengrui Overall Demonstration Center Qian Xuesen Institute of Military Systems Engineering Beijing100024 China Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Institute of Transportation System Science and Engineering School of Traffic and Transportation Beijing100044 China Shijiazhuang Land and Space Planning and Design Institute Co. Ltd. Hebei Shijiazhuang050019 China Data Center Agricultural Bank of China Limited Beijing100024 China

ISBN: (纸本)9798400716478

In order to reduce the impact of emergencies, this paper takes emergencies in complex geological environment as the background to study the optimization problem of emergency rescue routes. We measure the casualty consequences caused by the delay of rescue time based on conditional value at risk, and adopt multiple modes of transportation to coordinate rescue. A bi-objective optimization model is established with the total risk and total cost as the objectives, then the constraint method is applied to transform the model into a single objective optimization model for solution. Finally, an example is designed to analyze the relationship between the total risk and the total cost, and the rescue path scheme under the condition that the demand information is determined. The results indicate that the established model can provide a reference basis for emergency rescue of emergencies in the process of major Transportation engineering construction. © 2023 ACM.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Parallel Dual-Branch Fusion Network for Epileptic Seizure Prediction

引用

Computers in Biology and Medicine 2024年 176卷 108565-108565页

作者： Ma, Hongcheng Wu, Yajing Tang, Yongqiang Chen, Rui Xu, Tao Zhang, Wensheng School of Information and Communication Engineering Hainan University Haikou China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Taiyuan China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

Epilepsy is a prevalent chronic disorder of the central nervous system. The timely and accurate seizure prediction using the scalp Electroencephalography (EEG) signal can make patients adopt reasonable preventive measures before seizures occur and thus reduce harm to patients. In recent years, deep learning-based methods have made significant progress in solving the problem of epileptic seizure prediction. However, most current methods mainly focus on modeling short- or long-term dependence in EEG, while neglecting to consider both. In this study, we propose a Parallel Dual-Branch Fusion Network (PDBFusNet) which aims to combine the complementary advantages of Convolutional Neural Network (CNN) and Transformer. Specifically, the features of the EEG signal are first extracted using Mel Frequency Cepstral Coefficients (MFCC). Then, the extracted features are delivered into the parallel dual-branches to simultaneously capture the short- and long-term dependencies of EEG signal. Further, regarding the Transformer branch, a novel feature fusion module is developed to enhance the ability of utilizing time, frequency, and channel information. To evaluate our proposal, we perform sufficient experiments on the public epileptic EEG dataset CHB-MIT, where the accuracy, sensitivity, specificity and precision are 95.76%, 95.81%, 95.71% and 95.71%, respectively. PDBFusNet shows superior performance compared to state-of-the-art competitors, which confirms the effectiveness of our proposal. © 2024 Elsevier Ltd

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Squeeze Excitation Embedded Attention UNet for Brain Tumor Segmentation

arXiv

引用

arXiv 2023年

作者： Prasanna, Gaurav Ernest, John Rohit Lalitha, G. Narayanan, Sathiya School of Electronics Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India

Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures such as UNet, Attention UNet and Attention Residual UNet are already currently existing methods for the same application of brain tumor segmentation, but none of them address the issue of how to extract the features in channel level. In this paper, we propose a new architecture called Squeeze Excitation Embedded Attention UNet (SEEA-UNet), this architecture has both Attention UNet and Squeeze Excitation Network for better results and predictions, this is used mainly because to get information at both Spatial and channel levels. The proposed model was compared with the existing architectures based on the comparison it was found out that for lesser number of epochs trained, the proposed model performed better. Binary focal loss and Jaccard Coefficient were used to monitor the model’s performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis

arXiv

引用

arXiv 2024年

作者： Zhou, Xuehao Zhang, Mingyang Zhou, Yi Wu, Zhizheng Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Hong Kong Generative AI Research and Development Centre The Hong Kong University of Science and Technology Hong Kong Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS) systems is challenging due to the complex variations of accents and the inherent entanglement between speaker and accent identities. In this paper, we propose a novel approach for multispeaker multi-accent TTS synthesis that aims to synthesize speech for multiple speakers, each with various accents. Our approach employs a multi-scale accent modeling strategy to address accent variations on different levels. Specifically, we introduce both global (utterance level) and local (phoneme level) accent modeling to capture overall accent characteristics within an utterance and fine-grained accent variations across phonemes, respectively. To enable independent control of speakers and accents, we use the speaker embedding to represent speaker identity and achieve speaker-independent accent control through speaker disentanglement within the multi-scale accent modeling. Additionally, we present a local accent prediction model that enables our system to generate accented speech directly from phoneme inputs. We conduct extensive experiments on an English accented speech corpus. Experimental results demonstrate that our proposed system outperforms baseline systems in terms of speech quality and accent rendering for generating multispeaker multi-accent speech. Ablation studies further validate the effectiveness of different components in our proposed system. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Security Analysis and Threat Modelling of Mobile Banking Applications

Security Analysis and Threat Modelling of Mobile Banking App...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Amartyanil Chattopadhyay Divya Sripada School of Electronics Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India

Technology revolution has transformed the way consumers interact with financial institutions. With SMS and applications, the usage of mobile banking has exploded. With 5.22 billion mobile banking customers worldwide, the financial transactions made through mobile banking crosses into trillions. Though this has eased tedious banking processes, threats are rampant. Threats range from simple malwares to serious crimes threatening safety of financial assets and causing irreversible losses. This paper aims to collate the 5 major threats to banking applications (and also in the context of SMS), provide an objectified view of how vulnerabilities in mobile banking applications could cause these threats and ways to address them. This comprehensive review provides a threat modelling framework that help in detection and mitigation strategies for these threats.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

arXiv

引用

arXiv 2023年

作者： Zhu, Zihao Zhang, Mingda Wei, Shaokui Shen, Li Fan, Yanbo Wu, Baoyuan School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China JD Explore Academy China Tencent AI Lab United States

data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion strategies between triggers and benign samples. However, they often randomly select samples to be poisoned, disregarding the varying importance of each poisoning sample in terms of backdoor injection. A recent selection strategy filters a fixed-size poisoning sample pool by recording forgetting events, but it fails to consider the remaining samples outside the pool from a global perspective. Moreover, computing forgetting events requires significant additional computing resources. Therefore, how to efficiently and effectively select poisoning samples from the entire dataset is an urgent problem in backdoor attacks. To address it, firstly, we introduce a poisoning mask into the regular backdoor training loss. We suppose that a backdoored model training with hard poisoning samples has a more backdoor effect on easy ones, which can be implemented by hindering the normal training process (i.e., maximizing loss w.r.t. mask). To further integrate it with normal training process, we then propose a learnable poisoning sample selection strategy to learn the mask together with the model parameters through a min-max optimization. Specifically, the outer loop aims to achieve the backdoor attack goal by minimizing the loss based on the selected samples, while the inner loop selects hard poisoning samples that impede this goal by maximizing the loss. After several rounds of adversarial training, we finally select effective poisoning samples with high contribution. Extensive experiments on benchmark datasets demonstrate the effectiveness and efficiency of our approach in boosting backdoor attack performance. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Implementation of Medical Insurance Price Prediction System using Regression Algorithms

Implementation of Medical Insurance Price Prediction System ...

引用

International Conference on Smart Systems and Inventive Technology (ICSSIT)

作者： V. Vijayalakshmi A. Selvakumar K. Panimalar Department of Information Science and Engineering CMR Institute of Technology Bengaluru Department of Computational Intelligence SIMATS School of Engineering Chennai Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai

Medical expenses are increasing day by day due to unexpected epidemic diseases. People have awareness about the medical insurance and claiming processes which is helping in critical situations. Predicting the medical insurance cost is very important work in health care sectors. Many researcheis applied different machine learning algoiithms to predict the insurance premium in Kaggle data set with seven attributes such as age, sex, bmi, children, smoker, region and charges. But these features only not suitable for prediction. In this paper, the dataset with 24 features including all relevant attributes needed for prediction of insurance cost was used. The implementation done using regression algorithms such as Linear Regression, Decision Tree Regression, Lasso Regression, Ridge Regression, Random Forest Regression, ElasticNet Regression, Support Vector Regression, K Nearest Neighbor Regression and Neural Network Regression in R Programming. There were seven metiices applied to measure the performance of the model namely Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), RSquared (R 2 ), Adjusted R-Squared (Adj. $\mathrm{R}^{2}$), and Explained Variance Score (EVS). Random Forest Regression outperformed with 0.9533 as RS quared value. This prediction system will reduce the manual work and give the prediction accurately in medical field.

关键词： Support vector machines Costs Neural networks Measurement uncertainty Insurance Manuals Programming

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：