- Solar and Space Plasma Dynamics
- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Geophysics and Gravity Measurements
- Ionosphere and magnetosphere dynamics
- Network Traffic and Congestion Control
- Radio Astronomy Observations and Technology
- Advanced Wireless Communication Techniques
- Geomagnetism and Paleomagnetism Studies
- Interconnection Networks and Systems
- Pulsars and Gravitational Waves Research
- Wireless Communication Networks Research
- Power Line Communications and Noise
- Spacecraft Design and Technology
- Astro and Planetary Science
- Advanced Queuing Theory Analysis
- Advanced Data Compression Techniques
- GNSS positioning and interference
- Semiconductor Lasers and Optical Devices
- Satellite Communication Systems
- Advanced Wireless Network Optimization
- Astrophysics and Cosmic Phenomena
- Earthquake Detection and Analysis
- Face and Expression Recognition
- Stellar, planetary, and galactic studies
M S Ramaiah University of Applied Sciences
2024
Inter-University Centre for Astronomy and Astrophysics
2006-2018
Nanyang Technological University
2001-2016
Indira Gandhi Medical College
2013
Indian Institute of Astrophysics
2000-2010
Savannah River National Laboratory
2003
University of Cincinnati
2002
National Institute for Space Research
1997-2000
Zygo (United States)
1990
Raman Research Institute
1981-1988
In this paper, we present a metacognitive sequential learning algorithm for neuro-fuzzy inference system classification tasks, which is referred to as "metacognitive (McFIS)." The McFIS developed based on the principles of best human strategy, viz., self-regulatory strategy in framework. has two components: cognitive component and component. A forms McFIS, mechanism its ability monitored controlled by mechanism. For each sample training dataset, uses self-adaptive thresholds choose one...
In this paper, we propose an evolving interval type-2 neurofuzzy inference system (IT2FIS) and its fully sequential learning algorithm. IT2FIS employs fuzzy sets in the antecedent part of each rule consequent realizes Takagi-Sugeno-Kang mechanism. order to render fast accurate, a data-driven interval-reduction approach convert type-1 set number consequent. During learning, algorithm learns sample one-by-one only once. The structure evolves automatically adapts network parameters using...
We propose a sequential Meta-Cognitive learning algorithm for Neuro-Fuzzy Inference System (McFIS) to efficiently recognize human actions from video sequence. Optical flow information between two consecutive image planes can represent hierarchically local pixel level global object level, and hence are used describe the action in McFIS classifier. classifier its is developed based on principles of self-regulation observed meta-cognition. decides what-to-learn, when-to-learn how-to-learn...
Characterising the statistics of wavelet coefficients is a critical issue in image compression and denoising. Many powerful approaches have been investigated, but accurate modelling suffers from high computation complexity. In this work an efficient adaptive algorithm to capture dependency both inner inter scale proposed. Experimental results show that compared with , case higher noise variance, greater PSNR performance gain may be obtained.
This paper presents a complex-valued interval type-2 neuro-fuzzy inference system (CIT2FIS) and derive its metacognitive projection-based learning (PBL) algorithm. Metacognitive CIT2FIS (Mc-CIT2FIS) consists of CIT2FIS, which realizes Takagi-Sugeno-Kang type mechanism, as cognitive component. A PBL with self-regulation is The rules employ type-\(2~q\) -Gaussian membership functions that can represent different radial basis for values \(q\) . As each sample presented to the network, component...
In this paper, we propose a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS) for recognition of emotions from facial features. Local binary patterns have been proven to effectively describe the statistical characteristics face image as it contains information related edges, spots, etc. The aim McFIS is approximate functional relationship between features and various emotions. classifier its sequential learning algorithm developed based on principles self-regulation observed in human...
In this paper, we present a Meta-cognitive Interval Type-2 neuro-Fuzzy Inference System (McIT2FIS) classifier and its projection based learning algorithm. McIT2FIS consists of two components, namely, cognitive component meta-cognitive component. The is an (IT2FIS) represented as six layered adaptive network realizing Takagi-Sugeno-Kang type inference mechanism. IT2FIS begins with zero rules, rules are added updated depending on the relative knowledge by sample in comparison to that...
In this paper, we present a complex-valued neuro-fuzzy inference system (CNFIS) and its gradient descent based learning algorithm developed employing Wirtinger calculus. The proposed CNFIS is four layered network which realizes zero-order Takagi-Sugeno-Kang fuzzy mechanism. used to predict the speed direction of wind. Here, are considered as statistically independent variables represented signal (with magnitude phase). Performance compared with other algorithms available in literature...
Small-scale dynamos are expected to operate in all astrophysical fluids that turbulent and electrically conducting, for example the interstellar medium, stellar interiors, accretion discs, where they may also be affected by or competing with large-scale dynamos. However, possibility of small-scale being excited at small intermediate ratios viscosity magnetic diffusivity (the Prandtl number) has been debated, them depending on forcing wavenumber raised. Here, we show, using four values...
A new digital spectrograph for obtaining a dynamic spectrum of radio burst emission from the Sun in frequency range 30-80 MHz has been recently commissioned at Gauribidanur Radio Observatory (Lat: 13°36´12´´N and Long: 77° 27´07´´E), about 100 km north Bangalore, India. This paper describes various aspects antenna system, frontend receiver hardware spectrograph. Some initial results obtained with instrument are also presented.
A neuro-fuzzy classifier based on the meta-cognitive principle of human self-regulated learning (Mc-FIS) is proposed in this paper. The network decides what-to-learn, when-to-learn and how-to-learn current information present new sample. utilizes self-regulating error criterion to decide which sample learn when learn. rule pruned if its significance below a particular threshold, class specific information. This results compact deletion helps overfitting. Class used executing above tasks....
In this paper, we propose a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS) for accurate detection of human actions from video sequences. employ optical flow based features as they can represent information local pixel level to global object between two consecutive image planes. The functional relationship these and action classes is approximated using McFIS classifier. sequential learning algorithm developed on the principles self-regulation observed in meta-cognition. decides...
We report metric radio observations and the results obtained using two-dimensional ray-tracing analysis of solar corona close to onset phase exceptionally bright prominence eruption associated massive coronal mass ejection (CME) 1998 June 2. The average electron density observed enhancements at location was found be ~17 times greater than ambient medium. also calculated their width along line sight, mean value is ≈160,000 km. estimate CME about 4 less that white-light value.
Abstract Possible signatures of primordial magnetic fields on the Cosmic Microwave Background (CMB) temperature and polarization anisotropies are reviewed. The signals that could be searched for include excess particularly at small angular scales below Silk damping scale, B‐mode polarization, non‐Gaussian statistics. A field a few nG level produces 5 µK level, 10 times smaller, is therefore potentially detectable via CMB anisotropies. An even smaller field, with B 0 < 0.1 nG, lead to...
A fully functional Braille display terminal developed for visually handicapped people to access and work with IBM personal computers is described. The hardware software design required the fabrication of control circuitry, character conversion modules, are system consists a unit, keypad. To minimize number devices be accessed, special keypad issue commands unit integrated normal PC electromechanical components BDT comprise (a) 40-Braille cell which displays 40 characters at time (b) two...
Aims.We study the characteristics of doublet type II radio bursts in which two occur sequence and investigate their drivers.
Humans seek to select the best decision for a given problem in process that is highly efficient and often ends with success. This due high-order thinking skill: metacognition, which enables humans be successful makers by constantly monitoring their cognitive activities based on earlier experience. Besides this, social aspect of metacognition helps peers experience knowledge. Inspired we propose HumanCog: generic 3-layer architecture solving optimization problems. HumanCog functions way...