Matching Items (112)
Description
Background
Multicellular organisms consist of cells of many different types that are established during development. Each type of cell is characterized by the unique combination of expressed gene products as a result of spatiotemporal gene regulation. Currently, a fundamental challenge in regulatory biology is to elucidate the gene expression controls that generate the complex body plans during development. Recent advances in high-throughput biotechnologies have generated spatiotemporal expression patterns for thousands of genes in the model organism fruit fly Drosophila melanogaster. Existing qualitative methods enhanced by a quantitative analysis based on computational tools we present in this paper would provide promising ways for addressing key scientific questions.
Results
We develop a set of computational methods and open source tools for identifying co-expressed embryonic domains and the associated genes simultaneously. To map the expression patterns of many genes into the same coordinate space and account for the embryonic shape variations, we develop a mesh generation method to deform a meshed generic ellipse to each individual embryo. We then develop a co-clustering formulation to cluster the genes and the mesh elements, thereby identifying co-expressed embryonic domains and the associated genes simultaneously. Experimental results indicate that the gene and mesh co-clusters can be correlated to key developmental events during the stages of embryogenesis we study. The open source software tool has been made available at http://compbio.cs.odu.edu/fly/.
Conclusions
Our mesh generation and machine learning methods and tools improve upon the flexibility, ease-of-use and accuracy of existing methods.
Multicellular organisms consist of cells of many different types that are established during development. Each type of cell is characterized by the unique combination of expressed gene products as a result of spatiotemporal gene regulation. Currently, a fundamental challenge in regulatory biology is to elucidate the gene expression controls that generate the complex body plans during development. Recent advances in high-throughput biotechnologies have generated spatiotemporal expression patterns for thousands of genes in the model organism fruit fly Drosophila melanogaster. Existing qualitative methods enhanced by a quantitative analysis based on computational tools we present in this paper would provide promising ways for addressing key scientific questions.
Results
We develop a set of computational methods and open source tools for identifying co-expressed embryonic domains and the associated genes simultaneously. To map the expression patterns of many genes into the same coordinate space and account for the embryonic shape variations, we develop a mesh generation method to deform a meshed generic ellipse to each individual embryo. We then develop a co-clustering formulation to cluster the genes and the mesh elements, thereby identifying co-expressed embryonic domains and the associated genes simultaneously. Experimental results indicate that the gene and mesh co-clusters can be correlated to key developmental events during the stages of embryogenesis we study. The open source software tool has been made available at http://compbio.cs.odu.edu/fly/.
Conclusions
Our mesh generation and machine learning methods and tools improve upon the flexibility, ease-of-use and accuracy of existing methods.
ContributorsZhang, Wenlu (Author) / Feng, Daming (Author) / Li, Rongjian (Author) / Chernikov, Andrey (Author) / Chrisochoides, Nikos (Author) / Osgood, Christopher (Author) / Konikoff, Charlotte (Author) / Newfeld, Stuart (Author) / Kumar, Sudhir (Author) / Ji, Shuiwang (Author) / Biodesign Institute (Contributor) / Center for Evolution and Medicine (Contributor) / College of Liberal Arts and Sciences (Contributor) / School of Life Sciences (Contributor)
Created2013-12-28
Learning Sparse Representations for Fruit-Fly Gene Expression Pattern Image Annotation and Retrieval
Description
Background
Fruit fly embryogenesis is one of the best understood animal development systems, and the spatiotemporal gene expression dynamics in this process are captured by digital images. Analysis of these high-throughput images will provide novel insights into the functions, interactions, and networks of animal genes governing development. To facilitate comparative analysis, web-based interfaces have been developed to conduct image retrieval based on body part keywords and images. Currently, the keyword annotation of spatiotemporal gene expression patterns is conducted manually. However, this manual practice does not scale with the continuously expanding collection of images. In addition, existing image retrieval systems based on the expression patterns may be made more accurate using keywords.
Results
In this article, we adapt advanced data mining and computer vision techniques to address the key challenges in annotating and retrieving fruit fly gene expression pattern images. To boost the performance of image annotation and retrieval, we propose representations integrating spatial information and sparse features, overcoming the limitations of prior schemes.
Conclusions
We perform systematic experimental studies to evaluate the proposed schemes in comparison with current methods. Experimental results indicate that the integration of spatial information and sparse features lead to consistent performance improvement in image annotation, while for the task of retrieval, sparse features alone yields better results.
Fruit fly embryogenesis is one of the best understood animal development systems, and the spatiotemporal gene expression dynamics in this process are captured by digital images. Analysis of these high-throughput images will provide novel insights into the functions, interactions, and networks of animal genes governing development. To facilitate comparative analysis, web-based interfaces have been developed to conduct image retrieval based on body part keywords and images. Currently, the keyword annotation of spatiotemporal gene expression patterns is conducted manually. However, this manual practice does not scale with the continuously expanding collection of images. In addition, existing image retrieval systems based on the expression patterns may be made more accurate using keywords.
Results
In this article, we adapt advanced data mining and computer vision techniques to address the key challenges in annotating and retrieving fruit fly gene expression pattern images. To boost the performance of image annotation and retrieval, we propose representations integrating spatial information and sparse features, overcoming the limitations of prior schemes.
Conclusions
We perform systematic experimental studies to evaluate the proposed schemes in comparison with current methods. Experimental results indicate that the integration of spatial information and sparse features lead to consistent performance improvement in image annotation, while for the task of retrieval, sparse features alone yields better results.
ContributorsYuan, Lei (Author) / Woodard, Alexander (Author) / Ji, Shuiwang (Author) / Jiang, Yuan (Author) / Zhou, Zhi-Hua (Author) / Kumar, Sudhir (Author) / Ye, Jieping (Author) / Biodesign Institute (Contributor) / Center for Evolution and Medicine (Contributor) / Ira A. Fulton School of Engineering (Contributor) / College of Liberal Arts and Sciences (Contributor) / School of Life Sciences (Contributor)
Created2012-05-23
Description
Background
Drosophila melanogaster has been established as a model organism for investigating the developmental gene interactions. The spatio-temporal gene expression patterns of Drosophila melanogaster can be visualized by in situ hybridization and documented as digital images. Automated and efficient tools for analyzing these expression images will provide biological insights into the gene functions, interactions, and networks. To facilitate pattern recognition and comparison, many web-based resources have been created to conduct comparative analysis based on the body part keywords and the associated images. With the fast accumulation of images from high-throughput techniques, manual inspection of images will impose a serious impediment on the pace of biological discovery. It is thus imperative to design an automated system for efficient image annotation and comparison.
Results
We present a computational framework to perform anatomical keywords annotation for Drosophila gene expression images. The spatial sparse coding approach is used to represent local patches of images in comparison with the well-known bag-of-words (BoW) method. Three pooling functions including max pooling, average pooling and Sqrt (square root of mean squared statistics) pooling are employed to transform the sparse codes to image features. Based on the constructed features, we develop both an image-level scheme and a group-level scheme to tackle the key challenges in annotating Drosophila gene expression pattern images automatically. To deal with the imbalanced data distribution inherent in image annotation tasks, the undersampling method is applied together with majority vote. Results on Drosophila embryonic expression pattern images verify the efficacy of our approach.
Conclusion
In our experiment, the three pooling functions perform comparably well in feature dimension reduction. The undersampling with majority vote is shown to be effective in tackling the problem of imbalanced data. Moreover, combining sparse coding and image-level scheme leads to consistent performance improvement in keywords annotation.
Drosophila melanogaster has been established as a model organism for investigating the developmental gene interactions. The spatio-temporal gene expression patterns of Drosophila melanogaster can be visualized by in situ hybridization and documented as digital images. Automated and efficient tools for analyzing these expression images will provide biological insights into the gene functions, interactions, and networks. To facilitate pattern recognition and comparison, many web-based resources have been created to conduct comparative analysis based on the body part keywords and the associated images. With the fast accumulation of images from high-throughput techniques, manual inspection of images will impose a serious impediment on the pace of biological discovery. It is thus imperative to design an automated system for efficient image annotation and comparison.
Results
We present a computational framework to perform anatomical keywords annotation for Drosophila gene expression images. The spatial sparse coding approach is used to represent local patches of images in comparison with the well-known bag-of-words (BoW) method. Three pooling functions including max pooling, average pooling and Sqrt (square root of mean squared statistics) pooling are employed to transform the sparse codes to image features. Based on the constructed features, we develop both an image-level scheme and a group-level scheme to tackle the key challenges in annotating Drosophila gene expression pattern images automatically. To deal with the imbalanced data distribution inherent in image annotation tasks, the undersampling method is applied together with majority vote. Results on Drosophila embryonic expression pattern images verify the efficacy of our approach.
Conclusion
In our experiment, the three pooling functions perform comparably well in feature dimension reduction. The undersampling with majority vote is shown to be effective in tackling the problem of imbalanced data. Moreover, combining sparse coding and image-level scheme leads to consistent performance improvement in keywords annotation.
ContributorsSun, Qian (Author) / Muckatira, Sherin (Author) / Yuan, Lei (Author) / Ji, Shuiwang (Author) / Newfeld, Stuart (Author) / Kumar, Sudhir (Author) / Ye, Jieping (Author) / Biodesign Institute (Contributor) / Center for Evolution and Medicine (Contributor) / College of Liberal Arts and Sciences (Contributor) / School of Life Sciences (Contributor) / Ira A. Fulton School of Engineering (Contributor)
Created2013-12-03
Description
Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.
ContributorsLi, Vincent (Author) / Turaga, Pavan (Thesis director) / Buman, Matthew (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
The research shows that existing interventions that attempt to reduce sedentary behavior are effective. The purposes of this review were to examine: (1) how adherent individuals are to workplace sedentary behavior interventions in the short and long term and (2) how the use of incentives impact adherence in the short and long term. It was found that short-term studies showed higher rates of adherence than medium-term studies. Studies that used incentives showed lower rates of adherence than studies that did not use incentives. Medium-term studies that used incentives showed the same rates of adherence as short-term studies that used incentives, indicating that incentives can benefit adherence in longer term interventions.
ContributorsLitevsky, Gabriella (Author) / Buman, Matthew (Thesis director) / Leonard, Krista (Committee member) / Barrett, The Honors College (Contributor) / College of Health Solutions (Contributor)
Created2022-05
Description
Sleep diaries and actigraphy are two common methods used to assess sleep subjectively and objectively, respectively. Compared to the gold standard of sleep assessment, polysomnography, sleep diaries and actigraphic methods are more cost-effective and simpler to use. This study aimed to compare the sleep parameters derived from actigraphy and sleep diaries (total sleep time, sleep onset latency, number of awakenings, wake after sleep onset, percentage of time awake, and sleep efficiency). Based on results from previous similar studies, it was hypothesized that the sleep diaries would overestimate the total sleep time parameter and underestimate wake parameters. Twenty healthy young adults without sleep problems volunteered to participate. The participants wore an Actiwatch 2 on their wrist and filled out a sleep diary every morning for the duration of six days. A high intraclass correlation coefficient value between subjective and objective sleep was found for the parameter total sleep time, even though total sleep time was found to be slightly overestimated by the sleep diaries. Sleep onset latency, wake after sleep onset, number of awakenings, percentage of time awake, and sleep efficiency were underestimated by the sleep diaries and did not have high correlation values. Based off of the ICC results, there does not seem to be a strong correlation between the Actiwatch 2 and the sleep diaries, but looking at the Bland Altman plots, there seems to be agreement between the methods.
ContributorsRameshkumar, Aarthi (Author) / Buman, Matthew (Thesis director) / Petrov, Megan (Committee member) / Diaz-Piedra, Carolina (Committee member) / School of Molecular Sciences (Contributor) / Barrett, The Honors College (Contributor) / School of Nutrition and Health Promotion (Contributor)
Created2016-12
Description
The Walter Cronkite School of Journalism and Mass Communications stands as a "gold standard" of journalism education throughout the country. In my time at the school though, I found that some aspects in the whole of the curriculum were missing. I as well as several other friends became interested in production and the technical side of things. This seemed to be the direction we wanted to go and soon realized this played a crucial part in journalism. Although there is a studio production class and a studio production track through the immersive Cronkite News program, there is not much in between. This inspired me to take a look deeper into production skills and their place within a journalism education. The project is split into three main sections that dive into the ideas of teaching production skills and technical skills to journalism students and whether or not it is valuable. The first part is the background of the project and why this project came to be. The background section explores the inspiration for the project. The project continues with a look at job statistics and where the industry currently sits. This continues into the final section that contains personal stories and interviews with professionals in the field. This is a critical section to back up claims made through research and evaluation. There is a lot of personal experience and non-traditional research done through this project, but the assertions and conclusions made are clear. Through job statistics, personal stories, and interviews with professionals, this project examines how production could be taught in a traditional journalism program. These stories show that a journalism curriculum may not be the best place to teach production in depth, but that it still is an incredibly important part of the journalism world as a whole.
ContributorsHardy, Joseph Michael (Author) / Jacoby, Jim (Thesis director) / McJannet, Rob (Committee member) / College of Public Service and Community Solutions (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
The Chinese tourism market has become the largest tourism market in the world and continues to show promise in its future development. Global destinations such as Southeast Asia, France and now Australia have begun to see a major boom in Chinese tourists within the past decade due to less restrictive travel policies, a growing economy and higher disposable income rates within urban centers in China. Australia has become the top destination among Chinese citizens that wish to travel due to its coastal and beach attractions, unique wildlife, and general welcoming attitude toward Chinese citizens. As the market continues to grow, the characteristics and demographics change as well. The Chinese government did not allow for international travel until the early 1990s. During this time, package tours offered by government-regulated travel agencies were the prominent method of travel planning with travelers over the age of 35 making up the majority of travelers. However, in the past decade there has been a shift from group travel toward independent travel due to higher income and more independence among young adults. There remains a stigma against Chinese tourists due to behavioral and cultural challenges Chinese tourists face when traveling abroad, but as Chinese travelers begin to travel in smaller groups and have greater exposure to international cultures, these negative stereotypes will start to disappear. This paper focuses on the impact the Chinese tourism market has on Cairns, Australia. Cairns is characterized by its backpacking culture, easy access to environmental attractions and a high number of annual travelers from Asia and China specifically. The paper uses qualitative research and compiles information from news sources, government documents and statistical data regarding Chinese outbound tourism and its impacts on Australian tourism. There is also a case study composed of personal observations of a nature park in North Queensland which uses specific marketing and attraction coordination to appeal to Chinese tourists. This case study analyzes the tactics used by local destinations that cater to group travel over independent travel and points out the benefits of this type of specialized tourism. The research concludes by arguing the trend toward independent travel is beneficial to the Cairns tourism industry rather than harmful as long as the industry recognizes the new trends in Chinese tourism and does not focus on the previous trends of group travel when appealing to Chinese tourists. Instead, the industry should continue to focus on the backpacking culture and work toward catering to the demands of millennial travelers.
ContributorsRochon, Jacob Henri (Author) / Goodman, Rebekka (Thesis director) / McWilliams, Claire (Committee member) / College of Public Service and Community Solutions (Contributor) / School of Politics and Global Studies (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Translating research has been a goal of the Department of Health and Human Services since 1999. Through two years of iteration and interview with our community members, we have collected insights into the barriers to accomplishing this goal. Liberating Science is a think-tank of researchers and scientists who seek to create a more transparent process to accelerate innovation starting with behavioral health research.
ContributorsRaghani, Pooja Sioux (Author) / Hekler, Eric (Thesis director) / Buman, Matthew (Committee member) / Pruthi, Virgilia Kaur (Committee member) / Barrett, The Honors College (Contributor) / Department of Chemistry and Biochemistry (Contributor) / Biomedical Informatics Program (Contributor)
Created2014-05
Description
Over the last decade, the ability to track daily activity through step counting devices has undergone major changes. Advanced technologies have brought about new step counting devices and new form factors. The validity of these new devices is not fully known. The purpose of this study was to validate and compare the step counting accuracy of commercially available hip- and wrist-worn accelerometers. A total of 185 participants (18-64 years of age) were analyzed for this study, with the sample composed nearly evenly of each gender (53.5% female) and BMI classification (33% overweight, 31.9% obese). Each participant wore five devices including hip-worn Omron HJ-112 and Fitbit One, and wrist-worn Fitbit Flex, Nike Fuelband, and Jawbone UP. A range of activities (some constant among all participants, some randomly assigned) were then used to accumulate steps including walking on a hard surface for 400m, treadmill walking/running at 2mph, 3mph, and ≥5mph, walking up five flights of stairs, and walking down five flights of stairs. To validate the accuracy of each device, steps were also counted by direct observation. Results showed high concordance with directly observed steps for all devices (intraclass correlation coefficient range: 0.86 to 0.99), with hip-worn devices more accurate than wrist-worn devices. Absolute percent error values were lower among hip-worn devices and at faster walking/running speeds. Nike Fuelband consistently was the worst performing of all test devices. These results are important because as pedometers become more complex, it is important that they remain accurate throughout a variety of activities. Future directions for this research are to explore the validity of these devices in free-living settings and among younger and older populations.
ContributorsKramer, Cody Lee (Author) / Buman, Matthew (Thesis director) / Hoffner, Kristin (Committee member) / Marshall, Simon (Committee member) / Barrett, The Honors College (Contributor) / School of Nutrition and Health Promotion (Contributor)
Created2014-05