检索结果-内蒙古大学图书馆

31st International Conference on Multimedia Modeling, MMM 2025

作者： Lim, Xin Wong, Lai-Kuan Loh, Yuen Peng Gu, Ke Lin, Weisi Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia Beijing University of Technology Beijing China Nanyang Technological University Singapore Singapore

ISBN: (纸本)9789819620609

Atmospheric haze significantly impairs the performance of computer vision tasks such as image dehazing and object detection. Existing methods often address these tasks independently, failing to provide an integrated solution that can effectively handle hazy conditions while maintaining accurate object detection. This paper presents Mix-YOLONet, a novel joint network architecture designed to tackle both image dehazing and object detection simultaneously. Mix-YOLONet leverages the powerful image restoration capabilities of U-Net-like architecture and integrates it with the detection precision of a YOLO head. Additionally, we integrated Mix Structure Blocks (MSB) to our joint network and experimented various configurations at strategic locations to enhance feature extraction and context aggregation. Through extensive experiments, we demonstrate that Mix-YOLONet achieves superior performance in both dehazing and object detection tasks under challenging visibility conditions, outperforming state-of-the-art methods on three benchmark datasets both quantitatively and qualitatively. The proposed joint network not only improves the clarity of hazy images but also ensures accurate object localization, paving the way for more robust object detection in adverse environmental conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Predicting game-induced emotions using EEG, data mining and machine learning

引用

Bulletin of the National Research Centre 2024年第1期48卷 1-10页

作者： Lim, Min Xuan Teo, Jason Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia Creative Advanced Machine Intelligence Research Centre Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia Evolutionary Computing Laboratory Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia

Emotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal’s changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers’ performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions. The RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases’ results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm’s capabilities in precisely determining the emotion label for each participant’s EEG features’ instance. The findings in this study fill the existing gap of game-induced emotion recog

关键词：

来源：评论

学校读者我要写书评

暂无评论

Underwater Corrosion Recognition using Colour Illumination Mapping

Underwater Corrosion Recognition using Colour Illumination M...

引用

2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022

作者： Ibrahim, Amalina Mohd-Isa, Wan-Noorshahida Su'Ud, Mazliham Mohd Desa, Shahbe Mat Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9798350332421

Visual-based corrosion detection is one of the techniques that can be utilised for performing inspection in areas where human access is impossible because of environment, safety and other concerns such as underwater. Image quality has become a great factor in underwater image analysis. Noticeable challenges are limited source of natural lighting, loss of colour underwater at depth, magnification of objects underwater and much more. These factors may affect the process of estimating the actual corroded area underwater. Due to that, this work is proposing a technique to recognize underwater corrosion based on colour illumination mapping. © 2022 IEEE.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Data-Oriented Operating System for Big Data and Cloud

引用

Intelligent Automation & Soft computing 2024年第4期39卷 633-647页

作者： Selwyn Darryl Kessler Kok-Why Ng Su-Cheng Haw Faculty of Computing and Informatics Multimedia UniversityCyberjaya63100Malaysia

Operating System(OS)is a critical piece of software that manages a computer’s hardware and resources,acting as the intermediary between the computer and the *** existing OS is not designed for Big Data and Cloud computing,resulting in data processing and management *** paper proposes a simplified and improved kernel on an x86 system designed for Big Data and Cloud computing *** proposed algorithm utilizes the performance benefits from the improved Input/Output(I/O)*** performance engineering runs the data-oriented design on traditional data management to improve data processing speed by reducing memory access overheads in conventional data *** OS incorporates a data-oriented design to“modernize”various Data Science and management *** resulting OS contains a basic input/output system(BIOS)bootloader that boots into Intel 32-bit protected mode,a text display terminal,4 GB paging memory,4096 heap block size,a Hard Disk Drive(HDD)I/O Advanced Technology Attachment(ATA)driver and *** are also I/O scheduling algorithm prototypes that demonstrate how a simple Sweeping algorithm is superior to more conventionally known I/O scheduling algorithms.A MapReduce prototype is implemented using Message Passing Interface(MPI)for big data *** attempt was made to optimize binary search using modern performance engineering and data-oriented design.

关键词： Operating system big data cloud computing MapReduce data-oriented

来源：评论

学校读者我要写书评

暂无评论

Investigating Electrodermography (EDG) and Heart Rate (HR) Signals for Emotion Classification in Virtual Reality 1

Investigating Electrodermography (EDG) and Heart Rate (HR) S...

引用

1st International Visualization, informatics and Technology Conference, IVIT 2022

作者： Bulagang, Aaron Frederick Mountstephens, James Teo, Jason Universiti Malaysia Sabah Faculty of Computing and Informatics Malaysia

ISBN: (纸本)9781665486484

This paper shows the findings and results of combining Heart Rate and Electrodemography signals with KNN classifier for multimodal emotion detection using Virtual Reality (VR). The study was conducted by using a VR headset to show the participants 360 videos to elicit their emotional responses to the video. Their emotional response was captured using a wearable device that records both heart rate and skin activity in real time. A total of 5 participants took part in the experiment where the results are classified for intra-subject classification using KNN classifier. In the study, for the classification of intra-subject, the peak accuracy achieved amongst the five participants is 97.7% with HR and EDG signals combined with KNN as the classifier. These results demonstrate that by fusing HR and EDG signals, high-Accuracy results can be generated through the use of KNN as the classifier. The application and potential of this study can be useful in entertainment, VR rehabilitation, and gaming. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Crowd Monitoring of Hajj Pilgrimage using Video Analytics and Deep Learning *

Crowd Monitoring of Hajj Pilgrimage using Video Analytics an...

引用

2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022

作者： Bhuiyan, Md Roman Abdullah, Junaidi Hashim, Noramiza Farid, Fahmid Al Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9798350332421

This paper presents developments in crowd analysis, with a specific emphasis on crowd density during the Hajj and Umrah pilgrimages. In recent years, there has been a rising interest in increasing video analytics and video surveillance to enhance the safety and security of pilgrims throughout their stay in Mecca. Crowd surveillance research and development are still in their infancy. Real-time monitoring of crowds is impeded by a lack of distinct crowd scenes or the high intensity of the crowd, which reduces its use. This paper proposed a fully convolutional neural network (FCNN) method for large crowd analysis, and it is able to classify the three classes of crowd density. This is intended to overcome existing technical challenges in video analysis in situations involving the circulation of a large number of pilgrims at a density of seven to eight per square meter. This endeavor intends to build a new dataset based on the Hajj scenario, in part to overcome the aforementioned difficulty. Manual and semi-automatic approaches are now used for video analysis, notably during Hajj. However, it is vital to automatically monitor pilgrim crowd events. Integrating FCNN classification with FCNN regression requires a strategy that is more powerful than the direct approach. Using ResNet50 and Fully Convolutional Neural Networks, a deep learning architecture is constructed to predict the density of certain crowd footage (FCNNs). The new dataset (Hajj-Crowd dataset) and using the recommended strategy, our solution obtained 100 % accuracy in crowd analysis, exceeding the state-of-the-art technology. In addition, the ResNet50 method achieved an accuracy of 98.6% for the developed crowd dataset. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Noise-Aware Zero-Reference Low-light Image Enhancement for Object Detection

Noise-Aware Zero-Reference Low-light Image Enhancement for O...

引用

2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022

作者： Ang, Kelvin Lim, Wan Teng Loh, Yuen Peng Ong, Simying Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9798350332421

Computer vision advancement has proven to be able to automate many practical tasks such as object detection and recognition in challenging environments. However, most notable computer vision models are optimized to work under environment with ideal lighting conditions. Real-world scenarios are uncontrolled and it is common to encounter quality and performance deterioration due to challenges in poor lighting, especially related to the amplification of noise signals. Consequently, there is an increase of vision enhancement related works to maintain such models' performances, however there is still a gap in exploring the practical implication that such existing enhancement work has on detection models, as well as the issue and handling of noise signals. Hence, this paper investigates the incorporation of noise information into the enhancement modelling with the specific aim to improve the performance of object recognition. Building upon the zero-reference deep curve estimation (Zero-DCE) approach, a noisy data training strategy is designed in order to introduce noise priors into the curve estimation training to produce better image structure enhancement. Furthermore, the commonly implemented post-process denoising approach is also studied in this work to find out its impact and effectiveness in the context of object detection. Experiments on the ExDark dataset show that the enhanced images produced by the proposed approach is able to improve object detection in low-light images using YOLOv5 with an increase of up to 3% in precision, and comparable performance with significantly more complex state-of-The-Art low-light image enhancement models. © 2022 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Remote Moderated Usability Testing of a Web-Based Translation: A Case Study 26

Remote Moderated Usability Testing of a Web-Based Translatio...

引用

26th International Computer Science and Engineering Conference, ICSEC 2022

作者： Lim, Tek Yong Multmedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9781665491983

A new design of web-based translation, also known as easyTranslate, is proposed for non-native English-speaking students to translate a paragraph of academic text. However, there is a need to determine whether this new web-based translation is usable or not for students during the Covid-19 pandemic. Thus, this paper describes a remote moderated usability testing of a web-based translation. Five undergraduate students took part in the usability testing through an online video conferencing tool. The results showed that all students successfully completed the given tasks and the new web-based translation is considered usable. The advantages and challenges of the remote moderated usability testing are discussed. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Efficient Contrast Subspace Mining Method for Categorical Data 6

Efficient Contrast Subspace Mining Method for Categorical Da...

引用

6th International Conference on Computer Science and Artificial Intelligence, CSAI 2022

作者： Sia Fui Sze, Florence Alfred, Rayner Faculty of Computing and Informatics Universiti Malaysia Sabah Malaysia

ISBN: (纸本)9781450397773

Mining contrast subspace has recently received attention to identify contrast subspace where a query object is most likely similar to a target class but least likely similar to other class. It has many important applications in various domain such as healthcare, security, finance, and business. Tree-based contrast subspace mining method (TB-CSMiner) has been introduced that is capable to identify contrast subspace of query object in categorical data set. However, the effectiveness of the method has not been evaluated thoroughly. Besides, the efficiency of the method in finding contrast subspace has not yet been examined. Real world data sets more often than not containing large amount of data. It is important to have a method that can identify contrast subspace of query object not only effectively but also efficiently on large data set. This paper uses various classification methods to further evaluate the effectiveness of the TB-CSMiner and assesses the execution speed of the method in mining contrast subspace. TB-CSMiner is experimentally shown to be significantly faster and as effective in identifying contrast subspace of query object on real world categorical data sets. © 2022 ACM.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

ARCards: Marker-Based Augmented Reality Recognition for Business Cards 2

ARCards: Marker-Based Augmented Reality Recognition for Busi...

引用

2nd International Conference on Big Data Engineering and Education, BDEE 2022

作者： Liew, Jun-Xian Ng, Kok-Why Haw, Su-Cheng Ng, Sew-Lai Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (数字)9781665481847

ISBN: (纸本)9781665481847

Augmented Reality (AR) is an advanced technology that can improve human life. It provides the users an interactive experience where the real world objects are combined with the computer-generated virtual elements such as sound, video, graphics, GPS overlays and more. This paper surveys on the existing AR applications and also introduces ARCards which is an AR mobile application for business cards using marker-based recognition approach. ARCards is designed to enhance a person's insight view of reality. It changes the users' perception by analyzing and implementing a new way of business card sharing where additional features and functions are well equipped by recognizing the markers on the business card. This could deliver an invaluable experience through AR when introducing a person or a company detail. More valuable contents can be included and displayed as virtual digital information and this is hardly to be fitted into a normal business card. AR markers, are trained to identify as a trigger to output the visual components stored digitally in a database. The main camera in the scene is replaced by ARCamera from Vuforia Engine to recognize the feature markers on a business card and automatically revokes the digital contents from the database to be rendered on the phone scene. Extended tracking is enabled so the users are not required to always place the business card in front of the camera for constantly tracking. The functionalities are combined with the physical world and instantly offer realtime feedback to the users. Recognition process takes less than a second to identify the important features. With ARCards, one can easily stand out from others. ARCards also received 86.7% of users' full satisfaction. © 2022 IEEE.

关键词： Augmented reality

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：