scholarly journals Dynamic Railway Derailment Risk Analysis with Text-Data-Based Bayesian Network

2021 ◽  
Vol 11 (3) ◽  
pp. 994
Author(s):  
Liu Yang ◽  
Keping Li ◽  
Guozheng Song ◽  
Faisal Khan
Keyword(s):  
Bayesian Network ◽  
Graphical Model ◽  
Safety Analysis ◽  
Experimental Results ◽  
Unstructured Data ◽  
Sufficient Information ◽  
Text Data ◽  
Train Derailment ◽  
Prior Probabilities ◽  
Quantitative Results

In recent years, transportation system safety analysis has become increasingly challenging and highly demanding. Unstructured data contain sufficient information from which inherent interactions can be extracted. Determining how to process and fuse a large amount of unstructured data is a challenging task. In this paper, we propose a text-based Bayesian network (TBN) method to establish a Bayesian network (BN) based on text records, where the BN’s arcs are obtained from barrier relationships identified by a graphical model and its prior probabilities stem from fault trees. The comparative experimental results illustrate that the text-based method in TBN is efficient. The precision, recall and F-measure of TBN are 8.64%, 10.70% and 9.84% higher, respectively, than the most frequent (MF) result. Moreover, compared to the traditional BN, whose prior probabilities are frequently acquired from experts, the prior probabilities of the proposed text-based BN (TBN) have a high confidence. The experimental results of a train derailment accident case study show that with changes in the train derailment probabilities and the safety potentials of the barriers, the TBN generates quantitative results and reveals the critical risks of derailment accidents. Additionally, this work demonstrates relevant nonlinear relationships to improve the assessment results. Therefore, based on text-based data, this study reveals that barrier safety analysis has the potential to identify high-risk barriers, which can guide managers to enhance these barriers.

scholarly journals Probabilistic Safety Analysis of High Speed and Conventional Lines Using Bayesian Networks

2016 ◽  
Author(s):  
Zacarias Grande Andrade ◽  
Enrique Castillo Ron ◽  
Alan O'Connor ◽  
Maria Nogal
Keyword(s):  
Bayesian Network ◽  
High Speed ◽  
Human Error ◽  
Driver Behavior ◽  
Safety Evaluation ◽  
Safety Analysis ◽  
Human Errors ◽  
Maintenance Costs ◽  
Railway Line ◽  
Probabilistic Safety

A Bayesian network approach is presented for probabilistic safety analysis (PSA) of railway lines. The idea consists of identifying and reproducing all the elements that the train encounters when circulating along a railway line, such as light and speed limit signals, tunnel or viaduct entries or exits, cuttings and embankments, acoustic sounds received in the cabin, curves, switches, etc. In addition, since the human error is very relevant for safety evaluation, the automatic train protection (ATP) systems and the driver behavior and its time evolution are modelled and taken into account to determine the probabilities of human errors. The nodes of the Bayesian network, their links and the associated probability tables are automatically constructed based on the line data that need to be carefully given. The conditional probability tables are reproduced by closed formulas, which facilitate the modelling and the sensitivity analysis. A sorted list of the most dangerous elements in the line is obtained, which permits making decisions about the line safety and programming maintenance operations in order to optimize them and reduce the maintenance costs substantially. The proposed methodology is illustrated by its application to several cases that include real lines such as the Palencia-Santander and the Dublin-Belfast lines.DOI: http://dx.doi.org/10.4995/CIT2016.2016.3428

Bayesian Networks

2011 ◽  
pp. 89-93 ◽  
Author(s):  
Ahmad Bashir ◽  
Latifur Khan ◽  
Mamoun Awad
Keyword(s):  
Neural Networks ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Decision Trees ◽  
Graphical Model ◽  
Conditional Probabilities ◽  
Rule Bases

A Bayesian network is a graphical model that finds probabilistic relationships among variables of a system. The basic components of a Bayesian network include a set of nodes, each representing a unique variable in the system, their inter-relations, as indicated graphically by edges, and associated probability values. By using these probabilities, termed conditional probabilities, and their interrelations, we can reason and calculate unknown probabilities. Furthermore, Bayesian networks have distinct advantages compared to other methods, such as neural networks, decision trees, and rule bases, which we shall discuss in this paper.

Modeling of situation assessment in regional air defense combat

2018 ◽  
Vol 16 (2) ◽  
pp. 91-101
Author(s):  
Hai-yan Yang ◽  
Shuai-wen Zhang ◽  
Xu-yu Li
Keyword(s):  
Decision Making ◽  
Particle Swarm Optimization ◽  
Bayesian Network ◽  
Particle Swarm ◽  
Flight Path ◽  
Experimental Results ◽  
Situation Assessment ◽  
Swarm Optimization ◽  
Air Defense ◽  
New Framework

The purpose of situation assessment in regional air defense combat is to quickly fuse data as well as to provide commanders with timely support for decision making. We propose a new framework for situation assessment in regional air defense combat, which plays a very concrete role in real combat and follows the combat process. The proposed framework involves three aspects: assessment of the air defense capability of a region; the prediction of an enemy’s invasion route; and the generation of an interception plan. A Bayesian network is used to evaluate and infer the air defense capability of a region. In the network, the calculation of input evidence is based on threat models from radar, the terrain, and anti-aircraft firepower. The weak areas for air defense can be observed when the evaluation is completed. Accordingly, the possible flight path of an enemy invader can be predicted via particle swarm optimization. We build an interception model based on existing attack modes for intercepting enemy aircraft to provide pre-planning for interception. The experimental results prove the feasibility and effectiveness of the proposed method. In particular, the proposed method can contribute to quick decision making in regional air defense combat.

scholarly journals Effective processing of unstructured data using python in Hadoop map reduce

2018 ◽  
Vol 7 (2.21) ◽  
pp. 417
Author(s):  
K Kousalya ◽  
Shaik Javed Parvez
Keyword(s):  
Open Source ◽  
Unstructured Data ◽  
Map Reduce ◽  
Text Data ◽  
Apache Hadoop ◽  
Unstructured Text ◽  
Wide Range ◽  
Two Stages

In present scenario, the growing data are naturally unstructured. In this case to handle the wide range of data, is difficult. The proposed paper is to process the unstructured text data effectively in Hadoop map reduce using Python. Apache Hadoop is an open source platform and it widely uses Map Reduce framework. Map Reduce is popular and effective for processing the unstructured data in parallel manner.  There are two stages in map reduce, namely transform and repository. Here the input splits into small blocks and worker node process individual blocks in parallel. This map reduce generally is based on java. While Hadoop Streaming allows writing mapper and reducer in other languages like Python. In this paper, we are going to show an alternative way of processing the growing unstructured content data by using python. We will also compare the performance between java based and non-java based programs. 

Development of a Bayesian Network for the Prognosis of Head Injuries using Graphical Model Selection Techniques

1999 ◽  
Vol 38 (01) ◽  
pp. 37-42 ◽  
Author(s):  
G. C. Sakellaropoulos ◽  
G. C. Nikiforidis
Keyword(s):  
Model Selection ◽  
Bayesian Network ◽  
Analytical Approach ◽  
Graphical Model ◽  
Head Injuries ◽  
Sources Of Information ◽  
Laboratory Findings ◽  
Learning Techniques ◽  
Head Injured ◽  
Injured Patients

Abstract:The assessment of a head-injured patient’s prognosis is a task that involves the evaluation of diverse sources of information. In this study we propose an analytical approach, using a Bayesian Network (BN), of combining the available evidence. The BN’s structure and parameters are derived by learning techniques applied to a database (600 records) of seven clinical and laboratory findings. The BN produces quantitative estimations of the prognosis after 24 hours for head-injured patients in the outpatients department. Alternative models are compared and their performance is tested against the success rate of an expert neurosurgeon.

scholarly journals Thinning a Triangulation of a Bayesian Network or Undirected Graph to Create a Minimal Triangulation

2017 ◽  
Vol 25 (03) ◽  
pp. 1750014
Author(s):  
Edmund Jones ◽  
Vanessa Didelez
Keyword(s):  
Bayesian Network ◽  
Graphical Model ◽  
Undirected Graph ◽  
Computer Experiment ◽  
R Package ◽  
The Other ◽  
Prime Decomposition ◽  
Original Graph ◽  
Minimal Triangulation

In one procedure for finding the maximal prime decomposition of a Bayesian network or undirected graphical model, the first step is to create a minimal triangulation of the network, and a common and straightforward way to do this is to create a triangulation that is not necessarily minimal and then thin this triangulation by removing excess edges. We show that the algorithm for thinning proposed in several previous publications is incorrect. A different version of this algorithm is available in the R package gRbase, but its correctness has not previously been proved. We prove that this version is correct and provide a simpler version, also with a proof. We compare the speed of the two corrected algorithms in three ways and find that asymptotically their speeds are the same, neither algorithm is consistently faster than the other, and in a computer experiment the algorithm used by gRbase is faster when the original graph is large, dense, and undirected, but usually slightly slower when it is directed.

scholarly journals Probabilistic Graphical Model using Bayesian Networks for Predicting Clinical Outcome after Posterior Decompression in Patients with Cervical Spondylotic Myelopathy

2020 ◽  
Author(s):  
Sung Bae Park ◽  
Sohee Oh ◽  
Changwon Yoo ◽  
Dong Ah Shin ◽  
Sun-Ho Lee ◽  
...  
Keyword(s):  
Clinical Outcome ◽  
Bayesian Network ◽  
Cervical Spondylotic Myelopathy ◽  
Graphical Model ◽  
Probabilistic Graphical Model ◽  
Symptom Duration ◽  
Posterior Decompression ◽  
Causal Factors ◽  
Gait Impairment ◽  
Network Analyses

Abstract BackgroundThe objective of this study was to develop a probabilistic graphical model (PGM) to show the personalized prediction of clinical outcome in patients with cervical spondylotic myelopathy (CSM) with different clinical conditions after posterior decompression and to use the PGM to identify causal predictors of the outcome.MethodsWe included data from 59 patients who had undergone cervical posterior decompression for CSM. The candidate predictive parameters were age, sex, body mass index, trauma history, symptom duration, preoperative and last Japanese Orthopaedic Association (JOA) scores, gait impairment, claudication, bladder dysfunction, Nurick grade, American Spinal Injury Association (ASIA) grade, smoking, diabetes mellitus, cardiopulmonary disorders, hypertension, stroke, Parkinson disease, dementia, psychiatric disorders, arthritis, ossification of the posterior longitudinal ligament, cord signal change in T1-weighted images, postoperative kyphosis, and cord compression ratio. Statistical and Bayesian network analyses were used to create the PGM and identify predictive factors.ResultsIn multiple linear regression analysis, preoperative JOA score, presence of a psychiatric disorder, and ASIA grade were identified as significant factors associated with the last JOA score. Dementia, sex, preoperative JOA score, and gait impairment were causal factors in the PGM with 93.2% accuracy. Sex, dementia, and preoperative JOA score were direct causal factors related to the last JOA score. Being female, having dementia, and a low preoperative JOA score were significantly related to having a low last JOA score. The PGM showed that preoperative JOA score and sex did not affect the last JOA score in patients with dementia. The probability of having a high last JOA score was higher in men with a high preoperative JOA score than in women with the same preoperative state (74% vs. 2%, respectively).ConclusionsThe causal predictors of surgical outcome for CSM were sex, dementia, and preoperative JOA score. Use of the PGM with the Bayesian network may be useful personalized medicine tool for predicting the outcome for each patient with CSM.

scholarly journals Determination of the Type of Heart Syndrome in Traditional Chinese Medicine with the Bayesian Network Method

2020 ◽  
Vol 12 (2) ◽  
pp. 32-38
Author(s):  
Asto Buditjahjanto
Keyword(s):  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Bayesian Networks ◽  
Bayesian Network ◽  
Expert Knowledge ◽  
Prior Probabilities ◽  
Network Method

The determination of a disease syndrome in the TCM is difficult enough to determine because it requires a lot of experience in observing patients' symptoms that appear in disease syndrome and their disease syndrome history. Symptoms that appear in one disease syndrome are varied and can also appear in other disease syndromes. This research limits the determination of the type of syndrome only in the heart organ. The purpose of this study is to determine the type of heart syndrome in TCM by using Bayesian Networks. Bayesian Networks is used because it has the advantage of adapting expert knowledge toward the preferences of symptoms that arise at a type of heart syndrome. The expert's preference is in the weights that act as prior probabilities that are used as the basis for calculations on the Bayesian Networks. The results showed that the Bayesian Networks can be used to determine the type of heart syndrome well. The results of trials on 7 patients yield the same diagnosis between the doctor's diagnosis and the Bayesian Networks calculation

scholarly journals Research on Risk Assessment of Science and Technology Data in Network Finance Based on Portfolio Empowerment

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Qi Zhao
Keyword(s):  
Risk Assessment ◽  
Data Analysis ◽  
Decision Tree ◽  
Bayesian Network ◽  
Risk Index ◽  
Experimental Results ◽  
Characteristic Quantity ◽  
The Status ◽  
Assessment Time ◽  
Definition Of

At present, the proposed network finance technology data risk assessment time is too long, leading to low accuracy. In order to solve the above problems, this paper puts forward the research on the risk assessment of network financial S&T data based on portfolio weighting, determines the risk index of network financial S&T data, calculates the weight of risk data in network S&T data, searches the risk data characteristic quantity in networks according to network S&T risk index, and completes the extraction of risk data. According to the risk data characteristics of network finance, a decision tree is constructed, the data entropy involved in the decision tree is calculated, the types of risk data characteristics are induced, the nodes of the decision tree are created, and the status of risk data of network finance is obtained. The state of risk data is brought into the definition of Bayesian network probability, and the risk degree of risk data is analyzed to improve the precision of risk data analysis. The experimental results show that the risk assessment of network financial S&T data based on portfolio weighting can effectively shorten the assessment time and improve the accuracy.

Sign in / Sign up

Export Citation Format

Share Document