检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Belenguer-Llorens, Albert Sevilla-Salcedo, Carlos Tohka, Jussi Gómez-Verdejo, Vanessa Department of Signal Processing and Communications Universidad Carlos III de Madrid Leganés28911 Spain Department of Computer Science Aalto University Espoo02150 Finland Madrid28009 Spain

We present BALDUR, a novel Bayesian algorithm designed to deal with multi-modal datasets and small sample sizes in high-dimensional settings while providing explainable solutions. To do so, the proposed model combines within a common latent space the different data views to extract the relevant information to solve the classification task and prune out the irrelevant/redundant features/data views. Furthermore, to provide generalizable solutions in small sample size scenarios, BALDUR efficiently integrates dual kernels over the views with a small sample-to-feature ratio. Finally, its linear nature ensures the explainability of the model outcomes, allowing its use for biomarker identification. This model was tested over two different neurodegeneration datasets, outperforming the state-of-the-art models and detecting features aligned with markers already described in the scientific literature. © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Unified Bayesian representation for high-dimensional multi-modal biomedical data for small-sample classification

arXiv

引用

arXiv 2024年

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Integrating HL7 FHIR into Clinical Decision Support Systems: A Real-World Application with Pepper Humanoid Robot in Hospital During Doctor Visits 9

Integrating HL7 FHIR into Clinical Decision Support Systems:...

引用

9th International Conference on Mathematics and computers in sciences and Industry, MCSI 2024

作者： Safran, Valentino Horvat, Samo Ilijevec, Bojan Roj, Igor Rober Flis, Vojko Mlakar, Izidor University of Maribor Faculty of Electrical Engineering and Computer Science Laboratory of Digital Signal Processing Maribor Slovenia University Medical Centre Maribor Department of Thoracic Surgery Maribor Slovenia University Medical Centre Maribor Clinical Department of Abdominal and General Surgery Maribor Slovenia University Medical Centre Maribor Department of Nurses in Clinic for Surgery Maribor Slovenia University Medical Centre Maribor Clinical Department of Cardiac Surgery Maribor Slovenia

ISBN: (纸本)9798350377224

This study explores the integration of HL7 Fast Healthcare Interoperability Resources (FHIR) into a Clinical Decision Support System (CDSS) utilizing a Pepper robot to enhance doctor visits in a hospital setting. We evaluate a real-world implementation where the Pepper robot acts as an interface for data collection from patients, clinical monitors, and hospital information systems. The CDSS leverages FHIR to seamlessly integrate this data and present it visually, aiming to improve clinical decision-making processes for doctors. Our research investigates the potential of this FHIR-based CDSS with a robot interface to optimize healthcare delivery and potentially improve patient outcomes. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Himalayan Glacier and the Possibility of Past Ice Streams on Martian Outflow Channels using Remote Sensing Imagery

Himalayan Glacier and the Possibility of Past Ice Streams on...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Indranil Misra Mukesh Kumar Rohil S. Manthira Moorthi Debajyoti Dhar Signal and Image Processing Area Space Applications Centre Indian Space Research Organisation (ISRO) Ahmedabad India Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Martian outflow channels are extensive, long features on the planet's surface, running for thousands of kilometers and up to a kilometer deep. Scientific consensus attributes the formation of Martian outflow channels to catastrophic floods from overflowing lakes during Mars' early history. However, we present an alternative perspective, suggesting the possibility of past glacier ice streams on Mars, influenced by recent scientific studies indicating movements in Amazonian ice streams as potential carvers of Martian outflow channels. The paper proposes a hypothesis of a past cryosphere on Mars resulting in ice stream outflow channels. The study compares and analyzes Martian outflow channels and Himalayan glaciers using a novel remote sensing image processing workflow developed to support this proposed idea. The methodology involves topographic correction to normalize radiance measurements in uneven terrain, Principal Component Analysis (PCA) to extract maximum variance information, and feature matching using Scale Invariant Feature Transform (SIFT) with Random Sample Consensus (RANSAC) outlier removal to assign Feature Similarity Metric (FSM) scores for determining analogous sites. The paper highlights intriguing observations from Himalayan glaciers, which lend credence to the idea of an ice flow mechanism for the origin of Martian outflow channels.

关键词： Mars Visualization Transforms Feature extraction Glaciers Surface topography Streams

来源：评论

学校读者我要写书评

暂无评论

Image Registration of High Resolution Chandrayaan-2 Data

Image Registration of High Resolution Chandrayaan-2 Data

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Ridhi Makharia Jai G. Singla Amitabh Nitant Dube Harish Sharma Department of AIML School of Computer Science Engineering Manipal University Jaipur Rajasthan India Signal and Image Processing Area Space Applications Centre ISRO Ahmedabad Gujarat India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

Accurate and reliable detection of features, along with effective mapping and registration, has been a topic of considerable discussion. Detecting and identifying craters on the lunar surface poses significant challenges due to subtle intensity variations and shadow effects. Conventional corner and edge detection methods often struggle to outline these craters, complicating the image registration. This paper proposes a novel strategy for data preprocessing to enhance edge and corner detection for OHRC and NAC datasets. Utilizing SIFT (Scale-Invariant Feature Transform) and ASIFT (Affine Scale-Invariant Feature Transform) algorithms, the study identifies and maps key points between the OHRC (data to be registered) and NAC (reference) datasets, achieving high pixel-level registration accuracy (within the range of 0.2-2.5 pixels). The application of image stitching and warping, results in georeferenced images that are both accurate and precise, contributing to improved navigation and enhanced image quality.

关键词： Image quality Image registration Accuracy Navigation Image edge detection Moon Transforms Feature extraction Reliability Image stitching

来源：评论

学校读者我要写书评

暂无评论

Monitoring Riparian Vegetation Change Dynamics using Kullback-Leibler Divergence: A Case Study in the Vicinity of Sabarmati River, Gandhinagar, India

Monitoring Riparian Vegetation Change Dynamics using Kullbac...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Riparian Vegetation monitoring using remote sensing images involves using satellite or aerial imagery to assess the health, extent, and changes in vegetation along water bodies such as rivers and streams. This monitoring is important to balance the aquatic ecosystems. The paper presents a novel methodology to detect Riparian Vegetation change dynamics using multi-temporal satellite imagery. The workflow performs the image pre-processing task that includes multi-temporal image registration, top-of-atmosphere reflectance computation, and NDVI geophysical parameters retrieved to quantify the amount and health of vegetation in a Riparian zone buffer. The changes in Riparian Vegetation are detected using the Kullback-Leibler (KL) divergence technique and a change detection map is generated. The proposed approach is evaluated using recent INS-2B Nano-MX and historical IRS-1C LISS-3 imagery near Sabarmati River, Gandhinagar, India. It is found from the visual assessment that there is an increase in healthy Riparian Vegetation around the Sabarmati River. The results are cross-validated with Landsat NDVI time series analysis in the Riparian Vegetation Region of Interest (ROI) for the last two decades and it is found that vegetation change estimated around the river stream closely follows the trend with the proposed method.

关键词： Visualization Normalized difference vegetation index Time series analysis Vegetation mapping Landsat Rivers Satellite images

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation for Improved Lossless Screen Content Compression

Image Segmentation for Improved Lossless Screen Content Comp...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Shabhrish Reddy Uddehal Tilo Strutz Hannah Och André Kaup Department of Electrical Engineering and Computer Science Coburg University Coburg Germany Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen Germany

In recent years, it has been found that screen content images (SCI) can be effectively compressed based on appropriate probability modelling and suitable entropy coding methods such as arithmetic coding. The key objective is determining the best probability distribution for each pixel position. This strategy works particularly well for images with synthetic (textual) content. However, usually screen content images not only consist of synthetic but also pictorial (natural) regions. These images require diverse models of probability distributions to be optimally compressed. One way to achieve this goal is to separate synthetic and natural regions. This paper proposes a segmentation method that identifies natural regions enabling better adaptive treatment. It supplements a compression method known as Soft Context Formation (SCF) and operates as a pre-processing step. If at least one natural segment is found within the SCI, it is split into two subimages (natural and synthetic parts) and the process of modelling and coding is performed separately for both. For SCIs with natural regions, the proposed method achieves a bit-rate reduction of up to 11.6% and 1.52% with respect to HEVC and the previous version of the SCF.

关键词： Image segmentation Adaptation models Image coding signal processing Probability distribution Entropy coding Acoustics

来源：评论

学校读者我要写书评

暂无评论

IMAGE SEGMENTATION FOR IMPROVED LOSSLESS SCREEN CONTENT COMPRESSION

arXiv

引用

arXiv 2023年

作者： Uddehal, Shabhrish Reddy Strutz, Tilo Och, Hannah Kaup, André Department of Electrical Engineering and Computer Science Coburg University Coburg Germany Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen Germany

In recent years, it has been found that screen content images (SCI) can be effectively compressed based on appropriate probability modelling and suitable entropy coding methods such as arithmetic coding. The key objective is determining the best probability distribution for each pixel position. This strategy works particularly well for images with synthetic (textual) content. However, usually screen content images not only consist of synthetic but also pictorial (natural) regions. These images require diverse models of probability distributions to be optimally compressed. One way to achieve this goal is to separate synthetic and natural regions. This paper proposes a segmentation method that identifies natural regions enabling better adaptive treatment. It supplements a compression method known as Soft Context Formation (SCF) and operates as a pre-processing step. If at least one natural segment is found within the SCI, it is split into two sub-images (natural and synthetic parts) and the process of modelling and coding is performed separately for both. For SCIs with natural regions, the proposed method achieves a bit-rate reduction of up to 11.6% and 1.52% with respect to HEVC and the previous version of the SCF. Copyright © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Inappropriate Content Classification based on Video Rating: A Preliminary Study 2

Inappropriate Content Classification based on Video Rating: ...

引用

2nd International Conference on computer science and Engineering, IC2SE 2021

作者： Yong, Zuo Jun Lam Hoo, Wai University of Malaya Faculty of Computer Science and Information Technology Centre of Image and Signal Processing Department of Information Systems Kuala Lumpur Malaysia

ISBN: (纸本)9781665400459

With the rise of social media, video analysis becomes more important in understanding user behavior. Video analysis has been a challenging problem in the computer vision domain compared to image analysis, considering the number of image frames per second a video can have, and the time-series information that underlying within the video. While recent advancements in video analysis improved gradually, the inappropriate content classification remains challenging, mainly due to the limited number of frames to be detected that is contributing to the inappropriate context of the video. In this work, we tackled this problem by addressing the current algorithm in video analysis problems and investigating the majority algorithm that is widely used in video analysis problems and is heavily affected by the issues in inappropriate content classification. A weighted score strategy is proposed to overcome the limitation of the small number of image frame detection in terms of inappropriate content so that inappropriate content classification problems can be optimized. To prove the concept, a video dataset labeled with inappropriate content inspired by Malaysia movie rating has been collected. The proposed strategy can outperform the majority algorithm in a good margin, showing that the proposed solution helps get more effective in inappropriate content classification. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Detection via Graph Neural Networks: A Link Prediction Approach

arXiv

引用

arXiv 2024年

作者： Lin, Zhihao Gao, Chang Yan, Junkun Zhang, Qingfu Liu, Hongwei National Key Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Department of Computer Science City University of Hong Kong Hong Kong999077 Hong Kong

Multi-frame detection algorithms can effectively utilize the correlation between consecutive echoes to improve the detection performance of weak targets. Existing efficient multiframe detection algorithms are typically based on three sequential steps: plot extraction via a relative low primary threshold, track search and track detection. However, these three-stage processing algorithms may result in a notable loss of detection performance and do not fully leverage the available echo information across frames. As to applying graph neural networks in multi-frame detection, the algorithms are primarily based on node classification tasks, which cannot directly output target tracks. In this paper, we reformulate the multi-frame detection problem as a link prediction task in graphs. First, we perform a rough association of multiframe observations that exceed the low threshold to construct observation association graphs. Subsequently, a multi-feature link prediction network is designed based on graph neural networks, which integrates multi-dimensional information, including echo structure, Doppler information, and spatio-temporal coupling of plots. By leveraging the principle of link prediction, we unifies the processes of track search and track detection into one step to reduce performance loss and directly output target tracks. Experimental results show that, compared with traditional single-frame and multi-frame detection algorithms, the proposed algorithm improves the detection performance of weak targets while suppressing false alarms. Additionally, interpretable analysis indicates that the designed network effectively integrates the utilized features, allowing for accurate associations between targets and false alarms. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

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：