Search results for: hierarchical structure model

Authors: M. C. Padma, R. J. Prathibha

Abstract:

Parts of speech tagging is the process of assigning appropriate parts of speech tags to the words in a given text. The critical or crucial information needed for tagging a word come from its internal structure rather from its neighboring words. The internal structure of a word comprises of its morphological features and grammatical information. This paper presents a morpheme based parts of speech tagger for Kannada language. This proposed work uses hierarchical tag set for assigning tags. The system is tested on some Kannada words taken from EMILLE corpus. Experimental result shows that the performance of the proposed system is above 90%.

Keywords: hierarchical tag set, morphological analyzer, natural language processing, paradigms, parts of speech

Procedia PDF Downloads 263

Authors: M. Lesage, G. Raîche, M. Riopel, F. Fortin, D. Sebkhi

Abstract:

This paper describes a Web server implementation of the hierarchical aggregate assessment process in the field of education. This process describes itself as a field of teamwork assessment where teams can have multiple levels of hierarchy and supervision. This process is applied everywhere and is part of the management, education, assessment and computer science fields. The E-Assessment website named “Cluster” records in its database the students, the course material, the teams and the hierarchical relationships between the students. For the present research, the hierarchical relationships are team member, team leader and group administrator appointments. The group administrators have the responsibility to supervise team leaders. The experimentation of the application has been performed by high school students in geology courses and Canadian army cadets for navigation patrols in teams. This research extends the work of Nance that uses a hierarchical aggregation process similar as the one implemented in the “Cluster” application.

Keywords: e-learning, e-assessment, teamwork assessment, hierarchical aggregate assessment

Procedia PDF Downloads 344

Authors: Ali Hesari, Arezoo Esmaeeli

Abstract:

Regarding to dramatic changes of fertility and higher order births during recent decades in Iran, access to knowledge about affecting factors on different birth orders has crucial importance. In this study, According to hierarchical structure of many of social sciences data and the effect of variables of different levels of social phenomena that determine different birth orders in 365 days ending to 1390 census have been explored by multilevel approach. In this paper, 2% individual row data for 1390 census is analyzed by HLM software. Three different hierarchical linear regression models are estimated for data analysis of the first and second, third, fourth and more birth order. Research results displays different outcomes for three models. Individual level variables entered in equation are; region of residence (rural/urban), age, educational level and labor participation status and province level variable is GDP per capita. Results show that individual level variables have different effects in these three models and in second level we have different random and fixed effects in these models.

Keywords: fertility, birth order, hierarchical approach, fixe effects, random effects

Procedia PDF Downloads 316

Authors: Ashley Wei-Ting Wang, Wen-Yau Hsu

Abstract:

Objectives: The current study applies and expands the Tripartite Model to elaborate the link between non-suicidal self-injury (NSSI) and suicidal behavior. We propose a structural model of NSSI and suicidal risk, in which negative affect (NA) predicts both anxiety and depression, positive affect (PA) predicts depression only, anxiety is linked to NSSI, and depression is linked to suicidal risk. Method: Four hundreds and eighty seven undergraduates participated. Data were collected by administering self-report questionnaires. We performed hierarchical regression and structural equation modeling to test the proposed structural model. Results: The results largely support the proposed structural model, with one exception: anxiety was strongly associated with NSSI and to a lesser extent with suicidal risk. Conclusions: We conclude that the co-occurrence of NSSI and suicidal risk is due to NA and anxiety, and suicidal risk can be differentiated by depression. Further theoretical and practical implications are discussed.

Keywords: non-suicidal self-injury, suicidal risk, anxiety, depression, the tripartite model, hierarchical relationship

Procedia PDF Downloads 441

Authors: K. Umbleja, M. Ichino, H. Yaguchi

Abstract:

In this paper, we propose a coloring method for multivariate data visualization by using parallel coordinates based on dissimilarity and tree structure information gathered during hierarchical clustering. The proposed method is an extension for proximity-based coloring that suffers from a few undesired side effects if hierarchical tree structure is not balanced tree. We describe the algorithm by assigning colors based on dissimilarity information, show the application of proposed method on three commonly used datasets, and compare the results with proximity-based coloring. We found our proposed method to be especially beneficial for symbolic data visualization where many individual objects have already been aggregated into a single symbolic object.

Keywords: data visualization, dissimilarity-based coloring, proximity-based coloring, symbolic data

Procedia PDF Downloads 138

Authors: Vani Singhal, Jitendra Parmar, Satyendra Singh Chouhan

Abstract:

Unseen class discovery has now become an important part of a machine-learning algorithm to judge new classes. Unseen classes are the classes on which the machine learning model is not trained on. With the advancement in technology and AI replacing humans, the amount of data has increased to the next level. So while implementing a model on real-world examples, we come across unseen new classes. Our aim is to find the number of unseen classes by using a hierarchical-based active learning algorithm. The algorithm is based on hierarchical clustering as well as active sampling. The number of clusters that we will get in the end will give the number of unseen classes. The total clusters will also contain some clusters that have unseen classes. Instead of first discovering unseen classes and then finding their number, we directly calculated the number by applying the algorithm. The dataset used is for intent classification. The target data is the intent of the corresponding query. We conclude that when the machine learning model will encounter real-world data, it will automatically find the number of unseen classes. In the future, our next work would be to label these unseen classes correctly.

Keywords: active sampling, hierarchical clustering, open world learning, unseen class discovery

Procedia PDF Downloads 139

Authors: Lichung Jen, Yi Chun Liu, Kuan-Wei Lee

Abstract:

Fruitful data has been accumulated in database nowadays and is commonly used as support for decision-making. In the healthcare industry, hospital, for instance, ordering pharmacy inventory is one of the key decision. With large drug inventory, the current cost increases and its expiration dates might lead to future issue, such as drug disposal and recycle. In contrast, underestimating demand of the pharmacy inventory, particularly standing drugs, affects the medical treatment and possibly hospital reputation. Prescription behaviour of hospital physicians is one of the critical factor influencing this decision, particularly irregular prescription behaviour. If a drug’s usage amount in the month is irregular and less than the regular usage, it may cause the trend of subsequent stockpiling. On the contrary, if a drug has been prescribed often than expected, it may result in insufficient inventory. We proposed a hierarchical Bayesian mixture model with two components to identify physicians’ regular/irregular prescription patterns with probabilities. Heterogeneity of hospital is considered in our proposed hierarchical Bayes model. The result suggested that modeling the prescription patterns of physician is beneficial for estimating the order quantity of medication and pharmacy inventory management of the hospital. Managerial implication and future research are discussed.

Keywords: hierarchical Bayesian model, poission mixture model, medicines prescription behavior, irregular behavior

Procedia PDF Downloads 101

Authors: Salima Kouici, Abdelkader Khelladi

Abstract:

In this work, we begin with the presentation of the Tθ family of usual similarity measures concerning multidimensional binary data. Subsequently, some properties of these measures are proposed. Finally, the impact of the use of different inter-elements measures on the results of the Agglomerative Hierarchical Clustering Methods is studied.

Keywords: binary data, similarity measure, Tθ measures, agglomerative hierarchical clustering

Procedia PDF Downloads 445

Authors: Mirjana Ilic, Dragan Zivotic, Aleksandra Perovic, Predrag Gavrilovic

Abstract:

The service quality perception depends on many factors, such as the area in which the services are provided, socioeconomic status, educational status, experience, age and gender of consumers, as well as many others. For this reason, it is not possible to apply instrument for establishing the service quality perception that is developed in other areas and in other populations. The aim of the research was to form an instrument for assessing the quality perception in the field of fitness in Serbia. After analyzing the available literature and conducting a pilot research, there were 15 isolated areas in which it was possible to observe the service quality perception. The areas included: material and technical basis, secondary facilities, coaches, programs, reliability, credibility, security, rapid response, compassion, communication, prices, satisfaction, loyalty, quality outcomes and motives. These areas were covered by a questionnaire consisted of 100 items where the number of items varied from area to area from 3 up to 11. The questionnaire was administered to 350 subjects of both genders (174 men and 176 women) aged from 18 to 68 years, being beneficiaries of fitness services for at least 1 year. In each of the areas was conducted a factor analysis in its exploratory form by principal components method. The number of significant factors has been determined in accordance with the Kaiser Guttman criterion. The initial factor solutions were simplified using the Varimax rotation. Analyses per areas have produced from 1 to 4 factors. Afterward, the factor analysis of factor scores on the first principal component of each of the respondents in each of the analyzed area was performed, and the factor structure was obtained with four latent dimensions interpreted as offer, the relationship with the coaches, the experience of quality and the initial impression. This factor structure was analysed by hierarchical analysis of Oblique factors, which in the second order space produced single factor interpreted as a general factor of the service quality perception. The resulting questionnaire represents an instrument which can serve managers in the field of fitness to optimize the centers development, raising the quality of services in line with consumers needs and expectations.

Keywords: fitness, hierarchical model, quality perception, factor analysis

Procedia PDF Downloads 287

Authors: Luis Javier Serrano Tamayo

Abstract:

This research on technology makes a first approach to the selection of an amphibious landing ship with strategic capabilities, through the implementation of a multi-criteria model using Analytical Hierarchical Process (AHP), in which a significant group of alternatives of latest technology has been considered. The variables were grouped at different levels to match design and performance characteristics, which affect the lifecycle as well as the acquisition, maintenance and operational costs. The model yielded an overall measure of effectiveness and an overall measure of cost of each kind of ship that was compared each other inside the model and showed in a Pareto chart. The modeling was developed using the Expert Choice software, based on AHP method.

Keywords: analytic hierarchy process, multi-criteria decision-making, Pareto analysis, Colombian Marine Corps, projection operations, expert choice, amphibious landing ship

Procedia PDF Downloads 519

Authors: Amani Tahat, Serdal Kirmizialtin

Abstract:

Trajectory fragment methods such as Markov State Models (MSM), Milestoning (MS) and Transition Path sampling are the prime choice of extending the timescale of all atom Molecular Dynamics simulations. In these approaches, a set of structures that covers the accessible phase space has to be chosen a priori using cluster analysis. Structural clustering serves to partition the conformational state into natural subgroups based on their similarity, an essential statistical methodology that is used for analyzing numerous sets of empirical data produced by Molecular Dynamics (MD) simulations. Local transition kernel among these clusters later used to connect the metastable states using a Markovian kinetic model in MSM and a non-Markovian model in MS. The choice of clustering approach in constructing such kernel is crucial since the high dimensionality of the biomolecular structures might easily confuse the identification of clusters when using the traditional hierarchical clustering methodology. Of particular interest, in the case of MS where the milestones are very close to each other, accurate determination of the milestone identity of the trajectory becomes a challenging issue. Throughout this work we present two cluster analysis methods applied to the cis–trans isomerism of dinucleotide AA. The choice of nucleic acids to commonly used proteins to study the cluster analysis is two fold: i) the energy landscape is rugged; hence transitions are more complex, enabling a more realistic model to study conformational transitions, ii) Nucleic acids conformational space is high dimensional. A diverse set of internal coordinates is necessary to describe the metastable states in nucleic acids, posing a challenge in studying the conformational transitions. Herein, we need improved clustering methods that accurately identify the AA structure in its metastable states in a robust way for a wide range of confused data conditions. The single linkage approach of the hierarchical clustering available in GROMACS MD-package is the first clustering methodology applied to our data. Self Organizing Map (SOM) neural network, that also known as a Kohonen network, is the second data clustering methodology. The performance comparison of the neural network as well as hierarchical clustering method is studied by means of computing the mean first passage times for the cis-trans conformational rates. Our hope is that this study provides insight into the complexities and need in determining the appropriate clustering algorithm for kinetic analysis. Our results can improve the effectiveness of decisions based on clustering confused empirical data in studying conformational transitions in biomolecules.

Keywords: milestoning, self organizing map, single linkage, structure clustering

Procedia PDF Downloads 197

Authors: Ying Zhao, Xingyan Bin

Abstract:

Semi-supervised clustering algorithms have been shown effective to improve clustering process with even limited supervision. However, semi-supervised hierarchical clustering remains challenging due to the complexities of expressing constraints for agglomerative clustering algorithms. This paper proposes novel semi-supervised agglomerative clustering algorithms to build a hierarchy based on a known reference tree. We prove that by enforcing distance constraints defined by a reference tree during the process of hierarchical clustering, the resultant tree is guaranteed to be consistent with the reference tree. We also propose a framework that allows the hierarchical tree generation be aware of levels of levels of the agglomerative tree under creation, so that metric weights can be learned and adopted at each level in a recursive fashion. The experimental evaluation shows that the additional cost of our contraint-based semi-supervised hierarchical clustering algorithm (HAC) is negligible, and our combined semi-supervised HAC algorithm outperforms the state-of-the-art algorithms on real-world datasets. The experiments also show that our proposed methods can improve clustering performance even with a small number of unevenly distributed labeled data.

Keywords: semi-supervised clustering, hierarchical agglomerative clustering, reference trees, distance constraints

Procedia PDF Downloads 504

Authors: Kwaku Damoah

Abstract:

This paper presents a methodology and software application (App) designed to empower users in accessing, retrieving, and comparatively exploring data within the hierarchical network framework of the Government Finance Statistics (GFS) system. It explores the ease of navigating the GFS system and identifies the gaps filled by the new methodology and App. The GFS, embodies a complex Hierarchical Network Classification (HNC) structure, encapsulating institutional units, revenues, expenses, assets, liabilities, and economic activities. Navigating this structure demands specialized knowledge, experience, and skill, posing a significant challenge for effective analytics and fiscal policy decision-making. Many professionals encounter difficulties deciphering these classifications, hindering confident utilization of the system. This accessibility barrier obstructs a vast number of professionals, students, policymakers, and the public from leveraging the abundant data and information within the GFS. Leveraging R programming language, Data Science Analytics and Machine Learning, an efficient methodology enabling users to access, navigate, and conduct exploratory comparisons was developed. The machine learning Fiscal Analytics App (FLOWZZ) democratizes access to advanced analytics through its user-friendly interface, breaking down expertise barriers.

Keywords: data science, data wrangling, drilldown analytics, government finance statistics, hierarchical network classification, machine learning, web application.

Procedia PDF Downloads 32

Authors: Mingyu Xie, Mietek Brdys

Abstract:

The paper develops a non-linear model predictive control (NMPC) of water quality in drinking water distribution systems (DWDS) based on the advanced non-linear quality dynamics model including disinfections by-products (DBPs). A special attention is paid to the analysis of an impact of the flow trajectories prescribed by an upper control level of the recently developed two-time scale architecture of an integrated quality and quantity control in DWDS. The new quality controller is to operate within this architecture in the fast time scale as the lower level quality controller. The controller performance is validated by a comprehensive simulation study based on an example case study DWDS.

Keywords: model predictive control, hierarchical control structure, genetic algorithm, water quality with DBPs objectives

Procedia PDF Downloads 285

Authors: Katyana A. Vert-Pre, James T. Thorson, Thomas Trancart, Eric Feunteun

Abstract:

In marine ecosystems, spatial and temporal species structure is an important component of ecosystems’ response to anthropological and environmental factors. Although spatial distribution patterns and fish temporal series of abundance have been studied in the past, little research has been allocated to the joint dynamic spatio-temporal functional patterns in marine ecosystems and their use in multispecies management and conservation. Each species represents a function to the ecosystem, and the distribution of these species might not be random. A heterogeneous functional distribution will lead to a more resilient ecosystem to external factors. Applying a Vector-Autoregressive Spatio-Temporal (VAST) model for count data, we estimate the spatio-temporal distribution, shift in time, and abundance of 140 species of the Eastern English Chanel, Bay of Biscay and Mediterranean Sea. From the model outputs, we determined spatio-temporal clusters, calculating p-values for hierarchical clustering via multiscale bootstrap resampling. Then, we designed a functional map given the defined cluster. We found that the species distribution within the ecosystem was not random. Indeed, species evolved in space and time in clusters. Moreover, these clusters remained similar over time deriving from the fact that species of a same cluster often shifted in sync, keeping the overall structure of the ecosystem similar overtime. Knowing the co-existing species within these clusters could help with predicting data-poor species distribution and abundance. Further analysis is being performed to assess the ecological functions represented in each cluster.

Keywords: cluster distribution shift, European marine ecosystems, functional distribution, spatio-temporal model

Procedia PDF Downloads 167

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: Tapan Jain, Davender Singh Saini

Abstract:

Clustering is a useful mechanism in wireless sensor networks which helps to cope with scalability and data transmission problems. The basic aim of our research work is to provide efficient clustering using Hierarchical agglomerative clustering (HAC). If the distance between the sensing nodes is calculated using their location then it’s quantitative HAC. This paper compares the various agglomerative clustering techniques applied in a wireless sensor network using the quantitative data. The simulations are done in MATLAB and the comparisons are made between the different protocols using dendrograms.

Keywords: routing, hierarchical clustering, agglomerative, quantitative, wireless sensor network

Procedia PDF Downloads 564

Authors: Ho Young Son, Bu Seog Ju, Woo Young Jung

Abstract:

This study presents the seismic safety evaluation of weir structure subjected to strong earthquake ground motions, as a flood defense structure in civil engineering structures. The seismic safety analysis procedure was illustrated through development of Finite Element (FE) and InFinite Element (IFE) method in ABAQUS platform. The IFE model was generated by CINPS4, 4-node linear one-way infinite model as a sold continuum infinite element in foundation areas of the weir structure and then nonlinear FE model using friction model for soil-structure interactions was applied in this study. In order to understand the complex behavior of weir structures, nonlinear time history analysis was carried out. Consequently, it was interesting to note that the compressive stress gave more vulnerability to the weir structure, in comparison to the tensile stress, during an earthquake. The stress concentration of the weir structure was shown at the connection area between the weir body and stilling basin area. The stress both tension and compression was reduced in IFE model rather than FE model of weir structures.

Keywords: seismic, numerical analysis, FEM, weir, boundary condition

Procedia PDF Downloads 422

Authors: Po-Jen Chen, Jian-Jiun Ding, Hung-Wei Hsu, Chien-Yao Wang, Jia-Ching Wang

Abstract:

A more accurate scene classification algorithm using label relations and the hierarchy neural network was developed in this work. In many classification algorithms, it is assumed that the labels are mutually exclusive. This assumption is true in some specific problems, however, for scene classification, the assumption is not reasonable. Because there are a variety of objects with a photo image, it is more practical to assign multiple labels for an image. In this paper, two label relations, which are exclusive relation and hierarchical relation, were adopted in the classification process to achieve more accurate multiple label classification results. Moreover, the hierarchy neural network (hierarchy NN) is applied to classify the image and the directed acyclic graph structure is used for predicting a more reasonable result which obey exclusive and hierarchical relations. Simulations show that, with these techniques, a much more accurate scene classification result can be achieved.

Keywords: convolutional neural network, label relation, hierarchy neural network, scene classification

Procedia PDF Downloads 425

Authors: Yasser F. Hassan

Abstract:

Deep learning structure is a branch of machine learning science and greet achievement in research and applications. Cellular neural networks are regarded as array of nonlinear analog processors called cells connected in a way allowing parallel computations. The paper discusses how to use deep learning structure for representing neural cellular automata model. The proposed learning technique in cellular automata model will be examined from structure of deep learning. A deep automata neural cellular system modifies each neuron based on the behavior of the individual and its decision as a result of multi-level deep structure learning. The paper will present the architecture of the model and the results of simulation of approach are given. Results from the implementation enrich deep neural cellular automata system and shed a light on concept formulation of the model and the learning in it.

Keywords: cellular automata, neural cellular automata, deep learning, classification

Procedia PDF Downloads 161

Authors: Akiode Ayobami, Akiode Akinsewa, Odeku Mojisola, Salako Busola, Odutolu Omobola, Nuhu Khadija

Abstract:

Purpose: Evidence exists that family planning use can contribute to reduction in infant and maternal mortality in any country. Despite these benefits, contraceptive use in Nigeria still remains very low, only 10% among married women. Understanding factors that predict contraceptive use is very important in order to improve the situation. In this paper, we analysed data from the 2013 Nigerian Demographic and Health Survey (NDHS) to better understand predictors of contraceptive use in Nigeria. The use of logistics regression and other traditional models in this type of situation is not appropriate as they do not account for social structure influence brought about by the hierarchical nature of the data on response variable. We therefore used multilevel modelling to explore the determinants of contraceptive use in order to account for the significant variation in modern contraceptive use by socio-demographic, and other proximate variables across the different Nigerian states. Method: This data has a two-level hierarchical structure. We considered the data of 26, 403 married women of reproductive age at level 1 and nested them within the 36 states and the Federal Capital Territory, Abuja at level 2. We modelled use of modern contraceptive against demographic variables, being told about FP at health facility, heard of FP on TV, Magazine or radio, husband desire for more children nested within the state. Results: Our results showed that the independent variables in the model were significant predictors of modern contraceptive use. The estimated variance component for the null model, random intercept, and random slope models were significant (p=0.00), indicating that the variation in contraceptive use across the Nigerian states is significant, and needs to be accounted for in order to accurately determine the predictors of contraceptive use, hence the data is best fitted by the multilevel model. Only being told about family planning at the health facility and religion have a significant random effect, implying that their predictability of contraceptive use varies across the states. Conclusion and Recommendation: Results showed that providing FP information at the health facility and religion needs to be considered when programming to improve contraceptive use at the state levels.

Keywords: multilevel modelling, family planning, predictors, Nigeria

Procedia PDF Downloads 391

Authors: K. Khanafer

Abstract:

The aim of this investigation was to validate the fluid-structure interaction (FSI) model of type B aortic dissection with our experimental results from a bench-top-model. Another objective was to study the relationship between the size of a septectomy that increases the outflow of the false lumen and its effect on the values of the differential of pressure between true lumen and false lumen. FSI analysis based on Galerkin’s formulation was used in this investigation to study flow pattern and hemodynamics within a flexible type B aortic dissection model using boundary conditions from our experimental data. The numerical results of our model were verified against the experimental data for various tear size and location. Thus, CFD tools have a potential role in evaluating different scenarios and aortic dissection configurations.

Keywords: aortic dissection, fluid-structure interaction, in vitro model, numerical

Procedia PDF Downloads 247

Authors: Patrick Guggenberger

Abstract:

Extant literature has highlighted the importance of individual employees in the entrepreneurial process, as they are those that come up with novel ideas and promote their implementation throughout the organization. However, research on antecedents of individual entrepreneurial behavior (IEB) is very limited. The present study takes an initial step to investigate the interplay between transformational leader behaviors of direct supervisors and employees’ ability and willingness to act entrepreneurial and sheds light on the moderating role of an individual’s hierarchical level. A theoretically derived research model is empirically tested, drawing on survey data of 450 individuals working in medium- and large-sized corporations in two countries. Findings indicate that various transformational leader behaviors have a strong positive impact on IEB, while the ability of direct supervisors to influence their followers’ entrepreneurial behavior depends strongly on their own hierarchical level. The study reveals that transformational leadership has most impact at lower hierarchical levels, where employees’ motivation to act entrepreneurial is the lowest.

Keywords: corporate entrepreneurship, hierarchy, individual entrepreneurial behavior, transformational leadership

Procedia PDF Downloads 323

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 65

Authors: Ren Zuo Wang

Abstract:

In this paper, in order to investigate the behavior of the wood structure, the non-linearity of wood material model in LS-DYNA is adopted. It is difficult and less efficient to conduct the experiment of the ancient wood structure, hence LS-DYNA software can be used to simulate nonlinear responses of ancient wood structure. In LS-DYNA software, there is material model called *MAT_WOOD or *MAT_143. This model is to simulate a single-element response of the wood subjected to tension and compression under the parallel and the perpendicular material directions. Comparing with the exact solution and numerical simulations results using LS-DYNA, it demonstrates the accuracy and the efficiency of the proposed simulation method.

Keywords: LS-DYNA, wood structure, single-element simulations, MAT_143

Procedia PDF Downloads 591

Authors: Khadijah B. Alziyadi, Khawlh A. Alzubaidi, Amor M. Alsayari

Abstract:

Recently, GaMnAs diluted magnetic semiconductors(DMSs) have received considerable attention because they combine semiconductor and magnetic properties. GaMnAs has been used as a model DMS and as a test bed for many concepts and functionalities of spintronic devices. In this paper, a theoretical study on the band structure ofGaMnAswill be presented. The model that we used in this study is the 8-band k.p methodwherespin-orbit interaction, spin splitting, and strain are considered. The band structure of GaMnAs will be calculated in different directions in the reciprocal space. The effect of manganese content on the GaMnAs band structure will be discussed. Also, the influence of strain, which varied continuously from tensile to compressive, on the different bands will be studied.

Keywords: band structure, diluted magnetic semiconductor, k.p method, strain

Procedia PDF Downloads 114

Authors: Tingyu Zhang

Abstract:

This paper utilizes the Super-SBM model to assess water resources green efficiency (WRGE) among provinces in China and investigate its spatial and temporal features, based on the characteristic framework of “economy-environment-society.” The social network analysis is employed to examine the network pattern and spatial interaction of WRGE. Further, the quadratic assignment procedure method is utilized for examining the influencing factors of the spatial association of WRGE regarding “relationship.” The study reveals that: (1) the spatial distribution of WRGE demonstrates a distribution pattern of Eastern>Western>Central; (2) a remarkable spatial association exists among provinces; however, no strict hierarchical structure is observed. The internal structure of the WRGE network is characterized by the feature of "Eastern strong and Western weak". The block model analysis discovers that the members of the “net spillover” and “two-way spillover” blocks are mostly in the eastern and central provinces; “broker” block, which plays an intermediary role, is mostly in the central provinces; and members of the “net beneficiary” block are mostly in the western region. (3) Differences in economic development, degree of urbanization, water use environment, and water management have significant impacts on the spatial connection of WRGE. This study is dedicated to the realization of regional linkages and synergistic enhancement of WRGE, which provides a meaningful basis for building a harmonious society of human and water coexistence.

Keywords: water resources green efficiency, super-SBM model, social network analysis, quadratic assignment procedure

Procedia PDF Downloads 20

Authors: Panagiota Koliousi, Natasha Miaouli

Abstract:

We compare product and labour market liberalization under the two trade union bargaining models: the Right-to-Manage (RTM) model and the Efficient Bargaining (EB) model. The vehicle is a dynamic general equilibrium (DGE) model that incorporates two types of agents (capitalists and workers), imperfectly competitive product and labour markets. The model is solved numerically employing common parameter values and data from the euro area. A key message is that product market deregulation is favourable under any labour market structure while opting for labour market deregulation one should provide special attention to the structure of the labour market such as the bargaining system of unions. If the prevailing way of bargaining is the RTM model then restructuring both markets is beneficial for all agents.

Keywords: market structure, structural reforms, trade unions, unemployment

Procedia PDF Downloads 179

Authors: Shuo Liu, Dan Liu

Abstract:

In the field of named entity recognition, most of the research has been conducted around simple entities. However, for nested named entities, which still contain entities within entities, it has been difficult to identify them accurately due to their boundary ambiguity. In this paper, a hierarchical recognition model is constructed based on the grammatical structure and semantic features of Chinese text for boundary calculation based on lexical features. The analysis is carried out at different levels in terms of granularity, semantics, and lexicality, respectively, avoiding repetitive work to reduce computational effort and using the semantic features of words to calculate the boundaries of entities to improve the accuracy of the recognition work. The results of the experiments carried out on web-based microblogging data show that the model achieves an accuracy of 86.33% and an F1 value of 89.27% in recognizing nested named entities, making up for the shortcomings of some previous recognition models and improving the efficiency of recognition of nested named entities.

Keywords: coarse-grained, nested named entity, Chinese natural language processing, word embedding, T-SNE dimensionality reduction algorithm

Procedia PDF Downloads 99

Authors: Fateh Adhnouss, Husam El-Asfour, Kenneth McIsaac, AbdulMutalib Wahaishi, Idris El-Feghia

Abstract:

Conceptualization is an essential component of semantic ontology-based approaches. There have been several approaches that rely on extensional structure and extensional reduction structure in order to construct conceptualization. In this paper, several limitations are highlighted relating to their applicability to the construction of conceptualizations in dynamic and open environments. These limitations arise from a number of strong assumptions that do not apply to such environments. An intensional structure is strongly argued to be a natural and adequate modeling approach. This paper presents a conceptualization structure based on property relations and propositions theory (PRP) to the model ontology that is suitable for open environments. The model extends the First-Order Logic (FOL) notation and defines the formal representation that enables interoperability between software systems and supports semantic integration for software systems in open, dynamic environments.

Keywords: conceptualization, ontology, extensional structure, intensional structure

Procedia PDF Downloads 77