TTU Published Journals @ Volpe Library
Not a member yet
971 research outputs found
Sort by
*WINNER* An investigation of the factor structure and psychometric properties of the Adverse Childhood Experiences scale in college students
No full textThe purpose of this study was to examine the psychometric properties of the Adverse Childhood Experiences scale through exploratory and confirmatory factor analyses with a sample of college students (N=354). Health care professionals are being encouraged by the CDC to utilize the ACEs inventory to assess for negative events in childhood as the results are associated with physical and mental health concerns later in life. A 1-factor scale that sums an overall total score is commonly employed. Utilizing SPSS and AMOS software, the researchers compared a 1-, 2-, and 3-factor structure of the scale as theorized in a literature review. The results indicated a 3-factor model of abuse, neglect, and household dysfunction had the best overall model fit indices. A discussion on the conceptual transition from a 1-factor to a 3-factor scale and accompanying implications about scoring and interpretation is provided. Limitations and areas for future research are also expounded
Finding Patterns in The Music City
No full textAs we enter the waning side of the COVID-19 pandemic, global tourism and traveling has begun to grow again. Between 2020 and 2021, global tourism raised 4% from 400 million to 415 million. The United States saw almost 20 million international travelers during the pandemic. Including domestic travelers, tourism is a pillar for our economy. With tourism, finding a place to stay is crucial to any trip. With 7 million listings found across the world, AirBnB enables tourists to rent accommodations in specific locales. Using the Nashville 2021 dataset found at InsideAirbnb, we can apply data mining and machine learning techniques to aide the tourism industry. The dataset offers geo-location of every Airbnb in Nashville, along with the price and minimum stay length. Our first approach, we use regression to predict prices given different features about the Airbnb. The accuracy of the predictions are compared to the original, and are given a rating based on the comparison. Our second approach acts as a "related" recommender. Using clustering techniques, we explore the capability to discover similarities between Airbnbs, and suggest similar ones to the tourist. For the second data subset, sentiment analysis and word frequency is used on individual Airbnb's comments. We then build a "average sentiment" value to summarize the comments. Word frequency is used to figure out what common words are used across reviews for an Airbnb
Detecting Cyber Attacks using the Matrix Profile
No full textCyber-attacks have been increasing in recent years and are becoming a threat to IoT infrastructures. Anomaly Detection can detect the attacks earlier and form an early warning system. In this work, the overall goal is to detect Denial of Service (DoS) attacks aimed against a Smart Farming Infrastructure. We are using the Matrix Profile (MP) for anomaly detection on network traffic data that has been collected during a deauthentication attack. The MP is a data structure developed by Eamonn Keogh for time series analysis. While past work has used machine learning anomaly detection approaches such as Autoencoder on network traffic, no other work has applied the MP on network traffic data for anomaly detection of cyber-attacks. Since the dataset is labeled, we will evaluate our method using standard anomaly detection metrics including accuracy, precision, F1, and recall
Predicting Board Game Ratings
No full textIn this project, we are going to look at data about board games, taken from Kaggle. Our objective is to examine and classify board game data using multiple classification and clustering techniques. We will train our models on the provided data set, and then run the models to attempt to answer the following questions: What criteria makes it successful: money made, amount sold, number of people who bought, number of positive reviews, etc.? Is there a relationship between the volume sold to the number of reviews of the game? We will also look at other related questions. The goal of this is to help predict a board game's performance and rating to potentially help determine if the board game will be a success and worth pursuing or not
Data Profiling Phishing URLs to Find the Most Impactful Attributes
No full textPhishing is a common form of social engineering attack where an attacker crafts a malicious link, under the guise of a reputable source, that ultimately leads to a fraudulent website. The purpose of the fake website is to trick the user into entering personal or sensitive information, like account credentials, credit card numbers, or bank details. Phishing websites are becoming increasingly sophisticated and difficult to spot, especially due to the lack of user security training in most cases. Therefore, it is important to identify the most common attributes associated with the fraudulent URLs utilized in phishing attacks. A simple way to do this is data profiling, or reviewing source data, examining the structure and content, and identifying useful points to summarize the whole. This paper will utilize data profiling to analyze multiple phishing website datasets and locate the most impactful and easily identifiable features for recognizing if a URL is legitimate or not. The features found should be able to assist security professionals and nonprofessionals alike in identifying phishing websites
Joint Fault and Intrusion Detection For Industrial Internet of Things Sensing Environments
No full textThis on-going project aims to develop an Industrial Internet of Things (IIoT) testbed for undergraduate research and education. As Industry 4.0 becomes increasingly adopted in the mainstream factory environment, the burden of managing the physical sensing is placed upon the factory's network, presenting great information security risk as these IIoT devices are often significantly less secure than typical network nodes. With this research we provide a methodology for the implementation of insecure sensor devices in fault detection and isolation (FDI) while preserving the integrity of the environmental data in the event of network intrusion. This methodology will first determine if network intrusions influence data integrity through statistical analysis. Threshold and machine learning detection methods will be used to discover intruded datapoints and remove or remedy them before they enter the FDI systems. This research plans to show that defending against these intrusions is possible in the worst-case scenario, where only the telemetry data is available to detect from. Protecting the input into the FDI system is crucial. As reliance upon FDI systems, allowing them greater control over the factory environment, increases, the potential production risk due to intrusion increases in tandem. The current version of the testbed can retrieve single data telemetry from thermocouple and humidity sensors and display the output through a webpage and downloadable csv file
*WINNER* Using Graph-based Knowledge Discovery to Detect Anomalous Patterns in Crime Data
No full textThe naive approach to law enforcement is purely reaction-based. However, more effective preemption of criminal acts is made possible by analyzing datasets comprised of previous incidents; attributes such as time, location, and other specifics of the event serve as crucial details for predicting reoccurrence. Graphs are an appropriate approach for representing these elements, as they can provide structure and emphasize relationships that other techniques may fail to. In addition, graphs can highlight an underlying hierarchy between subjects if one is present. In particular, the Tucson Police Department has made their recent crime archives publicly available. Data from 2018 until the present is readily downloadable for modification, cleaning, and analysis. This dataset will allow data scientists to supplement law enforcement with predictive tools and a clearer picture of the threats they face. This, in turn, will help the TPD allocate resources where they are needed most
Hair Analysis: an Investigation into its Scientific Validity
No full textHair analysis has been a widely used forensic technique since the mid-20th century. One of the most common sources of evidence in a crime scene is from hair. As such, hair analysis has been used to convict many. This method is flawed, however. There has not been a consistent set of criteria for comparison, and no scientific knowledge of the frequency of occurrences of certain characteristics in hair. As a result, this technique has fallen under controversy in the past few decades. This project aims to investigate the forensic technique of hair analysis through a variety of means. In particular, the history of its use, the science behind it, its flaws, and its use in the present day will be examined. In conducting this study, one can identify issues and suggest methods to improve the scientific validity of hair analysis as a technique
Covid-19 and the effects of mental and physical health of school-aged children
No full textThe topic of this project is Covid-19's effect on school-aged children's mental and physical health. The problem is children were put at risk causing their mental and physical health to suffer. The purpose of this project is to explore how Covid-19 allegedly led to the decline in school-aged children's mental and physical health. The key words Covid-19, school-aged children, mental and physical health were used on Tennessee Tech's Eagle Search. I chose the articles based on the abstract information relating to my topic. The excluded articles did not meet the criteria based on key words such as non-school aged children. The participants in the reviewed studies were school-aged children six to 12 years of age from different ethnicity with random and convenience being the sampling. One of the most important findings was to prioritize mental health interventions for school-aged children by setting routines. This helps their physical activity because otherwise they are more likely to sleep and take advantage of screen time. Also, children who worry about being affected by Covid-19 are likely at risk for having depression symptoms. The implications of these findings show the need for routine to protect school-aged children's mental and physical health. School systems and parents at home need interventions for school-aged children's mental health needs to ensure that these children's physical and mental health don't suffer
Ways in Which Identifying as LGBTQ+ Affects Mental Health
No full textThe focus of this project is investigating ways in which identifying as LBGTQ+ affects youths' mental health. The purpose of this project was exploring how identifying as LGBTQ+ affects youths' mental health. The criteria used to select the studies was using these keywords: LGBTQ+, high school, lesbian, gay, and depression. I primarily used the Eagle Search Database to locate articles. Selected articles included relevant information for this project. The participants in identified studies were youth between 14 and 17 years old who identified as LGBTQ+. The participants were chosen randomly from the academic categories of homeschooled, attending public school, and attending private school. The housing categories chosen from were homeless, living with their biological family, and living with a foster family. The three most important findings from studies used were 1. youth who identify as LGBTQ+ need support from the people who are around them 2.the stigma that LGBTQ+ youth face leads to an increased suicide rate, and 3.inclusion for LGBTQ+ youth can make a positive impact on mental health. The implication of these results was that LGBTQ+ youth need more inclusion and understanding from the people around them (teachers, peers, parents, and community members). This is important because it creates a foundation on which we can use to lower suicide rates among youth who identify as LGBTQ+ and be allies to things we have yet to understand