Showing papers by "SDM College of Engineering and Technology published in 2012"

Comparison of DTW and HMM for isolated word recognition

Abstract: This study proposes limited vocabulary isolated word recognition using Linear Predictive Coding(LPC) and Mel Frequency Cepstral Coefficients(MFCC) for feature extraction, Dynamic Time Warping(DTW) and discrete Hidden Markov Model (HMM) for recognition and their comparisons. Feature extraction is carried over the speech frame of 300 samples with 100 samples overlap at 8 KHz sampling rate of the input speech. MFCC analysis provides better recognition rate than LPC as it operates on a logarithmic scale which resembles human auditory system whereas LPC has uniform resolution over the frequency plane. This is followed by pattern recognition. Since the voice signal tends to have different temporal rate, DTW is one of the methods that provide non-linear alignment between two voice signals. Another method called HMM that statistically models the words is also presented. Experimentally it is observed that recognition accuracy is better for HMM compared with DTW. The database used is TI-46 isolated word corpus zero-nine from Linguist Data Consortium.

Ion Exchange Membranes: Preparation, Properties, and Applications

Abstract: Membrane science is a relatively new area of applied chemistry and chemical engineering and plays a vital role in the field of alternative energy and separation applications. The field of membrane science is therefore an emerging area with enormous industrial and public health significance. Today, various kinds of separation membranes have been studied and utilized industrially in different processes including reverse osmosis, nanofiltration, ultrafiltration, microfiltration, electrodialysis, and pervaporation. Technical feasibility of all these processes largely depends on membrane and its properties. Among the separation membranes, ion exchange membranes are one of the advanced separation membranes. Therefore, this chapter addresses on different types of ion exchange membranes with reference to their preparation, properties, as well as their industrial applications. Although ion exchange membranes are broadly classified into homogeneous and heterogeneous membranes, this chapter also covers other types of ion exchange membranes such as amphoteric, mosaic, bipolar, interpolymer, and graft and block copolymer membranes. At the end, prospectives and conclusions on the ion exchange membranes have also been highlighted. The relevant literature was collected from different sources including Google sites, books, reviews, and research articles.

Design and Implementation of User Context aware Recommendation Engine for Mobile using Bayesian Network, Fuzzy Logic and Rule Base

Abstract: Purpose – The purpose of this paper is to propose an intelligent service recommendation model. The paper formulates the service adaptation process by using artificial intelligence techniques like Bayesian Network, fuzzy logic and rule based reasoning.Design/methodology/approach – The authors formulate the service adaptation process by using artificial intelligence techniques like Bayesian Network, fuzzy logic and rule based reasoning. Bayesian Network is used to classify the incoming call (high priority call, low priority call and unknown calls), fuzzy linguistic variables and membership degrees to define the context situations, the rules for adopting the policies of implementing a service, fitness degree computation and service recommendation. In addition to this the paper proposes maximum to minimum priority based context attributes matching algorithm for rule selection based on fitness degree of rules. The context aware mobile is tested for library and class room scenario to exemplify the proposed serv...

Development of Wireless Sensor Node to Monitor Poultry Farm

Abstract: In this paper we have proposed a Wireless Sensor Network (WSN) System and developed sensor node to monitor the Poultry farm and detect the highly pathogenic avian influenza virus in Chickens. WSN’s have tremendous potential and play a key role in such monitoring applications. The developed wireless sensor node monitors the body temperature and movement of the Chickens. Based on sudden variation in body temperature and slow movements of the Chicken, early detection of virus is possible. The proposed low cost WSN System was developed with the use of open source technology-ARDUINO (open electronics prototype and open source).

Design of adaptive question bank development and management system

Abstract: In the changing present competitive scenario, Intelligent development of question model is indispensible for intellectual growth of students and also to fulfill learning objectives of the course (Blooms Taxonomy). Although there are several computer based question paper generators but they typically use random selection from question bank. Also these databases (question bank) are not rich enough to avoid recalling (repetition of questions). Moreover, History is also not maintained for the previous question module generated. Such systems lack intelligency as they do not use concepts maps and are unable to provide quality questions with variations. In this paper, we are designing an adaptive question bank management system that is intelligently picking questions from rich database (question bank) and representing the question model according to the inputs or parameters provided by the question paper designer (QPD). This question bank uses concept map developed using graphical method that uses hierarchical knowledge of particular domain. The concept map integrated with question bank (question database) will ensure the question modeling process based on degree of certain criteria like Bloom's Taxonomy, difficulty level, marking scheme etc. The evaluation of generated question model will provide a feedback to check overall student's level of understanding and this will be an advantage for an organization for enhancing the growth of their students. In sum, our proposed system would be great aid for the organization in effective question modeling and its assessment.

Spit Dynamics along the Central West Coast of India: Implications for Coastal Zone Management

Abstract: HEGDE, V.S.; NAYAK, S.R.; SHALINI, G.; KRISHNAPRASAD, P.A.; RAJAWAT, A.S.; GIRISH, K.H., and TEJASWINI, B., 2012. Spit dynamics along the central west coast of India: Implications for coastal zone management. Spit growth is observed across many rivers of the central west coast of India. Studies on the seasonal dynamics of the spits of the central west coast of India on the basis of the multidate satellite images LISS III, landsat™ data, panchromatic camera (PAN) data etc. in a geographic information system (GIS) environment using ERDAS imagine 9.0 version followed by field-check and wave data analysis have been discussed in this paper. All types of spits such as paired spits, winglike spits, single spits, etc. are observed along the coast of Karnataka, central west coast of India. Spit growth is responsible not only for shifting of the river mouths, but also for rapid changes in estuarine morphology and in turn on the sedimentation process. It is observed that river mouths with a spit across them...

Application of Satellite Remote Sensing for Investigation of Suspended Sediment Dispersion Pattern in the Near Shore Region: A Case Study from the Central West Coast of India

Abstract: NAYAK, S.R.; HEGDE, V.S.; SHALINI, R.; RAJAWAT, A.S.; ALI, M.; VENKATESHWARLU, B., and RAMANA, I.V., 2012. Application of satellite remote sensing for investigation of suspended sediment dispersion pattern in the near shore region: A case study from the Central West Coast of India. Indian Remote Sensing -P4 (IRS P4) Ocean Color Monitor (OCM) data is used to understand seasonal variations in suspended sediment (SS) dispersal pattern in the near-shore waters of the Central West Coast of India. Four distinct patterns of sediment dispersion are observed. (1) During monsoon, plume-like sediment dispersion seaward is observed especially in the mouths of rivers. (2) As the monsoon progresses, there is northerly transport of sediments with anticlockwise pattern within the plumes. (3) During NE monsoon, sediment concentration is less and its transport is southward. (4) During premonsoon, SS concentration is high in the near-shore water and transport is landward. Sequential OCM data analyses indicated the ...

Context-Aware Information Processing in Visual Sensor Network

Abstract: A visual sensor network is one of the streams of sensor network in which an image from the sensor node is transmitted to the server to be processed further without human intervention. Object Recognition in specific applications such as agriculture, defense etc, requires only the object of importance to be captured and transmitted to the processing center. This can be done by training the visual sensor node using the multilayer feed-forward technique. In the proposed work, a fruit object recognition system has been developed using the multilayer feed-forward technique of the neural network by extracting features from the sample fruit images. The experimental results reveal average recognition rate of 94.23%.

FPGA implementation of CDMA trans-receiver

Abstract: Code division multiple access (CDMA) systems are being counted to provide the necessary infrastructure to implement future 3G systems. The CDMA is uniquely featured by its spread spectrum (a random) process employing a pseudo random noise (PN) sequence, thus it is called the spread spectrum multiple access (SSMA). The CDMA can eliminate the data transfer latency variations by sharing the data communication media among multiple users concurrently. In this proposed work, we simulate the functionality of CDMA system on Xilinx ISE platform. Here, we use Manchester encode/decode technique for encryption and decryption. The simulation results show the working of CDMA transmitter and receiver on Verilog platform. Implementation of proposed system is targeted on Virtex 5 FPGA.

Harnessing Maximum Power from Solar PV Panel for Water Pumping Application

Abstract: The problem of fast depleting fossil fuels is triggering exploration of alternate sources of electricity. Among such sources, Solar Photo Voltaic (PV) energy is gaining prominence due to its plentiful availability. Water pumping is an important application of solar PV power. However people are not opting for it in large numbers as the ‘cost per watt’ for solar pumping systems is high. The cost component can be reduced by harnessing more power per unit installed capacity of the solar panel. One method of realising this is by Maximum Power Point Tracking (MPPT) wherein a Power Electronic (PE) converter is used to match pump with the PV panel. Present paper deals with the MATLAB based simulation study of solar PV driven Permanent Magnet (PM) DC motor (brushed) Pump System. Two cases are considered: a) System without MPPT b) System with MPPT. It is shown that by varying duty cycle of the converter at different radiation levels, the pump speed and hence the useful mechanical output can be enhanced with MPPT. The simulation study reveals that the output power becomes the maximum when the motor voltage becomes the maximum. Hence it is proposed that the motor voltage can be used as a control parameter for varying the duty cycle of the converter in achieving maximum output.

Design and Implementation of Prototyping Simulator of Context-Aware Applications

Abstract: Although numerous context-aware applications have been developed and there have been technological advances for acquiring contextual information, it is still difficult to develop and prototype interesting context-aware applications. In this paper, we present a Graphic User Interface (GUI)-based prototyping simulator that allows end-users to visually design a wide variety of prototypes of context-aware applications, including those based on if-then rules, temporal-spatial relationships and environmental personalization. The prototyping simulator allows users to quickly prototype and test their applications without writing any code. The designed GUI is very simple and the user can create any situation based on the context by selecting the options provided in the user interface. The prototyping simulator is tested for designing a prototype of reading room, coffee shop, living room, classroom and meeting room. A series of conflict-resolving algorithms are embedded in the toolkit to resolve the conflict among users, devices and sensors. The conflict-resolving algorithms are designed using a hybrid of fuzzy logic, Bayesian probability and rough set theory.

Tools and Strategies for Product Life Cycle Management – A Case Study in Foundry

Abstract: Advances in information and communication technology (ICT) have opened new possibilities of collaborations among the customers, suppliers, manufactures and partners to effectively tackle various business challenges. Product Life Cycle Management (PLM) has been a proven approach for Original Equipment Manufacturers (OEMs) to increase their productivity, improve their product quality, speed up delivery, and increase their profit and to become more efficient. However, their Tier 2 and Tier 3 suppliers like foundry industries are still in their infancy without adopting PLM. Hence to enhance their understanding, the basic concepts, the tools and strategies for PLM are presented is this paper. By selecting and implementing appropriate PLM strategies in a small foundry, an attempt was also made to understand the immediate benefits of using PLM tools (commercial PLM software and digital manufacturing tools). This study indicated a reduction in lead time and improved utilization of organizational resources in the production of automobile impeller. These observations may be further extrapolated to other multi-product, multi-discipline and multi-customer companies to realize the advantages of using PLM technology.

A Novel Approach for Iris Encryption

Abstract: A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Iris recognition is one of such biometric systems and is regarded as the most reliable and accurate identification systems available. It is the process of recognizing a person by analyzing the random pattern of the iris [8]. It combines computer vision, pattern recognition, statistical inference, and optics. Its purpose is real-time, high confidence recognition of a person's identity by mathematical analysis of the random patterns that are visible within the iris of an eye[7][8]. The proposed system takes an image of the eye, detects the iris and extracts it. Then a binary image of the extracted iris is created in order to form an equivalent barcode. Similarly a test data is also processed into a barcode and is matched with the reference barcodes in the database [8]. Representation of iris as a barcode provides an efficient and encrypted way for storing the iris data and provides one more level of security. Thus, the system has its application in various areas like national border controls: the iris can be used as a living passport, cell phone and other wireless-device-based authentication, secure access to bank accounts at cash machines, premises access control, credit-card authentication, Internet security, Biometric-Key Cryptography, etc[10]. Following parameters are observed. i.e. ARAcceptance Ratio 58.90%. FRRFalse Rejection Ratio 41.10%.FAR-False Acceptance Ratio 33.34 %. RRRejection Ratio 66.66%. General Terms Encryption, Algorithms, Performance, Design, Experimentation, Security, Human Factors, Verification.

Restructuring procedures in construction industry to avoid disputes – a study through an arbitral award

Abstract: Conflicts have existed in all cultures, religions, and societies since time immemorial, as long as humans have walked the earth. Since conflicts are an integral part of human interaction, one must learn to manage them, to deal with them in a way that will prevent escalation and destruction, and come up with innovative and creative ideas to resolve them. Construction disputes, when not resolved in a timely manner, become very expensive – in terms of finances, personnel, time, and opportunity costs. There are many other ways of dealing with disputes. These options and possibilities create 'a menu' of Alternative or Appropriate Dispute Resolution (ADR) that parties may choose to use, with the intent of removing a potential source of conflict, preventing its escalation into a dispute, and finding the way back to a constructive cooperative and a potentially productive future working relationship. It is established beyond doubt that ADR mechanisms are the best options available especially after the enactment of Arbitration and Conciliation Act of 1996, with the role of judicial courts restricted to the barest minimum, yet the disputes by themselves could be avoided by restructuring procedures in the construction industry. This paper deals with restructuring and refining of construction procedures by studying an arbitral award. This award is taken as a typical case, as on most of occasions, it is observed that the contractor or the department would invoke the arbitration clause for remedy and further, the study of award would reveal that the dispute itself could have been avoided had all the procedures were in place.