Physical Sciences and Mathematics Commons^™

Early Detection Of Fake News On Social Media, Yang Liu

Dissertations

The ever-increasing popularity and convenience of social media enable the rapid widespread of fake news, which can cause a series of negative impacts both on individuals and society. Early detection of fake news is essential to minimize its social harm. Existing machine learning approaches are incapable of detecting a fake news story soon after it starts to spread, because they require certain amounts of data to reach decent effectiveness which take time to accumulate. To solve this problem, this research first analyzes and finds that, on social media, the user characteristics of fake news spreaders distribute significantly differently from those …

Bio-Inspired Learning And Hardware Acceleration With Emerging Memories, Shruti R. Kulkarni

Dissertations

Machine Learning has permeated many aspects of engineering, ranging from the Internet of Things (IoT) applications to big data analytics. While computing resources available to implement these algorithms have become more powerful, both in terms of the complexity of problems that can be solved and the overall computing speed, the huge energy costs involved remains a significant challenge. The human brain, which has evolved over millions of years, is widely accepted as the most efficient control and cognitive processing platform. Neuro-biological studies have established that information processing in the human brain relies on impulse like signals emitted by neurons called …

Generating Energy Data For Machine Learning With Recurrent Generative Adversarial Networks, Mohammad Navid Fekri, Ananda M. Ghosh, Katarina Grolinger

Electrical and Computer Engineering Publications

The smart grid employs computing and communication technologies to embed intelligence into the power grid and, consequently, make the grid more efficient. Machine learning (ML) has been applied for tasks that are important for smart grid operation including energy consumption and generation forecasting, anomaly detection, and state estimation. These ML solutions commonly require sufficient historical data; however, this data is often not readily available because of reasons such as data collection costs and concerns regarding security and privacy. This paper introduces a recurrent generative adversarial network (R-GAN) for generating realistic energy consumption data by learning from real data. Generativea adversarial …

Stochastic Orthogonalization And Its Application To Machine Learning, Yu Hong

Electrical Engineering Theses and Dissertations

Orthogonal transformations have driven many great achievements in signal processing. They simplify computation and stabilize convergence during parameter training. Researchers have introduced orthogonality to machine learning recently and have obtained some encouraging results. In this thesis, three new orthogonal constraint algorithms based on a stochastic version of an SVD-based cost are proposed, which are suited to training large-scale matrices in convolutional neural networks. We have observed better performance in comparison with other orthogonal algorithms for convolutional neural networks.

Multi-Agent Narrative Experience Management As Story Graph Pruning, Edward T. Garcia

University of New Orleans Theses and Dissertations

In this thesis I describe a method where an experience manager chooses actions for non-player characters (NPCs) in intelligent interactive narratives through story graph representation and pruning. The space of all stories can be represented as a story graph where nodes are states and edges are actions. By shaping the domain as a story graph, experience manager decisions can be made by pruning edges. Starting with a full graph, I apply a set of pruning strategies that will allow the narrative to be finishable, NPCs to act believably, and the player to be responsible for how the story unfolds. By …

A Qualitative Representation Of Spatial Scenes In R2 With Regions And Lines, Joshua Lewis

Electronic Theses and Dissertations

Regions and lines are common geographic abstractions for geographic objects. Collections of regions, lines, and other representations of spatial objects form a spatial scene, along with their relations. For instance, the states of Maine and New Hampshire can be represented by a pair of regions and related based on their topological properties. These two states are adjacent (i.e., they meet along their shared boundary), whereas Maine and Florida are not adjacent (i.e., they are disjoint).

A detailed model for qualitatively describing spatial scenes should capture the essential properties of a configuration such that a description of the represented objects …

Image-Based Malware Classification With Convolutional Neural Networks And Extreme Learning Machines, Mugdha Jain

Master's Projects

Research in the field of malware classification often relies on machine learning models that are trained on high level features, such as opcodes, function calls, and control flow graphs. Extracting such features is costly, since disassembly or code execution is generally required. In this research, we conduct experiments to train and evaluate machine learning models for malware classification, based on features that can be obtained without disassembly or execution of code. Specifically, we visualize malware samples as images and employ image analysis techniques. In this context, we focus on two machine learning models, namely, Convolutional Neural Networks (CNN) and Extreme …

Hot Fusion Vs Cold Fusion For Malware Detection, Snehal Bichkar

Master's Projects

A fundamental problem in malware research consists of malware detection, that is, dis- tinguishing malware samples from benign samples. This problem becomes more challeng- ing when we consider multiple malware families. A typical approach to this multi-family detection problem is to train a machine learning model for each malware family and score each sample against all models. The resulting scores are then used for classification. We refer to this approach as “cold fusion,” since we combine previously-trained models—no retraining of these base models is required when additional malware families are considered. An alternative approach is to train a single model …

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 …

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, …

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 …

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 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 …

Rehabilitation Training System Of Vr-Based Speech Apraxia, Huanhuan Jiao, Zhigeng Pan, Shuchang Xu, Qingshu Yuan

Journal of System Simulation

Abstract: Aiming at the problem that the enthusiasm of active training in patients with traditional speech apraxia rehabilitation is gradually weakened, a virtual reality-based rehabilitation training system for speech apraxia is designed. The system simulates the 26 monosyllabic pronunciation mouths shapes made by virtual human in Chinese and uses it for the learning module. It is proposed to identify 26 monosyllabic words by using the isolated word speech recognition algorithm, which improves the accuracy of speech recognition. The system includes a training module and a scene module for assisting the patient's pronunciation rehabilitation training. The evaluation results show that …

Multi-Objective Optimization Design Of Aerodynamic Layout For Twin Swept-Wing Aircraft, Yuchang Lei, Dengcheng Zhang, Yanhua Zhang, Guangxu Su, Luo Hao, Zhan Ren

Journal of System Simulation

Abstract: Multi-objective optimization of aerodynamic layout is a key technology in the design of vehicles. The overall configuration of the shape parameters is optimized with a double swept-shaped wave shape as the basic configuration. We use NSGA-Ⅱ multi-objective genetic algorithm, take the aircraft double sweep angle as the design variable, consider the maximum takeoff weight, range, volume ratio and other performance indicators, use Elman neural network to establish the relationship between shape parameters and performance parameters, and establish constraints based on mission planning requirements. The Pareto optimal solution set is obtained by using optimized design and the individuals with …

Dynamic Simulation Of Marine Pasture Water Quality Monitoring Network Based On Aug, Wenxia Xue, Bin Lin, Hu Xu, Jingbo Zhang

Journal of System Simulation

Abstract: The development of marine pastures puts forward higher requirements for water quality monitoring. In order to achieve large-scale and long-term underwater water quality monitoring, AUG-based Underwater Sensor Network (AUSN) is studied. The AUG is introduced as the underwater sink node of the sensor network and the sleep scheduling mechanism is adopted for the sensors, which can effectively reduce the total energy consumption of the network. Based on the analysis of energy consumption characteristics of underwater sensor networks, the energy consumption calculation formula of underwater sensor networks is discussed. Combined with the virtual visualization technology, the underwater sensor network simulation …

A Temporal Action Detection Algorithm Based On Spatio-Temporal Feature Pyramid Network, Liu Wang, Jinyu Sun, Shiwei Ma

Journal of System Simulation

Abstract: In view of the discontinuity of motion timing detection in the frame-level prediction network structure, a novel algorithm based on spatio-temporal feature pyramid network (ST-FPN) is proposed. In the frame-level action prediction, several 3D convolution-de-convolution (CDC) networks are used to sample spatial feature down to 1 dimension and sample temporal feature up to corresponding proposal level. Then the prediction scores of different CDC networks are fused by non-maximum suppression (NMS). The softmax classifier is used to classify frame-level actions, and then temporal action detection is obtained. The experimental results on dataset THUMOS14 show that the proposed algorithm improves the …

Fault Identification Of High-Speed Train Bogie Based On Siamese Convolutional Neural Network, Yunpu Wu, Weidong Jin, Junxiao Ren

Journal of System Simulation

Abstract: The performance degradation and failure of high-speed train bogie components will threaten the operation security of train. This paper proposes a fault type identification method based on siamese convolutional neural network to address the scarcity of data and the high-dimension of monitoring signals. Deep residual network with one-dimension convolution layers is employed for features extraction and fusion of vibration signals from multiple sensors. The siamese structure is employed to obtain the similarities between samples. Fault types are identified by ranking similarities in the support set. The experimental results show that the proposed method can identify the fault types with …

Pedestrian Navigation Method Based On Uwb And Sins, Yang Yang, Li Qing

Journal of System Simulation

Abstract: In view of the problem that the inertial navigation error is accumulating with time and UWB indoor is hard to continue tracking problems in complex environment, an extended Kalman filter (EKF) fusing UWB and sins pedestrian navigation is proposed.The zero speed correction algorithm is used to trigger EKF at zero speed. The sins is corrected by the velocity error measurement provided by sins and the position error measurement provided by UWB restraining error accumulation.When UWB signal is interrupted, the position of UWB output without interruption is taken as the starting position. The experiment results of SINS autonomous navigation …

Evaluation Method Of Simulation Results Based On Principal Component Analysis, Rusheng Ju, Zimin Cai, Yang Mei, Wang Song

Journal of System Simulation

Abstract: A large amount of result data are produced by complex system simulation. These data types are diverse and complex. Usually they cannot be used directly. The inner pattern can only be found by effective evaluation. Based on the characteristics of complex combat simulation results, this paper utilizes the Principal Component Analysis method to reduce the dimension of data analysis and explore the relationship between the system input data and output data. The key influence factors of the measure of force effectiveness is found. The application verification is done by typical examples. The selected principle factors are explored in …

Research On Nondestructive Blood Glucose Cloud Detection System Based On Improved Deep Regression Network, Mengjia He, Yingnian Wu, Yang Rui

Journal of System Simulation

Abstract: Invasive blood glucose measurement has a strong sense of discomfort and risk of infection, so the study of non-invasive blood glucose has a strong practical significance. At present, the optical method is not convenient for practical use, and the energy conservation method requires strict requirements. In view of the above problems, infrared thermography is used to detect blood glucose. After acquiring infrared thermal images of face figure, we extract the gray feature and reduce its dimension. In order to speed up the training and prevent over fitting, depth regression network is improved to model the infrared thermal image gray …

Intelligent Collaborative Networking Method For Workshop Emergencies, Kong Tao, Wang Yan

Journal of System Simulation

Abstract: Due to the complex environment of intelligent manufacturing workshop, abnormal emergencies will cause huge security threats and economic losses to the workshop. It is difficult to transmit the abnormal event data continuously, quickly and completely in the workshop production site, and the fluctuation of abnormal event data is great with high requirements on the integrity and real-time of data transmission. In this paper, a multi-agent cooperative networking method for workshop emergencies is proposed. Mobile robots are introduced as intermediary Sink nodes for data transmission between sensor networks and the Internet. In case of emergencies, the intelligent node and cluster …

A Method Of Manifold Learning For Locality Preserving Projections Based On Geodesic, Lijun Xu, Jinghan Fang, Yiping Wang

Journal of System Simulation

Abstract: In order to solve the problem of under-fitting state of LPP algorithm in practical application,in this paper, the mapping principle of Locality Preserving Projections (LPP) is discussed in detail. The relationship of LPP method between the under-fitting state on certain dataset and adjacency graph is analyzed. The LPP manifold learning method (ISOLPP) is proposed on the basis of geodesic. The experiment results show that the good embedded effect is achieved by implenmenting ISOLPP method on multiple test data sets. It significantly improves the adaptability of the algorithm by not only inheriting the advantages of LPP algorithm with explicit projection …

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also …

Synergic Production Scheduling Method For Distributed Multi-Plants Based On Fusion Decision Tree, Wang Yan, Tianlun Jiang

Journal of System Simulation

Abstract: In the synergic production scheduling optimization problem of distributed multi-plants, it is necessary to consider the two stages of job allocation between factories and job scheduling in factories at the same time. This paper first establishes a distributed multi-plant scheduling model with total cost and advance/delay as the optimization objectives, and then proposes a nested optimization algorithm framework integrating ID3 decision tree with Gauss particle swarm optimization. In this framework, independent scheduling optimization within the factory is nested in the process of inter factory allocation optimization, and elite retention strategy is introduced to improve the algorithm optimization. In …

3d Shape Deformation Simulation Algorithm Based On Haptics, Binbin Qi, Xuefang Zhu, Lipeng Fan

Journal of System Simulation

Abstract: Shape deformation is widely used in virtual reality, system simulation, computer animation and other graphics applications. Few people pay attention to introducing haptic interaction into 3D model deformation. We provide a haptic interactive framework by introducing haptic interaction into shape editing field. Based on the above haptic interactive framework, we propose a 3D model deformation simulation algorithm based on haptics. In order to realize the shape deformation, this algorithm needs to involve three parts: grid hierarchical structure, local mass-spring model and the dynamic shape deformation. Experimental results show that this algorithm has good stability and strong robustness, and the …

A Parallel Simulation Method For Combat Organization And Implementation, Yaxin Tan, Jianhua Luo, Fan Rui, Zhiming Dong

Journal of System Simulation

Abstract: Aiming at the difficult problem of battle parallel simulation, the realization of parallel simulation based on combat organization is analyzed theoretically. Furthermore, a parallel simulation based on combat organization is proposed. One by one, the methods of the simulation task partitioning, the simulation task integration and interaction between integration method are given. This paper breaks through the key technology of parallel simulation, based on the parallel simulation integration framework, implements the system integration, builds the parallel simulation prototype system of the size of the brigade, develops parallel simulation task allocation software, designs the operational application case, and tests parallel …

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 …

Agent Based Modeling And Simulation Analysis Of Low-Orbit Early-Warning Satellites, Liu Wen, Xiaolu Wang, Hongsheng Wang, Zhang Heng, Changqing Wang

Journal of System Simulation

Abstract: Low-Orbit Early-Warning Satellite has accurate midcourse ballistic missile tracking and surveillance capability. The paper takes Space Tracking and Surveillance System’s function and construction as the research subject. System model is constructed based on Agent method. The possible constellation configurations of STSS are analyzed considering the coverage performance,and the detection capability of ballistic missile target is simulated and analyzed. Simulation analysis of target detection is carried out. The result shows that STSS can effectively detect a certain number of targets, but detecting capability is affected severely by solar illumination.