检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Advancing XAI: new properties to broaden semantic-based explanations of black-box learning models 28th

Advancing XAI: new properties to broaden semantic-based expl...

引用

28th International Conference on Knowledge Based and Intelligent information and Engineering Systems, KES 2024

作者： Kosov, Pavel Kadhi, Nahla El Zanni-Merk, Cecilia Gardashova, Latafat Azerbaijan State Oil and Industry University Computer Engineering Department BakuAZ1010 Azerbaijan Normandie Université INSA Rouen LITIS Rouen76000 France French-Azerbaijani University Computer Science Research Department BakuAZ1000 Azerbaijan ASOIU Scientific Research Institute Geotechnological Problems of Oil Gas and Chemistry BakuAZ1010 Azerbaijan

For a long time, experts in different areas where Artificial Intelligence (AI) is widely applied have been requesting more clarity for the decisions made by AI. DARPA came up with a new framework for eXplainable AI (XAI) where the system exploits an explainable model to provide explanations through the explanation interface to users based on the level of their expertise. Later, ontologies were integrated in various ways, which paved the way for clearer explanations. Provided enough Expert Knowledge, ontologies can be a potent tool in XAI. Based on the ideas of Bellucci et al., their explainable system provides comprehensive explanations based on"visible" properties found in images by Machine Learning (ML) models and described via ontologies. However, we believe that any property, not only visible ones, can be used to explore the data. New"explanatory" properties are proposed to be used for explanations. Our system exploits ML models and more user-oriented Expert Knowledge using a wider range of properties for objects to build a more profound XAI. © 2024 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

EDB-Net: An Edge-Guided Dual-Branch Neural Network for Skin Cancer Classification 27th

EDB-Net: An Edge-Guided Dual-Branch Neural Network for Skin...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ray, Amartya Gayen, Soumyajit Kaplun, Dmitrii Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9783031781032

Skin cancer poses a serious global health challenge, where timely and precise diagnosis is essential to improve patient outcomes. Recently, neural networks have proven to be highly effective tools for automated skin cancer classification, significantly advancing the field of dermatology. This paper introduces a novel approach to generate edge maps from dermoscopic images using a holistically nested edge detector model. These edge maps enhance the detection of shape and symmetry irregularities, which are key indicators of malignancy, and improve the focus on relevant regions of interest. We then propose an edge-guided dual-branch neural network, called EDB-Net, for the classification task. Branch 1 handles edge maps, while Branch 2 processes original dermoscopic images. To highlight significant regions and focus on specific lesion areas, we incorporate a novel channel-spatial synergistic attention block within Branch 2. Additionally, we introduce a unique strategy to modulate the generated attention maps using edge features extracted from the edge maps in Branch 1, creating edge-guided features that refine the overall feature representation. In the final stage, both edge-guided and attention-aided features are combined, producing more distinct and contextually relevant outputs, thereby significantly enhancing classification performance. Our model achieves accuracies of 0.927 and 0.848 on the challenging HAM10000 and ISIC 2016 datasets, respectively, without employing any data augmentation. The source code of the proposed model is available at: https://***/Cmatermedicalimageanalysis/EDB_Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Wide-Swing CMOS Multiplier for AC Source Signal Tracking and Modulation

引用

Circuits, Systems, and Signal Processing 2024年第9期43卷 5377-5400页

作者： Wang, Wei Xu, Sendren Sheng-Dong Chen, Chi-Lin Chiu, Huang-Jen Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei 106335 Taiwan Graduate Institute of Automation and Control National Taiwan University of Science and Technology Taipei 106335 Taiwan Advanced Manufacturing Research Center National Taiwan University of Science and Technology Taipei 106335 Taiwan Himax Technologies Inc. Taipei 100507 Taiwan

The multiplier is a pervasive critical component today. However, most of them are difficult to be integrated into an integrated circuit. In this study, we proposed a novel analog multiplier for AC power application, using CMOS process to realize the analog voltage multiplication function of double-ended input and single-ended output. Under the working voltage of 3.3 V, the multiplier can operate with a wide input voltage range of 0–1.6 V (about 48.8% of the working voltage) and a wide output voltage range of 0–2.56 V (about 77.5% of the working voltage). The multiplier is implemented through the current difference between two NMOSs operating in the linear region and the saturation region, respectively. Compared with the existing technique, the proposed analog multiplier has a wider input and output range, and better linearity. It is suitable for AC power signal tracking and modulation. Finally, the United Microelectronics Corporation 0.18 μm 1P4M CMOS standard process was used for physical implementation. Moreover, there is not any BJT or special device used. It was measured that the analog multiplier circuit consumes about 0.56 mW at a working voltage of 3.3 V. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： AC power signal modulation AC source signal tracking Analog integrated circuit (IC) design Analog multipliers Circuits and systems

来源：评论

学校读者我要写书评

暂无评论

On the relationship between the activity at point of interests and road traffic

引用

Communications in Transportation research 2023年第1期3卷 150-160页

作者： MátéKolat Tamás Tettamanti TamásBécsi Domokos Esztergár-Kiss Department of Control for Transportation and Vehicle Systems Faculty of Transportation Eng.and Vehicle Eng.Budapest University of Technology and EconomicsBudapest1111PestHungary Systems and Control Laboratory Institute for Computer Science and Control of the Eötvös Lorand Research NetworkBudapest1053PestHungary Department of Transport Technology and Economics Faculty of Transportation Eng.and Vehicle Eng.Budapest University of Technology and EconomicsBudapest1111PestHungary

The estimation and analysis of road traffic represent the preliminary steps towards satisfying the current needs for smooth,safe,and green ***,effective traffic monitoring is an essential topic alongside the planning of sustainable transportation systems and the development of new traffic management *** contrast to classical traffic detection solutions,this study investigates the correlation between travelers'social activities and road *** s's primary goal is to investigate the presence of the relationship between social activity and road traffic,which might allow an infrastructure-independent traffic monitoring technique as ***'s general activities at Point of Interest(POI)locations(measured as occupancy parameter)are correlated with traffic data so that,finally,proper proxys can be defined for link-level average traffic speed *** method is tested and evaluated using real-world traffic and POI occupancy data from Budapest(District XI.).The results of the correlation investigation justify an indirect relationship between activity at POIs and road traffic,which holds promise for future practical applicability.

关键词： Road traffic estimation Google popular times(GPT) Point of interest(POI) POI occupancy Genetic algorithm(GA)

来源：评论

学校读者我要写书评

暂无评论

Dorsal Hand Vascular Imaging System

Dorsal Hand Vascular Imaging System

引用

2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Mizinov, Pavel V. Konnova, Natalia S. Kravchenko, Oleg V. Egorov, Dobroslav P. Osipenko, Gavriil V. Bauman Moscow State Technical University Department Of Information Security Moscow Russia Computer Science And Control Of Ras Federal Research Center Moscow Russia Kotel'nikov Institute Of Radio Engineering And Electronics Of Ras Moscow Russia Moscow Aviation Institute Moscow Russia

ISBN: (纸本)9798350362893

Biometric identification methods using vascular modalities (vein pattern of the finger, wrist, ventral and dorsal part of the metacarpal) use near infrared (NIR) illumination to obtain an image of the vein pattern. The 'classic' attack scenario for this type of biometric system involves the use of a photograph of the user's vein pattern, printed on ordinary office paper and obtained under NIR illumination, as a presentation attack tool. This attack scenario has been well studied by researchers and there are several reliable ways to detect such an attack. New biometric attack vectors on these systems involve the use of attack tools created using NIR reflective compounds. In order to develop effective methods to detect and counter this type of attack, it is necessary to study the characteristics of the attack tool in each of the 750-950 nm NIR sub-bands of the venous channel imaging band. In this paper, the authors present the stages of creating a hardware tool for obtaining an image of the vascular pattern to solve the problem at hand. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

SIFT-based Approach for Dorsal Hand Veins Images Recognition 26

SIFT-based Approach for Dorsal Hand Veins Images Recognition

引用

26th International Conference on Digital Signal Processing and its Applications, DSPA 2024

作者： Egorov, Dobroslav P. Mizinov, Pavel V. Kravchenko, Oleg V. Konnova, Natalia S. Osipenko, Gavriil V. Kotel'nikov Institute of Radio Engineering and Electronics of Ras Moscow Russia Bauman Moscow State Technical University Department of Information Security Moscow Russia Computer Science and Control of Ras Federal Research Center Moscow Russia Moscow Aviation Institute Moscow Russia

ISBN: (纸本)9798350361728

In this paper we present a system for person identification using dorsal hand veins pattern images. A simple approach is developed based on scale-invariant feature transform (SIFT) method for image features extraction, fast approximate nearest neighbors algorithm (FLANN) for keypoints matching in a preselected region-of-interest (ROI), and subsequent utilization of dense layer neural network for accurate friend-or-foe predictions. The efficiency of the considered approach is evaluated using an open dataset, and confusion matrices are calculated. The obtained results confirm again that dorsal hand veins identification systems are particularly promising for high-security settings. The proposed approach is implemented in software for Orange pi single-board computers. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A network-based bioinformatic analysis for identifying potential repurposable active molecules in different types of human cancers

A network-based bioinformatic analysis for identifying poten...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Brunetti, Martina Paci, Paola Fiscon, Giulia Sapienza University of Rome Department of Computer Control and Management Engineering 'A. Ruberti' Rome Italy Karolinska Institutet Stockholm Sweden National Research Council of Rome Institute for Systems Analysis and Computer Science 'A. Ruberti' Rome Italy

ISBN: (纸本)9798350337488

Drug repurposing, also known as drug repositioning, is the process of identifying novel therapeutic indications for existing drugs, offering a cost-effective and time-efficient strategy to drug discovery. In this context, we developed a network-based algorithm, named SAveRUNNER (Searching off-lAbel dRUg aNd NEtwoRk), which predicts drug-disease associations by accounting for the interaction between the drug targets and disease-associated genes in the human interactome, implementing a novel network-based similarity measure that prioritizes associations between drugs and diseases locating in the same network neighborhoods. Following its successful applications to different disorders (such as viral infections and neurological diseases), in this study, we applied SAveRUNNER on a panel of 13 types of cancers using both disease-associated genes downloaded from widely-used databases and from gene expression data. © 2023 IEEE.

关键词： Drug Repurposing Network Medicine Network Theory

来源：评论

学校读者我要写书评

暂无评论

Template-based text field segmentation for ID documents using dynamic squeezeboxes packing

引用

Multimedia Tools and Applications 2024年 1-15页

作者： Zingerenko, Michael Limonova, Elena Arlazarov, Vladimir V. Moscow Institute of Physics and Technology 9 Institutskiy perDolgoprudnii 141701 Russia Smart Engines Service LLC Prospekt 60-Letiya Oktyabrya 9 Moscow117312 Russia Federal Research Center "Computer Science and Control" of Russian Academy of Sciences Ulitsa Vavilova 44 Moscow119333 Russia

In this paper, we focus on the problem of text field segmentation in identity documents. These documents, characterized by their fixed layouts, present an opportunity to apply computationally efficient template-based algorithms. We consider the Dynamic Squeezeboxes Packing method and demonstrate its integration into document recognition systems, utilizing a single sample per document type. We benchmark text field segmentation on the MIDV-2019 public dataset using standard intersection-over-union and our custom intersection-over-template metrics, while also measuring processing time. We demonstrate that Dynamic Squeezeboxes Packing maintains competitive quality compared to text in the wild methods (EAST, CRAFT) and named-entity recognition method (LayoutLMv2). A significant advantage of this method is its processing speed, averaging 9 ms per image on the x86_64 platform, which is substantially faster than EAST (980 ms), CRAFT (2030 ms), and LayoutLMv2 (2210 ms). The obtained results suggest that the considered method has strong potential as a method in document image analysis, particularly for processing identity documents. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

How capable are state-of-the-art language models to cope with sarcasm? 24

How capable are state-of-the-art language models to cope wit...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Baroiu, Alexandru -Costin Trausan-Matu, Stefan Politehnica University of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania Romanian Academy Research Institute for Artificial Intelligence 'Mihai Drǎganescu' Academy of Romanian Scientists Bucharest Romania

ISBN: (纸本)9798350313390

Sarcasm detection has established itself as one of the more difficult Natural Language Processing tasks, due to the complex nature of sarcasm. This paper aims to benchmark the performance of state-of-the-art models like BERT, RoBERTa, ALBERT and GPT-3 when faced with this task. The dataset selected is MUStARD, which has increased in popularity in recent years, especially for multimodal tasks, and is one of the most qualitative and data rich dataset. An untuned GPT-3 based model was selected as the baseline and all the other models were fine-tuned using the textual data present in MUStARD, mainly the context and utterance information. The best performer was found to be the GPT-3 fine-tuned model, with an F1 score of 77. This is in line with the reported feats of GPT-3 based models that have popularized in recent months and reaffirms the superiority of GPT-3. Future avenues of research are then presented and explored, and the conclusions are drawn. © 2023 IEEE.

关键词： Benchmarking

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：