T. R. Rangaswamy

Bio: T. R. Rangaswamy is an academic researcher from B. S. Abdur Rahman University. The author has contributed to research in topics: Fuzzy control system & PID controller. The author has an hindex of 7, co-authored 25 publications receiving 166 citations.

Adaptive and optimal control of a non-linear process using intelligent controllers

Abstract: A time-optimal control for set point changes and an adaptive control for process parameter variations using neural network for a non-linear conical tank level process are proposed in this work. Time-optimal level control was formulated using dynamic programming algorithm and basic properties of the solutions were analysed. It was found that the control is of bang-bang type and there is only one switching. In this method, a mathematical step-by-step procedure is used to obtain the optimal valve position path with one switching and is trained by neural network, based on the back-propagation algorithm. The dynamic programming procedure allows the set point to be reached as fast as possible without overshoot. An adaptive system is also designed and proved to be useful in adjusting the trained parameter of the dynamic programming based neural network for the process parameter variations. A prototype of conical tank level system has been built and implementation of dynamic programming based neural network control algorithm for set point changes and implementation of adaptive control for process parameter variations are performed. Finally, the performance is compared with conventional control. The results prove the effectiveness of the proposed optimal and adaptive control schemes.

Energy efficient cluster based approach for data collection in wireless sensor networks with multiple mobile sink

Abstract: A wireless sensor network could be either homogeneous network or heterogeneous network. Depending upon the nature of application requirements a wireless sensor node could either be static or mobile one. When the nodes are static, data collection by the sink from various sources will be difficult and time consuming process. Also static deployment of sink as well as source nodes lead to energy hole problem because the nodes in one hop neighbor of sink must always be active to transmit the data from the sources down to it. This energy hole problem leads to network partition and reduction in life time of any wireless sensor network. So, to increase the lifetime of a wireless sensor network and energy efficient routing mobile sink based approach could be used. Due to the mobility of sink data collection will be carried out faster in time and energy hole problem could be eliminated. Introduction of a single mobile sink also leads to a problem like coverage area, time delay due to obstacles, interference or limited entry and pause time, time synchronization between the source and sink, link failure or node failure and so on. By considering the residual energy of each node and reliable data transfer in a wireless sensor network a new cluster based approach using controlled flooding is proposed with multiple mobile sink for prolonging the life time of a wireless sensor network. Irrespective of the medium this approach uses predetermined and controlled mobility model for determining the direction of movement for mobile sink. This approach uses some set of rules for path reconstruction phase with limited flooding of update message consisting of current location of the sink and Time Of Arrival (TOA). Simulation result shows that the multiple mobile sink with reduced reconstruction of route has improved the energy efficiency and increased lifetime of wireless sensor network.

Detection and Classification of Epileptic Seizures using Wavelet feature extraction and Adaptive Neuro-Fuzzy Inference System

Abstract: Epilepsy, a neurological disorder in which patients suffer from recurring seizures, affects approximately 1% of the world population. In this work, an attempt has been made to enhance the diagnostic importance of EEG using Adaptive neuro fuzzy inference system (ANFIS) and Wavelet transform coefficients. For this study, EEG for 20 normal and 30 seizure subjects under standard recording procedure is used. A method based on wavelet transform and ANFIS is used to detect the epileptic seizures. Further, BPN algorithm is used to study and compare the datasets. Average specificity of 99% and sensitivity of 97% are obtained. Results show that the ANFIS is able to detect seizure. It appears that this method of detection makes it possible as a real-time detector, which will improve the clinical service of Electroencephalographic recording.

Neuro based model reference adaptive control of a conical tank level process

Abstract: This paper deals with the adaptive control of a continuous time nonlinear system of conical tank level process using neural networks. An adaptive system based on MRAC technique is proposed and proved to be useful in adjusting the trained parameter of the neural network for approximating the non-linearity of the dynamical system and for the process parameter variations. A neuro model is also developed for this purpose. The weight adaptive laws are developed using an adaptive neural network. The tracking error, which is the difference between the neuro model and the plant output, converge to the required accuracy through the adaptive control algorithm derived by combining the inverse neural network and adaptive neural network. A lab scale experimental setup for the conical tank level process was fabricated. Experimental studies were carried out for conventional control, fuzzy control, neuro control, and adaptive neuro control. The performances of all the above schemes were investigated. The advantages of the proposed scheme, over other methods, were highlighted.

Proactive Hybrid Intrusion Prevention System for Mobile Adhoc Networks

Abstract: The open nature of Mobile Ad Hoc NETworks (MANETs) provides an opportunity for intrusions. The current intrusion mechanisms are reactive and incapable of preventing the intrusions proactively. This paper proposes the secure routing using Hybrid intrusion prevention systems against dropping and data integrity THreat (SHEATH). This proposal implements self-key and mutual-key reliant prevention and the appearance frequency based behavior certainty measurement on routing paths. The self-key prevention scheme exploits the encrypted value of the sequence number as a normal pattern and the decryption determine whether the route reply is the result of a malicious node or not. The behavior certainty measurement using distributed selection of Squad Head nodes ensures the effective observation of misuse pattern and minimum routing overhead. The data forwarding phase shares a mutual key between the communicating nodes that prevent the data integrity attacks. The simulation results confirm the efficiency of the hybrid preventive scheme against intrusions.

The knowledge complexity of interactive proof-systems

Abstract: Usually, a proof of a theorem contains more knowledge than the mere fact that the theorem is true. For instance, to prove that a graph is Hamiltonian it suffices to exhibit a Hamiltonian tour in it; however, this seems to contain more knowledge than the single bit Hamiltonian/non-Hamiltonian.In this paper a computational complexity theory of the “knowledge” contained in a proof is developed. Zero-knowledge proofs are defined as those proofs that convey no additional knowledge other than the correctness of the proposition in question. Examples of zero-knowledge proof systems are given for the languages of quadratic residuosity and 'quadratic nonresiduosity. These are the first examples of zero-knowledge proofs for languages not known to be efficiently recognizable.

A Review of RFID in Supply Chain Management: 2000–2015

Abstract: This paper presents a systematic literature review of papers that were published in academic journals on the applications of radio frequency identification (RFID) in supply chain management between the years 2000 and 2015. As the literature on RFID is not confined to specific disciplines or repositories, this paper proposes a discipline-based framework for classifying RFID literature. Five main classification categories are used in this paper: technology, supply chain management, research methodology, application industries, and social aspects. The paper then focuses on the category of supply chain management and reviews 1187 articles that were published between 2000 and 2015 in rated journals. All the papers reviewed are further classified into eight subclasses under this category of supply chain management. The review yields useful insights into the anatomy of RFID literature in supply chain management, enhances evidence-based knowledge, and contributes to informing practice, policymaking and future research. The review reveals that even presently, despite technical and cost challenges, enormous potential exists for the application of RFID in several areas of supply chain management and the prospects are likely to grow into the future. Since RFID solutions have emerged primarily over only the past 20 years, significant research opportunities exist and would need to be addressed to continue to support the technology’s maturation, evaluation, adoption, implementation, and diffusion.

Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis

Abstract: Many Neurological disorders are very difficult to detect. One such Neurological disorder which we are going to discuss in this paper is Epilepsy. Epilepsy means sudden change in the behavior of a human being for a short period of time. This is caused due to seizures in the brain. Many researches are going onto detect epilepsy detection through analyzing EEG. One such method of epilepsy detection is proposed in this paper. This technique employs Discrete Wave Transform (DWT) method for pre-processing, Approximate Entropy (ApEn) to extract features and Artificial Neural Network (ANN) for classification. This paper presented a detailed survey of various methods that are being used for epilepsy detection and also proposes a wavelet based epilepsy detection method.

Method of monitoring gas turbine engine operation

Abstract: A system, method and apparatus for monitoring the performance of a gas turbine engine. A counter value indicative of the comparison between the engine condition and the threshold condition is adjusted. The aircraft operator is warned of an impending maintenance condition based on the counter value and determines an appropriate course of action.