The International Neuroinformatics Coordinating Facility (INCF) is a non-profit organization dedicated to advancing neuroscience and neuroinformatics. Their mission involves promoting open, fair, and easily citable standards while providing support to researchers worldwide. INCF’s projects encompass a wide range of areas, from predicting Alzheimer’s and detecting cancer cells to mapping the brain in 3D, developing connectomes, and analyzing EEG data. Given this extensive and impactful work, there is a pressing need for an online portal to effectively track INCF’s progress and showcase its global contributions using simple language. This portal is thoughtfully designed to make INCF’s achievements accessible to a broad audience, regardless of their familiarity with technical terminology. Leveraging the capabilities of large language models and Langchain, a comprehensive dashboard is created. This user-friendly, interactive, and visually appealing platform serves to highlight research progress and the real-world impact on people’s lives. It aims at ultimately raising awareness about the field of neuroinformatics and INCF’s pivotal role in advancing neuroscience.
Proposed Ideas
Collaborative Filtering for Project Recommendations:
- Implement a recommendation system using collaborative filtering to suggest projects to users based on their interests and past interactions.
- Implementation: Use collaborative filtering algorithms like Singular Value Decomposition (SVD). Implement recommendation systems using scikit-surprise.
- Tools: Surprise library, scikit-surprise.
Sentiment Analysis with User Feedback:
- Create a user feedback system and integrate sentiment analysis to analyze user comments and feedback on projects and organizations. This can provide valuable insights into the community’s perception and satisfaction. Natural Language Processing (NLP) techniques can be applied to understand the sentiment behind user reviews and comments.
- Techniques: Utilize Natural Language Processing (NLP) techniques, specifically sentiment analysis.
- Tools: NLTK or spaCy for NLP preprocessing, and libraries like TextBlob or transformers (Hugging Face) for sentiment analysis.
Dynamic Visualization of Impact Metrics:
- Implement dynamic visualizations using data science libraries (e.g., Matplotlib, Plotly) to showcase impact metrics over time. Allow users to interact with the visualizations to explore trends and patterns in the impact of different projects or organizations.
- Techniques: Time-series analysis using methods like moving averages, trend analysis, and anomaly detection.
- Tools: Matplotlib and Seaborn for static visualizations, Plotly or Bokeh for interactive visualizations.
Semantic search:
- Enhance the search functionality by allowing users to search using natural language queries instead of just keywords. This would utilize NLP to understand the intent behind the query and retrieve relevant results even if the exact keywords aren’t used.
- Implementation: Making use of models like BERT for vector representations. Further use of algorithms like cosine similarity for promoting the search of relevant projects.
- Tools: Transformers Library (Hugging Face),Annoy or Faiss.
Multilingual support:
- Extend the website’s capabilities by using multiple languages, making the portal more accessible to a wider audience.
- Implementation: Add a user interface element, like a language switcher, that allows users to select their preferred language.
- Tools: Google Speech_recognition, Microsoft Translator, or DeepL.
Any new ideas that can improve the overall system are welcome as well as this project is yet in POC stage.
Skill level: Medium
Project Length: Medium (175 h)
Lead Mentor: Atharva Purohit (atharvaspurohi@gmail.com)
Tech Keywords: Python, Machine learning, Deep Learning, Django
Project URL(GitHub): GitHub - atharva434/INCF-Impact-visualization-Portal
1 Like
Respected @Atharva_Purohit Sir,
I am Vaishnavi Namdeo. I am currently pursuing Bachelor’s in Technology in computer engineering. I am excited to contribute to your organization. I want to express my interest in your project 14.1 INCF Impact Visualization Portal with ML and Data Analytics.
I have done projects based on NLP processing techniques and NLTK. I am also well versed in Python and Python libraries like scikit-learn, Matplotlib, seaborn and more. I have previously done project on hate speech detection, that analysis user comments and look for negative comments.
I am dedicated and willing to research and learn more about technologies relevant to the project. I kindly request your guidance. I would be grateful if you could provide me with resources and suggestions related to project. Thank You for considering my request. I eagerly await the opportunity to benefit from your mentorship.
Email: vaishnavinamdeo.21022855@gmail.com
GitHub: Vaishnaviieee (Vaishnavi Namdeo) · GitHub
Greetings @Atharva_Purohit @greg_incf ,
My name is Tvisha Vedant and I am currently a second-year B.Tech Computer Science student at Veermata Jijabai Technological Institute. I have a strong background in various areas of computer science, including natural language processing (NLP), web development, and version control with Git/GitHub. I am also aware about image processing which I learned while developing a gesture navigation music tool. I have worked extensively with LLMS like langchain, Transformer architecture, and NLP, which I applied in developing a healthcare chatbot(using the Llama model from hugging face after testing a lot many models).
Additionally,The motive and aim of your project appeals to me a lot and I too feel the need of such a tool where a track record for progress and tasks of orgs and projects under incf can be viewed and understood.
I had a few feature suggestions:
1)We can have a graphical analysis for the progress of every project or research being done.
2}A suggestion algorithm using nlp can be created to give users information about the various projects and researches related to their previous activities this can attract more contributors/mentors and also donations.
I read through your repo and I understood that the chatbot feature has been implemented to quite an extent,so what are the tasks we will be covering further?
It would be great if you could inform me about any tasks to be performed beforehand for GSOC 24?
Having spent 2 years in this ever expanding field of computer science I have developed a knack to learn various technologies in a smooth and quick way and I am ready to learn anything new for this project.
Looking forward to collaborating with you.
Email:
tnvedant_b22@ce.vjti.ac.in
My github repo:
https://github.com/tvilight4
My resume:
Resume
Hello @greg_incf @Atharva_Purohit,
I am Om Khare, pursuing B. Tech. in Computer Engineering from College Of Engineering Pune (COEP). I have worked extensively on Machine Learning, Data Analysis, Computer Vision projects. I interned at Deutsche Bank wherein I was one of the very few interns selected to work on live ML and data analysis projects. I have also implemented different NLP concepts from scratch during my elective course of NLP in final year. I have also done honours courses in deep learning and big data. I have two publications one in computer vision related project and other in applied machine learning project. I am really excited to work on this project!
Upon going through your article and your repository, here are some more feature suggestions:
- AI-Generated Summaries for Research : Make use of summarisation algorithms to provide layman-friendly summaries of complex research projects and findings. This can make the information more accessible to a broader audience.
- Language Model for Neuroinformatics Research: Train a specialized language model on neuroinformatics literature to assist researchers in drafting papers, generating hypotheses, or finding relevant literature.
- Community Building Features : Develop forums, discussion boards, or social networking features to foster a community around neuroinformatics research. This could enhance collaboration and knowledge sharing.
Hope to get in touch with you soon!
Email: omkhare02@gmail.com
Resume: Resume
Github: OmKhare (Om Khare) · GitHub
Greetings @Atharva_Purohit @greg_incf ,
I am Suraj Gajul, currently pursuing Bachelor’s of Computer Engineering at D Y Patil College of Engineering. After reviewing the GitHub repository and your blog pertaining to the project, it piqued my interest because of the technologies used. The INCF website uses Django framework and incorporates LLM for a navigable and user-friendly UI. I have previously worked with Django and Supervised Learning on my personality prediction project which also utilizes SQLite database for storing user input and prediction done by my model.
Additionally, my internship experience as a Cyber Data Analyst at Nexus Infosec, Dallas Texas, aided me in learning the basics of LLMs. Although the chatbot has been built impeccably, consistent innovations in the sector leads me to believe that there is room for improvement through meticulous optimization and tuning. All the proposed ideas of Collaborative Filtering, Sentiment Analysis, Dynamic Visualization, Semantic Search and Multilingual Support definitely improves the projects’ accessibility and reachability. I’m already familiar with these techniques, having implemented some of these in my projects. Moreover, I brainstormed a couple of ideas which I’ve mailed you personally.
I’ll research all the mentioned technologies and how they can be integrated to supplement website’s performance. I will also try to come up with better ideas for the project now that I have access to the codes and materials for further exploration.
In my opinion, INCF’s goal of promoting standard practices in data management for neuroscience is of critical importance. Not only does it aid in safeguarding the data, but also promotes hassle free data reusability and reproducibility for research endeavors. Working with this organization will enable me to contribute towards a global cause, so it would be an honor.
Regards,
Suraj B Gajul. (surajgajul20@gmail.com)
Github - surajgajul (surajgajul) / Repositories · GitHub
I am Prathamesh Devadiga, a second-year undergraduate student pursuing B. Tech. in Computer Engineering from PES University. With a diverse background and hands-on experience in Machine Learning, Deep Learning, NLP, MLOps projects, I have interned at esteemed institutions like IIT Indore and MedInn TechLabs. I have also been selected to attend in the Oxford University Machine Learning School for this year.
Furthermore, I mentor at several hackathons where I share knowledge and guiding others in solving complex problems. I have given talks on Neural Networks and have taken a few workshops (video will be uploaded on YouTube soon). Currently, I serve as the Head of Technology for the Entrepreneurship Club of PES University, where I lead initiatives aimed at fostering innovation and creativity among my peers, and building a website from scratch.
In addition, my previous role as the Webmaster at IEEE RAS I handled the website operations, built everything from scratch single-handedly. Leveraging my leadership, communication, and technical skills, I am well-prepared to contribute meaningfully to the INCF Impact Visualization Portal project.
Considering my experience and passion in this domain, I would be honored and thrilled to have the opportunity to collaborate with you on this project.
Email: devadigapratham8@gmail.com
Resume: Link to Resume
Portfolio: Portfolio Link
GitHub: GitHub Profile
Hi guys Atharva Purohit here. Thank you everyone for showing interest in this project. As you all know it is in POC stage so high priority task will be to find new and exciting ways to quantify impact INCF is having on scientific communities. I will be creating github issues some will be basic bug fixes while some research based. Anyone interested can go through them as they will help you understand codebase and search for new ideas.
2 Likes
I am Nanthakumar currently pursuing computer science in NIT TRICHY, Well experienced with python, LLM, tensorflow. previously build an RAG chatbot with prediction guard, and made an Ai-Video-app with combining Hugging face models. I also have some experience with web development. I am looking forward to contribute to this project
I’m Kushagra Mishra, currently pursuing Mathematics and Computing at IIT Indore. I’m excited to be a part of this group and eager to contribute to open-source projects.
My background includes experience with various technologies, including MySQL, C++, PyTorch, and several NLP libraries like NLTK and HuggingFace (transformers). I’ve previously worked on NLP projects.