Physical Sciences and Mathematics Commons^™

Geospatial Temporal Crime Prediction Using Convolution And Lstm Neural Networks: Enhancing The Las Vegas Cardiff Model, Corey D. Holmes, Christian Orji, Chris Papesh

SMU Data Science Review

According to the Department of Justice, more than half of violent crimes go unreported to law enforcement in the United States (Kollar et al., 2018). This data gap reduces the opportunity to implement proven solutions in the areas with the greatest need. In 1996, Dr. Shepherd developed the Cardiff Model with the aim of bringing together hospitals, law enforcement, and community leaders through the sharing of data. We partnered with ongoing efforts to implement the Cardiff Model in Las Vegas, Nevada. Our goal was to provide a geospatial temporal model that can predict the next 30 days of crime. By …

Pedestrian Pathing Prediction Using Complex Contextual Behavioral Data In High Foot Traffic Settings, Laurel Bingham

All Graduate Theses and Dissertations, Fall 2023 to Present

Ensuring the safe integration of autonomous vehicles into real-world environments requires a comprehensive understanding of pedestrian behavior. This study addresses the challenge of predicting the movement and crossing intentions of pedestrians, a crucial aspect in the development of fully autonomous vehicles.

The research focuses on leveraging Honda's TITAN dataset, comprising 700 unique clips captured by moving vehicles in high-foot-traffic areas of Tokyo, Japan. Each clip provides detailed contextual information, including human-labeled tags for individuals and vehicles, encompassing attributes such as age, motion status, and communicative actions. Long Short-Term Memory (LSTM) networks were employed and trained on various combinations of contextual …

Historical Perspectives In Volatility Forecasting Methods With Machine Learning, Zhiang Qiu, Clemens Kownatzki, Fabien Scalzo, Eun Sang Cha

Seaver College Research And Scholarly Achievement Symposium

Volatility forecasting in the financial market plays a pivotal role across a spectrum of disciplines, such as risk management, option pricing, and market making. However, volatility forecasting is challenging because volatility can only be estimated, and different factors influence volatility, ranging from macroeconomic indicators to investor sentiments. While recent works suggest advances in machine learning and artificial intelligence for volatility forecasting, a comprehensive benchmark of current statistical and learning-based methods for such purposes is lacking. Thus, this paper aims to provide a comprehensive survey of the historical evolution of volatility forecasting with a comparative benchmark of key landmark models. We …

Voice Synthesis Improvement By Machine Learning Of Natural Prosody, Joseph Kane, Michael N. Johnstone, Patryk Szewczyk

Research outputs 2022 to 2026

Since the advent of modern computing, researchers have striven to make the human–computer interface (HCI) as seamless as possible. Progress has been made on various fronts, e.g., the desktop metaphor (interface design) and natural language processing (input). One area receiving attention recently is voice activation and its corollary, computer-generated speech. Despite decades of research and development, most computer-generated voices remain easily identifiable as non-human. Prosody in speech has two primary components—intonation and rhythm—both often lacking in computer-generated voices. This research aims to enhance computer-generated text-to-speech algorithms by incorporating melodic and prosodic elements of human speech. This study explores a novel …

Short-Term Bus Passenger Flow Prediction Based On Convolutional Long-Short-Term Memory Network, Jing Chen, Zhaochong Zhang, Linkai Wang, Mai An, Wei Wang

Journal of System Simulation

Abstract: To address the problem that the traditional short-time passenger flow prediction method does not consider the temporal characteristics similarity between the inter-temporal passenger flows, a shorttime passenger flow prediction model k-CNN-LSTM is proposed by combining the improved k-means clustering algorithm with the CNN and the LSTM. The k-means is used to cluster the intertemporal timeseries data, the k-value is determined by using the gap-statistic, and a traffic flow matrix model is constructed. A CNN-LSTM network is used to process the short-time passenger flows with spatial and temporal characteristics. The model is tested and parameter tuned by the real dataset. …

Radiofrequency Interference Detection Using Lstmand Statistical Analysis Discriminator, Luke Smith

Masters Theses

"Wireless devices are becoming increasingly pervasive across all aspects of society. Examples of such devices include radios, routers, mobile phones, tablets, and more. As the number of radio frequency (RF) devices continues to rise, so does the amount of interference and noise increase. This is why an efficient approach to interference detection is explored. Most research within this area has been done strictly within the frequency domain as viewing a signal within this domain provides many insights into what makes the signal. This has, however, led to the time domain being underutilized for this area of research.

To explore the …

Brain-Inspired Spatio-Temporal Learning With Application To Robotics, Thiago André Ferreira Medeiros

USF Tampa Graduate Theses and Dissertations

The human brain still has many mysteries and one of them is how it encodes information. The following study intends to unravel at least one such mechanism. For this it will be demonstrated how a set of specialized neurons may use spatial and temporal information to encode information. These neurons, called Place Cells, become active when the animal enters a place in the environment, allowing it to build a cognitive map of the environment. In a recent paper by Scleidorovich et al. in 2022, it was demonstrated that it was possible to differentiate between two sequences of activations of a …

An Empirical Study On The Use Of Secure Predictive Analytics For Improving Trade Forecasting In The Uae, Asma Salem Alneyadi

Theses

Trade contributes to the United Arab Emirates' economic growth. This thesis focuses on trade dynamics in the UAE using Long Short-Term Memory (LSTM) neural networks. The study focuses on both import and export activities, providing understandings into the complex patterns and impacts of international trade on the UAE's economic growth. The research begins by constructing an LSTM model to forecast the UAE's Gross Domestic Product (GDP) through the utilization of historical trade data. We use time series data for imports and exports as key input features. This innovative approach highlights the relevance of trade statistics as a leading indicator of …

Application Of Model-Based Time Series Prediction Of Infrared Long-Wave Radiation Data For Exploring The Precursory Patterns Associated With The 2021 Madoi Earthquake, Jingye Zhang, Ke Sun, Junqing Zhu, Ning Mao, Dimitar Ouzounov

Mathematics, Physics, and Computer Science Faculty Articles and Research

Taking the Madoi M_S 7.4 earthquake of 21 May 2021 as an example, this paper proposes using time series prediction models to predict the outgoing long-wave radiation (OLR) anomalies and study short-term pre-earthquake signals. Five time series prediction models, including autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM), were trained with the OLR time series data of the aseismic moments in the 5° × 5° spatial range around the epicenter. The model with the highest prediction accuracy was selected to retrospectively predict the OLR values during the aseismic period and before the earthquake in the area. It …

Neutrosophic Adaptive Lsb And Deep Learning Hybrid Framework For Ecg Signal Classification, Abdallah Rezk, Ahmed S. Sakr, H. M. Abdulkader

Applied Mathematics & Information Sciences

This paper proposes a novel hybrid framework for ECG signal classification and privacy preservation. The framework includes two phases: the first phase uses LSTM+CNN with attention gate for ECG classification, while the second phase utilizes adaptive least signal bit with neutrosophic for hiding important data during transmission. The proposed framework converts data into three sets of degrees (true, false, and intermediate) using neutrosophic and passes them to an embedding layer. In the sender part, the framework hides important data in ECG signal as true and false degrees, using the intermediate set as a shared dynamic key between sender and receiver. …

Predictive Ai For The S&P 500 Index, Jacqueline Rose Perry

Computer Science Senior Theses

Artificial intelligence has powerful applications in virtually every field, and the financial world is no exception. Utilizing various elements of artificial intelligence, this research aims to predict the future value of the S&P 500 index using numerous models, and in doing so, identify relevant features. More specifically, models that include combinations of historical data, public sentiment, and technical indicators were employed to predict the stock price one day and three days forward. To account for public opinion, the sentiment of tweets and news headlines from the beginning of 2015 through the end of 2019 was calculated using FinBERT, a pre-trained …

Traditional Vs Machine Learning Approaches: A Comparison Of Time Series Modeling Methods, Miguel E. Bonilla Jr., Jason Mcdonald, Tamas Toth, Bivin Sadler

SMU Data Science Review

In recent years, various new Machine Learning and Deep Learning algorithms have been introduced, claiming to offer better performance than traditional statistical approaches when forecasting time series. Studies seeking evidence to support the usage of ML/DL over statistical approaches have been limited to comparing the forecasting performance of univariate, linear time series data. This research compares the performance of traditional statistical-based and ML/DL methods for forecasting multivariate and nonlinear time series.

Investigating Improvements To Mesh Indexing, Anurag Bhattacharjee

Electronic Thesis and Dissertation Repository

The MEDLINE database currently comprises an extensive collection of over 35 million citations, with more than 1 million records being added each year [28]. The abundance of information available in the database presents a significant challenge in identifying and locating relevant research articles on a given search topic. This has prompted the development of various techniques and approaches aimed at improving the efficiency and effectiveness of information retrieval from the MEDLINE database. A search engine devoted to the research publications on MEDLINE is called PubMed. MeSH, or Medical Subject Headings, is a restricted vocabulary used by PubMed to categorize each …

Trajectory Control Of Crawler Robot Based On Lstm And Smc, Dongyang Liu, Wenwen Zha, Liang Tao, Cheng Zhu, Lichuan Gu, Jun Jiao

Journal of System Simulation

Abstract: Trajectory tracking is an important part of mobile robot control technology and possesses prospect. Highly nonlinear dynamic characteristics are the main obstacles of controller design. A SMC method based on LSTM and quasi-sliding mode is proposed. The kinematics model and dynamics model of the tracked vehicle are given, and the sliding mode control system is established based on the dynamics model. LSTM network based on deep learning method is designed to control and compensate the unknown interference items, reduce the influence of external interference, and reduce the tremor phenomenon by combining the advantages of LSTM network and quasi-sliding …

Emotion Classification Of Indonesian Tweets Using Bidirectional Lstm, Aaron K. Glenn, Phillip M. Lacasse, Bruce A. Cox

Faculty Publications

Emotion classification can be a powerful tool to derive narratives from social media data. Traditional machine learning models that perform emotion classification on Indonesian Twitter data exist but rely on closed-source features. Recurrent neural networks can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that recurrent neural network variants can produce more than an 8% gain in accuracy in comparison with logistic regression and SVM techniques and a 15% gain over random forest when using FastText embeddings. This research found a statistical significance in the performance of …

Intelligent Health Care And Diseases Management System: Multi-Day-Ahead Predictions Of Covid-19, Ahed Abugabah, Farah Shahid

All Works

The rapidly growing number of COVID-19 infected and death cases has had a catastrophic worldwide impact. As a case study, the total number of death cases in Algeria is over two thousand people (increased with time), which drives us to search its possible trend for early warning and control. In this paper, the proposed model for making a time-series forecast for daily and total infected cases, death cases, and recovered cases for the countrywide Algeria COVID-19 dataset is a two-layer dropout gated recurrent unit (TDGRU). Four performance parameters were used to assess the model’s performance: mean absolute error (MAE), root …

Multimodal Learning: Generating Precise Chest X-Ray Report On Thorax Abnormality, Gaurab Subedi

Dissertations and Theses

Chronic respiratory diseases, ranking as the third leading cause of death worldwide according to the 2017 World Health Organization (WHO) report, affect a staggering 544.9 million individuals. Compounding this public health challenge is the fact that over 80% of health systems grapple with shortages in their radiology departments, highlighting an urgent need for accessible and efficient diagnostic solutions. While various image classification models for analyzing thorax abnormalities have been developed, relying solely on one type of dataset (image data, for example) for thorax abnormality analysis is insufficient. Integrating texts with image data could provide more accuracy as well as analysis. …

Rafid: A Lightweight Approach To Radio Frequency Interference Detection In Time Domain Using Lstm And Statistical Analysis, Luke A. Smith, Vishesh Kumar Tanwar, Maciej Jan Zawodniok, Sanjay Kumar Madria

Electrical and Computer Engineering Faculty Research & Creative Works

Recently, the utilization of Radio Frequency (RF) devices has increased exponentially over numerous vertical platforms. This rise has led to an abundance of Radio Frequency Interference (RFI) continues to plague RF systems today. The continued crowding of the RF spectrum makes RFI efficient and lightweight mitigation critical. Detecting and localizing the interfering signals is the foremost step for mitigating RFI concerns. Addressing these challenges, we propose a novel and lightweight approach, namely RaFID, to detect and locate the RFI by incorporating deep neural networks (DNNs) and statistical analysis via batch-wise mean aggregation and standard deviation (SD) calculations. RaFID investigates the …

Explainable Machine Learning For Evapotranspiration Prediction, Bamory Koné, Rima Grati, Bassem Bouaziz, Khouloud Boukadi

All Works

No abstract provided.

Lstm-Sdm: An Integrated Framework Of Lstm Implementation For Sequential Data Modeling[Formula Presented], Hum Nath Bhandari, Binod Rimal, Nawa Raj Pokhrel, Ramchandra Rimal, Keshab R. Dahal

Arts & Sciences Faculty Publications

LSTM-SDM is a python-based integrated computational framework built on the top of Tensorflow/Keras and written in the Jupyter notebook. It provides several object-oriented functionalities for implementing single layer and multilayer LSTM models for sequential data modeling and time series forecasting. Multiple subroutines are blended to create a conducive user-friendly environment that facilitates data exploration and visualization, normalization and input preparation, hyperparameter tuning, performance evaluations, visualization of results, and statistical analysis. We utilized the LSTM-SDM framework in predicting the stock market index and observed impressive results. The framework can be generalized to solve several other real-world time series problems.

A Data Driven Model To Promote Preparedness And Respond Intelligently To Pandemic Outbreaks, Safea Mohammed Al Senani

Theses

The COVID-19 pandemic has had a major effect on various vital sectors of the economy, including education healthcare, and the industry. Governments have imposed strict regulations to reduce the spread of this global disease outbreak. Consequently, working from home, online learning, social distancing and various control measures were enforced. In response, many schools shifted to distance learning, although most of these schools were neither technically ready nor administratively prepared for the online transition. Despite recent progress, countries are still experiencing daunting challenges to control the infection rate and magnitude, stabilize the economy, and relax socialization and public life activities. Decision-makers …

Hydrological Drought Forecasting Using A Deep Transformer Model, Amobichukwu C. Amanambu, Joann Mossa, Yin-Hsuen Chen

University Administration Publications

Hydrological drought forecasting is essential for effective water resource management planning. Innovations in computer science and artificial intelligence (AI) have been incorporated into Earth science research domains to improve predictive performance for water resource planning and disaster management. Forecasting of future hydrological drought can assist with mitigation strategies for various stakeholders. This study uses the transformer deep learning model to forecast hydrological drought, with a benchmark comparison with the long short-term memory (LSTM) model. These models were applied to the Apalachicola River, Florida, with two gauging stations located at Chattahoochee and Blountstown. Daily stage-height data from the period 1928–2022 were …

Stock Forecasts With Lstm And Web Sentiment, Michael Burgess, Faizan Javed, Nnenna Okpara, Chance Robinson

SMU Data Science Review

Traditional time-series techniques, such as auto-regressive and moving average models, can have difficulties when applied to stock data due to the randomness inherent to the markets. In this study, Long Short-Term Memory Recurrent Neural Networks, or LSTMs, have been applied to pricing data along with sentiment scores derived from web sources such as Twitter and other financial media outlets. The project team utilized this approach to complement the technical indicators observed at the end of each trading day for three stocks from the NASDAQ stock exchange over a 12-year span. A common benchmark to assess model performance on time series …

Predicting Insulin Pump Therapy Settings, Riccardo L. Ferraro, David Grijalva, Alex Trahan

SMU Data Science Review

Millions of people live with diabetes worldwide [7]. To mitigate some of the many symptoms associated with diabetes, an estimated 350,000 people in the United States rely on insulin pumps [17]. For many of these people, how effectively their insulin pump performs is the difference between sleeping through the night and a life threatening emergency treatment at a hospital. Three programmed insulin pump therapy settings governing effective insulin pump function are: Basal Rate (BR), Insulin Sensitivity Factor (ISF), and Carbohydrate Ratio (ICR). For many people using insulin pumps, these therapy settings are often not correct, given their physiological needs. While …

A New Approach For Congestive Heart Failure And Arrhythmia Classification Using Downsampling Local Binary Patterns With Lstm, Süleyman Akdağ, Fatma Kuncan, Yilmaz Kaya

Turkish Journal of Electrical Engineering and Computer Sciences

Electrocardiogram (ECG) is a vital diagnosis approach for the rapid explication and detection of various heart diseases, especially cardiac arrest, sinus rhythms, and heart failure. For this purpose, in this study, a different perspective based on downsampling one-dimensional-local binary pattern (1D-DS-LBP) and long short-term memory (LSTM) is presented for the categorization of Electrocardiogram (ECG) signals. A transformation method named 1DDS-LBP has been presented for Electrocardiogram signals. The 1D-DS-LBP method processes the bigness smallness relationship between neighbors. According to the proposed method, by downsampling the signal, the histograms of 1D local binary patterns (1D-LBP) calculated from the obtained signal groups are …

Diacritics Correction In Turkish With Context-Aware Sequence To Sequence Modeling, Asi̇ye Tuba Özge, Özge Bozal, Umut Özge

Turkish Journal of Electrical Engineering and Computer Sciences

Digital texts in many languages have examples of missing or misused diacritics which makes it hard for natural language processing applications to disambiguate the meaning of words. Therefore, diacritics restoration is a crucial step in natural language processing applications for many languages. In this study we approach this problem as bidirectional transformation of diacritical letters and their ASCII counterparts, rather than unidirectional diacritic restoration. We propose a context-aware character-level sequence to sequence model for this transformation. The model is language independent in the sense that no language-specific feature extraction is necessary other than the utilization of word embeddings and is …

Simultaneous Energy Harvesting And Gait Recognition Using Piezoelectric Energy Harvester, Dong Ma, Guohao Lan, Weitao Xu, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

Piezoelectric energy harvester, which generates electricity from stress or vibrations, is gaining increasing attention as a viable solution to extend battery life in wearables. Recent research further reveals that, besides generating energy, PEH can also serve as a passive sensor to detect human gait power-efficiently because its stress or vibration patterns are significantly influenced by the gait. However, as PEHs are not designed for precise measurement of motion, achievable gait recognition accuracy remains low with conventional classification algorithms. The accuracy deteriorates further when the generated electricity is stored simultaneously. To classify gait reliably while simultaneously storing generated energy, we make …

Integrating Deep Learning And Hydrodynamic Modeling To Improve The Great Lakes Forecast, Pengfei Xue, Aditya Wagh, Gangfeng Ma, Yilin Wang, Yongchao Yang, Tao Liu, Chenfu Huang

Michigan Tech Publications

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, …

Deeprobot: A Hybrid Deep Neural Network Model For Social Bot Detection Based On User Profile Data, Kadhim Hayawi, Sujith Mathew, Neethu Venugopal, Mohammad M. Masud, Pin Han Ho

All Works

Use of online social networks (OSNs) undoubtedly brings the world closer. OSNs like Twitter provide a space for expressing one’s opinions in a public platform. This great potential is misused by the creation of bot accounts, which spread fake news and manipulate opinions. Hence, distinguishing genuine human accounts from bot accounts has become a pressing issue for researchers. In this paper, we propose a framework based on deep learning to classify Twitter accounts as either ‘human’ or ‘bot.’ We use the information from user profile metadata of the Twitter account like description, follower count and tweet count. We name the …

Integrating Deep Learning And Hydrodynamic Modeling To Improve The Great Lakes Forecast, Pengfei Xue, Aditya Wagh, Gangfeng Ma, Yilin Wang, Yongchao Yang, Tao Liu, Chenfu Huang

Civil & Environmental Engineering Faculty Publications

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, …