Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

EPDM/CIIR Blends : Effect of EPDM Grade on Mechanical Properties

Blends of chlorobutyl rubber (CIIR) with two grades of ethylene-propylene diene monomer rubber (EPDM) were prepared and the effect of blend ratio on the cure characteristics, hot air ageing resistance, steam ageing resistance, and mechanical properties were evaluated. The blend of CIIR with EPDM grade 301 T showed additive behavior and the blend with the other grade of EPDM (NDR 4640) showed synergistic behavior.

Physiological and Genetic Diversity Studies on Regeneration of Santalum Album L.

S. album L. is the source of highly priced and fragrant heartwood which on steam distillation yields on an average 57 per cent oil of high perfumery value. Global demand for sandalwood is about 5000-6000 tons/year and that of oil is 100 tons/year. Heartwood of sandal is estimated to fetch up to Rs. 3.7 million/ton and wood oil Rs.70,000-100,000/ kg in the international market. Sandal heartwood prices have increased from Rs. 365/ton in 1900 to Rs. 6.5 lakhs/ton in 1999-2000 and to Rs. 37 lakhs/ton in 2007. Substantial decline in sandalwood production has occurred from 3176 tons/year during 1960-‘ 65 to 1500 tons/year in 1997-98, and to 500 tons/year in 2007.Depletion of sandal resources is attributed to several factors, both natural and anthropogenic. Low seed setting, poor seed germination, seedling mortality, lack of haustorial connection with host plant roots, recurrent annual fires in natural sandal forests, lopping of trees for fodder, excessive grazing, hacking, encroachments, seedling diseases and spread of sandal spike disease are the major problems facing sandal. While these factors hinder sandal regeneration in forest areas, the situation is accelerated by human activities of chronic overexploitation and illicit felling.Deterioration of natural sandal populations due to illicit felling, encroachments and diseases has an adverse effect on genetic diversity of the species. The loss of genetic diversity has aggravated during recent years due to extensive logging, changing landuse patterns and poor natural regeneration. The consequent genetic erosion is of serious concern affecting tree improvement programme in sandal. Conservation as well as mass propagation are the two strategies to be given due importance. To initiate any conservation programme, precise knowledge of the factors influencing regeneration and survival of the species is essential. Hence, the present study was undertaken with the objective of investigating the autotrophic and parasitic phase of sandal seedlings growth, the effects of shade on morphology, chlorophyll concentration and chlorophyll fluorescence of sandal seedlings, genetic diversity in sandal seed stands using ISSR markers, and the diversity of fungal isolates causing sandal seedling wilt using RAPD markers. All these factors directly influence regeneration and survival of sandal seedlings in natural forests and plantations.

Development of optical fiber sensors for selected chemical and physical sensing applications

The objective of the preset work is to develop optical fiber sensors for various physical and chemical parameters. As a part of this we initially investigated trace analysis of silica, ammonia, iron and phosphate in water. For this purpose the author has implemented a dual wavelength probing scheme which has many advantages over conventional evanescent wave sensors. Dual wavelength probing makes the design more reliable and repeatable and this design makes the sensor employable for concentration, chemical content, adulteration level, monitoring and control in industries or any such needy environments. Use of low cost components makes the system cost effective and simple. The Dual wavelength probing scheme is employed for the trace analysis of silica, iron, phosphate, and ammonia in water. Such sensors can be employed for the steam and water quality analysers in power plants. Few samples from a power plant are collected and checked the performance of developed system for practical applications.

Evaluation of the Power Consumption of Routing Protocols for Wireless Sensor Networks

Sensor networks are one of the fastest growing areas in broad of a packet is in transit at any one time. In GBR, each node in the network can look at itsneighbors wireless ad hoc networking (? Eld. A sensor node, typically'hop count (depth) and use this to decide which node to forward contains signal-processing circuits, micro-controllers and a the packet on to. If the nodes' power level drops below a wireless transmitter/receiver antenna. Energy saving is one certain level it will increase the depth to discourage trafiE of the critical issue for sensor networks since most sensors are equipped with non-rechargeable batteries that have limitedlifetime. Routing schemes are used to transfer data collectedby sensor nodes to base stations. In the literature many routing protocols for wireless sensor networks are suggested. In this work, four routing protocols for wireless sensor networks viz Flooding, Gossiping, GBR and LEACH have been simulated using TinyOS and their power consumption is studied using PowerTOSSIM. A realization of these protocols has beencarried out using Mica2 Motes.

COMBINED FEATURE EXTRACTION TECHNIQUES AND NAIVE BAYES CLASSIFIER FOR SPEECH RECOGNITION

Speech processing and consequent recognition are important areas of Digital Signal Processing since speech allows people to communicate more natu-rally and efficiently. In this work, a speech recognition system is developed for re-cognizing digits in Malayalam. For recognizing speech, features are to be ex-tracted from speech and hence feature extraction method plays an important role in speech recognition. Here, front end processing for extracting the features is per-formed using two wavelet based methods namely Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Naive Bayes classifier is used for classification purpose. After classification using Naive Bayes classifier, DWT produced a recognition accuracy of 83.5% and WPD produced an accuracy of 80.7%. This paper is intended to devise a new feature extraction method which produces improvements in the recognition accuracy. So, a new method called Dis-crete Wavelet Packet Decomposition (DWPD) is introduced which utilizes the hy-brid features of both DWT and WPD. The performance of this new approach is evaluated and it produced an improved recognition accuracy of 86.2% along with Naive Bayes classifier.

Channel Adaptive MAC Protocol with Traffic-Aware Distributed Power Management in Wireless Sensor Networks-Some Performance Issues

In Wireless Sensor Networks (WSN), neglecting the effects of varying channel quality can lead to an unnecessary wastage of precious battery resources and in turn can result in the rapid depletion of sensor energy and the partitioning of the network. Fairness is a critical issue when accessing a shared wireless channel and fair scheduling must be employed to provide the proper flow of information in a WSN. In this paper, we develop a channel adaptive MAC protocol with a traffic-aware dynamic power management algorithm for efficient packet scheduling and queuing in a sensor network, with time varying characteristics of the wireless channel also taken into consideration. The proposed protocol calculates a combined weight value based on the channel state and link quality. Then transmission is allowed only for those nodes with weights greater than a minimum quality threshold and nodes attempting to access the wireless medium with a low weight will be allowed to transmit only when their weight becomes high. This results in many poor quality nodes being deprived of transmission for a considerable amount of time. To avoid the buffer overflow and to achieve fairness for the poor quality nodes, we design a Load prediction algorithm. We also design a traffic aware dynamic power management scheme to minimize the energy consumption by continuously turning off the radio interface of all the unnecessary nodes that are not included in the routing path. By Simulation results, we show that our proposed protocol achieves a higher throughput and fairness besides reducing the delay

A Comparative Study of Wavelet Based Feature Extraction Techniques in Recognizing Isolated Spoken Words

Speech is a natural mode of communication for people and speech recognition is an intensive area of research due to its versatile applications. This paper presents a comparative study of various feature extraction methods based on wavelets for recognizing isolated spoken words. Isolated words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. This work includes two speech recognition methods. First one is a hybrid approach with Discrete Wavelet Transforms and Artificial Neural Networks and the second method uses a combination of Wavelet Packet Decomposition and Artificial Neural Networks. Features are extracted by using Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Training, testing and pattern recognition are performed using Artificial Neural Networks (ANN). The proposed method is implemented for 50 speakers uttering 20 isolated words each. The experimental results obtained show the efficiency of these techniques in recognizing speech

Synthesis, Characterization and Catalytic Activity of Nanocrystalline Ceria Modified With Zirconia

The use of catalysts in chemical and refining processes has increased rapidly since 1945, when oil began to replace coal as the most important industrial raw material. Catalysis has a major impact on the quality of human life as well as economic development. The demand for catalysts is still increasing since catalysis is looked up as a solution to eliminate or replace polluting processes. Metal oxides represent one of the most important and widely employed classes of solid catalysts. Much effort has been spent in the preparation, characterization and application of metal oxides. Recently, great interest has been devoted to the cerium dioxide (CeO2) containing materials due to their broad range of applications in various fields, ranging from catalysis to ceramics, fuel cell technologies, gas sensors, solid state electrolytes, ceramic biomaterials, etc., in addition to the classical application of CeO2 as an additive in the so-called three way catalysts (TWC) for automotive exhaust treatment. Moreover, it can promote water gas shift and steam reforming reactions, favours catalytic activity at the interfacial metal-support sites. The solid solutions of ceria with Group IV transitional-metals deserve particular attention for their applicability in various technologically important catalytic processes. Mesoporous CeO2−ZrO2 solid solutions have been reported to be employed in various reactions which include CO oxidation, soot oxidation, water-gas shift reaction, and so on. Inspired by the unique and promising characteristics of ceria based mixed oxides and solid solutions for various applications, we have selected ceria-zirconia oxides for our studies. The focus of the work is the synthesis and investigation of the structural and catalytic properties of modified and pure ceria-zirconia mixed oxide.

Evaluation of the Power Consumption of Routing Protocols for Wireless Sensor Networks

Sensor networks are one of the fastest growing areas in broad of a packet is in transit at any one time. In GBR, each node in the network can look at itsneighbors wireless ad hoc networking (? Eld. A sensor node, typically'hop count (depth) and use this to decide which node to forward contains signal-processing circuits, micro-controllers and a the packet on to. If the nodes' power level drops below a wireless transmitter/receiver antenna. Energy saving is one certain level it will increase the depth to discourage trafiE of the critical issue forfor sensor networks since most sensors are equipped with non-rechargeable batteries that have limited lifetime.