Data Science Commons^™

Learning Transferrable Parameters For Long-Tailed Sequential User Behavior Modeling, Jianwen Yin, Chenghao Liu, Weiqing Wang, Jianling Sun, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising. The performance of sequential modeling heavily depends on the scale and quality of historical behaviors. However, the number of user behaviors inherently follows a long-tailed distribution, which has been seldom explored. In this work, we argue that focusing on tail users could bring more benefits and address the long tails issue by learning transferrable parameters from both optimization and feature perspectives. Specifically, we propose a gradient alignment optimizer and adopt an adversarial training scheme to facilitate knowledge transfer …

A Novel Path Loss Forecast Model To Support Digital Twins For High Frequency Communications Networks, James Marvin Taylor Jr.

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

The need for long-distance High Frequency (HF) communications in the 3-30 MHz frequency range seemed to diminish at the end of the 20th century with the advent of space-based communications and the spread of fiber optic-connected digital networks. Renewed interest in HF has emerged as an enabler for operations in austere locations and for its ability to serve as a redundant link when space-based and terrestrial communication channels fail. Communications system designers can create a “digital twin” system to explore the operational advantages and constraints of the new capability. Existing wireless channel models can adequately simulate communication channel conditions with …

Combining Machine Learning And Empirical Engineering Methods Towards Improving Oil Production Forecasting, Andrew J. Allen

Master's Theses

Current methods of production forecasting such as decline curve analysis (DCA) or numerical simulation require years of historical production data, and their accuracy is limited by the choice of model parameters. Unconventional resources have proven challenging to apply traditional methods of production forecasting because they lack long production histories and have extremely variable model parameters. This research proposes a data-driven alternative to reservoir simulation and production forecasting techniques. We create a proxy-well model for predicting cumulative oil production by selecting statistically significant well completion parameters and reservoir information as independent predictor variables in regression-based models. Then, principal component analysis (PCA) …

Query Rewriting With Thesaurus-Based For Handling Semantic Heterogeneity In Database Integration, I Made Riyan Adi Nugroho, I Wayan Budi Sentana

Knowledge Engineering and Data Science

Nowadays, studies on handling semantic heterogeneity still become a challenge for researcher. Several methods have been used to solve these problems, one of which is query rewriting, implemented by rewriting a query into the latest one by using the selected schema. Semantic query rewriting needs a framework in order to identify the connection through the data schema sources. This line is used as a basis for scheme selection. Also, ontology is a model which often be used in these specific cases. The lack of ontology becomes a significant problem that usually seen. Therefore, this paper will describe an alternative framework …

Flood Prediction Using Artificial Neural Networks: Empirical Evidence From Mauritius As A Case Study, A. Z. Dhunny, Reena H. Seebocus, Z. Allam, Mohammad Yasser Chuttur

Knowledge Engineering and Data Science

Artificial Neural Networks (ANN) has been well studied for flood prediction. However, there is not enough empirical evidence to generalize ANN applicability to small countries with microclimates prevailing in a small geographical space. In this paper, we focus on the climatic conditions of Mauritius for which we seek to investigate the accuracy of using ANN to predict flooding using locally collected data from 11 meteorological stations spread across the country. The ANN model for flood prediction presented in this work is trained using 20,000 climate data records, collected over a period of two years for Mauritius. Our input climate features …

Human Intestinal Condition Identification Based-On Blended Spatial And Morphological Feature Using Artificial Neural Network Classifier, Ummi Athiyah, Arif Wirawan Muhammad, Ahmad Azhari

Knowledge Engineering and Data Science

Colon cancer is a type of disease that attacks the intestinal walls cell of humans. Colorectal endoscopic screening technique is a common step carried out by the health expert/gynecologist to determine the condition of the human intestine. Manual interpretation requires quite a long time to reach a result. Along with the development of increasingly advanced digital computing techniques, then some of the weaknesses of the manually endoscopic image interpretation analysis model can be corrected by automating the detection process of the presence or absence of cancerous cells in the gut. Identification of human intestinal conditions using an artificial neural network …

Earthquake Magnitude And Grid-Based Location Prediction Using Backpropagation Neural Network, Bagus Priambodo, Wayan Firdaus Mahmudy, Muh Arif Rahman

Knowledge Engineering and Data Science

Earthquakes, a type of inevitable natural disaster, is responsible for the highest average death toll per year compared to other types of a natural disaster. Even though it is inevitable, but it can be anticipated to minimize damage and casualties, such as predicting the earthquake‘s magnitude using a neural network. In this study, a backpropagation algorithm is used to train the multilayer neural network to weekly predict the average magnitude of earthquakes in grid-based locations in Indonesia. Based on the findings in this research, the neural network is able to predict the magnitude of earthquakes in grid-based locations across Indonesia …

Parallelization Of Partitioning Around Medoids (Pam) In K-Medoids Clustering On Gpu, Adhi Prahara, Dewi Pramudi Ismi, Ahmad Azhari

Knowledge Engineering and Data Science

K-medoids clustering is categorized as partitional clustering. K-medoids offers better result when dealing with outliers and arbitrary distance metric also in the situation when the mean or median does not exist within data. However, k-medoids suffers a high computational complexity. Partitioning Around Medoids (PAM) has been developed to improve k-medoids clustering, consists of build and swap steps and uses the entire dataset to find the best potential medoids. Thus, PAM produces better medoids than other algorithms. This research proposes the parallelization of PAM in k-medoids clustering on GPU to reduce computational time at the swap step of PAM. The parallelization …

Opinion Analysis For Emotional Classification On Emoji Tweets Using The Naïve Bayes Algorithm, Siti Sendari, Ilham Ari Elbaith Zaeni, Dian Candra Lestari, Hanny Prasetya Hariyadi

Knowledge Engineering and Data Science

Opinion Analysis is a research study needed to social media, since the content could become a trending topic and has a significant impact on social life. One of the social media that have a big contribution to cyberspace and information development is Twitter. In the Twitter application, users can insert images that represent emotions, facial expressions, or icons. Emoji is a graphic symbol in the form of an image to express a thing, with the Emoji, a text can be read and understood according to its meaning because the image represents it. Of the several things that have been mentioned …

Automatic Delamination Segmentation For Bridge Deck Based On Encoder-Decoder Deep Learning Through Uav-Based Thermography, Chongsheng Cheng, Zhexiong Shang, Zhigang Shen

Department of Construction Engineering and Management: Faculty Publications

Concrete deck delamination often demonstrates strong variations in size, shape, and temperature distribution under the influences of outdoor weather conditions. The strong variations create challenges for pure analytical solutions in infrared image segmentation of delaminated areas. The recently developed supervised deep learning approach demonstrated the potentials in achieving automatic segmentation of RGB images. However, its effectiveness in segmenting thermal images remains under-explored. The main challenge lies in the development of specific models and the generation of a large range of labeled infrared images for training. To address this challenge, a customized deep learning model based on encoder-decoder architecture is proposed …

Utilizing Neural Networks And Wearables To Quantify Hip Joint Angles And Moments During Walking And Stair Ascent, Megan V. Mccabe

ENGS 88 Honors Thesis (AB Students)

Wearable sensors were leveraged to develop two methods for computing hip joint angles and moments during walking and stair ascent that are more portable than the gold standard. The Insole-Standard (I-S) approach replaced force plates with force-measuring insoles and achieved results that match the curvature of results from similar studies. Peaks in I-S kinetic results are high due to error induced by applying the ground reaction force to the talus. The Wearable-ANN (W-A) approach combines wearables with artificial neural networks to compute the same results. Compared against the I-S, the W-A approach performs well (average rRMSE = 18%, R^{2 …}

Mining User-Generated Content Of Mobile Patient Portal: Dimensions Of User Experience, Mohammad Al-Ramahi, Cherie Noteboom

Research & Publications

Patient portals are positioned as a central component of patient engagement through the potential to change the physician-patient relationship and enable chronic disease self-management. The incorporation of patient portals provides the promise to deliver excellent quality, at optimized costs, while improving the health of the population. This study extends the existing literature by extracting dimensions related to the Mobile Patient Portal Use. We use a topic modeling approach to systematically analyze users’ feedback from the actual use of a common mobile patient portal, Epic’s MyChart. Comparing results of Latent Dirichlet Allocation analysis with those of human analysis validated the extracted …

Using Case-Level Context To Classify Cancer Pathology Reports, Shang Gao, Mohammed Alawad, Noah Schaefferkoetter, Lynne Penberthy, Xiao-Cheng Wu, Eric B. Durbin, Linda Coyle, Arvind Ramanathan, Georgia Tourassi

Kentucky Cancer Registry Faculty Publications

Individual electronic health records (EHRs) and clinical reports are often part of a larger sequence-for example, a single patient may generate multiple reports over the trajectory of a disease. In applications such as cancer pathology reports, it is necessary not only to extract information from individual reports, but also to capture aggregate information regarding the entire cancer case based off case-level context from all reports in the sequence. In this paper, we introduce a simple modular add-on for capturing case-level context that is designed to be compatible with most existing deep learning architectures for text classification on individual reports. We …

Development Of Fully Balanced Ssfp And Computer Vision Applications For Mri-Assisted Radiosurgery (Mars), Jeremiah Sanders

Dissertations and Theses (Open Access)

Prostate cancer is the second most common cancer in men and the second-leading cause of cancer death in men. Brachytherapy is a highly effective treatment option for prostate cancer, and is the most cost-effective initial treatment among all other therapeutic options for low to intermediate risk patients of prostate cancer. In low-dose-rate (LDR) brachytherapy, verifying the location of the radioactive seeds within the prostate and in relation to critical normal structures after seed implantation is essential to ensuring positive treatment outcomes.

One current gap in knowledge is how to simultaneously image the prostate, surrounding anatomy, and radioactive seeds within the …

Subsurface Analytics: Contribution Of Artificial Intelligence And Machine Learning To Reservoir Engineering, Reservoir Modeling, And Reservoir Management, Shahab D. Mohaghegh

Faculty & Staff Scholarship

Subsurface Analytics is a new technology that changes the way reservoir simulation and modeling is performed. Instead of starting with the construction of mathematical equations to model the physics of the fluid flow through porous media and then modification of the geological models in order to achieve history match, Subsurface Analytics that is a completely AI-based reservoir simulation and modeling technology takes a completely different approach. In AI-based reservoir modeling, field measurements form the foundation of the reservoir model. Using data-driven, pattern recognition technologies; the physics of the fluid flow through porous media is modeled through discovering the best, most …

Neural Network Pruning For Ecg Arrhythmia Classification, Isaac E. Labarge

Master's Theses

Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made in effectively reducing these overheads by pruning and compressing large CNNs with only a slight decline in model accuracy. In this study, two pruning methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a pruning phase interleaved with a finetuning phase. It is shown that when performing the scale-factor pruning …

Efficient Model-Data Integration For Flexible Modeling, Parameter Analysis & Visualization, And Data Management, Angela Gregory, Chao Chen, Rui Wi, Sarah Miller, Sajjad Ahmad, John W. Anderson, Hays Berrett, Karl Benedict, Dan Cadol, Sergiu M. Dascalu, Donna Delparte, Lynn Fenstermaker, Sarah Godsey, Frederick C. Harris Jr., James P. Mcnamara, Scott W. Tyler, John Savickas, Luke Sheneman, Mark Stone, Matthew A. Turner

Civil and Environmental Engineering and Construction Faculty Research

Due to the complexity and heterogeneity inherent to the hydrologic cycle, the modeling of physical water processes has historically and inevitably been characterized by a broad spectrum of disciplines including data management, visualization, and statistical analyses. This is further complicated by the sub-disciplines within the water science community, where specific aspects of water processes are modeled independently with simplification and model boundary integration receiving little attention. This can hinder current and future research efforts to understand, explore, and advance water science. We developed the Virtual Watershed Platform to improve understanding of hydrologic processes and more generally streamline model-data integration and …

Differential Privacy Techniques For Cyber Physical Systems: A Survey, Muneeb Ul Hassan, Mubashir Husain Rehmani, Jinjun Chen

Publications

Modern cyber physical systems (CPSs) has widely being used in our daily lives because of development of information and communication technologies (ICT).With the provision of CPSs, the security and privacy threats associated to these systems are also increasing. Passive attacks are being used by intruders to get access to private information of CPSs. In order to make CPSs data more secure, certain privacy preservation strategies such as encryption, and k-anonymity have been presented in the past. However, with the advances in CPSs architecture, these techniques also need certain modifications. Meanwhile, differential privacy emerged as an efficient technique to protect CPSs …

Algorithm Selection Framework: A Holistic Approach To The Algorithm Selection Problem, Marc W. Chalé

Theses and Dissertations

A holistic approach to the algorithm selection problem is presented. The “algorithm selection framework" uses a combination of user input and meta-data to streamline the algorithm selection for any data analysis task. The framework removes the conjecture of the common trial and error strategy and generates a preference ranked list of recommended analysis techniques. The framework is performed on nine analysis problems. Each of the recommended analysis techniques are implemented on the corresponding data sets. Algorithm performance is assessed using the primary metric of recall and the secondary metric of run time. In six of the problems, the recall of …

An Analysis Of Learning Curve Theory & Diminishing Rates Of Learning, Dakotah W. Hogan

Theses and Dissertations

Traditional learning curve theory assumes a constant learning rate regardless of the number of units produced; however, a collection of theoretical and empirical evidence indicates that learning rates decrease as more units are produced in some cases. These diminishing learning rates cause traditional learning curves to underestimate required resources, potentially resulting in cost overruns. A diminishing learning rate model, Boones Learning Curve (2018), was recently developed to model this phenomenon. This research confirmed that Boones Learning Curve is more accurate in modeling observed learning curves using production data of 169 Department of Defense end-items. However, further empirical analysis revealed deficiencies …

Edge-Cloud Computing For Iot Data Analytics: Embedding Intelligence In The Edge With Deep Learning, Ananda Mohon M. Ghosh, Katarina Grolinger

Electrical and Computer Engineering Publications

Rapid growth in numbers of connected devices including sensors, mobile, wearable, and other Internet of Things (IoT) devices, is creating an explosion of data that are moving across the network. To carry out machine learning (ML), IoT data are typically transferred to the cloud or another centralized system for storage and processing; however, this causes latencies and increases network traffic. Edge computing has the potential to remedy those issues by moving computation closer to the network edge and data sources. On the other hand, edge computing is limited in terms of computational power and thus is not well suited for …

Deep Learning For Load Forecasting With Smart Meter Data: Online Adaptive Recurrent Neural Network, Mohammad Navid Fekri, Harsh Patel, Katarina Grolinger, Vinay Sharma

Electrical and Computer Engineering Publications

No abstract provided.

Disaster Damage Categorization Applying Satellite Images And Machine Learning Algorithm, Farinaz Sabz Ali Pour, Adrian Gheorghe

Engineering Management & Systems Engineering Faculty Publications

Special information has a significant role in disaster management. Land cover mapping can detect short- and long-term changes and monitor the vulnerable habitats. It is an effective evaluation to be included in the disaster management system to protect the conservation areas. The critical visual and statistical information presented to the decision-makers can help in mitigation or adaption before crossing a threshold. This paper aims to contribute in the academic and the practice aspects by offering a potential solution to enhance the disaster data source effectiveness. The key research question that the authors try to answer in this paper is how …

Speech Mode Classification Using The Fusion Of Cnns And Lstm Networks, Pratyusha Chowdary Vakkantula

Graduate Theses, Dissertations, and Problem Reports (ETD)

Speech mode classification is an area that has not been as widely explored in the field of sound classification as others such as environmental sounds, music genre, and speaker identification. But what is speech mode? While mode is defined as the way or the manner in which something occurs or is expressed or done, speech mode is defined as the style in which the speech is delivered by a person.

There are some reports on speech mode classification using conventional methods, such as whispering and talking using a normal phonetic sound. However, to the best of our knowledge, deep learning-based …

Neural Network Classification Of Brainwave Alpha Signalsin Cognitive Activities, Ahmad Azhari, Adhi Susanto, Andri Pranolo, Yingchi Mao

Knowledge Engineering and Data Science

The signal produced by human brain waves is one unique feature. Signals carry information and are represented in electrical signals generated from the brain in a typical waveform. Human brain wave activity will always be active even when sleeping. Brain waves will produce different characteristics in different individuals. Physical and behavioral characteristics can be identified from patterns of brain wave activity. This study aims to distinguish signals from each individual based on the characteristics of alpha signals from brain waves produced. Brain wave signals are generated by giving several mental perception tasks measured using an Electroencephalogram (EEG). To get different …

Optimisation Of Rice Fertiliser Composition Using Genetic Algorithms, Retno Dewi Anissa, Wayan Firdaus Mahmudy, Agus Wahyu Widodo

Knowledge Engineering and Data Science

There are so many problems with food scarcity. One of them is not too good rice quality. So, an enhancement in rice production through an optimal fertiliser composition. Genetic algorithm is used to optimise the composition for a more affordable price. The process of genetic algorithm is done by using a representation of a real code chromosome. The reproduction process using a one-cut point crossover and random mutation, while for the selection using binary tournament selection process for each chromosome. The test results showed the optimum results are obtained on the size of the population of 10, the crossover rate …

Handwriting Character Recognition Usingvector Quantization Technique, Haviluddin Haviluddin, Rayner Alfred, Ni’Mah Moham, Herman Santoso Pakpahan, Islamiyah Islamiyah, Hario Jati Setyadi

Knowledge Engineering and Data Science

This paper seeks to explore Learning Vector Quantization (LVQ) processing stage to recognize The Buginese Lontara script from Makassar as well as explaining its accuracy. The testing results of LVQ obtained an accuracy degree of 66.66 %. The most optimal variant of network architecture in the recognition process is a variation of learning rate of 0.02, a maximum epoch of 5000 and a hidden layer of 90 neurons which was the result of recognition based on feature 8. Based on these variations, the obtained performance with a mean square error (MSE) of 0.0306 and the time required during the learning …

Comparison Of Indonesian Imports Forecastingby Limited Period Using Sarima Method, Harits Ar Rosyid, Mutyara Whening Aniendya, Heru Wahyu Herwanto

Knowledge Engineering and Data Science

The development of Indonesia's imports fluctuate over years. Inability to anticipate such rapid changes can cause economic slump due to inappropriate policy. For instance, recent years imports in rice led to the extermination of rice reserves. The reason is to maintain the market price of rice in Indonesia. To overcome these changes, forecasting the amount of imports should assist the Government in determining the optimum policy. This can be done by utilizing an algorithm to forecast time series data, in this case the amount of imports in the next few months with a high degree of accuracy. This study uses …

Comparison Of Naïve Bayes Algorithm And Decision Tree C4.5for Hospital Readmission Diabetes Patientsusing Hba1c Measurement, Utomo Pujianto, Asa Luki Setiawan, Harits Ar Rosyid, Ali M. Mohammad Salah

Knowledge Engineering and Data Science

Diabetes is a metabolic disorder disease in which the pancreas does not produce enough insulin or the body cannot use insulin produced effectively. The HbA1c examination, which measures the average glucose level of patients during the last 2-3 months, has become an important step to determine the condition of diabetic patients. Knowledge of the patient's condition can help medical staff to predict the possibility of patient readmissions, namely the occurrence of a patient requiring hospitalization services back at the hospital. The ability to predict patient readmissions will ultimately help the hospital to calculate and manage the quality of patient care. …

The Application Of Gray-Scale Level-Set Method In Segmentation Of Concrete Deck Delamination Using Infrared Images, Chongsheng Cheng, Zhigang Shen

Department of Construction Engineering and Management: Faculty Publications

Conventional nondestructive delamination detection of concrete pavements through thermography is often based on temperature contrasts between delaminated and sound areas. Non-uniform backgrounds caused by the environmental conditions are often challenging for contrast-based methods to robustly differentiate the delaminated areas from the sound areas. Instead of focusing on the temperature contrast, this study proposes a temperature gradient-based level set method (LSM) to detect boundaries for delamination segmentations. A modified edge indicator function is developed to represent the normalized temperature gradient of a thermal image. The experimental study was conducted to evaluate its applicability and stability for boundary detection in terms of …