The Fifth Elephant 2017

On data engineering and application of ML in diverse domains

##Theme and format
The Fifth Elephant 2017 is a four-track conference on:

  1. Data engineering – building pipelines and platforms; exposure to latest open source tools for data mining and real-time analytics.
  2. Application of Machine Learning (ML) in diverse domains such as IOT, payments, e-commerce, education, ecology, government, agriculture, computational biology, social network analysis and emerging markets.
  3. Hands-on tutorials on data mining tools, and ML platforms and techniques.
  4. Off-the-record (OTR) sessions on privacy issues concerning data; building data pipelines; failure stories in ML; interesting problems to solve with data science; and other relevant topics.

The Fifth Elephant is a conference for practitioners, by practitioners.

Talk submissions are now closed.

You must submit the following details along with your proposal, or within 10 days of submission:

  1. Draft slides, mind map or a textual description detailing the structure and content of your talk.
  2. Link to a self-record, two-minute preview video, where you explain what your talk is about, and the key takeaways for participants. This preview video helps conference editors understand the lucidity of your thoughts and how invested you are in presenting insights beyond your use case. Please note that the preview video should be submitted irrespective of whether you have spoken at past editions of The Fifth Elephant.
  3. If you submit a workshop proposal, you must specify the target audience for your workshop; duration; number of participants you can accommodate; pre-requisites for the workshop; link to GitHub repositories and documents showing the full workshop plan.

##About the conference
This year is the sixth edition of The Fifth Elephant. The conference is a renowned gathering of data scientists, programmers, analysts, researchers, and technologists working in the areas of data mining, analytics, machine learning and deep learning from different domains.

We invite proposals for the following sessions, with a clear focus on the big picture and insights that participants can apply in their work:

  • Full-length, 40-minute talks.
  • Crisp, 15-minute talks.
  • Sponsored sessions, of 15 minutes and 40 minutes duration (limited slots available; subject to editorial scrutiny and approval).
  • Hands-on tutorials and workshop sessions of 3-hour and 6-hour duration where participants follow instructors on their laptops.
  • Off-the-record (OTR) sessions of 60-90 minutes duration.

##Selection Process

  1. Proposals will be filtered and shortlisted by an Editorial Panel.
  2. Proposers, editors and community members must respond to comments as openly as possible so that the selection processs is transparent.
  3. Proposers are also encouraged to vote and comment on other proposals submitted here.

Selection Process Flowchart

We will notify you if we move your proposal to the next round or reject it. A speaker is NOT confirmed for a slot unless we explicitly mention so in an email or over any other medium of communication.

Selected speakers must participate in one or two rounds of rehearsals before the conference. This is mandatory and helps you to prepare well for the conference.

There is only one speaker per session. Entry is free for selected speakers.

##Travel grants
Partial or full grants, covering travel and accomodation are made available to speakers delivering full sessions (40 minutes) and workshops. Grants are limited, and are given in the order of preference to students, women, persons of non-binary genders, and speakers from Asia and Africa.

##Commitment to Open Source
We believe in open source as the binding force of our community. If you are describing a codebase for developers to work with, we’d like for it to be available under a permissive open source licence. If your software is commercially licensed or available under a combination of commercial and restrictive open source licences (such as the various forms of the GPL), you should consider picking up a sponsorship. We recognise that there are valid reasons for commercial licensing, but ask that you support the conference in return for giving you an audience. Your session will be marked on the schedule as a “sponsored session”.

##Important Dates:

  • Deadline for submitting proposals: June 10
  • First draft of the coference schedule: June 20
  • Tutorial and workshop announcements: June 20
  • Final conference schedule: July 5
  • Conference dates: 27-28 July

##Contact
For more information about speaking proposals, tickets and sponsorships, contact info@hasgeek.com or call +91-7676332020.

Hosted by

The Fifth Elephant - known as one of the best data science and Machine Learning conference in Asia - has transitioned into a year-round forum for conversations about data and ML engineering; data science in production; data security and privacy practices. more

Preeti Negi

@preeti14dec

ML Goes Fruitful

Submitted Jun 10, 2017

Industry is demanding for the real-time interactions, automation[2] and decision making. The latest trends like machine learning, Internet of Things, Artificial Intelligence, Virtual Reality, Digitization, Blockchain are booming in the market and can be leveraged to meet market demand. Highest customer experience is the key, that can be achieved by minimizing defects in the product. Food processing assembly is demanding for automatic detection/sorting/removing of rotten fruits and vegetables.
The ability to segregate material using robot arm in reusability scenarios (such as electronic waste segregation) requires detection of object. This workshop presents hands-on session to build object detection machine learning model using Google TensorFlow Library[1]. Learned model will be further optimized to fit into mobile or raspberry pi. Workshop gives end to end experience of installation, development and testing of food processing production scenario. Finally completing the exercise with camera enabled mobile or raspberry pi for live actions (fruit detection using camera).

The in-depth discussions with end to end hands-on experience on building fruit detection will equip attendees with:
•Gaining confidence in machine learning to identify more scenario in different industry domains.
•Learning of TensorFlow library[1], food processing scenario, Python, Docker, machine learning classification techniques (parameters for testing accuracy), Raspberry Pi/mobile app.
•Feeling of achievement by creating end to end fruit detection application.
•Understanding the integration of varied technologies such as python, machine learning, IoT, mobile etc.

The workshop is intended for Beginners who are interested in learning ML Image classification and its applications.
The workshop is for diverse audience: e.g. industry professionals, students, graduates, post-graduates etc.

Outline

To cater to the high demand of automation in food processing industry, machine learning object detection plays a vital role in the production line. In this workshop, we propose the fruit-salad processing scenario where two to four different fruits are being processed by single production line. The fruits are lined up in the production line and automation of removal of rotten fruits is achieved using image detection technique. Further on production line, each fruit is individually processed depending upon the specific fruit, for this we need fruit detection technique to automate the process. Finally packing the mixed fruit salad is executed. Overall in this use case we have avoided manual efforts for removal of rotten fruit, also the need of separate production line for each fruit for getting it processed such as peeling and cutting.
Firstly, to ensure the high quality of the fruit, the rotten fruits should be discarded. A robot arm is trained using machine learning to identify and dispose such rotten fruits from the production line. Secondly, the good quality fruits are to be segregated for cutting. Each fruit needs a different handling before packaging. For instance, an orange need to be peeled off and apple needs a deep cleansing before making a salad. While this is on production line a robot arm picks orange for peeling process execution. Finally, followed by fruit cutting/assembling process. To execute this process in automated way production line would require efficient fruit detection mechanism. To achieve the fruit detection, one of the solution is training the classification model and deploying it on Raspberry Pi unit enabled with live camera on the production line.

The focus in our fruit detection problem is to develop a model that can identify our salad fruits with high accuracy.
In this workshop participants, will get hands-on experience on, how to build a fruit detection using camera based application on mobile (android application) or Raspberry Pi.

It is important for participants of workshop to understand the scenario so that each of them can start thinking about it in the domain they are expert or have knowledge or are willing to explore in future. Our goal would be to trigger the thinking on business related problems in automation & real-time decision making in varied industry domain and to engage them in discussion during the workshop and later.

We also identified these business use cases from different industries-
Healthcare- identifying diseases like tumors, diabetes, cancer etc.
Food Sector- provide useful information like nutritional value, quality etc. of the fruits and vegetables.
Agriculture Sector- identifying crop diseases or automation of sorting, segregation and packaging.
Retail- identifying the quality of the products and remove defective products.

Overall the production line fruit detection problem is much simpler, since the image background remains same (production line background) as compared to fruit detection at other location. For example, detecting a watermelon of different size or cut in varied background is much difficult as compared to detecting watermelon of same size with similar background. This workshop would provide insights on training data and business scenario for learning the images. The participants would learn the complete case study and application of machine learning technology. While machine learning plays important role, to build the complete case we need other technologies too, for which they would get the knowledge to utilize the learned model in devices (Raspberry Pi or mobile).

Flow of Course Content:

The facilitators will guide the hands-on workshop to achieve fruit detection using the machine learning image classification TensorFlow library [1].
Workshop will provide the presentation (discussions for in-depth understanding of the topic) as well as hands-on machine learning fruit detection implementation experience for the participants. They would also create an application using the learned model in python or android to classify the object using live camera of the device.

Introduction (40m)
•Giving background on object detection/image classification problem.
•Architecture.
•Answering why TensorFlow is effective & efficient way to solve this problem.

Problem Statement (10m)
•Understanding the case study of fruit salad problem.

Solution (110m)
•Setting the Docker.
•Installing TensorFlow image.
•Downloading training and test images of fruits from repository.
•Training and testing the model.
•Learning parameter details to check accuracy with varied parameters. To give them understand of training data vs accuracy.
•Studying the analytics for trained model.
•Optimize the trained model to fit the memory space mobile or Raspberry Pi.
•Build android app utilizing the camera live feed for detecting the fruit. (We can also opt for camera enabled Raspberry Pi for classifying).

Summary and Conclusion (20m)
•Summarize the key points.
•Facilitator would share their experiment experience
during learning and classifying to help participant with deeper knowledge. The challenges that we faced were
performance, accuracy and system crashes. We will share how we overcome them and how it can be avoided while
implementation.

Pre-requisites: The participant would be requiring laptop, android mobile or Raspberry Pi (optional) with camera attached for the workshop. Workshop takes care of installation of required library and downloadable code for the smooth sailing.

Workshop Material: The Github link for workshop resources- https://github.com/mlsource/fruitclassifier .
It includes fruit detection Python script and fruits images for training and testing.

References:
[1] https://www.tensorflow.org/
[2] https://www.docker.com/community-edition

Requirements

Laptop (if possible install Android Studio for app deployment https://developer.android.com/studio/index.html)
Android mobile or raspberry pi (optional) with camera attached for the workshop.

Speaker bio

  1. Preeti Negi
    Preeti has 9 years of industry experience with SAP Labs India Pvt. Ltd. She has worked on innovation projects- Simplify Predictive Analytics for multiple industries solutions, Machine Learning Image classification for fruit detection, Optimizing the usage of Learning Rooms through IoT Solutions, Contract Approval SAP Fiori app. Her area of interest is to solve multiple industry problems using Machine Learning Prediction and Classification techniques.
    Preeti was the speaker at:
    •SAP HANA & IoT Meet-Up Event 2016. http://meetu.ps/31F5kj, Training Resources: https://github.com/SAPIoTGGN/sap-cloud-and-iot
    •SAP d-kom 2015 Silicon Valley (US) presenting Simplified Predictive Analytics using HANA PAL Libraries Linear Regression algorithm.
    •Official trainer for ‘Effective Communication with customers and colleagues’ workshops at SAP Labs India since 2015 till date.
    •‘Work with Customers’ Workshop for SRM Noida Customer in 2016.
    •Empowering Workshop for Israel Customer in 2015.
    •SAP Labs Gurgaon Demo Day 2014.

  2. Deepika Sharma:
    Deepika Sharma has 4 years of experience with SAP Labs India Pvt. Ltd. She has worked on projects related to Internet of Things and Image Classification using Google Tensorflow.

  3. Esha Ahuja
    Esha has been working in industry for 4 years. Her core work is in SRM Procurement. She has also worked on development projects for S4Hana TCO, SRM contract approval apps, offered an internet of things solution as in-house project. She started her work in Machine Learning with Image Classification using Google Tensorflow and explored further in its area of implementations.
    Esha was speaker at:
    •SAP d-Kom event Bangalore.
    •She conducted a hands-on workshop on SAP UI5 technology and a Delhi-NCR meet-up workshop in internet of things: http://meetu.ps/31F5kj, Training Resources: https://github.com/SAPIoTGGN/sap-cloud-and-iot at SAP Gurgaon location.
    •She is an official trainer for Fiori Advanced Development - Build SAP Fiori UIs with SAPUI5.

  4. Sudhir Verma
    https://www.linkedin.com/in/sudhir-verma-2469825

  5. Vikash Sharma
    Vikash is working with SAP Labs India Pvt. Ltd. for almost 8 years. His functional and technical expertise is in SAP GRC and SAP ABAP language. He has also worked on SAP HANA and he had developed innovative, real time, SAP HANA based application i.e. SAP Rakshak 2.0. He is working on Machine Learning Image classification using Google Tensorflow.
    Vikash was speaker multiple workshops and info pods for customers.

Slides

https://www.slideshare.net/PreetiNegi24/ml-goes-fruitful-77571885

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

The Fifth Elephant - known as one of the best data science and Machine Learning conference in Asia - has transitioned into a year-round forum for conversations about data and ML engineering; data science in production; data security and privacy practices. more