Matching Items (3,275)
Filtering by
- Creators: Debussy, Claude, 1862-1918
ContributorsDebussy, Claude, 1862-1918 (Composer)
ContributorsDebussy, Claude, 1862-1918 (Composer)
ContributorsDebussy, Claude, 1862-1918 (Composer)
ContributorsDebussy, Claude, 1862-1918 (Composer)
ContributorsDebussy, Claude, 1862-1918 (Composer)
Description
Social media refers computer-based technology that allows the sharing of information and building the virtual networks and communities. With the development of internet based services and applications, user can engage with social media via computer and smart mobile devices. In recent years, social media has taken the form of different activities such as social network, business network, text sharing, photo sharing, blogging, etc. With the increasing popularity of social media, it has accumulated a large amount of data which enables understanding the human behavior possible. Compared with traditional survey based methods, the analysis of social media provides us a golden opportunity to understand individuals at scale and in turn allows us to design better services that can tailor to individuals’ needs. From this perspective, we can view social media as sensors, which provides online signals from a virtual world that has no geographical boundaries for the real world individual's activity.
One of the key features for social media is social, where social media users actively interact to each via generating content and expressing the opinions, such as post and comment in Facebook. As a result, sentiment analysis, which refers a computational model to identify, extract or characterize subjective information expressed in a given piece of text, has successfully employs user signals and brings many real world applications in different domains such as e-commerce, politics, marketing, etc. The goal of sentiment analysis is to classify a user’s attitude towards various topics into positive, negative or neutral categories based on textual data in social media. However, recently, there is an increasing number of people start to use photos to express their daily life on social media platforms like Flickr and Instagram. Therefore, analyzing the sentiment from visual data is poise to have great improvement for user understanding.
In this dissertation, I study the problem of understanding human sentiments from large scale collection of social images based on both image features and contextual social network features. We show that neither
visual features nor the textual features are by themselves sufficient for accurate sentiment prediction. Therefore, we provide a way of using both of them, and formulate sentiment prediction problem in two scenarios: supervised and unsupervised. We first show that the proposed framework has flexibility to incorporate multiple modalities of information and has the capability to learn from heterogeneous features jointly with sufficient training data. Secondly, we observe that negative sentiment may related to human mental health issues. Based on this observation, we aim to understand the negative social media posts, especially the post related to depression e.g., self-harm content. Our analysis, the first of its kind, reveals a number of important findings. Thirdly, we extend the proposed sentiment prediction task to a general multi-label visual recognition task to demonstrate the methodology flexibility behind our sentiment analysis model.
One of the key features for social media is social, where social media users actively interact to each via generating content and expressing the opinions, such as post and comment in Facebook. As a result, sentiment analysis, which refers a computational model to identify, extract or characterize subjective information expressed in a given piece of text, has successfully employs user signals and brings many real world applications in different domains such as e-commerce, politics, marketing, etc. The goal of sentiment analysis is to classify a user’s attitude towards various topics into positive, negative or neutral categories based on textual data in social media. However, recently, there is an increasing number of people start to use photos to express their daily life on social media platforms like Flickr and Instagram. Therefore, analyzing the sentiment from visual data is poise to have great improvement for user understanding.
In this dissertation, I study the problem of understanding human sentiments from large scale collection of social images based on both image features and contextual social network features. We show that neither
visual features nor the textual features are by themselves sufficient for accurate sentiment prediction. Therefore, we provide a way of using both of them, and formulate sentiment prediction problem in two scenarios: supervised and unsupervised. We first show that the proposed framework has flexibility to incorporate multiple modalities of information and has the capability to learn from heterogeneous features jointly with sufficient training data. Secondly, we observe that negative sentiment may related to human mental health issues. Based on this observation, we aim to understand the negative social media posts, especially the post related to depression e.g., self-harm content. Our analysis, the first of its kind, reveals a number of important findings. Thirdly, we extend the proposed sentiment prediction task to a general multi-label visual recognition task to demonstrate the methodology flexibility behind our sentiment analysis model.
ContributorsWang, Yilin (Author) / Li, Baoxin (Thesis advisor) / Liu, Huan (Committee member) / Tong, Hanghang (Committee member) / Chang, Yi (Committee member) / Arizona State University (Publisher)
Created2018
Description
Breast microcalcifications are a potential indicator of cancerous tumors. Current visualization methods are either uncomfortable or impractical. Impedance measurement studies have been performed, but not in a clinical setting due to a low sensitivity and specificity. We are hoping to overcome this challenge with the development of a highly accurate impedance probe on a biopsy needle. With this technique, microcalcifications and the surrounding tissue could be differentiated in an efficient and comfortable manner than current techniques for biopsy procedures. We have developed and tested a functioning prototype for a biopsy needle using bioimpedance sensors to detect microcalcifications in the human body. In the final prototype a waveform generator sends a sin wave at a relatively low frequency(<1KHz) into the pre-amplifier, which both stabilizes and amplifies the signal. A modified howland bridge is then used to achieve a steady AC current through the electrodes. The voltage difference across the electrodes is then used to calculate the impedance being experienced between the electrodes. In our testing, the microcalcifications we are looking for have a noticeably higher impedance than the surrounding breast tissue, this spike in impedance is used to signal the presence of the calcifications, which are then sampled for examination by radiology.
ContributorsWen, Robert Bobby (Co-author) / Grula, Adam (Co-author) / Vergara, Marvin (Co-author) / Ramkumar, Shreya (Co-author) / Kozicki, Michael (Thesis director) / Ranjani, Kumaran (Committee member) / School of Molecular Sciences (Contributor) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Breastfeeding has been shown by a number of studies to have numerous benefits on both the mother and the infant. Major health organizations such as the World Health Organization (WHO), now agree that breastfeeding should be encouraged and supported in all countries. But like many things, the wheels of the law are slow to catch up with scientific evident. Although breastfeeding is supported, working women do not have the option of breastfeeding without consequences. For example, in 2003, Kirstie Marshall, a then member of parliament in Australia was ejected from the lower house chamber on February 23, for breastfeeding her baby [3]. According to standing order 30 at the time, "Unless by order of the House, no Member of this House shall presume to bring any stranger into any part of the House appropriated to the Members of this House while the House, or a Committee of the whole House, is sitting" [3]. The rules did not specify the age of strangers, so the then 11-day-old baby, Charlotte Louise and her mother were shown the exit door of parliament. She had to choose between being present at times of major discussions or leaving the house to breastfeed her child, she chose to leave. More recent statistics show that developed nations like the US and Australia which also have high rates of women employment had low rates of breastfeeding. This might mean that workplace policies do not favor breastfeeding or expressing milk at work. Fortunately, laws have since been introduced in both the United States and Australia that support breastfeeding at the workplace. The next step would be to access how these laws affect breastfeeding statistics and how variation between these two countries like the paid parental leave in Australia (which is not present in all US states) would affect these numbers.
ContributorsSakala, Lydia (Author) / Alison, Alison (Thesis director) / Reddy, Swapna (Committee member) / School of Molecular Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Ketone bodies are produced in the liver from the acetyl CoA derived from fatty acids that cannot enter the Krebs cycle. This is a sub-analysis of a larger study which had numerous outcome markers. This analysis focuses on the relationship between ketone blood levels and cognition. The study looked at the relationship between Time Restricted Feeding (TRF), a method of intermittent fasting. TRF is something that can be easily adapted into an individual’s lifestyle and has been shown to have multiple advantages. This 8-week study began with 23 enrolled participants, but due to COVID-19 only 11 participants could be tested for cognition and blood ketone levels after week 4. All participants had similar ranges of weight, height, age, BMI, hip, and waist measurements at baseline. Moreover, these demographic variables were not related to ketone levels or cognition. The data indicate that ketone bodies increased in participants practicing TRF and that the increase in ketone bodies in the blood, specifically β-hydroxybutyrate was strongly correlated to increased cognitive function. This is consistent with theories that elevated ketone levels allowed for early hunter-gather communities and other mammals to survive prolonged periods of nutrient deprivation while keeping high cognitive function.
ContributorsTaha, Basel Mahmoud (Author) / Johnston, Carol (Thesis director) / Karen, Sweazea (Committee member) / School of Molecular Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The purpose of this thesis experiment was to design and create an Acoustically Active Cannula (AAC), which is furnished by a piezoelectric crystal placed at its tip that produces an acoustic navigation signal. I tested the functionality of the cannula in vitro and demonstrated its navigational abilities in vivo in anesthetized pigs. This experiment was based upon ultrasound science and technology, and thus some practical experience with conventional (B-mode) and Doppler ultrasound was achieved as well. The results of bench and experimental animal studies indicated proper functionality of the AAC for identification and spatial navigation of its tip with color Doppler ultrasound imaging.
ContributorsShamsa, Kayvan (Author) / Tyler, William (Thesis director) / Belohlavek, Marek (Committee member) / School of Molecular Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05