检索结果-内蒙古大学图书馆

28th International Computer Science and Engineering Conference, ICSEC 2024

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

ISBN: (纸本)9798350366860

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. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Message

International Conference on Applied Intelligence and Sustain...

引用

International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023 2023年

作者： Aramvith, Supavadee Electrical Engineering Chulalongkorn University India Internationalization Head Multimedia Data Analytics and Processing Research Unit Thailand

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Attentive Pixels Network in Face Super-Resolution at Scale Factor of 16

Efficient Deep Attentive Pixels Network in Face Super-Resolu...

引用

International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Hein Htet Aung Supavadee Aramvith Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Faculty of Engineering Chulalongkorn University Bangkok Thailand

Nowadays, Face Super-Resolution (FSR) models utilize the fusion approach, which combines the attention technique with the super-resolution network. The fusion approach has been proposed and solves the problem of FSR. Facial attributes have been effectively used to guide low-level information of the face to perform robust face image restoration. Iterative techniques appraised the value of facial landmarks to boost the reconstruction capability of the super-resolution network. Nevertheless, the network parameters in FSR are high, while the learning rate is still low. This paper proposes an attention mechanism combined with the Face Alignment Network (FAN). The proposed attention mechanism consists of channel attention and a non-local module. Our proposed model outperforms at the scale of $\times 16$ compared to the other state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Advanced Features Extraction Module for Remote Sensing Image Super-Resolution

arXiv

引用

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

An Advanced Features Extraction Module for Remote Sensing Image Super-Resolution

An Advanced Features Extraction Module for Remote Sensing Im...

引用

International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

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

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

关键词： Computational modeling Superresolution Feature extraction Transformers Decoding Telecommunications Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Non-Local Technique on Deep Attentive Face Super-Resolution Network

Non-Local Technique on Deep Attentive Face Super-Resolution ...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Amir Hajian Hein Htet Aung Watchara Ruangsang Sovann Chen Supavadee Aramvith Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Multimedia Data Analytics and Processing Research Unit Chulalongkorn University Bangkok Thailand

Recent Face Super-resolution (FSR) based on iterative collaboration between facial image recovery network and landmark estimation has succeeded in super-resolving facial images. However, the existing noise in coarse features at the low-level feature extraction leads to inaccurate facial priors such as landmarks and component maps, consequently degrading the super-resolved face image on a large scale. This paper proposes, a Non-local technique for deep attentive face super-resolution network (NLDA). A Non-local module has been designed before the residual channel attention block (RCAB) to eliminate noise degradation on coarse features effectively. The proposed model optimizes feature extraction and improves facial landmark fusion to yield higher-quality super-resolved images. This approach facilitates more accurate landmark estimation and boosts the performance of our model on a large scale and various face poses. Quantitative and qualitative experiments over CelebA and Helen face image datasets show that the proposed method outperforms other state-of-the-art FSR methods in recovering high-quality face images in various face poses and at a large scale.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Golf Swing Sequence Analysis

Deep Learning-Based Golf Swing Sequence Analysis

引用

IEEE Region 10 International Conference TENCON

作者： Amir Hajian Karit Sookpreedee Kingrak Phairoh Watchara Ruangsang Supavadee Aramvith Department of Electrical Engineering Chulalongkorn University Bangkok Thailand Multimedia Data Analytic and Processing Research Unit Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Multimedia Data Analytics and Processing Research Unit Faculty of Engineering Chulalongkorn University Bangkok Thailand

Golf is widely recognized as one of the most popular sports globally. However, one drawback of playing golf is the relatively high cost of equipment and coaching. While numerous training programs are available to assist players in their practice, there is currently no swing analysis program developed by Thai professionals. In this project, advanced deep learning models were employed: SwingNet, capable of predicting the sequence of eight golf swing events in videos and determining the confidence level of each swing, and MoveN et, designed to identify joint positions on the body and represent them as skeletons. These models were integrated into a customized template-matching algorithm that utilized angle-based measurements to analyze the sequence of golf swings. This analysis assessed the similarity score, represented as a percentage, between two individuals for each golf swing event. Furthermore, various techniques were implemented to enhance the efficiency of SwingN et. Through performance evaluation, it was observed that the efficiency of SwingN et surpassed by one percent compared to the pre-trained model.

关键词：

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

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

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

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：