Search results for: bayesian regularization

Authors: Deepshikha Shukla, C. H. Solanki, Mayank K. Desai

Abstract:

Amongst all the natural hazards, earthquakes have the potential for causing the greatest damages. Since the earthquake forces are random in nature and unpredictable, the quantification of the hazards becomes important in order to assess the hazards. The time and place of a future earthquake are both uncertain. Since earthquakes can neither be prevented nor be predicted, engineers have to design and construct in such a way, that the damage to life and property are minimized. Seismic hazard analysis plays an important role in earthquake design structures by providing a rational value of input parameter. In this paper, both mathematical, as well as computational methods adopted by researchers globally in the past five years, will be discussed. Some mathematical approaches involving the concepts of Poisson’s ratio, Convex Set Theory, Empirical Green’s Function, Bayesian probability estimation applied for seismic hazard and FOSM (first-order second-moment) algorithm methods will be discussed. Computational approaches and numerical model SSIFiBo developed in MATLAB to study dynamic soil-structure interaction problem is discussed in this paper. The GIS-based tool will also be discussed which is predominantly used in the assessment of seismic hazards.

Keywords: computational methods, MATLAB, seismic hazard, seismic measurements

Procedia PDF Downloads 309

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 17

Authors: Derssie Mebratu

Abstract:

As a large variety of micro services, web services, social graphic applications, and media applications are continuously developed, it is substantially vital to design and build a reliable, efficient, and faster memory tiering system. Despite limited design, implementation, and deployment in the last few years, several techniques are currently developed to improve a memory tiering system in a cloud. Some of these techniques are to develop an optimal scanning frequency; improve and track pages movement; identify pages that recently accessed; store pages across each tiering, and then identify pages as a hot, warm, and cold so that hot pages can store in the first tiering Dynamic Random Access Memory (DRAM) and warm pages store in the second tiering Compute Express Link(CXL) and cold pages store in the third tiering Non-Volatile Memory (NVM). Apart from the current proposal and implementation, we also develop a new technique based on a machine learning algorithm in that the throughput produced 25% improved performance compared to the performance produced by the baseline as well as the latency produced 95% improved performance compared to the performance produced by the baseline.

Keywords: machine learning, bayesian optimization, memory tiering, CXL, DRAM

Procedia PDF Downloads 69

Authors: Ailing Yang, Penghan Song, Aihua Cai

Abstract:

The nonlinear maneuvering target tracking problem is mainly a state estimation problem when the target motion model is uncertain. Traditional solutions include Kalman filtering based on Bayesian filtering framework and extended Kalman filtering. However, these methods need prior knowledge such as kinematics model and state system distribution, and their performance is poor in state estimation of nonprior complex dynamic systems. Therefore, in view of the problems existing in traditional algorithms, a convolution LSTM target state estimation (SAConvLSTM-SE) algorithm based on Self-Attention memory (SAM) is proposed to learn the historical motion state of the target and the error distribution information measured at the current time. The measured track point data of airborne radar are processed into data sets. After supervised training, the data-driven deep neural network based on SAConvLSTM can directly obtain the target state at the next moment. Through experiments on two different maneuvering targets, we find that the network has stronger robustness and better tracking accuracy than the existing tracking methods.

Keywords: maneuvering target, state estimation, Kalman filter, LSTM, self-attention

Procedia PDF Downloads 109

Authors: Benmansour Nassima, Benmansour Souheyla

Abstract:

The appropriate integration of reward processing and decision making provided by the environment is vital for behavioural success and individuals’ well being in everyday life. Functional neurological investigation has already provided an inclusive image on affective and emotional (motivational) processing in the healthy human brain and has recently focused its interest also on the assessment of brain function in anxious and depressed individuals. This article offers an overview on the theoretical approaches that relate emotion and decision-making, and spotlights investigation with anxious or depressed individuals to reveal how emotions can interfere with decision-making. This research aims at incorporating the emotional structure based on response and stimulation with a Bayesian approach to decision-making in terms of probability and value processing. It seeks to show how studies of individuals with emotional dysfunctions bear out that alterations of decision-making can be considered in terms of altered probability and value subtraction. The utmost objective is to critically determine if the probabilistic representation of belief affords could be a critical approach to scrutinize alterations in probability and value representation in subjective with anxiety and depression, and draw round the general implications of this approach.

Keywords: decision-making, motivation, alteration, reward processing, response selection

Procedia PDF Downloads 444

Authors: Xia Huo

Abstract:

The composition and metabolites of the gut microbiota can be altered by environmental pollutants. However, the effect of co-exposure to multiple pollutants on the human gut microbiota has not been sufficiently studied. In this study, gut microorganisms and their metabolites were compared between 33 children from Guiyu and 34 children from Haojiang. The exposure level was assessed by estimating the daily intake (EDI) of polybrominated diphenyl ethers (PBDEs), polychlorinated biphenyls (PCBs), 6PPD-quinone (6PPDQ), and metal(loid)s in dust. Significant correlations were found between the EDIs of 6PPDQ, BDE28, PCB52, Ni, Cu, and both the alpha diversity index and specific metabolites in single-element models. The study found that the Bayesian kernel machine regression (BKMR) model showed a negative correlation between the EDIs of five pollutants (6PPDQ, BDE28, PCB52, Ni, and Cu) and the Chao 1 index, particularly beyond the 55th percentile. Furthermore, the EDIs of these five pollutants were positively correlated with the levels of the metabolite 2,4-diaminobutyric acid while negatively correlated with the levels of d-erythro-sphingosine and d-threitol. Our research suggests that exposure to 6PPDQ, BDE28, PCB52, Ni, and Cu in kindergarten dust is associated with alterations in the gut microbiota and its metabolites. These alterations may be associated with neurodevelopmental abnormalities in children.

Keywords: gut microbiota, 6PPDQ, PBDEs, PCBs, metal(loid)s, BKMR

Procedia PDF Downloads 17

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 53

Authors: Jugal Bhandari, K. Hari Priya

Abstract:

The ECG signal provides important clinical information which could be used to pretend the diseases related to heart. Accordingly, delineation of ECG signal is an important task. Whereas delineation of P and T waves is a complex task. This paper deals with the Study of ECG signal and analysis of signal by means of Verilog Design of efficient filters and MATLAB tool effectively. It includes generation and simulation of ECG signal, by means of real time ECG data, ECG signal filtering and processing by analysis of different algorithms and techniques. In this paper, we design a basic particle filter which generates a dynamic model depending on the present and past input samples and then produces the desired output. Afterwards, the output will be processed by MATLAB to get the actual shape and accurate values of the ranges of P-wave and T-wave of ECG signal. In this paper, Questasim is a tool of mentor graphics which is being used for simulation and functional verification. The same design is again verified using Xilinx ISE which will be also used for synthesis, mapping and bit file generation. Xilinx FPGA board will be used for implementation of system. The final results of FPGA shall be verified with ChipScope Pro where the output data can be observed.

Keywords: ECG, MATLAB, Bayesian filtering, particle filter, Verilog hardware descriptive language

Procedia PDF Downloads 342

Authors: Danielle M. Barna, Kolbjørn Engeland, Thordis Thorarinsdottir, Chong-Yu Xu

Abstract:

Design flood values give estimates of flood magnitude within a given return period and are essential to making adaptive decisions around land use planning, infrastructure design, and disaster mitigation. Often design flood values are needed at locations with insufficient data. Additionally, in hydrologic applications where flood retention is important (e.g., floodplain management and reservoir design), design flood values are required at different flood durations. A statistical approach to this problem is a development of a regression model for extremes where some of the parameters are dependent on flood duration in addition to being covariate-dependent. In hydrology, this is called a regional flood-duration-frequency (regional-QDF) model. Typically, the underlying statistical distribution is chosen to be the Generalized Extreme Value (GEV) distribution. However, as the support of the GEV distribution depends on both its parameters and the range of the data, special care must be taken with the development of the regional model. In particular, we find that the GEV is problematic when developing a GAMLSS-type analysis due to the difficulty of proposing a link function that is independent of the unknown parameters and the observed data. We discuss these challenges in the context of developing a regional QDF model for Norway.

Keywords: design flood values, bayesian statistics, regression modeling of extremes, extreme value analysis, GEV

Procedia PDF Downloads 44

Authors: J. J. Vargas, N. Prieto, L. A. Toro

Abstract:

Control charts are commonly used to monitor processes involving either variable or attribute of quality characteristics and determining the control limits as a critical task for quality engineers to improve the processes. Nonetheless, in some applications it is necessary to include an estimation of efficiency. In this paper, the ability to define the efficiency of an industrial process was added to a control chart by means of incorporating a data envelopment analysis (DEA) approach. In depth, a Bayesian estimation was performed to calculate the posterior probability distribution of parameters as means and variance and covariance matrix. This technique allows to analyse the data set without the need of using the hypothetical large sample implied in the problem and to be treated as an approximation to the finite sample distribution. A rejection simulation method was carried out to generate random variables from the parameter functions. Each resulting vector was used by stochastic DEA model during several cycles for establishing the distribution of each efficiency measures for each DMU (decision making units). A control limit was calculated with model obtained and if a condition of a low level efficiency of DMU is presented, system efficiency is out of control. In the efficiency calculated a global optimum was reached, which ensures model reliability.

Keywords: data envelopment analysis, DEA, Multivariate control chart, rejection simulation method

Procedia PDF Downloads 352

Authors: Aakansha Gupta, Neha Vadnere, Tapasvi Soni, M. Anbarsi

Abstract:

Protein secondary structure prediction is one of the most important goals pursued by bioinformatics and theoretical chemistry; it is highly important in medicine and biotechnology. Some aspects of protein functions and genome analysis can be predicted by secondary structure prediction. This is used to help annotate sequences, classify proteins, identify domains, and recognize functional motifs. In this paper, we represent protein secondary structure as a mathematical model. To extract and predict the protein secondary structure from the primary structure, we require a set of parameters. Any constants appearing in the model are specified by these parameters, which also provide a mechanism for efficient and accurate use of data. To estimate these model parameters there are many algorithms out of which the most popular one is the EM algorithm or called the Expectation Maximization Algorithm. These model parameters are estimated with the use of protein datasets like RS126 by using the Bayesian Probabilistic method (data set being categorical). This paper can then be extended into comparing the efficiency of EM algorithm to the other algorithms for estimating the model parameters, which will in turn lead to an efficient component for the Protein Secondary Structure Prediction. Further this paper provides a scope to use these parameters for predicting secondary structure of proteins using machine learning techniques like neural networks and fuzzy logic. The ultimate objective will be to obtain greater accuracy better than the previously achieved.

Keywords: model parameters, expectation maximization algorithm, protein secondary structure prediction, bioinformatics

Procedia PDF Downloads 444

Authors: Dang Thuy Binh, Truong Thi Oanh, Le Phan Khanh Hung, Luong thi Tuong Vy

Abstract:

One of the greatest environmental challenges facing Asia is the management and conservation of the marine biodiversity threaten by fisheries overexploitation, pollution, habitat destruction, and climate change. To date, a few molecular taxonomical studies has been conducted on marine fauna in Vietnam. The purpose of this study was to clarify the phylogeny of economic and ecological reef fish species in Vietnam Reef fish species covering Labridae, Scaridae, Nemipteridae, Serranidae, Acanthuridae, Lutjanidae, Lethrinidae, Mullidae, Balistidae, Pseudochromidae, Pinguipedidae, Fistulariidae, Holocentridae, Synodontidae, and Pomacentridae representing 28 genera were collected from South and Center, Vietnam. Combine with Genbank sequences, a phylogenetic tree was constructed based on 16S gene of mitochondrial DNA using maximum parsimony, maximum likelihood, and Bayesian inference approaches. The phylogram showed the well-resolved clades at genus and family level. Perciformes is the major order of reef fish species in Vietnam. The monophyly of Perciformes is not strongly supported as it was clustered in the same clade with Tetraodontiformes syngnathiformes and Beryciformes. Continue sampling of commercial fish species and classification based on morphology and genetics to build DNA barcoding of fish species in Vietnam is really necessary.

Keywords: reef fish, 16s rDNA, Vietnam, phylogeny

Procedia PDF Downloads 409

Authors: Caglayan Hizal, Hasan Emre Demirci, Engin Aktas, Alper Sezer

Abstract:

Offshore wind turbines consist of a long slender tower with a heavy fixed mass on the top of the tower (nacelle), together with a heavy rotating mass (blades and hub). They are always subjected to environmental loads including wind and wave loads in their service life. This study presents a three-stage methodology for reliability-based condition assessment of offshore wind-turbines against the seismic, wave and wind induced effects considering the soil-structure interaction. In this context, failure criterions are considered as serviceability limits of a monopile supporting an Offshore Wind Turbine: (a) allowable horizontal displacement at pile head should not exceed 0.2 m, (b) rotations at pile head should not exceed 0.5°. A Bayesian system identification framework is adapted to the classical reliability analysis procedure. Using this framework, a reliability assessment can be directly implemented to the updated finite element model without performing time-consuming methods. For numerical verification, simulation data of the finite model of a real offshore wind-turbine structure is investigated using the three-stage methodology.

Keywords: Offshore wind turbines, SHM, reliability assessment, soil-structure interaction

Procedia PDF Downloads 504

Authors: Bel G Raggad

Abstract:

An e-Learning setting is a distributed computing environment where information resources can be connected to any public network. Public networks are very unsecure which can compromise the reliability of an e-Learning environment. This study is only concerned with the intrusion detection aspect of e-Learning security and how incident responses are planned. The literature reported great advances in intrusion detection system (ids) but neglected to study an important ids weakness: suspected events are detected but an intrusion is not determined because it is not defined in ids databases. We propose an incident response generator (DIRG) that produces incident responses when the working ids system suspects an event that does not correspond to a known intrusion. Data involved in intrusion detection when ample uncertainty is present is often not suitable to formal statistical models including Bayesian. We instead adopt Dempster and Shafer theory to process intrusion data for the unknown event. The DIRG engine transforms data into a belief structure using incident scenarios deduced by the security administrator. Belief values associated with various incident scenarios are then derived and evaluated to choose the most appropriate scenario for which an automatic incident response is generated. This article provides a numerical example demonstrating the working of the DIRG system.

Keywords: decision support system, distributed computing, e-Learning security, incident response, intrusion detection, security risk, statefull inspection

Procedia PDF Downloads 398

Authors: Faiz N. K. Yusufi, Aquil Ahmed, Jamal Ahmad

Abstract:

Diabetes in India is growing at an alarming rate and the complications caused by it need to be controlled. Coronary heart disease (CHD) is one of the complications that will be discussed for prediction in this study. India has the second most number of diabetes patients in the world. To the best of our knowledge, there is no CHD risk score for Indian type 2 diabetes patients. Any form of CHD has been taken as the event of interest. A sample of 750 was determined and randomly collected from the Rajiv Gandhi Centre for Diabetes and Endocrinology, J.N.M.C., A.M.U., Aligarh, India. Collected variables include patients data such as sex, age, height, weight, body mass index (BMI), blood sugar fasting (BSF), post prandial sugar (PP), glycosylated haemoglobin (HbA1c), diastolic blood pressure (DBP), systolic blood pressure (SBP), smoking, alcohol habits, total cholesterol (TC), triglycerides (TG), high density lipoprotein (HDL), low density lipoprotein (LDL), very low density lipoprotein (VLDL), physical activity, duration of diabetes, diet control, history of antihypertensive drug treatment, family history of diabetes, waist circumference, hip circumference, medications, central obesity and history of CHD. Predictive risk scores of CHD events are designed by cox proportional hazard regression. Model calibration and discrimination is assessed from Hosmer Lemeshow and area under receiver operating characteristic (ROC) curve. Overfitting and underfitting of the model is checked by applying regularization techniques and best method is selected between ridge, lasso and elastic net regression. Youden’s index is used to choose the optimal cut off point from the scores. Five year probability of CHD is predicted by both survival function and Markov chain two state model and the better technique is concluded. The risk scores for CHD developed can be calculated by doctors and patients for self-control of diabetes. Furthermore, the five-year probabilities can be implemented as well to forecast and maintain the condition of patients.

Keywords: coronary heart disease, cox proportional hazard regression, ROC curve, type 2 diabetes Mellitus

Procedia PDF Downloads 189

Authors: O. Abiodun Adeyinka, B. Adeyemo Adesesan

Abstract:

The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses wherein a set of assumptions and methods for a given data set will be made. It is therefore important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR were presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of Law. The estimate of LR is fundamentally a Bayesian concept and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE) for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR has different confidence intervals which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the LoR performed better than the KDE when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.

Keywords: confidence interval, handwriting, kernel density estimator, KDE, logistic regression LoR, repeatability, reproducibility

Procedia PDF Downloads 95

Authors: Ayadi Aya, Ghorbel Oussama, M. Obeid Abdulfattah, Abid Mohamed

Abstract:

Nowadays, many wireless sensor networks have been distributed in the real world to collect valuable raw sensed data. The challenge is to extract high-level knowledge from this huge amount of data. However, the identification of outliers can lead to the discovery of useful and meaningful knowledge. In the field of wireless sensor networks, an outlier is defined as a measurement that deviates from the normal behavior of sensed data. Many detection techniques of outliers in WSNs have been extensively studied in the past decade and have focused on classic based algorithms. These techniques identify outlier in the real transaction dataset. This survey aims at providing a structured and comprehensive overview of the existing researches on classification based outlier detection techniques as applicable to WSNs. Thus, we have identified key hypotheses, which are used by these approaches to differentiate between normal and outlier behavior. In addition, this paper tries to provide an easier and a succinct understanding of the classification based techniques. Furthermore, we identified the advantages and disadvantages of different classification based techniques and we presented a comparative guide with useful paradigms for promoting outliers detection research in various WSN applications and suggested further opportunities for future research.

Keywords: bayesian networks, classification-based approaches, KPCA, neural networks, one-class SVM, outlier detection, wireless sensor networks

Procedia PDF Downloads 468

Authors: Zehai Yu, Hui Zhu, Linglong Lin, Huawei Liang, Biao Yu, Weixin Huang

Abstract:

With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.

Keywords: curve fitting, lane-level road map, line recognition, multi-thresholding, two-stage clustering

Procedia PDF Downloads 107

Authors: Ofosuhene O. Apenteng, Noor Azina Ismail

Abstract:

Over the last several years, concern has developed over how to minimize the spread of HIV/AIDS epidemic in many countries. AIDS epidemic has tremendously stimulated the development of mathematical models of infectious diseases. The transmission dynamics of HIV infection that eventually developed AIDS has taken a pivotal role of much on building mathematical models. From the initial HIV and AIDS models introduced in the 80s, various improvements have been taken into account as how to model HIV/AIDS frameworks. In this paper, we present the impact of migration on the spread of HIV/AIDS. Epidemic model is considered by a system of nonlinear differential equations to supplement the statistical method approach. The model is calibrated using HIV incidence data from Malaysia between 1986 and 2011. Bayesian inference based on Markov Chain Monte Carlo is used to validate the model by fitting it to the data and to estimate the unknown parameters for the model. The results suggest that the migrants stay for a long time contributes to the spread of HIV. The model also indicates that susceptible individual becomes infected and moved to HIV compartment at a rate that is more significant than the removal rate from HIV compartment to AIDS compartment. The disease-free steady state is unstable since the basic reproduction number is 1.627309. This is a big concern and not a good indicator from the public heath point of view since the aim is to stabilize the epidemic at the disease equilibrium.

Keywords: epidemic model, HIV, MCMC, parameter estimation

Procedia PDF Downloads 568

Authors: V. Jamuna, A. K. Chakravarty, C. S. Patil, Vijay Kumar, M. A. Mir, Rakesh Kumar

Abstract:

Intense selection of buffaloes for milk production at organized herds of the country without giving due attention to fertility traits viz. pregnancy rate has lead to deterioration in their performances. Aim of study is to develop an optimum model for predicting pregnancy rate and to assess the level of pregnancy rate with respect to milk production Murrah buffaloes. Data pertaining to 1224 lactation records of Murrah buffaloes spread over a period 21 years were analyzed and it was observed that pregnancy rate depicted negative phenotypic association with lactation milk yield (-0.08 ± 0.04). For developing optimum model for pregnancy rate in Murrah buffaloes seven simple and multiple regression models were developed. Among the seven models, model II having only Service period as an independent reproduction variable, was found to be the best prediction model, based on the four statistical criterions (high coefficient of determination (R 2), low mean sum of squares due to error (MSSe), conceptual predictive (CP) value, and Bayesian information criterion (BIC). For standardizing the level of fertility with milk production, pregnancy rate was classified into seven classes with the increment of 10% in all parities, life time and their corresponding average pregnancy rate in relation to the average lactation milk yield (MY).It was observed that to achieve around 2000 kg MY which can be considered optimum for Indian Murrah buffaloes, level of pregnancy rate should be in between 30-50%.

Keywords: life time, pregnancy rate, production, service period, standardization

Procedia PDF Downloads 600

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: stacking, multi-layers, ensemble, multi-class

Procedia PDF Downloads 236

Authors: Faiz N. K. Yusufi, Aquil Ahmed, Jamal Ahmad

Abstract:

Predicting the risk of diabetic retinopathy (DR) in Indian type 2 diabetes patients is immensely necessary. India, being the second largest country after China in terms of a number of diabetic patients, to the best of our knowledge not a single risk score for complications has ever been investigated. Diabetic retinopathy is a serious complication and is the topmost reason for visual impairment across countries. Any type or form of DR has been taken as the event of interest, be it mild, back, grade I, II, III, and IV DR. A sample was determined and randomly collected from the Rajiv Gandhi Centre for Diabetes and Endocrinology, J.N.M.C., A.M.U., Aligarh, India. Collected variables include patients data such as sex, age, height, weight, body mass index (BMI), blood sugar fasting (BSF), post prandial sugar (PP), glycosylated haemoglobin (HbA1c), diastolic blood pressure (DBP), systolic blood pressure (SBP), smoking, alcohol habits, total cholesterol (TC), triglycerides (TG), high density lipoprotein (HDL), low density lipoprotein (LDL), very low density lipoprotein (VLDL), physical activity, duration of diabetes, diet control, history of antihypertensive drug treatment, family history of diabetes, waist circumference, hip circumference, medications, central obesity and history of DR. Cox proportional hazard regression is used to design risk scores for the prediction of retinopathy. Model calibration and discrimination are assessed from Hosmer Lemeshow and area under receiver operating characteristic curve (ROC). Overfitting and underfitting of the model are checked by applying regularization techniques and best method is selected between ridge, lasso and elastic net regression. Optimal cut off point is chosen by Youden’s index. Five-year probability of DR is predicted by both survival function, and Markov chain two state model and the better technique is concluded. The risk scores developed can be applied by doctors and patients themselves for self evaluation. Furthermore, the five-year probabilities can be applied as well to forecast and maintain the condition of patients. This provides immense benefit in real application of DR prediction in T2DM.

Keywords: Cox proportional hazard regression, diabetic retinopathy, ROC curve, type 2 diabetes mellitus

Procedia PDF Downloads 148

Authors: Mohamed Al-Badrashiny, Abdelghani Bellaachia

Abstract:

This paper presents a classifier ensemble approach for predicting the survivability of the breast cancer patients using the latest database version of the Surveillance, Epidemiology, and End Results (SEER) Program of the National Cancer Institute. The system consists of two main components; features selection and classifier ensemble components. The features selection component divides the features in SEER database into four groups. After that it tries to find the most important features among the four groups that maximizes the weighted average F-score of a certain classification algorithm. The ensemble component uses three different classifiers, each of which models different set of features from SEER through the features selection module. On top of them, another classifier is used to give the final decision based on the output decisions and confidence scores from each of the underlying classifiers. Different classification algorithms have been examined; the best setup found is by using the decision tree, Bayesian network, and Na¨ıve Bayes algorithms for the underlying classifiers and Na¨ıve Bayes for the classifier ensemble step. The system outperforms all published systems to date when evaluated against the exact same data of SEER (period of 1973-2002). It gives 87.39% weighted average F-score compared to 85.82% and 81.34% of the other published systems. By increasing the data size to cover the whole database (period of 1973-2014), the overall weighted average F-score jumps to 92.4% on the held out unseen test set.

Keywords: classifier ensemble, breast cancer survivability, data mining, SEER

Procedia PDF Downloads 295

Authors: Ghulam Haider Haidaree, Nsenda Lukumwena

Abstract:

Today the world of research enjoys abundant data, available in virtually any field, technology, science, and business, politics, etc. This is commonly referred to as big data. This offers a great deal of precision and accuracy, supportive of an in-depth look at any decision-making process. When and if well used, Big Data affords its users with the opportunity to produce substantially well supported and good results. This paper leans extensively on big data to investigate possible smart solutions to urban mobility and related issues, namely road traffic accidents, its casualties, and fatalities based on multiple factors, including age, gender, location occurrences of accidents, etc. Multiple technologies were used in combination to produce an Information Communication Technology (ICT) based solution with embedded technology. Those technologies include principally Geographic Information System (GIS), Orange Data Mining Software, Bayesian Statistics, to name a few. The study uses the Leeds accident 2016 to illustrate the thinking process and extracts thereof a model that can be tested, evaluated, and replicated. The authors optimistically believe that the proposed model will significantly and smartly help to flatten the curve of road traffic accidents in the fast-growing population densities, which increases considerably motor-based mobility.

Keywords: accident factors, geographic information system, information communication technology, mobility

Procedia PDF Downloads 172

Authors: Ofosuhene O. Apenteng, Noor Azina Ismail

Abstract:

The human immunodeficiency virus (HIV) that causes acquired immune deficiency syndrome (AIDS) remains a global cause of morbidity and mortality. It has caused panic since its emergence. Relationships between migration and HIV/AIDS have become complex. In the absence of prospectively designed studies, dynamic mathematical models that take into account the migration movement which will give very useful information. We have explored the utility of mathematical models in understanding transmission dynamics of HIV and AIDS and in assessing the magnitude of how migration has impact on the disease. The model was calibrated to HIV and AIDS incidence data from Malaysia Ministry of Health from the period of 1986 to 2011 using Bayesian analysis with combination of Markov chain Monte Carlo method (MCMC) approach to estimate the model parameters. From the estimated parameters, the estimated basic reproduction number was 22.5812. The rate at which the susceptible individual moved to HIV compartment has the highest sensitivity value which is more significant as compared to the remaining parameters. Thus, the disease becomes unstable. This is a big concern and not good indicator from the public health point of view since the aim is to stabilize the epidemic at the disease-free equilibrium. However, these results suggest that the government as a policy maker should make further efforts to curb illegal activities performed by migrants. It is shown that our models reflect considerably the dynamic behavior of the HIV/AIDS epidemic in Malaysia and eventually could be used strategically for other countries.

Keywords: epidemic model, reproduction number, HIV, MCMC, parameter estimation

Procedia PDF Downloads 339

Authors: Suriya

Abstract:

Rapid socio-economic development and urbanization have led to an increasingly serious air pollution problem in Ulaanbaatar (UB), the capital of Mongolia. PM₂.₅ pollution has become the most pressing aspect of UB air pollution. Therefore, monitoring and predicting PM₂.₅ concentration in UB is of great significance for the health of the local people and environmental management. As of yet, very few studies have used models to predict PM₂.₅ concentrations in UB. Using data from 0:00 on June 1, 2018, to 23:00 on April 30, 2020, we proposed two deep learning models based on Bayesian-optimized LSTM (Bayes-LSTM) and CNN-LSTM. We utilized hourly observed data, including Himawari8 (H8) aerosol optical depth (AOD), meteorology, and PM₂.₅ concentration, as input for the prediction of PM₂.₅ concentrations. The correlation strengths between meteorology, AOD, and PM₂.₅ were analyzed using the gray correlation analysis method; the comparison of the performance improvement of the model by using the AOD input value was tested, and the performance of these models was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The prediction accuracies of Bayes-LSTM and CNN-LSTM deep learning models were both improved when AOD was included as an input parameter. Improvement of the prediction accuracy of the CNN-LSTM model was particularly enhanced in the non-heating season; in the heating season, the prediction accuracy of the Bayes-LSTM model slightly improved, while the prediction accuracy of the CNN-LSTM model slightly decreased. We propose two novel deep learning models for PM₂.₅ concentration prediction in UB, Bayes-LSTM, and CNN-LSTM deep learning models. Pioneering the use of AOD data from H8 and demonstrating the inclusion of AOD input data improves the performance of our two proposed deep learning models.

Keywords: deep learning, AOD, PM2.5, prediction, Ulaanbaatar

Procedia PDF Downloads 17

Authors: Guldana Zhigerbayeva, Ming Yang

Abstract:

Transportation of hazardous materials (HAZMAT) is inevitable in the process industries. The statistics show a significant number of accidents has occurred during the transportation of HAZMAT. This makes risk management of HAZMAT transportation an important topic. The tree-based methods including fault-trees, event-trees and cause-consequence analysis, and Bayesian network, have been applied to risk management of HAZMAT transportation. However, there is limited work on the development of a systematic approach. The existing approaches fail to build up the linkages between the regulatory requirements and the safety measures development. The analysis of historical data from the past accidents’ report databases would limit our focus on the specific incidents and their specific causes. Thus, we may overlook some essential elements in risk management, including regulatory compliance, field expert opinions, and suggestions. A systematic approach is needed to translate the regulatory requirements of HAZMAT transportation into specified safety measures (both technical and administrative) to support the risk management process. This study aims to first adapt the House of Quality (HoQ) to House of Safety (HoS) and proposes a new approach- Safety Function Deployment (SFD). The results of SFD will be used in a multi-criteria decision-support system to develop find an optimal route for HazMats transportation. The proposed approach will be demonstrated through a hypothetical transportation case in Kazakhstan.

Keywords: hazardous materials, risk assessment, risk management, quality function deployment

Procedia PDF Downloads 110

Authors: Roman Graf, Sergiu Gordea, Heather M. Ryan

Abstract:

This paper presents an approach for the classification of an unstructured format description for identification of file formats. The main contribution of this work is the employment of data mining techniques to support file format selection with just the unstructured text description that comprises the most important format features for a particular organisation. Subsequently, the file format indentification method employs file format classifier and associated configurations to support digital preservation experts with an estimation of required file format. Our goal is to make use of a format specification knowledge base aggregated from a different Web sources in order to select file format for a particular institution. Using the naive Bayes method, the decision support system recommends to an expert, the file format for his institution. The proposed methods facilitate the selection of file format and the quality of a digital preservation process. The presented approach is meant to facilitate decision making for the preservation of digital content in libraries and archives using domain expert knowledge and specifications of file formats. To facilitate decision-making, the aggregated information about the file formats is presented as a file format vocabulary that comprises most common terms that are characteristic for all researched formats. The goal is to suggest a particular file format based on this vocabulary for analysis by an expert. The sample file format calculation and the calculation results including probabilities are presented in the evaluation section.

Keywords: data mining, digital libraries, digital preservation, file format

Procedia PDF Downloads 472

Authors: Anthony Townsend, Robyn Fasser

Abstract:

While complete objectivity is a desirable scientific position from which to conduct a care and contact evaluation (CCE), it is precisely the recognition that we are inherently incapable of operating objectively that is the foundation of ethical practice and skilled assessment. Drawing upon recent research from Daniel Kahneman (2021) on the differences between noise and bias, as well as different inherent biases collectively termed “The Elephant in the Brain” by Kevin Simler and Robin Hanson (2019) from Oxford University, this presentation addresses both the various ways in which our judgments, perceptions and even procedures can be distorted and contaminated while conducting a CCE, but also considers the value of second order cybernetics and the psychodynamic concept of ‘ambivalence’ as a conceptual basis to inform our assessment methodologies to limit such errors or at least better identify them. Both a conceptual framework for ambivalence, our higher-order capacity to allow for the convergence and consideration of multiple emotional experiences and cognitive perceptions to inform our reasoning, and a practical methodology for assessment relying on data triangulation, Bayesian inference and hypothesis testing is presented as a means of promoting ethical practice for health care professionals conducting CCEs. An emphasis on widening awareness and perspective, limiting ‘splitting’, is demonstrated both in how this form of emotional processing plays out in alienating dynamics in families as well as the assessment thereof. In addressing this concept, this presentation aims to illuminate the value of ambivalence as foundational to ethical practice for assessors.

Keywords: ambivalence, forensic, psychology, noise, bias, ethics

Procedia PDF Downloads 63

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 110