Showing papers by "SDM College of Engineering and Technology published in 2016"
TL;DR: In this article, the performance of fiber-reinforced prepreg has been investigated in terms of in-plane mechanical properties, but has inadequate performance in the through thickness direction.
Abstract: Laminates of fibre-reinforced prepreg have excellent in-plane mechanical properties, but have inadequate performance in the through thickness direction. Here, we address this issue by application o...
18 citations
23 Mar 2016
TL;DR: This paper aims to build continuous speech recognition of regional language Kannada using phoneme modeling wherein each phoneme is represented by tristate Hidden Markov Model(HMM) with each state being represented by Gaussian Mixture Model (GMM).
Abstract: This paper aims to build continuous speech recognition of regional language Kannada using phoneme modeling wherein each phoneme is represented by tristate Hidden Markov Model(HMM) with each state being represented by Gaussian Mixture Model (GMM). The recordings were sampled at the rate of 16 kHz, blocked into overlapped frames of 25msec duration with 10 msec frame overlap using hamming window, converted into 39 dimensional Mel Frequency Cepstral Coefficients(MFCC), then modeled using continuous density HMM. Kannada language has 46 phonemes, out of which 12 phonemes represent vowels (swaragalu) and 34 phonemes represent consonants (vyanjanagalu). The recognition performance is tested for monophone modeling, word internal triphone modeling and tied state triphone modeling for different gaussian mixtures and results have been presented.
14 citations
01 Aug 2016
TL;DR: Evaluation of performance of three CBIR systems implemented using combined features colour, texture and shape as a prominent feature based on wavelet transform indicates that performance of CBIr systems using wavelet decomposition give better results than simplicity and FIRM, also wavelet decompposition with Local Binary Patterns (LBP) exhibit better retrieval efficiency compared to wave let decomposition using threshold and morphological operators.
Abstract: Digital era has produced large volume of images which created many challenges in computer science field to store, retrieve and manage images efficiently and effectively. Many techniques and algorithms have been proposed by different researcher to implement Content Based Image Retrieval (CBIR) systems. This paper discusses performance of different CBIR systems implemented using combined features colour, texture and shape as a prominent feature based on wavelet transform. Choice of the feature extraction technique used in image retrieval determines performance of CBIR systems. In this paper evaluation of performance of three CBIR systems based on wavelet decomposition using threshold, wavelet decomposition using morphology operators and wavelet decomposition using Local Binary Patterns (LBP) is done. Also the performance of these methods is compared with the existing methods SIMPLIcity and FIRM. Average precision is used to compare the performance of the implemented systems. Results indicate that performance of CBIR systems using wavelet decomposition give better results than simplicity and FIRM, also wavelet decomposition with Local Binary Patterns (LBP) exhibit better retrieval efficiency compared to wavelet decomposition using threshold and morphological operators. Theses CBIR systems have been tested on bench mark Wang's image database. Precision versus Recall graphs for each system shows the performance of respective systems.
11 citations
01 Mar 2016
TL;DR: A review on recent various approaches and challenges in hyper spectral images are presented and various approaches for classification related to hyperspectral data is made available.
Abstract: Hyper spectral imaging offers high spectral resolution and hence an improved in categorization of images, detection and identification is possible. In this study, a review on recent various approaches and challenges in hyper spectral images are presented. At first a brief glance towards the related work is made available followed by various approaches for classification related to hyperspectral data is made available. Finally outline the challenges connected to this area. In this paper particularly focused in the aspects of approaches and challenges in the hyperspectral image.
11 citations
TL;DR: Results presented prove robustness of the key point technique to accurately describe object shapes even in complex images and prove a better performance of proposed CBIR system.
Abstract: Content Based Image Retrieval CBIR is the process of retrieving visually similar images from huge datasets. Images are identified based on their content. Content identification using shape features is considered in this paper. Content identification using shapes is a challenging task considering multiple variations observed in images, complex backgrounds and vast categories of contents. This paper describes a shape descriptor based CBIR system. The content of an image is identified using a key point based shape descriptor. Template matching techniques are adopted to accurately describe object shapes. The object shape identified is described using histogram vectors. The use of SVM classifier for content recognition and image retrieval task is considered. Results presented prove robustness of the key point technique to accurately describe object shapes even in complex images. Performance of the proposed system is compared with existing state of art systems. Results obtained and described in the paper prove a better performance of proposed CBIR system.
11 citations
TL;DR: High speed background subtraction algorithm for moving object detection is proposed and it is observed that the proposed technique is better compared to existing method in terms of image quality and speed of operations.
10 citations
TL;DR: A framework of novel routing technique in order to jointly address the problem pertaining to routing overhead and energy drainage among the mobile nodes and shows significant reduction in routing overhead along with energy efficiency as compared to existing AODV and DSDV protocols.
10 citations
01 Sep 2016
TL;DR: In this article, the interlaminar fracture toughness of a unidirectional (UD) Glass epoxy composite laminates were subjected to Mode-I and Mode-II loadings.
Abstract: Laminates of fiber reinforced polymer composites are good in in-plane properties and inherently weak in through thickness direction. To address this through thickness properties, the inter-laminar fracture toughness (GIc and GIIc) of a unidirectional (UD) Glass epoxy composite laminates were subjected to Mode-I and Mode-II loadings. Experiments were conducted using Double cantilever beam (DCB) and End notch flexure (ENF) specimens with varying pre-crack lengths. Mode I energy release rate (GIc) were also evaluated with modified beam and modified compliance theories. The experimental results reveal that, GIc fracture toughness increases with increasing in pre-crack length, where as in GIIc the effect of increase in pre-crack length exhibits reduced fracture toughness.
10 citations
21 Jul 2016
TL;DR: This paper tries to critically review the present system technologies used in WSN for monitoring water challenges, and try to find out the research gaps.
Abstract: India is experiencing rapid urbanization at the cost of it is Environment. Hazards related to Air and Water, are leading contributors to humanitarian crisis and that result in disaster. To overcome this, a quick check on the crisis is required by frequently monitoring the water and air for quality. This paper survey's different Wireless Sensor Network (WSN) based Water Monitoring Systems that address the challenges pertaining to specific water threats like physical, biological, chemical or radioactive contaminations, that are caused due to industrial, Sewer or agricultural wastes that are dumped in the river or lake water. These systems will continuously monitor the water for any changes using parameters like pH, DO, Temp, TDS, TBD… etc, if there are any changes in any one of the parameters, it is reported to the data center for further investigation. There are also many other issues related to water monitoring like Deployment of sensors nodes, QOS parameters and Underwater Communication protocols which also need to be solved. This paper tries to critically review the present system technologies used in WSN for monitoring water challenges, and try to find out the research gaps.
9 citations
TL;DR: This research studies the performance evaluation of recognition method constructed in union with neuro fuzzy inference system employing PCA, ICA and SIFT, which is robust against considerable amount of noise.
Abstract: Face recognition has been widely used in much real-time application for biometric authentication. This paper is discussed with the implementation of multimodal face recognition with neuro-fuzzy fusion. We used principal component analysis, independent component analysis and scale invariant feature transform for feature extraction and result are fused with neuro fuzzy inference system to obtain the recognition ID. PCA is the statistical method for face recognition under the enormous subject of 'factor analysis'. This unsupervised method for a set of reference images represents faces as linear combination. The generalised expression independent component analysis can treat pixels as observations and images at random variables or vice versa. Another method considered is scale invariant feature transform that scales histogram orientation for dominant feature determination invariant to illumination, rotation and is robust against considerable amount of noise. This research studies the performance evaluation of recognition method constructed in union with neuro fuzzy inference system employing PCA, ICA and SIFT.
3 citations
29 Jul 2016
TL;DR: The recognition of Kannada language is presented by employing decision tree based clustering to build context dependent triphone HMMs and it is observed that, triphones which are clustered using universal list of articulatory questions performs well compared with manually created phonetic question list.
Abstract: This paper presents the recognition of Kannada language by employing decision tree based clustering to build context dependent triphone HMMs. Language-specific knowledge is required to generate phonetic questions required for clustering triphones. The success of clustering depends mainly on correctly identifying the parameters that are correlated and are grouped. By using phonetic table of the target language and universal list of articulatory questions, language specific articulatory question list is created which can then be used to cluster triphones. This method of triphone clustering requires least human intervention. Perplexity is also measured for the database of Kannada language and the database having lower perplexity is used for testing performance of the generated triphones. It is observed that, triphones which are clustered using universal list of articulatory questions performs well compared with manually created phonetic question list.
TL;DR: An efficient Finite State Machine FSM based reconfigurable architecture for fingerprint recognition using fusion scores with correlation matching technique for FVC2004 DB3 Database is proposed and performance parameters such as TSR Total Success Rate, FAR False Acceptance Rate, and FRR False Rejection Rate are computed.
Abstract: The fingerprint identification is an efficient biometric technique to authenticate human beings in real-time Big Data Analytics. In this paper, we propose an efficient Finite State Machine FSM based reconfigurable architecture for fingerprint recognition. The fingerprint image is resized, and Compound Linear Binary Pattern CLBP is applied on fingerprint, followed by histogram to obtain histogram CLBP features. Discrete Wavelet Transform DWT Level 2 features are obtained by the same methodology. The novel matching score of CLBP is computed using histogram CLBP features of test image and fingerprint images in the database. Similarly, the DWT matching score is computed using DWT features of test image and fingerprint images in the database. Further, the matching scores of CLBP and DWT are fused with arithmetic equation using improvement factor. The performance parameters such as TSR Total Success Rate, FAR False Acceptance Rate, and FRR False Rejection Rate are computed using fusion scores with correlation matching technique for FVC2004 DB3 Database. The proposed fusion based VLSI architecture is synthesized on Virtex xc5vlx30T-3 FPGA board using Finite State Machine resulting in optimized parameters.
01 Dec 2016
TL;DR: The methods for formation of beam are depicted which decreases the computational complexity of conventional LMS algorithm, and for the first time applied to smart antenna system by newly proposed signum algorithm.
Abstract: To provide effective communication among the mobile users, interference has to be reduced to maximum extent. Reducing the interference plays a major role in providing effective communication among mobile users. By using smart antennas we can increase the capacity and coverage area of wireless sensor networks. By increasing the capacity and coverage area it is possible to provide line of sight communication and continuous coverage of network for remote users. By using Adaptive Beam forming (ABF) algorithm we can direct the arrays beam in the desired direction at the same time nullifying the interference signal. This paper depicts the methods for formation of beam which decreases the computational complexity of conventional LMS algorithm, and for the first time applied to smart antenna system by newly proposed signum algorithm.
21 Jul 2016
TL;DR: This work, presents the effect of energy on delay and throughput with respect to different types of deployments like static and dynamic deployments in Wireless Sensor Networks.
Abstract: Wireless Sensor Networks are gaining more and more importance in present era. Recent Advances in WSN have extended the applicability of these to wide range of real time applications. In these applications, energy is one of the scarce resources. Hence, the main goal of any application using WSN is to spend less energy and extend the lifetime of the WSN. For any type of network communication, quality of service plays an important role. QoS can be either Application-Specific or Network-Specific. Network-specific QoS is measured with respect to different parameters like delay, bandwidth, and throughput. Deployment of nodes in WSN's are classified as static and dynamic deployments. The effect of energy on quality of service and deployment can be of importance with respect to extending the network lifetime. This work, presents the effect of energy on delay and throughput with respect to different types of deployments like static and dynamic.
TL;DR: In this paper, the seismic behaviors of the RC multistorey buildings with and without floating columns are considered and the analysis is carried out for the multi-storey buildings, using ETABS Software.
Abstract: In the present scenario, the buildings with floating columns are the typical features in the multi-storey construction. As the load path in the floating columns is not continuous, they are more vulnerable to the seismic activity. Sometimes, to meet the requirements these types of aspects cannot be avoided though these are not found to be of safe. Hence, an attempt is taken to study the behavior of the building during the seismic activity. In this study, the seismic behaviours of the RC multistorey buildings with and without floating column are considered. The analysis is carried out for the multi-storey buildings, Using ETABS Software.
01 Jan 2016
TL;DR: The convolutional and turbo codes being the most commonly used error control algorithms in wireless communication systems, the performances of the hard-decision Viterbi algorithm, soft output ViterBi algorithm, as well as MAP turbo decoders have been analysed for the random input bit stream in the AWGN channel with a code rate of 1/3 and 1/4.
Abstract: The successful accomplishment in any modern communication system lies in the reliable transmission of information from the transmitter to a receiver. Channel coding techniques provide a favourable platform to recover from errors at the receiver side. In this paper, the convolutional and turbo codes being the most commonly used error control algorithms in wireless communication systems, the performances of the hard-decision Viterbi algorithm, soft output Viterbi algorithm, as well as MAP turbo decoders have been analysed for the random input bit stream in the AWGN channel with a code rate of 1/3 and 1/4. The BER performance study is begun by varying the constraint lengths as well as generator polynomials for all the algorithms.
31 Oct 2016
18 Dec 2016
TL;DR: This paper uses nonlocal means (NLM) video denoising algorithm as to avoid motion estimation and compensation steps, and modify the weighing term of NLM filter to preserve the edges and fine structural details in the image sequences.
Abstract: In this paper feature-preserving denoising scheme for fluorescence video microscopy is presented. Fluorescence image sequences comprise of edges and fine structures with fast moving objects. Improving signal to noise ratio (SNR) while preserving structural details is a difficult task for these image sequences. Few existing denoising techniques result in over-smoothing these image sequences while others fail due to inappropriate implementation of motion estimation and compensation steps. In this paper we use nonlocal means (NLM) video denoising algorithm as to avoid motion estimation and compensation steps. The proposed shot boundary detection technique pre-processes the sequence systematically and accurately to form different shots with content-wise similar frames. To preserve the edges and fine structural details in the image sequences we modify the weighing term of NLM filter. Further, to accelerate the denoising process, separable non-local means filter is implemented for video sequences. We compare the results with existing fluorescence video de-noising techniques and show that the proposed method not only preserves the edges and small structural details more efficiently, also reduces the computational time. Efficacy of the proposed algorithm is evaluated quantitatively and qualitatively with PSNR and vision perception.
01 Sep 2016
TL;DR: A day's simulation has become great tool for designing of complex problems and to get the accurate results without actually building the model.
Abstract: Now a day's simulation has become great tool for designing of complex problems and to get the accurate results. Simulating something will give the appropriate result without actually building the model. LabVIEW software is used for the actuator simulation and to move the actuator on the path generated by this software. Defining of the path for the actuator is known as motion profile and it can be achieved by using the motion controllers. One of the prior control techniques used is a PID (proportional integral derivative) control and it is broadly utilized as a part of criticism control of mechanical procedures in early years and continued to be the main generally utilized controller in procedure controls till today.
Posted Content•
TL;DR: In this paper, the authors focused on the ability of online space, as a channel to serve as an interface between organization and consumer and aid the organization in achieving its CRM goals.
Abstract: This study revolves around eCRM practices in banking sector of North Karnataka and some of the opportunities which are not keenly adopted by the banks in this region. The researcher has widely utilized the exploratory study to gain insights of the opportunities and challenges of eCRM practices in banking industry. This study focuses on the ability of online space, as a channel to serve as an interface between organization and consumer and aid the organization in achieving its CRM goals. Lastly, the study reveals that there is wide opportunity to utilise the eCRM practices for a better competitive advantage.
TL;DR: A novel approach to access the medium using CSMA/CA (Carrier Sense Multiple Access with Collision Avoidance) protocols for SCADA system employed in power system operation and control and a Moore finite state Moore machine is designed and a VHDL model is developed.
Abstract: This paper discusses a novel approach toaccess the medium using CSMA/CA (Carrier Sense Multiple Access with Collision Avoidance) protocols for SCADA ( S upervisory C ontrol A nd D ata A cquisition) system employed in power systemoperation and control. This method offers superior performance over the existing practices of accessing medium using CSMA/CD protocols. The proposal makes use of binary countdown method with modifications. The requirements of SCADA system such as reliability and real time operation can be achieved by fast data transmission and prompt delivery. In this work, a program is written and the procedure is run to allocate the channel considering the priorities of the RTUs (Remote Terminal Units) and the type of data to be transmitted such as normal data for archival and event triggered data for operation control. The program uses generic statement and is applicable to a system having a MTU (Master Terminal Unit) and any number of RTUs. The results obtained by running the procedure show its novelty. Further, a Moore finite state Moore machine is designed and a VHDL model is developed
TL;DR: NoC is an approach to design the communication subsystem between IP cores in a System on Chip (SoC) that can span synchronous and asynchronous clock domains or use unclocked asynchronous logic.
Abstract: The aim of this paper is to give briefing of the concept of network-on-chip (NoC). NoC is an approach to design the communication subsystem between IP cores in a System on Chip (SoC). NoCs can span synchronous and asynchronous clock domains or use unclocked asynchronous logic. This NoC brings an effective improvement over conventional busses and cross bar switches. The power requirement of the SoC is high where as it can be reduced by the NoC architecture. NoC is an developing paper in the field of VLSI. Since the use of emerging NoC architecture in VLSI it reduces the size of the architecture due to the reduced amount of buses and transmission lines. .\" In a NoC system, modules such as processor cores, memories and specialized IP blocks exchange data using a network as a \"public transportation\" sub-system for the information traffic. The wires in the links of the NoC are shared by many signals
31 Mar 2016
TL;DR: In this article, an important step-stabilization process is performed as part of the oxidation process and the stabilization is performed by ranging temperatures between 200°C250°C.
Abstract: In Carbon Fibre (CF) production, generally Polyacrylonitrile (PAN) precursor issubjected to namely three process- polymerisation, carbonization, and heat treatment. Oxidationprocess is the first and foremost stage of the PAN fabrication, and subsequently it undergoescarbonization. Prior to carbonization, an important step-stabilization process is performed as part ofthe oxidation process. The stabilization is performed by ranging temperatures between 200°C250°C.The carbon fiber manufactured has the density of 1.75-1.76 g/cc and tensile strength of 3.5-3.8 Gpa.
01 Dec 2016
TL;DR: In this work, various performance analysis of SMIB and IEEE five bus systems by conventional methods are done using Mi-Power software, Simulink and PSAT tool of MATLAB software; and the results help to enhance the security and reliability of the power system.
Abstract: The increased power demand has led to lengthier, complex interconnections of power systems. Erection of new transmission lines is avoided due to environmental and economic reasons, hence increased power transfer in the existing system. To monitor and control of power system, continuous performance analysis is required; also FACTS devices helps in improving system performance. In this work, various performance analysis of SMIB and IEEE five bus systems by conventional methods are done using Mi-Power software, Simulink and PSAT tool of MATLAB software; and compared the results. A case study of the simulation is carried out with IEEE standard 5-bus system. The outcome of this work helps to enhance the security and reliability of the power system.
TL;DR: The purpose of this paper is to compare the basic methods Prewitt Edge Detector, Sobel edge detector and Robert edge detector with different structuring elements.
Abstract: Detecting text regions in natural scene images has become an important area due to its varies applications. Text Information Extraction (TIE) System involves detecting text regions in a given image, localizing it, extracting the text part and recognizing text using OCR. This work basically concentrates on the detection and extraction of text in natural scene images. In this work, the test image will be pre-processed using RGB to Gray conversion, binarization, Edge Detection method and Geometric based Noise removal method. The features from the pre-processed image are extracted. After detecting text regions, characters are extracted and finally displayed. The purpose of this paper is to compare the basic methods Prewitt Edge Detector, Sobel edge detector and Robert edge detector with different structuring elements.
TL;DR: The modified Booth Encoding circuit generates half the partial products in parallel and by extending sign bit of the operands and generating an additional partial product the SUMBE multiplier is obtained.
Abstract: This paper presents the design and implementation of Modified Booth encoding multiplier for both signed and unsigned 32 bit numbers multiplication. The already existed Modified Booth Encoding multiplier and the BaughWooley multiplier perform multiplication operation on signed numbers only. Whereas the array multiplier and Braun array multipliers perform multiplication operation on unsigned numbers only. Thus, the requirement of the modern computer system is a dedicated and very high speed unique multiplier unit for signed and unsigned numbers. Therefore, this paper presents the design and implementation of Booth multiplier. The modified Booth Encoder circuit generates half the partial products in parallel. By extending sign bit of the operands and generating an additional partial product the SUMBE multiplier is obtained. The Carry Save Adder (CSA) tree and the final Carry Look ahead (CLA) adder used to speed up the multiplier operation. Since signed and unsigned multiplication operation is performed by the same multiplier unit the required hardware and the chip area reduces and this in turn reduces power dissipation and cost of a system.