Interscience Research Network
Not a member yet
2523 research outputs found
Sort by
MFCC AND CMN BASED SPEAKER RECOGNITION IN NOISY ENVIRONMENT
Get PDFThe performance of automatic speaker recognition (ASR) system degrades drastically in the presence of noise and other distortions, especially when there is a noise level mismatch between the training and testing environments. This paper explores the problem of speaker recognition in noisy conditions, assuming that speech signals are corrupted by noise. A major problem of most speaker recognition systems is their unsatisfactory performance in noisy environments. In this experimental research, we have studied a combination of Mel Frequency Cepstral Coefficients (MFCC) for feature extraction and Cepstral Mean Normalization (CMN) techniques for speech enhancement. Our system uses a Gaussian Mixture Models (GMM) classifier and is implemented under MATLAB®7 programming environment. The process involves the use of speaker data for both training and testing. The data used for testing is matched up against a speaker model, which is trained with the training data using GMM modeling. Finally, experiments are carried out to test the new model for ASR given limited training data and with differing levels and types of realistic background noise. The results have demonstrated the robustness of the new system
A NEW REDUCED CLOCK POWER FLIP-FLOP FOR FUTURE SOC APPLICATIONS
Get PDFIn this paper a novel technique is proposed based on the comparison between Conventional Conditional Data Mapping Flip-flop and Clock Pair Shared D flip flop(CPSFF) here we are checking the working of CDMFF and the conventional D Flip-flop. Due to the immense growth in nanometer technology the SOC is became the future concept of the modern electronics the number of clock transistors are also considerably increased. In this paper we propose a new system which will considerably reduce the number of transistor which will lead to the reduction in clocking power which will improve the overall power consumption.Our proposed which is designed using Pass Transistor Logic (LCPTFF) Low Power Clocked Pass Transistor Flip-Flop system is showing much better output than all other designs as mentioned in the tabulation.The simulations are done using Microwind& DSCH analysis software tools and the result between all those types are listed below
LDPC ARCHITECTURE IMPLEMENTATION BY REDUCING THE MEMORY UTILIZATION
Get PDFAs the low density parity check codes has proved their accuracy in error correcting .considering the ldpc as reference the architecture of ldpc is studied .ldpc coding contains check nodes and variable nodes which has their memory elements respectively .so an efficient use of memory can decrease the computation time. Further the arrays of memory requirement has been decreased by making the memory global to all the nodes . ldpc is considered as a finite state machine in which each node is a state .An efficient memory utilization method has been proposed to decrease the memory utilization in the fpga
LANGUAGE INDEPENDENT ROBUST SKEW DETECTION AND CORRECTION TECHNIQUE FOR DOCUMENT IMAGES
Get PDFDocument image processing is an increasingly important technology essential in all optical character recognition (OCR) systems and for automation of various office documents. A document originally has zero-skew (tilt), but when a page is scanned or photo copied, skew may be introduced due to various factors and is practically unavoidable. Presence even a small amount of skew (0.50) will have detrimental effects on document analysis as it has a direct effect on the reliability and efficiency of segmentation, recognition and feature extraction stages. Therefore removal of skew is of paramount importance in the field of document analysis and OCR and is the first step to be accomplished. This paper presents a novel technique for skew detection and correction which is both language and content independent. The proposed technique is based on the maximum density of the foreground pixels and their orientation in the document image. Unlike other conventional algorithms which work only for machine printed textual documents scripted in English, this technique works well for all kinds of document images (machine printed, hand written, complex, noisy and simple). The technique presented here is tested with 150 different document image samples and is found to provide results with an accuracy of 0.1
VERY LARGE SCALE INTEGRATION TINY CHIP WITH NANOPOWER SENSOR APPLICATIONS
Get PDFSemiconductor devices have rapidly advanced over the past years increasing switching(on and off) speed and density of the device, causing an increase in power consumption and power dissipation; accordingly, the issues have been considered and improved . In CMOS 0.5μm process, the designed VLSI mirror-amplifier had power dissipation of 8.41 milliwatts. This technique is changed in this paper. The biasing is done in two steps proved to be correct procedure to improve overall power consumption. Source voltage was considered as 3V for the MOSIS process technology. Layout ,simulation and electrical characterization of the design were carried out by MENTOR GRAPHICS tool and CAD tools were used for the design Holding the scaling and process unchanged at 0.5μm as the previous design, the new VLSI design had power dissipation of 4.39 nanowatts in second step by reducing the dynamic loss. Multi-die chip placement is done for fabrication. More advanced 0.35um CMOS process is used for low threshold voltage and enhanced supply voltage range. This paper presents details of the key research works, results, completed chip layout and applications of the chip
Handwritten Script Recognition using DCT, Gabor Filter and Wavelet Features at Line Level
Get PDFIn a country like India where more number of scripts are in use, automatic identification of printed and handwritten script facilitates many important applications including sorting of document images and searching online archives of document images. In this paper, a multiple feature based approach is presented to identify the script type of the collection of handwritten documents. Eight popular Indian scripts are considered here. Features are extracted using Gabor filters, Discrete Cosine Transform, and Wavelets of Daubechies family. Experiments are performed to test the recognition accuracy of the proposed system at line level for bilingual scripts and later extended to trilingual scripts. We have obtained 100% recognition accuracy for bi-scripts at line level. The classification is done using k-nearest neighbour classifier
Prediction of Protein Tertiary Structure using Genetic Algorithm
Get PDFProteins are essential for the biological processes in the human body. They can only perform their functions when they fold into their tertiary structure .Protein structure can be determined experimentally and computationally. Experimental methods are time consuming and high-priced and it is not always feasible to identify the protein structure experimentally. In order to predict the protein structure using computational methods, the problem is formulated as an optimization problem and the goal is to find the lowest free energy conformation. In this paper, Genetic Algorithm (GA) based optimization is used. This algorithm is adapted to search the protein conformational search space to find the lowest free energy conformation. Interestingly, the algorithm was able to find the lowest free energy conformation for a test protein (i.e. Met enkephalin) using ECEPP force fields
Road Tracking from High resolution IRS And IKONOS Images Using Unscented Kalman Filtering
Get PDFA typical way to update map is to compare recent satellite images with existing map data, detect new roads and add them as cartographic entities to the road layer. At present image processing and pattern recognition are not robust enough to automate the image interpretation system feasible. For this reason we have to develop an image interpretation system that rely on human guidance. More importantly road maps require final checking by a human due to the legal implementations of error. Our proposed technique is applied to IRS and IKONOS images using Unscented Kalman Filter(UKF) . UKF is used for tracing the median axis of the single road segment. The Extended Kalman Filter (EKF) is probably the most widely used estimation algorithm for road tracking. However, more than 35 years of experience in the estimation community has shown that is difficult to implement and is difficult to tune. To overcome this limitation,UKF is introduced in road tracking which is more accurate, easier to implement, and uses the same order of calculations as linearization. The principles and algorithm of EKF and UKF were also discussed. The core of our system is based on profile matching.UKF traces the roadbeyond obstacles and tries to find the continuation of the road finding all road branches initializing at the road junction.The completeness and correctness of road tracking from the IRS and IKONOS images were also compared
Expert System for Diseases Occur due to Diabetes
Get PDFThis paper explains expert system which will be able to fully diagnoses and treat the diseases caused by diabetes. For example Pancreas, Thyroid and Parathyroid glands are some diseases caused by diabetes. Furthermore, the expert system will give first aids in emergency cases caused by diabetes. Since, diabetes diseases are widely spreads in the India; we chose it to be the primary target from the diabetes diseases. Our expert system is not meant to replace the human physician but using such system may be useful in cases like overcoming the problems of the shortage in human physicians and accuracy and speed in processing facts. This system can be used to help the physician in their work
FALSE MISBEHAVIOUR ELIMINATION IN WATCHDOG MONITORING SYSTEM USING CHANGE POINT IN A WIRELESS SENSOR NETWORK
Get PDFWireless Sensor Networks are to be widely deployed in the near future for data monitoring in commercial, industrial and military applications. Though much research has focused on making these networks feasible and useful security has received very little attention. Sensor networks are exposed to variety of attacks like eavesdropping, message tampering, selective forward, gray hole attack, and Wormhole and Sybil attacks. Watchdog is a kind of behaviour monitoring mechanism which is the base of many trust systems in Ad hoc and Wireless Sensor Network. Current watchdog mechanism only evaluates its next-hop’s behaviour and propagates the evaluation result to other nodes by broadcasting, which is neither energy efficient nor attack resilient. The fundamental problem of secure neighbour discovery is studied which is importunate in protecting the network from different forms of attacks. In this paper an improved watchdog monitoring mechanism is proposed by using the process of change point detection. By implementing this change point detection algorithm in watchdog mechanism, the limitations of the existing watchdog mechanism are overcome. From this the exact malicious node can be found out and the data will be routed through a secure path bypassing the malicious node. Finally to analyze the efficiency of this algorithm, the results obtained from the proposed algorithm and the existing algorithms are compared