检索结果-内蒙古大学图书馆

10th International Conference on Health Informatics and Medical Systems, HIMS 2024 and 10th International Conference on Biomedical Engineering, BIOENG 2024, held as part of the World Congress in Computer Science, Computer Engineering and applied Computing, CSCE 2024

作者： Shimizu, Shunji Hori, Masaya Inoue, Hiroaki Miwakeichi, Fumikazu Hirai, Nobuhide Kikuchi, Senichiro Kato, Satoshi Department of Applied Information Engineering Suwa University of Science Chino Japan Department of Engineering and Management Suwa University of Science Chino Japan Shimizu Research Laboratory Suwa University of Science Chino Japan Department of Interdisciplinary Statistical Mathematics The Institute of Statistical Mathematics Tachikawa Japan Health Administration Center Tokyo Medical and Dental University Bunkyo Japan Department of Rehabilitation Sciences Gunma University Maebashi Japan Oyama Fujimidai Hospital Shimotsuke Japan

ISBN: (纸本)9783031859076

In this study, we will investigate a new image signal processing method in order to develop a highly useful walking support device for visually impaired people. Visually impaired people walk independently using assistive devices. Currently, there are many support devices that use object detection and object recognition using deep learning, but there are still no highly useful devices. The smallest unit constituting an image signal is a pixel. Adjacent pixels are correlated with each other. The positional relationship of pixels expresses the features of objects, and scenery in the image. Autoregressive (AR) model is a regression analysis method used to analyze time-series signals. AR models are one of the basic methods for signal processing for speech recognition and control. Furthermore, in image signal processing, it can be used as a signal processing method when data has some kind of order, such as texture feature extraction, contour processing, and video processing. In this experiment, we converted the pixel array of the image signal into a one-dimensional time-series signal and process the signal. We tried to identify objects or regions within images. The method proposed in this study may be used to extract "Point of Interest" (POI) and "Point of Reference" (POR), which are important information for visually impaired people. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

Machine learning from a continuous viewpoint,I

引用

Science China mathematics 2020年第11期63卷 2233-2266页

作者： Weinan E Chao Ma Lei Wu Department of Mathematics Princeton UniversityPrincetonNJ 08544USA The Program in Applied and Computational Mathematics Princeton UniversityPrincetonNJ 08544USA Beijing Institute of Big Data Research Beijing 100871China

We present a continuous formulation of machine learning,as a problem in the calculus of variations and differential-integral equations,in the spirit of classical numerical *** demonstrate that conventional machine learning models and algorithms,such as the random feature model,the two-layer neural network model and the residual neural network model,can all be recovered(in a scaled form)as particular discretizations of different continuous *** also present examples of new models,such as the flow-based random feature model,and new algorithms,such as the smoothed particle method and spectral method,that arise naturally from this continuous *** discuss how the issues of generalization error and implicit regularization can be studied under this framework.

关键词： machine learning continuous formulation flow-based model gradient flow particle approximation

来源：评论

学校读者我要写书评

暂无评论

Microfluidic droplet detection using synthetic data generated by a Generative Adversarial Network

引用

Engineering Applications of Artificial Intelligence 2025年 156卷

作者： Marziyeh Karimzadeh Mohsen Alambardar Meybodi Mohammadreza Shams Zahra Goli-Malekabadi Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan 81746-73441 Iran Department of Computer Engineering Shahreza Campus University of Isfahan Isfahan Iran Department of Medical Technology and Tissue Engineering School of Life science Engineering College of Interdisciplinary Science and Technology University of Tehran Tehran Iran

Cellular heterogeneity, even among genetically identical cells, results in variations in their properties and behaviors, making single-cell analysis crucial for obtaining detailed insights. However, isolating single cells from a cell population poses major challenges, as conventional laboratory techniques often risk cell damage and involve complex procedures. Droplet microfluidics has emerged as a promising approach for encapsulating cells, particularly single cells, into individual droplets without causing harm. Despite this, factors like cell sedimentation and aggregation can reduce encapsulation efficiency and lead to deviations from the expected Poisson distribution. To address these challenges, leveraging artificial intelligence and deep learning to monitor, detect, and regulate encapsulation conditions in real-time is critical for enhancing system performance. However, deep learning models require substantial training data, and issues like microfluidic channel clogging and the scarcity of certain cell types often limit data availability. To overcome this limitation, researchers are turning to synthetic data generation to supplement training datasets and address data scarcity challenges effectively. This study emphasizes the potential of integrating synthetic data with cutting-edge deep learning techniques to enhance the accuracy and efficiency of single-cell analysis within droplet microfluidic systems. A diverse dataset integrating synthetic and real images was used to train the YOLOv8s model for automated detection and classification of microfluidic droplets, enhancing accuracy and system performance. The model trained on a combination of real and synthetic data outperformed the one trained using conventional data augmentation methods, achieving an mAP 0.5 of 98% due to the increased diversity of training images. It also demonstrated faster and more stable training. Additionally, the YOLOv8 network, with a detection rate of approximately 2338 droplets per se

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-Eulerian and High Order Gaussian Beam Methods for the Schrödinger Equation in the Semiclassical Regime

引用

Communications in Computational Physics 2011年第3期9卷 668-687页

作者： Shi Jin Hao Wu Xu Yang Department of Mathematics University of WisconsinMadisonWI 53706USA Department of Mathematical Sciences Tsinghua UniversityBeijing 10084China Program in Applied and Computational Mathematics Princeton UniversityNJ 08544USA

A novel Eulerian Gaussian beam method was developed in[8]to compute the Schrödinger equation efficiently in the semiclassical *** this paper,we introduce an efficient semi-Eulerian implementation of this *** new algorithm inherits the essence of the Eulerian Gaussian beam method where the Hessian is computed through the derivatives of the complexified level set functions instead of solving the dynamic ray tracing *** difference lies in that,we solve the ray tracing equations to determine the centers of the beams and then compute quantities of interests only around these *** yields effectively a local level set implementation,and the beam summation can be carried out on the initial physical space instead of the phase *** a consequence,it reduces the computational cost and also avoids the delicate issue of beam summation around the caustics in the Eulerian Gaussian beam ***,the semi-Eulerian Gaussian beam method can be easily generalized to higher order Gaussian beam methods,which is the topic of the second part of this *** numerical examples are provided to verify the accuracy and efficiency of both the first order and higher order semi-Eulerian methods.

关键词： Schrödinger equation semi-Eulerian Gaussian beam method high order methods

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Multiscale Methods: A Review

引用

Communications in Computational Physics 2007年第3期2卷 367-450页

作者： Weinan E Bjorn Engquist Xiantao Li Weiqing Ren Eric Vanden-Eijnden Department of Mathematics and Program in Applied and Computational Mathematics Princeton UniversityPrincetonNJ 08544USA Department of Mathematics The University of Texas at AustinAustinTX 78712USA Department of Mathematics Pennsylvania State UniversityUniversity ParkPA 16802USA Department of Mathematics Courant Institute of Mathematical SciencesNew York UniversityNew YorkNY 10012USA.

This paper gives a systematic introduction to HMM,the heterogeneous multiscale methods,including the fundamental design principles behind the HMM philosophy and the main obstacles that have to be overcome when using HMM for a particular *** is illustrated by examples from several application areas,including complex fluids,micro-fluidics,solids,interface problems,stochastic problems,and statistically self-similar *** is given to the technical tools,such as the various constrained molecular dynamics,that have been developed,in order to apply HMM to these *** of mathematical results on the error analysis of HMM are *** review ends with a discussion on some of the problems that have to be solved in order to make HMM a more powerful tool.

关键词： Multi-scale modeling heterogeneous multi-scale method multi-physics models constrained micro-scale solver data estimation.

来源：评论

学校读者我要写书评

暂无评论

Optimization production and characterization of fish protein hydrolysate (FPH) from Sardinella Lemuru head with papain protease

引用

AIP Conference Proceedings 2025年第1期3186卷

作者： Jannatul Firdaus Evi Susanti Suharti Suharti Department of Chemistry Faculty of Mathematics and Natural Sciences Universitas Negeri Malang Jl. Semarang 5 Malang 65145 Indonesia Biotechnology Program Department of Applied Science Faculty of Mathematics and Natural Sciences Universitas Negeri Malang Jl. Semarang 5 Malang 65145 Indonesia

Sardinella lemuru head has potential as Fish Protein Hydrolysate (FPH). This study aims to determine the optimum conditions and characterization of FPH from lemuru fish heads produced enzymatically with papain. This study was conducted through the following stages with (1) isolation of crude extract of papain, (2) optimization of papain enzymatic FPH production methods, (3) characterization of FPH including determined of proximate value, FTIR analysis, molecular weight, the antibacterial and antioxidant activity FPH produced from lemuru fish head powder was a short peptide measuring about 25 kDa and less. FPH has water, protein, and fat value of 24.54; 28.76; and 0.224 % (w/w). The resulting yield was at an optimum condition of 18.87% under the following conditions: 1 g of fish head powder was hydrolyzed with 0.705 U papain in 8 mL of phosphate buffer pH 7 0.1 M, incubated for 3 hours at room temperature, continued for 90 minutes at 75°C and at 90°C for 5 minutes. At a concentration of 10,000 ppm, the FPH can inhibit the growth of Escherichia coli bacteria by producing an inhibition zone diameter of 4.537±0.265 and Staphylococcus aureus bacteria by 5.5±0.212 and has an IC50 value to inhibit DPPH free radical oxidation of 70.175 ppm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional multi-release software modelling with testing effort, time and two types of imperfect debugging

引用

International Journal of Reliability and Safety 2016年第4期10卷 368-388页

作者： Kumar, Vijay Sahni, Ramita Shrivastava, A.K. Department of Mathematics Amity School of Engineering and Technology New Delhi110061 India Department of Applied Mathematics Amity Institute of Applied Sciences Amity University Sector 125 Noida UP India Amity Center for Interdisciplinary Research Amity University Noida UP India

An indispensable dependence on software systems for all activities is tremendously increasing in this industrialised era. This dependence demands good quality of the software. In order to fulfil these demands, software firms have strategised to release the software in successive releases. But adding new functionalities in the current version is a tedious task and makes the software more complicated. This complexity increases the risk of facing more faults in the software. Sometimes, the testing team may not have sufficient knowledge of the software to remove faults completely from the complex software or may add extra faults into it. Removing faults from the software needs time and resources. In this paper, the effect of two types of imperfect debugging to develop a generalised framework for a time and resource based multi upgradation model has been incorporated. Further, a two-stage fault removal technique which considers fault detection and correction as two-stage process is also proposed. The proposed models have been validated on real data set for four releases. Copyright © 2016 Inderscience Enterprises Ltd.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of nonlinear internal waves in deep water with miscible fluids

引用

Journal of Ocean Engineering and Marine Energy 2018年第4期4卷 243-257页

作者： Camassa, R. Hurley, M.W. McLaughlin, R.M. Passaggia, P.-Y. Thomson, C.F.C. Department of Mathematics Carolina Center for Interdisciplinary Applied Mathematics University of North Carolina Chapel HillNC27599 United States Department of Marine Sciences University of North Carolina Chapel HillNC27599 United States

Laboratory experimental results are presented for nonlinear internal solitary waves (ISW) propagation in ‘deep water’ configuration with miscible fluids. The results are validated against direct numerical simulations and traveling wave exact solutions where the effect of the diffused interface is taken into account. The waves are generated by means of a dam break and their evolution is recorded with laser-induced fluorescence and particle image velocimetry. In particular, data collected in a frame moving with the waves are presented here for the first time. Our results are representative of geophysical applications in the deep ocean where weakly nonlinear theories fail to capture the characteristics of large amplitude ISWs from field observations. © 2018, Springer Nature Switzerland AG.

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Grapenet_Lv1 for the Prediction of Optimum Hand-Picking Time of Nagano Purple Grapes

SSRN

引用

SSRN 2025年

作者： Islam, Md. Parvez Shinagawa, K. Hatou, K. Abdurrakhman, Arief Dian, K. Department of Biomechanical Systems Faculty of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan United Graduate School of Agriculture Ehime University 3-5-7 Tarumi Matsuyama790-8566 Japan Department of Instrumentation Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Business Mathematics Program Study School of Applied STEM Universitas Prasetiya Mulya BSD Campus BSD City Kav. Edutown I.1 Tangerang15339 Indonesia Indonesia

We investigated the optimum hand-picking time of Nagano Purple, a rare Japanese table grape variety. The color sensitivity between pure red–purple–black and pure purple–black makes it difficult for farmers to harvest these fruits at the right time while maintaining high sweetness level. We manually extracted 13 color parameters, namely, X, Y, Z, x, y, L*, a*, b*, L, a, b, C*, and h, from 355 grape skin samples using a colorimeter, which is a time-consuming and expensive process. In addition, we developed a 15-layer shallow long short-term memory (LSTM) and bidirectional long short-term memory (BLSTM) neural network, namely, GrapeNet_Lv1, with a learnable parameter of 1.39E+06. This network is compact and requires low computational cost for training. Furthermore, it has the ability to prevent the problems of vanishing gradient and overfitting. The combination of all the 13 aforementioned parameters yielded promising results in predicting color and sweetness levels, with test accuracies of 0.83 and 0.76, respectively. In the prediction of color level, our proposed network GrapeNet_Lv1 achieves a high validation accuracy of 0.92, F1 score of 0.88, recall of 0.87, low validation loss of 0.39, and RMSE of 0.31. However, in the prediction of sweetness level, GrapeNet_Lv1 achieves a relatively low validation accuracy of 0.79, F1 score of 0.70, recall of 0.69, high validation loss of 0.72, and RMSE of 0.33. Further research can help improve the accuracy. GrapeNet_Lv1 can be applied to other crops, where, predicting the whose optimal hand-picking time is difficult to predict based on color recognition. Keywords: Neural network;LSTM-BLSTM;Nagano Purple, color, sweetness © 2025, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

On the optimality system for a 1-d euler flow problem 6th

On the optimality system for a 1-d euler flow problem

引用

6th AIAA/NASA/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 1996

作者： Cliff, Eugene M. Heinkenschloss, Matthias Shenoy, Ajit R. Interdisciplinary Center for Applied Mathematics Virginia Tech BlacksburgVA24061 United States Interdisciplinary Center for Applied Mathematics Virginia Tech BlacksburgVA24061 United States Aerospace Engineering Department United States Mathematics Department United States

In this paper, a problem of shape design for a duct with the flow governed by the one-dimensional Euler equations is analyzed. The flow is assumed to be transonic, in the sense that we have a shock embedded in the flow. The presence of the shock introduces analytical and numerical difficulties that are overcome by introducing the shock location as an explicit state variable. We justify the use of adjoint variables by establishing conditions to ensure that the linearized constraint is surjective. These adjoint variables are used to state necessary optimality conditions and to compute gradients. In addition, our characterization of the adjoint variables is of interest for comparison to adjoints associated with shock-capturing formulations. © 1996 by the authors.

关键词： Computational fluid dynamics

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：