Srinivas Rahul Sapireddy

Assistant Professor, Illinois State University

Intelligent Neural & Signal Systems Laboratory

INSys Lab

Intelligent signal systems, hardware-aware machine learning, and low-power edge intelligence

The Intelligent Neural & Signal Systems Laboratory develops efficient, interpretable, and hardware-aware methods for intelligent signal processing and edge computing under strict power, latency, and memory constraints.

RF Signal Intelligence Hardware-Aware ML Edge AI Systems Efficiency and Interpretability
Publications Scholars Resume Contact
● RF Signal Intelligence
● Hardware-Aware ML
● Edge AI Systems
● Interpretable Learning
● VLSI-Aware Computing
● Low-Power Signal Processing
● Embedded Intelligence
● RF Signal Intelligence
● Hardware-Aware ML
● Edge AI Systems
● Interpretable Learning
● VLSI-Aware Computing
● Low-Power Signal Processing
● Embedded Intelligence
RF
Signal Intelligence
Classification, sensing, and feature extraction
AI
Hardware-Aware ML
Efficient models for constrained systems
Edge
Low-Power Computing
Latency, memory, and power-aware design
VLSI
System Awareness
Algorithm-to-hardware perspective

🔎 Lab Overview

INSys Lab adopts a systems-level research perspective that spans algorithm design, evaluation methodology, and deployment-aware considerations. The lab emphasizes methods that are not only accurate, but also practical for embedded, edge, and cyber-physical platforms.

Signal Processing Machine Learning RF Systems Edge Computing Hardware-Aware Evaluation Resource-Constrained AI
📡

RF Signal Intelligence

Intelligent RF signal analysis, modulation classification, statistical feature extraction, and interpretable signal-domain learning.

🧠

Efficient Learning Models

Lightweight and hardware-aware neural, statistical, and hybrid learning models for deployment-aware AI systems.

⚙️

Edge and Hardware Systems

Evaluation workflows for runtime, memory, power, and latency across embedded and edge-computing platforms.

🔬 Research Focus

  • Intelligent RF signal analysis and modulation classification
  • Lightweight and hardware-aware neural and statistical learning models
  • Signal-domain feature extraction and interpretable learning frameworks
  • Edge intelligence for embedded and resource-constrained systems
  • Robust and trustworthy intelligent signal processing architectures

🛠️ Tools and Platforms

  • Python and MATLAB for signal analysis and algorithm development
  • RF signal simulation and statistical feature extraction pipelines
  • Embedded and edge AI development environments
  • Hardware-aware evaluation workflows for runtime and resource analysis

🧭 Research Methodology

Step 1
Signal Capture and Modeling
Model, simulate, or collect signal data relevant to communication, sensing, and edge-intelligent systems.
Step 2
Feature Engineering
Extract signal-domain, statistical, time-frequency, and interpretable features from raw or processed data.
Step 3
Efficient Learning
Develop lightweight learning models and hardware-aware classification pipelines.
Step 4
Deployment-Aware Evaluation
Evaluate accuracy, runtime, memory, power, latency, and system feasibility.

📌 Research Philosophy

INSys Lab emphasizes principled and deployment-conscious research methodologies. Rather than relying exclusively on large or opaque models, the lab prioritizes approaches that balance performance, efficiency, and interpretability.

  • Integrating signal processing insights with learning-based models
  • Designing algorithms with explicit consideration of hardware constraints
  • Evaluating methods using accuracy, runtime, memory, and power metrics
  • Bridging theoretical foundations with system-level validation

👨‍🎓 Student Involvement and Mentoring

INSys Lab provides hands-on research opportunities for undergraduate and graduate students through independent study, senior design projects, and directed research.

Student pathways: signal processing projects, RF simulation, efficient machine learning, hardware-aware model evaluation, technical writing, and publication-oriented research.

Details of current and previously mentored students are available on the Scholars page.

📚 Scholarly Output

Research conducted within INSys Lab contributes to peer-reviewed journal articles, conference publications, and technical reports in signal processing, machine learning, RF systems, and hardware-aware computing.

Output areas: RF classification, envelope statistics, efficient AI, custom activations, edge systems, and hardware-conscious evaluation.

A complete list of publications is available on the Publications page.

🤝 Collaboration and Engagement

INSys Lab welcomes collaboration with academic researchers, industry partners, and government laboratories interested in intelligent signal systems, RF analysis, and edge computing. Collaborative activities may include joint research projects, co-supervised students, prototype development, proposal preparation, or exploratory system-level studies.

Academic Collaboration Industry Engagement Student Research Proposal Development Prototype Studies System-Level Evaluation

🚧 Lab Status

INSys Lab is currently in its establishment phase. Research activities are conducted through simulation-driven workflows and prototype-based experimentation, with laboratory infrastructure development ongoing.

📬 Contact

Prospective students and collaborators are encouraged to reach out by email to discuss research interests, project ideas, or collaboration opportunities.

Email Publications Scholars

🏛️ Institutional Affiliation

INSys Lab is an academic research initiative focused on intelligent signal systems, hardware-aware machine learning, and edge computing within the College of Engineering at Illinois State University.