AmeyArc

A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video

Sun, 05 Apr 2026 01:18:19 -0400

Special thanks to Sarvesh Talele for his meaningful contributions, support, and wisdom that helped shape this work. Traffic cameras record the circumstances of a great many collisions, but methods that read those recordings automatically are usually trained on annotated footage from the same camera. This work asks what can be recovered without any labelled real-world data at all, using three independent modules and only pre-trained weights.

Attention Is All You Need — Understanding the Mathematics of the Transformer

Mon, 16 Mar 2026 15:05:09 -0400

A visual cover introducing the mathematical foundations of the Transformer architecture from the paper Attention Is All You Need. The graphic highlights the core scaled dot-product attention equation alongside the key components of the architecture: self-attention, multi-head attention, and positional encoding.

Adaptive Cruise Control with Arduino & Simulink

Wed, 24 Jul 2024 00:00:00 -0400

An Arduino-based speed control system with Normal, Cruise, and Adaptive Cruise Control (ACC) modes. Speed is adjusted manually or automatically based on obstacle distance using an ultrasonic sensor. Real-time speed and mode are displayed on an LCD.

Introduction

Adaptive Cruise Control (ACC) is an exciting advancement in automotive technology that aims to enhance both convenience and safety on the roads. Unlike traditional cruise control systems, ACC utilizes sensors and intelligent algorithms to automatically adjust a vehicle’s speed and maintain a safe distance from the vehicle in front, even in changing traffic conditions [1].

Zero-Shot Video Generation

Wed, 22 Nov 2023 00:00:00 -0500

The intersection of artificial intelligence and multimedia continues to evolve, breaking down barriers between different forms of media. In this project, the research titled “Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators” conducted by Picsart AI Research Lab represents a significant breakthrough. This study introduces a pioneering method that directly converts textual descriptions into videos, bridging the gap between natural language processing and computer vision. This development not only caters to the growing demand for dynamic visual content but also showcases the machine’s capability to interpret and transform human language into a visual format. By addressing the challenge of text-to-video synthesis, this research sets a new standard for interdisciplinary studies in artificial intelligence.

Multiple Linear Regression

Fri, 29 Sep 2023 00:00:00 -0400

This study examines regression analysis within Supervised Machine Learning, focusing on Simple Linear Regression (SLR) and Multiple Linear Regression (MLR). A practical implementation demonstrates the predictive relationship between study hours and grades.

Efficient Home Insulation

Wed, 05 Apr 2023 10:00:00 -0500

In Canada, inadequate insulation in homes leads to excessive energy use, higher expenditures, and a huge carbon impact. Ineffective insulation lets cold air penetrate and heat escape, making Heating, Ventilation, and Air Conditioning (HVAC) systems work harder and use more energy to keep a comfortable temperature. This presents a challenge during the long, cold Canadian winters when home heating accounts for a significant portion of energy use and carbon emissions. Older or improperly placed insulation materials, such as fibreglass and mineral wool, may lose their insulating capacity due to exposure to moisture or poor installation, raising homeowners’ energy bills.

QuadTree Visualizer

Wed, 27 Apr 2022 00:00:00 -0500

Special thanks to Mega Satish and Hasan Rizvi for their meaningful contributions, support, and wisdom that helped shape this work. We propose to develop a program that can show a QuadTree view and data model architecture. Nowadays, many digital map applications have the need to present large quantities of precise point data on the map.

Online Chess Game

Fri, 15 Apr 2022 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. We developed an online chess game in Node.js for both single-player and multiplayer modes and deployed it on Heroku. The game follows Human-Machine Interaction principles and offers a clean, attractive, and user-friendly interface.

A Comparative Study on Distributed File Systems

Thu, 31 Mar 2022 00:00:00 -0500

Special thanks to Mega Satish and Hasan Rizvi for their meaningful contributions, support, and wisdom that helped shape this work. Distributed File Systems form the backbone of large-scale data storage. Systems like the Hadoop File System, Google File System, and Network File System have changed how data is managed across servers.

Clock Synchronization in Distributed Systems

Thu, 31 Mar 2022 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. Clock discrepancies are troublesome in distributed systems and pose major difficulties. To avoid mistakes, the clocks of separate CPUs must be synced. This is to ensure that communication and resource sharing are as efficient as possible.

Pizza Ordering Chatbot Using Amazon Lex

Sat, 19 Mar 2022 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. Because of breakthroughs in machine learning and deep learning, which are causing a change in every industry area and managing various types of activities better than people. The majority of monotonous jobs that were formerly performed by humans are now replaced by AI.

Text Summarizer Using Julia

Mon, 24 Jan 2022 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. The purpose of this paper is to introduce the Julia programming language with a concentration on Text Summarization. An extractive summarization algorithm is used for summarizing. Julia’s evolution and features, as well as comparisons to other programming languages, are briefly discussed.

Optimizing Stock Trading Strategy With Reinforcement Learning

Wed, 22 Sep 2021 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. The core aim of this project is to take raw data, analyse it, and perform exploratory data analysis to clearly understand the underlying patterns. Using these insights, we build and train a Neural Network model to achieve accurate results. Finally, the complete system is deployed as a web application.

Bangalore House Price Prediction

Tue, 07 Sep 2021 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. We propose to implement a house price prediction model of Bangalore, India. It’s a Machine Learning model which integrates Data Science and Web Development. We have deployed the app on the Heroku Cloud Application Platform. Housing prices fluctuate on a daily basis and are sometimes exaggerated rather than based on worth.

Neuro-Fuzzy: Artificial Neural Networks & Fuzzy Logic

Mon, 06 Sep 2021 00:00:00 -0500

Special thanks to Karan Dhiman for his meaningful contributions, support, and wisdom that helped shape this work. Neuro Fuzzy is a hybrid system that combines Artificial Neural Networks with Fuzzy Logic. Provides a great deal of freedom when it comes to thinking. This phrase, on the other hand, is frequently used to describe a system that combines both approaches.

Generative Adversarial Networks

Fri, 27 Aug 2021 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. Deep learning’s breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results.

Fundamentals of Neural Networks

Tue, 10 Aug 2021 00:00:00 -0500

Special thanks to Archit Konde for his meaningful contributions, support, and wisdom that helped shape this work. The purpose of this study is to familiarise the reader with the foundations of neural networks. Artificial Neural Networks (ANNs) are algorithm-based systems that are modelled after Biological Neural Networks (BNNs).

Adversarial Open Domain Adaption Framework (AODA): Sketch-to-Photo Synthesis

Wed, 28 Jul 2021 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. This paper aims to demonstrate the efficiency of the Adversarial Open Domain Adaption framework for sketch-to-photo synthesis. The unsupervised open domain adaption for generating realistic photos from a hand-drawn sketch is challenging as there is no such sketch of that class for training data.

Car Rental System

Sat, 17 Jul 2021 00:00:00 -0500

Customers will be able to reserve their vehicles from anywhere in the world due to the Car Rental System. Consumers provide information to this application by filling in their personal information. When a consumer creates an account on the website, he or she can reserve a car. The proposed system is an online system that is fully integrated. It effectively and efficiently automates manual procedures. Customers are aided by this automated method, which allows them to fill in the specifics according to their needs. It contains information on the sort of car they want to hire as well as the location. The goal of this system is to create a website where customers can book their automobiles and request services from anywhere in the world. There are three phases to this car rental system mentioned in the introduction.

Digital Bookstore

Sat, 17 Jul 2021 00:00:00 -0500

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. The project’s main goal is to build an online book store where users can search for and buy books based on title, author, and subject. The chosen books are shown in a tabular style and the customer may buy them online using a credit card.

White-Box Cartoonization: An Extended GAN Framework

Fri, 09 Jul 2021 00:00:00 -0500

Special thanks to Mega Satish and Hasan Rizvi for their meaningful contributions, support, and wisdom that helped shape this work. In the present study, we propose to implement a new framework for estimating generative models via an adversarial process to extend an existing GAN framework and develop a white-box controllable image cartoonization, which can generate high-quality cartooned images/videos from real-world photos and videos.

Chat Room Using HTML, PHP, CSS, JS, AJAX

Mon, 28 Jun 2021 00:00:00 -0500

Special thanks to Karan Dhiman for his meaningful contributions, support, and wisdom that helped shape this work. Earlier there was no mode of online communication between users. In big or small organizations communication between users posed a challenge. The main objective of our Simple Chat Room project is to create a chat application that helps different users to communicate with each other through a server connected.