AD ADRD small grant

 due March 17, 2023

https://grants.nih.gov/grants/guide/notice-files/NOT-AG-22-040.html

https://grants.nih.gov/grants/guide/pa-files/PAS-19-391.html

https://grants.nih.gov/grants/guide/pa-files/PAS-19-393.html

correlation matrix, predictive power score

 

https://towardsdatascience.com/rip-correlation-introducing-the-predictive-power-score-3d90808b9598

 

Association of step counts over time with the risk of chronic disease in the All of Us Research Program

https://www.nature.com/articles/s41591-022-02012-w

data set, imaging

 https://radiopaedia.org/articles/imaging-data-sets-artificial-intelligence

list of undergraduate research journals

 list of undergraduate research journals

https://www.cur.org/engage/undergraduate/journals/listing/

https://undergraduateresearch.virginia.edu/present-and-publish/undergraduate-symposia 

• Advanced Journal of Graduate Research

  Advanced Journal of Graduate Research (ISSN:2456-7108) is a refereed journal dedicated to publishing research work carried out by Bachelor/Master Degree students under the supervision of a faculty member. Normally research work carried out as a part of the undergraduate course or graduate course in the form of final year thesis (course project) will be considered in this specific graduate journal. Any mentored student may submit articles related to all area of Science and Technology including Life Science, Computer Science, Mathematics, Environmental Science, Earth Science, Agriculture Science, Medical Science, Chemical Science, Physical Science. This journal accepts original research article, review article and survey article. Normal publication is free in this journal with open access availability of published article.

names in AI research

 

Erik Brynjolfsson, promise and peril of human-like AI, Turing trap

Swati Gupta: AI4OPT

Beth Plale: AI accountability

Aaron Smith, ethics of AI in agriculture

Wendell Wallach

AI in the wild, 

Kris Hauser, AI FARMS, open-world AI

AI-EDGE, Kaushik Chowdhury, 

Machine learning for inverse problems, Alex Dimakis

AI for weather and costal forecasting, Philippe Tissot, 

Kathleen Fisher, an analytical framework for AI

Jeff Krolik

AI for social good, Michael Littman

Jim Dolon, NSF PO, Steven Thompson, AIVO/SAIL

Steve Brown, https://youtu.be/1Re9DX7cFRI 

tRNE python

 tRNE dimention reduction

https://towardsdatascience.com/an-introduction-to-t-sne-with-python-example-5a3a293108d1

EMDB

 electronic microscopy data bank

https://www.ebi.ac.uk/emdb/

new investigator in NIH diversity in genomics, bioinformatics, and bioengineering

 

New Investigators to Promote Workforce Diversity in Genomics, Bioinformatics, or Bioengineering and Biomedical Imaging Research (R01 Clinical Trial Optional)

https://grants.nih.gov/grants/guide/rfa-files/RFA-HG-21-041.html#_Section_III._Eligibility

cpsc4180 how to do presentation

 

How to do a research presentation

Qin AI 101 slides

CoLab tutorial on DNA.

cpsc4180 final project discussion

 go over student projects, poll about which project to discuss. 

go over a example research paper

https://www.nature.com/articles/s42256-022-00536-x

transition rate theory

 

https://en.wikipedia.org/wiki/Transition_state_theory 

Langevin equation

 

https://en.wikipedia.org/wiki/Langevin_equation

cpsc4180

 SFS

deep learning prediction

final project

final presentation

PULSE survey

 

State Information

I am sending you the data dictionary of the PULSE data. Once you open the file, you should be able to find a variable, named "EST_ST." As you can see, this variable indicates which state each of the respondents was from.

 

cpsc4180 one-hot encoding; project discussions

 

one-hot encoding

project presentations. 

NIH F31 Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship to Promote Diversity in Health-Related Research (Parent F31-Diversity)

 Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship to Promote Diversity in Health-Related Research (Parent F31-Diversity)

https://grants.nih.gov/grants/guide/pa-files/PA-21-052.html#_Section_II._Award

https://www.nia.nih.gov/research/training/f31-individual-fellowships-phd-students

F31 Individual Fellowships for PhD Students

NIA supports three F31 awards, one open to all PhD Students conducting aging research (PA-21-051), one open to students from underrepresented backgrounds conducting aging research (PA-21-052), and one specifically for students from underrepresented backgrounds conducting research on Alzheimer’s Disease and related dementias (PAR-21-218). All F31 recipients must be U.S. citizens or permanent residents at the time of award. View other NIA fellowships available to graduate students.

AD/ADRD

https://grants.nih.gov/grants/guide/pa-files/PAR-21-218.html

fairness in machine learing

independence

separation

sufficiency 

group fairness definitions, confusion matrix

Bias mitigation methods: preprocessing; reweighting; inprocessing; adversarial debiasing; postprocessing; reject option based classification

https://en.wikipedia.org/wiki/Fairness_(machine_learning)

https://en.wikipedia.org/wiki/Algorithmic_bias

cpsc4180 from gisaid alignment to mutations

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

How to identify mutations or variations? 

https://www.ebi.ac.uk/Tools/msa/clustalo/

>one
ChattanoogaIsAGreatPlace
>two
ChattanoogaMaybeAGreatPlace

Use AliView to explain the FASTA alignment file (gaps)

https://github.com/hongqin/Python-CoLab-bootcamp/blob/master/align2snv.ipynb

upload 0613 files to CoLab. This is too slow. So, I switched to run jupyter-notebook on my laptop

* UTC Course Evaluation 

* student presentation.

UTC individual study contract form

 

https://www.utc.edu/enrollment-management-and-student-affairs/registrar/individual-studies-contracts

network permutation

 

https://www.nature.com/articles/s43588-020-00009-4

cpsc 4180/5180 project discussion

zoom recording, live transcript

two student presentations. 

 

funding opportunites

 

https://beta.nsf.gov/funding/opportunities/research-mentoring-postbaccalaureates-biological

https://beta.nsf.gov/funding/opportunities/building-research-capacity-new-faculty-biology-brc

paperswithcode

 

https://paperswithcode.com/

python bioinfor in cpsc4180, D614G mutation

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

https://github.com/hongqin/Python-CoLab-bootcamp/blob/master/notebooks/Chapter_9-v2_Introduction_to_Biopython.ipynb 

D614G mutation annotation

mutation

TODO: 

FASTA format (GISAID)

2022 Fall acknowledgement

HQ thanks the USA NSF  award 1761839 and #2200138,  a catalyst award from the USA National Academy of Medicine, and the support from the Office of Vice Chancellor of Research at the University of Tennessee at Chattanooga. 

For covid19

HQ thanks the support of USA NSF PIPP #2200138, BD Spoke #1761839, SFS #1663105,  REU #1852042 and #2149956, and an internal CEACSE award and support from the Office of the Vice Chancellor of Research at the University of Tennessee at Chattanooga.

For REU: 

We thank the support of NSF REU #1852042 and  #2149956, and the support from the Office of Vice Chancellor of Research at the University of Tennessee at Chattanooga. 

For image related works
We thank the support of NSF Career award #1453078 and #1720215, BD Spoke  #1761839, and internal support of the University of Tennessee at Chattanooga. 


For yeast aging:
We thank the support of NSF Career award #1453078 and #1720215, BD Spoke  #1761839,  REU   #1852042, and the internal support of the University of Tennessee at Chattanooga. 

For Machine Learning
We thank the support of NSF Career award #1453078 and #1720215, BD Spoke  #1761839, and internal support of the University of Tennessee at Chattanooga. TP, DM thanks the support of a DoD capacity building grant. 

cpsc4180 biopython CDS, retrieve,

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

https://github.com/hongqin/Python-CoLab-bootcamp/blob/master/notebooks/Chapter_9-v2_Introduction_to_Biopython.ipynb 

retrieve a CDS? spike gene example. 

TODO: 

D614G mutation annotation

negative sense 

FASTA sequence

CCF journal and conference ranking

 CCF journal and conference ranking

中国计算机学会推荐国际学术会议和期刊目录

https://www.ccf.org.cn/Academic_Evaluation/By_category/

4180 biopython part 2

  

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

review of bioinformatic basic concepts

+Basic biology concept and data, 

Central Dogma: DNA (ATCG), RNA (AUCG), proteins (20 AA). Translation. Transcription. Replication. Genetic table. 

Genes. Genomes. 

Genome sequences. Expression levels.  

+biopython modules

 genbank file format; fasta file format

Breakout on final projects. 

TODO: 

retrieve a CDS? 

D614G mutation annotation

https://github.com/QinLab/aln2snv-2020format/blob/a670b48b00dffac244dc6a63bcd12cf6439c73fc/annotate_gwas_with_GFF.ipynb

Flu + RSV hybrid

 

https://medicalxpress.com/news/2022-10-flu-rsv-viruses-fuse-hybrid.html

https://www.nature.com/articles/s41564-022-01242-5

single phase versus triple phase power

https://www.fluke.com/en-us/learn/blog/power-quality/single-phase-vs-three-phase-power

In electricity, the phase refers to the distribution of a load. What is the difference between single-phase and three-phase power supplies? Single-phase power is a two-wire alternating current (ac) power circuit. Typically, there is one power wire—the phase wire—and one neutral wire, with current flowing between the power wire (through the load) and the neutral wire. Three-phase power is a three-wire ac power circuit with each phase ac signal 120 electrical degrees apart.

cpsc4180 biopython

 

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

+Basic biology concept and data, 

Central Dogma: DNA (ATCG), RNA (AUCG), proteins (20 AA). Translation. Transcription. Replication. Genetic table. 

Genes. Genomes. 

Genome sequences. Expression levels.  

+biopython modules

biopython tutorial

py4bio

https://github.com/agmcfarland/biopython_workshop

cpsc4180/5180 covid19-pandas, project discussion

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concepts or skills that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

Pandas on covid

GoogleDrive link in CoLab

final project milestones

N3C self study notes

how to duplicate code workbook 

https://unite.nih.gov/workspace/slate/documents/test-vector-duplication

https://unite.nih.gov/workspace/compass/view/ri.compass.main.folder.7403d6c8-3bab-4282-8904-6bcca88c08b9

https://unite.nih.gov/workspace/compass/view/ri.compass.main.folder.7403d6c8-3bab-4282-8904-6bcca88c08b9

NLM R25 program

SeattleStatSummer for Biomedical Data Science Research Training

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631342

Attracting Talented and Diverse Students to Biomedical Informatics and Data Science Careers Through Short-Term Study at OHSU

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10630618

Place-based Culturally Responsive Health Informatics Research Education (PHIRE) Program

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631819

Buffalo Research Innovation in Genomic and Healthcare Technology (BRIGHT) Short-Term Training and Education

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631367

DataWiz-IN scholars program for Biomedical Informatics workforce in Indiana

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631297

Biomedical Informatics and Data Science at Institute for Informatics (BIDS@I2)

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631739

Training and Experiential Learning in Biomedical Informatics (TExBioMed)

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631457

Culturally Augmented Learning In Biomedical Informatics Research (CALIBIR) Program

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631379

OSU Summer Internship Program in Biomedical Informatics and Data Science

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631689

The Biomedical Informatics and Behavioral Sciences (BIBS) Summer Research Program

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10631581

Building Accessible and Inclusive Paths for Students in Biomedical Informatics and Data Science

https://reporter.nih.gov/search/SN29ZULFFUSU5OR1aFTQiw/project-details/10630855

cpsc 4180/5180 pandas

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concept or skill that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in: 

midterm-review (volunteer to share their videos? )

cpsc4180/5180 python lec3 numpy

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concept or skill that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

PET challenge

Python lec 3. Numpy (numpy backend is C). 

Go over CoLab and GoogleDrive demo

Midterm exam peer-review

How to compete (Phase 2)

1. Only blue teams who participated in Phase 1 and met minimum requirements are eligible to participate in Phase 2. Eligible teams are automatically registered. If you need to make changes to your team, please contact info@drivendata.org.
2. Get familiar with the problem through the problem description and code submission format pages.
3. Develop and submit your centralized solution. Check out the centralized code submission format page for more details.
4. Develop and submit your federated solution. Check out the federated code submission format page for more details.

Data overview

Code skeleton

https://github.com/drivendataorg/pets-prize-challenge-runtime

 

cpsc4180 20221005Wed Python lec 2, data type

   == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concept or skill that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Conda environment. 

Python lec 2. Data types. 

 

MPC and data privacy

MPC and data privacy

note:

 threshold cryptography is often superior to block chain in many situation, because block chain are often used as a way of encryption?!

https://en.wikipedia.org/wiki/Threshold_cryptosystem 

+ joshua baron, DARPA

+ kurt nielsen, partisia blockchain

+ dan boneh, Stanford, https://crypto.stanford.edu/~dabo/pubs/pubs.html 

+ mariana raykova, google/columbia

zero knowledge authentication, distributed prover

N3C data download policy

 https://zenodo.org/record/4743249#.Yzx0pOzMLzf

cpsc4180 20221003 Mon

  == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what do you think are the most important concept or skill that we have discussed today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Conda environment. 

Show the hidden file .RData. A student show that RStudio can disable the loading of workspace. 

Python 1a. Quick start, Jupyter-notebook, 

adobe image highlights incompatible with Apple Preview

 

adobe image highlights incompatible with Apple Preview (show as yellow area that blocked the original view). 

Adobe filled box can work. 

GISAID and NCBI sars-cov-2 reference genomes

NCBI uses wuhan-hu-1

GISAID uses wuhan-hu-4. 

The two sequences only differ in the polyA tails. Qin verified this using MEGA alignment. 

So, wuhan-hu-1 and wuhan-hu-4 share the same gene coordinates, same GFF 

mentorship versus advisement

 mentorship versus advisement

mentorship means the person as a whole. 

advisement is just the academic advisement. 

cpsc4180 20220928 Wed

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what topics or question should we discuss today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: not today

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

go over final topics in the shared spread sheets

set up breakout room for students to discuss 2022 midterm project 1 and 2. 

midterm project

final project

machine learning model attrition challenge

 

machine learning model attrition challenge

https://mlmac.io/#submission

cpsc4180 midterm and final topic discussion

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q what topics or question should we discuss today? 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: not today

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Go over screencast effort in rubric. 

set up breakout room for students to discuss 2022 midterm project 1 and 2. 

breakout room discussion on final project topic, coding problems. When breakout rooms are assigned randomly, some room end up with all quiet personalities, and it become really awkward. When people are free to join any room on their own, a third of the class joined the first room. 

4 breakout room : 18:17 --> 

TODO: Worksheet on final project topic. what references (background on importance)

google data set search

 

https://datasetsearch.research.google.com/

COVID-19 death by age and sex

 

https://data.cdc.gov/NCHS/Provisional-COVID-19-Deaths-by-Sex-and-Age/9bhg-hcku

CPSC4180 2022 09 26 Mon, final project discussion

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q: what concept and skills do you think are useful today? do you find breakout room discussion helpful? questions on other videos. 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: not today

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Socrative

set up breakout room for students to discuss final project topics

breakout room discussion on final project topic, coding problems. When breakout rooms are assigned randomly, some room end up with all quiet personalities, and it become really awkward. When people are free to join any room on their own, a third of the class joined the first room. 

TODO: Worksheet on final project topic. what references (background on importance)

AllOfUs location

 state location 

https://aousupporthelp.zendesk.com/hc/en-us/articles/4583333207956-Accessing-geolocation-data-

cpsc4180 Wed, midterm Q&A, final project topic discussion

== pre-class to do: 

socrative questions (questions on contents from last lecture ): Q: what concept and skills do you think are useful today? do you find breakout room discussion helpful? questions on other videos. 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: not today

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Go over screencast effort in rubric. 

set up breakout room for students to discuss 2022 midterm project 1 and 2. 

breakout room discussion on final project topic, coding problems. When breakout rooms are assigned randomly, some room end up with all quiet personalities, and it become really awkward. When people are free to join any room on their own, a third of the class joined the first room. 

TODO: Worksheet on final project topic. what references (background on importance)

OMOP common data model

 

https://ohdsi.github.io/CommonDataModel/cdm60.html#Clinical_Data_Tables

Clinical data tables

allofus research workbench log

 

https://docs.google.com/spreadsheets/d/1dsvJV8B7EXQj5EWa2XG-KAhs-l7FsQnyJSSFMstLF2U/edit#gid=225511499

https://aousupporthelp.zendesk.com/hc/en-us/articles/4614687617556-How-the-All-of-Us-Genomic-data-are-organized

https://aousupporthelp.zendesk.com/hc/en-us/categories/5942702296468-Working-with-Data

https://aousupporthelp.zendesk.com/hc/en-us/articles/360040452471-How-do-I-cite-the-Researcher-Workbench-in-my-grants-or-publications-

user support hub: submit ticket for questions. 

cpsc4180, midterm prep, final project discussion

 == pre-class to do: 

add 2021 midterm project 2 videos. DONE

socrative questions (questions on contents from last lecture ): Q: what concept and skills do you think are useful today? Many picked normalization. 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: not today

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

set up breakout room for students to discuss midterm project 2. 

midterm global regions partitions among students. 

previous student midterm videos

Worksheet on final project topic

Flip classroom: assign previous lectures on input, output, loops, simple stats. 

observation: 

one student said that it feels nervous to talk and be video recorded. 

some breakout room discussion last longer. 

students asked how much screencast should be expected. I revised rubric to make this part 10pt. (Need to discuss this next time)

CPSC 4180, google mobility, covid19

 == pre-class to do: 

socrative questions (questions on contents from last lecture ): Q: what concept and skills do you think are useful today? Many picked normalization. 

update Canvas course materials, update learning objectives. assignments as needed: 

Test-run code: Rmd -> HTML report with content. 

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Review Chapter 2

R-COVID19  Chapter 3. Google Mobility. 

zoom, turn live caption on, record

socrative review

Running in RStudio

Ch3 on JHUCovid19 analysis, with Google Mobility. 

Last year: 

 == pre-class to do: 

calendar email invitation: done

socrative questions (questions on contents from last lecture ): 

update Canvas course materials, update learning objectives. assignments as needed: done

Test-run code: Rmd -> HTML report with content. done

* GitHub has a connection problem today due to hurrican Ida?!. So, we have to download the jhu data manually. *

== In-class to do: 

clean up destktop space, calendars, 

ZOOM, live transcript (start video recording). 

Socrative sign in 

Review Chapter 2

R-COVID19  Chapter 3. Google Mobility. 

R cdcfluview package

 https://github.com/hrbrmstr/cdcfluview

cnn filter, stride, paddling

# Create 10 random images of shape (1, 28, 28)

images = torch.rand(10, 1, 100, 50)

# Build 6 conv. filters

conv_filters = torch.nn.Conv2d(in_channels=1, out_channels=6, kernel_size=10, stride=4, padding=0)

print(output_feature.shape)

torch.Size([10, 6, 23, 11])

conv_filters = torch.nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, stride=4, padding=0) # Convolve the image with the filters output_feature = conv_filters(images) print(output_feature.shape)

torch.Size([10, 6, 24, 12])

conv_filters = torch.nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, stride=5, padding=0) # Convolve the image with the filters output_feature = conv_filters(images) print(output_feature.shape)

torch.Size([10, 6, 20, 10])

 

defense against inference attack

 defense against inference attack

https://arxiv.org/pdf/1806.01246.pdf 

dropout in deep neural networks

model stacking, Model stacking is a major class of ensemble learning

cpsc4180 lec4

 zoom, turn live caption on, record

socrative review

Running in RStudio

go through JHU data set R, chapter 1 and Chapter 2. Next time, Ch3 on JHUCovid19 analysis, with Google Mobility. 

allofus research workbench

The 1 min summary? All of Us data are made available in a Curated Data Repository (CDR). Participants may contribute any combination of survey, physical measurement, and electronic health record data. Not all participants contribute all possible data types. Each unique piece of health data is given a unique identifier called a concept_id and organized into specific tables according to our Common Data Model. You can use these concept_ids to query the CDR and pull data on specific health topics relevant to your analysis. See the Researcher Workbench Support Hub section on Learning the Basics of the All of Us Dataset for more information.

What are concept sets? 

Burrows–Abadi–Needham BAG logic

 

Burrows–Abadi–Needham (BAN) logic

https://en.wikipedia.org/wiki/Burrows%E2%80%93Abadi%E2%80%93Needham_logic#:~:text=Burrows%E2%80%93Abadi%E2%80%93Needham%20logic%20(,secured%20against%20eavesdropping%2C%20or%20both.

PET privacy enhancing techniques

Referecne:  https://www.drivendata.org/competitions/98/nist-federated-learning-1/rules/

privacy-preserving federated learning (PPFL) solutions

 democracy-affirming technologies.

 the global federated model is trained, the parameters related to the local models could be used to learn about the sensitive information contained in the training data of each client. Similarly, the released global model could also be used to infer sensitive information about the training datasets used.

1.4 GOALS AND OBJECTIVES:

• Drive innovation in the technological development and application of novel privacy enhancing technologies;

• Deliver strong privacy guarantees against a set of common threats and privacy attacks; and

• Generate effective models to accomplish a set of predictive or analytical tasks that support the use cases.

Organizers seek to mature federated learning approaches and build trust in adoption by accelerating the development of efficient PPFL solutions that leverage a combination of input and output privacy techniques to:

Phase 1: Concept Paper. Blue Team Participants will produce a technical white paper (“Concept Paper” or “White Paper”) setting out their proposed solution approach. Technical papers will be evaluated by a panel of judges across a set of weighted criteria. Participants will be eligible to win prizes awarded to the top technical papers, ranked by points awarded.

As you propose your technical solutions, be prepared to clearly describe the technical approaches and sketch out proof of or justification for privacy guarantees. Participants should consider a broad range of privacy threats during the model training and model use phases and consider technical and process aspects including but not limited to cryptographic and non-cryptographic methods, and protection needed within the deployment environment.

Successful technical approaches and proofs of privacy guarantees will include the design of any algorithms, protocols, etc. utilized, as well as formal or informal arguments of how the solution will provide privacy guarantees. Participants will clearly list any additional privacy issues specific to the technological approaches used and justify initial enhancements or novelties compared to the current state-of-the-art. Participant submissions must describe how the solution will cater to the types of data provided to participants and how generalizable the solution is to multiple domains. Expected efficiency/scalability of improvements, privacy vs. utility trade off should be articulated, if possible, at this conceptual stage.

Q: what is the definition of privacy guarantee? 

a one-page abstract and a Concept Paper.

Abstract: The one-page abstract must include a title and a brief description of the proposed solution, including the proposed privacy mechanisms and architecture of the federated model. The description should also describe the proposed machine learning model and expected results with regard to accuracy. Successful abstracts will outline how solutions will achieve privacy while minimizing loss to accuracy, a proposed solution, and the anticipated results, as more fully described on the Challenge Website. Abstracts must be submitted by following the instructions on the Challenge Website. Abstracts will be screened by the DrivenData and Organizers’ staff for contest eligibility and used to ensure the composition of the judging panel’s expertise aligns to proposed solutions that will be evaluated throughout the course of the Challenge. Feedback will not be provided.
Concept Paper: The Concept Paper should conceptualize solutions that describe the technical approaches and lay out the proof of privacy guarantees that solve a set of predictive or analytic tasks that support the use cases. Successful Concept Papers will incorporate the originally submitted abstract and be no more than ten pages in length. References will not count towards page length. Participant submissions shall:

• Include a title and abstract for the solution

• Clearly articulate the selected track(s) the solution addresses, understanding of the problem, and opportunities for privacy technology within the current state-of-the-art.

• Clearly describe the technical approaches and proof of privacy guarantees based on their described threat model, including:

• The design of any algorithms, protocols, etc. utilized,

• The formal or informal arguments of how the solution will provide privacy guarantees.

• Clearly list any additional privacy issues specific to the technological approaches used.

• Justify initial enhancement or novelty compared to the state-of-the-art.

• Articulate:

• The expected efficiency and scalability of the privacy solution,

• The expected accuracy and performance of the model,

• The expected tradeoffs between privacy and accuracy/utility,

• How the explainability of model outputs may be impacted by your privacy solution,

• The feasibility of implementing the solution within the competition timeframe.

• Describe how the solution will cater to the types of data provided to participants and articulate what additional work may be needed to generalize the solution to other types of data.

• Articulate the anticipated use and purpose of licensed software.

• Be free from typographical and grammatical errors.

Participants should refer to Section 7 on general submission requirements for additional guidance and style guidelines.
Judges will score the Concept Papers against the weighted criteria outlined in the table below. Solutions will need to carefully consider trade-offs between criteria such as privacy, accuracy, and efficiency, and should take the weightings of the criteria into account when considering these trade-offs. Concept Papers must also demonstrate how acceptable levels of both privacy and accuracy will be achieved – one must not be completely traded off for the other (a fully privacy-preserving but totally inaccurate model is not of use to anyone). Proposals that do not sufficiently demonstrate how both privacy and accuracy will be achieved will not be eligible to score points in the remaining criteria.

federated scope

 Alibaba federated learning

https://github.com/AI-in-Biomedical-Science/FederatedScope#quick-start

Concur travel reimbursement request

 

I submitted CONCUR Philadelphia ICIBM meeting travel reimbursement request. When I uploaded the hotel, there are errors for allowance. I then created Itinerary to add per diem, and the allowance error went away. 

So, next time, I should try create Itinerary first, and then upload hotel. 

To create a Travel Allowance Itinerary for an already created report:

1. Log in to Concur.
2. Click on Expense at the top of the screen.
3. Open your existing expense report.
4. Click Details.
5. Under the Travel Allowance section, click New Itinerary.
6. Populate all required fields (be accurate with dates and times).
7. Click Save.

Active Presenter

 screencast, and video editing

https://atomisystems.com/download/ 

4180 day 3

 zoom, turn live caption on, record

review simple R

learning R with GISAID 

Running in RStudio

Next time, go through JHU data set. 

ODE under uncertainty

 ODE under uncertainty

CyptTen

 

https://ai.facebook.com/blog/crypten-a-new-research-tool-for-secure-machine-learning-with-pytorch/

https://crypten.readthedocs.io/en/latest/

hormophic encrption

 holomorphic encryption: 

Enc(m1) + Enc(m2) = Enc( m1 + m2) 

Enc(m1) x Enc(m2) = Enc( m1 x m2) 

So, an untrusted entity can compute addition or multiplication without decryption. 

https://en.wikipedia.org/wiki/Homomorphic_encryption

Fully homomorphic encryption (FHE)

From Wikipedia:

Fourth-generation FHE[edit]

In 2016, Cheon, Kim, Kim and Song (CKKS)^[35] proposed an approximate homomorphic encryption scheme that supports a special kind of fixed-point arithmetic that is commonly referred to as block floating point arithmetic. The CKKS scheme includes an efficient rescaling operation that scales down an encrypted message after a multiplication. For comparison, such rescaling requires bootstrapping in the BGV and BFV schemes. The rescaling operation makes CKKS scheme the most efficient method for evaluating polynomial approximations, and is the preferred approach for implementing privacy-preserving machine learning applications. The scheme introduces several approximation errors, both nondeterministic and deterministic, that require special handling in practice.^[36]

A 2020 article by Baiyu Li and Daniele Micciancio discusses passive attacks against CKKS, suggesting that the standard IND-CPA definition may not be sufficient in scenarios where decryption results are shared.^[37] The authors apply the attack to four modern homomorphic encryption libraries (HEAAN, SEAL, HElib and PALISADE) and report that it is possible to recover the secret key from decryption results in several parameter configurations. The authors also propose mitigation strategies for these attacks, and include a Responsible Disclosure in the paper suggesting that the homomorphic encryption libraries already implemented mitigations for the attacks before the article became publicly available. Further information on the mitigation strategies implemented in the homomorphic encryption libraries has also been published.^[38][39]