IOWarp is a comprehensive data management platform designed to address the unique challenges in scientific workflows that integrate simulation, analytics, and Artificial Intelligence (AI). IOWarp builds on existing storage infrastructures, optimizing data flow and providing a scalable, adaptable platform for managing diverse data needs in modern scientific workflows, particularly those augmented by AI.[Specification] 

This material is based upon work supported in part by the National Science Foundation (NSF) under Grant 2411318 

 A collection of MCP servers specifically designed for scientific computing research that enable AI agents and LLMs to interact with data analysis tools, HPC resources, and research datasets through a standardized protocol.[Specification] 

This material is based upon work supported in part by the National Science Foundation (NSF), Office of Advanced Cyberinfrastructure (OAC) under Grants 2411318 and 2313154.

A comprehensive framework for filling genomic gaps using Large Language Models (LLMs). GenomIO leverages state-of-the-art DNA language models to predict and fill gaps in genomic sequences, with support for multiple model architectures and RAG-enhanced inference.[Specification]

The Industrial Worker Activity Recognition system is designed to monitor CCTV footage in real-time and identify worker actions, such as carrying, sewing, bending, drinking, eating, talking, and counting, using computer vision models optimized for CPU-only execution. The pipeline integrates lightweight detection, multi-object tracking, and temporal classification, further enhanced by quantization and DeepSparse acceleration, achieving 120 FPS on a 4-core CPU. For scalability, the system can also run on GPUs, with a single RTX 3060 supporting up to 15 camera streams simultaneously in real time. This architecture ensures accurate activity monitoring, efficient deployment on edge devices, and seamless scalability for industrial environments like factories and production floors.

This research is part of AlterSense Limited

In this paper, the primary objective is to classify Bangladeshi birds into their respective species using several machine learning algorithms through transfer learning. The dataset for this classification is one that I collected manually and consists only of bird species that are found in Bangladesh. This was done because there is no collection of local bird data in Bangladesh. We used the VGG-16 network as our model to extract the features from bird images. To perform the classification, we used several Algorithms. However, compared to other classification methods, such as Random Forest and K-Nearest Neighbor (KNN), the Support Vector Machine (SVM) achieved the maximum accuracy of 89%. 

This research is a part of a project called "Bangladeshi Car License Plate Detection and Recognition".  In this research, we use 10k Bangla numbers and the letters for recognition. We use Mobilenet and our own neural network architecture for classification. We achieve 99% accuracy for Bangla digits and letters.[Specification]

This research is part of AlterSense Limited and Rokkhi IT Solutions Limited.

We introduce a traffic system that is more robust and minimizes waiting time. The system aims to identify high-traffic and low-traffic areas, controlling traffic on each side of the road using a machine learning model. In this paper, we use a transfer learning technique where Pre-trained CNN networks are loaded to extract features from the image. The system will take a video feed of the roads and feed it to a machine learning model. The overall system will consist of a server and a client-side. The machine learning model is made up of a VGG-16 network for feature extraction and uses SVM to perform the classification.[Poster][Video][Paper Under Review]

This research is part of Rokkhi IT Solutions Limited