检索结果-内蒙古大学图书馆

Computational Optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress

作者： Aquilina, Matthias Sola, Alex Vicente Kirkland, Paul Lyons, Ashley Extreme Light Group Advanced Research Centre University of Glasgow Glasgow United Kingdom Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing University of Strathclyde Glasgow United Kingdom

We present a novel spiking neural network approach to building 3D LiDAR images from temporal information alone. Our method uses the "spike" events from individually detected photons without the need to const... 详细信息

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Personalized Game Design for Balance Rehabilitation in Multiple Sclerosis: Insights from Neuroimaging and Neurophysiological Test

Personalized Game Design for Balance Rehabilitation in Multi...

引用

2024 IEEE International Conference on Smart Systems and Power Management, IC2SPM 2024

作者： Ibrahim, Hiyam Diab, Ahmad Khalil, Mohamad Guardiola, Emmanuel Doctoral School of Sciences and Technology Lebanese University Beirut Lebanon Cologne University of Applied Sciences Cologne Game Lab Cologne Germany Lebanese International University Signal Processing Research Group Biomedical Engineering Department Tripoli Lebanon Signal Processing Research Group Biomedical Engineering Department Beirut Lebanon

ISBN: (纸本)9798331529796

The application of exergames as tools for balance rehabilitation in patients with multiple sclerosis (PwMS) has demonstrated promising results. However, despite these findings, the efficacy of these games remains inconclusive, largely due to the reliance on commercially available games. This highlights the necessity for the design of personalized games that better address patients' needs. The development of such games requires an understanding of the mechanisms underlying balance dysfunction in PwMS. Previous research has identified impairments in sensory integration and reweighting process among the key contributors to this issue. These observations were based on correlations between balance measures and both neuroimaging and neurophysiological test findings from various regions of the central nervous system (CNS). Consequently, this study aimed to develop a personalized game that specifically targets impairments in sensory integration and reweighting process, thereby addressing these limitations and observations noted in the existing knowledge. Our objective was accomplished utilizing Unity, a three-dimensional game engine widely employed in video game development. As a result, we developed a game prototype that incorporates specific in-game features designed to facilitate balance training under varying sensory conditions, such as eyes-open and eyes-closed conditions. The incorporation of these features into the game design has the potential to improve rehabilitation outcomes, thereby contributing to advancements in both the fields of game design and neurorehabilitation. Future research will evaluate the effectiveness of the game prototype in improving balance control under variable sensory conditions. © 2024 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Classification of large and heterogeneous LiDAR data sets

Classification of large and heterogeneous LiDAR data sets

引用

2023 Designing Futures: Zukunfte gestalten, INFORMATIK 2023 - 2023 Designing Futures: Shaping the Future, INFORMATIK 2023

作者： Kaubukowski, Kenn Nsonga, Baldwin Kretzschmar, Vanessa Annanias, Yves Wiegreffe, Daniel Hlawitschka, Mario LeipzigUniversity of Applied Sciences Chair of Computer Graphics Karl-Liebknecht-Straße 132 Leipzig04277 Germany Leipzig University Image and Signal Processing Group Augustusplatz 10 Leipzig04109 Germany

ISBN: (纸本)9783885797319

In the context of the renaturation of discontinued open-cast mines, the interactive visualization analysis of three-dimensional LiDAR provides a comprehensive overview for planning the subsequent use of these areas. When analyzing the measured point clouds, it is beneficial to classify the points, enabling the user to filter objects such as vehicles and buildings. Most current classification techniques for LiDAR data rely on good ground truth and work on specific types of measurements and resolutions. In this work, we present a semantic classification workflow for LiDAR data with highly heterogeneous acquisition and storage parameters. We apply the workflow to a freely available LiDAR data set and showcase the resulting classification. Our method is shown to reliably classify not only large-scale objects, such as buildings, but also small-scale objects, such as power lines and street lights. © 2023 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning-based salp swarm algorithm for fault diagnosis of photovoltaic systems

引用

Journal of Engineering and applied Science 2024年第1期71卷 12页

作者： Hichri, Amal Hajji, Mansour Mansouri, Majdi Nounou, Hazem Bouzrara, Kais Research Unit Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kairouan Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Laboratory of Automatic Signal and Image Processing National School of Engineers of Monastir University of Monastir Monastir5019 Tunisia

The diagnosis of faults in grid-connected photovoltaic (GCPV) systems is a challenging task due to their complex nature and the high similarity between faults. To address this issue, we propose a wrapper approach called the salp swarm algorithm (SSA) for feature selection. The main objective of SSA is to extract only the most important features from the raw data and eliminate unnecessary ones to improve the classification accuracy of supervised machine learning (SML) classifiers. Subsequently, the selected features are used to train supervised machine learning (SML) techniques in distinguishing between various operating modes. To evaluate the efficiency of the technique, we used healthy and faulty data from GCPV systems that have been injected with frequent faults, 20 different types of faults were introduced, including line-to-line, line-to-ground, connectivity faults, and those affecting the operation of bay-pass diodes. These faults present diverse conditions, such as simple and multiple faults in the PV arrays and mixed faults in both arrays. The performances of the developed SSA-SML are compared with those using principal component analysis (PCA) and kernel PCA (KPCA) based SML techniques through different criteria (i.e., accuracy, recall, precision, F1 score, and computation time). The experimental findings demonstrated that the proposed diagnosis paradigm outperformed the other techniques and achieved a high diagnostic accuracy (an average accuracy greater than 99%) while significantly reducing computation time. © 2023, The Author(s).

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

On Visualizing Music Storage Media for Modern Access to Historic Sources

On Visualizing Music Storage Media for Modern Access to Hist...

引用

24th Eurographics Conference on Visualization, EuroVis 2022

作者： Khulusi, R. Fricke, H. Image and Signal Processing Group Leipzig University Germany Research Center Digital Organology Leipzig University Germany

ISBN: (纸本)9783038681854

Finding a balance between conserving historic objects and using them for research is one of the big issues in historic collections. Digitization holds the opportunity to offer a safe and non-destructible access to historic objects, making them available for research. With this poster, we want to give insight into our planned visualization system, using close and distant reading access for visual analysis approaches and allowing musicologists novel approaches to normally fragile and endangered media. © 2022 The Author(s) Eurographics Proceedings © 2022 The Eurographics Association.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Geometric Correction and Mosaic Generation of Geo High Resolution Camera images

arXiv

引用

arXiv 2024年

作者： Garg, Ankur Thapa, Nitesh Sangar, Ghansham Gaur, Neha Sarkar, Meenakshi Moorthi, S. Manthira Dhar, Debajyoti Signal and Image Processing Group Space Applications Center Indian Space Research Organisation Ahmedabad380015 India

The Geo High Resolution Camera (GHRC) aboard the GSAT-29 satellite, operated by the Indian Space research Organization (ISRO), is a cutting-edge 6-band Visible and Near Infrared (VNIR) imager positioned in geostationary orbit at 55°E longitude. It achieves a ground sampling distance of 55 meters at nadir and covers an instantaneous area of 110x110 km, capturing imagery of the entire Earth’s disk thanks to its scan mirror mechanism. To comprehensively cover India, the GHRC employs a two-dimensional raster scanning technique, resulting in over 1,000 scenes that need to be skillfully stitched together into a seamless mosaic. This paper outlines the geolocation model and identifies potential sources of error affecting targeting accuracy. It also conducts an evaluation of the location accuracies. Challenges related to inter-band registration and inter-frame mosaicing with the GHRC are addressed. Several algorithms have been devised to address geometric correction, band-to-band registration, and seamless mosaic generation. Notably, adjustments to the instrument’s interior alignment angles, guided by ground reference images during in-flight geometric calibration, have significantly improved pointing and location precision. A groundbreaking backtracking algorithm has been developed to rectify frame-to-frame mosaicing errors for large-scale mosaic generation. This algorithm harnesses a combination of geometric models, advanced image processing techniques, and space resection. As a result of these advancements, operational generation of full India mosaics with 100-meter resolution and high geometric fidelity is now a reality. These accomplishments mark substantial progress in the capabilities of the GHRC and hold profound implications for applications in Earth observation and monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

Advancements in Data processing and Calibration for the Hyperspectral Imaging Satellite (HySIS)

arXiv

引用

arXiv 2024年

作者： Garg, Ankur Patil, Abhishek Sarkar, Meenakshi Moorthi, S. Manthira Dhar, Debajyoti Signal and Image Processing Group Space Applications Center Indian Space Research Organisation Ahmedabad380015 India

Hyperspectral imaging stands as a powerful tool in Earth exploration, owing to its exceptional ability to discern intricate spectral features. India has harnessed this capability through the launch of a dedicated hyperspectral earth observation satellite. This satellite is designed to scrutinize the Earth’s surface across a broad electromagnetic spectrum range spanning from 400 nm to 2500 nm, capturing an extensive array of spectral information. One of the key strengths of this satellite lies in its impressive spatial sampling resolution of 30 meters. This high resolution further amplifies its imaging prowess, enabling it to capture detailed and accurate data about the Earth’s surface features. This paper offers a comprehensive account of the meticulous calibration procedures that were meticulously executed during the pre-launch phase. Calibration is a critical process in ensuring the accuracy and reliability of the data captured by the satellite. This involved a series of precise adjustments and measurements to fine-tune the satellite’s imaging instruments, ensuring that they were operating at their optimal levels. The paper also highlights the achieved performance metrics, showcasing the satellite’s capability to deliver high-quality, detailed imagery of the Earth’s surface. These metrics serve as a testament to the effectiveness of the calibration procedures carried out prior to the satellite’s launch. Furthermore, the paper outlines the rigorous in-orbit radiometric and geometric calibration and validation endeavors that were conducted during the commissioning phase of the mission. This phase involved further fine-tuning and validation of the satellite’s instruments in the actual space environment. It ensured that the satellite was operating accurately and reliably in orbit, ready to fulfill its mission objectives. In addition, the paper sheds light on the observations made and anomalies encountered during the in-orbit phase. These observations provide valuable

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Spatial Super-Resolution using Keystone Error

arXiv

引用

arXiv 2024年

作者： Garg, Ankur Sarkar, Meenakshi Moorthi, S. Manthira Dhar, Debajyoti Signal and Image Processing Group Space Applications Center Indian Space Research Organisation Ahmedabad380015 India

Hyperspectral images aid in precise identification of objects on ground by measuring their signatures with very fine spectral resolution. If such images have high spatial resolution, it further boosts this ability. Increasing the spatial resolution with hardware by making use of bigger telescopes is a very costly affair in terms of the resources needed which makes the overall system optimization suffer. In comparison, increasing the spatial resolution with ground processing is the most optimal solution to handle this obstacle. Generally, to get advantage of both high spectral and spatial resolution data, hypersharpening approaches are used to merge high spectral resolution data with high spatial resolution. The approach gives good results when the two datasets have been acquired within very short time frame leading to similar atmospheric, viewing imaging conditions. This is usually possible when both high spectral and spatial resolution sensors are imaging from same platform. But using datasets from different dates and time often leads to radiometric artifacts which degrade the final image quality. In this work, we propose an approach to increase the spatial resolution of hyperspectral data without making use of any auxiliary input. The two key inputs for increasing the spatial resolution via superresolution algorithms are the high resolution point spread function and the sub-pixel shifts. For grating based hyperspectral sensors, misregistration between spectral channels occur due to instrument intrinsic keystone error which leads to sub-pixel shifts between spectral channels that vary across the spatial field of view. But the high resolution blur for such systems is seldom known due to the dynamic nature of the intervening atmosphere and platform jitter. Also, the optics blur for each channel differs due to differing wavelengths. To handle this dynamic effect, we first estimate the point spread function from lower resolution image using blind deconvolution and corr

关键词： Spectral resolution

来源：评论

学校读者我要写书评

暂无评论

Implementation and Performance Analysis of FFT and Inverse FFT Using Openmp, MPI and Hybrid Programming on Virtual SMP/HPC Architecture 1

引用

53rd Annual Convention of the Computer Society of India, CSI 2020

作者： Singla, Jai G. Padia, Kirti Signal and Image Processing Group Space Applications Centre Indian Space Research Organization Ahmedabad India

ISBN: (数字)9789811627231

ISBN: (纸本)9789811627224

A Fast Fourier transform (FFT) algorithm computes the discrete Fourier transform (DFT) of a sequence, or it’s inverse. Fourier analysis converts a signal from its original domain (often time or space) to a representation in the frequency domain and vice versa. An FFT rapidly computes such transformations by factorizing the DFT matrix into a product of sparse (mostly zero) factors. Fast Fourier transforms are widely used for many applications in engineering, science, and mathematics & signal and image processing. As, FFT remains a time consuming task on limited core machine and with a larger data set, we intended to implement this Fourier transformation technique on virtual SMP (HPC) with 144 CPU cores setup to improve the timings or to simultaneously handle multiple data sets. This paper consists of details about vSMP architecture designed by Scalemp [1], programming paradigms used, implementation details, performance and scalability analysis of Fast Fourier Transformation (FFT) on virtual Symmetric multiprocessor system (vSMP) using programming paradigms such as openMP, MPI and Hybrid programming, results and observations. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

A Novel Diagnostic Model for Early Detection of Alzheimer’s Disease Based on Clinical and Neuroimaging Features 11th

A Novel Diagnostic Model for Early Detection of Alzheimer’s...

引用

11th International Conference on Model and Data Engineering, MEDI 2022

作者： Gad, Eyad Gamal, Aya Elattar, Mustafa Selim, Sahar School of Engineering and Applied Sciences Nile University Giza Egypt Medical Imaging and Image Processing Research Group Center for Informatics Science Nile University Giza Egypt School of Information Technology and Computer Science Nile University Giza Egypt

ISBN: (纸本)9783031215940

Alzheimer’s Disease (AD) is a dangerous disease that is known for its characteristics of eroding memory and destroying the brain. The classification of Alzheimer's disease is an important topic that has recently been addressed by many studies using Machine Learning (ML) and Deep Learning (DL) methods. Most research papers tackling early diagnosis of AD use these methods as a feature extractor for neuroimaging data. In our research paper, the proposed algorithm is to optimize the performance of the prediction of early diagnosis from the multimodal dataset by a multi-step framework that uses a Deep Neural Network (DNN) as an optimization technique to extract features and train these features by Random Forest (RF) classifier. The results of the proposed algorithm showed that using only demographic and clinical data results in a balanced accuracy of 88% and an area under the curve (AUC) of 94.6. Ultimately, combining clinical and neuroimaging features, prediction results improved further to a balanced accuracy of 92% and an AUC of 97%. This study successfully outperformed other studies for both clinical and the combination of clinical and neuroimaging data, proving that multimodal data is efficient in the early diagnosis of AD. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Neuroimaging

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：