Current Seed Grants | Institute for Future Technologies

Cyber Technologies Topics

Optimizing Allocation of Inference Tasks of Deep Neural Networks for Edge Intelligence

Edge intelligence is an emerging computing paradigm that offloads the computationally intensive processes of AI model training and inference to edge devices. The growing demand for scalable and efficient edge intelligence systems calls for innovative solutions that effectively address both computational and communication challenges in dynamic edge environments. This project investigates task allocation for deep neural network (DNN) inference across edge devices by addressing key factors inherent to real-world systems, including device reliability, task allocation flexibility, and communication dynamics. Our goal is to jointly optimize computation and communication costs to improve the inference time and overall performance of distributed AI systems. The proposed research will advance the broader objective of developing scalable, cost-effective AI solutions for industry and other domains.

Development of Unsupervised Machine Learning Methods for Biodiversity Estimation

BGU PI: Chen Keasar

NJIT PI: Frank Y. Shih

The key to effective preservation of biodiversity is its estimation, and the ability to follow, and ultimately predict biodiversity changes in space and time. However, the current approaches to biodiversity estimation are slow and costly. They necessitate the classification of observed individuals and the creation of an inventory of taxa. Using automatic classification by deep-learning models is a major step forward, but it still requires manual annotation of large training sets, and the resulted models are limited in scope to the specific fauna and flora of a given location. Due to the high price tag of biodiversity estimation, the data available for decision makers is very sparse. Thus, cost-effective approaches to biodiversity estimation are essential. The current proposal aims to offer one, specifically, focusing on flying insects. Identifying and classifying insects by human experts is difficult and time-consuming, due to their huge number of species and small body sizes. These challenges motivate our search for automated biodiversity monitoring of insects. We propose a collaborative effort to the development of a novel approach to biodiversity estimation. The proposal focuses on estimating the diversity of flying insects, combining a cost-effective, low-tech sampling procedure (sticky traps) and cutting-edge analysis using supervised and unsupervised image processing and machine learning.

Diffusion Model Control for High-Performance Geometric Meta-Structures

BGU IP: Andrei Sharf

NJIT PI: Przemyslaw Musialski

Research on the synthesis of geometric meta-structures that are lightweight, strong, and adhere to other performance constraints is a highly active research topic in materials science, geometry, and machine learning. Additive manufacturing (AM) can fabricate cellular and porous solids with exceptional strength-to-weight ratios or other performance properties. However, current design tools either (i) respect the outer surface but ignore mechanical loads or (ii) optimize lattice density but distort the shape. Traditional computational design methods also require tedious manual editing and long processing times.

In this project, we address these challenges by exploring modern generative diffusion models. Our approach conditions 3D diffusion models on both the shape’s surface and associated vector or scalar performance fields, enabling automatic generation of manufacturable, performance-aware microstructures. Bridging this gap promises lighter, stronger components for aerospace, biomedical scaffolds, and energy absorbers.