检索结果-内蒙古大学图书馆

Open source ML framework algorithms for biophysical models

The European Physical Journal Special Topics 2025年 1-13页

作者： Andrikov, Denis A. Informatics and Control System Faculty Bauman Moscow State Technical University Moscow Russia

Biophysical models for processing multimodal data are mathematical computer program code and algorithms that integrate and process information from various sources (modalities), such as time series (e.g., biochemical indicators, electrocardiograms or electroencephalograms), genetic information, medical images, and other types of data to describe and understand complex biological processes. This article focuses on the application of open source AutoML framework algorithms for analyzing biophysical models. There are a lot of complex AutoML reviews out there. But none of them do not take into account biomedical/biophysical special fine-tuning and functional “out-of-the-box” procedures and code functionalities. It is the import areas such as processing cardiac signals, functional brain response, computer tomography, electronic medical/healthcare record’s textual data, and genetic information. By bridging the gap between machine learning automation and biophysical modeling, biophysical AutoML enables researchers to tackle complex biological problems with greater efficiency and accuracy. Research results confirm that Open source AutoML framework algorithms for biomed/biophysical models could improve diagnostic accuracy, reduce analysis time, and promote the development of personalized medicine, although further improvement of regulatory frameworks and validation methods is required.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning-Based Methodology for Detection of Postural Anomalies in Wheelchair Users

Unsupervised Learning-Based Methodology for Detection of Pos...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Vermander, Patrick Mancisidor, Aitziber Fortino, Giancarlo Cabanes, Itziar Gravina, Raffaele Department of Automatic Control and System Engineering Bilbao Spain Department of Informatics Modeling Electronics and Systems Engineering Rende Italy

ISBN: (纸本)9798350337020

Postural monitoring in wheelchair users is a topic of growing interest. The detection of changes in the sitting patterns of these patients may serve to detect changes in their functional status and be able to adapt rehabilitation early. For this reason, this paper presents a methodology for the detection of specific postural anomalies that, unlike previous works, adopts unsupervised learning. The proposed methodology involves data dimensionality reduction using Principal Component Analysis, and the application of K-means clustering to group different normal posture states. The anomalies are detected using a threshold approach, where data points that fall outside a certain threshold are considered as anomalies. The results show that the methodology is effective in identifying anomalies with a high degree of accuracy (around 90%). © 2023 IEEE.

关键词： Anomaly detection Kmeans PCA Postural monitoring Wheelchair

来源：评论

学校读者我要写书评

暂无评论

A Position-Force control Approach for an Underwater Vehicle-Manipulator system

A Position-Force Control Approach for an Underwater Vehicle-...

引用

2023 International Conference on Ocean Studies, ICOS 2023

作者： Kabanov, Aleksey A. Dementiev, Kirill V. Sevastopol State University Department of Informatics and Control in Technical Systems Sevastopol Russia Sevastopol State University Robotics and Intelligent Control System Laboratory Sevastopol Russia

ISBN: (纸本)9798350382457

The paper proposes an approach to position-force control in the underwater vehicle-manipulator systems. There are two different strategies to realize position-force control systems: through a decoupled or coupled controller. The first one is more flexible and is used in the present article as a PID-controllers array. The paper considers the generalized system design methodology applicable to control objects of any kinematic structure. Compensation blocks for manipulator disturbances and calculation of additional end-effector offset to maintain a constant force on the operating point are proposed. The system also utilizes the desired underwater vehicle position calculation based on the relativity of the vehicle position and operating point for a heading set point. The modeling results showed that the system is able to perform qualitatively force operations in a given point of the working space. In addition, the graphs revealed the compensator unit efficiency and confirmed the necessity of the additional offset calculation unit. © 2023 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

6-DOF AUV Identification with MIMO-NARX

6-DOF AUV Identification with MIMO-NARX

引用

2023 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2023

作者： Kabanov, Aleksey A. Lipko, Ivan Y. Dementiev, Kirill V. Sevastopol State University Department of Informatics and Control in Technical Systems Sevastopol Russia Sevastopol State University Robotics and Intelligent Control System Laboratory Sevastopol Russia

ISBN: (纸本)9781665475952

This paper applies the MIMO NARX neural model to identify AUV with six degrees of freedom. Strongly nonlinear dependencies are modeled using a MIMO NARX model trained using «input-output» experimental data. This results in a grey box model with a partially known internal structure that can be supervised. This is achieved by specifying a certain regressors type, which is feedback to the model input. Obtained results show that the neural model trained by the Levenberg-Marquardt numerical algorithm provides acceptable performance and accuracy. Validation of the model was performed using data from full-scale experiments, which allowed to identify the weaknesses and advantages of the resulting system more accurately. © 2023 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Features for Read Reference Voltage Estimation in NAND Flash Memory 13

Features for Read Reference Voltage Estimation in NAND Flash...

引用

13th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2023

作者： Bailon, Daniel Nicolas Shavgulidze, Sergo Freudenberger, Jurgen Institute for System Dynamics Htwg Konstanz University of Applied Sciences Germany Georgian Technical University Faculty of Informatics and Control Systems Georgia 06108 Germany

ISBN: (纸本)9798350324150

Reliability is a crucial aspect of non-volatile NAND flash memories, and it is essential to thoroughly analyze the channel to prevent errors and ensure accurate readout. Es-timating the read reference voltages (RRV s) is a significant challenge due to the multitude of physical effects involved. The question arises which features are useful and necessary for the RRV estimation. Various possible features require specialized hardware or specific readout techniques to be usable. In contrast we consider sparse histograms based on the decision thresholds for hard-input and soft-input decoding. These offer a distinct advantage as they are derived directly from the raw readout data without the need for decoding. This paper focuses on the information-theoretic study of different features, especially on the exploration of the mutual information (MI) between feature vector and RRV. In particular, we investigate the dependency of the MI on the resolution of the histograms. With respect to the RRV estimation, sparse histograms provide sufficient information for near-optimum estimation. © 2023 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Cell-wise encoding and decoding for TLC flash memories 12

Cell-wise encoding and decoding for TLC flash memories

引用

12th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2022

作者： Bailon, Daniel Nicolas Shavgulidze, Sergo Freudenberger, Jurgen University of Applied Sciences Institute for System Dynamics HTWG Konstanz Germany Georgian Technical University Faculty of Informatics and Control Systems Georgia

ISBN: (数字)9781665456760

ISBN: (纸本)9781665456760

Automotive computing applications like AI databases, ADAS, and advanced infotainment systems have a huge need for persistent memory. This trend requires NAND flash memories designed for extreme automotive environments. However, the error probability of NAND flash memories has increased in recent years due to higher memory density and production tolerances. Hence, strong error correction coding is needed to meet automotive storage requirements. Many errors can be corrected by soft decoding algorithms. However, soft decoding is very resource-intensive and should be avoided when possible. NAND flash memories are organized in pages, and the error correction codes are usually encoded page-wise to reduce the latency of random reads. This page-wise encoding does not reach the maximum achievable capacity. Reading soft information increases the channel capacity but at the cost of higher latency and power consumption. In this work, we consider cell-wise encoding, which also increases the capacity compared to page-wise encoding. We analyze the cell-wise processing of data in triple-level cell (TLC) NAND flash and show the performance gain when using Low-Density Parity-Check (LDPC) codes. In addition, we investigate a coding approach with page-wise encoding and cell-wise reading. © 2022 IEEE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Finding patterns in employee attrition rates using self-organizing Kohonen maps and decision trees

Finding patterns in employee attrition rates using self-orga...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2023

作者： Degtyareva, Ksenia Ageev, Daniel Alikhanovich Kukartsev, Vladislav Viktorovich Reshetnev Siberian State University of Science and Technology Department of Information Economic System Krasnoyarsk Russia Moscow State Technical University Informatics Artificial Intelligence and Control Systems Faculty Bauman Moscow Russia

ISBN: (纸本)9798350319200

This text presents a study of the causes of employee termination in organizations. Using employee data such as age, gender, marital status, monthly income, education, and others, an analysis was conducted using neural network algorithms (Kohonen maps) and Decision Trees. The results showed that both methods were suitable for analysis, but the neural network method showed the lowest error (7.4%). The analysis allowed to identify the most significant factors such as monthly income, age of employees, marital status and years of employment with the company. The analysis will help to optimize the process of predicting employee dismissal and save resources on unnecessary analyses. © 2023 IEEE.

关键词： data analysis data set economy finance Kohonen map

来源：评论

学校读者我要写书评

暂无评论

Pallet Detection and Distance Estimation with YOLO and Fiducial Marker Algorithm in Industrial Forklift Robot

Pallet Detection and Distance Estimation with YOLO and Fiduc...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Eric Sean Kesuma Pranoto Hidaya Rusmin Devira Anggi Maharani Control and Computer System Research Group School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

Utilising technology such as artificial intelligence and robotics potentially improves E-Commerce in efficiency. In this trends, the usage of autonomous forklifts in the warehouse to lift and arrange things should be implemented. The picking system in the warehouse needs pallet detection and tracking to carry out the things. This research will find the best performance of the YOLOv5 model and correct the distance estimation model to the fiducial marker. In this paper, we used the ArUco fiducial marker to mark the pallet target and estimate the pose and distance in real time. The insertion points of the pallet were also detected using the YOLOv5 algorithm to validate the pallet and get the coordinate variables of the holes. The YOLOv5n gives the best performance at 24 fps in real-time detection. Distance measurement from the marker detection had an average error of 2.28 cm with linear regression.

关键词： Robot kinematics Linear regression Transportation Cameras Fiducial markers Real-time systems Distance measurement

来源：评论

学校读者我要写书评

暂无评论

Estimating Mutual Information for Link Adaptation in Generalized Spatial Modulation systems with Neural Networks 26

Estimating Mutual Information for Link Adaptation in General...

引用

26th International ITG Workshop on Smart Antennas, WSA 2023 and 13th Conference on systems, Communications, and Coding, SCC 2023

作者： Bailon, Daniel Nicolas Kühn, Volker Shavgulidze, Sergo Freudenberger, Jürgen Institute for System Dynamics HTWG Konstanz University of Applied Sciences Germany Institute of Communications Engineering Faculty of Computer Science and Electrical Engineering University of Rostock Germany Faculty of Informatics and Control Systems Georgian Technical University Georgia Germany

ISBN: (纸本)9783800760510

Spatial modulation (SM) is a low-complexity multiple-input/multiple-output transmission technique that combines index modulation and quadrature amplitude modulation for wireless communications. In this work, we consider the problem of link adaption for generalized spatial modulation (GSM) systems that use multiple active transmit antennas simultaneously. Link adaption algorithms require a real-time estimation of the link quality of the time-variant communication channels, e.g., by means of estimating the mutual information. However, determining the mutual information of SM is challenging because no closed-form expressions have been found so far. Recently, multilayer feedforward neural networks were applied to compute the achievable rate of an index modulation link. However, only a small SM system with two transmit and two receive antennas was considered. In this work, we consider a similar approach but investigate larger GSM systems with multiple active antennas. We analyze the portions of mutual information related to antenna selection and the IQ modulation processes, which depend on the GSM variant and the signal constellation. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Neural network aided reference voltage adaptation for NAND flash memory 12

Neural network aided reference voltage adaptation for NAND f...

引用

12th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2022

作者： Bailon, Daniel Nicolas Taburet, Guillaume Shavgulidze, Sergo Freudenberger, Jurgen HTWG Konstanz University of Applied Sciences Institute for System Dynamics Germany ENSICAEN Engineering School France Georgian Technical University Faculty of Informatics and Control Systems Georgia

ISBN: (数字)9781665456760

ISBN: (纸本)9781665456760

Large persistent memory is crucial for many applications in embedded systems and automotive computing like AI databases, ADAS, and cutting-edge infotainment systems. Such applications require reliable NAND flash memories made for harsh automotive conditions. However, due to high memory densities and production tolerances, the error probability of NAND flash memories has risen. As the number of program/erase cycles and the data retention times increase, non-volatile NAND flash memories' performance and dependability suffer. The read reference voltages of the flash cells vary due to these aging processes. In this work, we consider the issue of reference voltage adaption. The considered estimation procedure uses shallow neural networks to estimate the read reference voltages for different life-cycle conditions with the help of histogram measurements. We demonstrate that the training data for the neural networks can be enhanced by using shifted histograms, i.e., a training of the neural networks is possible based on a few measurements of some extreme points used as training data. The trained neural networks generalize well for other life-cycle conditions. © 2022 IEEE.

关键词： Life cycle

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：