检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sultan, Naveed Hajian, Amir Aramvith, Supavadee Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Multimedia Data Analytics and Processing Research Unit Department of Electrical Engineering Chulalongkorn University Bangkok Thailand

In recent years, convolutional neural networks (CNNs) have achieved remarkable advancement in the field of remote sensing image super-resolution due to the complexity and variability of textures and structures in remote sensing images (RSIs), which often repeat in the same images but differ across others. Current deep learning-based super-resolution models focus less on high-frequency features, which leads to suboptimal performance in capturing contours, textures, and spatial information. State-of-the-art CNN-based methods now focus on the feature extraction of RSIs using attention mechanisms. However, these methods are still incapable of effectively identifying and utilizing key content attention signals in RSIs. To solve this problem, we proposed an advanced feature extraction module called Channel and Spatial Attention Feature Extraction (CSA-FE) for effectively extracting the features by using the channel and spatial attention incorporated with the standard vision transformer (ViT). The proposed method trained over the UCMerced dataset on scales 2, 3, and 4. The experimental results show that our proposed method helps the model focus on the specific channels and spatial locations containing high-frequency information so that the model can focus on relevant features and suppress irrelevant ones, which enhances the quality of super-resolved images. Our model achieved superior performance compared to various existing models. © 2024, CC BY-NC-ND.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Classification of Mental Health State Using the DASS-21 Profile

Machine Learning-Based Classification of Mental Health State...

引用

Biomedical Engineering International Conference (BMEiCON)

作者： Khanita Duangchaemkarn Patiphan Khammarew Supavadee Aramvith Department of Pharmacy Practice School of Pharmaceutical Sciences University of Phayao Phayao Thailand Pharmacy research extern under the Doctor of Pharmacy Program School of Pharmaceutical Sciences University of Phayao Phayao Thailand Multimedia Data Analytic and Processing Research Unit Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798331505431

ISBN: (纸本)9798331505448

This study aimed to determine the most effective machine learning model for classifying emotional states of depression, anxiety, and stress based on the DASS-21 profile. Six machine learning models were developed and tested using 2,602 records from the University of Phayao Counselling Center, collected between 23 July and 16 August 2020. The results demonstrate that the deep learning model provided the highest accuracy and precision, exceeding 90% for all three emotional categories, with an AUC greater than 99%. These findings introduce an innovative approach for classifying emotional states of depression, anxiety, and stress using the DASS-21 profile as a benchmark. Incorporating additional features into the model could further enhance its utility in clinical decision-making, improving the accuracy of mental health screening and diagnosis.

关键词： Deep learning Employee welfare Adaptation models Accuracy Anxiety disorders Decision making Mental health Depression Reliability engineering data models

来源：评论

学校读者我要写书评

暂无评论

Stroke Home Rehabilitation Approach Using Mobile Application Based on PostNet Machine Learning Model 23

Stroke Home Rehabilitation Approach Using Mobile Application...

引用

7th International Conference on Medical and Health Informatics, ICMHI 2023

作者： Das, Utpal Chandra Le, Ngoc Thien Benjapolakul, Watit Vitoonpong, Timporn Pluempitiwiriyawej, Charnchai Center of Excellence in Artificial Intelligence Machine Learning and Smart Grid Technology Department of Electrical Engineering Chulalongkorn University Bangkok10330 Thailand Department of Rehabilitation Medicine Faculty of Medicine Chulalongkorn University Bangkok10330 Thailand Multimedia Data Analytics and Processing Research Unit Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok10330 Thailand

ISBN: (纸本)9798400700712

Stroke is a significant cause of mortality and disability globally, with its occurrence in the human brain and motor function being linked to various parts of the human body. Stroke victims often experience disabilities or mobility problems in affected body parts, either on one or both sides of the body. Physiotherapy exercises are the primary treatment and medication for stroke patients, necessitating daily monitoring by a physiotherapist. However, this approach is expensive, and rehabilitation centers and physicians are scarce. Numerous research studies have been conducted to address this issue from various perspectives. This study proposes a Convolutional Neural Network (CNN) based pose net machine learning (ML) model for stroke home rehabilitation using pose detection and classification with a skeleton base model and human pose estimation drawing. We trained our ML model using different human pose images for this model. The tested accuracy of our CNN model is 100% for our exercise pose image test case. Later we build and mobile application for remote rehabilitation. Tested the application with ten different subjects, achieving a 98% for elbow extension, and in the case of elbow flexion and Normal position of balancing both sides, all the persons achieved a 100 % accuracy rate under a laboratory environment. © 2023 ACM.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Optimizing LiDAR-Based Depth Map Accuracy Through Multiview Angle Analysis to Enhance Shape Measurement Efficiency

Optimizing LiDAR-Based Depth Map Accuracy Through Multiview ...

引用

International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： Possathon Teerakantapirut Rungrat Viratikul Charnchai Pluempittiwiriyawej Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Telecommunication Networking and Systems Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

This study introduces an advanced methodology to overcome the intrinsic challenges associated with Light Detection and Ranging (LiDAR) technology integrated into Apple's devices, specifically focusing on optimizing depth map accuracy through multiview angle analysis. Despite the extensive utility of LiDAR in generating detailed three-dimensional models for various applications, from autonomous vehicle navigation to environmental conservation, the efficiency of the technology is often compromised by difficulties in accurately rendering complex geometries from multiple perspectives and by its substantial demands on computational resources. To address these limitations, depth map data are systematically collected and evaluated from four distinct viewing angles (0, 90, 180, and 270 degrees) against established ground truth benchmarks. With a threshold of Intersection over Union (IoU) set at 0.8, it is inferred that the predicted shape exhibits over 80% similarity to the actual shape. When only one view is utilized, an IoU of 0.95 is achieved, alongside a size reduction of 73.07%, a Perimeter Accuracy reduction of 1.56%, and an increase in Root Mean Square Error (RMSE) of 29.37%. This comprehensive analysis highlights the critical need for precise geometric representation and marks a significant step toward enhancing the fidelity of LiDAR measurements. The results of this research indicate a substantial improvement in the accuracy of three-dimensional representations, suggesting a potential shift in the utilization of LiDAR technology across various scientific and infrastructural domains. By proposing a novel framework that optimizes data precision and processing efficiency, this paper contributes to the ongoing discourse on improving 3D modeling and analysis techniques.

关键词： Geometry Solid modeling Laser radar Accuracy Three-dimensional displays Shape Shape measurement

来源：评论

学校读者我要写书评

暂无评论

Compressed Image Super Resolution using Convolutional Neural Network

Compressed Image Super Resolution using Convolutional Neural...

引用

IEEE Region 10 International Conference TENCON

作者： Ei Ei Tun Aktanin Konkitkriengkrai Watchara Ruangsang Supavadee Aramvith Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Faculty of Engineering Chulalongkorn University Bangkok Thailand

Image compression is a topic of significant interest as it reduces file sizes in stored data. In this paper, we propose a model that achieves multiple levels of compression, thereby minimizing the storage space required for images, which typically consume substantial amounts of data due to their size and resolution. We combine an image downscaling and upscaling model with an image compression model. By leveraging convolutional techniques to identify image features, we can effectively reduce the size of the image through downscaling and subsequently upscaling it. Additionally, we employ entropy image compression and arithmetic encoding to compress and reconstruct the image while preserving its lossless data. Through experimentation with the Kodak dataset, we observed that our proposed model achieved a compression rate of 96.92%, significantly reducing the data needed for file storage. Moreover, our reconstructed images attained a standardized measure with a signal-to-noise ratio of 33.10 dB and a structural similarity of 0.9219. Notably, the perceptual quality of the images, including intricate details, remained intact to the human eye.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Visual Fidelity in Unpaired Night-to-Day Image Translation through a Perceptual Quality Focused Training Objective

Enhancing Visual Fidelity in Unpaired Night-to-Day Image Tra...

引用

Artificial Intelligence (SLAAI-ICAI), SLAAI International Conference on

作者： H.K.I.S. Lakmal Maheshi B. Dissanayake Supavadee Aramvith Dept. of Electrical and Electronic Engineering Faculty of Engineering University of Peradeniya Peradeniya Sri Lanka Dept. of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Chulalongkorn University Bangkok Thailand

Nighttime driving poses visibility challenges, but image translation methods can help by transforming night images into day-like scenes. The Cycle-GAN is a versatile unpaired image translation model which can easily be adept to night-to-day image translation tasks. However, it generates unnatural and unrealistic outcomes in these cases. This study is focused on addressing this with a novel training strategy for the Cycle-GAN, employing a tailored training objective that incorporates perceptual quality optimization. This training objective aims to boost the naturalness and perceptual quality of the generated images by preserving high-level image features. The optimization process involves minimizing Euclidean distances between synthesized and target image feature maps, which are derived from the pre-trained VGG19 network. Experimental findings attest to the effectiveness of this method, revealing noteworthy improvements of 8% in Inception Score, 2% in NIQE Score, and 13% in BRISQUE Score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combined Channel and Spatial Attention-based Stereo Endoscopic Image Super-Resolution

arXiv

引用

arXiv 2023年

作者： Hayat, Mansoor Armvith, Supavadee Achakulvisut, Titipat Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Multimedia Data Analytics and Processing Research Unit Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Department of Biomedical Engineering Mahidol University Bangkok Thailand

Stereo Imaging technology integration into medical diagnostics and surgeries brings a great revolution in the field of medical sciences. Now, surgeons and physicians have better insight into the anatomy of patients' organs. Like other technologies, stereo cameras have limitations, e.g., low resolution (LR) and blurry output images. Currently, most of the proposed techniques for super-resolution focus on developing complex blocks and complicated loss functions, which cause high system complexity. We proposed a combined channel and spatial attention block to extract features incorporated with a specific but very strong parallax attention module (PAM) for endoscopic image super-resolution. The proposed model is trained using the da Vinci dataset on scales 2 and 4. Our proposed model has improved PSNR up to 2.12 dB for scale 2 and 1.29 dB for scale 4, while SSIM is improved by 0.03 for scale 2 and 0.0008 for scale 4. By incorporating this method, diagnosis and treatment for endoscopic images can be more accurate and effective. Copyright © 2023, The Authors. All rights reserved.

关键词： Geometrical optics

来源：评论

学校读者我要写书评

暂无评论

Combined Channel and Spatial Attention-Based Stereo Endoscopic Image Super-Resolution

Combined Channel and Spatial Attention-Based Stereo Endoscop...

引用

IEEE Region 10 International Conference TENCON

作者： Mansoor Hayat Supavadee Armvith Titipat Achakulvisut Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Chulalongkorn University Bangkok Thailand Department of Biomedical Engineering Mahidol University Bangkok Thailand

关键词：

来源：评论

学校读者我要写书评

暂无评论

Power aware scheme for water pipeline monitoring based on Wireless Sensor Networks

Power aware scheme for water pipeline monitoring based on Wi...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Manel Elleuchi Manel Boujelben Mohamed Abid Abdulfattah M. Obeid Mohammed S. BenSaleh Multimedia and Digital Data Processing (CETIC) National School of Engineers of Sfax ResearchCenter in Informatics Sfax Tunisia CES research unit National School of Engineers of Sfax Research Center in Informatics Multimedia and Digital Data Processing (CETIC) Technopark Sfax Tunisia National Center for Electronics Communications and Photonics King Abdulaziz City for Science and Technology Riyadh Kingdom of Saudi Arabi King Abdulaziz City for Science And Technology Riyadh Al Riyadh Province SA

ISBN: (纸本)9781467387101

Recently, using Wireless Sensor Networks (WSNs) is increasing in many areas, whether scientific, logistic, military, health and water monitoring. Water is among the vital material transported by pipeline systems. Any leakage in the pipe can cause major financial losses and possible environmental damages. Therefore, it is necessary to have a real time leak detection system. WSNs can play an important role to effectively detect the leak and minimize the water loss. Sensor size, however, is a significant limitation in terms of energy autonomy. In fact, the battery is very small and in general, it is not replaceable or rechargeable. Therefore, many studies are currently focusing on the management of the energy consumed by sensor nodes. In this paper, we propose a new energy efficient scheme for leak detection in water pipeline based on WSNs. The main goal of our proposal is to solve the problem of losing water and ameliorate network lifetime by reducing energy needs. The proposed scheme is composed of three tasks: deployment of sensors, routing and replacement of failed nodes. Simulations results validate the choice of the best cluster based routing protocol which will be executed in the second task of the proposed scheme.

关键词： Monitoring Routing Wireless sensor networks Logic gates Color Clustering algorithms Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cross-Modality MRI Segmentation Using Dilated Convolutions and Multi-Scale Gradient Map

Enhanced Cross-Modality MRI Segmentation Using Dilated Convo...

引用

International Computer Science and Engineering Conference (ICSEC)

作者： Ghulam Murtaza Charnchai Pluempitiwiriyawej Somkiat Wangsiripitak Mohammad Jawad Fareed Mudassar Khalid Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Chulalongkorn University Bangkok Thailand Machine Intelligence and Vision Laboratory School of Information Technology King Mongkut’s Insittute of Technology Ladkrabang Thailand

ISBN: (数字)9798350366860

ISBN: (纸本)9798350366877

In recent years, convolutional neural networks have significantly advanced image segmentation, particularly for brain images, where important edge features are automatically found. However, accurate segmentation of tumors in a brain remains a challenge across different magnetic resonance modalities, like T1, T2, T1ce, and FLAIR. Using a simple gradient map as an input to the neural networks is not effective due to variations in cross-modality image characteristics. To address this issue, we introduced multi-scale gradient maps that incorporate Holistically Nested Edge Detection (HED) and dilated convolutions into the UNet model. The HED model captures detailed gradient information, enhancing structural feature identification across modalities, while dilated convolutions expand the UNet receptive field for better contextual understanding without increasing parameters. Our method was trained and evaluated on the BraTS2018 dataset. The experimental results demonstrate significant improvements in segmentation accuracy and robustness. Specifically, our method achieved a Dice Similarity Coefficient (DSC) of 0.6902 for T2 to T1ce, 0.6858 for T2 to T1, 0.4329 for FLAIR to T1, and 0.6004 for FLAIR to T1ce, outperforming previous state-of-the-art methods. This demonstrates the effectiveness of our approach in enhancing segmentation performance across different MR image modalities.

关键词：

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：