ThereForYou: Your mental health ally. Kai, our AI assistant, offers compassionate support. Track your mood trends, find solace in a secure community, and access crisis resources swiftly. We're here to empower your journey towards improved well-being, leveraging technology for a brighter tomorrow.
License: Other
I want to perform EDA on medical condition model. Please assign this task to me. Also, please provide the dataset 'he.csv' used for training.
ThereForYou's camera software(suicide attempt prevention) predicts if there's danger and alerts nearby users. We need a good-looking design(Frontend) for its presentation.
The Contributor needs to make only the frontend for this, the above points are written to understand the working of the software.
Problem:
In recent years, there has been a concerning rise in railway-related suicides. Detecting individuals on railway tracks in real time to prevent such incidents is a critical challenge. Existing methods often rely on human intervention, which may not always be timely or effective.
Solution:
I propose implementing a feature within the existing railway safety systems to detect individuals on railway tracks using an advanced computer vision algorithm. This feature would analyze live camera feeds along railway tracks and identify human presence, alerting railway authorities or relevant emergency services promptly.
I am gssoc contributor, kindly assign this to me.
👋 Hi @TAHIR0110,
I am Prince,web developer(Core Team) Girlscript Summer of Code. I'll be collaborating with you on preparing your repo for GSSoC'24 Program
Why are these changes required?
After Analysing last year's contributions and feedback it would be great for students to have a couple of standard readme files on the repo to understand what the project is all about and some issues detailing what they can contribute. This will help you to see increased engagement in your repository as well.
As mentioned students get a chance to learn step by step, how to build this project as well as invite mentors to collaborate and add features to this repo. I will generate issues, which will provide guidance on how to prepare your repo for Girlscript summer of code 2024 on 10th May.
This issue will serve as a tracking issue to track all issues related to GSSoC'24. I recommend creating a new branch for every issue and opening a pull request to track changes so we can effectively collaborate with each other and merge changes when you and I feel like those changes are ready to be merged on your primary branch.
If you have any questions or concerns, please feel free to leave a comment on this issue or any of the other issues that are generated.
I look forward to working with you 
Data Collection: Gather a dataset containing relevant health information such as age, gender, blood pressure, cholesterol levels, body mass index (BMI), smoking status, family history of CVD, and other risk factors associated with cardiovascular diseases. You can obtain this data from sources such as electronic health records, health surveys, or medical research studies.
Data Preprocessing: Clean and preprocess the collected data to handle missing values, normalize numerical features, encode categorical variables, and remove any noise or outliers that may affect the performance of the ML models.
Is your feature request related to a problem? Please describe.
It can work as a sweet and warm greeting to the user.
Describe the solution you'd like
When the user opens this page, a prompt can come up "Hey, hope you are having a good day! How are you feeling today?" Followed by emojis with "bad...fine...good...very good".
Based on the selection of the user, a message or some suggestion would come up.
eg, if the user chooses "very good" the message would come up "yaay! keep up with that energy!"
Describe alternatives you've considered
none.
Additional context
Something just like this.
Please assign me this feature under GGSOC'24.
Hi @TAHIR0110 I would like to do further work on this Dataset on the EDA file These are proposed steps :
1.Imputing Outliers and NULL values
2.Normalization of skewed values and One Hot coding Text attributes
3.Comparing KNN.Random Forest and SVC
4.Validatiing the Evaluated models on the validation set using metrics like accuracy, precision, recall, and F1 score
5.Including visualizations (e.g., training curves, confusion matrices) to better illustration of the model performance.
Further :
Creation of Automated Pipeline and Custom Tranformer For the Datset each steps proposed .
The task aims to develop a machine learning model capable of analysing road scenes to detect the presence of animals in the middle of the road, thereby mitigating the risk of road accidents. Through object detection techniques, the model will learn to identify and localise animals within the road environment.
Is your feature request related to a problem? Please describe.
Some of the most appealing causes of suicide are depression, anxiety, and feeling competitively lost.
Describe the solution you'd like
Building an advanced sentiment analysis model, will analyze the sentiment of the user and accordingly provide the level of chatbot. If a single chatbot is made that is available for all moods such as suicidal, depressing, or anxiety it would be hard. So I think the AI chatbots should be divided into a few parts that will handle the different moods. My analysis model will provide the most probable mood case for a user and accordingly, the chatbot will be assigned to the user.
Additional context
Detecting whether a person is wearing sunglasses or not in images is a common computer vision task with various practical applications. For example, in security systems, it can help identify individuals in surveillance footage or control access to secure areas. In retail, it can be used for personalized advertising or customer analytics. However, accurately distinguishing between sunglass-wearing and non-sunglass-wearing individuals can be challenging due to factors like varying lighting conditions, poses, and facial occlusions.
Train a model to recognise Morse code sequences from audio inputs for improved communication in emergencies. Collect diverse Morse code audio datasets, preprocess data, select appropriate architecture, train, evaluate, deploy within the existing system, and iterate based on feedback for enhanced performance.
One could consider using machine learning models like Hidden Markov Models.
reference material: https://github.com/f4exb/morseangel
kindly write the approach you would follow.
Description:
It is essential to maintain consistency and clarity in the information provided with each PR.
Introducing a pull request template will ensure that contributors include all necessary details, making it easier for reviewers to understand the proposed changes and provide feedback efficiently.
Proposed Template Content:
Description: Provide a brief overview of the changes made in the PR.
Changes Made: Detail the specific modifications implemented in the PR.
Testing Instructions: Outline steps for testing the changes, including any setup or configuration required.
Related Issues: Link any associated issues or pull requests that are addressed by this PR.
_Checklist: Include a checklist to ensure that contributors have completed necessary tasks such as testing, code review, and documentation updates.
Expected Outcome:
Note: Feedback and suggestions for refining the pull request template are welcome and encouraged from the project community.
In GSSoC'24, GitHub Topics will help the discoverability of your project.
I see that you already have great topics on your repository!
I would recommend adding the name of the company like the software you use to build like "vs-code, ghdesktop" to improve your discoverability.
If you are happy with the topics you have, feel free to close this issue. 👍
Hey @TAHIR0110 ,
Identifying gastrointestinal conditions from medical images is crucial for accurate diagnosis and treatment planning. However, distinguishing between various conditions such as Diverticulosis, Neoplasm, Peritonitis, and Ureters can be challenging without automated classification systems.
I would like to develop a multiclass classification system capable of accurately identifying different gastrointestinal conditions from medical images. This system should be trained on a diverse dataset covering a wide range of conditions, including Diverticulosis, Neoplasm, Peritonitis, and Ureters.
One alternative solution is to manually analyze each medical image, which is time-consuming and prone to human error. Another option is to develop separate binary classification models for each condition, but this approach may not efficiently utilize the available data and could lead to suboptimal performance.
The proposed system aims to improve the efficiency and accuracy of diagnosing gastrointestinal conditions, ultimately benefiting both patients and healthcare providers.
I'm enthusiastic about contributing, and I firmly believe that integrating this model aligns with our mission of advancing overall well-being. Please assign me the issue.
project should reduce online dependency for NLP models. Offline dependency models should be considered
Perform EDA on heart.csv dataset, after which we would finalise this dataset and move to train It for stress level prediction
Is your feature request related to a problem? Please describe.
containerizing application ensures that they would run in anyone's system
Describe the solution you'd like
I want to dockerize the whole system by creating an appropriate dockerfile for the backend part of the system.
Additional context
Kindly assign this to me under gssoc.
The repository currently lacks a CONTRIBUTING.md file, which is an important resource for guiding potential contributors on how to engage with the project effectively. A CONTRIBUTING.md file outlines the contribution guidelines, coding standards, and procedures for submitting pull requests, thus streamlining the contribution process and ensuring consistency across contributions.
Could you please assign this issue to me under GSSOC 24.
This task aims to identify a potential suicide attempt for the user based on the presence of a rope. Here's what the model will check:
If all three conditions are met, the model will predict danger. This information can then be used to warn the user or take appropriate action.
We can use transfer learning model like vgg-16 or vgg-19 or hyperparameter to increase accuracy.
If possible then plz assign me this issue
make a ml model using deep learning frameworks which would tell if the person is male or female.
We aim to enhance the visual appeal of our project's user interface by refining and beautifying our CSS styles. This initiative is crucial for providing users with a delightful and immersive experience while navigating through our application.
Improved Aesthetics: Revamp existing CSS styles to achieve a visually appealing design that aligns with modern UI/UX standards.
Consistency: Ensure consistency in design elements such as colors, typography, spacing, and layout across all pages of the application. Colour Scheme should not be changed
Accessibility: Prioritize accessibility by adhering to best practices, including high contrast ratios, appropriate font sizes, and keyboard navigation.
Responsiveness: Ensure that the UI remains aesthetically pleasing and functional across various screen sizes and devices.
Tasks:
Refinement of Design Elements: Enhance visual elements such as buttons, forms, navigation bars to create a more polished look.
Layout Improvements: Optimize page layouts for better organization and flow, ensuring intuitive navigation and information hierarchy.
Responsive Design Implementation: Implement responsive design principles to ensure a seamless user experience across various devices and screen sizes.
ThereForYou -> voice-to-text_text-to-voice -> static -> css
style.css according to above guidlinespip install -r requirements.txt on windows and pip3 install -r requirements.txt on Linux and MacOpen-AI key in .env path.another.py inside root folderLearn repos should have a LEARN.md file to teach student how to build your project step by step. You can explain how to build your project with text, code snippets, images, or even short (5 minute) long video lessons. As the maintainer of a Learn repo, the LEARN.md file requires you to think critically about how to explain the building of your project and how to also make it engaging. We don't expect you to be an expert teacher, but we would like you to reflect on how difficult it was to get to your level of knowledge, and then provide friendly guidance to help other students to learn.
Reference: https://github.com/Recode-Hive/Stackoverflow-Analysis/blob/main/Learn.md
It is very important to add contributing steps to the readme file. I want to do this task. Could you please assign me this sir.
We recommend that every repo has a code of conduct. If you don’t feel comfortable creating your own Code of Conduct from scratch we highly recommend using one of the templates provided by GitHub. If you do use a template, please read through the template and ensure that you can and will abide by the Code of Conduct.
Please follow these instructions on how to add a Code of Conduct.
Sample: https://github.com/Recode-Hive/Stackoverflow-Analysis/blob/main/CODE_OF_CONDUCT.md
Is your feature request related to a problem? Please describe.
A feature which enhances the functionality of the predictions of danger, or suicidal thoughts. When the victim is in danger and is unable to speak at the moment, a text can be displayed to the camera which can predict the outcomes and notify the nearby users accordingly. For suicide predictions, it is helpful in the situation where the victim is writing the death note, so that the camera may get a glimpse of the note, and via the predictions of the model, it can infer the outcomes.
Describe the solution you'd like
The sole purpose is to provide functionality for image to text conversion. For visualization, the frame will have the detected text surrounded with bounding boxes with the text detected and the confidence, if the latter surpasses a certain threshold. A pretrained model from easyocr will be used along with cv2.
Use Case
The extracted text can be used with the existing models in the repository that takes text as their primary input for various predictions.
Please assign it to me under GSSoC'24.
Is your feature request related to a problem? Please describe.
Yes, my feature can be helpful as many people like journaling daily.
Describe the solution you'd like
We can add a separate personalized section/option for journaling for each user.
There the user can write about their day in different fonts, add pictures, change themes of their note, access their previous journals, etc. We can add a calendar for this purpose, where users can simply click on the current date or the previous dates to access their journals or write a new one.
Describe alternatives you've considered
None.
Please assign me this under gssoc'24.
An extemely beautiful Homepage
Navbar
Hero Section depicting that we are solving mental health and safety issues
How it works section
Testimonial Section
Android and iOS app store section
Footer
Try to use these color schemes
Try to use these fonts
Please drop your best front end projects, if you wish to contribute to this issue
Is your feature request related to a problem? Please describe.
Improve platform's health assessment with a Cardiovascular Risk Prediction Model due to lacking specific tools for assessing users' cardiovascular disease risk, a major global mortality factor.
Describe the solution you'd like
Integrate a Cardiovascular Risk Prediction Model considering age, gender, medical history (hypertension, diabetes), lifestyle (smoking, physical activity), and Biometrics (Body Mass Index, blood pressure) to estimate risk over time. This model will help determine more disease than only heart disease, like strokes and several other.
Describe alternatives you've considered
Integrating a custom Cardiovascular Risk Prediction Model tailored to our platform's user base and data would provide more accurate and personalized risk assessments.
Additional context
Adding this model can help us as it aligns with our goal. This will enhance the overall value of our model.
ContentFlow is a content recommendation platforms which aims to provide personalized content recommendations to its users based on their preferences and behaviours. The platform collects user data such as browsing history, search queries, and interactions with the platform, to build a recommendation system that suggests relevant content to each user.
Develop an algorithm that utilizes the user data to make accurate content recommendations. The algorithm should consider the user's historical preferences, similarity to other users, and the content's relevance to generate personalized recommendations.
The goal is to maximize the user engagement and satisfaction by delivering high-quality content that aligns with their interests and preferences.
As the maintainer of a Collaborate repo, keeping Issues up-to-date will help the student community understand what they can do to contribute. Issues should vary by the easy (update documentation) to the difficult (add a new feature). The more involved you are, the more opportunities there are to collaborate.
Recommendations:
Add issues of varying difficulty to the repo often. you must add the tag GSSoC'24, Level 1, Level2, Level 3 good first issue etc.
How we cacluclate the Scores on Leaderboard: Every PR one point
Level 1: 10 points
Level 2: 25 points
Level 3: 45 points
Try to add some documentation issues as well it would be easy for beginner contributor to explore opensource through your repo.
Generate issues even if you plan on solving them, so the repository appears as active.
Contribute/commit often to the repo so it does not go stale.
Reference https://github.com/Recode-Hive/Stackoverflow-Analysis/issues
Can i add heart disease prediction by heart.cv.please assign me to do task undr gssoc24
Develop an AI Psychiatrist platform leveraging pre-trained models and empathetic prompts to provide confidential mental health support. Tailored prompts encourage open dialogue.
the prompts should be concise, clear, and thought-provoking.
I'm labelling it as level 3 task, as we need very good chat bot with effective prompts.
I suggest adding a Flask API endpoint to the repository, streamlining access to machine learning models. Presently, navigating the codebase to find individual models is tedious. This feature would offer users a straightforward HTTP interface for interacting with the models, enhancing usability. The endpoint should provide a list of available models with pertinent metadata, and allow users to request predictions by submitting input data. Error handling should be robust, ensuring informative responses for invalid requests. Implementation will involve Flask for web framework, intuitive route design, and serialization for data transmission. Consideration should be given to compatibility with common data formats and potential authentication mechanisms. This addition promises to simplify model interaction, promote code maintainability, and foster community engagement through feedback and documentation.
Kindly assign this to me in gssoc.
Develop a model to detect facial emotions from images or video frames. Gather diverse data, train the model, and assess its accuracy.
I have a NLP model that can predict if someone is in danger based on what they say(speech is converted to text then text is being analysed). However, it currently only works with English text. I'd like to make it work with Indian languages as well.
The problem is, my model needs English input. So, I need to convert text from any Indian language to English before feeding it into my model.
Issue templates are very helpful for a collaboration repo. When users identify a bug or want to add a new feature, you can provide templates so you can collect all the pertinent information you need to fix a bug or add a new feature.
We recommend creating a “Report Bug” and “Feature Request” issue template.
you can refer this: https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/configuring-issue-templates-for-your-repository
Some suggested prompts/questions you can add to a “Report Bug” template are:
Briefly describe the bug
What is the expected behavior?
Please provide step by step instructions on how to reproduce the bug
Some suggested prompts/questions you can add to a “Feature Request” issue template are:
Briefly describe your feature request
What problem is this feature trying to solve?
How do we know when the feature is complete?
Reference: https://github.com/Recode-Hive/Stackoverflow-Analysis/issues/new/choose
Click on Get Started button and copy the template to your
Is your feature request related to a problem? Please describe.
The general issue when it comes to current generation is unavoidable stress and high self esteem.Everyone wants to continuously achieve and fail to accept small setbacks and get extremely worked up.
Describe the solution you'd like
"Laughter is the best medicine",says a famous quote upon asking the user his preferences initially when he launches the app,we can provide memes and funny videos personalised to his taste and with the chatbot data can be tracked and mood analysed. We can also provide with healing and self-worth uplifting quotations which provides a sense of belief to the person.
Kindly assign me with this task
Problem:
Predicting the orientation of human faces in images is a fundamental task in computer vision with numerous applications. It involves determining the pose or angle at which a person's face is positioned relative to the camera. Accurate face orientation prediction is essential for tasks such as face recognition, facial landmark detection, and emotion analysis. However, detecting face orientations accurately can be challenging due to variations in lighting conditions, facial expressions, and occlusions.
Solution:
To address the problem of predicting face orientations, we can employ machine learning and computer vision techniques to build a robust model. Here's a step-by-step solution:
Data Collection:
Gather a diverse dataset of face images with annotations indicating their respective orientations (e.g., frontal, left profile, right profile). Ensure the dataset contains sufficient variations in poses, lighting conditions, and facial expressions to train a robust model.
Data Preprocessing:
Preprocess the face images to standardize them for training. This may involve tasks such as face detection, alignment, and normalization to ensure consistency across the dataset. Additionally, augment the data by applying transformations like rotation, scaling, and flipping to increase its diversity and improve model generalization.
Feature Extraction:
Extract meaningful features from the face images that capture important characteristics related to their orientations. This could involve traditional feature extraction techniques like geometric features, texture descriptors, or deep learning-based feature extraction methods using convolutional neural networks (CNNs).
Model Selection and Training:
Choose an appropriate machine learning model architecture for face orientation prediction. CNNs are commonly used for this task due to their ability to automatically learn hierarchical features from data.
Split the dataset into training and testing sets and train the model using the training data. Fine-tune the model's parameters using techniques like cross-validation to optimize its performance.
Model Evaluation:
Evaluate the trained model's performance using the testing data. Calculate metrics such as accuracy, precision, recall, and F1-score to assess its effectiveness in predicting face orientations accurately. Adjust the model architecture or training parameters as needed to improve performance.
Deployment:
Once satisfied with the model's performance, deploy it in real-world applications where face orientation prediction is required. This could include systems for face recognition, surveillance, or human-computer interaction.
Continuous Improvement:
Monitor the model's performance over time and collect feedback from users to identify areas for improvement. Update the model periodically with new data or fine-tune its parameters to enhance its accuracy and robustness.
Design an AI avatar to complement the existing chatbot, displaying the opposite gender based on the ML model gender prediction. the task is solely avatar creation for user interaction. The avatar should be male if the model predict female and vice-versa.
Kindly provide a short brief on how you would make the avatar. accordingly we will assign the issue.
Hey, @TAHIR0110
Develop a predictive model capable of assessing an individual's likelihood of being addicted to harmful items or behaviors and at risk of suicide, considering their medical condition. This model would analyze various factors such as behavior patterns, environmental influences, mental health history, underlying medical conditions, and personal characteristics to generate a comprehensive risk assessment, including the likelihood of addiction and suicide risk.
Alternatives:
Manual assessment by healthcare professionals, which can be time-consuming and subjective, and may not adequately consider the individual's medical condition.
Using existing screening tools for addiction and suicide risk separately, although they may not be tailored to individual needs or provide real-time feedback on the combined risk, especially considering medical factors.
Additional Context:
Creating such a predictive model could significantly improve early intervention efforts for both addiction and suicide prevention, taking into account the individual's medical condition. It could be implemented in various healthcare settings, addiction support programs, or mental health crisis hotlines to provide targeted support and intervention to those most in need, while considering their specific medical needs and vulnerabilities.
Please assign me this issue
Is your feature request related to a problem? Please describe.
Ans. Our repository emphasizes mental health prediction models, but it doesn't currently include one for Parkinson's disease. This is crucial as Parkinson's is linked to mental health issues like depression and anxiety. Predicting Parkinson's could indirectly support mental health efforts by enabling early intervention for interconnected conditions. Therefore, adding this model would align with our goal of promoting well-being.
Describe the solution you'd like
Ans. Let's add a Parkinson's disease prediction model. It would analyze demographics, medical history, and possibly genetics to predict the risk of developing Parkinson's.
Describe alternatives you've considered
Ans. We could collaborate with others, but an in-house model would give us more control.
Additional context
I'm eager to contribute, and I believe incorporating this model aligns with our goal of promoting overall well-being.
Make a chatbot for ThereForYou website which would answer user questions and would primarily focus on mental health.
I propose to create a GitHub workflow named "Greetings". This workflow will automatically greet users who create new issues or pull requests in this repository. The Greeting will look like "Hi there! Thanks for opening this issue. We appreciate your contribution to this open-source project. We aim to respond or assign your issue as soon as possible."
Please assign this issue to me
Detecting the facial features and voiceovers of a person try to recommend them the music which can help them to come out from their depression. Also use music therapy in a daily treatment like basis to treat different psychiatric problems.
Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when I have overloaded work and I get anxious. In that case, some deep breathing exercises are really helpful.
Describe the solution you'd like
Offer guided mindfulness and meditation programs led by certified instructors or mindfulness coaches.
Provide audio and video sessions tailored to different skill levels, durations, and meditation techniques to promote relaxation and stress reduction.
Describe alternatives you've considered
Offer stress reduction tools and relaxation techniques, such as guided imagery, progressive muscle relaxation, breathing exercises, and biofeedback games. Incorporate interactive features and feedback mechanisms to enhance engagement and effectiveness.
Please assign me this issue under GSSOC'24.
Description:
We propose the development of a resume parser using Python. This project aims to create a tool that can extract relevant information from resumes in various formats (such as PDF, DOCX, and TXT) and store it in a structured format.
Features:
Implementation:
Hey there, I can make a model which can accurately predict any sort of suicide attempt and detect it accordingly real fast. The problem with most models I have seen is that they are not particularly accurate and fast in action which is definitely not desirable in these type of situations.
The model I can make can clearly identify suicidal and non suicidal statements or words categorically and also put emphasis on each word it sees or uses along with their frequencies , classes, etc. to properly show and identify and reason to classify something as a suicide attempt.
I have tried looking and working with some models on this topic before but sure they work but not very accurate to sort out this issue without further verification or time lag.
I would like to contribute to this task under GSSOC'24 and solve out this problem real quick.
Hope I make it to your sight.
Thanks...
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.