elen.xynogala@gmail.com bio

PLASTICITY

film, interactive installation, machine learning

This project was developed during a 6-month residency programme HIVE#03 at thecamp.
In collaboration with: Dian Song , Dongmei Lu and Myroslava Kuts.

What is Plastic?

When people think of plastic, they probably imagine half-liter bottles, fields of straws, plastic pieces inside a dead bird, single-use bags fluttering in the wind or mountains piled high with plastic trash.
But nobody thinks of the recycled plastic that is a supply of hygiene medical equipment or cosmic radiation protection. What is Plastic?
Is it an evil monster that destroys the environment that mankind depends on? Or is it a friendly creature that represents the advancement of human civilization?
We want people to understand that there are two sides to plastic. Depending on the way that people treat it, plastic can transform into a monster or a helper.
What we need is not a world without plastic.
What we need is to figure out how to use plastic in a better way.
Website

PLASTICITY was exhibited in Prototype Showcase: HIVE#03 - Collaborative Residency on September 2019.

Film

A performer creates a dialogue with different plastic objects, using dancing and body expressions.
A symbolic performance that open up discussion and guide us to rethink about plastic usage and its destination.
What is plastic?
How is our relationship with it?
Can we start over again?

Script: Dongmei Lu
Art Direction: Eleni Xynogala & Dongmei Lu
Filmmaker: Francesco Garbo
Choreography & Dance: Mimi Jeong
Sound Design: Myroslava Kuts
Costume Design: Audrey Jaillard
Light Design: Pascal Baltazar
Set up: Dian Song

Film's Poster designed by Florian Tiphoteau.
The film was presented at Athens Video Dance Project in January 2020.

Interactive Installation

Artistic 3D Model made by Soliman Lopez in Blender. / Realistic 3D Model made by Xinwei Liu in V-ray and 3ds Max.

Plastic is a “creature”.
It has two sides: the monstrous or the helper
What is it now?
It depends on how you behave.
A smart bin is integrated with the installation, therefore the “creature” have the ability to properly recognize trash and classify them into recycling categories.
When people sort their trash correctly, the creature will be activated as an alive and joyful helper, moving and creating joyful sound. On the other hand, when you don’t recycle properly, the creature will be transformed into a monster, roaring and acting aggressively .
What is your choice?

Animation of the different states of the installation in Cinema 4D.

Smart Bin

The smart bin is able to recognise and classify trash into different categories.
When people sort their trash correctly, the installation - made of plastic objects, will be activated as an alive and joyful helper, moving and creating sound.
On the other hand, if individuals don’t recycle properly, the creature will be transformed into a monster.
Multi Label Classification (MLC) model developed by the machine learning enginner Israel Goytom.
The MLC model is used to classify the material of the waste as plastic or other types. Using a pre-trained model which is trained on ImageNet with 1.2 million images as a feature extractor and then a dataset of plastic waste consists of 1000 images (open source), we trained a deep learning model for classification and detection. The model was trained on NVIDIA V1000 GPU for 6 hrs and it has 91% accuracy.

Animation of the interaction of people with the bin and the reaction of the installation and the sound in Cinema 4D.