检索结果-内蒙古大学图书馆

23rd International Symposium on Communications and Information Technologies, ISCIT 2024

作者： Mekruksavanich, Sakorn Tancharoen, Datchakorn Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand Panyapiwat Institute of Management Faculty of Engineering and Technology Nonthaburi Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350353952

Recognition of human activities using wearable sensors is essential for applications related to health and well-being. However, the complex data captured by inertial sensors poses challenges in accurately identifying actions. This research introduces MotionNeXt, a residual deep neural network incorporating aggregated transformation. MotionNeXt utilizes residual and multi-kernel blocks to extract spatial and temporal characteristics from raw IMU data. Subsequently, it employs global average pooling, a fully connected layer, and softmax for classification purposes. An attention layer enables the model to focus on specific segments of the input sequence while categorizing each time step. MotionNeXt is evaluated using a publicly available dataset of activities collected from wearable inertial measurement devices. It achieves state-of-the-art accuracy, boasting an F1-score of 99.37%, surpassing previous deep learning methods by 2- 5%. By integrating accelerometer, gyroscope, and magnetometer modalities, MotionNeXt mitigates the limitations of individual inputs, significantly improving accuracy across various models. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational Hardness of Detecting Graph Lifts and Certifying Lift-Monotone Properties of Random Regular Graphs

Computational Hardness of Detecting Graph Lifts and Certifyi...

引用

Annual IEEE Symposium on Foundations of computer science

作者： Dmitriy Kunisky Xifan Yu Department of Applied Mathematics & Statistics Johns Hopkins University Baltimore Maryland USA Department of Computer Science Yale University New Haven Connecticut USA

ISBN: (数字)9798331516741

ISBN: (纸本)9798331516758

We introduce a new conjecture on the computational hardness of detecting random lifts of graphs: we claim that there is no polynomial-time algorithm that can distinguish between a large random $d$ -regular graph and a large random lift of a Ramanujan $d$ -regular base graph (provided the lift is corrupted by a small amount of extra noise), and likewise for bipartite random graphs and lifts of bipartite Ramanujan graphs. We give evidence for this conjecture by proving lower bounds against the local statistics hierarchy of hypothesis testing semidefinite programs. We then explore the consequences of the conjecture for the hardness of certifying bounds on numerous functions of random regular graphs, expanding on a direction initiated by Bandeira, Banks, Kunisky, Moore, and Wein (2021). Conditional on this conjecture, we show that no polynomial-time algorithm can certify tight bounds on the maximum cut or maximum independent set of random 3- or 4-regular graphs, or on the chromatic number of random 7-regular graphs. Asymptotically for large degree for the maximum independent set and for any degree for the minimum dominating set, we show similar gaps, finding that naive spectral and combinatorial bounds are optimal among efficiently computable ones. Likewise, for small set vertex and edge expansion in the limit of very small sets, we show that the spectral bounds due to Kahale (1995) are optimal efficient certificates.

关键词： computer science Image edge detection Noise Certification Testing

来源：评论

学校读者我要写书评

暂无评论

Fit and Forecasting Indonesia Banking Stock Price During Covid-19 Pandemic Based on Logistic Differential Equation System 22

Fit and Forecasting Indonesia Banking Stock Price During Cov...

引用

Proceedings of the 2022 4th International Conference on E-Business and E-Commerce Engineering

作者： Viska Noviantri Andree Sulistio Chandra Yuhani Yusof Mathematics Department School of Computer Science Bina Nusantara University Indonesia Mathematics and Computer Science Department School of Computer Science Bina Nusantara University Indonesia Centre for Mathematical Sciences College of Computing and Applied Sciences Universiti Malaysia Pahang Malaysia

来源：评论

学校读者我要写书评

暂无评论

Unbiased Parameter Estimation for Bayesian Inverse Problems

arXiv

引用

arXiv 2025年

作者： Chada, Neil K. Jasra, Ajay Maama, Mohamed Tempone, Raul Department of Mathematics City University of Hong Kong China School of Data Science The Chinese University of Hong Kong Shenzhen CN Shenzhen China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

In this paper we consider the estimation of unknown parameters in Bayesian inverse problems. In most cases of practical interest, there are several barriers to performing such estimation, This includes a numerical approximation of a solution of a differential equation and, even if exact solutions are available, an analytical intractability of the marginal likelihood and its associated gradient, which is used for parameter estimation. The focus of this article is to deliver unbiased estimates of the unknown parameters, that is, stochastic estimators that, in expectation, are equal to the maximizer of the marginal likelihood, and possess no numerical approximation error. Based upon the ideas of [4] we develop a new approach for unbiased parameter estimation for Bayesian inverse problems. We prove unbiasedness and establish numerically that the associated estimation procedure is faster than the current state-of-the-art methodology for this problem. We demonstrate the performance of our methodology on a range of problems which include a PDE and ODE. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Generalized Multiquadric Neural Networks in Image Reconstruction 4

Generalized Multiquadric Neural Networks in Image Reconstruc...

引用

4th International Conference on Machine Learning and Intelligent Systems, MLIS 2022

作者： Pongchalee, Pornthip Inthapong, Pirapong Chanthawara, Krittidej Paewpolsong, Pichapop Kaennakham, Sayan Department of Applied Mathematics and Statistics Faculty of Science and Liberal Arts Rajamangala University of Technology Isan Nakhon Ratchasima30000 Thailand School of Mathematics Institute of Science Suranaree University of Technology Nakhon Ratchasima30000 Thailand Program of Mathematics Faculty of Science Ubon Ratchathani Rajabhat University Ubon Ratchathani34000 Thailand

ISBN: (纸本)9781643683560

This work aims to numerically investigate the performance of the multiquadric (MQ) radial basis function in more general formats for image reconstruction applications. Desired features, i.e., accuracy and shape parameter sensitivity, of each form is numerically compared and explored. The famous Lena image is damaged using two levels of damage: 20% and 40%, in a Salt-and-Pepper manner. It has been discovered in this work that β=3/2 produces reasonably good accuracy and is least affected by the change in shape parameter while keeping both the CPU time and the condition number reasonably acceptable. This finding is promising and useful for further applications of MQ in more complex contexts. © 2022 The authors and IOS Press.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLMs for Multimodal Medical Time Series Analysis 9

Leveraging LLMs for Multimodal Medical Time Series Analysis

引用

9th Machine Learning for Healthcare Conference, MLHC 2024

作者： Chan, Nimeesha Parker, Felix Bennett, William Wu, Tianyi Jia, Mung Yao Fackler, James Ghobadi, Kimia Department of Civil and Systems Engineering Johns Hopkins University BaltimoreMD United States Department of Anesthesiology and Critical Care Medicine Johns Hopkins University BaltimoreMD United States Department of Applied Mathematics and Statistics Johns Hopkins University BaltimoreMD United States Department of Computer Science Johns Hopkins University BaltimoreMD United States

The complexity and heterogeneity of data in many real-world applications pose significant challenges for traditional machine learning and signal processing techniques. For instance, in medicine, effective analysis of diverse physiological signals is crucial for patient monitoring and clinical decision-making and yet highly challenging. We introduce MedTsLLM, a general multimodal large language model (LLM) framework that effectively integrates time series data and rich contextual information in the form of text to analyze physiological signals, performing three tasks with clinical relevance: semantic segmentation, boundary detection, and anomaly detection in time series. These critical tasks enable deeper analysis of physiological signals and can provide actionable insights for clinicians. We utilize a reprogramming layer to align embeddings of time series patches with a pretrained LLM’s embedding space and make effective use of raw time series, in conjunction with textual context. Given the multivariate nature of medical datasets, we develop methods to handle multiple covariates. We additionally tailor the text prompt to include patient-specific information. Our model outperforms state-of-the-art baselines, including deep learning models, other LLMs, and clinical methods across multiple medical domains, specifically electrocardiograms and respiratory waveforms. MedTsLLM presents a promising step towards harnessing the power of LLMs for medical time series analysis that can elevate data-driven tools for clinicians and improve patient outcomes. © 2024 Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Investigation of district heating peak load reduction in residential neighbourhoods 18

Investigation of district heating peak load reduction in res...

引用

18th IBPSA Conference on Building Simulation, BS 2023

作者： Mokhtari, Reza Filonenko, Konstantin Junker, Rune Grønborg Madsen, Henrik Li, Rongling Department of Civil Engineering and Mechanical Engineering Technical University of Denmark Brovej 118 Kgs. Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Richard Petersens Plads Building 324 Kgs. Lyngby2800 Denmark

This study explores the potential of utilizing the energy flexibility of heat customers to reduce peak loads and improve the efficiency of district heating systems. Using Modelica and compiled in Dymola, a rule-based controller and dynamic heat price signals were developed to unlock the energy flexibility of buildings. Simulations were conducted to estimate peak load reduction and potential energy savings that could be realized. To investigate this opportunity, we conducted a simulation-based modeling study of a case study consisting of 19 apartment blocks connected to a local district heating network in a certain location. © 2023 *** rights reserved.

关键词： District heating

来源：评论

学校读者我要写书评

暂无评论

A Secure and Lightweight Batch Authentication Scheme for Internet of Drones Environment

SSRN

引用

SSRN 2023年

作者： Zhang, Yuanyuan Meng, Lingzhe Zhang, Mingwu Meng, Weizhi School of Computer Science Hubei University of Technology Wuhan China The Department of Applied Mathematics and Computer Science Technical University of Denmark Copenhagen region Denmark

In the early 21st century, Internet of Drones (IoD) ushered in a rapid growth period and is gradually expanded from military field to civilian field. Currently, there are more and more scenarios where multiple drones are needed to complete a task together. Considering the high efficiency of completing tasks, the current authentication schemes for single drone are not suitable for the application scenario of multiple drones. Therefore, we propose a novel lightweight authentication scheme, which supports users' batch authentication of multiple drones to ensure high efficiency of authentication. In our scheme, increasing the number of drones has little impact on the performance of our scheme, making it very suitable for the batch authentication of a large number of drones. In addition, Physical Unclonable Functions (PUFs) are introduced into our scheme to resist physical capture attack. Furthermore, our formal and informal security analyses reveal that our scheme can withstand most known attacks. The experimental result shows that our scheme can provide better security and lower storage and computation overheads when authenticating multiple drones, as compared with existing similar schemes. © 2023, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Optimal Prediction of Heart Disease by Identifying the Type of Chest Pain Using Machine Learning Techniques 4th

Optimal Prediction of Heart Disease by Identifying the Type ...

引用

4th International Conference on Communication and Intelligent Systems, ICCIS 2022

作者： Ahmad, Ghulab Nabi Fatima, Hira Shafiullah Noor, Arshil Institute of Applied Sciences Mangalayatan University Uttar Pradesh Aligarh India Department of Mathematics K.C.T.C College BRA Bihar University Muzaffarpur Raxual India Department of Computer Science Institute of Technology and Management Uttar Pradesh Aligarh India

ISBN: (纸本)9789819920990

Any serious heart ailment is referred to as coronary heart disease. Researchers are concentrating on developing smart systems to identify heart disease precisely based on electronic health data, with the use of machine learning algorithms (MLAs), because they can be fatal. This study introduces ten machine learning techniques (MLTs) for predicting heart diseases using patient data on key healthcare outcomes as: logistic regression classifier (LRC), decision tree classifier (DTC), random forest classifier (RFC), extra tree classifier (EXTC), K-nearest neighbours classifier (KNNC), support vector machine classifier (SVMC), bagging classifier (BC), gradient boosting classifier (GBC), light GBM classifier (LGBMC), Gaussian Naive Bayes classifier (GNBC) on standard datasets from Cleveland, Hungarian, Switzerland, Long Beach VA database, and Statlog Heart Disease of University of California Irvine (UCI) repository to build the prediction models. Data preprocessing and feature selection steps are done before building the models. The models are evaluated based on the accuracy, precision, recall, and F1-score, specificity, MCC, ROC–AUC, and balanced accuracy. The extra tree classifier performed best with 89.10% accuracy, 93.50% precision, 87.80% recall, 90.06% F1-score, 91.10% specificity, 78.00% MCC, 89.44% ROC–AUC, and 89.10% balanced accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

In-process monitoring of selective thermoplastic electrophotographic process by laser profiling system and digital fingerprint 23

In-process monitoring of selective thermoplastic electrophot...

引用

23rd International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2023

作者： Shan, Shuo Yeh, Hao-Ping Rotari, Marta Meinert, Kenneth Ælkær Hattel, Jesper Henri Pedersen, David Bue Kulahci, Murat Hansen, Hans Nørgaard Zhang, Yang Calaon, Matteo Department of Mechanical Engineering Technical University of Denmark Building 427A Produktionstorvet Kgs. Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Building 324 Richard Petersens Plads Kgs. Lyngby2800 Denmark

ISBN: (纸本)9781998999132

In the past decade, the demand for high-volume production of high-precision products with complex shapes has led to the development of new manufacturing processes. Among these processes, the Selective Thermoplastic Electrophotographic Process (STEP) shows potential for meeting these production demands. STEP involves layer-wise construction of a 3D object from a CAD model. However, during process characterization and optimization, defects such as dimensional flaws have been detected in the final products. To address this quality control issue, a laser profiling system has been installed on the STEP machine to detect process stability for every layer added to the 3D bulk. Additionally, finger print test structures have been introduced in the build job to evaluate process performance. Image detection post-processing of the test geometries is carried out to quantify the dynamic dimensional conformance layer by layer of the manufactured component. By using the online data collected through this quality control process, greater control over the manufacturing process can be achieved, and a feedback loop can be established. This feedback loop will allow for the online adjustment of manufacturing parameters, which will be applicable and provide great help for product optimization. The new sensors and algorithms used for this quality control process will also be incorporated into the digital twin, making this technology even more valuable for a wide range of applications. © 2023 Euspen Headquarters.

关键词： 3D printing

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：