SEECS Research Groups
Centre for Research in Modeling & Simulation (Crimson) Lab
Centre for research in Modeling, Simulation and Vision (CRIMSON) was established in June 2016. This research group at SEECS positions its primary focus in solving “Complex Engineering Problems” crucial to the National Interest. These problems may include: (i) ICT Ennoblement of real world processes e.g., Building Smart Cities, Electronic Surveillance & bio-Surveillance; (ii) Design decisions in complex engineering e.g., Building of Sustainable and Resilient urban infrastructures, CPEC: (iii) Optimization of real world operations e.g., Water supply & management, Waste Management and (iv) Prediction & forecasting e.g., Energy planning in Pakistan, Disaster Management, Emergency evacuation. Further, recent technological advances such as cloud computing, Big data, and the Internet of Things and Cyber security necessitate new developments in modeling and simulation to fully exploit these capabilities, and therefore constitutes the research theme at CRIMSON.
Information Processing & Transmission Lab
The Information Processing and Transmission (IPT) Lab is intended to provide a research platform that investigates problems at the interface of wireless communication theory, signal processing theory, and Applied Mathematics. The research at IPT helps in solving theoretical problems that find applications in real system. The mission of the lab is to provide innovative solutions from a variety of areas, including communication and information theories, statistical signal processing, signal estimation and detection, multi-hop cooperative networks, green wireless communications, smart grid communications, and multi-user systems.
OPTImization & MAchine Learning (OPTIMAL) lab
OPTImization & MAchine Learning (OPTIMAL) lab is developing wearable glasses to assist the visually impaired in interacting with the environment using deep neural networks. The system not only detects obstacles but also categorize objects and their relative distances from the user. The information will be fed to the user in the form of an audio feedback.
For details click here
Signature Research Clusters
We are focusing on multi-disciplinary research and in that context research in SEECS has been broadly divided into seven Signature Research Clusters. Originally we established six research groups but recently we added another cluster, ‘Artificial Intelligence & Machine learning’, considering its growing importance and priority in the contemporary world. The seven signature research clusters include: Internet of Things, Wireless and Photonic Networks, Cyber Security, Smart Grid, Cloud Computing and Big Data Analytics and Artificial Intelligence & Machine learning.
Speech and Language Technology Research Group
This research group aims to conduct research in the areas of machine learning and natural language processing. Specific application areas are speech recognition, automatic voice and text based chat bots, and deep neural network architectures. The group maintains close links with Pakistani industry; because we believe that economic progress will be achieved only through capacity building and up gradation of Pakistan's industry. The group prides itself with developing Pakistan's first web-based Urdu dictation service UrduAsr.com
Technische Universitat Kaiserslautern Research and Development Centre (TUKL-NUST R&D Centre)
TUKL-NUST Research & Development Centre is being established on the model of German Research Centre for Artificial Intelligence (DFKI), which serves as a role model for creating world-class on-campus research centre for providing pragmatic solutions to the thriving and diverse consumer market. The newly established centre will leverage the rich experience and expertise of DFKI and its host institution Technical University of Kaiserslautern (TUKL), Germany to establish a long-term sustainable collaboration between TUKL and NUST.
System Analysis and Verification (SAVe) Lab
These days hardware and software systems are increasingly being used in safety-critical domains, such as electronic military and medicine equipment and automated transportation systems. This fact makes the accuracy of their analysis very important as an uncaught system bug may endanger human life or lead to a significant financial loss. Traditionally, the verification of these systems has predominantly been accomplished by computer simulation. However, it does not ascertain 100% correctness and thus has primarily been responsible for many unfortunate incidents that happened due to an erroneous hardware or software system deployed in a safety-critical domain.
The primary focus of our research is on using formal methods, which are based on mathematical techniques and thus unlike simulation ensure complete results, for the analysis and verification of hardware, software, and embedded systems. In particular, we aim at using theorem proving and model checking, which are the some of the widely used formal methods, to develop methodologies, algorithms and tools for the accurate analysis of systems that are continuous or random in nature or interact with continuous or random physical environments.
Besides the formal verification, we are also involved in designing algorithms and techniques for hardware systems. Some of these ongoing activities cover the domains hardware security, approximate computing, thermal and resource management in many-core systems, surgical robotics and cell biology.
NeuroInformatics Research Lab
Home to Pakistan's first EEG Research Lab, establishment of the Neuro-Informatics Lab at SEECS-NUST has enabled Pakistani researchers and members of the faculty to actively participate in the global efforts to understand the human brain. The lab collaborates with leading international institutions to develop highly skilled human resource in the related field. We facilitate neuroscientists and computer scientists to conduct experiments and analysis on the data using state of the art neurotech equipment without having to invest in establishing their own experimental neuroscience facilities. The key goal of this lab is to provide state of the art experimental facilities to all beneficiaries including higher education institutes, medical researchers/practitioners, and technology industry. The lab is being used for Brain Computer Interfaces (BCI / BMI), Neuromarketing, Neuroscience, Diagnostic Research, and Neural Engineering, by Neurologists, Psychologists, computer scientists, and Biomedical Engineers.For details click here
Robotics and Machine Intelligence (ROMI) Lab
Industrial robots have revolutionized industry during the last couple of decades. The world of robotics has now moved on to developing mobile robots with navigational intelligence and scene interpretation ability so that they can interact with their environment and efficiently execute a task. Therefore the robotics today is a combination of navigational intelligence (that includes localization, mapping, SLAM, path planning etc) and computer vision based scene interpretation. These research areas continue to attract researchers and there are many challenges to be solved before we can see a truly autonomous mobile agent capable to navigating on its own interacting with its environment.
Robotics and Machine Intelligence (ROMI) lab, being part of the department of electrical engineering at SEECS, is mainly interested in developing intelligent systems for robots. We work in the areas of robot localization, mapping, SLAM and path planning. These capabilities lie at the heart of any system that claims to be truly autonomous. We are currently working in all these areas with a funded project to develop efficient SLAM algorithms for indoor and outdoor mobile robots.
With the need to develop intelligent robots, scene understanding has become essential skill for robots and with that computer vision and machine learning are now part of almost any robotic system that interacts with environment. We are also interested in these areas and are actively pursuing computer vision and machine learning techniques that can be used in robotics. Current areas of work include human pose estimation for robotic application, SLAM with vision sensors in dark/low lightening conditions, reinforcement learning in robotics, and developing transferable skills for robotics.For details click here
Advanced Energy Efficient Nano Group (AEENG)
The Research group aims to gauge Energy efficiency at the Nano Scale Electronics with special emphasis on the Silicon CMOS fabrication Technology. With CMOS manufacturing industry possibly reaching to its pinnacle with composite requirements imposed by the International Technology Roadmap of Semiconductors; a “More Moore” approach is fully exploited. The approach is in complete unison with other two strategies “More than Moore” and “Beyond CMOS”. The functional output characteristics of MOS/CMOS and its variant devices would be reexamined with energy efficiency in focus. The process and Design protocols for the Energy Efficient Structure would be designed, developed and tested. The energy efficient and conservation such as power consumption, performance and reliability of the devices would be envisaged and improved .The energy efficient electronics being a field of tomorrow is directly linked to the evolution of Internet of Things (IoT) and its ultra-low power requirements. Energy efficiency would also be studied by virtue of the concepts of thermal budget. Process characterization is planned to be accomplished by employing Current-Voltage, Capacitance-Voltage, Current Density, Leakage Resistance, Built-in Voltage, Doping Profiling, Charge-storage/ Permittivity, Hall Effect and Vertical Field analysis. Refined metrology techniques such as Charge-Deep Level Transient Spectroscopy and Spectroscopic Ellipsometry would be applied to determine the hypersensitive electrical and electro-optical indices such as charge-transient behavior, activation energy, trap density, capture cross-section, refractive index, dielectric and extinction coefficients etc.
Adaptive Signal Processing (ASP)
The Adaptive signal processing research group at SEECS is actively doing
research in different signal processing areas including convex
optimization, Real time signal processing, Machine/Deep learning for
time series data, Images, video, text, data fusion etc. etc. Major
projects include sensor data fusion at multiple sampling rates, sparse
signal processing, IoT predictive maintenance for industrial and
household loads, load prediction, load disaggregation, smart grids
optimization. Research Lab is also working on funded projects in domain
of IoT for grain storage, Soil moisture and nutrients sensor design,
SoC/SoH prediction for batteries. Another area where lab is focusing on
is deep learning for different applications e.g. adversarial attacks, Urdu OCR, Deep learning for agriculture, disease prediction
and yield estimation for rice, wheat and mango.