检索结果-内蒙古大学图书馆

A novel approach combined transfer learning and deep learning to predict TMB from histology image

Pattern Recognition Letters 2020年 135卷 244-248页

作者： Wang, Liansheng Jiao, Yudi Qiao, Ying Zeng, Nianyin Yu, Rongshan Department of Computer Science School of Informatics Xiamen University Fujian361005 China School of Informatics Xiamen University Fujian361005 China Department of Instrumental and Electrical Engineering Xiamen University Fujian361005 China

Tumor Mutation Burden(TMB) is a quantifiable clinical indicator that can be used to predict the responses to immunotherapy of a range of tumors. However, the current DNA sequencing-based TMB measurement method represented by Whole Exome Sequencing (WES) is expensive and time-consuming, which limits its utilization in clinical practice. In this paper, we design a method through deep learning in order to predict TMB from available H&E stained whole slide images of gastrointestinal cancer. Experimental results demonstrate that our approach is capable of distinguishing high and low TMB with an AUC higher than 0.75. We further performed post-processing to improve the accuracy on both test sets to above 0.7 (0.71 accuracy for TMB-STAD and 0.77 accuracy for TMB-COAD-DX). Furthermore, the predicted low and high TMB patients with gastric and colon cancer have different survival rates, with p values of 0.348 and 0.8113, respectively, which indicates that our study is potentially helpful for practical treatment. © 2020 Elsevier B.V.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Adrias: Interference-Aware Memory Orchestration for Disaggregated Cloud Infrastructures

Adrias: Interference-Aware Memory Orchestration for Disaggre...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Dimosthenis Masouros Christian Pinto Michele Gazzetti Sotirios Xydis Dimitrios Soudris Microprocessors and Digital Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Greece IBM Research Europe Dublin Ireland Department of Informatics and Telematics Harokopio University of Athens Greece

Workload co-location has become the de-facto approach for hosting applications in Cloud environments, leading, however, to interference and fragmentation in shared resources of the system. To this end, hardware disaggregation is introduced as a novel paradigm, that allows fine-grained tailoring of cloud resources to the characteristics of the deployed applications. Towards the realization of hardware disaggregated clouds, novel orchestration frameworks must provide additional knobs to manage the increased scheduling *** present Adrias, a memory orchestration framework for disaggregated cloud systems. Adrias exploits information from low-level performance events and applies deep learning techniques to effectively predict the system state and performance of arriving workloads on memory disaggregated systems, thus, driving cognitive scheduling between local and remote memory allocation modes. We evaluate Adrias on a state-of-art disaggregated testbed and show that it achieves 0.99 and 0.942 R 2 score for system state and application’s performance prediction on average respectively. Moreover, Adrias manages to effectively utilize disaggregated memory, by offloading almost 1/3 of deployed applications with less than 15% performance overhead compared to a conventional local memory scheduling, while clearly outperforms naive scheduling approaches (random and round-robin), by providing up to ×2 better performance.

关键词： Deep learning Memory management Interference Hardware Resource management

来源：评论

学校读者我要写书评

暂无评论

Communicative Robot Signals: Presenting a New Typology for Human-Robot Interaction

arXiv

引用

arXiv 2023年

作者： Holthaus, Patrick Schulz, Trenton Lakatos, Gabriella Soma, Rebekka University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom Norwegian Computing Center Department of Applied Research in ICT Oslo Norway University of Oslo Department of Informatics Oslo Norway

We present a new typology for classifying signals from robots when they communicate with humans. For inspiration, we use ethology, the study of animal behaviour and previous efforts from literature as guides in defining the typology. The typology is based on communicative signals that consist of five properties: the origin where the signal comes from, the deliberateness of the signal, the signal’s reference, the genuineness of the signal, and its clarity (i.e., how implicit or explicit it is). Using the accompanying worksheet, the typology is straightforward to use to examine communicative signals from previous human-robot interactions and provides guidance for designers to use the typology when designing new robot behaviours. © 2023, CC BY.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Villages Status Classification Analysis Involving K-Means Algorithm to Support Kementerian Desa Pembangunan Daerah Tertinggal dan Transmigrasi Work Programs 1

Villages Status Classification Analysis Involving K-Means Al...

引用

1st International Conference on Advanced Information Scientific Development, ICAISD 2020

作者： Hasugian, Paska Marto Hutahaean, Harvei Desmon Sinaga, Bosker Sriadhi Silaban, Saranom Informatics Engineering Study Program STMIK Pelita Nusantara Computer Science and Informatics Education Study Program Faculty of Engineering Universitas Negeri Medan Medan20221 Indonesia

Data mining is a technique of extracting information that has not been known before in a collection of data in the database. Data mining has been applied in various fields that require extracting information, some of the work that can be generated with data mining is classification, prediction, and data grouping. In this study, an analysis of village data collection was carried out to explore the potential or knowledge of the data that has been presented with the main objective of producing a grouping of village status. To support clustering or grouping activities the K-means algorithm used with the general process is to carry out the modeling process without supervision and is one of the methods for grouping data with a system partition, with the principle of allocating each data to the centroid or the closest average, work steps conducted in support of this research is to collect data related to the analysis of data grouping and proceed with the calculation process in accordance with the work steps of the K-means algorithm, the amount of data used as a test of 303 villages scattered in the old Padang regency. The results of calculations by displaying a new group of Cluster 0 is occupied by 120 villages, cluster 1 with a total data of 123 villages, Cluster 2 with a total of 6 villages, cluster 3 with a total of 33 villages while cluster 4 with a total of 21. © 2020 Published under licence by IOP Publishing Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Referenceless User Controllable Semantic Image Synthesis

Referenceless User Controllable Semantic Image Synthesis

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jonghyun Kim Gen Li Joongkyu Kim AI Lab CTO Division LG Electronics Seoul Republic of Korea School of Informatics University of Edinburgh Edinburgh UK Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Republic of Korea

Despite recent progress in semantic image synthesis, complete control over image style remains a challenging problem. Existing methods require reference images to feed style information into semantic layouts, which indicates that the style is constrained by the given image. In this paper, we propose a model named RUCGAN for user controllable semantic image synthesis, which utilizes a singular color to represent the style of a specific semantic region. The proposed network achieves reference-free semantic image synthesis by injecting color as user-desired styles into each semantic layout, and is able to synthesize semantic images with unusual colors. Extensive experimental results on various challenging datasets show that the proposed method outperforms existing methods, and we further provide an interactive UI to demonstrate the advantage of our approach for style controllability. The codes and UI are available at: https://***/BenjaminJonghyun/RUCGAN

关键词：

来源：评论

学校读者我要写书评

暂无评论

An equivalent reformulation and multi-proximity gradient algorithms for a class of nonsmooth fractional programming

arXiv

引用

arXiv 2023年

作者： Zhou, Junpeng Zhang, Na Li, Qia School of Computer Sciences and Engineering Sun Yat-Sen University Guangzhou510006 China Department of Applied Mathematics College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China School of Computer Sciences and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-Sen University Guangzhou510006 China

In this paper, we consider a class of structured fractional programs, where the numerator part is the sum of a block-separable (possibly nonsmooth nonconvex) function and a locally Lipschitz differentiable (possibly nonconvex) function, while the denominator is a convex (possibly nonsmooth) function. We first present a novel reformulation for the original problem and show the relationship between optimal solutions, critical points and KL exponents of these two problems. Inspired by the reformulation, we propose a flexible framework of multi-proximity gradient algorithms (MPGA), which computes the proximity operator with respect to the Fenchel conjugate associated with the convex denominator of the original problem rather than evaluating its subgradient as in the existing methods. Also, MPGA employs a nonmonotone linear-search scheme in its gradient descent step, since the smooth part in the numerator of the original problem is not globally Lipschitz differentiable. Based on the framework of MPGA, we develop two specific algorithms, namely, cyclic MPGA and randomized MPGA, and establish their subsequential convergence under mild conditions. Moreover, the sequential convergence of cyclic MPGA with the monotone line-search (CMPGA ML) is guaranteed if the extended objective associated with the reformulated problem satisfies the Kurdyka-Lojasiewicz (KL) property and some other mild assumptions. In particular, we prove that the corresponding KL exponents are 12 for several special cases of the fractional programs, and so, CMPGA ML exhibits a linear convergence rate. Finally, some preliminary numerical experiments are performed to demonstrate the efficiency of our proposed algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Automatic Data Clustering Based Mean Best Artificial Bee Colony Algorithm

引用

computers, Materials & Continua 2021年第8期68卷 1575-1593页

作者： Ayat Alrosan Waleed Alomoush Mohammed Alswaitti Khalid Alissa Shahnorbanun Sahran Sharif Naser Makhadmeh Kamal Alieyan Deanship of Information and Communication Technology Imam Abdulrahman bin Faisal UniversityDammamSaudi Arabia Computer Department Imam Abdulrahman bin Faisal UniversityDammamSaudi Arabia School of Electrical and Computer Engineering Department of Information and Communication TechnologyXiamen University MalaysiaSepang43900Malaysia Department of Computer Science College of Computer Science and Information TechnologyImam Abdulrahman bin Faisal UniversityDammamSaudi Arabia Center for Artificial Intelligence Technology(CAIT) Faculty of Information Science and TechnologyUniversiti Kebangsaan Malaysia43600 BangiMalaysia School of Computer Sciences Universiti Sains Malaysia11800PenangMalaysia Faculty of Computer Sciences and Informatics Amman Arab UniversityAmmanJordan

Fuzzy C-means(FCM)is a clustering method that falls under unsupervised machine *** main issues plaguing this clustering algorithm are the number of the unknown clusters within a particular dataset and initialization sensitivity of cluster *** Bee Colony(ABC)is a type of swarm algorithm that strives to improve the members’solution quality as an iterative process with the utilization of particular kinds of ***,ABC has some weaknesses,such as balancing exploration and *** improve the exploration process within the ABC algorithm,the mean artificial bee colony(MeanABC)by its modified search equation that depends on solutions of mean previous and global best is ***,to solve the main issues of FCM,Automatic clustering algorithm was proposed based on the mean artificial bee colony called(AC-MeanABC).It uses the MeanABC capability of balancing between exploration and exploitation and its capacity to explore the positive and negative directions in search space to find the best value of clusters number and centroids value.A few benchmark datasets and a set of natural images were used to evaluate the effectiveness of *** experimental findings are encouraging and indicate considerable improvements compared to other state-of-the-art approaches in the same domain.

关键词： Artificial bee colony automatic clustering natural images validity index number of clusters

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Camera Assisted High-Flow Imaging Cytometry for Particle Classification

Neuromorphic Camera Assisted High-Flow Imaging Cytometry for...

引用

Conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Ioannis Tsilikas Stavros Deligiannidis Aris Tsirigotis Georgios N. Tsigaridas Adonis Bogris Charis Mesaritakis Dept. Physics National Technical University of Athens Zografou Athens Greece Dept. Information and Communication Systems Engineering University of the Aegean Karlovasi Samos Greece Dept. Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (纸本)9798350345995

In this work we combine a high flow cytometry experimental setup and a 10Kframe/sec capable neuromorphic event-based camera, followed by lightweight machine learning schemes, thus allowing the simultaneous imaging and real-time classification of test particles, moving at a speed of 0.8m/sec with an accuracy of 97.6%. The key advantage of the utilized microscopy system, is the use of an event-based camera, generating spiking events, triggered by pixel's contrast changes. This bio-inspired operation, contrary to conventional CMOS cameras [1], alleviates bandwidth constraints and can significantly boost frame-rate capabilities, thus capturing high speed events. Following this paradigm, medical imaging modalities, where the detection and analysis of fast-moving particles is a necessity, such as high-flow cytometry, can greatly proliferate from the proposed approach.

关键词： Biomedical imaging Cameras CMOS cameras Cytometry Machine learning Real time imaging

来源：评论

学校读者我要写书评

暂无评论

Customizing and Deploying Data Science Roadmapping: A Case Study of an Oil and Gas Company

Customizing and Deploying Data Science Roadmapping: A Case S...

引用

2022 IEEE International Conference on Technology Management, Operations and Decisions, ICTMOD 2022

作者： Kayabay, Kerem Gokalp, Mert Onuralp Gokalp, Ebru Alagoz, Serhat Murat Eren, P. Erhan Kocyigit, Altan Data Informatics Middle East Technical University Network Technologies Department TÜBITAK ULAKBIM Ankara Turkey Data Analytics Center TÜPRAŞ Ankara Turkey Hacettepe University Computer Engineering Department Ankara Turkey Information Systems Middle East Technical University Ankara Turkey

ISBN: (纸本)9781665470278

Many organizations still face challenges leveraging data science in production and need strategic planning for organization-wide data science efforts and assets. Data Science Roadmapping (DSR) customizes the widely used Technology Roadmapping to facilitate such planning in organizations, aligning market, business, data, technology, and organization perspectives. This paper employs the action research method to customize and apply DSR in an oil and gas company. The approach mostly met the expectations regarding objectives and outcomes, the first step toward generalizability. The case study provides researchers and practitioners insights into roadmapping customization, remote and agile roadmap development process, and strategic planning for technology adoption in a large organization. Lastly, we identify the future research directions using the recent roadmapping literature. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Implementation Learning Vector Quantization Using Neural Network for Classification of Ear, Nose and Throat Disease 1

Implementation Learning Vector Quantization Using Neural Net...

引用

1st Lekantara Annual Conference on engineering and Information Technology, LiTE 2021

作者： Samsir, Samsir Daulay, Nelly Khairani Harahap, Syaiful Zuhri Zalmi, Wahyuni Fithratul Sari, Afni Nia Nasution, Fitri Aini Watrianthos, Ronal Department of Informatics Engineering Universitas Al Washliyah Labuhanbatu Indonesia Department of Computer System Universitas Bina Insan Indonesia Department of Information System Universitas Labuhanbatu Indonesia Department of Information System Universitas Putra Indonesia Padang Indonesia Department of Software Engineer Universitas Dharmawangsa Medan Indonesia

This study aims to use data from 57 patients at Rantauprapat Hospital to train a Neural Network using a quantization learning vector method for the categorization of ear, nose, and throat disorders. The input factors were fever, tiredness, nausea, breathing pain, sore throat, hearing loss, allergies, chills and sweating, and thick and transparent mucus. The factors studied were ear canal infections, pharyngitis of the neck, throat, nose, and sinusitis. The findings revealed that ten neurons with an objective value of 0.01 in the learning rate range of 0.01 - 0.05 resulted in categorizing snoring, nose, and ear disorders, including the input layer. The MATLAB program is utilized in this approach, with an average accuracy of 67 per cent and a mean square error of 0.2. © Published under licence by IOP Publishing Ltd.

关键词： Mean square error

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：