Parameter Tuning for ABC-Based Service Composition with End-to-End QoS Constraints

2014 ◽  
Author(s):  
Ruilin Liu ◽  
Zhongjie Wang ◽  
Xiaofei Xu
Keyword(s):  
Service Composition ◽  
Parameter Tuning ◽  
End To End

scholarly journals EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

2020 ◽  
Vol 34 (07) ◽  
pp. 10778-10785
Author(s):  
Linpu Fang ◽  
Hang Xu ◽  
Zhili Liu ◽  
Sarah Parisot ◽  
Zhenguo Li
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Detection System ◽  
Parameter Tuning ◽  
Heat Map ◽  
Level Data ◽  
End To End ◽  
Weakly Supervised ◽  
Yield State ◽  
Activation Heat

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably in a realistic setting. In this paper, we study the hybrid-supervised object detection problem, aiming to train a high quality detector with only a limited amount of fully-annotated data and fully exploiting cheap data with image-level labels. State of the art methods typically propose an iterative approach, alternating between generating pseudo-labels and updating a detector. This paradigm requires careful manual hyper-parameter tuning for mining good pseudo labels at each round and is quite time-consuming. To address these issues, we present EHSOD, an end-to-end hybrid-supervised object detection system which can be trained in one shot on both fully and weakly-annotated data. Specifically, based on a two-stage detector, we proposed two modules to fully utilize the information from both kinds of labels: 1) CAM-RPN module aims at finding foreground proposals guided by a class activation heat-map; 2) hybrid-supervised cascade module further refines the bounding-box position and classification with the help of an auxiliary head compatible with image-level data. Extensive experiments demonstrate the effectiveness of the proposed method and it achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data, e.g. 37.5% mAP on COCO. We will release the code and the trained models.

Parameter Tuning for S-ABCPK

2019 ◽  
Vol 16 (2) ◽  
pp. 88-109
Author(s):  
Ruilin Liu ◽  
Zhongjie Wang ◽  
Xiaofei Xu
Keyword(s):  
Service Composition ◽  
Time Complexity ◽  
Parameter Tuning ◽  
Validation Dataset ◽  
Bee Colony ◽  
Composition Problem ◽  
The Neural Network ◽  
Service Oriented ◽  
Optimum Solution ◽  
Priori Knowledge

QoS-aware service composition problem has been drawn great attention in recent years. As an NP-hard problem, high time complexity is inevitable if global optimization algorithms (such as integer programming) are adopted. Researchers applied various evolutionary algorithms to decrease the time complexity by looking for a near-optimum solution. However, each evolutionary algorithm has two or more parameters, the values of which are to be assigned by algorithm designers and likely have impacts on the optimization results (primarily time complexity and optimality). The authors' experiments show that there are some dependencies between the features of a service composition problem, the values of an evolutionary algorithm's parameters, and the optimization results. In this article, the authors propose an improved algorithm called Service-Oriented Artificial Bee Colony algorithm considering Priori Knowledge (S-ABCPK) to solve service composition problem and focus on the S-ABCPK's parameter turning issue. The objective is to identify the potential dependency for designers of a service composition algorithm easily setting up the values of S-ABCPK parameters to obtain a preferable composition solution without many times of tedious attempts. Eight features of the service composition problem and the priori knowledge, five S-ABCPK parameters and two metrics of the final solution are identified. Based on a large volume of experiment data, S-ABCPK parameter tuning for a given service composition problem is conducted using C4.5 algorithm and the dependency between problem features and S-ABCPK parameters are established using the neural network method. An experiment on a validation dataset shows the feasibility of the approach.

scholarly journals Behavioral clusters revealed by end-to-end decoding from microendoscopic imaging

2021 ◽  
Author(s):  
Chia-Jung Chang ◽  
Wei Guo ◽  
Jie Zhang ◽  
Jon Newman ◽  
Shao-Hua Sun ◽  
...  
Keyword(s):  
Parameter Tuning ◽  
Relevant Information ◽  
User Input ◽  
Functional Clustering ◽  
Saliency Maps ◽  
Behavioral Variables ◽  
Roi Extraction ◽  
Freely Behaving ◽  
End To End

AbstractIn vivo calcium imaging using head-mounted miniature microscopes enables tracking activity from neural populations over weeks in freely behaving animals. Previous studies focus on inferring behavior from a population of neurons, yet it is challenging to extract neuronal signals given out-of-focus fluorescence in endoscopic data. Existing analysis pipelines include regions of interest (ROIs) identification, which might lose relevant information from false negatives or introduce unintended bias from false positives. Moreover, these methods often require prior knowledge for parameter tuning and are time-consuming for implementation. Here, we develop an end-to-end decoder to predict the behavioral variables directly from the raw microendoscopic images. Our framework requires little user input and outperforms existing decoders that need ROI extraction. We show that neuropil/background residuals carry additional behaviorally relevant information. Video analysis further reveals an optimal decoding window and dynamics between residuals and cells. Critically, saliency maps reveal the emergence of video-decomposition across our decoder, and identify distinct clusters representing different behavioral aspects. Together, we present a framework that is efficient for decoding behavior from microendoscopic imaging, and may help discover functional clustering for a variety of imaging studies.

scholarly journals End-to-end QoS computation for vertical service composition in the cloud

2021 ◽  
Author(s):  
Raed Karim
Keyword(s):  
Service Composition ◽  
Cloud Service ◽  
Cloud Services ◽  
Prior History ◽  
Functional Requirements ◽  
Active System ◽  
Qos Prediction ◽  
Cloud Providers ◽  
End To End ◽  
Prediction Approach

Cloud services are designed to provide users with different computing models such as software-as-a-Services (SaaS), Infrastructure-as-a-Service (IaaS), Data-as-a-Service (DaaS), and other IT related services (denoted as XaaS). Easy, scalable and on-demand cloud services are offered by cloud providers to users. With the prevalence of different types of cloud services, the task of selecting the best cloud service solution has become more and more challenging. Cloud service solutions are offered through a collaboration of different cloud services at different cloud layers. This type of collaborations is denoted as vertical service composition. Quality of Service (QoS) properties are used as differentiating factors for selecting the best services among functionally equivalent services. In this thesis, we introduce a new service selection framework for the cloud which vertically matches services offered by different cloud providers based on users’ end-to-end QoS requirements. Functional requirements can be satisfied by the required cloud service (software service, platform service, etc) alone. However, users’ QoS requirements must be satisfied using all involved cloud services in a service composition. Therefore, in order to select the best cloud service compositions for users, QoS values of these compositions must be end-to-end. To tackle the problem of computing unknown end-to-end QoS values of vertical cloud service compositions for target users (for whom these values are computed), we propose two strategies: QoS mapping and aggregation and QoS prediction. The former deals with new cloud service compositions with no prior history. Using this strategy, we can map users’ QoS requirements onto different cloud layers and then we aggregate QoS values guaranteed by cloud providers to estimate end-to-end QoS values. The latter deals with cloud service compositions for which QoS data have been recorded in an active system. Using the QoS prediction strategy, we utilize historical QoS data of previously invoked service compositions and other service and user information to predict end-to-end QoS values. The presented experimental results demonstrate the importance of considering vertically composed cloud services when computing end-to-end QoS values as opposed to traditional prediction approaches. Our QoS prediction approach outperforms other prediction approaches in terms of the prediction accuracy by at least 20%.

scholarly journals An End-to-End Approach for QoS-Aware Service Composition

2009 ◽  
Author(s):  
Florian Rosenberg ◽  
Predrag Celikovic ◽  
Anton Michlmayr ◽  
Philipp Leitner ◽  
Schahram Dustdar
Keyword(s):  
Service Composition ◽  
End To End

A novel heuristic algorithm for QoS-aware end-to-end service composition

2011 ◽  
Vol 34 (9) ◽  
pp. 1137-1144 ◽  
Author(s):  
Yuan-sheng Luo ◽  
Yong Qi ◽  
Di Hou ◽  
Lin-feng Shen ◽  
Ying Chen ◽  
...  
Keyword(s):  
Heuristic Algorithm ◽  
Service Composition ◽  
End To End

Converged Network-Cloud Service Composition with End-to-End Performance Guarantee

2018 ◽  
Vol 6 (2) ◽  
pp. 545-557 ◽  
Author(s):  
Jun Huang ◽  
Qiang Duan ◽  
Song Guo ◽  
Yuhong Yan ◽  
Shui Yu
Keyword(s):  
Service Composition ◽  
Cloud Service ◽  
Performance Guarantee ◽  
Converged Network ◽  
End To End ◽  
Cloud Service Composition

scholarly journals End-to-end QoS computation for vertical service composition in the cloud

2021 ◽  
Author(s):  
Raed Karim
Keyword(s):  
Service Composition ◽  
Cloud Service ◽  
Cloud Services ◽  
Prior History ◽  
Functional Requirements ◽  
Active System ◽  
Qos Prediction ◽  
Cloud Providers ◽  
End To End ◽  
Prediction Approach

Cloud services are designed to provide users with different computing models such as software-as-a-Services (SaaS), Infrastructure-as-a-Service (IaaS), Data-as-a-Service (DaaS), and other IT related services (denoted as XaaS). Easy, scalable and on-demand cloud services are offered by cloud providers to users. With the prevalence of different types of cloud services, the task of selecting the best cloud service solution has become more and more challenging. Cloud service solutions are offered through a collaboration of different cloud services at different cloud layers. This type of collaborations is denoted as vertical service composition. Quality of Service (QoS) properties are used as differentiating factors for selecting the best services among functionally equivalent services. In this thesis, we introduce a new service selection framework for the cloud which vertically matches services offered by different cloud providers based on users’ end-to-end QoS requirements. Functional requirements can be satisfied by the required cloud service (software service, platform service, etc) alone. However, users’ QoS requirements must be satisfied using all involved cloud services in a service composition. Therefore, in order to select the best cloud service compositions for users, QoS values of these compositions must be end-to-end. To tackle the problem of computing unknown end-to-end QoS values of vertical cloud service compositions for target users (for whom these values are computed), we propose two strategies: QoS mapping and aggregation and QoS prediction. The former deals with new cloud service compositions with no prior history. Using this strategy, we can map users’ QoS requirements onto different cloud layers and then we aggregate QoS values guaranteed by cloud providers to estimate end-to-end QoS values. The latter deals with cloud service compositions for which QoS data have been recorded in an active system. Using the QoS prediction strategy, we utilize historical QoS data of previously invoked service compositions and other service and user information to predict end-to-end QoS values. The presented experimental results demonstrate the importance of considering vertically composed cloud services when computing end-to-end QoS values as opposed to traditional prediction approaches. Our QoS prediction approach outperforms other prediction approaches in terms of the prediction accuracy by at least 20%.

Sign in / Sign up

Export Citation Format

Share Document