We held WiDS2020 Subotica on 29-April-2020 as an online event. It featured outstanding women within the DS community.
Due to the situation regarding COVID-19 we had to move our event online with the programme containing five presentations by outstanding women directly engaged within the world of data science.
This year we were aiming to gather a number of women in DS not just from Serbia, but to connect regionally. We were also intending to engage with young women still attending local universities. However, despite not being able to go ahead with our originally planned programme, through this online event we have managed to bring together a number of inspirational women directly engaged with DS with in the region.
It has certainly motivated and galvanised us and we should build upon this to create a stronger regional community within the global WiDS. It would provide us with the opportunity to outreach to women and young girls in more remote places within the region. Encouraging, inspiring and empowering them on their DS journeys are what we’re all about.
We sincerely hope that we will meet up next year in a greater number and in happier circumstances.
If you were not able to join us on 29-April you can watch the full recording of the event available here 👉🎦.
On the 29th of April, 2020 Subotica is joining the international conference WiDS. The Women in Data Science (WiDS) initiative aims to inspire and educate data scientists worldwide, regardless of gender, and support women in the field. WiDS started as a conference at Stanford in November 2015. Now, WiDS includes a global conference, with 150+ regional events worldwide including a datathon (encouraging participants to hone their skills) and a podcast (featuring leaders in the field talking about their work, and their journeys).
All genders are invited to attend WiDS regional events, which feature outstanding women within the DS community. WiDS Subotica welcomes anyone with an interest in DS. The goal is to promote DS, exchange knowledge and create a DS community among women. We are fully inclusive and respectful of LGBT identities and are welcome anyone interested in the field of DS.
Due to the situation regarding COVID-19 we have moved our even online with the programme containing five presentations by women directly engaged within the world of data science. The talks will provide an opportunity to hear about the advances and research in a number of data domains. Learn how leading women in data are advancing, and connect with potential mentors in the field.
The event is free, but registration is required by registering at 👉📄
Programme
17:00 Welcome to WiDS regional event: Introduction, Announcements
17:05 The Global WiDS opening video
17:10 Speakers:
18:55 Closing Remark
Speakers
- Maria Knorps: Challenges of “small data”
Using an example of fragrance industry data I will describe challenges of working with “small data”. First challenge is gathering the data in unified way. I will tell about the results of client’s questionnaires and how important is a unified methodology of conducting those experiments. Second challenge is data cleaning - decisions made at this stage have a huge impact on a success and extendibility of the project. Last but not least is modelling sparse data, where a classical train/test split is no longer available. I will present pitfalls that we fell into and how we climb up from them.
Maria Knorps is a Data Scientist creating analytics, BI and machine learning solutions from the data collection to the web development. She combines scientific background (PhD in fluid mechanics) with several years of industry experience. Maria believes that simple solutions and clean code are at the center of well-designed applications, thus the growing interest in functional programming.
- Agnieszka Kamińska: A secret weapon of DS projects. The importance of feature preprocessing on the example of human brain research.
Regardless of the domain, working with large and complex datasets in order to find reliable and interpretable insights brings a lot of challenges. Building an efficient data processing pipeline can be a demanding task when computational and time resources are limited. Given such context, how can we, data-driven people, find a way to tackle our research or business goals? In this talk I will focus on the critical importance of feature preprocessing - the initial phase of data science projects. I will refer to the group project for The ABCD Neurocognitive Prediction Challenge and a few lessons learned from this competition.
Agnieszka Kamińska is a Data and Science enthusiast. In her everyday work she combines analytical and research skills with machine learning knowledge in order to provide new solutions for Product Analytics purposes in OLX Group. Having a background in Cognitive Neuroscience, she is engaged in non-commercial open science projects aimed to develop open source analytical tools for reproducible neuroimaging data science. Agnieszka believes that living in a data-driven world requires building a strong and diverse community of experts understanding the nature of big data and algorithms. She started a chapter of Women in Machine Learning & Data Science in Poland to empower women and other underrepresented people in the field.
- Tijana Blagojev: Coding, Tool for Assisting Media Policy Development
Nowadays, technological advances allow for large amount of information to be gathered and used for various purposes and there is an increasing need for interdisciplinarity. It is crucial that people with expertise in particular field are skilled in coding to conduct their own analysis as well as follow and monitor the work of others. This presentation will focus on application of programming in R for media policy development, with practical examples of use of Shiny and flexdashboard packages. It will also highlight the importance of reproducibility of research that could assist in finding better legislative solutions in the media sector.
Tijana Blagojev holds a Master’s degree in Politics, Big Data and Quantitative Methods from the University of Warwick. She is also a recipient of renowned Chevening scholarship that provided her with the opportunity to study in the UK. She absolutely loves R and wants to share her knowledge with people and students in Serbia. She is a coorganiser of R-ladies Belgrade chapter.
- Željana Grbović: Wheat ear automatic detection and counting in RGB and thermal images using deep learning
The number of farmers who use smart phones is increasing rapidly and furthermore RGB and thermal cameras are becoming more and more available either as smart phone gadgets or as integrated parts of the smart phone. Using them, farmers could have early information about the wheat yield. Currently, counting ears on part of a field and extrapolating the values for the whole field requires ears to be counted manually, which is prone to subjective evaluation, takes a lot of time and requires large human resources. In the case of larger fields, samples must be taken from more than one location, which additionally slows down the process. The aim of the research was to develop a system for wheat ear recognition and counting, which is necessary step for further estimation of wheat ear coverage density in the field, and yield prediction. Images of winter wheat were taken at 4 dates during the growing season and segmented manually to acquire the ground truth. Image segmentation was done using deep learning. Namely, convolutional neural networks were applied to RGB and thermal images and the results were compared to the ground truth to assess the system accuracy. Development of a comprehensive system for ear counting and yield prediction has a huge practical value for crop monitoring and optimal decision-making in wheat production.
Željana Grbović is a young researcher at BioSense Institute and PhD student in electrical engineering at the University of Novi Sad. She is highly interested in the application of machine learning algorithms and deep learning in the field of agriculture. Her beginnings in machine learning started 2016 when her team ranked in the top 5 among 52 teams from 23 countries on prestigious competition SP Cup organized by IEEE. She received her master’s degree with the thesis about ear detection in wheat thermal images using deep neural networks. She has expanded the field experiment on the wheat involving images from mobile phones to provide early prediction yield and automatic counted ears. She is a guest researcher at Wageningen University and Research (WUR) which is declared as the world’s best agricultural university for the fourth consecutive time. She is involved in Humistatus project about the prediction of spreading fungal infection on tomatoes based on hyperspectral images funded by the company Green Yard and WUR. She was a member of the team who tested PerClass MIRA Software for hyperspectral image processing before it is launched as public. She was involved in pilot project with WUR Food safety on hyperspectral dataset of pig kidney images. Her main interests are image processing and application of transfer deep learning in plant phenotyping, food quality and safety. She is actively involved in few Horizon 2020 projects including ANTARES, Cybele and Dragon.
- Bojana Soro: Content intelligence that informs content optimisations
Data Science has dominated almost all the industries of the world today. There is no industry in the world today that does not use data. This presentation will focus on data science application in digital publishing industry. Publishers and media organizations that operate in the digital area need to listen to their readers and closely monitor content performance through different dimensions. By using insights to identify what resonates with their audience, they can explore different growth directions and business models with a higher chance of success. For the purpose of improving content performance it was used machine learning technique clustering to gain some valuable insights from data.
Bojana Soro is the Data Analyst at Content Insights. She has a Masters in Applied Mathematics. She has studyed Financial Mathematics at the University of Novi Sad. Her field of interest is Data Science. She deals with data visualization, lab research, big data, mathematical modeling, statistics, data analysis and optimisation. Her favorite software is R and she really likes to share her experience with other people who love data science. She is a member of the R-Ladies Novi Sad chapter and Data Science Serbia.
