Physical Sciences and Mathematics Commons^™

Data-Optimized Spatial Field Predictions For Robotic Adaptive Sampling: A Gaussian Process Approach, Zachary Nathan

Computer Science Senior Theses

We introduce a framework that combines Gaussian Process models, robotic sensor measurements, and sampling data to predict spatial fields. In this context, a spatial field refers to the distribution of a variable throughout a specific area, such as temperature or pH variations over the surface of a lake. Whereas existing methods tend to analyze only the particular field(s) of interest, our approach optimizes predictions through the effective use of all available data. We validated our framework on several datasets, showing that errors can decline by up to two-thirds through the inclusion of additional colocated measurements. In support of adaptive sampling, …

Towards An Unsupervised Bayesian Network Pipeline For Explainable Prediction, Decision Making And Discovery, Daniel Mallia

Theses and Dissertations

An unsupervised learning pipeline for discrete Bayesian networks is proposed to facilitate prediction, decision making, discovery of patterns, and transparency in challenging real-world AI applications, and contend with data limitations. We explore methods for discretizing data, and notably apply the pipeline to prediction and prevention of preterm birth.

A High Resolution Reconstruction Method Of Temperature Distribution In Acoustic Tomography, Lifeng Zhang, Yu Miao

Journal of System Simulation

Abstract: Accurate measurement temperature distribution is important for industrial production. In order to solve the number of mesh divisions will impact reconstruction accuracy in acoustic tomography, the TR-RBF (Tikhonov regularization-radial basis function) reconstruction algorithm is rebuilt to reconstruct the temperature field with high resolution. The Tikhonov regularization is used to reconstruct the ultrasound time of flight (TOF) to obtain a temperature distribution on coarse grids, and use local weighted regression method to smooth processing; use RBF neural networks to predict the temperature distribution on fine grids. Through numerical simulation with and without noise, compared with ART,SVD and Tikhonov, the proposed …

Data And Algorithmic Modeling Approaches To Count Data, Andraya Hack

Honors College Theses

Various techniques are used to create predictions based on count data. This type of data takes the form of a non-negative integers such as the number of claims an insurance policy holder may make. These predictions can allow people to prepare for likely outcomes. Thus, it is important to know how accurate the predictions are. Traditional statistical approaches for predicting count data include Poisson regression as well as negative binomial regression. Both methods also have a zero-inflated version that can be used when the data has an overabundance of zeros. Another procedure is to use computer algorithms, also known as …

Algebraic Graph-Assisted Bidirectional Transformers For Molecular Property Prediction, Dong Chen, Kaifu Gao, Duc Duy Nguyen, Xin Chen, Yi Jiang, Guo-Wei Wei, Feng Pan

Mathematics Faculty Publications

The ability of molecular property prediction is of great significance to drug discovery, human health, and environmental protection. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Although some machine learning models, such as bidirectional encoder from transformer, can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy, it neglects three-dimensional (3D) stereochemical information. Algebraic graph, specifically, element-specific multiscale weighted colored algebraic graph, embeds complementary 3D molecular information into graph invariants. We propose an algebraic graph-assisted bidirectional transformer (AGBT) framework by fusing representations generated by algebraic graph and bidirectional transformer, as well as …

Application Of Machine Learning Techniques To Forecast Harmful Algal Blooms In Gulf Of Mexico, Bala Tripura Sundari Yerrapothu

Master's Theses

The Harmful Algal Blooms (HABs) forecast is crucial for the mitigation of health hazards and to inform actions for the protection of ecosystems and fisheries in the Gulf of Mexico (GoM). For the sake of simplicity of our application we assume ocean color satellite imagery from the National Oceanic and Atmospheric Administration as a proxy for HABs.

In this study we use a deep neural network trained on the 2-Dimensional time series proxy data to provide a forecast of the HABs’ manifestations in the GoM.Our approach analyzes between both spatial and temporal features simultaneously. In addition, the network also helps …

A Class Of Prediction Based Adaptive Pid Controller, Yanjun Liu, Yawen Mao

Journal of System Simulation

Abstract: The PID controller has been widely used in various industrial processes. However, for real practical control plants, their mechanisms, structures and operation conditions are different, and conventional tuning methods cannot always work in a desirable state. In order to improve the robustness and the stability of the control systems, advanced PID control algorithms have been attracted much attention. A prediction based adaptive control algorithm is proposed for CARIMA models, where the PID parameters can be tuned adaptively according to the parameters of the control plant. The key is minimizing a performance index which considers the quadratic predicted output, over …

Research On Flame Radical Imaging And Extreme Learning Machine To Prediction Of Nox Emissions, Xinli Li, Li Nan, Yujia Sun, Lu Gang, Yan Yong, Liu Shi

Journal of System Simulation

Abstract: Flame radicals are crucial for an in-depth understanding of the combustion mechanisms. The spectral characteristics of flame radicals were studied based on digital imaging and feature extraction techniques. The information obtained was used to establish the extreme learning machine (ELM) model which can be used to predict the NOx emissions based on the experimental data and digital simulation from a biomass-gas-air combustion process. The digital images of four flame radicals, i.e., OH*, CN*, CH* and C₂*, were collected using an EMCCD (Electron Multiplying Charge Coupled Device) camera. The image segmentation was performed using the fuzzy C-means (FCM) …

Key Technologies Of Precaution And Prediction Of Abnormal Spatial-Temporal Trajectory: A Review Of Recent Advances, Gongda Qiu, He Ming, Yang Jie, Yuting Cao, Jihong Sun

Journal of System Simulation

Abstract: The ex-post disposition of a major incident, which is expected to transform into prediction and precaution of abnormal behavior, is increasingly unable to meet the urgent needs of the society.Therapid development and popularization of sensor network and positioning technology lay the foundation for mining spatial-temporal trajectory data. With the key objective of prediction and precaution of abnormal trajectory based on big data mining, the future research directions and prospects on trajectory clustering and recognitionareanalyzed, discussed and elaboratedinthis paper.Temporal trajectory prediction applied in prediction and precaution of abnormal spatial-temporal trajectory is also presented, providing a reference for further research on …

Topology Control Algorithm Based On Link Available Time For Cognitive Radio Network, Huaide Yang

Journal of System Simulation

Abstract: The topology changes frequently in cognitive wireless network as nodes' mobility, the main user interference, residual energy of nodes which cause link unavailable. A new topology control algorithm based on predict of link available time was proposed to resolve the problem. The algorithm forecasted link available time using probabilistic principles, and built a stable topology with longest available time links. Simulation results show that the new algorithm can take advantage of links with low mobility nodes, less interference caused by the primary user, and large remaining energy, simplify the network topology, effectively reduce the cost of the link topology …

Wind Turbine Gearing Temperature Prediction Based On Sample Optimization, Dazhong Li, Chang Cheng, Bingkun Xu

Journal of System Simulation

Abstract: Condition monitoring of wind turbine can greatly raise the operation of unit and reduce the maintenance cost. Nonlinear state estimation technique (NSET) was used to construct the behavior model of gearbox bearing temperature to complete bearing temperature prediction; grey correlation analysis method was used to verify the rationality of variable selection aiming at the lack of theoretical basis for observation vector choose; similarity analysis method was used to structure simple process memory matrix to shorten the modeling time for the data redundancy of process memory matrix. Prediction residual distribution of model will change when gear box works abnormally and …

Modeling Analysis And Prediction On Ncp Epidemic Transmission, Huaxiong Sheng, Wu Lin, Changliang Xiao

Journal of System Simulation

Abstract: The modeling analysis on the NCP (Novel Coronavirus Pneumonia) epidemic transmission before and after the closure of Wuhan is presented. On the basis of preprocessing the epidemic data, the classical SIR model and differential recurrence method are used to analyze and forecast the epidemic situation in the stage of control. The theoretical value and measured value fits well. In the stage of free transmission, the logistic model is used to compare and analyze the epidemic data five days in advance or later with the actual data to show the importance of taking the epidemic prevention measures in time. The …

Tele-Robot Control System With Online Virtual Simulation Prediction, Lingyan Hu, Kangbai Shi, Bichun Zhang, Shaoping Xu

Journal of System Simulation

Abstract: When a tele-robot with virtual simulation system works in a complicated environment, the virtual scene may not synchronize with the real one. This may cause the operator on the master side to give wrong instruction. This paper presents a tele-robot with online virtual model correction. The virtual simulation system on the master side builds a virtual model of environment and robot on the slave side. It predicts the motion of the slave robot in real time according the commands from the operator. In order to ensure the virtual scene synchronize with the real one, the measured data on the …

Chaotic Time Series Prediction Based On Gaussian Processes Mixture, Zhenjie Feng, Fan Yu

Journal of System Simulation

Abstract: Aiming at the problem that the existing learning algorithms of Gaussian processes mixture (GPM) model, such as Markov Chain Monte Carlo (MCMC), variation or leave one out, have high computational complexity, a hidden variables posterior hard-cut iterative training algorithm is proposed, which simplifies the training process of the model. The GPM model based on the proposed algorithm is applied to chaotic time series prediction. The effects of embedding dimension, time delay, learning sample number, and testing sample numbers on predictive ability are discussed. It is demonstrated by the experimental results that the prediction of the GPM model is more …

Optimization Of Material Release For Printed Circuit Board Template Based On Data Mining, Shengping Lü, Qiangsheng Yue, Liu Tao

Journal of System Simulation

Abstract: Data mining were employed for the optimization of material release of PCB (Printed Circuit Board) template. PCB scrap ratio related parameters were specified and prediction model variables were chosen according to hypothesis test. Multiple linear regression (MLR), Chi-squared automatic interaction detector, artificial neural network and support vector machine approaches for the prediction of scrap ratio were employed. Evaluation indictors called as superfluous ratio, supplement release ratio and weighted sum of the two were presented; the material release simulation was conducted and then the four approaches were compared and MLR was taken as the preferred one. Adjust coefficient …

Mlaas: Machine Learning As A Service, Mauro Ribeiro, Katarina Grolinger, Miriam Am Capretz

Electrical and Computer Engineering Publications

The demand for knowledge extraction has been increasing. With the growing amount of data being generated by global data sources (e.g., social media and mobile apps) and the popularization of context-specific data (e.g., the Internet of Things), companies and researchers need to connect all these data and extract valuable information. Machine learning has been gaining much attention in data mining, leveraging the birth of new solutions. This paper proposes an architecture to create a flexible and scalable machine learning as a service. An open source solution was implemented and presented. As a case study, a forecast of electricity demand was …

Predicting Disease Outbreaks Using A Support Vector Machine Model, Nicolae Dragu

Senior Theses and Projects

The purpose of this research is to create an efficient way of detecting disease outbreaks from news articles using Support Vector Machines (SVM). An SVM is a supervised machine learning method used for classification and regression problems. The role of the SVM in this project is to “learn” to distinguish between news articles that may indicate a disease outbreak and those that do not.

A series of health-related articles from the World Health Organization is parsed using a Java program in order to create vectors for the SVM. Each such article thus results in a vector. A basic negation detection …