检索结果-内蒙古大学图书馆

KartalOl: a new deep neural network framework based on transfer learning for iris segmentation and localization task—new dataset for iris segmentation

引用

Iran Journal of computer Science 2023年第4期6卷 307-319页

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Ul. Nowowiejska 15/19 Warsaw 00-665 Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Faculty of Engineering Arak University Arak Iran Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Tehran Iran Stanford University Stanford United States

Iris segmentation and localization in unconstrained environments are challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature have somehow mitigated some of the above-mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture initialized with a pre-trained MobileNetV2 model. In addition, to better study the detectors in iris recognition scenarios, we have collected 1000 images. The provided dataset (KartalOl) is made publicly available for the research community. In the proposed framework, to have better generalization, we fine-tuned the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Likewise, data augmentation techniques are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa, along with the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The implementation source code of KartalOl is made publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © The Author(s) 2023.

关键词： Iris segmentation Localization MobileNetV2 model Unconstrained environment

来源：评论

学校读者我要写书评

暂无评论

Big data link stability-based path observation for network security

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data engineering and Communications Technologies 2021年 66卷 459-468页

作者： Arappali, Nedumaran Mekonnen, Melaku Tamene Tefera, Wondatir Teka Sundaram, B. Barani Karthika, P. Department of Electrical and Computer Engineering Wollo University Kombolcha Institute of Technology Kombolcha Ethiopia Department of Computer Science College of Informatics Bule Hora University Bule Hora Ethiopia Department of Computer Application Kalasalingam Univerity Viruthunagar Tamilnadu India

Wireless ad hoc network [WANET] systems are creating multihop communication structure between the mobiles to transfer the data groups. The remarkable qualities of remote frameworks cause the correspondence to interface among the conflicting mobiles. To manage high convey ability and biological blocks, most physical directing shows will not believe the stable associations during pack communication, which prompts the elevated delay and bundle reducing in the master-mind. The proposed research work recommends a way perception support physical steering convention that specifies POPR for WANET. The anticipated guiding show merges the relative partition, course and mid-expand forwarder center point with transfer thickness to propel data toward the objective in order to recover physical sending among the connection point. Multiplication results illustrate the projected directing convention, which performs superior to the existing arrangements. © The Author(s).

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Improving bot detection of fake followers on Twitter via a hybrid B-HC optimisation algorithm

Improving bot detection of fake followers on Twitter via a h...

引用

International Conference on Electronics, Communication and Computing Technologies (ICECCT)

作者： Haider Alzeyadi Fecir Duran Department of Computer Science Informatics Institute Gazi University Ankara Turkey Department of Computer Engineering Engineering Faculty of Technology Gazi University Ankara Turkey

Sophisticated cyber threats are seen on Online Social Networks (OSNs) social media accounts automated to imitate human behaviours has an impactful effect on distorting public thoughts and opinions. OSNs are weaponized to diffuse deception, misinformation, and malicious activities, that forms a serious threat to society. The deceptive nature of imitating human behaviour has become a challenging and crucial task to detect automated accounts (socialbots). This research, however, proposes a hybrid metaheuristic optimisation algorithm for socialbot detection. Specifically, a hybrid B-Hill Climbing (B-HC) optimisation algorithm works in tandem with a k-NN nearest neighbour classifier to accurately select a relevant feature subset. It is applied to be tested for fake followers account on Twitter data. Experimental results showed that the proposed method is better than the traditional and the latest feature selection techniques as well as the rule-set methods. The B-HC alongside with k-NN method achieved promising results using only relevant feature subset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WildGaussians: 3D Gaussian Splatting in the Wild 38

WildGaussians: 3D Gaussian Splatting in the Wild

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kulhanek, Jonas Peng, Songyou Kukelova, Zuzana Pollefeys, Marc Sattler, Torsten Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czech Republic Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic Department of Computer Science ETH Zurich Switzerland Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Day and Night Cycle Impact in a Serious VR Game

Dynamic Day and Night Cycle Impact in a Serious VR Game

引用

Virtual Reality (ICVR), IEEE International Conference on

作者： Fardani Annisa Damastuti Kenan Firmansyah Yunifa Miftachul Arif Ali Ridho Barakbah Mochamad Hariadi Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Creative Multimedia Technology Electronic Engineering Polytechnic Institute of Surabaya Surabaya Indonesia Department of Informatics Engineering Universitas Islam Negeri Maulana Malik Ibrahim Malang Indonesia Department of Informatics and Computer Engineering Electronic Engineering Polytechnic Institute of Surabaya Surabaya Indonesia Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350364231

ISBN: (纸本)9798350364248

The immersive nature of virtual reality (VR) gaming is significantly improved by the implementation of dynamic environmental systems. This paper focuses on the development and impact of a dynamic day and night cycle in a serious VR game. This feature is intended to simulate a full 24-hour cycle within a 10-minute gameplay session, resulting in a seamless transition between different times of day that impacts both the visual aesthetics and gameplay mechanics. The day and night cycle introduces strategic depth by requiring players to adjust their management strategies according to the time of day, which affects resource availability, operational efficiency, and conditions. This system not only enhances visual fidelity but also directly impacts gameplay, necessitating that player modify their strategies in response to the changing environment. Visual aesthetics are expected to increase by 15%, strategic profundity will be improved by 20%, and player immersion will be enhanced by 25%, according to the research findings. This investigation underscores the importance of natural cycles in enhancing the strategic complexity, interactivity, and realism of virtual reality environments, thereby offering valuable insights for the creation of future virtual reality games.

关键词： Visualization Accuracy Virtual reality Games Immersive experience Hardware Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Reducing ADC Front-end Costs During Training of On-sensor Printed Multilayer Perceptrons

arXiv

引用

arXiv 2024年

作者： Afentaki, Florentia Duarte, Paula Carolina Lozano Zervakis, Georgios Tahoori, Mehdi B. Computer Engineering & Informatics Dept. University of Patras Patras26504 Greece Department of Computer Science Karlsruhe Institute of Technology Karlsruhe76131 Germany

Printed electronics technology offers a cost-effective and fully-customizable solution to computational needs beyond the capabilities of traditional silicon technologies, offering advantages such as on-demand manufacturing and conformal, low-cost hardware. However, the low-resolution fabrication of printed electronics, which results in large feature sizes, poses a challenge for integrating complex designs like those of machine learning (ML) classification systems. Current literature optimizes only the Multilayer Perceptron (MLP) circuit within the classification system, while the cost of analog-to-digital converters (ADCs) is overlooked. Printed applications frequently require on-sensor processing, yet while the digital classifier has been extensively optimized, the analog-to-digital interfacing, specifically the ADCs, dominates the total area and energy consumption. In this work, we target digital printed MLP classifiers and we propose the design of customized ADCs per MLP’s input which involves minimizing the distinct represented numbers for each input, simplifying thus the ADC’s circuitry. Incorporating this ADC optimization in the MLP training, enables eliminating ADC levels and the respective comparators, while still maintaining high classification accuracy. Our approach achieves 11.2x lower ADC area for less than 5% accuracy drop across varying MLPs. Copyright © 2024, The Authors. All rights reserved.

关键词： Comparator circuits

来源：评论

学校读者我要写书评

暂无评论

Performing Aerobatic Maneuver with Imitation Learning 23rd

Performing Aerobatic Maneuver with Imitation Learning

引用

23rd International Conference on Computational Science, ICCS 2023

作者： Freitas, Henrique Camacho, Rui Silva, Daniel Castro Department of Informatics Engineering Faculty of Engineering University of Porto Rua Dr. Roberto Frias s/n. Porto4200-465 Portugal LIAAD/INESC TEC - Artificial Intelligence and Decision Support Laboratory/Institute for Systems and Computer Engineering Technology and Science Porto Portugal LIACC - Artificial Intelligence and Computer Science Laboratory Porto Portugal

ISBN: (纸本)9783031359941

The work reported in this article addresses the challenge of building models for non-trivial aerobatic aircraft maneuvers in an automated fashion. It is built using a Behavioural Cloning approach where human pilots provide a set of example maneuvers used by a Machine Learning algorithm to induce a control model for each maneuver. The best examples for each maneuver were selected using a set of objective evaluation metrics. Using those example sets, robust models were induced that could replicate (and in some cases outperform) the human pilots that provided the examples (the clean-up effect). Complete complex maneuvers were performed using a meta-controller capable of sequencing the basic ones learned by imitation. This endeavor was rewarded by the results that show several Machine Learning models capable of performing highly complex aircraft maneuvers. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

3D Skull Completion via Two-stage Conditional Diffusion-Based Signed Distance Fields

3D Skull Completion via Two-stage Conditional Diffusion-Base...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Zhenhong Ru, Xudong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Zhang, Chong Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China Bioimage Analysis Barcelona Spain School of Engineering University of Manchester Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Department of Computer Science United Kingdom Department of Cardiovascular Sciences Department of Electrical Engineering Leuven Belgium Alan Turing Institute London United Kingdom

ISBN: (纸本)9798350386226

A fast and fully automatic design of 3D cranial implants is highly desired in cranioplasty, and is key to the treatment of skull trauma. We have defined the repair of skull defects as a 3D shape completion task by proposing a two-stage diffusion model based on the representation of 3D shapes using signed distance function (SDF). Specifically, we design a diffusion model conditioned on partial shapes, we compress the 3D shape into a compact latent representation using the encoder in the vector quantized variational autoencoder (VQ-VAE) and learn the diffusion model based on this compressed discrete representation. Encoding the latent space with the autoencoder can achieve high-quality 3D cranial shape completion. In order to accurately capture local and fine-grained shape details, the training data is geometrically encoded from a compactly learned code-book. The two-stage diffusion generator with a coarse-to-fine approach possesses precise and expressive structural modeling capabilities to ensure the supplementation of detailed geometric information. Experimental results verified sufficient expressiveness of our model with generating high-fidelity results with fine-grained local details, outperforming the state-of-the-art methods. © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Slice-Fusion: Reducing False Positives in Liver Tumor Detection for Mask R-CNN

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2023年第5期20卷 3267-3277页

作者： Tu, Deng-Yao Lin, Peng-Chan Chou, Hsin-Hung Shen, Meng-Ru Hsieh, Sun-Yuan National Cheng Kung University Master Degree Program on Artificial Intelligence Tainan City70101 Taiwan National Cheng Kung University Institute of Medical Informatics Department of Oncology Department of Genomic Medicine National Cheng Kung University Hospital College of Medicine Department of Computer Science and Information Engineering Tainan City70101 Taiwan National Chi Nan University Department of Computer Science and Information Engineering Nantou County54561 Taiwan National Cheng Kung University Graduate Institute of Clinical Medicine Department of Obstetrics and Gynecology Department of Pharmacology National Cheng Kung University Hospital College of Medicine Tainan City70101 Taiwan National Cheng Kung University Institute of Medical Information Institute of Manufacturing Information and Systems Center for Innovative FinTech Business Models International Center for the Scientific Development of Shrimp Aquaculture Department of Computer Science and Information Engineering Tainan City70101 Taiwan

Automatic liver tumor detection from computed tomography (CT) makes clinical examinations more accurate. However, deep learning-based detection algorithms are characterized by high sensitivity and low precision, which hinders diagnosis given that false-positive tumors must first be identified and excluded. These false positives arise because detection models incorrectly identify partial volume artifacts as lesions, which in turn stems from the inability to learn the perihepatic structure from a global perspective. To overcome this limitation, we propose a novel slice-fusion method in which mining the global structural relationship between the tissues in the target CT slices and fusing the features of adjacent slices according to the importance of the tissues. Furthermore, we design a new network based on our slice-fusion method and Mask R-CNN detection model, called Pinpoint-Net. We evaluated proposed model on the Liver Tumor Segmentation Challenge (LiTS) dataset and our liver metastases dataset. Experiments demonstrated that our slice-fusion method not only enhance tumor detection ability via reducing the number of false-positive tumors smaller than 10mm, but also improve segmentation performance. Without bells and whistles, a single Pinpoint-Net showed outstanding performance in liver tumor detection and segmentation on LiTS test dataset compared with other state-of-the-art models. © 2004-2012 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Automated Estimation of Left Myocardial Strain from Cine CTA: A Comparison with Cine MRI

Automated Estimation of Left Myocardial Strain from Cine CTA...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Sun, An-Yu Hsu, Li-Yueh Chang, Lin-Ching Bandettini, W Patricia Chen, Marcus Y. National Institutes of Health National Heart Lung and Blood Institute BethesdaMD United States Catholic University of America Department of Electrical Engineering and Computer Science WashingtonDC United States National Institutes of Health Clinical Center BethesdaMD United States New Jersey Institute of Technology Department of Informatics NewarkNJ United States

ISBN: (纸本)9798350362480

Cardiovascular disease, the leading cause of death in the U.S., affects both the heart and blood vessels. Contrast-enhanced cardiac computed tomography angiography (CTA) is a prominent imaging modality for assessing heart and coronary artery morphology, aiding in the diagnosis of cardiovascular disease. Cine CTA, which captures multiple 3D heart images throughout the cardiac cycle, is particularly useful for evaluating nonischemic cardiomyopathy, a common cause of heart failure unrelated to coronary artery disease. Key biomarkers, such as left ventricular ejection fraction, which measures the amount of blood pumped from the heart's lower chambers per contraction, and myocardial strain, which evaluates the deformation of the heart muscle during contraction and relaxation, are vital for assessing heart function. We developed an automated artificial intelligence (AI) framework to segment various cardiac structures across all image volumes representing different phases of the cardiac cycle. The framework also automatically extracts three short-axis slices to calculate the myocardial strain in the left ventricle. The results are compared with strain measurements obtained from cardiovascular magnetic resonance (CMR) cine imaging. Our study shows both radial and circumferential strains from cine CTA are comparable to those from cine CMR. The proposed AI framework facilitates a comprehensive evaluation of myocardial function throughout the cine CTA, supporting improved diagnostic accuracy. © 2024 IEEE.

关键词： computerized tomography

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：