检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Benko, Matúš Mehlitz, Patrick Johann Radon Institute for Computational and Applied Mathematics Linz4040 Austria Philipps-Universität Marburg Department of Mathematics and Computer Science Marburg35032 Germany

In this paper, we characterize Lipschitzian properties of different multiplier-free and multiplier-dependent perturbation mappings associated with the stationarity system of a so-called generalized nonlinear program popularized by Rockafellar. Special emphasis is put on the investigation of the isolated calmness property at and around a point. The latter is decisive for the locally fast convergence of the so-called semismooth* Newton-type method by Gfrerer and Outrata. Our central result is the characterization of the isolated calmness at a point of a multiplier-free perturbation mapping via a combination of an explicit condition and a rather mild assumption, automatically satisfied e.g. for standard nonlinear programs. Isolated calmness around a point is characterized analogously by a combination of two stronger conditions. These findings are then related to so-called criticality of Lagrange multipliers, as introduced by Izmailov and extended to generalized nonlinear programming by Mordukhovich and Sarabi. We derive a new sufficient condition (a characterization for some problem classes) of nonexistence of critical multipliers, which has been also used in the literature as an assumption to guarantee local fast convergence of Newton-, SQP-, or multiplier-penalty-type methods. The obtained insights about critical multipliers seem to complement the vast literature on the *** Codes 49J52, 49J53, 90C30 © 2024, CC BY-NC-SA.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

Reconfigurations of Plane Caterpillars and Paths

arXiv

引用

arXiv 2024年

作者： Antić, Todor Quintero, Guillermo Gamboa Glišić, Jelena Department of Applied Mathematics Charles University Prague Czech Republic Computer Science Institute of Charles University Prague Czech Republic

Let S be a point set in the plane, P(S) and C(S) sets of all plane spanning paths and caterpillars on S. We study reconfiguration operations on P(S) and C(S). In particular, we prove that all of the commonly studied reconfigurations on plane spanning trees still yield connected reconfiguration graphs for caterpillars when S is in convex position. If S is in general position, we show that the rotation, compatible flip and flip graphs of C(S) are connected while the slide graph is disconnected. For paths, we prove the existence of a connected component of size at least 2n−1 and that no component of size at most 7 can exist in the flip graph on P(S).MSC Codes 05C10 (Primary) 68R10 (Secondary) Copyright © 2024, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Modeling and Nonlinear Predictive Control of Solar Thermal Systems in District Heating

SSRN

引用

SSRN 2024年

作者： Lorenz Svensen, Jan Bergsteinsson, Hjörleifur G. Madsen, Henrik Department of Applied Mathematics and Computer Science Technical University of Denmark Richard Petersens Plads 324 Kongens Lyngby2800 Denmark

This study presents data-driven modeling and nonlinear model predictive control of solar thermal plants in district heating. The study considers the efficient operation of a solar thermal plant in Hillerød, Denmark. The dynamic model is presented using grey-box modeling and real-world *** objectives are considered in the design of nonlinear model predictive controllers;e.g., maximizing energy or *** study also provides simulations for analyzing the model fitness and controller *** model is shown to fit the daytime operation of the plant. The designed controllers are shown to improve efficiency, increasing the transported energy up to 28%. © 2024, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Complex Activity Recognition Based on Wrist-Worn Sensor 38

Deep Learning Networks for Complex Activity Recognition Base...

引用

38th IEEE Region 10 Conference, TENCON 2023

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

ISBN: (纸本)9798350302196

Wearable smart devices, such as smartphones and smartwatches, offer great potential as platforms for automated human action identification. However, accurately monitoring complex human actions on these devices poses a challenge due to the presence of similarities in patterns across different actions. This occurs when distinct human actions exhibit comparable signal patterns or characteristics. The placement of motion sensors on the body plays a crucial role in detecting human behavior. Typically, wearable sensors placed at the trouser pocket or a similar location are used for this purpose. However, this positioning is not suitable for identifying actions involving manual gestures. To address this, wrist-worn motion sensors are employed to detect these specific behaviors. This study aims to investigate the effectiveness of deep learning models in accurately categorizing complex human actions using sensor data from wrist-worn devices. Nine deep learning models utilizing convolutional neural networks and recurrent neural networks were examined for their identification capabilities. The models were evaluated using the WHARF dataset, a publicly available benchmark dataset for human activity recognition. The investigation revealed that the proposed CNN-BiGRU model outperformed other deep learning models, achieving an accuracy rate of 87.20% and an Fl-score of 84.46%. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

A General Recipe for Contractive Graph Neural Networks - Technical Report

arXiv

引用

arXiv 2024年

作者： Bechler-Speicher, Maya Eliasof, Moshe Blavatnik School of Computer Science Tel-Aviv University Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom

Graph Neural Networks (GNNs) have gained significant popularity for learning representations of graph-structured data due to their expressive power and scalability. However, despite their success in domains such as social network analysis, recommendation systems, and bioinformatics, GNNs often face challenges related to stability, generalization, and robustness to noise and adversarial attacks. Regularization techniques have shown promise in addressing these challenges by controlling model complexity and improving robustness. Building on recent advancements in contractive GNN architectures, this paper presents a novel method for inducing contractive behavior in any GNN through SVD regularization. By deriving a sufficient condition for contractiveness in the update step and applying constraints on network parameters, we demonstrate the impact of SVD regularization on the Lipschitz constant of GNNs. Our findings highlight the role of SVD regularization in enhancing the stability and generalization of GNNs, contributing to the development of more robust graph-based learning algorithms dynamics. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving EEG-Based Epileptic Seizures Detection Using Self-Normalizing Neural Network 4

Improving EEG-Based Epileptic Seizures Detection Using Self-...

引用

4th International Conference on Big Data Analytics and Practices, IBDAP 2023

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

ISBN: (纸本)9798350300192

Epilepsy, a neurological disorder, is typically identified by analyzing electroencephalogram (EEG) signals. However, manually inspecting epileptic seizures is a time-consuming and labor-intensive task. Previous automatic detection algorithms utilizing traditional methods have demonstrated good accuracy in specific EEG classification scenarios but have shown poor performance in others. To tackle this challenge, our study introduces a new deep learning model called the self-normalizing neural network. This model leverages convolutional neural networks and recurrent neural networks to enhance the detection of epileptic seizures using EEG signals. To evaluate our approach, we designed and assessed the proposed detection model using a publicly available Epileptic Seizures Recognition Dataset (ESRD). The experimental findings indicate that the self-normalizing neural network achieves a performance improvement of up to 1.03% accuracy and 1.78% F1-score in epileptic seizure detection, surpassing traditional convolutional neural network approaches. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Cloud-Computing Trend Analysis of Urbanization Impacts on Land Surface Temperature and Electricity Demand in Gaborone, Botswana

引用

Remote Sensing in Earth Systems sciences 2024年第1期8卷 283-306页

作者： Moyo, Boineelo Schröder, Dietrich Moreri, Kealeboga Institute for living conditions in rural areas Johann Heinrich von Thuenen-Institut Bundesallee 50 Lower Saxony Braunschweig 38116 Germany Department of Geomatics Computer Science and Mathematics Stuttgart University of Applied Sciences Schellingstr. 24 Baden-Wuerttemberg Stuttgart 70174 Germany Department of Civil Engineering University of Botswana Notwane Rd Gaborone Botswana

Land use land cover (LULC) changes are critical drivers of global environmental changes, profoundly impacting sustainability in rapidly urbanizing regions. In urban areas, where vegetation cover is reduced, LULC changes significantly affect the distribution and intensity of Land Surface Temperature (LST), which in turn influences electricity demand and consumption. This study explores the relationship between urbanization, vegetation loss, surface temperature and electricity demand in Gaborone, Botswana. The study utilized the Landsat data to conduct a 15-year (2005–2020) spatio-temporal analysis of LULC changes and LST dynamics, identified surface urban heat islands (SUHI) using the Getis-Ord Gi* hot-spot analysis and assessed the correlation between LST and key spectral indices adopted in the study. The analysis employed Google Earth Engine (GEE) cloud computing platform and the Random Forest (RF) machine learning algorithm, known for their accuracy and efficiency in classification and change detection studies. Findings reveal substantial LULC transformations in Gaborone with approximately 12 km² of land converted to Built-Up areas, driving a 2.36% annual urban growth rate and shrinking green and bare spaces. Consequently, surface temperatures rose by about 2.1 °C, impacting energy demand, particularly for cooling during hot summers. This demand surge, coupled with urban expansion, has fueled higher electricity prices, posing new challenges in climate adaptation and mitigation. The study provides critical insights into the interplay between urbanization, rising temperatures, and energy consumption in Gaborone. These insights highlight the urgent need for developing sustainable urban planning and energy strategies to address the impacts of climate change, land degradation, and energy poverty. © The Author(s) 2024.

关键词： Climate change Electricity demand Google earth engine Land surface temperature Land use land cover Random forest

来源：评论

学校读者我要写书评

暂无评论

Improving Lower Limb Activity Recognition Based on Inertial Sensors using CNN-LSTM Network 4

Improving Lower Limb Activity Recognition Based on Inertial ...

引用

4th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2023

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9798350330618

The utilization of wearable sensors has gained significant popularity across various domains. This widespread adoption has driven the need for advancements in sensor technology, focusing on attributes such as lightweight design, dependability, and integration capabilities. One specific area where wearable sensor networks have faced challenges is in human activity recognition, particularly in accurately inferring movement data. The effectiveness of this process depends on several factors, such as the quality of sensor-derived features, the discriminatory power of selected features, and the chosen classification methodology. To address these challenges, this research introduces a novel hybrid deep learning architecture called CNN-LSTM. The primary goal of this architecture is to enhance the accuracy of recognizing human lower limb movement. To evaluate the effectiveness of the proposed model, a series of investigations were conducted using the publicly available HuGaDB dataset. This dataset consists of data collected from a body sensor network comprising six wearable inertial sensors, including accelerometers and gyroscopes. These sensors were positioned on both the right and left thighs, shins, and feet. The outcomes of the investigation demonstrated that the suggested model achieved an impressive precision of 97.81% and a maximum F1-score of 95.50%. These results highlight the effectiveness of the CNN-LSTM model in accurately recognizing human lower limb movement. ©2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Residual Neural Network for Aggressive Physical Activity Recognition Using Surface Electromyography Sensors 14

Deep Residual Neural Network for Aggressive Physical Activit...

引用

14th IEEE International Conference on Software Engineering and Service science, ICSESS 2023

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

ISBN: (纸本)9798350336269

Wearable sensors and machine learning have opened new doors for innovative automated systems. Smart wearables like smartwatches and wristbands can efficiently record human movements due to their integrated, compact sensors. This data collection is vital for understanding human behavior, a field known as human activity recognition (HAR), dedicated to classifying actions. Deep learning methods, which autonomously extract intricate features, have shown promise in HAR. Sensor-based HAR is extensively studied in academia and applied across domains like wellness tracking, medical diagnosis, and mobility analysis. However, challenges persist in detecting complex activities. Our study focuses on recognizing aggressive behaviors through surface electromyography (sEMG) sensor data analysis. We introduce ResNeXt, a novel deep neural network, to improve recognition accuracy. Through a series of tests, we evaluate ResNeXt's recognition capabilities and compare its results to other deep learning models. Our experiments reveal that ResNeXt outperforms other models, achieving an impressive 94.06% overall accuracy and an exceptional 97.68% accuracy in distinguishing normal from aggressive actions. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Attention Based Hybrid Deep Learning Network for Locomotive Mode Recognition in Natural Environments Using Wearable Sensors 4

Attention Based Hybrid Deep Learning Network for Locomotive ...

引用

4th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2023

ISBN: (纸本)9798350330618

The field of pervasive computing encompasses the significant domain of study known as WS-LMR, which focuses on identifying locomotive modes through wearable sensors. WS-LMR aims to automatically evaluate and interpret individual locomotive actions along with contextual information using wearable sensor data. This technology finds applications in medical surveillance systems and various systems involving interactions between individuals and intelligent wearable devices. However, existing WS-LMR algorithms are often evaluated using data collected under controlled conditions, limiting their effectiveness in uncontrolled real-world environments. This scholarly article addresses the primary objective of identifying human locomotion activities in real-world contexts. To enhance the efficacy of the WS-LMR system, our study proposes the utilization of an attention-based hybrid deep learning network that combines convolutional neural network and long-short term memory networks, referred to as the Att-CNN-LSTM model. We evaluated the performance of the proposed network using the publicly available Bath Natural Environment HAR dataset, a benchmark LMR dataset. Both model training and testing were conducted using a 5-fold cross-validation approach. The Att-CNN-LSTM model achieved the highest accuracy of 94.25% and an F1-score of 91.47% based on the results obtained from multiple experiments. ©2023 IEEE.

关键词： Benchmarking

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：