Digital Commons Network^™

Question Answering With Distilled Bert Models: A Case Study For Biomedical Data, Brittany Lewandowski, Rayon Morris, Pearly Merin Paul, Robert Slater

SMU Data Science Review

In the healthcare industry today, 80% of data is unstructured (Razzak et al., 2019). The challenge this imposes on healthcare providers is that they rely on unstructured data to inform their decision-making. Although Electronic Health Records (EHRs) exist to integrate patient data, healthcare providers are still challenged with searching for information and answers contained within unstructured data. Prior NLP and Deep Learning research has shown that these methods can improve information extraction on unstructured medical documents. This research expands upon those studies by developing a Question Answering system using distilled BERT models. Healthcare providers can use this system on their …

Comparison Of Sampling Methods For Predicting Wine Quality Based On Physicochemical Properties, Robert Burigo, Scott Frazier, Eli Kravez, Nibhrat Lohia

SMU Data Science Review

Using the physicochemical properties of wine to predict quality has been done in numerous studies. Given the nature of these properties, the data is inherently skewed. Previous works have focused on handful of sampling techniques to balance the data. This research compares multiple sampling techniques in predicting the target with limited data. For this purpose, an ensemble model is used to evaluate the different techniques. There was no evidence found in this research to conclude that there are specific oversampling methods that improve random forest classifier for a multi-class problem.

Following The Crowd: Beginners Investors Guide To The Options Market, Jeremy Dawkins, Alexy Morris, Jacob Gipson, Masoud Valizadeh

SMU Data Science Review

While the options market may be intimidating for a beginner, having the right tools can help improve the outcome of their investments. This project aims to develop a tool that uses time-series analysis and forecasting to model the future demand of S&P 500 and AAPL options contracts. The open interest of these contracts will be analyzed using various models such as AR, ARIMA, Neural Networks, and VAR, along with the put-call ratio. The goal is not to make buy or sell recommendations, but alert the user when money is flowing into a security or index. Of all the models, the …

Profiting From Dow Jones Industrial Index And Hang Seng Index Using Moving Average And Macd Optimization Model, Anthony Yeung, Joe Wailun Chung, Nibhrat Lohia, Onyeka Emmanuel

SMU Data Science Review

Before the internet, high-speed laptop computers, and big data became accessible and popular, academia on stock market trading concentrated on Efficient Market Hypothesis (EMH). EMH hinges on the idea that the market is efficient and there is no extra return that could be generated. With the dynamic development of the internet, big-data and computing technology, many researchers started to pay attention to Technical Analysis and its usage. Numerous academic papers claimed that technical analysis can enhance returns by using various technical tools. This paper explores in-depth the simulation model of Moving Average and Moving Average Convergence/Divergence (MACD) to come up …

The Role Of Machine Learning In Improved Functionality Of Lower Limb Prostheses, Joaquin Dominguez, Richard Kim, Robert Slater

SMU Data Science Review

Lower-limb amputations can cause a plethora of obstacles that lead to a lower quality of life. Implementing machine learning techniques means advanced prosthetics can contribute to facilitating the lives of those that live with lower-limb amputations. Using the publicly available HuGaDB data set, the current study investigates several classification models (random forest, neural network, and Vowpal Wabbit) to predict the locomotive intentions of individuals using lower-limb prostheses. The results of this study show that the neural network model yielded the highest accuracy, comparable precision, and recall scores to the other models. However, the Vowpal Wabbit model's advantage in speed may …

Using Nlp To Model U.S. Supreme Court Cases, Katherine Lockard, Robert Slater, Brandon Sucrese

SMU Data Science Review

The advantages of employing text analysis to uncover policy positions, generate legal predictions, and inform or evaluate reform practices are multifold. Given the far-reaching effects of legislation at all levels of society these insights and their continued improvement are impactful. This research explores the use of natural language processing (NLP) and machine learning to predictively model U.S. Supreme Court case outcomes based on textual case facts. The final model achieved an F1-score of .324 and an AUC of .68. This suggests that the model can distinguish between the two target classes; however, further research is needed before machine learning models …

Content-Based Unsupervised Fake News Detection On Ukraine-Russia War, Yucheol Shin, Yvan Sojdehei, Limin Zheng, Brad Blanchard

SMU Data Science Review

The Ukrainian-Russian war has garnered significant attention worldwide, with fake news obstructing the formation of public opinion and disseminating false information. This scholarly paper explores the use of unsupervised learning methods and the Bidirectional Encoder Representations from Transformers (BERT) to detect fake news in news articles from various sources. BERT topic modeling is applied to cluster news articles by their respective topics, followed by summarization to measure the similarity scores. The hypothesis posits that topics with larger variances are more likely to contain fake news. The proposed method was evaluated using a dataset of approximately 1000 labeled news articles related …

Professor Text: University Fundraising Optimization, Braden Anderson, Connor Dobbs, Hien Lam, John Santerre

SMU Data Science Review

University fundraising campaigns are a unique type of cause-related marketing with its own challenges and opportunities. Campaigns like this typically last an extended period, such as five or more years, and goals exist beyond the dollar amount raised. These supplemental goals, such as awareness among potential future donators or brand reputation within the local community, are important to consider and strategize. There can also be unique limitations, such as requiring advertising specifically on recent large gifts or endowment programs. This research explores how machine learning techniques such as natural language processing can be used to optimize a fundraising campaign strategy, …

Extending The M3-Competition: Category And Interval-Specific Time Series Forecasting, Will Sherman, Kati Schuerger, Randy Kim, Bivin Sadler

SMU Data Science Review

The M3-Competition found that simple models outperform more complex ones for time series forecasting. As part of these competitions, several claims were made that statistical models exceeded machine learning (ML) techniques, such as recurrent neural networks (RNN), in prediction performance. These findings may over-generalize the capabilities of statistical models since the analysis measured the total forecasting accuracy across a wide range of industries and fields and with different interval lengths. This investigation aimed to assess how statistical and ML methods compared when individuating series by category and time interval. Utilizing the M3 data and building individual models using Facebook© Prophet …

The Effects Of A High Grass Input Feeding System Compared To High Concentrate Input Feeding System Offered To Spring Calving Dairy Cows In Early Lactation, E. Kennedy, M. O'Donovan, J. P. Murphy, F. P. O'Mara, L. Delaby

IGC Proceedings (1977-2023)

Grazed grass is the cheapest feed available on Irish dairy farms. The inclusion of grass in the diet of the spring-calving dairy cow in early lactation is recommended. Previous studies focused on introducing grazed herbage into the cows diet in early spring in conjunction with grass silage and concentrate, and compared this to cows fed indoors. The objective of this study was to compare the milk production and feed budget of two contrasting early lactation feeding regimes. One regime was based on a high herbage inclusion with a low concentrate level (HG), while the other was based on a high …

A Comparison Of A Full Time Grazing And A Partial Storage Feeding System, For Dairy Cows, C. P. Ferris, D. C. Patterson

IGC Proceedings (1977-2023)

Partial storage feeding has been adopted by a number of Northern Ireland dairy farmers in recent years. This is due in part to increasing cow numbers, and as such, insufficient pasture close to the milking parlour to permit full time grazing. Partial storage feeding may also have environmental benefits, as well as reducing labour requirements associated with 'droving' and pasture management. In view of this, a study was undertaken to examine animal performance with either a full-time grazing, or a partial storage feeding regime.

Effect Of A Summer Period At Pasture On The Performance Of Young Bulls Offered Concentrates Ad Libitum, R. J. Fallon, M. G. Keane

IGC Proceedings (1977-2023)

Holstein bull calves can produce a 250 kg carcass at 11 to 12 months of age on indoor feeding of ad libitum concentrates. An outdoor period at pasture would reduce housing costs. Two experiments were undertaken to determine the effect of an outdoor period at pasture on concentrate intake, liveweight gain and selected carcass traits of Holstein young bulls.

Spring Calving Suckler Beef Systems: Influence Of Grassland Management System On Herbage Availability, Utilisation, Quality And Cow And Calf Performance To Weaning, M. J. Drennan, M. Mcgee, S. Kyne, B. O'Neill

IGC Proceedings (1977-2023)

Suckler beef systems in Ireland are primarily based on grass. Suckler systems vary in intensity but many operate low input systems and participate in REPS (Rural Environmental Protection Scheme). As there is a considerable cost associated with second-cut silage this research compared a two-cut system with a simplified low input one-cut system.

Effect Of Time Spent On Pasture On Milk Production And Quality In Latxa Dairy Sheep, A. Garcia-Rodriguez, N. Mandaluniz, L. M. Oregui

IGC Proceedings (1977-2023)

Dairy sheep production systems in the Basque country are pasture based. Forage resources are managed by shepherds who match herbage, forage and supplement availability with production requirements. This is achieved through a part-time grazing system, where ewes spend 3 to 7 hours grazing. The aim of this study was to evaluate the effect of restricted access to pasture on milk production and quality.

Animal Unit Of Sheep (Zel Breed) Grazing In Mazandaran Grasslands In Iran, Hossein Arzani, Reza Erfanzadeh, S. Farazmand

IGC Proceedings (1977-2023)

Animal unit equivalents (AUEs), provide a means of summarising grazing capacity, calculating stocking rates and other stocking variables (Scarnecchia, 1990). Animal units (AU) are often defined in relation to the dominant animal type in an area In Iran there are 27 sheep breeds which are classified into three main body size classes, namely: small, medium and large. The objective of this experiment was to define animal units, animal and forage requirements for sheep grazing in Mozandaran grasslands.

Mixed Fattening Of Steers And Lambs On Improved Grasslands In Uruguay: I. Pasture Performance, D. F. Risso, Fabio Montossi, E. J. Berretta, R. Cuadro, I. De Barbieri, R. San Julián, A. Dighiero, A. Zarza

IGC Proceedings (1977-2023)

The use of P fertilisers together with legume broadcasting is a low cost and high impact technology for improving native grassland (Risso et al., 2001). Its use is increasing in Uruguay, although not for mixed grazing, even though this management is a common practice on native grasslands. Good pasture response may occur under mixed grazing when it is adequately managed (Nolan & Connolly, 1989). The following trials characterise pasture response with such management, in Uruguayan conditions.

Mixed Fattening Of Steers And Lambs On Improved Grasslands In Uruguay: Ii. Animal Performance And Productivity, D. F. Risso, Fabio Montossi, E. J. Berretta, R. Cuadro, I. De Barbieri, R. San Julián, A. Dighiero, A. Zarza

IGC Proceedings (1977-2023)

In cow-calf operations in Uruguay, mixed cattle and sheep grazing on rangelands is predominant, while fattening is a specialised process. Within certain limits of the lamb/steer ratio and stocking rate, a complementary grazing effect occurs under mixed grazing, improving net results (Nolan & Connolly, 1977; Risso et al., 2002). These trials characterise animal performance under such management.

The Rostock Energetic Feed Evaluation On The Base Of Net Energy, W. Jentsch, A. Chudy, M. Beyer, S. Kuhla

IGC Proceedings (1977-2023)

Feed evaluation was an emphasis of research from the foundation of the "Oskar-Kellner-Institute of Animal Nutrition" in 1953 at Rostock by Prof. Kurt Nehring. The aim of the research work was the elaboration of a feed evaluation system containing reference numbers of feed values and requirements of farm animals. The approach and the present system are outlined in this paper.

Constraints On Dairy Cattle Production From Locally Available Forages In Bangladesh, M. A. S. Khan

IGC Proceedings (1977-2023)

The productivity of milk producing animals in Bangladesh is low because of low individual yield and poor fertility. The reasons for the low productivity are complex but, in order of priority, appear to be (a) the imbalanced nature of the nutrients that arise from the digestion of the forage resources, (b) the incidence of disease/parasitism, and (c) the often harsh climatic circumstances. Thus, the purpose of this study was to find out the practical constraints on dairy cattle production from locally available forages under small holding village conditions of Bangladesh.

Effects Of Supplementary Concentrate Level And Separate Or Mixed Feeding Of Grass Silage And Concentrates On Rumen Fluid Composition In Steers, J. Caplis, M. G. Keane, F. P. O'Mara

IGC Proceedings (1977-2023)

The effects of dietary concentrate level and method of feeding (separate or mixed) on performance and carcass traits of steers may be mediated through changes in rumen fluid composition. The objectives of this study were to determine the effects on rumen fluid composition of (1) supplementary concentrate level with grass silage, and (2) separate or mixed feeding of silage and concentrates,

Body Temperature In Free-Roaming Beef Cattle, T. L. Mader, S. L. Colgan

IGC Proceedings (1977-2023)

Body temperature (BT) measurements are traditionally used in diagnosing sick animals, but may also be used as an indicator of stress or activity. Based on results of metabolism studies, Mader et al. (1999) reported that BT can vary as much as 0.9^oC and can depend on metabolisable energy (ME) of the diet consumed. Acceptable measures of BT can be obtained from the rectum, vagina, or ear canal. Technologies are also being developed for continuously monitoring BT via radio-telemetry. The objectives of this study were to determine the effect of high concentrate (low fibre) versus high fibre diets on …

Yield And Quality Parameters Of An Interspecific Hybrid Pennisetum Purpureum Schum. (Elephant-Grass) X Pennisetum Glaucum (L.) R. Br. Stuntz (Pearl Millet), J. A. Usberti Jr., R. Usberti, P. B. Alcantara, V. B. G. Alcantara, R. A. Possenti, M. A. C. Lucena

IGC Proceedings (1977-2023)

Elephant-grass is a tropical forage grass used either as a supplement fodder or for direct grazing. It usually shows regular nutritive value (6-13% crude protein, CP, and 55-60% forage digestibility) (Alcantara et al., 1981). Most of the available cultivars produce no viable seeds. On the other hand, pearl millet has high seed yielding potential along with high quality forage (>15% CP and 70% forage digestibility). However, it shows poor forage production, low field persistence under grazing and low regrowth potential after cutting or grazing. During the 90's, an interspecific hybrid between the two species was developed, trying to …

Avoiding “Bad” Design In The Age Of Dei, Chloe Zarafshar

Seminar in Textiles and Clothing

This insightful presentation focused on the crucial topic of avoiding “bad” design in the current era of Diversity, Equity, and Inclusion (DEI). One of the most pressing issues in this area is cultural appropriation, which occurs when designers adopt customs, practices, or ideas from a particular culture without giving proper credit or acknowledgment to its creators. It is essential to differentiate between cultural appropriation and cultural appreciation, where designers can integrate elements from different cultures into their designs while respecting their origins and meaning. Several examples of designers, fashion shows, and runways that have been accused of cultural appropriation were …

Challenges In The Beauty Industry: Disability Inclusive Design, Casey Badal

Seminar in Textiles and Clothing

The beauty industry has long struggled with disability inclusion, despite the fact that a significant portion of the population faces various mobility and accessibility challenges. Inclusive design in the beauty industry can have lasting positive effects, such as improving self-esteem and body satisfaction for those with disabilities and increasing the availability of products for people with disabilities and the aging population. In addition, it can also increase profits and expand the consumer market by appealing to a wider range of people.

Ai Design For Fashion, Gabrielle Gluberman

Seminar in Textiles and Clothing

Artificial intelligence (AI) is the process of stimulating human intelligence through a branch of science and technology. AI has been evolving rapidly and is being used in the creative process for many artistic endeavors. It is a major force influencing fashion products. While AI has advantages, there are risks.

Backmatter (Volume 1, Issue 1), Grayson Carter

Sehnsucht: The C. S. Lewis Journal

No abstract provided.

Review Essay: Lewis Agonistes: How C. S. Lewis Can Train Us To Wrestle With The Modern And Postmodern World, William Gentrup

Sehnsucht: The C. S. Lewis Journal

A lengthy review of Lewis Agonistes: How C. S. Lewis Can Train Us to Wrestle with the Modern and Postmodern World. By Louis Markos. Nashville: Broadman & Holman Publishers, 2003.

ISBN 0-8054-2778-3. Pp. xv + 174. $19.99 [paper].

All My Dogs Before Me, Bruce R. Johnson

Sehnsucht: The C. S. Lewis Journal

Excerpt: "Dogs? Did C. S. Lewis own dogs?" That casual question, raised at one of the organizational meetings of the Arizona C. S. Lewis Society,1 led to a rather obscure search. Was Lewis a pet owner? It is well known that he had created two imaginary worlds filled with talking animals: Narnia and Boxen. Less well known was his opposition to vivisection. An entire chapter of The Problem of Pain deals with pain as experienced by animals. A bear at the Whipsnade Zoo, nicknamed “Mr. Bultitude” by Lewis and his brother, Warren, appears as a minor character in That Hideous …

Defending The Dangerous Idea: An Update On C.S. Lewis' Argument From Reason, Victor Reppert

Sehnsucht: The C. S. Lewis Journal

Although C. S. Lewis's argument against naturalism is widely thought to have been undermined by Elizabeth Anscombe’s criticisms (and indeed it is sometimes claimed that Lewis was considerably weakened as an apologist by this exchange), I thought that an adequately reformulated version of the argument could surmount Anscombe’s objections. This claim was defended for the first time in print in “ ‘The Lewis-Anscombe Controversy’: A Discussion of the Issues,” which appeared in Christian Scholar’s Review in 1989

Upcoming Events, Grayson Carter

Sehnsucht: The C. S. Lewis Journal

No abstract provided.