Статті в журналах: "Multi-scale architecture"

1

Gao, Shang-Hua, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, and Philip Torr. "Res2Net: A New Multi-Scale Backbone Architecture." IEEE Transactions on Pattern Analysis and Machine Intelligence 43, no. 2 (February 1, 2021): 652–62. http://dx.doi.org/10.1109/tpami.2019.2938758.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Jayashankar, Vaishali, Irina A. Mueller, and Susanne M. Rafelski. "Shaping the multi-scale architecture of mitochondria." Current Opinion in Cell Biology 38 (February 2016): 45–51. http://dx.doi.org/10.1016/j.ceb.2016.02.006.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Knolle, Moritz, Georgios Kaissis, Friederike Jungmann, Sebastian Ziegelmayer, Daniel Sasse, Marcus Makowski, Daniel Rueckert, and Rickmer Braren. "Efficient, high-performance semantic segmentation using multi-scale feature extraction." PLOS ONE 16, no. 8 (August 19, 2021): e0255397. http://dx.doi.org/10.1371/journal.pone.0255397.

Повний текст джерела

Анотація:

The success of deep learning in recent years has arguably been driven by the availability of large datasets for training powerful predictive algorithms. In medical applications however, the sensitive nature of the data limits the collection and exchange of large-scale datasets. Privacy-preserving and collaborative learning systems can enable the successful application of machine learning in medicine. However, collaborative protocols such as federated learning require the frequent transfer of parameter updates over a network. To enable the deployment of such protocols to a wide range of systems with varying computational performance, efficient deep learning architectures for resource-constrained environments are required. Here we present MoNet, a small, highly optimized neural-network-based segmentation algorithm leveraging efficient multi-scale image features. MoNet is a shallow, U-Net-like architecture based on repeated, dilated convolutions with decreasing dilation rates. We apply and test our architecture on the challenging clinical tasks of pancreatic segmentation in computed tomography (CT) images as well as brain tumor segmentation in magnetic resonance imaging (MRI) data. We assess our model’s segmentation performance and demonstrate that it provides performance on par with compared architectures while providing superior out-of-sample generalization performance, outperforming larger architectures on an independent validation set, while utilizing significantly fewer parameters. We furthermore confirm the suitability of our architecture for federated learning applications by demonstrating a substantial reduction in serialized model storage requirement as a surrogate for network data transfer. Finally, we evaluate MoNet’s inference latency on the central processing unit (CPU) to determine its utility in environments without access to graphics processing units. Our implementation is publicly available as free and open-source software.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Akinniyi, Oluwatunmise, Md Mahmudur Rahman, Harpal Singh Sandhu, Ayman El-Baz, and Fahmi Khalifa. "Multi-Stage Classification of Retinal OCT Using Multi-Scale Ensemble Deep Architecture." Bioengineering 10, no. 7 (July 10, 2023): 823. http://dx.doi.org/10.3390/bioengineering10070823.

Повний текст джерела

Анотація:

Accurate noninvasive diagnosis of retinal disorders is required for appropriate treatment or precision medicine. This work proposes a multi-stage classification network built on a multi-scale (pyramidal) feature ensemble architecture for retinal image classification using optical coherence tomography (OCT) images. First, a scale-adaptive neural network is developed to produce multi-scale inputs for feature extraction and ensemble learning. The larger input sizes yield more global information, while the smaller input sizes focus on local details. Then, a feature-rich pyramidal architecture is designed to extract multi-scale features as inputs using DenseNet as the backbone. The advantage of the hierarchical structure is that it allows the system to extract multi-scale, information-rich features for the accurate classification of retinal disorders. Evaluation on two public OCT datasets containing normal and abnormal retinas (e.g., diabetic macular edema (DME), choroidal neovascularization (CNV), age-related macular degeneration (AMD), and Drusen) and comparison against recent networks demonstrates the advantages of the proposed architecture’s ability to produce feature-rich classification with average accuracy of 97.78%, 96.83%, and 94.26% for the first (binary) stage, second (three-class) stage, and all-at-once (four-class) classification, respectively, using cross-validation experiments using the first dataset. In the second dataset, our system showed an overall accuracy, sensitivity, and specificity of 99.69%, 99.71%, and 99.87%, respectively. Overall, the tangible advantages of the proposed network for enhanced feature learning might be used in various medical image classification tasks where scale-invariant features are crucial for precise diagnosis.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Reyes, J. A., and E. M. Stoudenmire. "Multi-scale tensor network architecture for machine learning." Machine Learning: Science and Technology 2, no. 3 (July 14, 2021): 035036. http://dx.doi.org/10.1088/2632-2153/abffe8.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Yang, Lintao, Pietro Liò, Xu Shen, Yuyang Zhang, and Chengbin Peng. "Adaptive multi-scale Graph Neural Architecture Search framework." Neurocomputing 599 (September 2024): 128094. http://dx.doi.org/10.1016/j.neucom.2024.128094.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Chuen, Alvin Lim Fang, Khoh Wee How, Pang Ying Han, and Yap Hui Yen. "In-Air Hand Gesture Signature Recognition Using Multi-Scale Convolutional Neural Networks." JOIV : International Journal on Informatics Visualization 7, no. 3-2 (November 30, 2023): 2025. http://dx.doi.org/10.30630/joiv.7.3-2.2359.

Повний текст джерела

Анотація:

The hand signature is a unique handwritten name or symbol that serves as a proof of identity. Due to its practicality and widespread use, hand signature is still used by financial institutions as a means of verifying and validating the identity of their customers. The emergence of the COVID-19 global pandemic has raised hygiene concerns regarding the conventional touch-based hand signature recognition system, which often requires sharing the acquisition devices among the public. This paper presents in-air hand gesture signature recognition using convolutional neural networks to address this concern. We designed a shallow multi-scale convolutional neural network using 3x3 and 5x5 kernel filter sizes to extract features on different scales. The feature maps from these two filters are then concatenated to provide more robust features, which improve the modelâ€™s performance.Â The experiment results show that the proposed architecture outperforms other architectures, which obtained the highest accuracy of 93.00%. On the other hand, our architecture consumed significantly fewer computational resources, requiring only an average of 3 minutes and 33 seconds to train. Additionally, the performance of the proposed architecture could be further enhanced by integrating it with recurrent neural networks (RNN). This integrated architecture of convolutional recurrent neural networks (C-RNN) can capture spatio-temporal features simultaneously.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Li, Bo, Guofeng Zhou, Wei Ge, Limin Wang, Xiaowei Wang, Li Guo, and Jinghai Li. "A multi-scale architecture for multi-scale simulation and its application to gas–solid flows." Particuology 15 (August 2014): 160–69. http://dx.doi.org/10.1016/j.partic.2013.07.004.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Shi, Lu, Xu Chen, Yuqian Xu, Xing Gao, Jialong Lai, and Shusheng Wang. "Towards an Effective Architectural Form: The Composition of Squareness and Roundness Based on Scale Proportion—Evidence from the Yingxian Wooden Pagoda." Buildings 14, no. 5 (May 18, 2024): 1472. http://dx.doi.org/10.3390/buildings14051472.

Повний текст джерела

Анотація:

Investigating the mathematical and geometric principles embedded in ancient classic architecture is a significant tradition in the history of architectural development. Drawing inspiration from the modular design and creative ideology based on the geometric proportions of squareness and roundness in ancient Chinese architecture, we propose a new mode of squareness and roundness composition based on scale proportion specifically for the design of multi-story buildings. Taking Yingxian Wooden Pagoda as the case study, we not only re-evaluate the modular system and proportional rules followed in the design of the entire pagoda, but also reveal the technical approaches and geometric rules for effectively controlling the form of multi-story buildings. In particular, the mode of squareness and roundness composition based on scale proportion, utilizing a modular grid combined with squareness and roundness drawings as decision-making tools, can control the scale and proportion of buildings across different design dimensions and organically coordinate the design of multi-story buildings’ plans and elevations. Thus, it can achieve an effective balance of multi-story architectural forms. This study has potential applications in the creation of traditional multi-story buildings and heritage restoration projects, and offers valuable insights for future research on ancient multi-story buildings.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Alotaibi, Hatim, Masoud Jabbari, Chamil Abeykoon, and Constantinos Soutis. "Numerical Investigation of Multi-scale Characteristics of Single and Multi-layered Woven Structures." Applied Composite Materials 29, no. 1 (January 24, 2022): 405–21. http://dx.doi.org/10.1007/s10443-022-10010-x.

Повний текст джерела

Анотація:

AbstractResin flow through multi-ply woven fabrics is affected by the fibre orientation and laminate stacking sequence during the impregnation process. This is characterised by permeability, which measures the ability of transferring fluids within a 2D or 3D layered woven fibre architecture (i.e., through a porous medium). The work aims to investigate the feasibility of characterising macro-scale flow permeability via the micro-meso-scale (dual-scale) permeability across and along woven yarns, with different structures of yarn nesting, non-shifting, and ply orientation. The permeability characterisation is performed using Ansys-Fluent software package where textile architectures and resin flow in porous media are simulated. The results show that in- and out-plane permeability of the nested, non-shifted and oriented single-ply woven preforms are different than that corresponding to multi-layered plates, making them only applicable for dual-scale permeabilities. However, with a number of plies in the multi-ply woven fabrics — e.g., 9-ply and 5-ply, for in- and out-of-plane flows, respectively — the dual-scale permeabilities can be extended to macro-flow making them applicable at all scales (multi-scale flow). The calculated in-plane multi-scale permeabilities are then used in the 2D simulations and compared with the analytical solution of the Darcy’s equation, which resulted in a very good agreement.

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Jian, Lihua, Shaowu Wu, Lihui Chen, Gemine Vivone, Rakiba Rayhana, and Di Zhang. "Multi-Scale and Multi-Stream Fusion Network for Pansharpening." Remote Sensing 15, no. 6 (March 20, 2023): 1666. http://dx.doi.org/10.3390/rs15061666.

Повний текст джерела

Анотація:

Pansharpening refers to the use of a panchromatic image to improve the spatial resolution of a multi-spectral image while preserving spectral signatures. However, existing pansharpening methods are still unsatisfactory at balancing the trade-off between spatial enhancement and spectral fidelity. In this paper, a multi-scale and multi-stream fusion network (named MMFN) that leverages the multi-scale information of the source images is proposed. The proposed architecture is simple, yet effective, and can fully extract various spatial/spectral features at different levels. A multi-stage reconstruction loss was adopted to recover the pansharpened images in each multi-stream fusion block, which facilitates and stabilizes the training process. The qualitative and quantitative assessment on three real remote sensing datasets (i.e., QuickBird, Pléiades, and WorldView-2) demonstrates that the proposed approach outperforms state-of-the-art methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Prade, Lucio, Jean Moraes, Eliel de Albuquerque, Denis Rosário, and Cristiano Bonato Both. "Multi-radio and multi-hop LoRa communication architecture for large scale IoT deployment." Computers and Electrical Engineering 102 (September 2022): 108242. http://dx.doi.org/10.1016/j.compeleceng.2022.108242.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Villa, Ferdinando. "Integrating modelling architecture: a declarative framework for multi-paradigm, multi-scale ecological modelling." Ecological Modelling 137, no. 1 (February 2001): 23–42. http://dx.doi.org/10.1016/s0304-3800(00)00422-1.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Piechocka, Izabela K., Karin A. Jansen, Chase P. Broedersz, Nicholas A. Kurniawan, Fred C. MacKintosh, and Gijsje H. Koenderink. "Multi-scale strain-stiffening of semiflexible bundle networks." Soft Matter 12, no. 7 (2016): 2145–56. http://dx.doi.org/10.1039/c5sm01992c.

Повний текст джерела

Анотація:

Bundles of polymer filaments are responsible for the rich and unique mechanical behaviors of many biomaterials. We show that the extraordinary strain-stiffening response of networks of fibrin fibers important for blood clotting reflects the fiber's hierarchical architecture.

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Jiang, Junzhe, Cheng Xu, Hongzhe Liu, Ying Fu, and Muwei Jian. "DSA: Deformable Segmentation Attention for Multi-Scale Fisheye Image Segmentation." Electronics 12, no. 19 (September 27, 2023): 4059. http://dx.doi.org/10.3390/electronics12194059.

Повний текст джерела

Анотація:

With a larger field of view (FOV) than ordinary images, fisheye images are becoming mainstream in the field of autonomous driving. However, the severe distortion problem of fisheye images also limits its application. The performance of neural networks designed for narrow FOV images degrades drastically for fisheye images, and the use of large composite models can improve the performance, but it brings huge time overhead and hardware costs. Therefore, we decided to balance real time and accuracy by designing the deformable segmentation attention(DSA) module, a generalpurpose architecture based on a deformable attention mechanism and a spatial pyramid architecture. The deformable mechanism serves to accurately extract feature information from fisheye images, together with attention to learn the global context and the spatial pyramid structure to balance multiscale feature information, thus improving the perception of fisheye images by traditional networks without increasing the amount of excessive computation. Lightweight networks such as SegNeXt equipped with the DSA module enable effective and rapid multi-scale segmentation of fisheye images in complex scenes. Our architecture achieves outstanding results on the WoodScape dataset, while our ablation experiments demonstrate the effectiveness of various parts of the architecture.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Ordóñez Salinas, Sonia, and Alba Consuelo Nieto Lemus. "A model of multilayer tiered architecture for big data." Sistemas y Telemática 14, no. 37 (August 5, 2016): 23–44. http://dx.doi.org/10.18046/syt.v14i37.2257.

Повний текст джерела

Анотація:

Until recently, the issue of analytical data was related to Data Warehouse, but due to the necessity of analyzing new types of unstructured data, both repetitive and non-repetitive, Big Data arises. Although this subject has been widely studied, there is not available a reference architecture for Big Data systems involved with the processing of large volumes of raw data, aggregated and non-aggregated. There are not complete proposals for managing the lifecycle of data or standardized terminology, even less a methodology supporting the design and development of that architecture. There are architectures in small-scale, industrial and product-oriented, which limit their scope to solutions for a company or group of companies, focused on technology but omitting the functionality. This paper explores the requirements for the formulation of an architectural model that supports the analysis and management of data: structured, repetitive and non-repetitive unstructured; there are some architectural proposals –industrial or technological type– to propose a logical model of multi-layered tiered architecture, which aims to respond to the requirements covering both Data Warehouse and Big Data.

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Zhang, Yifei, Weipeng Li, Daling Wang, and Shi Feng. "Unsupervised Image Translation Using Multi-Scale Residual GAN." Mathematics 10, no. 22 (November 19, 2022): 4347. http://dx.doi.org/10.3390/math10224347.

Повний текст джерела

Анотація:

Image translation is a classic problem of image processing and computer vision for transforming an image from one domain to another by learning the mapping between an input image and an output image. A novel Multi-scale Residual Generative Adversarial Network (MRGAN) based on unsupervised learning is proposed in this paper for transforming images between different domains using unpaired data. In the model, a dual generater architecture is used to eliminate the dependence on paired training samples and introduce a multi-scale layered residual network in generators for reducing semantic loss of images in the process of encoding. The Wasserstein GAN architecture with gradient penalty (WGAN-GP) is employed in the discriminator to optimize the training process and speed up the network convergence. Comparative experiments on several image translation tasks over style transfers and object migrations show that the proposed MRGAN outperforms strong baseline models by large margins.

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Liao, Haibin, Li Yuan, Mou Wu, Liangji Zhong, Guonian Jin, and Neal Xiong. "Face Gender and Age Classification Based on Multi-Task, Multi-Instance and Multi-Scale Learning." Applied Sciences 12, no. 23 (December 5, 2022): 12432. http://dx.doi.org/10.3390/app122312432.

Повний текст джерела

Анотація:

Automated facial gender and age classification has remained a challenge because of the high inter-subject and intra-subject variations. We addressed this challenging problem by studying multi-instance- and multi-scale-enhanced multi-task random forest architecture. Different from the conventional single facial attribute recognition method, we designed effective multi-task architecture to learn gender and age simultaneously and used the dependency between gender and age to improve its recognition accuracy. In the study, we found that face gender has a great influence on face age grouping; thus, we proposed a random forest face age grouping method based on face gender conditions. Specifically, we first extracted robust multi-instance and multi-scale features to reduce the influence of various intra-subject distortion types, such as low image resolution, illumination and occlusion, etc. Furthermore, we used a random forest classifier to recognize facial gender. Finally, a gender conditional random forest was proposed for age grouping to address inter-subject variations. Experiments were conducted by using two popular MORPH-II and Adience datasets. The experimental results showed that the gender and age recognition rates in our method can reach 99.6% and 96.14% in the MORPH-II database and 93.48% and 63.72% in the Adience database, reaching the state-of-the-art level.

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Fernandez-Gonzalez, Rodrigo, Irineu Illa-Bochaca, Bryan E. Welm, Markus C. Fleisch, Zena Werb, Carlos Ortiz-de-Solorzano, and Mary Helen Barcellos-Hoff. "Mapping mammary gland architecture using multi-scale in situ analysis." Integr. Biol. 1, no. 1 (2009): 80–89. http://dx.doi.org/10.1039/b816933k.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Liu, Dongfang, Yiming Cui, Liqi Yan, Christos Mousas, Baijian Yang, and Yingjie Chen. "DenserNet: Weakly Supervised Visual Localization Using Multi-Scale Feature Aggregation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 7 (May 18, 2021): 6101–9. http://dx.doi.org/10.1609/aaai.v35i7.16760.

Повний текст джерела

Анотація:

In this work, we introduce a Denser Feature Network(DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more key point features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level an-notation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during forwarding propagation. Our method is flexible and can be crafted on a light-weighted backbone architecture to achieve appealing efficiency with a small penalty on accuracy. Extensive experiment results indicate that our method sets a new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks with the same level of supervision. The code is available at https://github.com/goodproj13/DenserNet

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Devi, Wangkheirakpam, Sudipta Roy, and Khelchandra Thongam. "Multi-Scale Dilated Fusion Network (MSDFN) for Automatic Instrument Segmentation." Journal of Computer Science and Technology Studies 4, no. 1 (February 16, 2022): 66–72. http://dx.doi.org/10.32996/jcsts.2022.4.1.7.

Повний текст джерела

Анотація:

With the recent advancements in the field of semantic segmentation, an encoderdecoder approach like U-Net are most widely used to solve biomedical image segmentation tasks. To improve upon the existing U-Net, we proposed a novel architecture called Multi-Scale Dilated Fusion Network (MSDFNet). In this work, we have used the pre-trained ResNet50 as the encoder, which had already learned features that can be used by the decoder to generate the binary mask. In addition, we used skip-connections to directly facilitate the transfer of features from the encoder to the decoder. Some of these features are lost due to the depth of the network. The decoder consists of a Multi-Scale Dilated Fusion block, as the main components of the decoder, where we fused the multiscale features and then applied some dilated convolution upon them. We have trained both the U-Net and the proposed architecture on the Ksavir-Instrument dataset, where the proposed architecture has a 3.701 % gain in the F1 score and 4.376 % in the Jaccard. These results show the improvement over the existing U-Net model.

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Song, Yingluo, Aili Wang, Yan Zhao, Haibin Wu, and Yuji Iwahori. "Multi-Scale Spatial–Spectral Attention-Based Neural Architecture Search for Hyperspectral Image Classification." Electronics 12, no. 17 (August 29, 2023): 3641. http://dx.doi.org/10.3390/electronics12173641.

Повний текст джерела

Анотація:

Convolutional neural networks (CNNs) are indeed commonly employed for hyperspectral image classification. However, the architecture of cellular neural networks typically requires manual design and fine-tuning, which can be quite laborious. Fortunately, there have been recent advancements in the field of Neural Architecture Search (NAS) that enable the automatic design of networks. These NAS techniques have significantly improved the accuracy of HSI classification, pushing it to new levels. This article proposes a Multi-Scale Spatial–Spectral Attention-based NAS, MS3ANAS) framework for HSI classification to automatically design a neural network structure for HSI classifiers. First, this paper constructs a multi-scale attention mechanism extended search space, which considers multi-scale filters to reduce parameters while maintaining large-scale receptive field and enhanced multi-scale spectral–spatial feature extraction to increase network sensitivity towards hyperspectral information. Then, we combined the slow–fast learning architecture update paradigm to optimize and iteratively update the architecture vector and effectively improve the model’s generalization ability. Finally, we introduced the Lion optimizer to track only momentum and use symbol operations to calculate updates, thereby reducing memory overhead and effectively reducing training time. The proposed NAS method demonstrates impressive classification performance and effectively improves accuracy across three HSI datasets (University of Pavia, Xuzhou, and WHU-Hi-Hanchuan).

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Ara, Hadi Alizadeh, Amir Behrouzian, Martijn Hendriks, Marc Geilen, Dip Goswami, and Twan Basten. "Scalable Analysis for Multi-Scale Dataflow Models." ACM Transactions on Embedded Computing Systems 17, no. 4 (August 29, 2018): 1–26. http://dx.doi.org/10.1145/3233183.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Xiao, Zhanding, Bo Zheng, Jinghui Xia, and Zongqu Zhao. "Multi-core shared tree based MP2MP RWA algorithms in large scale and multi-domain optical networks." Journal of Physics: Conference Series 2722, no. 1 (March 1, 2024): 012005. http://dx.doi.org/10.1088/1742-6596/2722/1/012005.

Повний текст джерела

Анотація:

Abstract The increasing demands of bandwidth-intensive parallel computing and collaborative applications, efficient service provisioning to support multipoint to multipoint (MP2MP) communications have attracted increasing attention. However, with the development of larger-scale and multi-domain optical networks, MP2MP RWA are introduced optimal domain sequence selection and core nodes belong to which domains problems which cannot be tackled by the conventional algorithms proposed aim at a signal domain. In this paper, we proposed a multi-core node shared multicast tree heuristic algorithm (MCSMT) which calculation could be parallelized, delay and minimal cost constrained for multi-domain optical networks. It could realize the accurate calculation of minimum number of cores and the hosted domains of the cores. The source and destination nodes were added in different shared trees respectively with delay constrained algorithms according to specific QoS selection strategy. At the same time, according to more complicated MP2MP algorithms we propose a PCE-cloud based control architecture for optical networks by applying the cloud computing technology (e.g. virtualization and parallel computing) to reform the control plane for improving system reliability, intelligence and maximizing resource utilization. The performances of the proposed heuristic with regard to the number of multi-core nodes, wavelength channel occupied and MP2MP setup latency are compared. In addition, the performance about path computing latency for PCE-cloud control architecture is compared with conversional control architecture.

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Ren, Shasha, and Xiaodong Zhang. "Complex Scene Segmentation Network Based on Multi-scale Encoding-decoding Architecture." Journal of Physics: Conference Series 2219, no. 1 (April 1, 2022): 012042. http://dx.doi.org/10.1088/1742-6596/2219/1/012042.

Повний текст джерела

Анотація:

Abstract With the progress of artificial intelligence, the study of scene segmentation for complex scene understanding is of great significance. Due to the large number of activities, there are many target categories, large scale changes, many mutual occlusions, difficult target recognition, and large data labeling costs. In order to achieve accurate understanding of the complex scene, this paper proposes to add a scale adaptive feature module on the basis of Encode-Decode, so that the network can make good use of the features and context information of each level to effectively adapt to changes in target size. At the same time, we use the scale size function to weight encode different levels of features, which improves the prediction accuracy of pixels in the intersection area of each class. Experiments conducted on Cityscapes, Put_campus and PASCAL VOC 2012 datasets show that the method in this article is improved by about 1% compared with the three segmentation algorithms such as FCN, PSPNet, and Deeplabv3 +.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Qian, Xuelin, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, and Xiangyang Xue. "Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification." IEEE Transactions on Pattern Analysis and Machine Intelligence 42, no. 2 (February 1, 2020): 371–85. http://dx.doi.org/10.1109/tpami.2019.2928294.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Weimer, Daniel, Hendrik Thamer, and Klaus-Dieter Thoben. "GPU Architecture for Unsupervised Surface Inspection Using Multi-scale Texture Analysis." Procedia Technology 15 (2014): 278–84. http://dx.doi.org/10.1016/j.protcy.2014.09.081.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Martínez-Sanz, Marta, Deirdre Mikkelsen, Bernadine Flanagan, Michael J. Gidley, and Elliot P. Gilbert. "Multi-scale model for the hierarchical architecture of native cellulose hydrogels." Carbohydrate Polymers 147 (August 2016): 542–55. http://dx.doi.org/10.1016/j.carbpol.2016.03.098.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Al Khafaji, Ibtisam Abdulelah, and Israa Jabber Theban. "The Impact of Multi-functionality in Promoting the Aesthetic Values of Modern Islamic Architecture." Association of Arab Universities Journal of Engineering Sciences 27, no. 2 (June 30, 2020): 122–34. http://dx.doi.org/10.33261/jaaru.2020.27.2.011.

Повний текст джерела

Анотація:

Relationship between function and aesthetic has been occupied researchers, philosophers, artists and architects considerably to define meanings and to show significance degree of mutual influences. This analytical research investigates – How multi-functionality improve aesthetic values of architectural forms in contemporary Islamic architecture. We have defined procedurally the concept of multi-functionality as a potential forces of generative centers and aesthetic as geometrical coherence of architectural form. The absence of clear relations between multi-functionality and how it can be used to improve aesthetic values formed a basic research problem. The main target of this research is to determine how designers can enhancing aesthetic values of forms by using different functions. We suppose that multi-functionality improve the aesthetic values of the architectural form by strengthening geometrical coherence. We selected Five projects of contemporary Islamic centers and sample of 20 person’s. Semantic differential scale was used to analyze variables. The research found that multi-functionality has a great role in supporting the aesthetic values of architectural form by defining physical characters, Identifying and intensifying its visual and physical connections.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Tomasi, Matteo, Mauricio Vanegas, Francisco Barranco, Javier Diaz, and Eduardo Ros. "High-Performance Optical-Flow Architecture Based on a Multi-Scale, Multi-Orientation Phase-Based Model." IEEE Transactions on Circuits and Systems for Video Technology 20, no. 12 (December 2010): 1797–807. http://dx.doi.org/10.1109/tcsvt.2010.2087590.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Murtiyoso, Arnadi, Pierre Grussenmeyer, Deni Suwardhi, and Rabby Awalludin. "Multi-Scale and Multi-Sensor 3D Documentation of Heritage Complexes in Urban Areas." ISPRS International Journal of Geo-Information 7, no. 12 (December 17, 2018): 483. http://dx.doi.org/10.3390/ijgi7120483.

Повний текст джерела

Анотація:

The 3D documentation of heritage complexes or quarters often requires more than one scale due to its extended area. While the documentation of individual buildings requires a technique with finer resolution, that of the complex itself may not need the same degree of detail. This has led to the use of a multi-scale approach in such situations, which in itself implies the integration of multi-sensor techniques. The challenges and constraints of the multi-sensor approach are further added when working in urban areas, as some sensors may be suitable only for certain conditions. This paper describes the integration of heterogeneous sensors as a logical solution in addressing this problem. The royal palace complex of Kasepuhan Cirebon, Indonesia, was taken as a case study. The site dates to the 13th Century and has survived to this day as a cultural heritage site, preserving within itself a prime example of vernacular Cirebonese architecture. This type of architecture is influenced by the tropical climate, with distinct features designed to adapt to the hot and humid year-long weather. In terms of 3D documentation, this presents specific challenges that need to be addressed both during the acquisition and processing stages. Terrestrial laser scanners, DSLR cameras, as well as UAVs were utilized to record the site. The implemented workflow, some geometrical analysis of the results, as well as some derivative products will be discussed in this paper. Results have shown that although the proposed multi-scale and multi-sensor workflow has been successfully employed, it needs to be adapted and the related challenges addressed in a particular manner.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Gainer, Paul, Sven Linker, Clare Dixon, Ullrich Hustadt, and Michael Fisher. "Multi-scale verification of distributed synchronisation." Formal Methods in System Design 55, no. 3 (September 20, 2020): 171–221. http://dx.doi.org/10.1007/s10703-020-00347-z.

Повний текст джерела

Анотація:

AbstractAlgorithms for the synchronisation of clocks across networks are both common and important within distributed systems. We here address not only the formal modelling of these algorithms, but also the formal verification of their behaviour. Of particular importance is the strong link between the very different levels of abstraction at which the algorithms may be verified. Our contribution is primarily the formalisation of this connection between individual models and population-based models, and the subsequent verification that is then possible. While the technique is applicable across a range of synchronisation algorithms, we particularly focus on the synchronisation of (biologically-inspired) pulse-coupled oscillators, a widely used approach in practical distributed systems. For this application domain, different levels of abstraction are crucial: models based on the behaviour of an individual process are able to capture the details of distinguished nodes in possibly heterogenous networks, where each node may exhibit different behaviour. On the other hand, collective models assume homogeneous sets of processes, and allow the behaviour of the network to be analysed at the global level. System-wide parameters may be easily adjusted, for example environmental factors inhibiting the reliability of the shared communication medium. This work provides a formal bridge across the “abstraction gap” separating the individual models and the population-based models for this important class of synchronisation algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Sharma, Harsh, Lukas Pfromm, Rasit Onur Topaloglu, Janardhan Rao Doppa, Umit Y. Ogras, Ananth Kalyanraman, and Partha Pratim Pande. "Florets for Chiplets: Data Flow-aware High-Performance and Energy-efficient Network-on-Interposer for CNN Inference Tasks." ACM Transactions on Embedded Computing Systems 22, no. 5s (September 9, 2023): 1–21. http://dx.doi.org/10.1145/3608098.

Повний текст джерела

Анотація:

Recent advances in 2.5D chiplet platforms provide a new avenue for compact scale-out implementations of emerging compute- and data-intensive applications including machine learning. Network-on-Interposer (NoI) enables integration of multiple chiplets on a 2.5D system. While these manycore platforms can deliver high computational throughput and energy efficiency by running multiple specialized tasks concurrently, conventional NoI architectures have a limited computational throughput due to their inherent multi-hop topologies. In this paper, we propose Floret, a novel NoI architecture based on space-filling curves (SFCs). The Floret architecture leverages suitable task mapping, exploits the data flow pattern, and optimizes the inter-chiplet data exchange to extract high performance for multiple types of convolutional neural network (CNN) inference tasks running concurrently. We demonstrate that the Floret architecture reduces the latency and energy up to 58% and 64%, respectively, compared to state-of-the-art NoI architectures while executing datacenter-scale workloads involving multiple CNN tasks simultaneously. Floret achieves high performance and significant energy savings with much lower fabrication cost by exploiting the data-flow awareness of the CNN inference tasks.

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Benedykciuk, Emil, Marcin Denkowski, and Krzysztof Dmitruk. "Material classification in X-ray images based on multi-scale CNN." Signal, Image and Video Processing 15, no. 6 (February 6, 2021): 1285–93. http://dx.doi.org/10.1007/s11760-021-01859-9.

Повний текст джерела

Анотація:

AbstractSecurity X-ray baggage scanners provide images based on the different levels of radiation absorption by different materials. Images captured by such scanners are inspected by a human operator, which can slow down the verification process. To speed up inspection time, computer vision and machine learning methods are increasingly being used. While object recognition has been the subject of a huge number of articles, the problem of material recognition in X-ray images still requires some work to achieve equivalent accuracy. This paper focuses on the problem of discrimination of materials into several classes, such as organic substances or metals, in images obtained from dual-energy X-ray security scanners. We propose a new multi-scale convolutional neural network (CNN) for predicting the material class, in which five different sizes of patches are implemented parallelly to balance the trade-off between the increase in the receptive field and the loss of detail. We analyze some regularization methods and activation functions and their impact on the effectiveness of our architecture. The results were compared with other popular CNN architectures and demonstrate the superiority of our solution.

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Zhang, Junxing, Lijun Chen, Chunjuan Bo, and Shuo Yang. "Multi-Scale Vehicle Logo Detector." Mobile Networks and Applications 26, no. 1 (February 2021): 67–76. http://dx.doi.org/10.1007/s11036-020-01722-0.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Ban, Yuseok, and Kyungjae Lee. "Multi-Scale Ensemble Learning for Thermal Image Enhancement." Applied Sciences 11, no. 6 (March 22, 2021): 2810. http://dx.doi.org/10.3390/app11062810.

Повний текст джерела

Анотація:

In this study, we propose a multi-scale ensemble learning method for thermal image enhancement in different image scale conditions based on convolutional neural networks. Incorporating the multiple scales of thermal images has been a tricky task so that methods have been individually trained and evaluated for each scale. However, this leads to the limitation that a network properly operates on a specific scale. To address this issue, a novel parallel architecture leveraging the confidence maps of multiple scales have been introduced to train a network that operates well in varying scale conditions. The experimental results show that our proposed method outperforms the conventional thermal image enhancement methods. The evaluation is presented both quantitatively and qualitatively.

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Sun, Fan, Xiangfeng Zhang, Yunzhong Liu, and Hong Jiang. "Multi-Object Detection in Security Screening Scene Based on Convolutional Neural Network." Sensors 22, no. 20 (October 15, 2022): 7836. http://dx.doi.org/10.3390/s22207836.

Повний текст джерела

Анотація:

The technique for target detection based on a convolutional neural network has been widely implemented in the industry. However, the detection accuracy of X-ray images in security screening scenarios still requires improvement. This paper proposes a coupled multi-scale feature extraction and multi-scale attention architecture. We integrate this architecture into the Single Shot MultiBox Detector (SSD) algorithm and find that it can significantly improve the effectiveness of target detection. Firstly, ResNet is used as the backbone network to replace the original VGG network to improve the feature extraction capability of the convolutional neural network for images. Secondly, a multi-scale feature extraction (MSE) structure is designed to enrich the information contained in the multi-stage prediction feature layer. Finally, the multi-scale attention architecture (MSA) is fused onto the prediction feature layer to eliminate the redundant features’ interference and extract effective contextual information. In addition, a combination of Adaptive-NMS and Soft-NMS is used to output the final prediction anchor boxes when performing non-maximum suppression. The results of the experiments show that the improved method improves the mean average precision (mAP) value by 7.4% compared to the original approach. New modules make detection much more accurate while keeping the detection speed the same.

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Ogrean, Valentin, and Remus Brad. "Multi-Organ Segmentation Using a Low-Resource Architecture." Information 13, no. 10 (September 30, 2022): 472. http://dx.doi.org/10.3390/info13100472.

Повний текст джерела

Анотація:

Since their inception, deep-learning architectures have shown promising results for automatic segmentation. However, despite the technical advances introduced by fully convolutional networks, generative adversarial networks or recurrent neural networks, and their usage in hybrid architectures, automatic segmentation in the medical field is still not used at scale. One main reason is related to data scarcity and quality, which in turn generates a lack of annotated data that hinder the generalization of the models. The second main issue refers to challenges in training deep models. This process uses large amounts of GPU memory (that might exceed current hardware limitations) and requires high training times. In this article, we want to prove that despite these issues, good results can be obtained even when using a lower resource architecture, thus opening the way for more researchers to employ and use deep neural networks. In achieving the multi-organ segmentation, we are employing modern pre-processing techniques, a smart model design and fusion between several models trained on the same dataset. Our architecture is compared against state-of-the-art methods employed in a publicly available challenge and the notable results prove the effectiveness of our method.

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Rafique, M. Mustafa, Benjamin Rose, Ali R. Butt, and Dimitrios S. Nikolopoulos. "Supporting MapReduce on large-scale asymmetric multi-core clusters." ACM SIGOPS Operating Systems Review 43, no. 2 (April 21, 2009): 25–34. http://dx.doi.org/10.1145/1531793.1531800.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Munde, Amit V., and Dr Pranjali P. Deshmukh. "Multi Cloud Data Hosting with SIC Architecture." International Journal for Research in Applied Science and Engineering Technology 10, no. 3 (March 31, 2022): 1830–33. http://dx.doi.org/10.22214/ijraset.2022.40999.

Повний текст джерела

Анотація:

Abstract: Data hosting on cloud decreases cost of IT maintenance and data reliability get enhance. Nowadays, customers can store their data on single cloud, which has some drawbacks. First is vendor lock in problem and second is security on cloud. The solution to this problem is to store the data on different cloud server without redundancy using encryption algorithm. Customers do not want to lose their sensitive data on cloud. Another issue of cloud computing is data thievery should be overcome to supply higher service. Multi-cloud environment has ability to scale back security risks. To avoid security risk we offer framework. Keywords: Cloud computing, cloud storage, data hosting, data intrusion, multi-cloud, single cloud.

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Yang, Ziyuan. "Dual Cultural Influence on the Architectural Style Evolution of San Francisco Chinatown: A Comprehensive Examination." Civil and Environmental Engineering 20, no. 1 (June 1, 2024): 274–82. http://dx.doi.org/10.2478/cee-2024-0021.

Повний текст джерела

Анотація:

Abstract The unique neighborhood style of San Francisco Chinatown is influenced by Chinese and American culture, history and social system. Through field investigation, Chinese and English literature collection, and spatial analysis, this paper interprets the motivation of its style evolution. In the process of research, the author tries to analyze the changes and driving forces of Chinatown in San Francisco from three dimensions: the city scale, the blocks scale, and the building scale. The results show that the formation process of Chinatown in San Francisco and the range of its blocks are deeply influenced by the world political pattern in the early 20th century, the Sino-American multi-party regulations and Sino-American relations. The architectural style of the block is influenced by the Eastern and Western cultures, which is a distinctive architectural feature. The traditional architecture is deeply influenced by the architectural style of southern Fujian, while the new architecture is mainly based on the modernist architectural style. Among the main factors affecting the evolution of Chinatown in San Francisco, gold rush, earthquake, traditional Chinese architectural style and immigration policy to China are the internal mechanisms of the formation of Chinatown’s spatial characteristics.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Zhou, Zhiqiang, Sun Li, and Bo Wang. "Multi-scale weighted gradient-based fusion for multi-focus images." Information Fusion 20 (November 2014): 60–72. http://dx.doi.org/10.1016/j.inffus.2013.11.005.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Huang, You, Junzhong Shen, Yuran Qiao, Mei Wen, and Chunyuan Zhang. "MALMM: A multi-array architecture for large-scale matrix multiplication on FPGA." IEICE Electronics Express 15, no. 10 (2018): 20180286. http://dx.doi.org/10.1587/elex.15.20180286.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

44

Ahmad, Parvez, Hai Jin, Roobaea Alroobaea, Saqib Qamar, Ran Zheng, Fady Alnajjar, and Fathia Aboudi. "MH UNet: A Multi-Scale Hierarchical Based Architecture for Medical Image Segmentation." IEEE Access 9 (2021): 148384–408. http://dx.doi.org/10.1109/access.2021.3122543.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Demetci, Pinar, Wei Cheng, Gregory Darnell, Xiang Zhou, Sohini Ramachandran, and Lorin Crawford. "Multi-scale inference of genetic trait architecture using biologically annotated neural networks." PLOS Genetics 17, no. 8 (August 19, 2021): e1009754. http://dx.doi.org/10.1371/journal.pgen.1009754.

Повний текст джерела

Анотація:

In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. We treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects manifest at different genomic scales. The BANNs software uses variational inference to provide posterior summaries which allow researchers to simultaneously perform (i) mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations, we show that our method improves upon state-of-the-art association mapping and enrichment approaches across a wide range of genetic architectures. We then further illustrate the benefits of BANNs by analyzing real GWA data assayed in approximately 2,000 heterogenous stock of mice from the Wellcome Trust Centre for Human Genetics and approximately 7,000 individuals from the Framingham Heart Study. Lastly, using a random subset of individuals of European ancestry from the UK Biobank, we show that BANNs is able to replicate known associations in high and low-density lipoprotein cholesterol content.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Zhang Pan, 张盼, and 张为 Zhang Wei. "Efficient Very Large Scale Integration Architecture of Multi-Level Discrete Wavelet Transform." Acta Optica Sinica 39, no. 4 (2019): 0412004. http://dx.doi.org/10.3788/aos201939.0412004.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Li, Wenzhe, Bingli Guo, Xin Li, Yu Zhou, Shanguo Huang, and George N. Rouskas. "A large-scale nesting ring multi-chip architecture for manycore processor systems." Optical Switching and Networking 31 (January 2019): 183–92. http://dx.doi.org/10.1016/j.osn.2018.10.004.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Díaz-Pernas, F. J., M. Antón-Rodríguez, F. J. Perozo-Rondón, and D. González-Ortega. "A multi-scale supervised orientational invariant neural architecture for natural texture classification." Neurocomputing 74, no. 18 (November 2011): 3729–40. http://dx.doi.org/10.1016/j.neucom.2011.06.028.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Tomasi, Matteo, Mauricio Vanegas, Francisco Barranco, Javier Diaz, and Eduardo Ros. "Real-Time Architecture for a Robust Multi-Scale Stereo Engine on FPGA." IEEE Transactions on Very Large Scale Integration (VLSI) Systems 20, no. 12 (December 2012): 2208–19. http://dx.doi.org/10.1109/tvlsi.2011.2172007.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Wang, C. H., C. H. Yeh, F. Y. Shih, C. W. Chow, K. C. Hsu, Y. Lai, and S. Chi. "Self-Protection Multi-Ring-Architecture Fiber Sensing System." Advanced Materials Research 47-50 (June 2008): 793–96. http://dx.doi.org/10.4028/www.scientific.net/amr.47-50.793.

Повний текст джерела

Анотація:

In this investigation, we propose and experimentally investigate a simply self-restored ring-based fiber Bragg grating (FBG) based sensor system. This proposed multi-ring passive sensing architecture is without any active components in the entire network. In this experiment, the network survivability and capacity for the multi-point sensor systems are also enhanced. Besides, the tunable laser source (TLS) is adopted in central office (CO) for FBG sensing. The survivability of a eight-point FBG sensor is examined and analyzed. Due to the passive sensor network, the cost-effective and intelligent sensing system is entirely centralized by CO. As a result, the experimental results show that the proposed system can assist the reliable FBG sensing network for a large-scale and multi-point architecture.

Стилі APA, Harvard, Vancouver, ISO та ін.

Статті в журналах з теми "Multi-scale architecture"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями