Physical Sciences and Mathematics Commons^™

Ethics And Bias In Machine Learning: A Technical Study Of What Makes Us “Good”, Ashley Nicole Shadowen

Student Theses

The topic of machine ethics is growing in recognition and energy, but bias in machine learning algorithms outpaces it to date. Bias is a complicated term with good and bad connotations in the field of algorithmic prediction making. Especially in circumstances with legal and ethical consequences, we must study the results of these machines to ensure fairness. This paper attempts to address ethics at the algorithmic level of autonomous machines. There is no one solution to solving machine bias, it depends on the context of the given system and the most reasonable way to avoid biased decisions while maintaining the …

Study Of Self-Similarity In Brain Data, Jennifer Holst

Student Theses

In the area of computer science, past research has found that the concept of self-similarity is present in local and Internet-based network traffic. This study considers the possibility that data traveling through the neuronal network in the human brain is also self-similar. By analyzing publicly available raw EEG data and estimating its Hurst parameter, we find indications that brain data traffic may in fact be self-similar.

Digital Anti-Forensics: An Implementation And Examination, Stephanie Dachs

Student Theses

The rise of computer use and technical adeptness by the general public in the last two decades are undeniable. With greater use comes a greater possibility for misuse, evidenced by today’s incredible number of crimes involving computers as well as the growth in severity from that of cyber hooliganism to cyber warfare. Although frequently utilized for privacy and security purposes, the vast range of anti-forensic techniques has contributed to the ability for hackers and criminals to obstruct computer forensic investigations.

Understanding how anti-forensics may alter important and relevant data on an electronic device will prove useful for the success and …

The Quantification Of Cocaine From The Erythroxylum Coca Plant And The Comparison On High Performance Liquid Chromatography And Gas Chromatography Mass Spectroscopy As An Analytical Method., Tuesday James

Student Theses

Cocaine is derived from the Erythroxylum coca plant, is a highly addictive stimulant abused all over the world. There are two types of Erythroxylum coca plants that produce cocaine; the E. Coca and E. Novogranatense. Cocaine exists as the salt, and the freebase which is typically referred to as “crack” due to the crackling sound it makes when heated. It is popular because it is inexpensive and easily available on the streets, mainly in poor urban areas. The purpose of this project was to determine the amount of cocaine that can be extracted from E.coca and to assess which analytical …

Detection Of Cathinone And Mephedrone In Plasma By Lc-Ms/Ms Using Standard Addition Quantification Technique, Theron W. Ng-A-Qui

Student Theses

Designer drugs are structural analogs of Drug Enforcement Agency (DEA) Schedule I and II substances. They are synthesized to mimic the effects of illegal drugs of abuse and to bypass the provisions of drug regulations. Despite the increased availability of designer drugs, few studies have focused on specific analytical extraction techniques for their detection and quantification in biological samples. Solid phase extraction (SPE) is the most commonly used technique for sample preparation. The purpose of this study is to evaluate the extraction efficiency of the various SPE columns with different sorbent materials for two designer drugs, cathinone and mephedrone in …