检索结果-内蒙古大学图书馆

International Conference on Display Technology, 2024

作者： Tang, Shu Tuen Chiu, Hon Wah Tseng, Man Chun Kwok, Hoi Sing State Key Laboratory on Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

Vertically Aligned LCD is one of the most widely used optical modes in LCD TV and mobile devices. It is also a very important category of passive LC displays used in Automobiles. It has the advantages of perfect dark state and very high contrast ratio for normal viewing. However, single domain VA LCD has the intrinsic issue of dead zone (contrast vanishing zone) in certain viewing direction in the voltage-on state, which seriously limits its viewing angle performance. Recently, the State Key laboratory on Advanced Displays and Optoelectronics Technologies of the Hong Kong University of science and Technology has developed an easy-to-apply multi-domain VA LCD technology that can be readily implemented in LCD factories without major investment and change in current production process. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Azo dyes

来源：评论

学校读者我要写书评

暂无评论

Secure speaker identification in open and closed environments modeled with symmetric comb filters

引用

Multimedia Tools and Applications 2025年第18期84卷 19147-19189页

作者： Shafik, Amira Monir, Mohamad El-Shafai, Walid Khalaf, Ashraf A. M. Nassar, M.M. El-Fishawy, Adel S. El-Din, M. A. Zein Dessouky, Moawad I. El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Minia University Minia61519 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Speech is a fundamental means of human interaction. Speaker Identification (SI) plays a crucial role in various applications, such as authentication systems, forensic investigation, and personal voice assistance. However, achieving robust and secure SI in both open and closed environments remains challenging. To address this issue, researchers have explored new techniques that enable computers to better understand and interact with humans. Smart systems leverage Artificial Neural Networks (ANNs) to mimic the human brain in identifying speakers. However, speech signals often suffer from interference, leading to signal degradation. The performance of a Speaker Identification System (SIS) is influenced by various environmental factors, such as noise and reverberation in open and closed environments, respectively. This research paper is concerned with the investigation of SI using Mel-Frequency Cepstral Coefficients (MFCCs) and polynomial coefficients, with an ANN serving as the classifier. To tackle the challenges posed by environmental interference, we propose a novel approach that depends on symmetric comb filters for modeling. In closed environments, we study the effect of reverberation on speech signals, as it occurs due to multiple reflections. To address this issue, we model the reverberation effect with comb filters. We explore different domains, including time, Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Discrete Sine Transform (DST) domains for feature extraction to determine the best combination for SI in case of reverberation environments. Simulation results reveal that DWT outperforms other transforms, leading to a recognition rate of 93.75% at a Signal-to-Noise Ratio (SNR) of 15 dB. Additionally, we investigate the concept of cancelable SI to ensure user privacy, while maintaining high recognition rates. Our simulation results show a recognition rate of 97.5% at 0 dB using features extracted from speech signals and their DCTs. Fo

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Real Time Human Detection by Unmanned Aerial Vehicles

arXiv

引用

arXiv 2024年

作者： Guettala, Walid Sayah, Ali Kahloul, Laid Tibermacine, Ahmed Computer Science Department Biskra University Algeria LINFI Laboratory Computer Science Department Biskra University Algeria

One of the most important problems in computer vision and remote sensing is object detection, which identifies particular categories of diverse things in pictures. Two crucial data sources for public security are the thermal infrared (TIR) remote sensing multi-scenario photos and videos produced by unmanned aerial vehicles (UAVs). Due to the small scale of the target, complex scene information, low resolution relative to the viewable videos, and dearth of publicly available labeled datasets and training models, their object detection procedure is still difficult. A UAV TIR object detection framework for pictures and videos is suggested in this study. The Forward-looking Infrared (FLIR) cameras used to gather ground-based TIR photos and videos are used to create the "You Only Look Once" (YOLO) model, which is based on CNN architecture. Results indicated that in the validating task, detecting human object had an average precision at IOU (Intersection over Union) = 0.5, which was 72.5%, using YOLOv7 (YOLO version 7) state of the art model [1], while the detection speed around 161 frames per second (FPS/second). The usefulness of the YOLO architecture is demonstrated in the application, which evaluates the cross-detection performance of people in UAV TIR videos under a YOLOv7 model in terms of the various UAVs’ observation angles. The qualitative and quantitative evaluation of object detection from TIR pictures and videos using deep-learning models is supported favorably by this *** Codes 68T45, 68U10, 68U99 © 2024, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Do Not Trust a Model because It is Confident: Uncovering and Characterizing Unknown Unknowns to Student Success Predictors in Online-Based Learning 2023

Do Not Trust a Model because It is Confident: Uncovering and...

引用

13th International Conference on Learning Analytics and Knowledge: Towards Trustworthy Learning Analytics, LAK 2023

作者： Galici, Roberta Kaser, Tanja Fenu, Gianni Marras, Mirko Department of Mathematics and Computer Science University of Cagliari Cagliari Italy Machine Learning for Education Laboratory EPFL Lausanne Switzerland

ISBN: (纸本)9781450398657

Student success models might be prone to develop weak spots, i.e., examples hard to accurately classify due to insufficient representation during model creation. This weakness is one of the main factors undermining users' trust, since model predictions could for instance lead an instructor to not intervene on a student in need. In this paper, we unveil the need of detecting and characterizing unknown unknowns in student success prediction in order to better understand when models may fail. Unknown unknowns include the students for which the model is highly confident in its predictions, but is actually wrong. Therefore, we cannot solely rely on the model's confidence when evaluating the predictions quality. We first introduce a framework for the identification and characterization of unknown unknowns. We then assess its informativeness on log data collected from flipped courses and online courses using quantitative analyses and interviews with instructors. Our results show that unknown unknowns are a critical issue in this domain and that our framework can be applied to support their detection. The source code is available at https://***/epfl-ml4ed/unknown-unknowns. © 2023 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhanced Traffic Sign Recognition Using Deep Learning Techniques 15

Enhanced Traffic Sign Recognition Using Deep Learning Techni...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mahmud, Tanjim Akter, Tahmina Islam, Dilshad Aziz, Mohammad Tarek Hossain, Mohammad Shahadat Andersson, Karl Rangamati Science and Technology University Dept. of Cse Rangamati4500 Bangladesh Port City International University Department of Computer Science and Engineering Chittagong Bangladesh Chattogram Veterinary and Animal Sciences University Dept. of Physical and Mathematical Sciences Chittagong Bangladesh Chittagong University of Engineering & Technology Department of Computer Science and Engineering Chittagong Bangladesh University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Luleå University of Technology Cybersecurity Laboratory Luleå97187 Sweden

ISBN: (纸本)9798350370249

Traffic sign recognition plays a pivotal role in modern intelligent transportation systems, contributing significantly to traffic management and road safety. This thesis presents a comprehensive investigation into the utilization of deep learning techniques for enhanced traffic sign recognition. The research delves into edge detection methodologies, deep learning architectures, and classification techniques specifically tailored for the identification of traffic and road signs. A diverse range of deep learning models, including Convolutional Neural Networks (CNN), VGG19, ResNet50, ResNet101, and ResNet152, are scrutinized for their effectiveness in traffic sign classification. The evaluation is conducted on a comprehensive dataset encompassing various road signs captured under diverse environmental conditions. The classification pipeline integrates edge detection algorithms such as Canny, Sobel, and Prewitt in conjunction with the selected neural network models. Experimental results exhibit notable performance disparities among the evaluated architectures. CNN achieves the highest accuracy of 96% when combined with the Prewitt edge detection method, while VGG19 attains 95% accuracy under the same conditions. ResNet50 achieves a peak accuracy of 96% with the Prewitt edge detection technique, while ResNet101 demonstrates the capability to achieve 97% accuracy when utilizing the Canny edge detection method. Remarkably, ResNet152 emerges as the top-performing model, achieving an impressive accuracy rate of 98% when employing the Sobel edge detection method, along with an exceptional F1-Score. © 2024 IEEE.

关键词： CNN deep learning edge detection Modified-ResNet Traffic sign VGG19

来源：评论

学校读者我要写书评

暂无评论

Proposal of Human-like Spatiotemporal Language Understanding Based on Mental Image Model for Language-centered Human-Robot Interaction 8

Proposal of Human-like Spatiotemporal Language Understanding...

引用

Joint 8th International Conference on Digital Arts, Media and Technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering, ECTI DAMT and NCON 2023

作者： Khummongkol, Rojanee Yokota, Masao University of Phayao Department of Computer Engineering Phayao Thailand Fukuoka Institute of Technology Information Science Laboratory Fukuoka Japan

ISBN: (纸本)9798350396546

Mental-image based spatiotemporal (4D) language understanding in human was considered from the viewpoint of cognitive science and simulated based on the mental image model proposed in mental image directed semantic theory (MIDST). The application system was evaluated based on a psychological experiment involving human subjects and found a good success in answering questions concerning the scenes expressed in 4D language. © 2023 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Using Deep Learning and Object-Oriented Metrics to Identify Critical Components in Object-Oriented Systems 23

Using Deep Learning and Object-Oriented Metrics to Identify ...

引用

5th World Symposium on Software Engineering, WSSE 2023

作者： Tete, Akpedje Touré, Fadel Badri, Mourad Software Engineering Research laboratory Department of Mathematics and Computer Science University of Quebec Trois-RivièresQC Canada

ISBN: (纸本)9798400708053

This paper aims at studying the ability of deep machine learning to predict software faults based on object-oriented metrics. This research investigated software faults from the perspective of fault-proneness, faults number and faults frequency, and used data collected from several versions of a Java open-source software system. This study relied on Chidamber and Kemerer suite of metrics as proxy to capture various software characteristics. In this study, the deep learning regression and classification results were compared to linear and logistic regressions. Auto-Encoders (AE) and Principal Components Analysis (PCA) have been used to reduce redundant information from the dataset. To evaluate the prediction ability of the models, this research used the inter-version validation strategy. The results showed that the models can achieve a significant average performance up to 89%. © 2023 Copyright held by the owner/author(s).

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Attention Graph Convolutions for Skeleton-based Action Recognition 23rd

Spatio-temporal Attention Graph Convolutions for Skeleton-b...

引用

22nd Scandinavian Conference on Image Analysis, SCIA 2023

作者： Le, Cuong Liu, Xin Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping Sweden

ISBN: (纸本)9783031314346

In skeleton-based action recognition, graph convolutional networks (GCN) have been applied to extract features based on the dynamic of the human body and the method has achieved excellent results recently. However, GCN-based techniques only focus on the spatial correlations between human joints and often overlook the temporal relationships. In an action sequence, the consecutive frames in a neighborhood contain similar poses and using only temporal convolutions for extracting local features limits the flow of useful information into the calculations. In many cases, the discriminative features can present in long-range time steps and it is important to also consider them in the calculations to create stronger representations. We propose an attentional graph convolutional network, which adapts self-attention mechanisms to respectively model the correlations between human joints and between every time steps for skeleton-based action recognition. On two common datasets, the NTU-RGB+D60 and the NTU-RGB+D120, the proposed method achieved competitive classification results compared to state-of-the-art methods. The project’s GitHub page: STA-GCN. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Epidemic criticality in temporal networks

引用

Physical Review Research 2024年第2期6卷 L022017-L022017页

作者： Chao-Ran Cai Yuan-Yuan Nie Petter Holme School of Physics Northwest University Xi'an 710127 China Shaanxi Key Laboratory for Theoretical Physics Frontiers Xi'an 710127 China Department of Computer Science Aalto University Espoo 02150 Finland Center for Computational Social Science Kobe University Kobe 657–8501 Japan

Analytical studies of network epidemiology almost exclusively focus on the extreme situations where the timescales of network dynamics are well separated (longer or shorter) from that of epidemic propagation. In realistic scenarios, however, these timescales could be similar, which has profound implications for epidemic modeling (e.g., one can no longer reduce the dimensionality of epidemic models). Combining Monte Carlo simulations and mean-field theory, we analyze the critical behavior of susceptible-infected-susceptible epidemics in the vicinity of the critical threshold on the activity-driven model of temporal networks. We find that the persistence of links in the network causes the threshold to decrease as the recovery rate increases. Dynamic correlations (coming from being close to infected nodes increases the likelihood of infection) drive the threshold in the opposite direction. These two counteracting effects make epidemic criticality in temporal networks a remarkably complex phenomenon.

关键词： Complex networks Epidemic spreading Evolving network models

来源：评论

学校读者我要写书评

暂无评论

Frequency-Guided Network for Low-contrast Staining-free Dental Plaque Segmentation

Frequency-Guided Network for Low-contrast Staining-free Dent...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Yiming Song, Wenfeng Li, Shuai Yang, Yuming Xia, Bin Hao, Aimin Qin, Hong Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China Beijing Information Science and Technology University School of Computer Science Beijing China Peking University School and Hospital of Stomatology Department of Pediatric Dentistry Beijing China Stony Brook University Department of Computer Science New York United States

ISBN: (纸本)9798350386226

Traditional dental plaque detection relies on medical staining reagents and professional intervention. Deep learning-based automatic staining-free dental plaque segmentation provides an alternative for patients to perform plaque detection at home without staining reagents. However, existing methods still struggle with low-contrast visual features between unstained plaque and healthy teeth. To address this, we propose a Frequency-Guided Network (FGN) for low-contrast staining-free dental plaque segmentation. We observe that dental plaque tends to concentrate specifically near the junction between the teeth and the gingiva. This junction demonstrates abrupt changes in pixel values, indicating high-frequency regions in the image. In other words, dental plaque tends to appear near the high-frequency regions of oral endoscope images. Exploiting this characteristic, we employ a frequency-guided decoupling module to separate the image into high-frequency and low-frequency regions automatically and expand the high-frequency region to encompass nearby potential dental plaque. Then we supervise two regions individually to specifically focus on the expended high-frequency region for localizing nearby dental plaque. Additionally, we propose a high-to-low frequency multiple tasks framework. In the first phase, the network segments the teeth region, and then we input the teeth mask into the second phase. In the second stage, the teeth mask allows us to have a higher frequency at the junction between the teeth and gums, thereby enhancing the effectiveness of frequency-guided decoupling. Furthermore, FGN integrates a frequency-driven refinement module to enhance the guidance quality of the teeth mask for the second phase. Extensive evaluations of the oral endoscope dataset demonstrate that our method outperforms existing high-performance segmentation methods. User studies also confirm that our approach achieves superior results to experienced dentists. https://frequency-guided-netw

关键词： Image segmentation

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：