Research Sites/Labs
SRM University-AP is home to a number of advanced research sites and labs designed to support groundbreaking scientific exploration and innovation. These state-of-the-art facilities provide students and faculty with the tools and technologies needed to push the boundaries of knowledge in various fields. Key research sites include the Artificial Intelligence Lab, Biotechnology Lab, Materials Science Lab, and Renewable Energy Lab. These labs foster interdisciplinary collaboration, encouraging innovative solutions to real-world problems.
Academic Labs
Eleven Academic Labs with 65 systems each
Six Specialisation labs (getting established
Six Specialisation labs (getting established
- Cybersecurity Lab with 60 systems
- Network Lab with 60 systems
- IoT Lab with 60 systems (and other equipments)
- Data Science and AIML Lab with 140 systems
- Distributed and Cloud computing Lab with 60 systems
17
Labs
1095
Systems
System Specification
| Types of Systems | Total | Lab location |
|---|---|---|
| Intel i7 with GPU (NVIDIA GeForce RTX 3060 with 12GB 3584 NVIDIA CUDA® Cores) 32GB DDR5, 1TB SSD |
244 | New Academic Building |
| Intel i5 10400 2.9GHz ,16 GB, 500 GB HDD Windows 11 with Intel Wifi pro |
782 | W101,W106,W403,W601,W62, W603,W604 Vikram Sarabhai Block, Labs in: New Academic building |
| i7,16 GB DDR4 2933 DIMM, 1TB SSD with Intel Wifi pro | 70 | W102, Vikram Sarabhai Block |
| DGX NVIDIA with GPU 32 GB | 01 | Data Centre |
Research Labs
- DGX
The NVIDIA DGX-1 is a deep learning system, architected for high throughput and high interconnect bandwidth to maximize neural network training performance. The core of the system is a complex of Eight Tesla V100 GPUs connected in the hybrid cube-mesh NVLink network topology.
In addition to the eight GPUs, DGX-1 includes two CPUs for boot, storage management, and deep learning framework coordination. DGX-1 is built into a three-rack-unit (3U) enclosure that provides power, cooling, network, multi-system interconnect, and SSD file system cache, balanced to optimize throughput and deep learning training time.
Hardware Overview
- GPUs 8xTesla V100
- GPU Memory 256 GB (32 GB/GPU)
- CPU Dual 20-core Intel Xeon E5-2698 v4 2.2 GHz
- NVIDIA CUDA Cores 40,960
- NVIDIA Tensor Cores (on V100-based systems) 5,120
- System Memory 512 GB 2.133 GHz DDR4 RDIMM
- Storage 4x1.92 TB SSD RAID-0
- Network Dual 10 GbE
Performance - 1 PETA FLOPS [Mixed Precision]
Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry’s standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book.
- Cloud Computing Lab
Multi-node Openstack software-based private Cloud Lab consists of different nodes such as the Controller node, Compute node, Network node, and Storage node. This Lab is useful for conducting hands-on experience on a private cloud as well as also useful to do research work.
| Number of Systems | Software Specification | Hardware Specification |
|---|---|---|
| 6 (i7 Systems) | Openstack Cloud (Multi-node), Ubuntu 20 |
Intel i7-10700 CPU @ 2.9 GHZ X 16 RAM: 16 GB HDD: 1 TB Graphics: Mesa Intel @ UHD Graphics 630 |
- Algorithms and Complexity Theory Lab
Lab Aim and Objectives:
The Algorithms and Complexity Theory lab focuses on developing advanced algorithms to analyse and optimize complex networks.
- Identify influential nodes, improve information propagation model in graphs.
- We explore novel centrality measures, network structures, and computational techniques to solve real-world problems in graph theory, hypergraphs, and data-driven applications.
- Implement recommender systems using content-based, collaborative and hybrid techniques to analyse user-item interactions.
- Implement scalable algorithms for large-scale complex networks.
System Configuration:
High-end systems configuration:
System 1:
- Processor: 13th Gen Intel® Core™ i9-13900 (2.00 GHz)
- Cores: 24 cores (8 P-cores + 16 E-cores), 32 logical processors
- RAM: 128 GB (128 GB usable)
- Operating System: Windows 11 pro
- Graphic card: T1000 8GB
- Software: Anaconda, Origin
System 2:
- Model: HP Z2 G8 Tower Workstation Desktop PC
- Processor: 11th Gen Intel® Core™ i9-11900 (2.50 GHz, 2496 MHz)
- Cores: 8 physical cores, 16 logical processors
- RAM: 64 GB
- Operating System: Microsoft Windows 11 Pro (10.0.26100 Build 26100)
- Graphic card: NVIDIA GeForce RTX 3060 12GB
- Software: Anaconda, Origin
System 3:
- Model: MSI (Micro-Star International Co., Ltd.) MS-7D88
- Processor: Intel® Core™ i9-14900K (3.20 GHz, 3200 MHz)
- Cores: 24 physical cores, 32 logical processors
- RAM: 64 GB
- Operating System: Microsoft Windows 11 Pro (10.0.26100 Build 26100)
- Graphic Card: NVDIA 4060TI 8GB
- Software: Anaconda, Origin
For five PCs we have the following configuration:
- Processor: Intel Core™ i7-10700 CPU (2.90 GHz, 2904 MHz)
- Cores: 8 physical cores, 16 logical processors
- RAM: 16 GB
- Operating System: Windows 11
- Software: Anaconda, Origin
- Visual Information Processing Lab
Aim
To enhance research and innovation in visual information processing by creating computational models and intelligent systems that can analyse, interpret, and comprehend visual data for a wide range of real-world applications.
Objective
- To develop and implement state-of-the-art algorithms for image and video processing, computer vision, and pattern recognition.
- To investigate and apply deep learning and machine learning approaches to problems such as object identification, segmentation, recognition, and scene understanding.
- To build reliable systems for verifying the authenticity and integrity of images and videos using forensic and cryptographic approaches.
- To explore the use of deep learning and machine learning models for automated image forgery detection and source identification.
- Apply research to medical imaging, remote sensing, industrial automation, and smart devices.
- To develop low-power, real-time vision systems for edge computing.
The research within the lab focuses on the emerging technologies like, image forensics, object detection, medical image analysis, content-based video retrieval. The lab is also extending its work into 3-D image modelling, deepfake image detection, and high spectral image forensics analysis.
System Configuration:
- 05 PC: intel(R) Core(TM) i5-10400 @ 2.90GHz 2.90 GHz, 16 GB RAM
- 04 PC: intel(R) Core(TM) i7-10700 CPU @ 2.90GHz 2.90 GHz, 16 GB RAM
- 1 PC: 12th Gen Intel(R) Core (TM) i7-12700 2.10 GHz, 32 GB RAM
- IoT & Cyber Security Lab
Lab's aim and objectives
The IoT and Cybersecurity Lab at the university aims to create a secure and innovative research environment that addresses critical challenges in cybersecurity, with a particular focus on protecting IoT ecosystems from evolving cyber threats. The lab is dedicated to advancing cybersecurity knowledge through cutting-edge research, hands-on learning, and industry collaboration.
A key objective of the lab is to equip researchers with expertise in cybersecurity practices, ethical hacking, secure IoT development, and advanced threat mitigation strategies. By integrating theoretical knowledge with practical applications, the lab prepares future cybersecurity professionals to tackle real-world security challenges.
The research within the lab focuses on emerging technologies such as federated learning, blockchain, and virtual reality (VR), with a strong emphasis on cybersecurity. The lab is also extending its work into healthcare applications, where cybersecurity plays a crucial role in safeguarding patient data, medical devices, and immersive healthcare systems. Through federated learning, the lab explores privacy-preserving machine learning models that enhance security while minimizing data exposure. Blockchain research is directed toward developing decentralized security frameworks for IoT devices, ensuring data integrity, authentication, and secure transactions. Additionally, the lab is integrating VR into immersive healthcare systems, enhancing security measures to protect sensitive medical interactions and data.
System Configuration:
- 2 x i5 systems - DELL
- 3 x i7 systems – HP
- Tyrone Workstation, CAMARERO-SS400TA-55
- Nano Communication and Networking Lab
The Nano Communication and Networking Lab explores various cutting-edge nanotechnologies and solutions. The lab conducts research on in vivo Wireless Nanosensor Networks for cardiac health monitoring, and designs nanoantennas for in vivo communications and networking at terahertz. It develops cross-layer MAC and Network layer solutions for in vivo information exchange between IoBNT and IoT. The research team in the lab also works on developing nano-sized biocompatible antennas operating in the terahertz band as a coupling device suitable for nanomachines for in vivo communications. The lab also extends to apply Machine Learning techniques to the prediction of deadly diseases in nano networks.
System Configuration:
- 2 x i5 systems - DELL
- 3 x i7 systems – HP
- Tyrone Workstation, CAMARERO-SS400TA-55
- Data Science Research Lab
- Networking Research Lab