Computer Sciences Commons^™

Personalized Detection Of Anxiety Provoking News Events Using Semantic Network Analysis, Jacquelyn Cheun Phd, Luay Dajani, Quentin B. Thomas

SMU Data Science Review

In the age of hyper-connectivity, 24/7 news cycles, and instant news alerts via social media, mental health researchers don't have a way to automatically detect news content which is associated with triggering anxiety or depression in mental health patients. Using the Associated Press news wire, a semantic network was built with 1,056 news articles containing over 500,000 connections across multiple topics to provide a personalized algorithm which detects problematic news content for a given reader. We make use of Semantic Network Analysis to surface the relationship between news article text and anxiety in readers who struggle with mental health disorders. …

A Data Science Approach To Defining A Data Scientist, Andy Ho, An Nguyen, Jodi L. Pafford, Robert Slater

SMU Data Science Review

In this paper, we present a common definition and list of skills for a Data Scientist using online job postings. The overlap and ambiguity of various roles such as data scientist, data engineer, data analyst, software engineer, database administrator, and statistician motivate the problem. To arrive at a single Data Scientist definition, we collect over 8,000 job postings from Indeed.com for the six job titles. Each corpus contains text on job qualifications, skills, responsibilities, educational preferences, and requirements. Our data science methodology and analysis rendered the single definition of a data scientist: A data scientist codes, collaborates, and communicates – …

Detecting Myocardial Infarctions Using Machine Learning Methods, Aniruddh Mathur

Master's Projects

Myocardial Infarction (MI), commonly known as a heart attack, occurs when one of the three major blood vessels carrying blood to the heart get blocked, causing the death of myocardial (heart) cells. If not treated immediately, MI may cause cardiac arrest, which can ultimately cause death. Risk factors for MI include diabetes, family history, unhealthy diet and lifestyle. Medical treatments include various types of drugs and surgeries which can prove very expensive for patients due to high healthcare costs. Therefore, it is imperative that MI is diagnosed at the right time. Electrocardiography (ECG) is commonly used to detect MI. ECG …

A Data Driven Approach To Forecast Demand, Hannah Kosinovsky, Sita Daggubati, Kumar Ramasundaram, Brent Allen

SMU Data Science Review

Abstract. In this paper, we present a model and methodology for accurately predicting the following quarter’s sales volume of individual products given the previous five years of sales data. Forecasting product demand for a single supplier is complicated by seasonal demand variation, business cycle impacts, and customer churn. We developed a novel prediction using machine learning methodology, based upon a Dense neural network (DNN) model that implicitly considers cyclical demand variation and explicitly considers customer churn while minimizing the least absolute error between predicted demand and actual sales. Using parts sales data for a supplier to the oil and gas …

Ordinal Hyperplane Loss, Bob Vanderheyden

Doctor of Data Science and Analytics Dissertations

This research presents the development of a new framework for analyzing ordered class data, commonly called “ordinal class” data. The focus of the work is the development of classifiers (predictive models) that predict classes from available data. Ratings scales, medical classification scales, socio-economic scales, meaningful groupings of continuous data, facial emotional intensity and facial age estimation are examples of ordinal data for which data scientists may be asked to develop predictive classifiers. It is possible to treat ordinal classification like any other classification problem that has more than two classes. Specifying a model with this strategy does not fully utilize …

Analyze Informant-Based Questionnaire For The Early Diagnosis Of Senile Dementia Using Deep Learning, Fubao Zhu, Xiaonan Li, Daniel Mcgonigle, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chu, Weihua Zhou

Faculty Publications

Objective: This paper proposes a multiclass deep learning method for the classification of dementia using an informant-based questionnaire.

Methods: A deep neural network classification model based on Keras framework is proposed in this paper. To evaluate the advantages of our proposed method, we compared the performance of our model with industry-standard machine learning approaches. We enrolled 6,701 individuals, which were randomly divided into training data sets (6030 participants) and test data sets (671 participants). We evaluated each diagnostic model in the test set using accuracy, precision, recall, and F1-Score.

Results: Compared with the seven conventional machine learning …

Information Extraction From Biomedical Text Using Machine Learning, Deepti Garg

Master's Projects

Inadequate drug experimental data and the use of unlicensed drugs may cause adverse drug reactions, especially in pediatric populations. Every year the U.S. Food and Drug Administration approves human prescription drugs for marketing. The labels associated with these drugs include information about clinical trials and drug response in pediatric population. In order for doctors to make an informed decision about the safety and effectiveness of these drugs for children, there is a need to analyze complex and often unstructured drug labels. In this work, first, an exploratory analysis of drug labels using a Natural Language Processing pipeline is performed. Second, …

Assessing Wildfire Damage From High Resolution Satellite Imagery Using Classification Algorithms, Ai-Linh Alten

Master's Projects

Wildfire damage assessments are important information for first responders, govern- ment agencies, and insurance companies to estimate the cost of damages and to help provide relief to those affected by a wildfire. With the help of Earth Observation satellite technology, determining the burn area extent of a fire can be done with traditional remote sensing methods like Normalized Burn Ratio. Using Very High Resolution satellites can help give even more accurate damage assessments but will come with some tradeoffs; these satellites can provide higher spatial and temporal resolution at the expense of better spectral resolution. As a wildfire burn area …

Finding A Viable Neural Network Architecture For Use With Upper Limb Prosthetics, Maxwell Lavin

Master of Science in Computer Science Theses

This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy …

Graph Deep Learning: Methods And Applications, Muhan Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

The past few years have seen the growing prevalence of deep neural networks on various application domains including image processing, computer vision, speech recognition, machine translation, self-driving cars, game playing, social networks, bioinformatics, and healthcare etc. Due to the broad applications and strong performance, deep learning, a subfield of machine learning and artificial intelligence, is changing everyone's life.Graph learning has been another hot field among the machine learning and data mining communities, which learns knowledge from graph-structured data. Examples of graph learning range from social network analysis such as community detection and link prediction, to relational machine learning such as …

On Algebraic Structures And Automaton For Optimal Computer Network Design And Performance Study, Xiangrong Ma

UNLV Theses, Dissertations, Professional Papers, and Capstones

For decades, study of computer networks has been concentrated on the use of the well-established OSI or TCP/IP reference models that have found tremendous success in the actual implementation of various network structures and protocols. Lack of theoretical foundation, this implementation-driven, empirical approach, however, is experiencing insurmountable difficulties in delivering, tuning for, and sustaining the promised peak performance of a computer system that is so heavily dependent on the performance of the underline computer networks. This issue is becoming particularly prevalent in today’s cloud-based high-performance computing environment where CPU-time-extensive computation loads need to get distributed among computing machines through high-speed …

On The Human Factors Impact Of Polyglot Programming On Programmer Productivity, Phillip Merlin Uesbeck

UNLV Theses, Dissertations, Professional Papers, and Capstones

Polyglot programming is a common practice in modern software development. This practice is often considered useful to create software by allowing developers to use whichever language they consider most well suited for the different parts of their software. Despite this ubiquity of polyglot programming there is no empirical research into how this practice affects software developers and their productivity. In this dissertation, after reviewing the state of the art in programming language and linguistic research pertaining to the topic, this matter is investigated by way of two empirical studies with 109 and 171 participants solving programming tasks. Based on the …

Towards Interpretable Machine Learning With Applications To Clinical Decision Support, Zhicheng Cui

McKelvey School of Engineering Graduate Student Theses & Dissertations

Machine learning models have achieved impressive predictive performance in various applications such as image classification and object recognition. However, understanding how machine learning models make decisions is essential when deploying those models in critical areas such as clinical prediction and market analysis, where prediction accuracy is not the only concern. For example, in the clinical prediction of ICU transfers, in addition to accurate predictions, doctors need to know the contributing factors that triggered the alert, which factors can be quickly altered to prevent the ICU transfer. While interpretable machine learning has been extensively studied for years, challenges remain as among …

Learning Nearest Neighbor Graphs From Noisy Distance Samples, Blake Mason, Ardhendu S. Tripathy, Robert Nowak

Computer Science Faculty Research & Creative Works

We consider the problem of learning the nearest neighbor graph of a dataset of n items. The metric is unknown, but we can query an oracle to obtain a noisy estimate of the distance between any pair of items. This framework applies to problem domains where one wants to learn people's preferences from responses commonly modeled as noisy distance judgments. In this paper, we propose an active algorithm to find the graph with high probability and analyze its query complexity. In contrast to existing work that forces Euclidean structure, our method is valid for general metrics, assuming only symmetry and …

Maxgap Bandit: Adaptive Algorithms For Approximate Ranking, Sumeet Katariya, Ardhendu S. Tripathy, Robert Nowak

Computer Science Faculty Research & Creative Works

This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate ranking, noisy sorting, outlier detection, and top-arm identification in bandits. The key novelty of the MaxGap bandit problem is that it aims to adaptively determine the natural partitioning of the distributions into a subset with larger means and a subset with smaller means, where the split is determined by the largest gap rather than a pre-specified rank or threshold. Estimating an arm's gap requires …

Computational Screening Of New Perovskite Materials Using Transfer Learning And Deep Learning, Xiang Li, Yabo Dan, Rongzhi Dong, Zhuo Cao, Chengcheng Niu, Yuqi Song, Shaobo Li, Jianjun Hu

Faculty Publications

As one of the most studied materials, perovskites exhibit a wealth of superior properties that lead to diverse applications. Computational prediction of novel stable perovskite structures has big potential in the discovery of new materials for solar panels, superconductors, thermal electric, and catalytic materials, etc. By addressing one of the key obstacles of machine learning based materials discovery, the lack of sufficient training data, this paper proposes a transfer learning based approach that exploits the high accuracy of the machine learning model trained with physics-informed structural and elemental descriptors. This gradient boosting regressor model (the transfer learning model) allows us …

Design Of A Flexible System Simulation Evaluation Framework, Rusheng Ju, Zimin Cai, Wang Song, Wang Peng

Journal of System Simulation

Abstract: To meet variable evaluation requirement of complex system simulation, this paper puts forward a design strategy of flexible effectiveness evaluation framework. The composition structure of system simulation evaluation framework is analyzed. To help users design reference dynamically, the method of evaluation reference edit and display is introduced based on Web. To enhance the extensibility of evaluation model, the method of interface design and code generation is investigated. To ensure the flexibility and extensibility of evaluation framework, the relation and mapping mechanism of evaluation references, evaluation model and evaluation result is studied. The framework is realized and verified in …

Research On Simulation Platform For Equipment System Analysis, Yuping Li, Shaojie Mao, Zhenqi Ju, Zhou Fang, Guoqiang Yan

Journal of System Simulation

Abstract: With the development of equipment construction from platform-centric to network-centric, simulation analysis of equipment system is an important means and tool to support the transformation and development of equipment construction under the condition of multi-task joint operation. Starting from the requirement of system simulation analysis, a cloud-based equipment system simulation architecture is proposed to realize flexible and configurable simulation environment according to task requirements; and a high-performance simulation framework is conducted, which provides strong support for different application modes, such as parallel hyper-real-time and distributed simulation deduction. The unified description, organization and management method of model and data resources …

Design And Finite Element Analysis Of Reflector Spherical Shell For Flight Simulator, Hailiang Bai, Jiang Nan, Zhang Liao, Yuewen Fu

Journal of System Simulation

Abstract: The fight simulator with six-degree-of-freedom motion platform can simulate the flight attitude in real time and provide realistic overload dynamic feeling, which requires that the equipment on the platform must adapt to the overload during flight simulation. To solve the contradiction between the rigidity and weight of material, the glass fiber composite material is used to design and manufacture the spherical shell of the mirror . To improve the optical collimation of the reflector, the specific hyperboloid aspheric surface is selected as the surface design scheme,the 3D model of the spherical shell is constructed. The parameters of the …

Numerical Simulation Of Rock Breaking Mechanism For Compound Percussion Drilling, Yumei Li, Liwei Yu, Zhang Tao, Su Zhong, Jianming Liu

Journal of System Simulation

Abstract: The ABAQUS dynamic impact module is used to establish the numerical calculation model for PDC single tooth-rock impact. The effects of PDC cutting teeth on the dynamic rock breaking mode and rock breaking effect under the combined action of rotating speed, drilling pressure, alternating impact torque and alternating impact force are studied. The study shows that the torsional impact mode is 39.28% higher than the rock breaking efficiency of the rotary impact, and the compound percussion mode is 27.79% higher than the rock breaking efficiency of the torsional impact. Under the same conditions of impact time, the rock surface …

Research On Corridor Setting Based On Pedestrian Simulation Of Social Groups, Yiting Xu, Zhang Rui

Journal of System Simulation

Abstract: As the connector of each space in the hub, the rail transit hub corridor plays the role of transition and buffer. The existence of social groups makes an important impact on pedestrian traffic and its simulation. The paper supplements the consideration of pedestrian traffic related studies on social groups travel, analyses the characteristics of social groups in rail transit hub corridor, improves Moussaïd social group force model, and redevelops AnyLogic micro-simulation platform based on Python language. Taking a subway station in Beijing as an example, fully considering the influence of social groups, it is obtained that the optimal channel …

Research On Simulation Optimization Of Disk-Based Storage Operation Mode In Warehouse, Danlan Xie, Liu Meng, Haihong Yu, Chen Jing, Yubo Zhou, Kazi Mohiuddin

Journal of System Simulation

Abstract: As the efficiency of operation affects the overall competitiveness of the port, it is very necessary to design the storage operation mode reasonably. A disk-based storage operation mode is proposed. And the simulation model is established by using the logistics simulation software FlexSim based on the operational requirements of the warehouse. Through a large number of simulation experiments, comparing the primary storage mode with the disk-based storage mode, the results of the increase in total idle rate and the more balanced distribution of each hour utilization ratio of the forklifts are obtained. The result verifies the feasibility and effectiveness …

Research On Extraction Method Of Time-Frequency Feature Of Fall Detection, Tianrun Wang, Su Zhong, Liu Ning, Li Chao, Guodong Fu

Journal of System Simulation

Abstract: Aiming at the problem of features extract method for fall detection, the method using time-frequency analyze and features extraction by Fractional Fourier Transform (FRFT) has been proposed. The inertial data is measured by 15 IMU wearing on body, the features extracted after FRFT with multiple order are analyzed and compared. The difference of feature distribution of eight fall actions has been compared, and the difference of feature distribution between fall action and 4 normal actions has been compared. The feasibility of using FRFT in fall detection is proved.

Parallel Tasks Optimization Scheduling In Cloud Manufacturing System, Chenwei Feng, Wang Yan

Journal of System Simulation

Abstract: To solve the problem of unbalanced resource requirements and low resource utilization when the same type of tasks are executed in parallel in the cloud manufacturing system, a task resource scheduling model with the goal of minimizing cost, minimizing time, maximizing reliability and optimizing quality is established. A non-dominated sorting genetic algorithm based on reference points (NSGA-III) is adopted to solve the model by combining real number matrix coding and crossover and mutation based on real number coding instead of common evolutionary strategy. And an optimal decision strategy based on combination of analytic hierarchy process and entropy value method …

Comparative Study On Resistance Modeling Method In Yacht Simulator, Xiaochen Li, Yin Yong

Journal of System Simulation

Abstract: In order to solve the problem that the existing resistance modeling method of yacht has poor universality and the calculation accuracy is not high, approximate resistance modeling methods of high speed craft are analyzed and summarized. The actual yacht model is simplified into a prismatic hull. “ЦАГИ” method and SIT method are reproduced and the simulation results are compared with model test. The application of resistance approximate modeling in the yacht simulator is discussed. The results reveal that the resistance is in good agreement with the experimental value, and the SIT method with simplified hull form is more …

Research On The Value Accessing Method For Calibrating Micro Traffic Simulation Model Parameters, Chenjing Zhou, Rong Jian, Kwok Lam

Journal of System Simulation

Abstract: Parameter calibration is the precondition of the application of micro traffic simulation technology. This study focuses on the value accessing method for parameter calibration in order to further improve the parameter calibration process. The analysis of the distribution characteristics of each parameter calibration results shows that the parameters have different trends in the process of gradual iteration, and there are multiple optimal solutions for the model parameter calibration results. In this paper, the dispersion is used as the quantitative analysis index of the concentration degree of each parameter calibration result, and the parameter value of the model is determined …

Research On Source Seeking Methods Of Harmful Gas Leakage In Chemical Industry Parks, Zhao Yong, Bin Chen, Xiaodong Wang, Zhengqiu Zhu, Rongxiao Wang, Xiaogang Qiu

Journal of System Simulation

Abstract: Chemical production safety accidents often lead to harmful gas leakage, causing serious environmental damage and casualties. Mastering the information of leaking source quickly can assist in emergency disposal decisions and reduce the harm of accidents. In this paper, Entrotaxis algorithm is used to guide the ground source seeking equipment to move to the vicinity of the leaking source quickly and autonomously in a chemical park scene, and to master the source information. According to the characteristics of the chemical industry park scene, this paper applies intermittent search module into Entrotaxis algorithm and proposes a robust and suitable algorithm (Entrotaxis-Jump …

Numerical Simulation Analysis Of Anti-Blast Impact Of Underground Rescue Capsule Based On Ls-Dyna, Zhang Fan, Yuanhua Yang, Xiaoxu He, Deng Yu

Journal of System Simulation

Abstract: Aiming at the strength problem of the underground rescue cabin under explosion impact load, a finite element model of overall explosion impact load and fluid-solid coupling structure response is established in transient dynamic soft LS-DYNA. The flow field impact load is generated by explosion algorithm, and the propagation of the impact load in the air is calculated. The dynamic response of the rescue cabin structure under the impact load is calculated by the fluid-solid coupling method. The results show that the maximum load occurs on the end surface closest to the explosion source, and the structural deformation is small …

The Scheduling Algorithm Of Cloud Job Based On Hopfield Neural Network, Yudong Guo, Jinping Zuo

Journal of System Simulation

Abstract: Focusing on the low efficiency of cloud job scheduling and the insufficient utility of resource, a job scheduling algorithm based on Hopfield Neural Network is proposed. In order to improve the resource scheduling ability of the system, The resource characteristics which influence the cloud job scheduling are shown. The mathematical model of resource constraints is established, and the Hopfield energy function is designed and optimized. The average utilization rate of 9 nodes is analyzed by using the standard test cases, and the performance and resource utilization of the proposed strategy are compared with three typical algorithms. …

Simulation Research On Attitude Solution Method Of Micro-Mini Missile, Chunbo Zhao, Junfang Fan, Liu Ning

Journal of System Simulation

Abstract: Aiming at the problem of attitude measurement error in the inertial navigation system of micro and small guided ammunition under eccentric structure, the attitude solution and error compensation optimization are studied by using rotation vector optimization of multiple sub-samples, such as monotone sample, two sub-samples, three sub-samples and four sub-samples, and the fourth-order runge kutta algorithm. Through error compensation and optimization of measured data, the results show that the monomorphic modified algorithm has the worst optimization effect, the fourth-order runge kutta optimization algorithm has the best effect, and the maximum drift error of attitude Angle is better than 10 …