检索结果-内蒙古大学图书馆

IEEE Metrology for Aerospace

作者： Oleksii Siechko Anton Kitsera Roman Kochan Jerzy Józwik Arkadiusz Tofil Dariusz Mika Department of Specialized Computer Systems Lviv Polytechnic National University Lviv Ukraine Institute of Technical Sciences and Aviation The University College of Applied Sciences in Chelm Chelm Poland

ISBN: (数字)9798350385045

ISBN: (纸本)9798350385052

Acoustic methods of aircraft detection are an alternative method of airspace monitoring that was widely used in the pre-radar era and is now being developed again using new achievements in microelectronics, computer science, and communications. Turning the acoustic channel of an acoustic airspace monitoring system requires an investigation of the parameters of acoustic signals generated by aircraft. The significant number of existed aircrafts, as well as their acoustic signal variation depended of operating mode requires a huge amount of experiments. This paper utilizes the recordings posted on public video and audio data services to analyze acoustic signals. The essence of the analysis is a investigations the spectral composition of acoustic signals for seven classes of aircraft. The obtained results represent the frequency ranges of the three main harmonics of acoustic signals for each class of aircraft. The obtained results provide the possibility of frequency optimization of data acquisition channels of acoustic airspace monitoring systems.

关键词： Harmonic analysis Turning Acoustics Recording Aircraft Monitoring Power harmonic filters

来源：评论

学校读者我要写书评

暂无评论

Identification of driving factors of algal growth in the South-to-North Water Diversion Project by Transformer-based deep learning

引用

Water Biology and Security 2023年第3期2卷 47-56页

作者： Jing Qian Nan Pu Li Qian Xiaobai Xue Yonghong Bi Stefan Norra Institute of Applied Geosciences Karlsruhe Institute of TechnologyKarlsruhe76131Germany Institute of Advanced Computer Science Leiden UniversityLeiden2333CANetherlands Institute of Informatics Ludwig Maximilian University of MunichMunich80538Germany MioTech Research Yingtou Information Technology(Shanghai)LimitedShanghai200120China State Key Laboratory of Freshwater Ecology and Biotechnology Institute of HydrobiologyChinese Academy of SciencesWuhan430072China Institute of Environmental Sciences and Geography Soil Sciences and GeoecologyPotsdam University Potsdam-Golm14476Germany

Accurate and credible identification of the drivers of algal growth is essential for sustainable utilization and scientific management of *** this study,we developed a deep learning-based Transformer model,named Bloomformer-1,for end-to-end identification of the drivers of algal growth without the needing extensive a priori knowledge or prior *** Middle Route of the South-to-North Water Diversion Project(MRP)was used as the study site to demonstrate that Bloomformer-1 exhibited more robust performance(with the highest R^(2),0.80 to 0.94,and the lowest RMSE,0.22–0.43μg/L)compared to four widely used traditional machine learning models,namely extra trees regression(ETR),gradient boosting regression tree(GBRT),support vector regression(SVR),and multiple linear regression(MLR).In addition,Bloomformer-1 had higher interpretability(including higher transferability and understandability)than the four traditional machine learning models,which meant that it was trustworthy and the results could be directly applied to real ***,it was determined that total phosphorus(TP)was the most important driver for the MRP,especially in Henan section of the canal,although total nitrogen(TN)had the highest effect on algal growth in the Hebei *** on these results,phosphorus loading controlling in the whole MRP was proposed as an algal control strategy.

关键词： Algal growth Deep learning Driving factor determination Model interpretability Transformer

来源：评论

学校读者我要写书评

暂无评论

Classification of Nursing Care Activities Using Smartwatches

Classification of Nursing Care Activities Using Smartwatches

引用

Activity and Behavior Computing (ABC), International Conference on

作者： Sergio Staab Vincent Abt Henning Schmid Johannes Luderschmidt Mark Wetter Ludger Martin RheinMain University of Applied Sciences Wiesbaden Germany Fraunhofer Institute for Computer Graphics Research Darmstadt Germany Technical University of Darmstadt Darmstadt Germany

ISBN: (数字)9798350375503

ISBN: (纸本)9798350375510

Around 46.8 million people worldwide currently suffer from dementia. More than 7.7 million new cases occur every year. As the prevalence increases with age and our life expectancy trends more and more towards an older population, this can become a growing burden for care homes, the healthcare system and the public. Nursing homes are already suffering from a shortage of nursing staff. To make matters worse, nurses are overwhelmed by the increasing amount of care documentation that takes away their time to interact with and care for their patients. With this work, we therefore evaluate the performance of wearable sensors for automatic recognition and documentation of 10 common nursing tasks using machine learning. Our main goal is to reduce the documentation workload and allow the nursing staff to refocus on patient care by finding the most suitable, robust and accurate combination of sensors and machine learning algorithms for automatic documentation of nursing activities. We evaluated 12 machine learning algorithms using 3D motion data collected at the wrist. Our test data contains 10 activities and was generated in collaboration with two care communities using a Google Pixel Watch GQF4C. While there was no single best solution to classify all activity types, Fast Tree, Generalized Additive Models and Light Gradient Boosting Machine showed superior results compared to all other classifiers. Additional improvements could be achieved by dividing the activities into 3 main groups with best per group classifier types and implementing a quick model calibration ner user.

关键词： Wrist Machine learning algorithms Three-dimensional displays Medical services Documentation Market research Internet

来源：评论

学校读者我要写书评

暂无评论

Automatic Timetable Generation using Neural Networks Trained by Genetic Algorithms

Automatic Timetable Generation using Neural Networks Trained...

引用

International Conference on Open Source Systems and Technologies (ICOSST)

作者： Shaheer Abbas Ahmad Maaz Raja Hashim Ali Talha Ali Khan Iftikhar Ahmed Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi Pakistan Department of Business University of Europe for Applied Sciences Think Campus Potsdam Germany

ISBN: (数字)9798331508692

ISBN: (纸本)9798331508708

Scheduling is a crucial task in various real-life situations, including educational institutions where creating a feasible timetable is a complex challenge due to numerous constraints. The educational timetable scheduling problem is NP-hard, making it a difficult problem to solve optimally within reasonable time frames. Traditional methods like Genetic Algorithms (GAs) and Evolutionary Algorithms (EAs) have been applied to this problem with varying degrees of success. In this paper, we introduce a novel approach for automatic timetable generation using neural networks trained by genetic algorithms. Our method leverages the strengths of neural networks in pattern recognition and GAs in optimization to effectively handle the constraints and complexities of timetable scheduling. Experimental results demonstrate a significant improvement in scheduling accuracy and computational efficiency. We compare the performance of our proposed method with traditional GAs and demonstrate that the neural network approach trained by GAs achieves superior results in terms of speed and solution quality. This research paves the way for more efficient and intelligent scheduling systems in educational environments.

关键词： Training Processor scheduling Neural networks Manuals Scheduling Pattern recognition Optimization Tuning Genetic algorithms Overfitting

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of image super-resolution: A concurrent study of RGB and depth images

Comparative analysis of image super-resolution: A concurrent...

引用

International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa)

作者： Zhouyan Qiu Shang Zeng Joaquín Martínez Sánchez Pedro Arias Applied Geotechnology Group CINTECX Universidade de Vigo Vigo Spain Chinese Academy of Sciences Chengdu Institute of Computer Applications Chengdu China

ISBN: (数字)9798350365504

ISBN: (纸本)9798350365511

The introduction of deep learning has significantly advanced super-resolution techniques, allowing for the extraction of detailed textures and nuances vital for accurately analyzing visual information. The main contribution of our study is the development of the iDFD-SR dataset, an enhancement of the existing Indoor Depth from Defocus (iDFD) dataset [1], designed to evaluate super-resolution algorithms in the complex and varied indoor settings. Utilizing cutting-edge deep learning models such as EDSR (Enhanced Deep Super-Resolution Network), ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks), RDN (Residual Dense Network), LIIF (Local Implicit Image Function) and HAT (Hybrid Attention Transformer), we perform a thorough comparison across several datasets—All in Focus (AIF), Out of Focus (OOF), Raw Depth (DR), and Depth after In-Painting (DI)—to identify the strengths and challenges of each approach. Our findings demonstrate notable enhancements in image quality for both RGB and depth images. However, the research acknowledges limitations, notably its indoor setting focus and the extensive computational resources required. Future work aims to broaden the application of super-resolution techniques, increase computational efficiency, and enhance the accuracy of depth estimations.

关键词： Deep learning Visualization Accuracy Multimodal sensors Superresolution Refining Radar imaging Transformers Computational efficiency Indoor environment

来源：评论

学校读者我要写书评

暂无评论

StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection

arXiv

引用

arXiv 2024年

作者： Vosshans, Marcel Ait-Aider, Omar Mezouar, Youcef Enzweiler, Markus The Institute for Intelligent Systems The Faculty of Computer Science and Engineering University of Applied Sciences Esslingen Germany Universite Clermont Auvergne INP CNRS France

In this work, we present a novel approach for general object segmentation from a monocular image, eliminating the need for manually labeled training data and enabling rapid, straightforward training and adaptation with minimal data. Our model initially learns from LiDAR during the training process, which is subsequently removed from the system, allowing it to function solely on monocular imagery. This study leverages the concept of the Stixel-World to recognize a medium level representation of its surroundings. Our network directly predicts a 2D multi-layer Stixel-World and is capable of recognizing and locating multiple, superimposed objects within an image. Due to the scarcity of comparable works, we have divided the capabilities into modules and present a free space detection in our experiments section. Furthermore, we introduce an improved method for generating Stixels from LiDAR data, which we use as ground truth for our network. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Learned Image Compression With Text Quality Enhancement

Learned Image Compression With Text Quality Enhancement

引用

IEEE International Conference on Image Processing

作者： Chih-Yu Lai Dung Tran Kazuhito Koishida Massachusetts Institute of Technology Electrical Engineering and Computer Science Cambridge MA USA Microsoft Corporation Applied Sciences Group Redmond WA USA

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Learned image compression has gained widespread popularity for their efficiency in achieving ultra-low bit-rates. Yet, images containing substantial textual content, particularly screen-content images (SCI), often suffers from text distortion at such compressed levels. To address this, we propose to minimize a novel text logit loss designed to quantify the disparity in text between the original and reconstructed images, thereby improving the perceptual quality of the reconstructed text. Through rigorous experimentation across diverse datasets and employing state-of-the-art algorithms, our findings reveal significant enhancements in the quality of reconstructed text upon integration of the proposed loss function with appropriate weighting. Notably, we achieve a Bjontegaard delta (BD) rate of $-32.64 \%$ for Character Error Rate (CER) and $-28.03 \%$ for Word Error Rate (WER) on average by applying the text logit loss for two screenshot datasets. Additionally, we present quantitative metrics tailored for evaluating text quality in image compression tasks. Our findings underscore the efficacy and potential applicability of our proposed text logit loss function across various text-aware image compression contexts.

关键词： Measurement Visualization Image coding Error analysis Bit rate Distortion Task analysis

来源：评论

学校读者我要写书评

暂无评论

Safe and Secure? On the Timing Analysability of Cryptographic Implementations

Safe and Secure? On the Timing Analysability of Cryptographi...

引用

IEEE Symposium on Real-Time and Embedded Technology and Applications

作者： Alexander Stegmeier Peter Knauer Philipp Schubaur Christian Piatka Dominik Merli Sebastian Altmeyer Department of Computer Science University of Augsburg Augsburg Germany Augsburg Technical University of Applied Sciences Institute for Innovative Safety and Security Augsburg Germany

ISBN: (数字)9798350358414

ISBN: (纸本)9798350358421

Hard real-time systems are increasingly vulnerable to cyberattacks. Since real-time systems represent a significant proportion of safety-critical systems not only established safety standards but also security standards have to be considered. In particular, standard cryptographic libraries are required to reach an adequate level of protection. In this study, we investigate whether it is possible to en-sure security and hard real-time without compromising either side. Thus, we examine relevant state-of-the-art cryptographic primitives provided by one of the de-facto standard libraries Mbed TLS, which is widely-used in embedded systems. We investigate the possibility to derive a Worst-Case Execution Time (WCET) for these primitives and review the code base with regard to compliance on safety-related coding guidelines. In addition, we assess the relevant aspects when security concerns must be considered in the safety-related context. Our research reveals several obstacles to fully apply Mbed TLS in hard real- time systems.

关键词： Codes Embedded systems Libraries Real-time systems Encoding Safety Timing

来源：评论

学校读者我要写书评

暂无评论

computer-aided diagnosis of breast cancer from mammogram images using deep learning algorithms

引用

Journal of Electrical Systems and Information Technology 2024年第1期11卷 1-16页

作者： Dada, Emmanuel Gbenga Oyewola, David Opeoluwa Misra, Sanjay Department of Mathematical Sciences University of Maiduguri Maiduguri Nigeria Department of Mathematics and Computer Science Federal University Kashere Gombe Nigeria Department of Computer Science and Communication Østfold University College Halden Norway Department of Applied Data Science Institute for Energy Technology Halden Norway

Even though accurate detection of dangerous malignancies from mammogram images is mostly dependent on radiologists' experience, specialists occasionally differ in their assessments. computer-aided diagnosis provides a better solution for image diagnosis that can help experts make more reliable decisions. In medical applications for diagnosing cancerous growths from mammogram images, computerized and accurate classification of breast cancer mammogram images is critical. The deep learning approach has been widely applied in medical image processing and has had considerable success in biological image classification. The Convolutional Neural Network (CNN), Inception, and EfficientNet are proposed in this paper. The proposed models attain better performance compared to the conventional CNN. The models are used to automatically classify breast cancer mammogram images from Kaggle into benign and malignant. Simulation results demonstrated that EfficientNet, with an accuracy between 97.13 and 99.27%, and overall accuracy of 98.29%, perform better than the other models in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Interdisciplinary Framework for Systematic Innovation: A Case Study on Nature-Inspired Imaging Solutions

An Interdisciplinary Framework for Systematic Innovation: A ...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Nicolas Douard Ahmed Samet Denis Cavallucci George Giakos National Institute of Applied Sciences University of Strasbourg Strasbourg France Department of Electrical and Computer Engineering Manhattan University New York NY USA

ISBN: (数字)9798350378214

ISBN: (纸本)9798350378221

This research presents a novel interdisciplinary framework designed to uncover connections across diverse knowledge domains through advanced semantic modeling techniques. A case study focused on nature-inspired imaging solutions illustrates the potential of the framework. Innovation often emerges at the intersection of various scientific fields. However, manually identifying these intersections within the vast scientific literature is impractical. By exploring how biological principles can inspire the development of advanced imaging technologies, such as image sensors for rapid motion tracking, we underscore the critical role of interdisciplinary research in the promotion of technological innovation. Our framework systematically identifies and analyzes cross-domain connections, showcasing the potential of automated bioinspired approaches to drive innovation from the early stages. This research highlights how semantic modeling can bridge gaps between disparate fields, facilitating the discovery of novel insights, and fostering a more integrated approach to academic research. By automating the process of identifying relevant intersections within extensive literature, our framework not only enhances research efficiency, but also broadens the scope for innovative solutions. Ultimately, this work underscores the value of interdisciplinary collaboration and the transformative potential of bioinspired methodologies in the advancement of technology. The findings presented offer an actionable roadmap for leveraging semantic modeling to accelerate the pace of innovation in various domains.

关键词： Image sensors Bridges Technological innovation Systematics Tracking Animals Biological system modeling Semantics Collaboration Biomedical imaging

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：