517 research outputs found
Feedback Study (Video Data)
No full textUsing AI-driven Feedback to Improve Novice Performance on a Robotic Suturing Tas
Deep learning with limited labelled cardiac data
Get PDFCardiac data, that which pertain to the heart, are a rich source of information that reflect a patient's cardiac status. Extracting clinically-useful insight from such data can be achieved via deep learning, a sub-field of artificial intelligence. Current clinical deep learning algorithms, however, are heavily dependent upon resources such as abundant data and high-quality annotations, both of which are scarce in many clinical settings. In low-resource settings, for example, the prohibitively high cost of medical infrastructure precludes the collection of data and the limited number of physicians hampers the provision of annotations. The reasons for data paucity in high-resource settings are multi-fold, ranging from stringent patient-privacy regulations to the low inter-operability of medical records. Physicians in this setting can also be disengaged due to the overwhelming number of annotation requests.
To address this challenge, in this thesis, we design deep learning algorithms that exploit cardiac data to achieve more with less; less data, fewer labels, and less medical supervision during the learning process. While designing these algorithms, we focus predominantly on the clinical task of cardiac arrhythmia classification, which involves diagnosing abnormalities in the functioning of the heart.
We deploy our algorithms in three paradigms characterized by an incrementally increasing level of resource availability. In Part I of the thesis, we simulate a low-resource scenario with limited data and exploit conditional generative adversarial networks to generate cardiac time-series data for augmentation purposes. In Part II, we simulate access to abundant unlabelled data and limited labelled data. In this environment, we propose an active learning framework that dynamically determines whether an annotation should be requested from a physician or generated by an algorithm instead. We also present a family of patient-specific contrastive learning methods that improve resource-efficiency; the ability of a learner to solve a task with less data. In Part III, we deal with more extensive multi-modal data. We explore the degree to which algorithms suffer from catastrophic forgetting (the impaired ability to solve tasks from the past upon learning tasks in the present), and propose a continual learning framework to overcome this phenomenon. We also simultaneously exploit cardiac data and clinical textual reports to design a captioning system that, upon receiving cardiac signals, generates clinical reports in multiple languages.
By designing such resource-efficient frameworks, we hope to improve the accessibility of clinical deep learning algorithms, and, in turn, healthcare to vulnerable patients in low-resource settings
CITRA PEREMPUAN SUKU DANI DALAM NOVEL ETNOGRAFI SALI, KISAH SEORANG WANITA SUKU DANI KARYA DEWI LINGGASARI: ANALISIS KRITIK SASTRA FEMINIS RUTHVEN
No full textThe research conducted on a novel tittled Sali, The Story of a Dani Woman
(SKSWSD) by Linggasari aims to contribute ideas on the study of women,
especially images of Dani women by using feminist literary criticism from
Ruthven. Dani women live in a patriarchal system that treats women in a
disadvantageous position. In this research, the concept images of women is used
to reveal the nature of stereotype representation of women oppression. In
ethnographic novel SKSWSD, the author tried to criticize the patriarchal system
that is represented from Dani female figures with their life background, there by it
establishes the image of Dani women.
The results from the character identification shows that there contrafeminist
and profeminist characters in the middle of patriarchal culture. The analysis of
language aspects are used for the reflection of Dani women�s image. According to
the analysis of aspects of language usage, there are three conceptions. First, the
language showed gender differences. Second, the language refers to the symbols
of feminine and masculine. Third, as a form of criticism from women toward men
in the middle of patriarchal culture. The ideology of women's imaging proves that
women rule over theirself, always trying to be free from male dominance, and
they have right to get education. Analysis of the image of women shows Dani
women have image in the domestic sector and the image in the public sector.
Based on the research, it can be concluded that novel ethnography SKSWSD
raises the problems of women who live in the middle of the patriarchal system.
The female characters in the novel have to make a protest action for the gender
inequality they get, not merely an idea or discourse of feminism
Mechanisms of social regulation change across colony development in an ant
Get PDFabstract: Background
Mutual policing is an important mechanism for reducing conflict in cooperative groups. In societies of ants, bees, and wasps, mutual policing of worker reproduction can evolve when workers are more closely related to the queen's sons than to the sons of workers or when the costs of worker reproduction lower the inclusive fitness of workers. During colony growth, relatedness within the colony remains the same, but the costs of worker reproduction may change. The costs of worker reproduction are predicted to be greatest in incipient colonies. If the costs associated with worker reproduction outweigh the individual direct benefits to workers, policing mechanisms as found in larger colonies may be absent in incipient colonies.
Results
We investigated policing behaviour across colony growth in the ant Camponotus floridanus. In large colonies of this species, worker reproduction is policed by the destruction of worker-laid eggs. We found workers from incipient colonies do not exhibit policing behaviour, and instead tolerate all conspecific eggs. The change in policing behaviour is consistent with changes in egg surface hydrocarbons, which provide the informational basis for policing; eggs laid by queens from incipient colonies lack the characteristic hydrocarbons on the surface of eggs laid by queens from large colonies, making them chemically indistinguishable from worker-laid eggs. We also tested the response to fertility information in the context of queen tolerance. Workers from incipient colonies attacked foreign queens from large colonies; whereas workers from large colonies tolerated such queens. Workers from both incipient and large colonies attacked foreign queens from incipient colonies.
Conclusions
Our results provide novel insights into the regulation of worker reproduction in social insects at both the proximate and ultimate levels. At the proximate level, our results show that mechanisms of social regulation, such as the response to fertility signals, change dramatically over a colony's life cycle. At the ultimate level, our results emphasize the importance of factors besides relatedness in predicting the level of conflict within a colony. Our results also suggest policing may not be an important regulatory force at every stage of colony development. Changes relating to the life cycle of the colony are sufficient to account for major differences in social regulation in an insect colony. Mechanisms of conflict mediation observed in one phase of a social group's development cannot be generalized to all stages.The electronic version of this article is the complete one and can be found online at: http://bmcevolbiol.biomedcentral.com/articles/10.1186/1471-2148-10-32
Insecticide and miticide registrations in Oregon caneberries
No full textDani Lightle, Pesticide Registration Research Leader, Oregon State University ; support provided by the Oregon Raspberry and Blackberry Commission.Title from PDF caption (viewed on July 8, 2020).This archived document is maintained by the State Library of Oregon as part of the Oregon Documents Depository Program. It is for informational purposes and may not be suitable for legal purposes.Mode of access: Internet from the Oregon Government Publications Collection.Text in English
A clinical deep learning framework for continually learning from cardiac signals across diseases, time, modalities, and institutions.
Get PDFDeep learning algorithms trained on instances that violate the assumption of being independent and identically distributed (i.i.d.) are known to experience destructive interference, a phenomenon characterized by a degradation in performance. Such a violation, however, is ubiquitous in clinical settings where data are streamed temporally from different clinical sites and from a multitude of physiological sensors. To mitigate this interference, we propose a continual learning strategy, entitled CLOPS, that employs a replay buffer. To guide the storage of instances into the buffer, we propose end-to-end trainable parameters, termed task-instance parameters, that quantify the difficulty with which data points are classified by a deep-learning system. We validate the interpretation of these parameters via clinical domain knowledge. To replay instances from the buffer, we exploit uncertainty-based acquisition functions. In three of the four continual learning scenarios, reflecting transitions across diseases, time, data modalities, and healthcare institutions, we show that CLOPS outperforms the state-of-the-art methods, GEM1 and MIR2. We also conduct extensive ablation studies to demonstrate the necessity of the various components of our proposed strategy. Our framework has the potential to pave the way for diagnostic systems that remain robust over time
Contextualization of the Gospel in the Context of the Life of the Dani Tribe in Papua
Get PDFBefore the ascension of Jesus Christ into heaven, He gave the commandment, a Great Commission to preach the gospel to all nations. Dani tribe is one of the tribes in Papua and is certainly one of the objectives of the evangelistic mission. And it is not only Christianity that wants to reach out there but other religions as well. To carry out this mission, in this study the author formulated how the gospel could be understood and accepted by the Dani tribe. The authors used qualitative methods with a literature study approach. Each nation has a different culture and life from each other, even if the area is in the same country, When the Gospel will be preached in that area, the evangelists must study the context of the people's lives so that the gospel can be contextualized into the culture of life of the people. The authors hope it will benefit evangelists who will carry out missions on the Dani tribe through stone-burning ceremonies, work, and daily life
CROCS: Clustering and revival of cardiac signals based on patient disease class, sex, and age
Get PDFThe process of manually searching for relevant instances in, and extracting information from, clinical databases underpin a multitude of clinical tasks. Such tasks include disease diagnosis, clinical trial recruitment, and continuing medical education. This manual search-and-extract process, however, has been hampered by the growth of large-scale clinical databases and the increased prevalence of unlabelled instances. To address this challenge, we propose a supervised contrastive learning framework, CROCS, where representations of cardiac signals associated with a set of patient-specific attributes (e.g., disease class, sex, age) are attracted to learnable embeddings entitled clinical prototypes. We exploit such prototypes for both the clustering and retrieval of unlabelled cardiac signals based on multiple patient attributes. We show that CROCS outperforms the state-of-the-art method, DTC, when clustering and also retrieves relevant cardiac signals from a large database. We also show that clinical prototypes adopt a semantically meaningful arrangement based on patient attributes and thus confer a high degree of interpretability
CLOCS: contrastive learning of cardiac signals across space, time, and patients
Get PDFThe healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity
Recommended from our members
Teacher Education as a Site of Nonviolent Resistance
No full textIn this audio piece, Dani O’Brien interviews the President of the Massachusetts Teacher’s Association (MTA), Barbara Madeloni. The MTA is the 110,000-member union representing educators in public PK-12 and higher education in Massachusetts. Barbara Madeloni is an education activist, a former high school English teacher, and a teacher-educator at the University of Massachusetts Amherst. She was elected President of the MTA in 2014, supported by a grassroots organization of teachers working to move the union in a more progressive, and activist, direction. In the interview, Barbara explains how the corporate assault on education produces structural violence, and talks about the nonviolent resistance she and other educators are engaged in. She discusses her campaign to become union president and the work she hopes to accomplish in that office.Kysa Nygreen is Assistant Professor of Education at University of Massachusetts Amherst. Her research and teaching focus on diversity and equity in education, community-based education, critical ethnography, and critical pedagogy. She is the author of These Kids: Identity, Agency, and Social Justice at a Last Chance High School (University of Chicago Press). Dani O’Brien is an educator, activist and doctoral candidate living in Western Massachusetts. She is a former English teacher who is currently working on her Ph.D. in Teacher Education and Curriculum Studies at the University of Massachusetts, Amherst. Her activism and research attempt to understand and push back against neoliberal policies that undermine the promise of public education and stand in the way of social justic
- …
