Activity
-
Google's new algorithm just shrunk 31GB of vectors into 4GB. Storing embeddings for RAG eats memory fast. Ten million documents in float32 takes…
Google's new algorithm just shrunk 31GB of vectors into 4GB. Storing embeddings for RAG eats memory fast. Ten million documents in float32 takes…
Liked by Lauren Yee
-
🌶️ Environmental data hot take of the day... Don't make me install a Python package just to access a specific dataset! 🤦 I'm seeing an…
🌶️ Environmental data hot take of the day... Don't make me install a Python package just to access a specific dataset! 🤦 I'm seeing an���
Liked by Lauren Yee
Experience & Education
Licenses & Certifications
Publications
-
Avian Influenza Risk Surveillance in North America with Online Media
PLOS ONE
The use of Internet-based sources of information for health surveillance applications has increased in recent years, as a greater share of social and media activity happens through online channels. The potential surveillance value in online sources of information about emergent health events include early warning, situational awareness, risk perception and evaluation of health messaging among others. The challenge in harnessing these sources of data is the vast number of potential sources to…
The use of Internet-based sources of information for health surveillance applications has increased in recent years, as a greater share of social and media activity happens through online channels. The potential surveillance value in online sources of information about emergent health events include early warning, situational awareness, risk perception and evaluation of health messaging among others. The challenge in harnessing these sources of data is the vast number of potential sources to monitor and developing the tools to translate dynamic unstructured content into actionable information. In this paper we investigated the use of one social media outlet, Twitter, for surveillance of avian influenza risk in North America. We collected AI-related messages over a five-month period and compared these to official surveillance records of AI outbreaks. A fully automated data extraction and analysis pipeline was developed to acquire, structure, and analyze social media messages in an online context. Two methods of outbreak detection; a static threshold and a cumulative-sum dynamic threshold; based on a time series model of normal activity were evaluated for their ability to discern important time periods of AI-related messaging and media activity. Our findings show that peaks in activity were related to real-world events, with outbreaks in Nigeria, France and the USA receiving the most attention while those in China were less evident in the social media data. Topic models found themes related to specific AI events for the dynamic threshold method, while many for the static method were ambiguous. Further analyses of these data might focus on quantifying the bias in coverage and relation between outbreak characteristics and detectability in social media data.
Other authorsSee publication -
Spatial data issues in geographical zoonoses research
Canadian Geographer / Le Géographe canadien
Linkages between human, environmental, and animal health have been an increasingly important topic of geographical research in recent years. As more data become available for explicitly representing the geographies of these systems, and how they interact, geographers are playing an important role in shaping this research area. Whereas previously these linkages have been known, but rarely quantified, geographical data are now enabling surveillance of environmental changes, animal populations…
Linkages between human, environmental, and animal health have been an increasingly important topic of geographical research in recent years. As more data become available for explicitly representing the geographies of these systems, and how they interact, geographers are playing an important role in shaping this research area. Whereas previously these linkages have been known, but rarely quantified, geographical data are now enabling surveillance of environmental changes, animal populations, and human populations in order to realize fine-grained estimates of disease risk. In this paper, we consider the role of spatial data in this new research area, and characterize challenges of integrating and analyzing data across these domains. We explore these issues through three case studies into emerging zoonoses; avian influenza, Japanese encephalitis, and syndromic animal health surveillance. Issues of scale, availability and access, and linkage uncertainties are found to be key data issues. We anticipate these issues will be important research challenges for geographers working on zoonoses, and as part of multidisciplinary research teams. Finally, we suggest that geographers working in this area adopt the concept of vulnerability surveillance to address these issues and refocus research on vulnerable populations, interfaces, and areas.
Other authorsSee publication
Honors & Awards
-
Eliza Tschirhart Award
-
-
The Carol & Russell Muncaster Bursary Award in Geography & Environmental Studies
WLU
Authored and presented a paper in geography at the annual meetings of the Canadian Association of Geographers. The recipient is chosen by the chair of the department.
-
MS2Discovery Travel Award
MS2Discovery
Travel award granted to present research abroad
Languages
-
English
Native or bilingual proficiency
Organizations
-
Wildlife Disease Association
-
- Present -
The Canadian Association of Geographers
-
- Present -
COPEH-Canada
-
- PresentCommunity of Practice in Ecosystems approaches to Health EcoHealth Training Program brings together people from different domains who integrate, or who are looking to integrate, the ecosystem approaches to health in their work, thereby creating a network of people drawing upon the richness of these approaches. • Field experience in different areas of the Saint Lawrence River Basin illustrating the complexity of the water system and environmental challenges • Interactive class-based sessions…
Community of Practice in Ecosystems approaches to Health EcoHealth Training Program brings together people from different domains who integrate, or who are looking to integrate, the ecosystem approaches to health in their work, thereby creating a network of people drawing upon the richness of these approaches. • Field experience in different areas of the Saint Lawrence River Basin illustrating the complexity of the water system and environmental challenges • Interactive class-based sessions aimed to understand EcoHealth approaches to a diverse range of problems • Collaborative groups, activities and projects to practice and working in transdisciplinary teams
More activity by Lauren
-
I don't talk about this often, but my path into data was not only a non-traditional detour from the recording studio, it also started from the…
I don't talk about this often, but my path into data was not only a non-traditional detour from the recording studio, it also started from the…
Liked by Lauren Yee
-
"Code generation, in its default mode, is antithetical to skill retention, particularly because its UX affordances are reminiscent of a slot…
"Code generation, in its default mode, is antithetical to skill retention, particularly because its UX affordances are reminiscent of a slot…
Liked by Lauren Yee
-
At our first conference (or more precisely, our first Nature Tech Collective *Unconference*) as Echo Labs, we dove in with both feet by hosting a…
At our first conference (or more precisely, our first Nature Tech Collective *Unconference*) as Echo Labs, we dove in with both feet by hosting a…
Liked by Lauren Yee
-
A very interesting and engaging night last night at the Bristol AI Ethics meetup. As well as a talk about trust around AI systems there was a news…
A very interesting and engaging night last night at the Bristol AI Ethics meetup. As well as a talk about trust around AI systems there was a news…
Liked by Lauren Yee
-
Do not go gentle into that good night, Methane should burn and rave at close of day; Rage, rage against the dying of the light. Though wise…
Do not go gentle into that good night, Methane should burn and rave at close of day; Rage, rage against the dying of the light. Though wise…
Liked by Lauren Yee
-
🔥 Hot take: Geospatial Foundation Models (GFMs) are brittle. Real-world remote sensing deployment means models are exposed to new time periods…
🔥 Hot take: Geospatial Foundation Models (GFMs) are brittle. Real-world remote sensing deployment means models are exposed to new time periods…
Liked by Lauren Yee
-
Last week, I had the opportunity to attend the 2nd annual ESA-NASA Workshop on AI Foundation Models for Earth Observation. The conversations…
Last week, I had the opportunity to attend the 2nd annual ESA-NASA Workshop on AI Foundation Models for Earth Observation. The conversations…
Liked by Lauren Yee
-
Why data scientists are potatoes: I've spent the last 20 years of my career in data science (although not all my consulting gigs are in 'data…
Why data scientists are potatoes: I've spent the last 20 years of my career in data science (although not all my consulting gigs are in 'data…
Liked by Lauren Yee
-
New Feature Alert: Embedding Export 🚚 You can now export LGND geo-embeddings directly to your modeling stack. A single endpoint transfers hive…
New Feature Alert: Embedding Export 🚚 You can now export LGND geo-embeddings directly to your modeling stack. A single endpoint transfers hive…
Liked by Lauren Yee
-
If I ran a one-day in-person workshop in Toronto in August on shutting down software and research projects, based on https://lnkd.in/eg-qBqkK, would…
If I ran a one-day in-person workshop in Toronto in August on shutting down software and research projects, based on https://lnkd.in/eg-qBqkK, would…
Liked by Lauren Yee
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More