Santosh Kumar S.,SVCE |
Santosh Kumar S.,Reva University |
Bharathi S.H.,Reva University |
Proceedings of the International Conference on Communication and Electronics Systems, ICCES 2016 | Year: 2017
Recently, use of automatic speech recognition system is demanded for various applications such as security, word to text conversion etc. During the speech signal acquisition, other unwanted signals from various sources are added to the original signal which degrades the performance of ASR system. These unwanted signals are called as noise or mixing of sources which are caused due to multi-user recording, echo effect etc. this issues motivates to develop an efficient algorithm for audio demixing or source separation. To address this issue in this work we propose a new approach for source separation method using nonnegative factorization method. Proposed work utilized source mixing signal modelling, filter bank designing and source separation algorithm implementation. Modelling of signal is performed by combining two different channels which are acquired from different source, this signal is called mixture signal. Later a filter bank is designed using scattering algorithm based on wavelet transform method and a optimization problem is formulated for audio demixing. Experimental study shows the robustness of proposed model by considering various implementation scenarios. © 2016 IEEE.
Journal of Theoretical and Applied Information Technology | Year: 2016
The fourth generation 4 and beyond networks define the future of mobile communication. Handover management in 4 networks based on the IPv6 core is a problem that exists. The co-channel interference in wireless channels effect network and handover performance. In this paper the proposed Noise Resilient Reduced Registration Time Care-of Mobile IP protocol is modelled considering practical network conditions. A threshold based handover decision making algorithm is incorporated in the proposed protocol. The results presented in this paper clearly put forth the effects of the co-channel interference on handover management and network performance in the presence of multiple users. The comparative study prove that the proposed protocol is robust and minimizes network performance degradation considering practical conditions. © 2005 - 2015 JATIT & LLS. All rights reserved.
Sudir P.,SJCIT |
Advances in Intelligent Systems and Computing | Year: 2014
Proposed approach explores a new framework for Curved video text detection and extraction by utilizing fast texture descriptor LU-transform and Maximal H-Transform for the text detection. Connected Component filtering method and Nearest Neighborhood (NN) constraint is utilized for false positive elimination. B-Spline curve is fitted to centroid of each character and each oriented character is vertically aligned by finding angle that aligns the normal vector to the vertical axis. The aligned text string is fed to OCR for recognition. Experiments on various curved video data and Hua’s horizontal video text dataset shows that proposed method is efficacious and robust in detecting and recognizing multioriented videotext. © Springer International Publishing Switzerland 2015.
Mamatha C.,Sri Venkateswara University |
Krishnaiah M.,Sri Venkateswara University |
Prakash C.S.,SJCIT |
Rewatkar K.G.,Dr Ambedkar College |
International Journal of ChemTech Research | Year: 2014
M-type calcium Hexaferrites with substitution of trivalent Aluminum ions were prepared by Solution combustion technique using metal nitrates as oxidants and ODH as reducing agents. The powders were characterized with XRD, SEM, and EDS. XRD analysis indicated the formation of single-phase substituted Mtype calcium hexaferrites with space group of P63/mmc(194). The average crystallite size is calculated and found to be in Nano size. DC conductivity and AC conductivity of bulk samples have been investigated as a function of frequency and temperature. The measurements were carried out in the frequency range of 100 to 10 × 105 Hz,at room temperature. Activation energies were calculated at both ferrimagnetic and paramagnetic regions. The enhanced resistivity of aluminum doped calcium hexaferrite is a prospective application in microwave devices. Magnetic properties are studied with the help of vibrating sample magnetometer (VSM). Results of VSM studies show the decrease in saturation magnetization with the increase of Al concentration. Increase in coercivity and Retentivity illustrated that these are hard ferrite materials.
Ravikumar K.M.,SJCIT |
2015 International Conference on Emerging Research in Electronics, Computer Science and Technology, ICERECT 2015 | Year: 2015
In this paper we will discuss on how electronically linked Brain to Computer Interface(BCI) and Computer to Brain Interface(CBI) can be used to develop Brain to Brain Interface(BBI). In this system, non-invasive technology is deployed to achieve conscious Brain to Brain(B2B) communication. At BCI site, data is transmitted using ElectroEncephaloGraphy (EEG) a non-invasive method to record electrical activity of the brain along the scalp. At CBI site Transcranial Magnetic Stimulation (TMS) or Transcranial direct current stimulation (tDCS) again a non-invasive method used to stimulate small regions of the brain is used to receive the data. From the proposed system, it allows information transfer between brains to do away with language or can send thoughts from one brain to another brain in a way not represented by sounds or words. Connecting brains with computers as well as other brains is profoundly important as it will change human society in future communication technology. © 2015 IEEE.
Mallamma C.G.,SJCIT |
Communications in Computer and Information Science | Year: 2011
This paper presents forecasting of short-term electricity load using dynamic neural networks, DNN, and an assessment of the neural network stability to ascertain continued reliability. This includes an assessment and comparative study of three different neural networks, feedforward, Elman and the radial basis neural network. The performance and stability of each DNN is evaluated by means of an extensive simulation study using actual hourly load data. The neural networks weights are dynamically adapted. Stability for each of the three different networks is determined through Eigen values analysis. Evaluation of the neural network methods is done in terms of estimation performance, stability and the difficulty in training a particular network. The results show that the radial basis method performs better than the rest Eigen value analysis also shows that it is more reliable as it remains stable as the input varies. © 2011 Springer-Verlag.
Mithun P.S.,SJCIT |
International Journal of Applied Engineering Research | Year: 2011
The aluminum based composite material with aluminum as base alloy (AA 443.0) and silicon carbide and magnesium oxide as reinforcement materials was made by stir casting. Three different weight percent (2.5, 5.0 & 7.5) of reinforcement materials were added to the base alloy. The specimens were prepared as per ASTM standards and tested. The ultimate tensile strength, yield strength, young's modulus and hardness of the composite material were at higher rate and the percent elongation and specific wear rate were low when the specimens made of 7.5 weight percent reinforcement materials than with 5.0 and 2.50 weight percent reinforcement materials added to the base alloy. The specific wear rate of the aluminum based composite material was high at higher load (60N) than at lower loads (40 N & 20 N). © Research India Publications.
Raghuveera G.R.,SJCIT |
IET Conference Publications | Year: 2013
While many protocols for sensor network security provide confidentiality for the content of messages, contextual information usually remains exposed. Such contextual information can be exploited by an adversary to derive sensitive information such as the locations of monitored objects and data sinks in the field. Attacks on these components can significantly undermine any network application. Existing techniques defend the leakage of location information from a limited adversary who can only observe network traffic in a small region. However, a stronger adversary, the global eavesdropper, is realistic and can defeat these existing techniques. This paper first formalizes the location privacy issues in sensor networks under this strong adversary model and computes a lower bound on the communication overhead needed for achieving a given level of location privacy. The paper then proposes two techniques to provide location privacy to monitored objects (source-location privacy)-periodic collection and source simulation-and two techniques to provide location privacy to data sinks (sink-location privacy)-sink simulation and backbone flooding. These techniques provide trade-offs between privacy, communication cost, and latency. Through analysis and simulation, we demonstrate that the proposed techniques are efficient and effective for source and sink-location privacy in sensor networks.
Geetha C.R.,Jain University |
2nd International Conference on Electronics and Communication Systems, ICECS 2015 | Year: 2015
Cryptography is a technique for secret communication where as obscuring the secret communication using for different data is Steganography. The secret communication is carried through many sources like image, audio & video files. Our work is mainly proposing data hiding by embedding the message of interest using geometric style of cryptographic algorithm, thus providing high security. Wavelet and curvelet transform algorithms are used to perform preprocessing of images. Even if the image carrying embedded data i.e., Stego image undergoes a reverse operation and data cannot be extracted if the receiver is unaware of the exact coordinates of the geometric shape. Hence retrieving secret image for an attacker becomes a hard task. Our Experimental results are verified for both the properties of Cryptography and Steganography it may be applicable for kind of multimedia applications. © 2015 IEEE.
Venkatesh A.S.V.,PESIT |
Apoorva B.M.R.,PESIT |
Concrete Solutions - Proceedings of Concrete Solutions, 5th International Conference on Concrete Repair | Year: 2014
Many existing Reinforced Concrete (RC) buildings need retrofit to overcome deficiencies to resist seismic loads. The use of steel bracing systems for strengthening or retrofitting seismically inadequate reinforced concrete frames is a viable solution for enhancing earthquake resistance. The present study is concerned with the structural response of a 4 × 4 bays, 15 storeys RC building on incorporating steel bracings externally or internally and masonry infill as diagonal strut at the center of the middle frame of the building up to 10 stories as Lateral Load Resisting System (LLRS). The models analyzed consist of one basic moment resisting RC frame (bare frame) with square column of size 900 × 900mm and others include the same bare frame, but provided with External Steel Bracing at the centre of the middle frame of the building, Internal steel bracing at the centre of the building and masonry infill at the centre frame of the building as LLRS. The detail investigations are carried out in zone V of seismic zones of India, considering primary loads (dead, live and seismic loads) and their combinations. The results obtained from the linear static analysis are thoroughly investigated for maximum values of joint displacements, support reactions, beam forces and truss forces. The results indicate better resistance to lateral loads in the presence of masonry infill provided at centre frame of the building up to 10 stories. © 2014 Taylor & Francis Group.