检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhu, Yan Zhu, Jingyang Wang, Ting Shi, Yuanming Jiang, Chunxiao Letaief, Khaled Ben MoE Engineering Research-Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University Shanghai200062 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Advancements in artificial intelligence (AI) and low-earth orbit (LEO) satellites have promoted the application of large remote sensing foundation models for various downstream tasks. However, direct downloading of these models for fine-tuning on the ground is impeded by privacy concerns and limited bandwidth. Satellite federated learning (FL) offers a solution by enabling model fine-tuning directly on-board satellites and aggregating model updates without data downloading. Nevertheless, for large foundation models, the computational capacity of satellites is insufficient to support effective on-board fine-tuning in traditional satellite FL frameworks. To address these challenges, we propose a satellite-ground collaborative federated fine-tuning framework. The key of the framework lies in how to reasonably decompose and allocate model components to alleviate insufficient on-board computation capabilities. During fine-tuning, satellites exchange intermediate results with ground stations or other satellites for forward propagation and back propagation, which brings communication challenges due to the special communication topology of space transmission networks, such as intermittent satellite-ground communication, short duration of satellite-ground communication windows, and unstable inter-orbit inter-satellite links (ISLs). To reduce transmission delays, we further introduce tailored communication strategies that integrate both communication and computing resources. Specifically, we propose a parallel intra-orbit communication strategy, a topology-aware satellite-ground communication strategy, and a latency-minimalization inter-orbit communication strategy to reduce space communication costs. Simulation results demonstrate significant reductions in training time with improvements of approximately 33%. Copyright © 2025, The Authors. All rights reserved.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Industrial Smoke Image Segmentation Based on a New Algorithm of Cross-Entropy Model 16th

Industrial Smoke Image Segmentation Based on a New Algorithm...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Huang, Qian-Jing Zou, Le Wu, Zhi-Ze Li, Huan-Yi Wang, Xiao-Feng Chen, Yan-Ping Department of Environmental Engineering Hefei University HefeiAnhui230601 China Anhui Provincial Engineering Laboratory of Big Data Technology Application for Urban Infrastructure Department of Computer Science and Technology Hefei University Hefei230601 China Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei University HefeiAnhui230601 China

ISBN: (纸本)9783030607982

Smoke segmentation from the industrial images is a key concern of environmental monitoring. As the similarities between the gray value of the background and the smoke, the existing segmentation algorithms are difficult to accurately segment the target smoke. In this paper, we construct a cross-entropy based industrial smoke image segmentation by integrating the iterative convolution-thresholding. Specially, we use the iterative convolution-thresholding to implicitly represent the interface of each image domain through a characteristic function. We further perform the combination of a regularization term and a fidelity term in the cross-entropy model. In the proposed algorithm, the fidelity term is first converted into the product of the characteristic function and the cross-entropy function. Then the functional of the characteristic function is used to obtain the regularization term by the approach of thermonuclear convolution approximation. The experimental results demonstrate that our proposal has a more accurate segmentation effect and higher segmentation efficiency. © 2020, 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

Literature Review of Religion Video Game

Literature Review of Religion Video Game

引用

2019 International Congress on Applied Information technology, AIT 2019

作者： Wibawa, Setya Chendra Rahayu, Yuni Sri Wrahatnolo, Tri Vindy, V. Warnars, Harco Leslie Hendric Spits Hashimoto, Kiyota Universitas Negeri Surabaya Jawa Timur Informatics Department 60213 Indonesia Universitas Negeri Surabaya Jawa Timur Biology Department 60213 Indonesia Universitas Negeri Surabaya Jawa Timur Electrical Engineering Department 60213 Indonesia Game Application Technology Program School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Faculty of Technology and Environment Prince Songkla University Thailand

ISBN: (纸本)9781728158624

In this current digital era, the video game is favorite especially among young people. Besides widely known as a form of entertainment, some messages or lessons can be learned from a video game that may affect the players. Conscious or unconscious, games have influenced many sectors of life, and it has been recognized as a serious game and no exception to religion. Human as a living creature, like or dislike or even as an atheist should believe with something out there, and religion is as a medium which connects human with something out there. The game as a representation of entertaining, intelligent application will represent joy and happiness in human life's activities, and inevitably games will influence human religion. In the end, religion game will help the human to increase their faith in those their belief based on their religion. Similar to Information technology which is implemented in business to increase revenue, the game as an entertaining intelligent application will increase human's faith. One kind of video game that provides it is religion video games which are the result of the incorporation between religion and video games. In this paper, we do a literature review about religion video games. We try to summarize how religious elements can be incorporated into a video game which can be seen from the parts, components, and approaches of the religion video game itself. We also try to summarize the positive side and controversies in religion video games. © 2019 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Factors that Influence Learning Experience through Game Based Learning using Visual Novel Game for Learning Pancasila

引用

Procedia computer science 2019年 157卷 353-359页

作者： J Andrew S Henry A.N. Yudhisthira Yulyani Arifin Syarifah Diana Permai Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Statistics Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Games are not only used as a means of entertainment but also can be used as a learning tool. Attractive learning tools can increase the interest of young people or millennial generations, especially for learning conceptual or too theoretical. Pancasila as the basis of the Indonesian nation’s life view needs to be understood by the Indonesian people, especially the younger generation. But the way of learning about the Pancasila is currently too theoretical and does not attract young people. Therefore, by making the game that is liked and favorited by young people today is used to study the Pancasila. Through this research the author wants to analyze the factors that can affect learning experience using game-based learning. Researchers use multiple linear regression methods to analyze these factors. The game prototype developed in this study uses the visual novel genre which has an interesting story. There are 101 respondents as samples. The analysis showed that there are two factors that influence game-based learning, namely the gameplay factor and the story of the game. So, it can be concluded that for developing game based learning we need to pay attention to these two factors and through this visual novel prototype game, it can be concluded that the prototype of this game has an interesting game play and a story that is easy to understand.

关键词： Game Based Learning Gamification Visual Novel Pancasila Regression Analysis

来源：评论

学校读者我要写书评

暂无评论

Single-nucleus chromatin accessibility profiling highlights regulatory mechanisms of coronary artery disease risk (vol 54, pg 804, 2022)

引用

NATURE GENETICS 2022年第8期54卷 1259-1259页

作者： Turner, Adam W. Hu, Shengen Shawn Mosquera, Jose Verdezoto Ma, Wei Feng Hodonsky, Chani J. Wong, Doris Auguste, Gaelle Song, Yipei Sol-Church, Katia Farber, Emily Kundu, Soumya Kundaje, Anshul Lopez, Nicolas G. Ma, Lijiang Ghosh, Saikat Kumar B. Onengut-Gumuscu, Suna Ashley, Euan A. Quertermous, Thomas Finn, Aloke V. Leeper, Nicholas J. Kovacic, Jason C. Bjorkegren, Johan L. M. Zang, Chongzhi Miller, Clint L. Center for Public Health Genomics University of Virginia Charlottesville VA USA Department of Biochemistry and Molecular Genetics University of Virginia Charlottesville VA USA Medical Scientist Training Program University of Virginia Charlottesville VA USA Department of Pathology University of Virginia Charlottesville VA USA Robert M. Berne Cardiovascular Research Center University of Virginia Charlottesville VA USA Genome Sciences Laboratory University of Virginia Charlottesville VA USA Department of Public Health Sciences University of Virginia Charlottesville VA USA Genome Analysis & Technology Core University of Virginia Charlottesville VA USA Department of Genetics Stanford University School of Medicine Stanford CA USA Department of Computer Science Stanford University Stanford CA USA Division of Cardiovascular Medicine Department of Medicine Stanford University Stanford CA USA Division of Vascular Surgery Department of Surgery Stanford University Stanford CA USA Department of Genetics and Genomic Sciences Icahn Institute for Genomics and Multiscale Biology Icahn School of Medicine at Mount Sinai New York NY USA Integrated Cardio Metabolic Centre Department of Medicine Karolinska Institutet Huddinge Sweden CVPath Institute Gaithersburg MD USA Cardiovascular Research Institute Icahn School of Medicine at Mount Sinai New York NY USA Victor Chang Cardiac Research Institute Darlinghurst New South Wales Australia St. Vincent’s Clinical School University of New South Wales Sydney New South Wales Australia

Coronary artery disease (CAD) is a complex inflammatory disease involving genetic influences across cell types. Genome-wide association studies have identified over 200 loci associated with CAD, where the majority of risk variants reside in noncoding DNA sequences impactingcis-regulatory elements. Here, we applied single-nucleus assay for transposase-accessible chromatin with sequencing to profile 28,316 nuclei across coronary artery segments from 41 patients with varying stages of CAD, which revealed 14 distinct cellular clusters. We mapped ~320,000 accessible sites across all cells, identified cell-type-specific elements and transcription factors, and prioritized functional CAD risk variants. We identified elements in smooth muscle cell transition states (for example, fibromyocytes) and functional variants predicted to alter smooth muscle cell- and macrophage-specific regulation ofMRAS(3q22) andLIPA(10q23), respectively. We further nominated key driver transcription factors such as PRDM16 and TBX2. Together, this single-nucleus atlas provides a critical step towards interpreting regulatory mechanisms across the continuum of CAD risk.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Magnetic and levitation properties of YBCO/polymer composite drop-casting films

Next Materials

引用

Next Materials 2025年 8卷

作者： Beatriz Lucas Miguel Brito Canan Aksoy Bakiye Cakir Elvan Coşkun Ali Gencer Anabela Pronto Isabel Ferreira CENIMAT|i3N Department of Materials Science School of Science and Technology NOVA University Lisbon Caparica Portugal Electrical and Computer Engineering Department School of Science and Technology NOVA University Lisbon Caparica Portugal Electronics and Communication Engineering Faculty of Technology Karadeniz Technical University Trabzon 61830 Turkiye Vocational School of Health Services Artvin Çoruh University Artvin 08000 Turkiye Ankara University Superconductor Technologies Application and Research Center Gölbaşı Ankara Turkiye Ankara University Faculty of Sciences Physics Department Ankara 06100 Turkiye Center of Technology and Systems CTS/UNINOVA School of Science and Technology NOVA University Lisbon Caparica Portugal

Superconducting materials have been extensively studied for various applications, with YBCO alloys among the most researched and widely applied. This paper investigates the feasibility of using YBCO powder-based inks to produce cost-effective films with magnetic properties. Our studies demonstrate that levitation in liquid nitrogen is consistently observed in all fabricated films, regardless of ink composition or application method. Both drop-casting and spray-coating techniques were successfully employed to create levitating films. Additionally, various substrates—including aluminum foil (with and without adhesive), plastic foil, Teflon, and paper—were evaluated, with no significant impact on levitation performance. The levitation height was also compared to samples without a substrate. Depending on the binder, the resulting films exhibit rigidity or flexibility while maintaining their levitation capabilities even after multiple bending cycles. However, film conductivity is influenced by the binder type and concentration, which also affects the critical current density. A film with a thickness of 300 μm demonstrated a Jc of 2 kA/cm² at 65 K and zero magnetic field.

关键词： YBCO superconductor powders Polymers superconductor hybrid materials Selfsustained drop-casting films Levitation and magnetic properties Surface and chemical analysis

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search for Optimization of Spatial-Temporal Brain Network Decomposition 23rd

Neural Architecture Search for Optimization of Spatial-Tempo...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Li, Qing Zhang, Wei Lv, Jinglei Wu, Xia Liu, Tianming School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States Department of Biomedical Engineering University of Melbourne ParkvilleVIC Australia

ISBN: (纸本)9783030597276

Using neural networks to explore spatial patterns and temporal dynamics of human brain activities has been an important yet challenging problem because it is hard to manually design the most optimal neural networks. There have been several promising deep learning methods that can decompose neuroscientifically meaningful spatial-temporal patterns from 4D fMRI data, e.g., the deep sparse recurrent auto-encoder (DSRAE). However, those previous studies still depend on hand-crafted neural network structures and hyperparameters, which are not optimal in various senses. In this paper, we employ evolutionary algorithms to optimize such DSRAE neural networks by minimizing the expected loss of the generated architectures on data reconstruction via the neural architecture search (NAS) framework, named NAS-DSRAE. The optimized NAS-DSRAE is evaluated by the publicly available human connectome project (HCP) fMRI datasets and our promising results showed that NAS-DSRAE has sufficient generalizability to model the spatial-temporal features and is better than the hand-crafted model. To our best knowledge, the proposed NAS-DSRAE is among the earliest NAS models that can extract connectome-scale meaningful spatial-temporal brain networks from 4D fMRI data. © 2020, Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes

arXiv

引用

arXiv 2023年

作者： Huang, Shijie Zhang, Xukun Cui, Zhiming Zhang, He Chen, Geng Shen, Dinggang School of Biomedical Engineering ShanghaiTech University Shanghai China Academy for Eng. & Tech. Fudan University Shanghai China Department of Radiology Obstetrics and Gynecology Hospital of Fudan University Shanghai China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence company Ltd. Shanghai200030 China Shanghai Clinical Research Trial Center Shanghai201210 China

Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality volumes to thick-slice scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans. Extensive experiments on a large-scale dataset of 372 clinically acquired thick-slice MR scans demonstrate that our C2DA-Net achieves much better performance than cutting-edge methods quantitatively and qualitatively. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

A Design of Crowd-Based Corruption Prevention System in Indonesia: Indonesia Corruption Map 4

A Design of Crowd-Based Corruption Prevention System in Indo...

引用

4th International Conference on Information Management and technology, ICIMTech 2019

作者： Nurlina Kristin, Desi Maya Muqsith, Andi Muhammad Mursitama, Tirta Nugraha Sasmoko Makalew, Brilly Andro Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Primary Teacher Education Bina Nusantara University Jakarta11480 Indonesia Mobile Application Technology Program School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

Combatting corruption requires not only centralized and institution-based strategy, but must be met with distributive effort supported by abundance of data and technological advancement. This work tackles the issue of decentralized corruption prevention by describing the method of doing heuristic analysis based on multiple data regarding corruption. There are four main data source used for the input of the system in this work, where each data corresponds to a city in a region. All the data are processed into corresponding index, while the indexes will be further used in index interpretation and suggestion mapping process. The output of this system is a decision support system for relevant decision making related to corruption prevention, visualized using Google Map API. This system will be very powerful in the long and tedious war against corruption, when used to its maximum potential. © 2019 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Applying mobility business intelligence concept in analyzing oil palm plantation productivity

引用

AIP Conference Proceedings 2024年第1期3026卷

作者： Andreas Wahyu Krisdiarto Irya Wisnubhadra Anzaludin Samsinga Perbangsa Teddy Suparyanto Bens Pardamean Faculty of Agricultural Technology STIPER Institute of Agriculture Yogyakarta Indonesia Informatics Engineering Department Atma Jaya Yogyakarta University Yogyakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia BDSRC Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

The palm oil business employs almost 20 million people, generates USD 21 billion in revenue, and plays a vital role in Indonesia’s social economy. The Fresh Fruit Bunches (FFB) to Palm Oil Mills (POM) distribution system is one important aspect of fruit quality. Three steps are involved in getting Oil Palm FFB from the plantation to the POM. The first part of the procedure involves cutting FFB from the tree, the second stage involves gathering the fruit at a fruit collection point (FCP), and the third stage involves transporting the fruit to the palm oil mill (POM). As of now, the cost of the FFB transportation is still considerable, accounting for roughly 15% to 20% of the FFB pricing. The use of the Business Intelligence (BI) idea in the oil palm harvesting system is presented in this study as a foundation for creating web-based applications.

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：