Search results for: bayesian inference

Authors: Rajesh Kumar G

Abstract:

A challenging aspect of any clinical trial is to carefully plan the study design to meet the study objective in optimum way and to validate the assumptions made during protocol designing. And when it is a pediatric study, there is the added challenge of stringent guidelines and difficulty in recruiting the necessary subjects. Unlike adult trials, there is not much historical data available for pediatrics, which is required to validate assumptions for planning pediatric trials. Typically, pediatric studies are initiated as soon as approval is obtained for a drug to be marketed for adults, so with the adult study historical information and with the available pediatric pilot study data or simulated pediatric data, the pediatric study can be well planned. Generalizing the historical adult study for new pediatric study is a tedious task; however, it is possible by integrating various statistical techniques and utilizing the advantage of hybrid study design, which will help to achieve the study objective in a smoother way even with the presence of many constraints. This research paper will explain how well the hybrid study design can be planned along with integrated technique (SEV) to plan the pediatric study; In brief the SEV technique (Simulation, Estimation (using borrowed adult data and applying Bayesian methods)) incorporates the use of simulating the planned study data and getting the desired estimates to Validate the assumptions.This method of validation can be used to improve the accuracy of data analysis, ensuring that results are as valid and reliable as possible, which allow us to make informed decisions well ahead of study initiation. With professional precision, this technique based on the collected data allows to gain insight into best practices when using data from historical study and simulated data alike.

Keywords: adaptive design, simulation, borrowing data, bayesian model

Procedia PDF Downloads 76

Authors: Fally Titikpina, Abderafi Charki, Antoine Caucheteux, David Bigaud

Abstract:

The building sector is one of the largest energy consumer with about 40% of the final energy consumption in the European Union. Ensuring building energy performance is of scientific, technological and sociological matter. To assess a building energy performance, the consumption being predicted or estimated during the design stage is compared with the measured consumption when the building is operational. When valuing this performance, many buildings show significant differences between the calculated and measured consumption. In order to assess the performance accurately and ensure the thermal efficiency of the building, it is necessary to evaluate the uncertainties involved not only in measurement but also those induced by the propagation of dynamic and static input data in the model being used. The evaluation of measurement uncertainty is based on both the knowledge about the measurement process and the input quantities which influence the result of measurement. Measurement uncertainty can be evaluated within the framework of conventional statistics presented in the \textit{Guide to the Expression of Measurement Uncertainty (GUM)} as well as by Bayesian Statistical Theory (BST). Another choice is the use of numerical methods like Monte Carlo Simulation (MCS). In this paper, we proposed to evaluate the uncertainty associated to the use of a simplified model for the estimation of the energy consumption of a given building. A detailed review and discussion of these three approaches (GUM, MCS and BST) is given. Therefore, an office building has been monitored and multiple sensors have been mounted on candidate locations to get required data. The monitored zone is composed of six offices and has an overall surface of 102 $m^2$. Temperature data, electrical and heating consumption, windows opening and occupancy rate are the features for our research work.

Keywords: building energy performance, uncertainty evaluation, GUM, bayesian approach, monte carlo method

Procedia PDF Downloads 458

Authors: Sabyasachi Mukhopadhyay, Joseph Ogutu, Gundula Bartzke, Hans-Peter Piepho

Abstract:

Rainfall is a critical component of climate governing vegetation growth and production, forage availability and quality for herbivores. However, reliable rainfall measurements are not always available, making it necessary to predict rainfall values for particular locations through time. Predicting rainfall in space and time can be a complex and challenging task, especially where the rain gauge network is sparse and measurements are not recorded consistently for all rain gauges, leading to many missing values. Here, we develop a flexible Bayesian model for predicting rainfall in space and time and apply it to Narok County, situated in southwestern Kenya, using data collected at 23 rain gauges from 1965 to 2015. Narok County encompasses the Maasai Mara ecosystem, the northern-most section of the Mara-Serengeti ecosystem, famous for its diverse and abundant large mammal populations and spectacular migration of enormous herds of wildebeest, zebra and Thomson's gazelle. The model incorporates geographical and meteorological predictor variables, including elevation, distance to Lake Victoria and minimum temperature. We assess the efficiency of the model by comparing it empirically with the established Gaussian process, Kriging, simple linear and Bayesian linear models. We use the model to predict total monthly rainfall and its standard error for all 5 * 5 km grid cells in Narok County. Using the Monte Carlo integration method, we estimate seasonal and annual rainfall and their standard errors for 29 sub-regions in Narok. Finally, we use the predicted rainfall to predict large herbivore biomass in the Maasai Mara ecosystem on a 5 * 5 km grid for both the wet and dry seasons. We show that herbivore biomass increases with rainfall in both seasons. The model can handle data from a sparse network of observations with many missing values and performs at least as well as or better than four established and widely used models, on the Narok data set. The model produces rainfall predictions consistent with expectation and in good agreement with the blended station and satellite rainfall values. The predictions are precise enough for most practical purposes. The model is very general and applicable to other variables besides rainfall.

Keywords: non-stationary covariance function, gaussian process, ungulate biomass, MCMC, maasai mara ecosystem

Procedia PDF Downloads 294

Authors: H. G. C. P. Dinesh, G. Tharshini, M. P. B. Ekanayake, G. M. R. I. Godaliyadda

Abstract:

This paper presents a new spatial feature extraction method based on principle component analysis (PCA) and Fisher Discernment Analysis (FDA) for facial expression recognition. It not only extracts reliable features for classification, but also reduces the feature space dimensions of pattern samples. In this method, first each gray scale image is considered in its entirety as the measurement matrix. Then, principle components (PCs) of row vectors of this matrix and variance of these row vectors along PCs are estimated. Therefore, this method would ensure the preservation of spatial information of the facial image. Afterwards, by incorporating the spectral information of the eigen-filters derived from the PCs, a feature vector was constructed, for a given image. Finally, FDA was used to define a set of basis in a reduced dimension subspace such that the optimal clustering is achieved. The method of FDA defines an inter-class scatter matrix and intra-class scatter matrix to enhance the compactness of each cluster while maximizing the distance between cluster marginal points. In order to matching the test image with the training set, a cosine similarity based Bayesian classification was used. The proposed method was tested on the Cohn-Kanade database and JAFFE database. It was observed that the proposed method which incorporates spatial information to construct an optimal feature space outperforms the standard PCA and FDA based methods.

Keywords: facial expression recognition, principle component analysis (PCA), fisher discernment analysis (FDA), eigen-filter, cosine similarity, bayesian classifier, f-measure

Procedia PDF Downloads 425

Authors: Bo Yan, Amy Y. M. Chow

Abstract:

Bereavement is recognized as a universal challenging experience. It is important to gather research evidence on protective factors in bereavement. Hope is considered as one of the protective factors in previous coping studies. The present study aims to add knowledge by investigating hope at the first month after death to predict psychological symptoms altogether including complicated grief (CG), anxiety, and depressive symptoms at the seventh month. The data were collected via one-on-one interview survey in a longitudinal project with Hong Kong hospice users (sample size 105). Most participants were at their middle age (49-year-old on average), female (72%), with no religious affiliation (58%). Bayesian Structural Equation Modeling (BSEM) analysis was conducted on the longitudinal dataset. The BSEM findings show that hope at the first month of bereavement negatively predicts both CG and anxiety symptoms at the seventh month but not for depressive symptoms. Age and gender are controlled in the model. The overall model fit is good. The current study findings suggest assessing hope at the first month of bereavement. Hope at the first month after the loss is identified as an excellent predictor for complicated grief and anxiety symptoms at the seventh month. The result from this sample is clear, so it encourages cross-cultural research on replicated modeling and development of further clinical application. Particularly, practical consideration for early intervention to increase the level of hope has the potential to reduce the psychological symptoms and thus to improve the bereaved persons’ wellbeing in the long run.

Keywords: anxiety, complicated grief, depressive symptoms, hope, structural equational modeling

Procedia PDF Downloads 203

Authors: Behnaz Moradijamei, Michael Higgins

Abstract:

Identifying community structure is a critical task in analyzing social media data sets often modeled by networks. Statistical models such as the stochastic block model have proven to explain the structure of communities in real-world network data. In this work, we develop a goodness-of-fit test to examine community structure's existence by using a distinguishing property in networks: cyclic structures are more prevalent within communities than across them. To better understand how communities are shaped by the cyclic structure of the network rather than just the number of edges, we introduce a novel method for deciding on the existence of communities. We utilize these structures by using renewal non-backtracking random walk (RNBRW) to the existing goodness-of-fit test. RNBRW is an important variant of random walk in which the walk is prohibited from returning back to a node in exactly two steps and terminates and restarts once it completes a cycle. We investigate the use of RNBRW to improve the performance of existing goodness-of-fit tests for community detection algorithms based on the spectral properties of the adjacency matrix. Our proposed test on community structure is based on the probability distribution of eigenvalues of the normalized retracing probability matrix derived by RNBRW. We attempt to make the best use of asymptotic results on such a distribution when there is no community structure, i.e., asymptotic distribution under the null hypothesis. Moreover, we provide a theoretical foundation for our statistic by obtaining the true mean and a tight lower bound for RNBRW edge weights variance.

Keywords: hypothesis testing, RNBRW, network inference, community structure

Procedia PDF Downloads 150

Authors: Riyadh Jamegh, AllaEldin Kassam, Sawsan Sabih

Abstract:

In modern trends of market, organizations face high-pressure environment which is characterized by globalization, high competition, and customer orientation, so it is very crucial to control and know the weak and strong points of the supply chain in order to improve their performance. So the performance measurements presented as an important tool of supply chain management because it's enabled the organizations to control, understand, and improve their efficiency. This paper aims to identify supply chain performance measurement (SCPM) by using Fuzzy Analytical Hierarchical Process (FAHP). In our real application, the performance of organizations estimated based on four parameters these are cost parameter indicator of cost (CPI), inventory turnover parameter indicator of (INPI), raw material parameter (RMPI), and safety stock level parameter indicator (SSPI), these indicators vary in impact on performance depending upon policies and strategies of organization. In this research (FAHP) technique has been used to identify the importance of such parameters, and then first fuzzy inference (FIR1) is applied to identify performance indicator of each factor depending on the importance of the factor and its value. Then, the second fuzzy inference (FIR2) also applied to integrate the effect of these indicators and identify (SCPM) which represent the required output. The developed approach provides an effective tool for evaluation of supply chain performance measurement.

Keywords: fuzzy performance measurements, supply chain, fuzzy logic, key performance indicator

Procedia PDF Downloads 141

Authors: Serge Tshibangu, Turgay Celik, Zenzo Ncube

Abstract:

Road crashes kill nearly over a million people every year, and leave millions more injured or permanently disabled. Various annual reports reveal that the percentage of fatal crashes due to fatigue/driver falling asleep comes directly after the percentage of fatal crashes due to intoxicated drivers. This percentage is higher than the combined percentage of fatal crashes due to illegal/Un-Safe U-turn and illegal/Un-Safe reversing. Although a relatively small percentage of police reports on road accidents highlights drowsiness and fatigue, the importance of these factors is greater than we might think, hidden by the undercounting of their events. Some scenarios show that these factors are significant in accidents with killed and injured people. Thus the need for an automatic drivers fatigue detection system in order to considerably reduce the number of accidents owing to fatigue.This research approaches the drivers fatigue detection problem in an innovative way by combining cues collected from both temporal analysis of drivers’ faces and environment. Monotony in driving environment is inter-related with visual symptoms of fatigue on drivers’ faces to achieve fatigue detection. Optical and infrared (IR) sensors are used to analyse the monotony in driving environment and to detect the visual symptoms of fatigue on human face. Internal cues from drivers faces and external cues from environment are combined together using machine learning algorithms to automatically detect fatigue.

Keywords: intelligent transportation systems, bayesian networks, yawning computing, machine learning algorithms

Procedia PDF Downloads 455

Authors: Ren Moses, Emmanuel Kidando, Eren Ozguven, Yassir Abdelrazig

Abstract:

This study applied traffic speed and occupancy to develop clustering models that identify different traffic conditions. Particularly, these models are based on the Dirichlet Process Mixture of Generalized Linear regression (DML) and change-point regression (CR). The model frameworks were implemented using 2015 historical traffic data aggregated at a 15-minute interval from an Interstate 295 freeway in Jacksonville, Florida. Using the deviance information criterion (DIC) to identify the appropriate number of mixture components, three traffic states were identified as free-flow, transitional, and congested condition. Results of the DML revealed that traffic occupancy is statistically significant in influencing the reduction of traffic speed in each of the identified states. Influence on the free-flow and the congested state was estimated to be higher than the transitional flow condition in both evening and morning peak periods. Estimation of the critical speed threshold using CR revealed that 47 mph and 48 mph are speed thresholds for congested and transitional traffic condition during the morning peak hours and evening peak hours, respectively. Free-flow speed thresholds for morning and evening peak hours were estimated at 64 mph and 66 mph, respectively. The proposed approaches will facilitate accurate detection and prediction of traffic congestion for developing effective countermeasures.

Keywords: traffic congestion, multistate speed distribution, traffic occupancy, Dirichlet process mixtures of generalized linear model, Bayesian change-point detection

Procedia PDF Downloads 294

Authors: Ozgu Hafizoglu

Abstract:

Analogy is an essential tool of human cognition that enables connecting diffuse and diverse systems with attributional, deep structural, casual relations that are essential to learning, to innovation in artificial worlds, and to discovery in science. Cognitive Model of Analogy (CMA) leads and creates information pattern transfer within and between domains and disciplines in science. This paper demonstrates the Cognitive Model of Analogy (CMA) as an evolutionary approach to scientific research. The model puts forward the challenges of deep uncertainty about the future, emphasizing the need for flexibility of the system in order to enable reasoning methodology to adapt to changing conditions. In this paper, the model of analogical reasoning is created based on brain cells, their fractal, and operational forms within the system itself. Visualization techniques are used to show correspondences. Distinct phases of the problem-solving processes are divided thusly: encoding, mapping, inference, and response. The system is revealed relevant to brain activation considering each of these phases with an emphasis on achieving a better visualization of the brain cells: glial cells, axons, axon terminals, and neurons, relative to matching conditions of analogical reasoning and relational information. It’s found that encoding, mapping, inference, and response processes in four-term analogical reasoning are corresponding with the fractal and operational forms of brain cells: glial, axons, and neurons.

Keywords: analogy, analogical reasoning, cognitive model, brain and glials

Procedia PDF Downloads 185

Authors: Vivek Vaishnav, Shamim Akhtar Ansari

Abstract:

Teak (Tectona grandis L.f.) belonging to plant family Lamiaceae and the most commercialized timber species is endemic to South-Asia. The adaptive fitness of the species metapopulation was evaluated through its genetic differentiation and assessing the influence of geo-climatic conditions. 290 genotypes were sampled from 29 locations of its natural distribution and the genetic data was incorporated with geo-climatic parameters. Through Bayesian approach based analysis of 43 highly polymorphic ISSR markers, six homogeneous clusters (0.8% genetic variability) were identified. The six clusters were found with the various regimes of the temperature range, i.e., I - 9.10±1.35⁰C, II -6.35±0.21⁰C, III -12.21±0.43⁰C, IV - 10.8±1.06⁰C, V - 11.67±3.04⁰C, and VI - 12.35±0.21⁰C. The population had a very high percentage of LD (21.48%) among the amplified loci possibly due to experiencing restricted gene flow as well as co-adaptation and association of distant/diverse loci/alleles as a result of the stabilized climatic conditions and countless cycles of historical recombination events on a large geological timescale. The same possibly accounts for the narrow distribution of teak as a climax species in the tropical deciduous forests of the country. The regions of strong LD in teak genome significantly associated with climatic parameters also reflect that the species is tolerant to the wide regimes of the temperature range and may possibly withstand global warming and climate change in the coming millennium.

Keywords: Bayesian analysis, inter simple sequence repeat, linkage disequilibrium, marker-geoclimatic association

Procedia PDF Downloads 263

Authors: Yichao Liu, Peter Fransson, Julian Heidecke, Jonas Wallin, Joacim Rockloev

Abstract:

Dengue, a mosquito-borne viral disease, poses a significant public health challenge in endemic tropical or subtropical countries, including Sri Lanka. To reveal insights into the complexity of the dynamics of this disease and study the drivers, a comprehensive model capable of both robust forecasting and insightful inference of drivers while capturing the co-circulating of several virus strains is essential. However, existing studies mostly focus on only one aspect at a time and do not integrate and carry insights across the siloed approach. While mechanistic models are developed to capture immunity dynamics, they are often oversimplified and lack integration of all the diverse drivers of disease transmission. On the other hand, purely data-driven methods lack constraints imposed by immuno-epidemiological processes, making them prone to overfitting and inference bias. This research presents a hybrid model that combines machine learning techniques with mechanistic modelling to overcome the limitations of existing approaches. Leveraging eight years of newly reported dengue case data, along with socioeconomic factors, such as human mobility, weekly climate data from 2011 to 2018, genetic data detecting the introduction and presence of new strains, and estimates of seropositivity for different districts in Sri Lanka, we derive a data-driven vector (SEI) to human (SEIR) model across 16 regions in Sri Lanka at the weekly time scale. By conducting ablation studies, the lag effects allowing delays up to 12 weeks of time-varying climate factors were determined. The model demonstrates superior predictive performance over a pure machine learning approach when considering lead times of 5 and 10 weeks on data withheld from model fitting. It further reveals several interesting interpretable findings of drivers while adjusting for the dynamics and influences of immunity and introduction of a new strain. The study uncovers strong influences of socioeconomic variables: population density, mobility, household income and rural vs. urban population. The study reveals substantial sensitivity to the diurnal temperature range and precipitation, while mean temperature and humidity appear less important in the study location. Additionally, the model indicated sensitivity to vegetation index, both max and average. Predictions on testing data reveal high model accuracy. Overall, this study advances the knowledge of dengue transmission in Sri Lanka and demonstrates the importance of incorporating hybrid modelling techniques to use biologically informed model structures with flexible data-driven estimates of model parameters. The findings show the potential to both inference of drivers in situations of complex disease dynamics and robust forecasting models.

Keywords: compartmental model, climate, dengue, machine learning, social-economic

Procedia PDF Downloads 84

Authors: Tayo P. Ogundunmade, Adedayo A. Adepoju

Abstract:

Terrorist attacks in liberal democracies bring about a few pessimistic results, for example, sabotaged public support in the governments they target, disturbing the peace of a protected environment underwritten by the state, and a limitation of individuals from adding to the advancement of the country, among others. Hence, seeking for techniques to understand the different factors involved in terrorism and how to deal with those factors in order to completely stop or reduce terrorist activities is the topmost priority of the government in every country. This research aim is to develop an efficient deep learning-based predictive model for the prediction of future terrorist activities in Nigeria, addressing low-quality prediction accuracy problems associated with the existing solution methods. The proposed predictive AI-based model as a counterterrorism tool will be useful by governments and law enforcement agencies to protect the lives of individuals in society and to improve the quality of life in general. A Heterogeneous Bayesian Neural Network (HETBNN) model was derived with Gaussian error normal distribution. Three primary transfer functions (HOTTFs), as well as two derived transfer functions (HETTFs) arising from the convolution of the HOTTFs, are namely; Symmetric Saturated Linear transfer function (SATLINS ), Hyperbolic Tangent transfer function (TANH), Hyperbolic Tangent sigmoid transfer function (TANSIG), Symmetric Saturated Linear and Hyperbolic Tangent transfer function (SATLINS-TANH) and Symmetric Saturated Linear and Hyperbolic Tangent Sigmoid transfer function (SATLINS-TANSIG). Data on the Terrorist activities in Nigeria gathered through questionnaires for the purpose of this study were used. Mean Square Error (MSE), Mean Absolute Error (MAE) and Test Error are the forecast prediction criteria. The results showed that the HETFs performed better in terms of prediction and factors associated with terrorist activities in Nigeria were determined. The proposed predictive deep learning-based model will be useful to governments and law enforcement agencies as an effective counterterrorism mechanism to understand the parameters of terrorism and to design strategies to deal with terrorism before an incident actually happens and potentially causes the loss of precious lives. The proposed predictive AI-based model will reduce the chances of terrorist activities and is particularly helpful for security agencies to predict future terrorist activities.

Keywords: activation functions, Bayesian neural network, mean square error, test error, terrorism

Procedia PDF Downloads 165

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

With the widespread popularity of mobile devices and the development of artificial intelligence (AI), deep learning (DL) has been extensively applied in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace; a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Moreover, using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. We conducted an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace has a more robust performance than FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: mobile computing, deep learning apps, sensitive information, static analysis

Procedia PDF Downloads 177

Authors: Demet Ozgur-Unluakin, Busenur Turkali, Ayse Karacaorenli

Abstract:

Maintenance strategies can be classified into two types, which are reactive and proactive, with respect to the time of the failure and maintenance. If the maintenance activity is done after a breakdown, it is called reactive maintenance. On the other hand, proactive maintenance, which is further divided as preventive and predictive, focuses on maintaining components before a failure occurs to prevent expensive halts. Recently, the number of interacting components in a system has increased rapidly and therefore, the structure of the systems have become more complex. This situation has made it difficult to provide the right maintenance decisions. Herewith, determining effective decisions has played a significant role. In multi-component systems, many methodologies and strategies can be applied when a component or a system has already broken down or when it is desired to identify and avoid proactively defects that could lead to future failure. This study focuses on the comparison of various maintenance strategies on a multi-component dynamic system. Components in the system are hidden, although there exists partial observability to the decision maker and they deteriorate in time. Several predefined policies under corrective, preventive and predictive maintenance strategies are considered to minimize the total maintenance cost in a planning horizon. The policies are simulated via Dynamic Bayesian Networks on a multi-component system with different policy parameters and cost scenarios, and their performances are evaluated. Results show that when the difference between the corrective and proactive maintenance cost is low, none of the proactive maintenance policies is significantly better than the corrective maintenance. However, when the difference is increased, at least one policy parameter for each proactive maintenance strategy gives significantly lower cost than the corrective maintenance.

Keywords: decision making, dynamic Bayesian networks, maintenance, multi-component systems, reliability

Procedia PDF Downloads 129

Authors: Ahmad Rabby

Abstract:

The demographic trend analyses of Bombay-duck from time series catch data using CMSY and BSM for the first time in Bangladesh. During 2000-2018, CMSY indicates average lowest production in 2000 and highest in 2018. This has been used in the estimation of prior biomass by the default rules. Possible 31030 viable trajectories for 3422 r-k pairs were found by the CMSY analysis and the final estimates for intrinsic rate of population increase (r) was 1.19 year-1 with 95% CL= 0.957-1.48 year-1. The carrying capacity(k) of Bombay-duck was 283×103 tons with 95% CL=173×103 - 464×103 tons and MSY was 84.3×103tons year-1, 95% CL=49.1×103-145×103 tons year-1. Results from Bayesian state-space implementation of the Schaefer production model (BSM) using catch & CPUE data, found catchabilitiy coefficient(q) was 1.63 ×10-6 from lcl=1.27×10-6 to ucl=2.10×10-6 and r= 1.06 year-1 with 95% CL= 0.727 - 1.55 year-1, k was 226×103 tons with 95% CL=170×103-301×103 tons and MSY was 60×103 tons year-1 with 95% CL=49.9 ×103- 72.2 ×103 tons year-1. Results for Bombay-duck fishery management based on BSM assessment from time series catch data illustrated that, Fmsy=0.531 with 95% CL =0.364 - 0.775 (if B > 1/2 Bmsy then Fmsy =0.5r); Fmsy=0.531 with 95% CL =0.364-0.775 (r and Fmsy are linearly reduced if B < 1/2Bmsy). Biomass in 2018 was 110×103 tons with 2.5th to 97.5th percentile=82.3-155×103 tons. Relative biomass (B/Bmsy) in last year was 0.972 from 2.5th percentile to 97.5th percentile=0.728 -1.37. Fishing mortality in last year was 0.738 with 2.5th-97.5th percentile=0.525-1.37. Exploitation F/Fmsy was 1.39, from 2.5th to 97.5th percentile it was 0.988 -1.86. The biological reference points of B/BMSY was smaller than 1.0, while F/FMSY was higher than 1.0 revealed an over-exploitation of the fishery, indicating that more conservative management strategies are required for Bombay-duck fishery.

Keywords: biological reference points, catchability coefficient, carrying capacity, intrinsic rate of population increase

Procedia PDF Downloads 124

Authors: F. Ghazalnaz Sharifonnasabi, Iman Makhdoom

Abstract:

Breast cancer is a serious health concern that affects many people around the world. According to a study published in the Breast journal, the global burden of breast cancer is expected to increase significantly over the next few decades. The number of deaths from breast cancer has been increasing over the years, but the age-standardized mortality rate has decreased in some countries. It’s important to be aware of the risk factors for breast cancer and to get regular check- ups to catch it early if it does occur. Machin learning techniques have been used to aid in the early detection and diagnosis of breast cancer. These techniques, that have been shown to be effective in predicting and diagnosing the disease, have become a research hotspot. In this study, we consider two deep learning approaches including: Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). We also considered the five-machine learning algorithm titled: Decision Tree (C4.5), Naïve Bayesian (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) Algorithm and XGBoost (eXtreme Gradient Boosting) on the Breast Cancer Wisconsin Diagnostic dataset. We have carried out the process of evaluating and comparing classifiers involving selecting appropriate metrics to evaluate classifier performance and selecting an appropriate tool to quantify this performance. The main purpose of the study is predicting and diagnosis breast cancer, applying the mentioned algorithms and also discovering of the most effective with respect to confusion matrix, accuracy and precision. It is realized that CNN outperformed all other classifiers and achieved the highest accuracy (0.982456). The work is implemented in the Anaconda environment based on Python programing language.

Keywords: breast cancer, multi-layer perceptron, Naïve Bayesian, SVM, decision tree, convolutional neural network, XGBoost, KNN

Procedia PDF Downloads 75

Authors: Diana F. Lopes, Jorge Simoes, José Martins, Eduardo Castro

Abstract:

Health professionals are the keystone of any health system, by delivering health services to the population. Given the time and cost involved in training new health professionals, the planning process of the health workforce is particularly important as it ensures a proper balance between the supply and demand of these professionals and it plays a central role on the Health 2020 policy. In the past 40 years, the planning of the health workforce in Portugal has been conducted in a reactive way lacking a prospective vision based on an integrated, comprehensive and valid analysis. This situation may compromise not only the productivity and the overall socio-economic development but the quality of the healthcare services delivered to patients. This is even more critical given the expected shortage of the health workforce in the future. Furthermore, Portugal is facing an aging context of some professional classes (physicians and nurses). In 2015, 54% of physicians in Portugal were over 50 years old, and 30% of all members were over 60 years old. This phenomenon associated to an increasing emigration of young health professionals and a change in the citizens’ illness profiles and expectations must be considered when planning resources in healthcare. The perspective of sudden retirement of large groups of professionals in a short time is also a major problem to address. Another challenge to embrace is the health workforce imbalances, in which Portugal has one of the lowest nurse to physician ratio, 1.5, below the European Region and the OECD averages (2.2 and 2.8, respectively). Within the scope of the HEALTH 2040 project – which aims to estimate the ‘Future needs of human health resources in Portugal till 2040’ – the present study intends to get a comprehensive dynamic approach of the problem, by (i) estimating the needs of physicians and nurses in Portugal, by specialties and by quinquenium till 2040; (ii) identifying the training needs of physicians and nurses, in medium and long term, till 2040, and (iii) estimating the number of students that must be admitted into medicine and nursing training systems, each year, considering the different categories of specialties. The development of such approach is significantly more critical in the context of limited budget resources and changing health care needs. In this context, this study presents the drivers of the healthcare needs’ evolution (such as the demographic and technological evolution, the future expectations of the users of the health systems) and it proposes a Bayesian methodology, combining the best available data with experts opinion, to model such evolution. Preliminary results considering different plausible scenarios are presented. The proposed methodology will be integrated in a user-friendly decision support system so it can be used by politicians, with the potential to measure the impact of health policies, both at the regional and the national level.

Keywords: bayesian estimation, health economics, health workforce planning, human health resources planning

Procedia PDF Downloads 252

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 152

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: deep neural models, natural language inference, recognizing textual entailment (RTE), sentence-to-sentence relation

Procedia PDF Downloads 348

Authors: Niroshan K. Walgama Wellalage, Tieling Zhang, Richard Dwight

Abstract:

State-based Markov deterioration models (SMDM) sometimes fail to find accurate transition probability matrix (TPM) values, and hence lead to invalid future condition prediction or incorrect average deterioration rates mainly due to drawbacks of existing nonlinear optimization-based algorithms and/or subjective function types used for regression analysis. Furthermore, a set of separate functions for each condition state with age cannot be directly derived by using Markov model for a given bridge element group, which however is of interest to industrial partners. This paper presents a new approach for generating Homogeneous SMDM model output, namely, the Modified Weibull approach, which consists of a set of appropriate functions to describe the percentage condition prediction of bridge elements in each state. These functions are combined with Bayesian approach and Metropolis Hasting Algorithm (MHA) based Markov Chain Monte Carlo (MCMC) simulation technique for quantifying the uncertainty in model parameter estimates. In this study, factors contributing to rail bridge deterioration were identified. The inspection data for 1,000 Australian railway bridges over 15 years were reviewed and filtered accordingly based on the real operational experience. Network level deterioration model for a typical bridge element group was developed using the proposed Modified Weibull approach. The condition state predictions obtained from this method were validated using statistical hypothesis tests with a test data set. Results show that the proposed model is able to not only predict the conditions in network-level accurately but also capture the model uncertainties with given confidence interval.

Keywords: bridge deterioration modelling, modified weibull approach, MCMC, metropolis-hasting algorithm, bayesian approach, Markov deterioration models

Procedia PDF Downloads 727

Authors: Hyeon-Kyo Lim, Hyunjung Kim, Kune-Woo Lee

Abstract:

Decommissioning process of nuclear facilities can be said to consist of a sequence of problem solving activities, partly because there may exist working environments contaminated by radiological exposure, and partly because there may also exist industrial hazards such as fire, explosions, toxic materials, and electrical and physical hazards. As for an individual hazard factor, risk assessment techniques are getting known to industrial workers with advance of safety technology, but the way how to integrate those results is not. Furthermore, there are few workers who experienced decommissioning operations a lot in the past. Therefore, not a few countries in the world have been trying to develop appropriate counter techniques in order to guarantee safety and efficiency of the process. In spite of that, there still exists neither domestic nor international standard since nuclear facilities are too diverse and unique. In the consequence, it is quite inevitable to imagine and assess the whole risk in the situation anticipated one by one. This paper aimed to find out an appropriate technique to integrate individual risk assessment results from the viewpoint of experts. Thus, on one hand the whole risk assessment activity for decommissioning operations was modeled as a sequence of individual risk assessment steps, and on the other, a hierarchical risk structure was developed. Then, risk assessment procedure that can elicit individual hazard factors one by one were introduced with reference to the standard operation procedure (SOP) and hierarchical task analysis (HTA). With an assumption of quantification and normalization of individual risks, a technique to estimate relative weight factors was tried by using the conventional Analytic Hierarchical Process (AHP) and its result was reviewed with reference to judgment of experts. Besides, taking the ambiguity of human judgment into consideration, debates based upon fuzzy inference was added with a mathematical case study.

Keywords: decommissioning, risk assessment, analytic hierarchical process (AHP), fuzzy inference

Procedia PDF Downloads 424

Authors: Amin Salighehdar, Ziwen Ye, Mingzhe Liu, Ionut Florescu, Alan F. Blumberg

Abstract:

Storm surge is an abnormal water level caused by a storm. Accurate prediction of a storm surge is a challenging problem. Researchers developed various ensemble modeling techniques to combine several individual forecasts to produce an overall presumably better forecast. There exist some simple ensemble modeling techniques in literature. For instance, Model Output Statistics (MOS), and running mean-bias removal are widely used techniques in storm surge prediction domain. However, these methods have some drawbacks. For instance, MOS is based on multiple linear regression and it needs a long period of training data. To overcome the shortcomings of these simple methods, researchers propose some advanced methods. For instance, ENSURF (Ensemble SURge Forecast) is a multi-model application for sea level forecast. This application creates a better forecast of sea level using a combination of several instances of the Bayesian Model Averaging (BMA). An ensemble dressing method is based on identifying best member forecast and using it for prediction. Our contribution in this paper can be summarized as follows. First, we investigate whether the ensemble models perform better than any single forecast. Therefore, we need to identify the single best forecast. We present a methodology based on a simple Bayesian selection method to select the best single forecast. Second, we present several new and simple ways to construct ensemble models. We use correlation and standard deviation as weights in combining different forecast models. Third, we use these ensembles and compare with several existing models in literature to forecast storm surge level. We then investigate whether developing a complex ensemble model is indeed needed. To achieve this goal, we use a simple average (one of the simplest and widely used ensemble model) as benchmark. Predicting the peak level of Surge during a storm as well as the precise time at which this peak level takes place is crucial, thus we develop a statistical platform to compare the performance of various ensemble methods. This statistical analysis is based on root mean square error of the ensemble forecast during the testing period and on the magnitude and timing of the forecasted peak surge compared to the actual time and peak. In this work, we analyze four hurricanes: hurricanes Irene and Lee in 2011, hurricane Sandy in 2012, and hurricane Joaquin in 2015. Since hurricane Irene developed at the end of August 2011 and hurricane Lee started just after Irene at the beginning of September 2011, in this study we consider them as a single contiguous hurricane event. The data set used for this study is generated by the New York Harbor Observing and Prediction System (NYHOPS). We find that even the simplest possible way of creating an ensemble produces results superior to any single forecast. We also show that the ensemble models we propose generally have better performance compared to the simple average ensemble technique.

Keywords: Bayesian learning, ensemble model, statistical analysis, storm surge prediction

Procedia PDF Downloads 309

Authors: Li Yin, Xiaoqin Wang

Abstract:

Background and purpose: Cancer diagnosis is part of a complex stochastic process, in which patients' personal and social characteristics influence the choice of diagnosing methods, diagnosing methods, in turn, influence the initial assessment of cancer stage, the initial assessment, in turn, influences the choice of treating methods, and treating methods in turn influence cancer outcomes such as cancer survival. To evaluate diagnosing methods, one needs to estimate and test the causal effect of a regime of cancer diagnosis and treatments. Recently, Wang and Yin (Annals of statistics, 2020) derived a new general formula, which expresses these causal effects in terms of the point effects of treatments in single-point causal inference. As a result, it is possible to estimate and test these causal effects via point effects. The purpose of the work is to estimate and test causal effects under various regimes of cancer diagnosis and treatments via point effects. Challenges and solutions: The cancer stage has influences from earlier diagnosis as well as on subsequent treatments. As a consequence, it is highly difficult to estimate and test the causal effects via standard parameters, that is, the conditional survival given all stationary covariates, diagnosing methods, cancer stage and prognosis factors, treating methods. Instead of standard parameters, we use the point effects of cancer diagnosis and treatments to estimate and test causal effects under various regimes of cancer diagnosis and treatments. We are able to use familiar methods in the framework of single-point causal inference to accomplish the task. Achievements: we have applied this method to stomach cancer survival from a clinical study in Sweden. We have studied causal effects under various regimes, including the optimal regime of diagnosis and treatments and the effect moderation of the causal effect by age and gender.

Keywords: cancer diagnosis, causal effect, point effect, G-formula, sequential causal effect

Procedia PDF Downloads 195

Authors: Nikolaos Papadimas, Joanna Bennett, Amir Sakhaei, Timothy Dodwell

Abstract:

Composite modeling of consolidation processes is playing an important role in the process and part design by indicating the formation of possible unwanted prior to expensive experimental iterative trial and development programs. Composite materials in their uncured state display complex constitutive behavior, which has received much academic interest, and this with different models proposed. Errors from modeling and statistical which arise from this fitting will propagate through any simulation in which the material model is used. A general hyperelastic polynomial representation was proposed, which can be readily implemented in various nonlinear finite element packages. In our case, FEniCS was chosen. The coefficients are assumed uncertain, and therefore the distribution of parameters learned using Markov Chain Monte Carlo (MCMC) methods. In engineering, the approach often followed is to select a single set of model parameters, which on average, best fits a set of experiments. There are good statistical reasons why this is not a rigorous approach to take. To overcome these challenges, A hierarchical Bayesian framework was proposed in which population distribution of model parameters is inferred from an ensemble of experiments tests. The resulting sampled distribution of hyperparameters is approximated using Maximum Entropy methods so that the distribution of samples can be readily sampled when embedded within a stochastic finite element simulation. The methodology is validated and demonstrated on a set of consolidation experiments of AS4/8852 with various stacking sequences. The resulting distributions are then applied to stochastic finite element simulations of the consolidation of curved parts, leading to a distribution of possible model outputs. With this, the paper, as far as the authors are aware, represents the first stochastic finite element implementation in composite process modelling.

Keywords: data-driven , material consolidation, stochastic finite elements, surrogate models

Procedia PDF Downloads 145

Authors: Shu-Yu Chung, Ying-Fang Wang, Shih-Min Wang

Abstract:

To conduct long-term exposure assessments are important for workers exposed to chemicals with chronic effects. However, it usually encounters with several constrains, including cost, workers' willingness, and interference to work practice, etc., leading to inadequate long-term exposure data in the real world. In this study, an integrated approach was developed for conducting long-term exposure assessment for welding workers in a shipbuilding factory. A laboratory study was conducted to yield the fume generation rates under various operating conditions. The results and the measured environmental conditions were applied to the near field/far field (NF/FF) model for predicting long term fume exposures via the Monte Carlo simulation. Then, the predicted long-term concentrations were used to determine the prior distribution in Bayesian decision analysis (BDA). Finally, the resultant posterior distributions were used to assess the long-term exposure and serve as basis for initiating control strategies for shipbuilding workers. Results show that the NF/FF model was a suitable for predicting the exposures of metal contents containing in welding fume. The resultant posterior distributions could effectively assess the long-term exposures of shipbuilding welders. Welders' long-term Fe, Mn and Pb exposures were found with high possibilities to exceed the action level indicating preventive measures should be taken for reducing welders' exposures immediately. Though the resultant posterior distribution can only be regarded as the best solution based on the currently available predicting and monitoring data, the proposed integrated approach can be regarded as a possible solution for conducting long term exposure assessment in the field.

Keywords: Bayesian decision analysis, exposure assessment, near field and far field model, shipbuilding industry, welding fume

Procedia PDF Downloads 140

Authors: Nigina Toktasynova, Sholpan Sagyndykova, Zhanat Kenzhebayeva, Maksat Kalimoldayev, Mariya Ishimova, Irbulat Utepbergenov

Abstract:

Any business needs a stable operation and continuous improvement, therefore it is necessary to constantly interact with the environment, to analyze the work of the enterprise in terms of employees, executives and consumers, as well as to correct any inconsistencies of certain types of processes and their aggregate. In the case of heat supply organizations, in addition to suppliers, local legislation must be considered which often is the main regulator of pricing of services. In this case, the process approach used to build a functional organizational structure in these types of businesses in Kazakhstan is a challenge not only in the implementation, but also in ways of analyzing the employee's salary. To solve these problems, we investigated the management system of heating enterprise, including strategic planning based on the balanced scorecard (BSC), quality management in accordance with the standards of the Quality Management System (QMS) ISO 9001 and analysis of the system based on expert judgment using fuzzy inference. To carry out our work we used the theory of fuzzy sets, the QMS in accordance with ISO 9001, BSC according to the method of Kaplan and Norton, method of construction of business processes according to the notation IDEF0, theory of modeling using Matlab software simulation tools and graphical programming LabVIEW. The results of the work are as follows: We determined possibilities of improving the management of heat-supply plant-based on QMS; after the justification and adaptation of software tool it has been used to automate a series of functions for the management and reduction of resources and for the maintenance of the system up to date; an application for the analysis of the QMS based on fuzzy inference has been created with novel organization of communication software with the application enabling the analysis of relevant data of enterprise management system.

Keywords: balanced scorecard, heat supply, quality management system, the theory of fuzzy sets

Procedia PDF Downloads 367

Authors: Demet Ozgur-Unluakin, Busenur Turkali, S. Caglar Aksezer

Abstract:

Since the age of industrialization, maintenance has always been a very crucial element for all kinds of factories and plants. With today’s increasingly developing technology, the system structure of such facilities has become more complicated, and even a small operational disruption may return huge losses in profits for the companies. In order to reduce these costs, effective maintenance planning is crucial, but at the same time, it is a difficult task because of the complexity of systems. The most important aspect of correct maintenance planning is to understand the structure of the system, not to ignore the dependencies among the components and as a result, to model the system correctly. In this way, it will be better to understand which component improves the system more when it is maintained. Undoubtedly, proactive maintenance at a scheduled time reduces costs because the scheduled maintenance prohibits high losses in profits. But the necessity of corrective maintenance, which directly affects the situation of the system and provides direct intervention when the system fails, should not be ignored. When a fault occurs in the system, if the problem is not solved immediately and proactive maintenance time is awaited, this may result in increased costs. This study proposes various maintenance methods with different efficiency measures under corrective maintenance strategy on a subsystem of a thermal power plant. To model the dependencies between the components, dynamic Bayesian Network approach is employed. The proposed maintenance methods aim to minimize the total maintenance cost in a planning horizon, as well as to find the most appropriate component to be attacked on, which improves the system reliability utmost. Performances of the methods are compared under corrective maintenance strategy. Furthermore, sensitivity analysis is also applied under different cost values. Results show that all fault effect methods perform better than the replacement effect methods and this conclusion is also valid under different downtime cost values.

Keywords: dynamic Bayesian networks, maintenance, multi-component systems, reliability

Procedia PDF Downloads 128

Authors: Yonas Shuke Kitawa

Abstract:

Background: Although malaria incidence has substantially fallen sharply over the past few years, the rate of decline varies by district, time, and malaria type. Despite this turn-down, malaria remains a major public health threat in various districts of Ethiopia. Consequently, the present study is aimed at developing a predictive model that helps to identify the spatio-temporal variation in malaria risk by multiple plasmodium species. Methods: We propose a multivariate spatio-temporal Bayesian model to obtain a more coherent picture of the temporally varying spatial variation in disease risk. The spatial autocorrelation in such a data set is typically modeled by a set of random effects that assign a conditional autoregressive prior distribution. However, the autocorrelation considered in such cases depends on a binary neighborhood matrix specified through the border-sharing rule. Over here, we propose a graph-based optimization algorithm for estimating the neighborhood matrix that merely represents the spatial correlation by exploring the areal units as the vertices of a graph and the neighbor relations as the series of edges. Furthermore, we used aggregated malaria count in southern Ethiopia from August 2013 to May 2019. Results: We recognized that precipitation, temperature, and humidity are positively associated with the malaria threat in the area. On the other hand, enhanced vegetation index, nighttime light (NTL), and distance from coastal areas are negatively associated. Moreover, nonlinear relationships were observed between malaria incidence and precipitation, temperature, and NTL. Additionally, lagged effects of temperature and humidity have a significant effect on malaria risk by either species. More elevated risk of P. falciparum was observed following the rainy season, and unstable transmission of P. vivax was observed in the area. Finally, P. vivax risks are less sensitive to environmental factors than those of P. falciparum. Conclusion: The improved inference was gained by employing the proposed approach in comparison to the commonly used border-sharing rule. Additionally, different covariates are identified, including delayed effects, and elevated risks of either of the cases were observed in districts found in the central and western regions. As malaria transmission operates in a spatially continuous manner, a spatially continuous model should be employed when it is computationally feasible.

Keywords: disease mapping, MSTCAR, graph-based optimization algorithm, P. falciparum, P. vivax, waiting matrix

Procedia PDF Downloads 77

Authors: Emna Hlel, Salma Jamousi, Abdelmajid Ben Hamadou

Abstract:

Every model for knowledge representation to model real-world applications must be able to cope with the effects of uncertain phenomena. One of main defects of classical ontology is its inability to represent and reason with uncertainty. To remedy this defect, we try to propose a method to construct probabilistic ontology for integrating uncertain information in an ontology modeling a set of basic publications DBLP (Digital Bibliography & Library Project) using a probabilistic model.

Keywords: classical ontology, probabilistic ontology, uncertainty, Bayesian network

Procedia PDF Downloads 347