LEARNING NAIVE PHYSICS BY VISUAL OBSERVATION: USING QUALITATIVE SPATIAL REPRESENTATIONS AND PROBABILISTIC REASONING

2001 ◽  
Vol 01 (03) ◽  
pp. 273-285 ◽  
Author(s):  
PAUL A. BOXER
Keyword(s):  
Bayesian Network ◽  
Probabilistic Reasoning ◽  
Autonomous Robots ◽  
Visual Observation ◽  
Spatial Representations ◽  
Physical Behavior ◽  
Naive Physics ◽  
Action At A Distance ◽  
General Physical ◽  
Test Scenarios

Autonomous robots are unsuccessful at operating in complex, unconstrained environments. They lack the ability to learn about the physical behavior of different objects through the use of vision. We combine Bayesian networks and qualitative spatial representation to learn general physical behavior by visual observation. We input training scenarios that allow the system to observe and learn normal physical behavior. The position and velocity of the visible objects are represented as qualitative states. Transitions between these states over time are entered as evidence into a Bayesian network. The network provides probabilities of future transitions to produce predictions of future physical behavior. We use test scenarios to determine how well the approach discriminates between normal and abnormal physical behavior and actively predicts future behavior. We examine the ability of the system to learn three naive physical concepts, "no action at a distance", "solidity" and "movement on continuous paths". We conclude that the combination of qualitative spatial representations and Bayesian network techniques is capable of learning these three rules of naive physics.

Bayesian Network: Probabilistic Reasoning, Statistical Learning, and Applications

2004 ◽  
Vol 8 (2) ◽  
pp. 93-99 ◽  
Author(s):  
Yoichi Motomura ◽  
Keyword(s):  
Information Processing ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Statistical Learning ◽  
Probabilistic Models ◽  
Probabilistic Reasoning ◽  
Network Models ◽  
Intelligent Information Processing ◽  
Intelligent Information ◽  
Bayesian Network Models

Bayesian networks are probabilistic models that can be used for prediction and decision-making in the presence of uncertainty. For intelligent information processing, probabilistic reasoning based on Bayesian networks can be used to cope with uncertainty in real-world domains. In order to apply this, we need appropriate models and statistical learning methods to obtain models. We start by reviewing Bayesian network models, probabilistic reasoning, statistical learning, and related researches. Then, we introduce applications for intelligent information processing using Bayesian networks.

scholarly journals Attack Impact Discovery and Recovery with Dynamic Bayesian Networks

2019 ◽  
Vol 8 (S1) ◽  
pp. 74-79
Author(s):  
T. Rajeshwari ◽  
C. Thangamani
Keyword(s):  
Bayesian Network ◽  
Impact Analysis ◽  
Probabilistic Reasoning ◽  
Belief Propagation ◽  
Dynamic Bayesian Network ◽  
Data Communication ◽  
Dynamic Bayesian Networks ◽  
Attack Detection ◽  
Object State ◽  
Dependency Network

The network attacks are discovered using the Intrusion Detection Systems (IDS). Anomaly, signature and compound attack detection schemes are employed to fetch malicious data traffic activities. The attack impact analysis operations are carried out to discover the malicious objects in the network. The system objects are contaminated with process injection or hijacking. The attack ramification model discovers the contaminated objects. The dependency networks are built to model the information flow over the objects in the network. The dependency network is a directed graph built to indicate the data communication over the objects. The attack ramification models are designed with intrusion root information. The attack ramifications are applied to identify the malicious objects and contaminated objects. The attack ramifications are discovered with the information flows from the attack sources. The Attack Ramification with Bayesian Network (ARBN) scheme discovers the attack impact without the knowledge of the intrusion root. The probabilistic reasoning approach is employed to analyze the object state for ramification process. The objects lifetime is divided into temporal slices to verify the object state changes. The system call traces and object slices are correlated to construct the Temporal Dependency Network (TDN). The Bayesian Network (BN) is constructed with the uncertain data communication activities extracted from the TDN. The attack impact is fetched with loopy belief propagation on the BN model. The network security system is built with attack impact analysis and recovery operations. Live traffic data analysis process is carried out with improved temporal slicing concepts. Attack Ramification and Recovery with Dynamic Bayesian Network (ARRDBN) is built to support attack impact analysis and recovery tasks. The unsupervised attack handling mechanism automatically discovers the feasible solution for the associated attacks.

scholarly journals Mapping Flood-Based Farming Systems with Bayesian Networks

Land ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 369 ◽  
Author(s):  
Issoufou Liman Harou ◽  
Cory Whitney ◽  
James Kung’u ◽  
Eike Luedeling
Keyword(s):  
Remote Sensing ◽  
Bayesian Network ◽  
Spatial Data ◽  
Probabilistic Reasoning ◽  
Expert Knowledge ◽  
Agricultural Research ◽  
Remote Sensing Data ◽  
Farming Systems ◽  
Spatially Explicit ◽  
Sensing Data

Many actors in agricultural research, development, and policy arenas require accurate information on the spatial extents of cropping and farming practices. While remote sensing provides ways for obtaining such information, it is often difficult to distinguish between different types of agricultural practices or identify particular farming systems. Stochastic system behavior or similarity in the spectral signatures of different system components can lead to misclassification. We addressed this challenge by using a probabilistic reasoning engine informed by expert knowledge and remote sensing data to map flood-based farming systems (FBFS) across Kisumu County in Kenya and the Tigray region in Ethiopia. Flood-based farming is an important form of agricultural production employed in regions with seasonal water surplus, which can be harvested and used to irrigate crops. Geographic settings for FBFS vary widely in terms of hydrology, vegetation, and local practices of agronomic flooding. Agronomic success is often difficult to anticipate, because the timing and amount of flooding usually cannot be precisely predicted. We generated a Bayesian network model to describe the FBFS settings of the study regions. We acquired three years (2014–2016) of Moderate Resolution Imaging Spectroradiometer (MODIS) Terra spectral data as eight-day composite time series and elevation data from the Shuttle Radar Topography Mission (SRTM) to compute 10 spatial data metrics corresponding to 10 of the 17 Bayesian network nodes. We used the spatial data metrics in a fully probabilistic framework to generate the 10 spatial data nodes. We then used these as inputs for the probabilistic model to generate prior and posterior spatial estimates for specific metrics along with their spatially explicit uncertainties. We show how such an approach can be used to predict plausible areas for FBFS based on several scenarios. We demonstrate how spatially explicit information can be derived from remote sensing data as fuzzy quantifiers for incorporating uncertainties when mapping complex systems. The approach achieved a remarkably accurate result in both study areas, where 84–90% of various FBFS fields sampled were correctly mapped as having a high chance of being suitable for the practice.

scholarly journals Estimating Bridge Reliability by Using Bayesian Networks

2021 ◽  
Author(s):  
Andrew B. Groeneveld ◽  
Stephanie G. Wood ◽  
Edgardo Ruiz
Keyword(s):  
Mechanical Properties ◽  
Reinforced Concrete ◽  
Bayesian Network ◽  
Cross Section ◽  
Visual Observation ◽  
Expert Elicitation ◽  
Structural System ◽  
Concrete Girders ◽  
Bridge Reliability ◽  
Main Components

As part of an inspection, bridge inspectors assign condition ratings to the main components of a bridge’s structural system and identify any defects that they observe. Condition ratings are necessarily somewhat subjective, as they are influenced by the experience of the inspectors. In the current work, procedures were developed for making inferences on the reliability of reinforced concrete girders with defects at both the cross section and the girder level. The Bayesian network (BN) tools constructed in this work use simple structural m echanics to model the capacity of girders. By using expert elicitation, defects observed during inspection are correlated with underlying deterioration mechanisms. By linking these deterioration mechanisms with reductions in mechanical properties, inferences on the reliability of a bridge can be made based on visual observation of defects. With more development, this BN tool can be used to compare conditions of bridges relative to one another and aid in the prioritization of repairs. However, an extensive survey of bridges affected by deterioration mechanisms is needed to confidently establish valid relationships between deterioration severity and mechanical properties.

scholarly journals Performance optimization scheme of turboshaft aeroengine based on Bayesian network

2021 ◽  
Vol 39 (2) ◽  
pp. 375-381
Author(s):  
Ning Wang ◽  
Yuhang Wang ◽  
Zhiqiang Cai ◽  
Shuai Zhang
Keyword(s):  
Bayesian Network ◽  
Performance Optimization ◽  
Probabilistic Reasoning ◽  
Temperature Limit ◽  
Performance Model ◽  
Machine Learning Algorithms ◽  
Pass Rate ◽  
Maximum Temperature ◽  
Data Set ◽  
Important Indicator

The turboshaft aeroengine is mainly used in helicopters. As a power device that drives the rotor to generate lift and propulsion, it has been rapidly developed in recent years. The manufacturing process of turboshaft aeroengine is complex, and there is a strict factory inspection mechanism. Only when the various performance indicators meet the qualified requirements of the factory conditions, it makes the ex factory pass rate of turboshaft aeroengine often not ideal. The key section temperature is an important indicator to characterize the performance of turboshaft aeroengine. In order to ensure the reliability of the whole machine, it has a maximum temperature limit. According to the manufacturer's suggestions, four attribute variables that affect the key section temperature are extracted to form a research data set. Then, after preprocessing the data set, the performance model for the turboshaft aeroengine is established based on the Bayesian network. According to the characteristics of Bayesian network, the posterior qualified probability is calculated through probabilistic reasoning of the performance model, and the current mainstream machine learning algorithms are introduced to compare and verify the validity of the performance model. Finally, the recommended state combination table is proposed, which provides the effective suggestions for the performance optimization of turboshaft aeroengine.

scholarly journals A Bayesian Network under Strict Chain Model for Computing Flow Risks in Smart City

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Zengfanxiang Wei ◽  
Lei Zhang ◽  
Qi Yue ◽  
Muchen Zhong
Keyword(s):  
Risk Factor ◽  
Bayesian Network ◽  
Smart City ◽  
Probabilistic Reasoning ◽  
Medical Surgery ◽  
Chain Model ◽  
Process Step ◽  
Transportation Management ◽  
Smart Hospital ◽  
Key Factor

Risk management is a key factor for smart city running. There are many risk events in a strict process like transportation management of a smart city or a medical surgery in a smart hospital, and every step may lead to one kind of risk or more. In view of the fact that the occurrence of the flow risks follows the sequence formed by each process step, this paper presents a Bayesian network under strict chain (BN_SC) to model this situation. In this model, the probabilistic reasoning formula is given according to the sequence of process steps, and the probabilities given by the model can do risk factor analysis to support the system to find an effective way to improve the process like machine manufacturing or a medical surgery. Finally, an example is analyzed based on the information given by doctors according to the situation of LC in their hospital located in Sichuan Province of China, which shows the effectiveness and rationality of the proposed BN_SC model.

Sign in / Sign up

Export Citation Format

Share Document