• The project titled A study on the utilization of student welfare schemes offered by Government of Tamil Nadu in Coimbatore district, is funded by Indian Council Of Social Science Research. The investigators of the project are R.Gowtham, Dr. Prakash P, Mr. M.Vamsee Krishna Kiran, Ms. R. Archanaa. The duration of the project is 1 year.

  • The project titled A Service - Oriented Pervasive Framework for Smart Hospitals, is funded by NRDMS/DST. The investigators of the project are Dr. Vidhya Balasubramanian, Dr. G.Jeyakumar, Dr. C.K.Shyamala.  The duration of the project is 24 months.

  • The project titled A Framework for event modeling and detection for Smart Buildings using Vision Systems, is funded by DST(NRDMS). The investigators of the project are Dr. Latha Parameswaran, Dr.T.Senthil Kumar.  The duration of the project is 24 months.

  • The project titled Technology inputs in promoting indigenous food recipes of Irulas and Kurumbas tribes and empowering disadvantaged youth of Masinagudi and Ebbanad village of The Nilgiri District, is funded by Ministry of Tribal Affairs. The investigators of the project are Dr. T. Senthil Kumar, Dr. S. Rajendra Kumar, Dr. Udhaya Kumar. The duration of the project is 1 year.

  • The project titled "A study on the utilization of student welfare schemes offered by Government of Tamilnadu in Coimbatore district," is funded by Indian Council of Social Science Research. 

  • Asset and people tracking solutions are crucial in providing seamless operations devoid of clashes between services and elements, especially when designing smart environments for large hospitals.

  • In this project, we aim to monitor mobile patients, locate important personnel, detect and locate crowds, locate and track essential surgical assets and verify access control restrictions with respect to people and assets by developing a low-cost, end-to-end system that can help configure and operate a smart hospital, which supports the above functionalities.

  • The objective of the project is to design a secure and efficient authenticated encryption algorithm. This algorithm could be implemented on a variety of platforms including GPUs and mobile devices. This implementation will have an impact on the level of security as well as the speed, which however can be suitably tailored. From the perspective of national security, there is a need to give considerable importance for the research, development and deployment of indigenously built secure and efficient authenticated encryption algorithm in major communication systems.

  • Dr. T. Senthil kumar, Dr. T. Gireesh Kumar, Dr. Harish Ram D. S. received a grant of USD 12000 (Rs 7,68,000) under the IBM Shared University Research (SUR) scheme for a project titled "Malware detection using FPGA, Sandboxing and Machine Learning under the IBM Shared University Research (SUR) scheme during October 2015.

  • Computationally intensive applications are very diverse. As a consequence, the next generation computing architectures are expected to be heterogeneous---comprising variable granularity computing blocks with varied communication mechanisms. Capturing this heterogeneity across applications is an area of research that has a profound impact in the definition of its architectural features.

  • Today’s computing systems are heterogeneous, with diverse microarchitectures. It is common to design systems comprising multi-core CPUs, Graphic Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs). Each of these devices have proven to be advantageous for accelerating diverset complex computational problems.

  • COTS Security Incident and Event Management (SIEM) Systems process log events based on built-in rules and identify actionable incidents. These primarily identify known attacks. Using Machine Learning techniques such as Naive Bayes and AdaBoost algorithms, we aim to predict new attacks probabilistically for wired and wireless networks. The Machine Learning-based prediction system in tandem with an SIEM system to predict an attack before it actually occurs. Evaluate the effectiveness of the ML system comparing with the SIEM system in network attack prediction

  • Over the recent years, video camera networks have become ubiquitous and a part of our everyday environments. Such camera networks are deployed in a wide gamut of applications ranging from surveillance, emergency response, disaster recovery, and health care monitoring to name a few.

  • The goal of this project is to create a hierarchical extendible data model for indoor information which can represent buildings, entities within it, utilities, objects inside the building, and sensors inside the building for object tracking and localization, so that the represented data is easily stored and queried using a spatio-temporal database. An indoor information system will be developed which can support indoor asset tracking and real-time navigation over this data model. This project is funded by DST, India.

  • An indoor information system is a system that gives information about the details of a building such as the different spaces within the building, exits, and their properties and also about other entities in the buildings like utilities, objects like tables, shelves etc.

  • The project titled “Indoor Information Representation and Management System” is funded by Department of Science and Technology, India. Dr. Vidhya Balasubramanian, Associate Professor, Department of Computer Science Engineering, Amrita School of Engineering, Coimbatore, is the Principal Investigator. 

  • AMMACHI Labs believes that women empowerment is the key to alleviating poverty, social injustice and economic instability. Our innovative and solid programs offer sustainable solutions to India’s challenges and provide concrete steps to tackle problems and empower women and communities.

  • A solar powered classroom on wheels is what the MoVE project is all about. Skills training is the least accessible to those who stand to benefit the most from it. Making vocational education mobile may be one solution to this. In an effort to bring quality vocational education to the otherwise inaccessible regions of the diverse geography that India is, AMMACHI Labs conceptualised, designed and built a mobile vocational training center. 

  • As with computing systems, trends show sharp increase in more and more electronic devices and appliances networked to the internet. From simple home appliances to more complex systems such as medical devices and industrial control (SCADA) systems, there is an integration of software and hardware that causes new security threats due to its contact to the internet.

  • Visual cryptography is a perfectly secure way to protect secrets and is characterized by its decryption method. This project is to develop new visual cryptographic scheme satisfying certain conditions. In this project, a secret image is split into a set of shares, so that some authorized shares can have access to the secret, where as other unauthorized shares cannot leak out any secret information.

  • The project 'Security Event Processing Acceleration Using GPGPU' proposes to provide a proof of concept for building a FPGA based NIDS for highspeed network environments. The proposed FPGA based NIDS would employ a lightweight snort detection engine to filter packets based on predefined rules over packet headers and payloads.

  • Attacks on information systems have grown exponentially in volume and in sophistication. While there are many security systems and ‘honeypots’ designed to harvest or trap the malware and study its behaviour, still it is very difficult to detect and identify the advanced malwares that are stealthy in nature and causing more serious damage. The traditional ‘honeypot’ systems that are traps set to detect attempts at unauthorised use of information systems, do not identify or do not have the capability to attract and detect advanced threats.

  • Speaker recognition systems are useful for deriving intelligence information by tracking telephone conversations of people who are perceived to be a threat to the national security. Rules prohibit security agencies from eavesdropping on telephone conversations of private citizens. However, it may be necessary to eavesdrop on people with questionable national integrity.

  • In order to facilitate remote experimentation for multiple users, the project demonstrates the possibility of real-time shared access for multiplexing the usage of control and acquisition hardware. The project also investigates and develops the architecture for scaling up the experiments by effective timesharing of available resources to be made available to large scale of users.

  • Comprehensive study of threats, their operational architecture, and adoption of threat modeling for their classification, form the foundation for development of secure technologies for cloud. Cloud platforms today assist providers in controlling and managing the customer VMs. In addition, they also help monitor and manage cloud performance. 

  • This project is ongoing as part of the Amrita E-Learning Research Center. The goal of this project is to develop solutions for content based search and retrieval of multimedia E-Learning material.

  • Wordnet is an online lexical reference system. Its design is inspired by current psycholinguistic and computational theories of human lexical memory. Nouns, verbs, adjectives and adverbs are organized into synonymous sets, each representing one underlying lexicalized concept. Different semantic relations link the synonymous sets. Wordnet is neither a traditional dictionary nor a thesaurus but combines features of both types of lexical reference resources.

  • This project is an initiative of Ministry of Communication and Information Technology. The principal investigator of the project is Dr. Soman K. P., Professor and Head, Amrita Center for Computational Engineering and Networking (CEN). 

  • AMMACHI Labs uses computerized vocational education training (cVET) to make education accessible and interesting. The smart classroom concept was introduced into the many training centers across India to enable a learning environment that would scale up skill training, maximize student participation and enhance learning.

  • The stability theory of stream ciphers suggests that good key stream sequences must not only have a large linear complexity, but also change of a few terms must not cause a significant drop of the Linear complexity. This unfavorable property leads to the concept of k-error linear complexity. In this project we propose to extend this to the case of multisequences.

  • This research project identifies an appropriate combination of metal-elastomeric module configuration, using multi-layer shear damped viscoelastic approach, for mitigating the structure-bound vibrations on to the sensitive equipment. The composites are made of a metal (aluminium), and an elastomer (natural rubber and silicone rubber).

  • This is concerned with development of video summarization techniques like Non negative matrix factorization, singular value decomposition etc.

  • METASIM is a highly distributed collection of simulation tools connected by a series of translators that access a common database.

  • A Cryptographically Secure Power Generators (CSPRNG) is a power generator with properties that makes it suitable for use in cryptography. CSPRNGs are designed explicitly to resist determined mathematical reverse engineering. In this project, we are studying the designs of power generators based on number theory. We concentrate in fast generation of the following generators: Power generators such as BBS generators.

  • It is a micro-level response activity simulator developed as part of Rescue and Responsphere for the purpose of testing IT solutions in the context of a crisis response. It is a multi-agent simulator for simulating campus level crisis response activities. It has plug and play capabilities where models and IT solutions can be incorporated into the system.

  • It currently being developed under the SUGA project at UCI, that supports cross disability access. The distance-learning framework is built on top of the MPEG-4 framework and supports the adaptation techniques developed as part of the SUGA project.

  • The project proposes to develop a hardware based network intrusion detection system for high speed networks.

  • The aim of this work is the generation of a three dimensional (3D) model of a Scanning Electron Microscopy (SEM) image from a singular two dimensional (2D) image using filtering, feature extraction, segmentation and mapping of the depth of the features on the nano surface.

  • The project titled “Smart Handheld  Device for Detection of Gas Poisoning in Sewage Works" is funded by Amrita TBI. Mr. V. Anantha Narayanan is the Principal Investigator. The duration of the project is 6 months. 

  • This project aims to improve the state of art in effective retrieval of text and image data from large web corpora. As part of this project novel topic modeling approaches and change detection algorithms are being developed to improve the retrieval efficiency.

  • The project titled “Predictive Modeling of Complex IT systems" is funded by DRDO. Mr. Prashant R. Nair, Dr. M. Sethumadhavan are the investigators. The duration of the project is 1 year.

  • In this work an efficient lifting scheme based on denoising for super resolution reconstruction of low resolution mammogram images is proposed. We have presented a way to improve the quality of x-ray mammography images without having to use more radiations, which increases health risks of patients. The results indicate that the proposed system can facilitate the doctor to detect breast cancer in early stage of diagnosis process. Early detection tests for breast cancer can save many thousands of lives, with super resolution reconstruction the cancer can be diagnosed at an early stage and treated successfully. High resolution images give better visibility of the breast, particularly near the skin line, chest wall and in women with dense breast tissues.

  • The project titled “Augmented Reality Headset" is funded by Amrita TBI Tide. Mr. Shriram K .V. is the Principal Investigator.

  • Current product recommender systems only allow users to select from off the shelf products. However if they wish to mix and match components to create customized products, current recommendation systems do not support that.

  • The project titled “Smart water management" is submitted to DeitY. Dr. P. Bagavathi Sivakumar, Dr. Latha Parameswaran, Mr. V. Ananthanarayanan, Mr.Prashant Nair are the investigators. The duration of the project is 3 years. 

  • Modelling the changing behavior of a user is done by defining a user context for personalized ser­vices. Though many parameters have been identi­fied to sense the context of a user automatically by a mobile device, identifying the right semantic context is still a challenge. Towards better defining user context for context aware mobile applications, this work pro­poses models for smarter context detection, a multi­dimensional evolutionary ontology, dynamic user pro­file generation, and a mapping of context and user preferences using a regression model.

  • Accelerating feature extraction and matching algorithms using GPUs for low vision images is the aim of this work. Feature relationships are built from pixel level features to facilitate subsequent learning and generalization of the object information in an image.

  • The goal of this project is to improve the ease of generating knowledge representations, so that semantic search can be better supported. The project aims to simplify the process of knowledge representation by using statistical approaches and enhancing their expressivity using graph theoretical approaches

  • The project titled “Autonomous Visual and Wireless Sensor Network based Smart Evacuation System" is submitted to DeitY. Dr. T. Senthil Kumar is the Principal Investigator. The duration of the project is 3 years. 

  • Medical diagnosis devices are being built with IoT. Health professionals can monitor diagnosis data from a remote location and act based on observations. The project also addresses issues related to the security of information transfer through Access control and Device Authentication mechanisms.