We (Medical Imaging Group (MIG), CDS, IISc Bangalore and ACPS Group, ICT, UiA Campus Grimstad) have developed a Mobile-friendly deep learning model for point-of-care detection of COVID19 using Ultrasound Images for better triaging of patients. This manuscript is accepted for publication in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (Special issue on Ultrasound in COVID-19 and Lung Diagnostics).
Navchetan Awasthi, Aveen Dayal, Linga R. Cenkeramaddi, and Phaneendra K. Yalavarthy, “Mini-COVIDNet : Efficient Light Weight Deep Neural Network for Ultrasound based Point-of-Care Detection of COVID-19,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (Special issue on Ultrasound in COVID-19 and Lung Diagnostics) 2021 (in press). [Reprint is available at: http://cds.iisc.ac.in/faculty/yalavarthy/Publications.html] Project Repository: https://github.com/navchetan-awasthi/Mini-COVIDNet
Abstract: Lung ultrasound imaging has the potential to be an effective point-of-care test for detection of COVID-19, due to its ease of operation with minimal personal protection equipment along with easy disinfection. The current state-of-the-art deep learning models for detection of COVID-19 are heavy models that may not be easy to deploy in commonly utilized mobile platforms in point-of-care testing. In this work, we developed a lightweight mobile-friendly efficient deep learning model for the detection of COVID-19 using lung ultrasound images. The developed method was shown to be sensitive to the damage to the pleural surface of the lung, which has been proven to have prognostic value, commonly observed in intensive care unit–admitted and deceased patients. The developed model has utility in the context of a massive COVID-19 pandemic, where it can better triage patients with pulmonary symptoms (suspected of infection).
P. Veda Bhanu, Rahul Govindan, Plava Kattamuri, Soumya J, and Linga Reddy Cenkeramaddi, “Flexible Spare Core Placement in Torus Topology based NoCs and its validation on an FPGA,” has been accepted for publication in IEEE AccessJournal (2021).
Keywords: Topology, Fault tolerant systems, Fault tolerance, Field programmable gate arrays, Power capacitors, Transform coding, Genetic algorithms
Abstract: In the nano-scale era, Network-on-Chip (NoC) interconnection paradigm has gained importance to abide by the communication challenges in Chip Multi-Processors (CMPs). With increased integration density on CMPs, NoC components namely cores, routers, and links are susceptible to failures. Therefore, to improve system reliability, there is a need for efficient fault-tolerant techniques that mitigate permanent faults in NoC based CMPs. There exists several fault-tolerant techniques that address the permanent faults in application cores while placing the spare cores onto NoC topologies. However, these techniques are limited to Mesh topology based NoCs. There are few approaches that have realized the fault-tolerant solutions on an FPGA, but the study on architectural aspects of NoC is limited. This paper presents the flexible placement of spare core onto Torus topology-based NoC design by considering core faults and validating it on an FPGA. In the first phase, a mathematical formulation based on Integer Linear Programming (ILP) and meta-heuristic based Particle Swarm Optimization (PSO) have been proposed for the placement of spare core. In the second phase, we have implemented NoC router addressing scheme, routing algorithm, run-time fault injection model, and fault-tolerant placement of spare core onto Torus topology using an FPGA. Experiments have been done by taking different multimedia and synthetic application benchmarks. This has been done in both static and dynamic simulation environments followed by hardware implementation. In the static simulation environment, the experimentations are carried out by scaling the network size and router faults in the network. The results obtained from our approach outperform the methods such as Fault-tolerant Spare Core Mapping (FSCM), Simulated Annealing (SA), and Genetic Algorithm (GA) proposed in the literature. For the experiments carried out by scaling the network size, our proposed methodology shows an average improvement of 18.83%, 4.55%, 12.12% in communication cost over the approaches FSCM, SA, and GA, respectively. For the experiments carried out by scaling the router faults in the network, our approach shows an improvement of 34.27%, 26.26%, and 30.41% over the approaches FSCM, SA, and GA, respectively. For the dynamic simulations, our approach shows an average improvement of 5.67%, 0.44%, and 3.69%, over the approaches FSCM, SA, and GA, respectively. In the hardware implementation, our approach shows an average improvement of 5.38%, 7.45%, 27.10% in terms of application runtime over the approaches SA, GA, and FSCM, respectively. This shows the superiority of the proposed approach over the approaches presented in the literature.
Daniel S. Breland, Simen B. Skriubakken, Aveen Dayal, Ajit Jha, Phaneendra K. Yalavarthy, and Linga R. Cenkeramaddi, “Deep Learning based Sign Language Digits Recognition from Thermal Images with Edge Computing System,” IEEE Sensors Journal 2021 (in press).
Abstract: The sign language digits based on hand gestures have been utilized in various applications such as human-computer interaction, robotics, health and medical systems, health assistive technologies, automotive user interfaces, crisis management and disaster relief, entertainment, and contactless communication in smart devices. The color and depth cameras are commonly deployed for hand gesture recognition, but the robust classification of hand gestures under varying illumination is still a challenging task. This work presents the design and deployment of a complete end-to-end edge computing system that can accurately provide the classification of hand gestures captured from thermal images. A thermal dataset of 3200 images was created with each sign language digit having 320 thermal images. The solution presented here utilizes live images taken from a low-resolution thermal camera of 32×32 pixels, feeding into a novel light weight deep learning model based on bottleneck motivated from deep residual learning for classification of hand gestures. The edge computing system presented here utilizes Raspberry pi with a thermal camera making it highly portable. The designed system achieves an accuracy of 99.52% on the test data set with an added advantage of accuracy being invariable to background lighting conditions as it is based on thermal imaging.
L. R. Cenkeramaddi, P. K. Rai, A. Dayal, J. Bhatia, A. Pandya, J. Soumya, A. Kumar, & A. Jha., “A Novel Angle Estimation for mmWave FMCW radars using Machine Learning,” IEEE Sensors Journal 2021 (in press).
Abstract: In this article, we present a novel machine learning based angle estimation and field of view (FoV) enhancement techniques for mmWave FMCW radars operating in the frequency range of 77 – 81 GHz. Field of view is enhanced in both azimuth and elevation. The Elevation FoV enhancement is achieved by keeping the orientation of antenna elements in elevation. In this orientation, radar focuses the beam in vertical direction there by enhancing the elevation FoV. An Azimuth FoV enhancement is achieved by mechanically rotating the radar horizontally, which has antenna elements in the elevation. With the proposed angle estimation technique for such rotating radars, root mean square error (RMSE) of 2.56 degrees is achieved. These proposed techniques will be highly useful for several applications in cost-effective and reliable autonomous systems such as ground station traffic monitoring and control systems for both on ground and aerial vehicles.
Naveen Paluru, Aveen Dayal, Havard B. Jenssen, Tomas Sakinis, Linga R. Cenkeramaddi, Jaya Prakash, and Phaneendra K. Yalavarthy, “Anam-Net : Anamorphic Depth Embedding based Light-Weight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images,” IEEE Transactions on Neural Networks and Learning Systems (Fast Track: COVID-19 Focused Papers) 2021 (in press).
Keywords: COVID-19, Coronavirus, Deep Learning, Segmentation, and Abnormalities.
Abstract: Chest computed tomography (CT) imaging has become indispensable for staging and managing of COVID-19, and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding based light-weight CNN, called Anam-Net, to segment anomalies in COVID-19 Chest CT images. The proposed Anam-Net has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it light-weight capable of providing inferences in mobile or resource constraint (point-of-care) platforms. The results from chest CT images (test cases) across different experiments showed that the proposed method could provide good Dice similarity scores for abnormal as well as normal regions in the lung. We have benchmarked Anam-Net with other state-of-the-art architectures like ENet, LEDNet, UNet++, SegNet, Attention UNet and DeepLabV3+. The proposed AnamNet was also deployed on embedded systems like Raspberry Pi 4, NVIDIA Jetson Xavier, and mobile based Android application (CovSeg) embedded with Anam-Net to demonstrate its suitability for point-of-care platforms. The generated codes, models, and the mobile application are available for enthusiastic users at https://github.com/NaveenPaluru/Segmentation-COVID-19.
A. Dayal, N. Paluru, L. R. Cenkeramaddi, S. J., and P. K. Yalavarthy, “Design and Implementation of Deep Learning Based Contactless Authentication System Using Hand Gestures,” MDPI Electronics (Artificial Intelligence Circuits and Systems (AICAS)), vol. 10, no. 2, p. 182, Jan. 2021.
Keywords: hand gestures recognition, security, edge computing, deep learning, neural networks, contactless authentication, camera-based authentication
Abstract: Hand gestures based sign language digits have several contactless applications. Applications include communication for impaired people, such as elderly and disabled people, health-care applications, automotive user interfaces, and security and surveillance. This work presents the design and implementation of a complete end-to-end deep learning based edge computing system that can verify a user contactlessly using ‘authentication code’. The ‘authentication code’ is an ‘n’ digit numeric code and the digits are hand gestures of sign language digits. We propose a memory-efficient deep learning model to classify the hand gestures of the sign language digits. The proposed deep learning model is based on the bottleneck module which is inspired by the deep residual networks. The model achieves classification accuracy of 99.1% on the publicly available sign language digits dataset. The model is deployed on a Raspberry pi 4 Model B edge computing system to serve as an edge device for user verification. The edge computing system consists of two steps, it first takes input from the camera attached to it in real-time and stores it in the buffer. In the second step, the model classifies the digit with the inference rate of 280 ms, by taking the first image in the buffer as input.
Sensors Applications: Sensor applications are rapidly expanding into new fields and domains, and here are some emerging research areas in sensor applications of the ACPS research group. Autonomous Vehicles: Sensors play a critical role in enabling autonomous vehicles to navigate and avoid obstacles. ACPS group research focuses on developing sensors that can detect a wider range of objects, operate in low-light conditions, and work in complex environments. Smart Cities: Sensors can be used to monitor traffic flow, air quality, and other factors in cities to improve public safety and quality of life. ACPS group research focuses on developing sensors that can provide real-time data and enable more efficient city management. Energy Efficiency: Sensors can be used to monitor energy usage in buildings and optimize energy consumption. ACPS research group focuses on developing sensors that can track energy usage in real-time, provide recommendations for reducing energy consumption, and enable more efficient use of renewable energy sources. Industrial Automation: Sensors can be used in manufacturing to monitor equipment performance, detect faults, and optimize production processes. ACPS research group focuses on developing sensors that can work in harsh environments, detect a wider range of issues, and enable more efficient manufacturing processes. Personalized Healthcare: Wearable sensors can track vital signs, detect early warning signs of health issues, and monitor medication adherence. ACPS research group focuses on developing sensors that can collect more comprehensive health data, predict health outcomes, and enable personalized treatment plans.
Sensors: Sensors are becoming more important in a variety of fields, including healthcare, smart cities, and environmental monitoring. Here are some potential research areas where the ACPS research group focuses: Internet of Things (IoT) Sensors: With the growth of IoT, sensors will become more important in collecting and transmitting data from various devices. ACPS research group focuses on developing new sensors that are more energy-efficient and can transmit data wirelessly over longer distances. Wearable Sensors: Wearable sensors have the potential to revolutionize healthcare by allowing for continuous monitoring of patients’ vital signs. ACPS research group focuses on developing sensors that are more comfortable, non-invasive, and can be integrated into clothing or jewelry. Environmental Sensors: Environmental sensors can be used to monitor air quality, water quality, and other environmental factors. ACPS research group focuses on developing sensors that are more sensitive and can detect a wider range of pollutants. Chemical Sensors: Chemical sensors can be used to detect various gases, liquids, and other chemicals. ACPS research group focuses on developing sensors that are more selective and sensitive, as well as miniaturizing sensors for use in portable devices. Imaging Sensors: Imaging sensors are used in various applications, including digital cameras, medical imaging, and security cameras. ACPS research group focuses on improving the resolution and sensitivity of sensors, as well as developing sensors that can operate in low-light conditions. Smart Sensors: Smart sensors can analyze data in real-time and make decisions based on that data. ACPS research group focuses on developing sensors that are more intelligent and can learn from their environment, as well as developing new applications for smart sensors in fields such as transportation and manufacturing.
2019 – Indo-Norwegian collaboration in Autonomous Cyber-Physical Systems (INCAPS): The Research Council of Norway (NFR) under the INTPART program; Project Manager and PI: Professor Linga Reddy Cenkeramaddi,ACPS Research Group, Department of ICT, UiA Grimstad, Project duration: 2019-2023. Partners and/or collaborators: Indian Institute of Science, Bangalore (IISc); Indian Institute of Technology, Hyderabad (IITH); International Institute of Information Technology, Hyderabad (IIITH); Birla Institute of Technology and Science, Hyderabad (BITS); Norwegian University of Science and Technology (NTNU); Norwegian Institute for Water Research (NIVA)
The INTPART (International Partnerships for Excellent Education and Research) Program, from the Research Council of Norway, funds partnerships between Norwegian higher education and research institutions and other excellent research partners in prioritized countries: Brazil, Russia, India, China, South Africa, USA, and Canada. The ACPS Group at the University of Agder was granted funding to collaborate with highly reputed Indian Universities in the field of Autonomous Cyber-physical Systems
Fig. 1. Indo-Norwegian collaboration, partners, activities and main areas of expertise.
The ACPS Research Group (https://acps.uia.no/) at the University of Agder collaborates with highly reputed and top Indian Universities and leads the INTPART project Indo-Norwegian collaboration in Autonomous Cyber-Physical Systems (INCAPS), with funding of around 6 MNOK from the Research Council of Norway. This project establishes a long-term collaboration between several top-ranked Indian Universities, including the Indian Institute of Science (IISc), Bangalore, Indian Institute of Technology, Hyderabad (IITH), International Institute of Information Technology, Hyderabad (IIITH), Birla Institute of Technology and Science (BITS), Hyderabad, BML Munjal University (Through Prof. M.B.Srinivas) and several Norwegian Universities and institutes, including University of Agder (UiA), Norwegian University of Science and Technology (NTNU) and Norwegian Institute for Water Research (NIVA) in world-class research and education.
Key active participants from the University of Agder are researchers from the ACPS Group, Prof. Linga Reddy Cenkeramaddi, Prof. Ajit Jha, and Prof. Jing Zhou. Other key researchers involved in the project are Prof. Kimmo Kansanen from NTNU, Dr. Christopher Harman from NIVA, Prof. Phaneendra K. Yalavarthy from the Department of computational data sciences, Indian Institute of Science, Bangalore, Prof. Abhinav Kumar from Indian Institute of Technology, Hyderabad, Prof. Soumya J. from Birla Institute of Technology and Science, Hyderabad, Prof. M B Srinivas from Birla Institute of Technology and Science, Hyderabad (Presently at BML University, Founded by Hero Group) and Prof. Lalitha Vadlamani from the International Institute of Information Technology, Hyderabad. Søren Kragholm at UiA will participate in the administrative coordination of the INCAPS project.
Major goals are to strengthen competitiveness and innovation capacity, solve major societal challenges, and develop high-quality academic environments. This project considers broad areas of research which include smart sensing for autonomous systems, mmWave sensors-based system design, analog, digital, and mixed signal circuit design, prototyping of wireless communication systems, low-altitude UAVs tracking and communications, de-centralized wireless communications, in-network processing and intelligence for heterogeneous wireless sensor and communication networks, machine learning and deep learning for autonomous systems, data analytics, energy harvesting based smart electronic systems, smart water networks and inference methods for timely detection and prediction of events, cognitive control and adaptive learning in autonomous cyber-physical systems.
The key objectives of the INCAPS project are the following: I). Strengthening collaborative network between industry (both public and private enterprises, small and medium-sized enterprises, and multi-national companies) and academia. II). Increased value creation and enhanced innovation by using smart sensing, machine, and deep learning techniques in autonomous cyber-physical systems. III). Facilitate education and knowledge sharing through better mobility for students and researchers. IV). Create an arena for the generation of research and innovation projects. V). Increased utilization of research and educational infrastructure both in Norway and India. VI). Integrate professionals from industries and academics through workshops, seminars, webinars, and summer/winter schools.
Best Master’s Thesis in ICT 2019 (Supervised by Prof. Linga Reddy Cenkeramaddi and Prof. Professor Magne Arild Hauglund)
Master Thesis: “Design and implementation of wake-up radios for long-range wireless IoT devices”
Best master thesis in ICT 2019 (Student and Professor).
Master Student Anders Frøytlog, did his Master’s Thesis under the main supervision of Professor Linga Reddy Cenkeramaddi and co-supervision of Professor Magne Arild Hauglund. The project task is defined by Assoc. Prof. Linga Reddy Cenkeramaddi. The solutions (especially DC-MAC protocol along with wakeup radio) proposed in the thesis greatly reduce the power consumption in long-range wireless IoT devices. A summary of the thesis can be found below.
Summary of the thesis: As the development within Internet of things (IoT) increases rapidly and the market starts to utilize its potential, an enormous effort is being made in both academia and industry to optimize solutions according to the market demands. The demands vary from case to case and some of them include high data rate, long battery lifetime, low latency, and long-range/area coverage depending on application scenarios. The numerous use cases and demands for IoT resulted in various IoT technologies.
System overview: Design and implementation of wake-up radios for long-range wireless IoT devices.
In many IoT applications, especially Wireless IoT applications, energy efficiency and battery lifetime are the most important performance metrics. The wireless access mechanisms used in current technologies utilize Duty-cycling (DC) to reduce power consumption. DC allows a node to turn the radio on and off in specific intervals in order to reduce power consumption. These DC-MAC protocols suffer from overhearing, idle listening, or unnecessary transmission of advertisement packets. The different protocols may also include long delay time caused by the inactive period in the MAC protocol. The recent research and development of Wake-up Radios (WuRs) address some of these problems. A WuR is a simple low-power radio receiver that always listens to the channel to detect a Wake-up Call (WuC). A wake-up radio receiver (WuRx) is attached to the main radio which is always OFF, except when it is supposed to send data. The WuRx and the main radio (MR) are two parts of an IoT node. The use of WuRx eliminates the unnecessary power consumption caused by idle listening and reduces the overhearing consumption as well as the latency. Many articles have been published about WuRs. However, most of the current WuR solutions focus on short-range applications. The objective of this thesis is to design a WuRx for long-range applications (10km to 15km range), implement a WuRx and evaluate the results and compare them to existing solutions.
