Singh U.P.,Madhav Institute of Technology and Science |
Jain S.,Madhav Institute of Technology and Science
Soft Computing | Year: 2017
Success of neural networks depends on an important parameter, initialization of weights and bias connections. This paper proposes modified quaternion firefly algorithm (MQFA) for initial optimal weight and bias connection to neural networks. The proposed modified quaternion firefly method is based on updating population, moving fireflies and best solution in quaternion space. The combination of modified quaternion firefly and neural network is developed with the scope of creating an improved balance between premature convergence and stagnation. The performance of the proposed method is tested on two nonlinear discrete time systems, Box–Jenkins time series data and exchange rate prediction of Indian currency. Results of the MQFA with back-propagation neural network (MQFA-BPNN) compared with existing differential evolution-based neural network and opposite differential evolution-based neural network. Results obtain using MQFA-BPNN envisage that this method is effective and provides better identification accuracy. Computational complexity of MQFA-BPNN is deliberated, and validation of proposed method is tested by statistical methods. © 2017 Springer-Verlag Berlin Heidelberg
Murthy G.R.S.,Madhav Institute of Technology and Science |
Jadon R.S.,Madhav Institute of Technology and Science
2010 IEEE 2nd International Advance Computing Conference, IACC 2010 | Year: 2010
Visual Interpretation of gestures can be useful in accomplishing natural Human Computer Interactions (HCI). In this paper we proposed a method for recognizing hand gestures. We have designed a system which can identify specific hand gestures and use them to convey information. At any time, a user can exhibit his/her hand doing a specific gesture in front of a web camera linked to a computer. Firstly, we captured the hand gesture of a user and stored it on disk. Then we read those videos captured one by one, converted them to binary images and created 3D Euclidian Space of binary values. We have used supervised feed-forward neural net based training and back propagation algorithm for classifying hand gestures into ten categories: hand pointing up, pointing down, pointing left, pointing right and pointing front and number of fingers user was showing. We could achieve up to 89% correct results on a typical test set. ©2010 IEEE.
Gupta R.A.,Indian National Institute of Engineering |
Wadhwani A.K.,Madhav Institute of Technology and Science |
Kapoor S.R.,Rajasthan Technical University Kota
IEEE Transactions on Energy Conversion | Year: 2011
Even though induction motors are frequently used electromagnetic devices in industries owing to their high reliability, high efficiency, and low maintenance requirements, they are prone to various faults and failures. Most of these faults occurring in the induction motors are perceptible in nascent stages. This averts the inopportune machine failures and helps to adeptly plan the maintenance schedules. Most of the methods used for preprediction of faults in induction motors are based on complicated techniques involving tortuous mathematical analysis. Although the importance and accuracy of these methods cannot be overruled, but a simple method is required as a first stage necessary condition test, which can classify the motor health condition into one of the three broad categories, namely, healthy, fault prone, and critical. This paper discusses a simple method based on symbolic dynamic analysis of stator current samples to detect faults in the induction motors. The experimentation has been performed on a 3Φ, 1.5 kW, 4P, 1440 RPM squirrel cage motor to validate the proposed scheme. The data captured through the laboratory setup have been used to corroborate the proposed symbolic dynamic-based scheme. © 2010 IEEE.
Varshney S.,Madhav Institute of Technology and Science |
Srivastava L.,Madhav Institute of Technology and Science |
Pandit M.,Madhav Institute of Technology and Science
International Journal of Electrical Power and Energy Systems | Year: 2012
This paper presents the application of cascade neural network (CANN) based approach for integrated security (voltage and line flow security) assessment. The developed cascade neural network is a combination of one screening module and two ranking modules, which are Levenberg-Marquardt Algorithm based neural networks (LMANNs). All the single line outage contingency cases are applied to the screening module, which is 3-layered feed-forward ANN having two outputs. The screening module is trained to classify them either in critical contingency class or in non-critical contingency class from the viewpoint of voltage/line loading. The screened critical contingencies are passed to the corresponding ranking modules, which are developed simultaneously by using parallel computing. Parallel computing deals with the development of programs where multiple concurrent processes cooperate in the fulfillment of a common task. For contingency screening and ranking, two performance indices: one based on voltage security of power system (VPI) and other based on line flow (MWPI) are used. Effectiveness of the proposed cascade neural network based approach has been demonstrated by applying it for contingency selection and ranking at different loading conditions for IEEE 30-bus and a practical 75-bus Indian system. The results obtained clearly indicate the superiority of the proposed approach in terms of speedup in training time of neural networks as compared to the case when the two ranking neural networks were developed sequentially to estimate VPI and MWPI. © 2012 Elsevier Ltd. All rights reserved.
Dua V.K.,Bharat Heavy Electricals Ltd. |
Kumar A.,Madhav Institute of Technology and Science |
Pandey A.C.,Bharat Heavy Electricals Ltd. |
Kumar S.,Bharat Heavy Electricals Ltd.
Parasites and Vectors | Year: 2013
Background: Indiscriminate use of synthetic insecticides to eradicate mosquitoes has caused physiological resistance. Plants provide a reservoir of biochemical compounds; among these compounds some have inhibitory effect on mosquitoes. In the present study the larvicidal, adulticidal and genotoxic activity of essential oil of Psoralea corylifolia Linn. against Culex quinquefasciatus Say was explored. Methods. Essential oil was isolated from the seeds of P. corylifolia Linn. Larvicidal and adulticidal bioassay of Cx. quinquefasciatus was carried out by WHO method. Genotoxic activity of samples was determined by comet assay. Identification of different compounds was carried out by gas chromatography- mass spectrometry analysis. Results: LC§ssub§50§esub§ and LC§ssub§90§esub§ values of essential oil were 63.38±6.30 and 99.02±16.63 ppm, respectively against Cx. quinquefasciatus larvae. The LD§ssub§50§ esub§ and LD§ssub§90§esub§ values were 0.057±0.007 and 0.109±0.014 mg/cm§ssup§2§esup§ respectively against adult Cx. quinquefasciatus,. Genotoxicity of adults was determined at 0.034 and 0.069 mg/cm§ssup§2§esup§. The mean comet tail length was 6.2548±0.754 μm and 8.47±0.931 μm and the respective DNA damage was significant i.e. 6.713% and 8.864% in comparison to controls. GCMS analysis of essential oil revealed 20 compounds. The major eight compounds were caryophyllene oxide (40.79%), phenol,4-(3,7-dimethyl-3- ethenylocta-1,6-dienyl) (20.78%), caryophyllene (17.84%), α-humulene (2.15%), (+)- aromadendrene (1.57%), naphthalene, 1,2,3,4-tetra hydro-1,6-dimethyle-4-(1-methyl)-, (1S-cis) (1.53%), trans- caryophyllene (0.75%), and methyl hexadecanoate (0.67%). Conclusion: Essential oil obtained from the seeds of P. corylifolia showed potent toxicity against larvae and adult Cx. quinquefasciatus. The present work revealed that the essential oil of P. corylifolia could be used as environmentally sound larvicidal and adulticidal agent for mosquito control. © 2013 Dua et al.; licensee BioMed Central Ltd.
Sharma P.,Madhav Institute of Technology and Science |
Arya K.V.,ABV Indian Institute of Information Technology and Management |
Yadav R.N.,Maulana Azad National Institute of Technology
Signal Processing | Year: 2013
This paper presents an efficient face recognition method where enhanced local Gabor binary pattern histogram sequence has been used for efficient face feature extraction and generalized neural network with wavelet as activation function is being used for classification. In this method the face is first decomposed into multiresolution Gabor wavelets the magnitude responses of which are applied to enhanced local binary patterns. The efficiency has been significantly improved by combining two efficient local appearance descriptors named Gabor wavelet and enhanced local binary pattern with generalized neural network. Generalized neural network is a proven technique for pattern recognition and is insensitive to small changes in input data. The proposed method is robust-to-slight variation of imaging conditions and pose variations. Performance comparison with other existing techniques shows that the proposed technique provides better results in terms of false acceptance rate, false rejection rate, equal error rate and time complexity. © 2012 Elsevier B.V.
Khaliq A.,Jamia Millia Islamia University |
Agrawal B.K.,Jamia Millia Islamia University |
Kumar R.,Madhav Institute of Technology and Science
International Journal of Refrigeration | Year: 2012
In the proposed cogeneration cycle, a LiBr-H2O absorption refrigeration system is employed to the combined power and ejector refrigeration system which uses R141b as a working fluid. Estimates for irreversibilities of individual components of the cycle lead to possible measures for performance improvement. Results of exergy distribution of waste heat in the cycle show that around 53.6% of the total input exergy is destroyed due to irreversibilities in the components, 22.7% is available as a useful exergy output, and 23.7% is exhaust exergy lost to the environment, whereas energy distribution shows 44% is exhaust energy and 19.7% is useful energy output. Results also show that proposed cogeneration cycle yields much better thermal and exergy efficiencies than the previously investigated combined power and ejector cooling cycle. Current investigation clearly show that the second law analysis is quantitatively visualizes losses within a cycle and gives clear trends for optimization. © 2011 Elsevier Ltd and IIR. All rights reserved.
Saxena A.R.,Madhav Institute of Technology and Science
Journal of Electrical Systems | Year: 2014
In this paper, the comparative analysis of two maximum power point tracking (MPPT) algorithms namely Perturb and Observe (P&O) and Incremental conductance (InC) is presented for the Photo-Voltaic (PV) power generation system. The mathematical model of the PV array is developed and transformed into MATLAB/Simulink environment. This model is used throughout the paper to simulate the PV source characteristics identical to that of a 20 Wp PV panel. The MPPT algorithms generate proper duty ratio for interfacing dc-dc boost converter driving resistive load. The performances of these algorithms are evaluated at gradual and rapidly changing weather conditions where it is observed that InC method tracks the rapidly changing insolation level at a faster rate as compared to P&O. Depending upon the prevailing environmental conditions the MPPT algorithms finds a unique operating point to track the maximum available power. The algorithms find a fixed duty ratio by comparing the previous power, voltage and current thereby optimizing the power output of the panel. The main objective is to compare the tracking capability and stability of the algorithms under different environmental situations on par with other real world tests. © JES 2014.
Singh H.,Madhav Institute of Technology and Science |
Srivastava L.,Madhav Institute of Technology and Science
International Journal of Electrical Power and Energy Systems | Year: 2014
Reactive power or VAR management is one of the most crucial tasks required for proper operation and control of a power system. Reactive power management is carried out to reduce losses and to improve voltage profile in a power system, by adjusting the reactive power control variables such as generator voltages, transformer tap-settings and other sources of reactive power such as capacitor banks or FACTS devices. VAR management provides better system security, improved power transfer capability and overall system operation. VAR management is a complex combinatorial optimization problem involving nonlinear functions having multiple local minima and nonlinear and discontinuous constraints. In this paper, the VAR management problem is formulated as a nonlinear constrained multi-objective optimization problem with equality and inequality constraints for minimization of real power losses and voltage deviation simultaneously. This multi-objective problem is solved using Differential Evolution (DE), which is a population based search algorithm. For avoiding the time and the effort in tuning the parameters of DE algorithm, a modified DE algorithm with time varying chaotic mutation and crossover is proposed for solving the multi-objective VAR management problem. Weighing factor method has been employed for finding Pareto optimal set for VAR management problem. Fuzzy membership function is used to obtain the best compromise solution out of the available Pareto-optimal solutions. Effectiveness of the proposed modified DE algorithm based approach has been demonstrated on IEEE 30-bus system and is found to be superior to classical DE and its variants Self-adaptive Differential Evolution (SaDE) and Ensemble of Mutation and Crossover Strategies and Parameters in Differential Evolution (EPSDE) in terms of convergence behavior and solution quality. © 2013 Elsevier Ltd. All rights reserved.
Agarwal K.,Madhav Institute of Technology and Science
Proceedings - 2015 International Conference on Computational Intelligence and Communication Networks, CICN 2015 | Year: 2015
The mobile Adhoc network is deployed in the environment where traditional wired network cannot be established due to its required features and their limitation. Use of directional antenna is one of the most promising techniques for the high speed wireless network such as 802.11ac, IEEE 802.11ad and IEEE 802.15.3c. Directional antenna offer remarkable possibilities for improving the performance of the adhoc network. In this paper proposed a new directional MAC mechanism to improve the spatial reuse of MANET. And compare proposed DMAC scheme with the recently proposed directional MAC scheme and result show that proposed scheme outperforms these scheme in several scenarios. © 2015 IEEE.