AI4D Posts

New podcast by Wale Akinfaderin on AI for parliamentary documents in Nigerian

Adewale Akinfaderin
Adewale Akinfaderin

Wale Akinfaderin is a K4A grantee within the AI4D programme working on Predicting and Analyzing Law-Making in Kenya has delivered a podcast for an episode of “I Am Change” podcast series with Korede Azeez. The interview can be found on Soundcloud and Apple podcast.

The project proposes expanding a framework on categorizing parliamentary bills in Nigeria using Optical Character Recognition (OCR), document embedding and recurrent neural networks to three other countries in Africa: Kenya, Ghana, and South Africa.

His work was accepted at 4th Widening NLP Workshop, Annual Meeting of the Association for Computational Linguistics, ACL 2020.

New call for AI4D innovation grants open now

Deep Learning Indaba 2019, Nairobi, Kenya
Deep Learning Indaba 2019, Nairobi, Kenya

Knowledge 4 All Foundation partnered with the Deep Learning Indaba to fund research projects across Africa that are collaborative at heart and have a strong development focus.

This Call for Proposals invites individuals, grassroots organizations, initiatives, academic, and civil society institutions to apply for funding for mini-projects.

A mini-project could also be early-stage research around our Grand Challenge of curing leishmaniasis.

AI4D blog series: Building a Medicinal Plant Database for Facilitating the Exploitation of Local Ethnopharmacological Knowledge

Context

In many African countries such as Burkina Faso, people still rely quite often on traditional medicine for both common and uncommon diseases. This is particularly true in rural areas where 71% of the Burkinabe people live. While the research literature acknowledges the pharmacological virtues of some plants, the relevant knowledge is neither sufficiently organized nor widely shared.

Objectives

The ultimate goal of this project is to build an open and searchable database on medical plants. To that end, the project focuses on (1) collecting a variety of information on such plants from diverse sources, (2) implementing a platform to expose the constructed knowledge, (3) develop context-specific tools to accelerate the accurate identification of plants in the wild.

Team

To successfully carry out the project, we have set up a dedicated team of 10 people:

  • A research mentor with a background in AI,
  • A practice mentor with a background in traditional medicine. In this case, the mentor happened to be the director of the promotion of traditional medicine at the Ministry of Health,
  • A research assistant with a background in Sociology. In this case, the assistant was a student whose responsibility was to help on the collection of ethnobotanical data,
  • Three computer programmers. In this case, the programmers were computer science students who were tasked to devise and implement the database, the search engine as well as the plant identification tool.

And four investigators to collect data on the virtues of plants

Implementation

(1) Data collection: Work sessions with the practice mentor allowed us to devise an adapted methodology and identify data sources.

The adopted methodology consists of drawing a list of plants based on relevant research literature and leveraging online databases. Then, the team can conduct an ethnobotanical study with traditional medicine practitioners to gather information on the uses of plants for therapeutic purposes. For each plant, we agreed to focus on the following information:  Scientific name, Species, Family, Name in three local languages (Moore, Dioula, Fulfulde), Spatial location,  Status (endangered or not), medical use (virtues).

The data collection is mainly performed in the two largest cities in the country, namely Ouagadougou and Bobo-Bobo-Dioulasso. In the implementation of the activities, we were surprised by the amount of research that has already been done on medicinal plants, although the data is not sufficiently structured and shared. In addition, we discovered that both at the level of traditional practitioners as well as the state, there are actions being structured for the valorization of traditional medicine. Our project, therefore, reinforces the existing mechanism. In the continuation of the activities, in addition to plants, we plan to create a database of traditional practitioners. In order to be able to reference them more easily in the research works that are carried out.

(2) Platform development: With respect to the platform, we leverage the ElasticSearch engine to build the backend database and search engine.

(3) Plant detector implementation: We also devised a deep learning system to classify plant leaf images for fast identification in the wild. This work required contextualization as we supposed that users will carry mobile phones with little computing power and potentially no data network connectivity. Thus we implemented a neural network model compression algorithm that yielded a classifier with reasonable prediction accuracy and yet was runnable on low-resource devices.

Results

At this stage, while we just crossed the mid-term of the project execution, we can report that a number of milestones have been achieved:

  • the plant detector has been implemented
  • the first batch of medicinal plant dataset has been collected
  • the platform backend architecture has been finalized

Reposted within the project “Network of Excellence in Artificial Intelligence for Development (AI4D) in sub-Saharan Africa” #UnitedNations #artificialintelligence #SDG #UNESCO #videolectures #AI4DNetwork #AI4Dev #AI4D

Mini-documentary on Artificial Intelligence 4 Development

Mini-documentary on AI4D Artificial Intelligence 4 Development
Mini-documentary on AI4D Artificial Intelligence 4 Development

We produced a mini-documentary describing the ideas, aspirations, and research potential of our African colleagues in the field of Artificial Intelligence.

The footage was taken at the kick-off of the workshop Organized by K4A, IDRC, SIDA at workshop “Toward a Network of Excellence in Artificial Intelligence for Development (AI4D) in sub-Saharan Africa”, Nairobi, Kenya, April 2019 @IDRC_CRDI #UnitedNations #artificialintelligence #SDG #UNESCO #videolectures #AI4DNetwork #AI4Dev #AI4D

The emerging network of machine learning and AI practitioners and researchers undertaking a collaborative roadmap for AI for Development in Africa. The three-day workshop zoomed in on three critical areas of 1) policy and regulations, 2) skills and capacity building and 3) the application of AI in Africa.

 

ICLR presentations of AI4D mini-grants

As part of the AfricaNLP – Unlocking Local Languages workshop, we hosted a number of projects working in Artificial Intelligence in Africa for Development, funded via IDRC grants.

K4A grant to solve access to Nigeria’s legislative bills with AI

AI4D mini-grants presentations, Nairobi 2019
AI4D mini-grants presentations, Nairobi 2019

K4A grant recipients Adewale Akinfaderin, Olamilekan Wahab and Olubayo Adekanmb, are successfully using Artificial Intelligence to digitize parliamentary bills in Sub-Saharan Africa and Specifically in Nigeria. Read their recent interview in the Techpoint.Africa article.

Knowledge 4 All Foundation sponsors #AI4D Africa Innovation Awards @Indaba

In July 2019 we issued a call for proposals to invite individuals, grassroots organizations, initiatives, academic, and civil society institutions to submit their proposals for mini-projects within the 2019 Artificial Intelligence for Development (AI4D) initiative funded by IDRC.  We selected 10 winners and invited the Awardees to present their solutions at the AI4D workshop during the Deep Learning Indaba 2019 conference.

Deep Learning Indaba is the most exciting AI event in Africa

Last week more than 700 machine learning researchers from over 30 African countries came together at Kenyatta University in Nairobi, Kenya for the third annual Deep Learning Indaba. Knowledge 4 All Foundation helped fundraising for Indaba in order to support its aims to Strengthen African Machine Learning.

Knowledge 4 All Foundation runs #IJCAI presentations that show appetite for AI and SDGs

At this years edition of IJCAI, we successfully organised a workshop  on the topic of Sustainable Development Goals. The talks presented machine learning solutions in practice, from poaching to building structures, and poverty and wealth. It seems that the topic of SDGs  and AI in development are gaining traction in practice and can have a valid contribution to science. The X5GON project focusing on education and Open Educational Resources was featured with a keynote presentation.

Revisiting the Nairobi meeting of the African Network in Artificial Intelligence

We are revisiting the great event in April in Nairobi where K4A with IDRC support provided the capacity building and funding needed to launch the African Network in Artificial Intelligence and its basic activities around the African machine learning communities to support the pioneering stages of development driven approached within AI in Africa. The pictures are form the last day of the Nairobi workshop hosted at IBM Kenya.