Graduate Student Papers
Permanent URI for this collection
Browse
Browsing Graduate Student Papers by Content Type "Article"
Now showing 1 - 6 of 6
Results Per Page
Sort Options
- Deep Learning for Forest Plantation Mapping in Godavari Districts of Andhra Pradesh, IndiaMore, Snehal; Karpatne, Anuj; Wynne, Randolph H.; Thomas, Valerie A. (Virginia Tech, 2019-08)Small-area forest plantations play a vital role in the socioeconomic well-being of farmers in Southeast Asia. Most plantations are established on former agricultural land, often on land less suitable for agriculture. Plantations that are converted from natural forest have adverse impacts on biodiversity. Mapping small-area plantations is thus important to understand the dynamics of forest cover in Southeast Asia and to study the social, economic, and ecological effects of this important land cover and land use change. While the small size of forest plantations makes it difficult to detect them using moderate resolution satellite sensors, the problem is exacerbated by the high degree of mixing between plantations, surrounding vegetation, and other land covers, which often show variegated responses in satellite signals across space and time. In this paper, we study the problem of mapping small-area forest plantations in East and West Godavari districts of Andhra Pradesh, India using deep learning methods. Remotely sensed cloud-free data from the Harmonized Landsat Sentinel-2 S10 product were classified using a pixel-level neural network and training data labeled using a field-based survey in concert with expert aerial photo interpretation. We compare the performance of deep learning methods with a baseline random forest classifier in our study region of 21543 sq. km over a period of 3 years and analyze the differences in the results across land cover classes and seasons.
- Gender Analysis of Factors Influencing Soil and Water Conservation Technology Utilization among Vegetable Farmers in Ekiti and Oyo States, NigeriaFaniyi, Ebunoluwa; Deji, Olanike; Olowoyo, Olamide; Sulaimon, Waheed; Aduwo, Oluwafunke (Nigerian Journal of Rural Sociology, 2019)The study assessed the gender analysis of factors associated with soil and water conservation technology usage among vegetable farmers in Ekiti and Oyo States, Nigeria. It specifically, described the socioeconomic characteristics of vegetable farmers and examined the gender-specific factors associated with soil and water conservation technology utilisation in vegetable production. The study adopted a multi-stage sampling procedure. Data were elicited from the respondents using an interview schedule and focus group discussion guide. The study used inferential and descriptive statistics to analyse the data from the survey. The findings showed that the mean age for male was 35 years and female vegetable farmers 41 years. While the mean years of vegetable farming experience for male was 16 years and female vegetable farmers was 19 years. Varimax factor rotation pattern was used to isolate six factors associated with soil and water conservation technology usage for male vegetable farmers, which were information-source factor (14.4%), family factor (14.0%), resources factor (11.7%), economic factor (10.5%), soil-fertility factor (8.3%), and institutional factor (8.0%). Also,five factors were isolated for the female vegetable which were include; personal-experience factor (21.6%), information source factor (20.0%), land acquisition factor (10.7%), resources factor (10.0%), and group membership factor (7.7%). Information, resources, economic, personal experience, and land acquisition were the gender-specific factors influencing soil water conservation (SWC) technology usage. It was recommended that the factors identified should be noted as springboard for technology development and dissemination in Nigeria, this will help in the removal of the existing gender gaps among the farmers, especially in the rural areas and ensure sustainable agricultural practices and rural transformation.
- Nearest Neighbor Classifier – From Theory to PracticeTorfi, Amirsina (Machine Learning Mindset, 2020-01-11)The K-nearest neighbors (KNNs) classifier or simply Nearest Neighbor Classifier is a kind of supervised machine learning algorithm that operates based on spatial distance measurements. In this article, we investigate the theory behind it. Furthermore, a working example of the k-nearest neighbor classifier will be represented.
- Rawls and capabilities: the current debate [draft]D'Amato, Claudio (Virginia Tech, 2014)The capability approach to justice was con-ceived as an alternative to the Rawlsian scholar-ship that became dominant in moral and political philosophy at the end of the XX century. Among other issues, capability theorists have objected to Rawls’s identification of the currency of distribu-tive justice with primary goods and to the claim that the appropriate subject of distributive justice is the basic structure of society. As Ingrid Robeyns (2011) puts it, capability theorists argue that capability as a “metric of justice” does a better job than Rawlsian primary goods at capturing what human beings seek in a social distributive scheme. How-ever, the relation between the two sides of the debate is not one of stark opposition, but rather one of productive exchange: all work within the liberal political tradition, and in the last few years there has been considerable mutual understanding, co-operation, and a certain softening of the two sides’ original positions—pun intended. This paper surveys the main arguments in the debate and evaluates recent (2003-2013) contributions to the literature that attempt to bridge the gap between justice as fairness and the capability approach.
- The road to moral independence: agency, gender, and family in The Last of Us [draft]D'Amato, Claudio (Virginia Tech, 2014)... The Last of Us (TLOU) is one of the most literary games of the modern era, and my personal favorite in a long time, perhaps since the equally well-written Mass Effect 2. It is ripe with moral dilemmas and psychologically fascinating characters, and it allows players and critics to discuss gender roles at a con-ceptual depth seldom seen in the video game industry. Much has been said in the popular press about whether the game is fundamentally sexist with some redeeming qualities or fundamentally feminist with some dark spots. It is in fact both. From a purely critical standpoint, it is a sharp, at times virulent, critique of patriarchal gender roles. But its critique is too understated, and most players will be unable to see it and will risk mistaking villains for heroes and sexism for equality. TLOU is the best possible game that could have been written given its constraints, but it could have made its feminist point—which it does have, and which is extremely good—much better.
- Supplemental Materials - Effects of varying extracellular amino acid concentrations on bidirectional amino acid transport and intracellular fluxes in mammary epithelial cellsYoder, Peter S.; Castro, Juan J.; Ruiz-Cortes, Tatiana; Hanigan, Mark D. (Elsevier Inc. and Fass Inc., 2021)