5646 research outputs found
Sort by
Qiao
No full textIn an era where digital currencies are increasingly preferred over traditional fiat, Qiao aims to facilitate the seamless conversion of USD to Bitcoin, with a twist. The definition of Qiao (桥) is bridge , which effectively describes what the program is used for. Qiao is a web application engineered to act as a medium between traditional and digital economies. It is designed to automate the conversion of USD to Bitcoin, using a commonly used payment method. Users will be presented with several mystery boxes that are available to purchase. Upon selecting a mystery box, users are shown the odds of the boxes and the possible rewards there are. There are several boxes to choose from, varying from low to high risk. Once a box is selected and a deposit is made and a crypto address is provided, the mystery box will choose an output by choosing a random number according to the client and server seed. After the output is chosen, the user will be paid out via Bitcoin with the reward that was chosen
Almari
No full textTrading in college isn\u27t as straightforward or secure as some might assume. Platforms like Facebook Marketplace and eBay, commonly used by college students, pose significant risks of theft and scams. Introducing the \u27Almari\u27 app, a modern solution tailored to the needs of college students in the United States. Almari functions as a specialized marketplace, designed as a web application where college students can safely buy, sell, and exchange items. Users will access Almari through a web browser, logging in with their email addresses associated with their respective schools. This system mirrors the approach of YikYak, allowing students to access their school\u27s dedicated server using their school email accounts. Once logged in, users can create profiles and list items for sale within their college community. They can provide detailed information about each product, including the title, price, photos, description, and condition (ranging from excellent to poor). Users can utilize advanced search and filtering options based on criteria such as price range, condition, or category. Additionally, Users can use the chat feature to exchange credentials such as student IDs and communicate effectively to ensure secure transactions
GenreGenius
No full textMusic, an intrinsic part of the human experience, resonates within us all. GenreGenius, a music recommender system, employs machine learning techniques to predict genres from real-world music datasets and offers personalized song recommendations to users based on their preferred genres, enriching musical exploration through the fusion of AI and music. This project applies unsupervised learning algorithms to explore the music datasets, revealing hidden patterns and structures that aid in grouping songs with similar characteristics. Following this exploration, supervised learning algorithms are employed to develop predictive models capable of classifying genres with precision based on audio features, such as tempo and beat. To deliver tailored recommendations, the project integrates content-based filtering, utilizing audio features to suggest songs aligned with users\u27 preferred genres. Through the analysis of musical content shared with similar genres, the machine learning model enhances recommendation accuracy, providing users with tailored musical experiences that resonate with their tastes and preferences
Human Counter
No full textHuman Counter is a mobile app that allows users to automatically count the number of people using their phone\u27s camera. The core of the app utilizes a neural network to detect people and is implemented on Android. The app also enables users to store footage and provides a simple guide for converting previous footage into training data to improve the neural network\u27s performance in specific environments. The primary purpose of Human Counter is to enable users to use their phones as a surveillance camera, passively counting people without needing to pay attention. This can be utilized in galleries, libraries, and stores to record headcounts
apex™
No full textapex™ is a system that enables LLM-powered agents to act as the primary interface between the user and system, enabling advanced AI collaboration for any task. It represents a new way to interact with one’s PC; simply engage in a conversation as one would a colleague and get work done. Actions will be performed automatically to accomplish tasks a user collaboratively specifies alongside the tool. It also connects to a hosted memory of prior experiences, which allows apex™ to learn from previous experiences. In a way, apex™ gives LLMs a ‘body’ in the form of the machine the software is running on. apex™ utilizes a combination of cutting-edge techniques, including Tree of Thought, RAG, dynamic vector-store memory, multi-agent collaboration, and most importantly, a tool-free architecture, to deliver an experience designed for robust performance in the long term. This architecture is built for the future. It is not constrained by fixed tools, and leverages LLM-powered soft reasoning wherever possible. This means that while it may stumble a bit now, as the experience pool grows, the codebase matures, and LLMs become more powerful, this tool will become increasingly generally capable
Laundry-Aid
No full textLaundry-Aid is an interactive website that allows users to monitor the status of washing machines and dryers in their house. Designed for users who live in dorm-style living, Laundry-Aid aims to make laundry easier. Laundry-Aid also can send notifications to users when their laundry is done and allows other users to see the status of washers and dryers. Laundry-Aid is based on users completing a form that tracks the following: The status of a washer/dryer, the duration of the washing and drying cycle, and contact information. Once that information is gathered, Laundry-Aid uploads this to the website for it to track and for other users to view the status of machines. Additionally, users are given the choice to opt-in for notification features such as when a laundry load is complete and when washers/dryers become available. Users can also see whether certain machines are occupied or not before they head to the laundry room, allowing them to save time and better plan their day
AB Fantasy Football (ABFB)
No full textFantasy football is a complex game played competitively all over the United States. With the increasing popularity of the NFL, fantasy football has become incredibly more mainstream over the last several years. For new users, however, the game can sometimes seem intimidating. AB Fantasy Football (ABFB) provides guidance to new players trying to set their weekly lineups by giving them suggested substitutions and waiver wire pick-ups. After importing teams, the user can compare their team to each of the others in the league. Each team consists of one Quarterback (QB), two Running Backs (RB), two Wide Receivers (WR), one Tight End (TE), one Kicker (K), one Team Defense (DFNS) and five Bench Players (BNCH). These players accumulate points based on the stats gathered from real NFL games. After all the NFL games have been played, the user will be able to see their team’s points side by side with their opponent’s for that week
LeakLens
No full textProtecting intellectual property requires efforts for many film production companies in today’s fast paced Internet world. They have to ensure that their content such as movie scenes, scripts and celebrities’ photos is not leaked and distributed widely on the Internet. To minimize the time and cost of finding leaked content, LeakLens is an advanced web application designed for content security professionals to enhance image detection and similarity analysis. Utilizing Machine Learning, the app enables users to customize image searches for greater accuracy compared to existing tools like Google Lens or TinEye, minimizing false positives. Key functionalities include the ability to upload original image files, scrape the Internet for similar images, index a vector database, and store image embeddings. The app employs Python and the OpenAI CLIP (Contrastive Language–Image Pretraining) model to convert images into embeddings, which are then used for accurate similarity scoring. The image detection process involves two main phases. During the image search phase, users upload images that need to be monitored for leaks. The app processes these images with OpenAI CLIP, converting them into embeddings and storing them in Pinecone, the vector database. It then retrieves and ranks the top 5 most similar images based on similarity scores. In the training and indexing phase, content security personnel assist by scraping images using keyword searches. These images are converted into embeddings and indexed in the Pinecone database, improving the system’s accuracy and efficiency
MatchMail
No full textMatchMail is an advanced software solution designed to streamline and automate the process of connecting students with recruiters. This application addresses the common challenges students face during their job search, particularly the time-consuming task of crafting personalized emails to recruiters. MatchMail automates this process by generating customized emails that align with job descriptions, the student’s qualifications, and the recruiter’s preferences. By leveraging the power of AI and intelligent data scraping, MatchMail enables students to efficiently create tailored messages that capture recruiters’ attention and facilitate meaningful professional connections. MatchMail’s core functionality lies in its ability to analyze job descriptions and the student’s expertise, utilizing these insights to generate personalized email content. Additionally, the software uses Proxycurl to scrape LinkedIn and X (formerly Twitter) for recruiter information, ensuring that each email is highly targeted. The result is a powerful tool that simplifies the job application process, making it easier for students to connect with potential employers. MatchMail is built with a robust technology stack, including React for the front-end, Golang for the backend server, and a combination of PostgreSQL and MongoDB for data storage. The system’s performance is further enhanced by integrating Redis and gRPC, while the AI-powered content generation is driven by the ChatGPT 3.5 Turbo API and Langchain. This combination of technologies ensures that MatchMail is not only efficient but also scalable, capable of handling the complex needs of job seekers in today’s competitive market
