scholarly journals Matching models across abstraction levels with Gaussian Processes

2016 ◽  
Author(s):  
Giulio Caravagna ◽  
Luca Bortolussi ◽  
Guido Sanguinetti
Keyword(s):  
Machine Learning ◽  
Gaussian Processes ◽  
Random Function ◽  
Statistical Machine Learning ◽  
Levels Of Abstraction ◽  
Model Predictions ◽  
Matching Models ◽  
Abstraction Levels ◽  
Different Levels ◽  
Proof Of Principle

AbstractBiological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively concordant predictions over specific parametrisations, but it is generally unclear whether model predictions are quantitatively in agreement, and whether such agreement holds for different parametrisations. Here we present a generally applicable statistical machine learning methodology to automatically reconcile the predictions of different models across abstraction levels. Our approach is based on defining a correction map, a random function which modifies the output of a model in order to match the statistics of the output of a different model of the same system. We use two biological examples to give a proof-of-principle demonstration of the methodology, and discuss its advantages and potential further applications.

scholarly journals A Hierarchy-Based System for Recognizing Customer Activity in Retail Environments

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4712
Author(s):  
Jiahao Wen ◽  
Luis Guillen ◽  
Toru Abe ◽  
Takuo Suganuma
Keyword(s):  
Machine Learning ◽  
Activity Recognition ◽  
Experimental Results ◽  
Levels Of Abstraction ◽  
Concurrent Use ◽  
Marketing Planning ◽  
Store Management ◽  
End To End ◽  
Different Levels

Customer activity (CA) in retail environments, which ranges over various shopper situations in store spaces, provides valuable information for store management and marketing planning. Several systems have been proposed for customer activity recognition (CAR) from in-store camera videos, and most of them use machine learning based end-to-end (E2E) CAR models, due to their remarkable performance. Usually, such E2E models are trained for target conditions (i.e., particular CA types in specific store spaces). Accordingly, the existing systems are not malleable to fit the changes in target conditions because they require entire retraining of their specialized E2E models and concurrent use of additional E2E models for new target conditions. This paper proposes a novel CAR system based on a hierarchy that organizes CA types into different levels of abstraction from lowest to highest. The proposed system consists of multiple CAR models, each of which performs CAR tasks that belong to a certain level of the hierarchy on the lower level’s output, and thus conducts CAR for videos through the models level by level. Since these models are separated, this system can deal efficiently with the changes in target conditions by modifying some models individually. Experimental results show the effectiveness of the proposed system in adapting to different target conditions.

scholarly journals Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dimitri Boeckaerts ◽  
Michiel Stock ◽  
Bjorn Criel ◽  
Hans Gerstmans ◽  
Bernard De Baets ◽  
...  
Keyword(s):  
Machine Learning ◽  
Predictive Model ◽  
Receptor Binding ◽  
Bacterial Infections ◽  
Sequence Data ◽  
Sequence Similarity ◽  
Area Under The Curve ◽  
Local Alignment ◽  
Search Tool ◽  
Different Levels

AbstractNowadays, bacteriophages are increasingly considered as an alternative treatment for a variety of bacterial infections in cases where classical antibiotics have become ineffective. However, characterizing the host specificity of phages remains a labor- and time-intensive process. In order to alleviate this burden, we have developed a new machine-learning-based pipeline to predict bacteriophage hosts based on annotated receptor-binding protein (RBP) sequence data. We focus on predicting bacterial hosts from the ESKAPE group, Escherichia coli, Salmonella enterica and Clostridium difficile. We compare the performance of our predictive model with that of the widely used Basic Local Alignment Search Tool (BLAST). Our best-performing predictive model reaches Precision-Recall Area Under the Curve (PR-AUC) scores between 73.6 and 93.8% for different levels of sequence similarity in the collected data. Our model reaches a performance comparable to that of BLASTp when sequence similarity in the data is high and starts outperforming BLASTp when sequence similarity drops below 75%. Therefore, our machine learning methods can be especially useful in settings in which sequence similarity to other known sequences is low. Predicting the hosts of novel metagenomic RBP sequences could extend our toolbox to tune the host spectrum of phages or phage tail-like bacteriocins by swapping RBPs.

scholarly journals Model-Driven Architectural Framework towards Safe and Secure Nuclear Power Reactors

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5136
Author(s):  
Bassem Ouni ◽  
Christophe Aussagues ◽  
Saadia Dhouib ◽  
Chokri Mraidha
Keyword(s):  
Nuclear Power ◽  
Nuclear Reactors ◽  
System Development ◽  
Levels Of Abstraction ◽  
Model Driven ◽  
Case System ◽  
Architectural Framework ◽  
Performance Check ◽  
High Level ◽  
Different Levels

Sensor-based digital systems for Instrumentation and Control (I&C) of nuclear reactors are quite complex in terms of architecture and functionalities. A high-level framework is highly required to pre-evaluate the system’s performance, check the consistency between different levels of abstraction and address the concerns of various stakeholders. In this work, we integrate the development process of I&C systems and the involvement of stakeholders within a model-driven methodology. The proposed approach introduces a new architectural framework that defines various concepts, allowing system implementations and encompassing different development phases, all actors, and system concerns. In addition, we define a new I&C Modeling Language (ICML) and a set of methodological rules needed to build different architectural framework views. To illustrate this methodology, we extend the specific use of an open-source system engineering tool, named Eclipse Papyrus, to carry out many automation and verification steps at different levels of abstraction. The architectural framework modeling capabilities will be validated using a realistic use case system for the protection of nuclear reactors. The proposed framework is able to reduce the overall system development cost by improving links between different specification tasks and providing a high abstraction level of system components.

Sign in / Sign up

Export Citation Format

Share Document