Showing papers by "Kongu Engineering College published in 2011"
TL;DR: The experimental results proved that the electrocoagulation is a suitable method for treating bleaching plant effluents for reuse.
177 citations
TL;DR: Through this work the hebbian algorithm on non-linear units is used for training FCMs for the autistic disorder prediction problem and the investigated approach serves as a guide in determining the prognosis and in planning the appropriate therapies to special children.
Abstract: The soft computing technique of fuzzy cognitive maps (FCM) for modeling and predicting autistic spectrum disorder has been proposed. The FCM models the behavior of a complex system and is used to develop new knowledge based system applications. FCM combines the robust properties of fuzzy logic and neural networks. To overwhelm the limitations and to improve the efficiency of FCM, a good learning method of unsupervised training could be applied. A decision system based on human knowledge and experience with a FCM trained using unsupervised non-linear hebbian learning algorithm is proposed here. Through this work the hebbian algorithm on non-linear units is used for training FCMs for the autistic disorder prediction problem. The investigated approach serves as a guide in determining the prognosis and in planning the appropriate therapies to special children.
100 citations
01 Nov 2011
TL;DR: From the simulation and experimental results presented, the designed fractional order controller works efficiently with improved performance comparing with the integer order controller.
Abstract: In this paper, Fractional Order Proportional Integral Derivative Controller (FOPID) is designed for liquid level control of a spherical tank which is modeled as a First Order Plus Dead Time (FOPDT) system about an operating point. The response of designed FOPID controller is compared with the traditional integer order PID (IOPID) controller in simulation and with IOPI controller on experimental setup. The PIλDμ controller is designed using minimization of Integral Square Error (ISE) method. This method offers a practical and systematic way of the controllers design for the considered class of FOPDT plant. From the simulation and experimental results presented, the designed fractional order controller works efficiently with improved performance comparing with the integer order controller.
48 citations
TL;DR: In this article, a guanidinium perchlorate crystal was grown from aqueous solution by low temperature solution growth technique and the cell parameter values were found out using X-ray diffraction analysis.
34 citations
TL;DR: In this article, an E20P10D70 was used as an additive to prevent separation of bioethanol from diesel, and the results showed that the brake thermal efficiency of the engine was almost equal to that of base diesel.
Abstract: In this study, ethyl ester of pungamia oil is added as an additive to prevent separation of bioethanol from diesel. Stability, fuel properties, performance, and emission characteristics of the blended fuels were investigated and compared with base diesel. The result of the tests shows that brake thermal efficiency of the engine was almost equal to that of base diesel. It was observed that the exhaust gas temperature and Carbon dioxide (CO2) emissions of the blends were lower than those of base diesel. The oxides of nitrogen (NOx) and smoke emissions were decreased upto 15% and 12% respectively with an increase of bioethanol upto 25% in the blends as compared with the base diesel. However, a slight increase in hydrocarbon (HC) and carbon monoxide (CO) emissions were observed. It can be concluded from the analysis of experimental results that the blend mixture E20P10D70 could be effectively used as a hybrid fuel in the existing compression ignition engine without any hardware modification.
33 citations
Abstract: This study deals with artificial neural network modeling to predict the performance and exhaust emissions of the diesel engine using hybrid fuel. A single cylinder, four-stroke diesel engine was fueled with hybrid fuel and operated at different load conditions to acquire data for training and testing the proposed artificial neural network model. About 70% of the acquired experimental data were used in the view of training while the other 30% was used for testing the proposed model. The artificial neural network model was developed on the basis of standard back propagation algorithm. The developed artificial neural network model predicts the performance and exhaust emissions of the diesel engine with a correlation coefficient of 0.975–0.999 and a low root mean square error. The present study reveals that the artificial neural network approach could be confidently used to predict the performance and emissions of the diesel engine accurately.
30 citations
TL;DR: The symmetric coefficient matrix is decomposed into two systems of equations by using Cholesky method and then a solution can be obtained.
Abstract: In this paper, we present a method to solve fully fuzzy linear systems with symmetric coefficient matrix The symmetric coefficient matrix is decomposed into two systems of equations by using Cholesky method and then a solution can be obtained Numerical examples are given to illustrate our method
26 citations
TL;DR: The results indicate that the proposed system supplements SNP diagnosis experts with more precise key decision support information, which assists health care organizations to systematically identify appropriate occupations that grounds high risk for the occurrence of SNP and so the curative practices can be executed effectively.
Abstract: This research provides an analytical tool, fuzzy decision support system (FDSS), to find the precedence of jeopardy in occupations spawning shoulder and neck pain (SNP), an important musculoskeletal disorder and the most ubiquitous pain complaint in an occupational environment. FDSS evaluates and prioritizes the relative importance of the imprecise, uncertain and vague nature of risk factors causing occupational SNP. The objective involves derivation of mechanical-, physical- and psychosocial-related risk categories using knowledge acquisition implemented by identifying the risk factors through literature analysis, conventional and concept mapping interviews with expert neurologists, orthopedists, psychologists and physiotherapists. Fuzzy analytic hierarchy process is applied as an evaluation tool to measure the significance of the risk factors in each occupation. The results indicate that the proposed system supplements SNP diagnosis experts with more precise key decision support information. This assists health care organizations to systematically identify appropriate occupations that grounds high risk for the occurrence of SNP and so the curative practices can be executed effectively.
23 citations
TL;DR: In this paper, the authors presented the standardization of nutrient concentration, pH and temperature required to decolorize the anerobically treated distillery spent wash using the fungus Cladosporium cladosporioides.
Abstract: This study presents the standardization of nutrient concentration, pH and temperature required to decolorize the anerobically treated distillery spent wash using the fungus Cladosporium cladosporioides. Experiments were carried out to measure the decolorization of distillery spent wash effluent and it was found to be effective in acidic environment. From the results it was observed that a maximum color reduction of 52.6 % and Chemichal Oxygen Demand. removal of 62.5 % were achieved. The optimum conditions required for the growth of the fungus was found to be 5 g/L of fructose, 3 g/L of peptone, 5 pH and 35 °C. It was also observed that during the process a maximum of 1.2 g of fungal growth was attained. Decolorizing ability of the fungus was confirmed using spectrophotometer and High Performance Liquid Chromatography analysis. Single factorial experimental design was used to optimize the parameters. Apart from decolorization it was observed that fungus also has the ability to degrade the spent wash efficiently. This investigation could be an approach towards control of environmental pollution and health hazards of people in and around the distillery unit.
21 citations
03 Jun 2011
TL;DR: This research work has analyzed the performance of two perturbative masking techniques namely data transformation technique and bit transformation technique which are used for protecting sensitive numeric data in the micro data table and shows that theData transformation technique has produced better results than bit transformation approach.
Abstract: Primary goal of data mining is determining new and precious facts and knowledge from the large databases. Privacy preserving data mining is one of the research areas in the field of data mining which deals with the side effects of the data mining techniques. The results of data mining techniques may produce complete or accurate data; it produces privacy issues regardless of their intended use. Most of the circumstances, the knowledge extracted from the data mining algorithm is highly confidential and it should be modified before giving it to the public. For restricting and protecting the confidential knowledge, first we have to modify the sensitive data items in a data set. Several masking techniques are used for protecting sensitive data items. In this research work, we have analyzed the performance of two perturbative masking techniques namely data transformation technique and bit transformation technique which are used for protecting sensitive numeric data in the micro data table. The experimental result shows that the data transformation technique has produced better results than bit transformation approach.
18 citations
Journal Article•
TL;DR: It is found that Spathadia campanulata dye can be successfully used for the dyeing of cotton to obtain a wide range of colours by using various combinations of mordants.
Abstract: The colour fastness properties of the colourant extracted from the flower of Spathodea campanulata on cotton have been studied using different combination (1:3,1:1 and 3:1) of various mordants, such as myrobolan:nickel sulphate, myrobolan: aluminium sulphate, myrobolan: potassium dichromate, myrobolan: ferrous sulphate and myrobolan:stannous chloride. The wash, rub, light and perspiration fastness of the dyed samples have been evaluated. It is found that Spathadia campanulata dye can be successfully used for the dyeing of cotton to obtain a wide range of colours by using various combinations of mordants. With regards to colour fastness, test samples exhibit excellent fastness to washing, and rubbing, except for pre-mordanting using myrobolan: potassium dichromate combination; and good to excellent fastness to perspiration in both acidic and alkaline media.
01 Mar 2011
TL;DR: This research develops a fuzzy knowledge-based decision support system (FKBDSS) that measures and predicts the degree of severity of the work-related risk associated with shoulder and neck pain (SNP) that is a prevalent pain complaint in an occupational environment.
Abstract: This research develops a fuzzy knowledge-based decision support system (FKBDSS) that measures and predicts the degree of severity of the work-related risk associated with shoulder and neck pain (SNP) that is a prevalent pain complaint in an occupational environment. Assessing the harshness of SNP is a dreary chore, since the risk factors are featured with imprecision, uncertainty and vagueness. Predicting SNP subjective risk level provides key decision support information to medical practitioners in diagnosis. The objective involves knowledge acquisition performed through literature analysis, traditional and concept mapping interviews with domain experts comprising neurologist, orthopaedist, psychologist and physiotherapist to identify risk factors that include mechanical, physical and psychosocial categories. The determination of ranking the relative factor importance has accomplished using analytic hierarchy processing (AHP) analysis. The linguistic variables that qualify risk levels are quantified using fuzzy set theory (FST) that provides linguistic and numeric value outputs to predict the hazard level of SNP.
TL;DR: Non-Dominated Ranked Genetic Algorithm NRGA is used in this paper for clustering, which has the capability of providing a better classification result than other techniques used for document clustering.
Abstract: The increase in the number of documents has aggravated the difficulty of classifying those documents according to specific needs. Clustering analysis in a distributed environment is a thrust area in artificial intelligence and data mining. Its fundamental task is to utilize characters to compute the degree of related corresponding relationship between objects and to accomplish automatic classification without earlier knowledge. Document clustering utilizes clustering technique to gather the documents of high resemblance collectively by computing the documents resemblance. Recent studies have shown that ontologies are useful in improving the performance of document clustering. Ontology is concerned with the conceptualization of a domain into an individual identifiable format and machine-readable format containing entities, attributes, relationships, and axioms. By analyzing types of techniques for document clustering, a better clustering technique depending on Genetic Algorithm GA is determined. Non-Dominated Ranked Genetic Algorithm NRGA is used in this paper for clustering, which has the capability of providing a better classification result. The experiment is conducted in 20 newsgroups data set for evaluating the proposed technique. The result shows that the proposed approach is very effective in clustering the documents in the distributed environment.
TL;DR: Improved Location aided Cluster based Routing Protocol (ILCRP) for GPS enabled MANETs has been evaluated for performance metrics such as end to end delay, control overhead, and packet delivery ratio and illustrates that ILCRP performs better compared to other protocols.
Abstract: Routing has been the main challenge for ad hoc networks due to dynamic topology as well as resource constraints. Completely GPS(Global Positioning System) free as well as GPS scarce positioning systems for wireless, mobile, ad-hoc networks has been proposed recently by many authors. High computational overhead and high mobility of the nodes typically require completely GPS enabled MANETs for higher performance. In this article, Improved Location aided Cluster based Routing Protocol (ILCRP) for GPS enabled MANETs has been evaluated for performance metrics such as end to end delay, control overhead, and packet delivery ratio. Use of cluster based routing as well as exact location information of the nodes in ILCRP reduces the control overhead resulting in higher packet delivery ratio. GPS utility in nodes reduces the end to end delay even during its high mobility. Simulations are performed using NS2 by varying the mobility (speed) of nodes as well as number of the nodes. The results illustrate that ILCRP performs better compared to other protocols.
01 Nov 2011
TL;DR: From the simulation and experimental results presented, it is observed that the designed fractional order controller works efficiently, with improved performance comparing with the integer order controller.
Abstract: In this paper, Fractional Order Proportional Integral (FOPI) controller is designed for a liquid level control in a spherical tank which is modeled as a Fractional Order System (FOS). The performance of FOPI controller is compared with the traditional Integer Order PID (IOPID) controller designed for the same spherical tank which is modeled as a First Order Plus Dead Time (FOPDT) system in simulation and with the Integer Order PI (IOPI) controller in experimental setup. The FOPI controller is designed following a set of imposed tuning constraints, which can guarantee the desired control performance and the robustness to the loop gain variations. This design scheme offers a practical and systematic way of the controllers design for the considered class of fractional order plant. The integer order controller is tuned based on Ziegler-Nichols (ZN) tuning method. From the simulation and experimental results presented, it is observed that the designed fractional order controller works efficiently, with improved performance comparing with the integer order controller.
TL;DR: In this paper, the authors presented the results of the past three years productivity data and discussed different results obtained after implementing the procedures of total productive maintenance (TPM) in the failure textile industry.
Abstract: This paper provides an overview of the various processes in textile fabric industry. From the analysis of data taken during the past three years, the company has noted that it has not achieved the targeted productivity. Total productive maintenance (TPM) has been a major component of improvement strategy to enhance the organisational productivity and profitability. Identification of resources and use resources play a critical role in any industry for the improvement of quality and productivity. For example, fabric industry could not get the determined productivity since TPM was not followed. The objective of this paper is to present the result of the past three years productivity data and discussed different results obtained after implementing the procedures of TPM in the failure textile industry. A systematic methodology is presented and analysed by software for improvement productivity at the factory level. Metrics of overall equipment effectiveness (OEE) is introduced and developed a structured robust framework for improvement of quality and productivity.
TL;DR: The simulation analysis shows that, delivery ratio of MMFGW improves from 35% to 50% with optimal latency and overhead ratio, and this paper investigates the results of simulations, by comparing the performance of the protocols which uses message ferries proposed previously with epidemic routing protocol.
Abstract: Most ad hoc network routing algorithms are designed primarily for networks that are always connected. While it is certainly desirable to maintain a connected network, various conditions may cause a mobile ad hoc network to become partitioned. If the partitions last for a long duration of time, then it is not possible to deliver a packet from source to destination. To deliver messages in a partitioned network, new routing approaches were proposed for delivering data using message ferries and/or gateways. This paper analyzes various parameters of the routing scheme called Routing with Multiple Message Ferries and Gateways (MMFGW) which eliminates online collaboration between all the communication entities in the network. This paper also investigates the results of simulations, by comparing the performance of our protocols which uses message ferries proposed previously with epidemic routing protocol. The simulation analysis shows that, delivery ratio of MMFGW improves from 35% to 50% with optimal latency and overhead ratio.
TL;DR: In this article, an attempt was made to utilize the waste materials by effectively recycling and filling in steel tubular circular columns with recycled aggregate concrete instead of conventional concrete, and an empirical equation for calculating the design load carrying capacity of the composite column was developed using the experimental results.
Abstract: The climate change due to global warming is one of the greatest environmental issues we face now. The green house gases including CO2 are released during cement and steel manufacturing process. In order to reduce the amount of green house gases, an attempt has been made to reuse the waste materials along with concrete in construction industries. In recent years, attempts have been made to increase the utilization of fly ash, quarry dust, granite and construction and demolition debris to partially replace the use of fine aggregate and coarse aggregate in concrete are gathering momentum. This paper presents information on fly ash, granite and quarry dust based concrete, material and the mixture proportions, the manufacturing process, and the influence of various parameters on the properties of fresh and hardened concrete with plain concrete and partial replacement of fine aggregate by flyash and quarry dust and coarse aggregate by granite and C & D debris concrete. The column specimens were tested under axial compression to investigate the effects of waste materials. Since the materials used were locally available waste materials, a detailed characterization was planned. In this paper, an attempt was made to utilize the waste materials by effectively recycling and filling in steel tubular circular columns with recycled aggregate concrete instead of conventional concrete. An empirical equation for calculating the design load carrying capacity of the composite column was developed using the experimental results. The test results were compared with the international codes and new theoretical models were suggested for the design. In this paper, experimental and analytical investigations were carried out to study the strength and behaviour of CFST columns over the entire range of loading. The ultimate loads and behaviour of CFST were compared with those of the hollow steel tube columns. From these elaborative experimental and analytical investigations that were done, it is concluded that out of all the waste materials used, the contribution of C & D debris and quarry dust are significant. The remaining materials that include fly-ash and granite are reasonably contributed in the performance enhancement under axial loading conditions. Finally, it is concluded that materials recovered from various waste stream are suitable to be used as secondary aggregates in concrete. The advantage of using such waste materials provides generally a low cost construction than using virgin aggregates and the elimination of the need for waste disposal in landfills. Utilization of these waste materials in concrete leads to an effective solid waste management technique and will also be cost effective. The exploitation of available natural resources and raw materials required for the construction industries can also be reduced which in turn reduces the
20 Jul 2011
TL;DR: In this article, neutral point clamped inverter is combined with 12 sector methodology to restrict the torque and the flux errors, within torque and flux hysteresis bands, which results in production of ripples in the flux as well as torque.
Abstract: Direct Torque Control (DTC) is an advanced computation speed control method and is possibly the best among the techniques for variable frequency drive. Because it does not need axes transformation and voltage decoupling blocks. DTC provides direct selection of voltage vectors according to the error obtained and allows direct and independent control of flux linkage and electromagnetic torque by the selection of optimum inverter switching modes. Based on the estimates of flux position and instantaneous errors in torque and stator flux magnitude, a voltage vector is selected to restrict the torque and the flux errors, within the torque and flux hysteresis bands. In the conventional DTC the circular locus is divided into 6 sectors and a total of 8 voltage vectors are used. However, the discrete inverter switching vectors cannot always generate exact stator voltage required to obtain the demanded electromagnetic torque and stator flux linkages. This results in production of ripples in the flux as well as torque. In this proposed work, neutral point clamped inverter is combined with 12 sector methodology. At present, the researchers have used all the 27 voltage vectors available in the 12 sector methodology. But in this proposed work the new switching table is constructed by using only 12 voltage vectors which includes large, medium and zero voltage vectors. The usage of 12 voltage vector gives satisfactory performance as compared to usage of all the 27 voltage vectors. The performance of the proposed work is also compared with classical DTC and 12 sector methodology with 27 voltage vectors. The simulation is performed in MATLAB / SIMULINK environment.
TL;DR: The experiment results show that the proposed approach is efficient and outperforms the existing approach and the proposed system generates optimal summary by Genetic Algorithm-based sentence extraction strategy.
Abstract: Automatic document summarisation is the process of generating a summary of the original documents with the aim of shorter reading time. Sentence extraction is a widely adopted document summarisation technique by which relevant sentences are extracted from documents. The proposed system generates optimal summary by Genetic Algorithm-based sentence extraction strategy. Based on individual word weight and other sentence-specific features sentence score is calculated. To produce optimal summary fitness function is used. Machine-generated summaries are compared against human summaries using different measures. The experiment results show that the proposed approach is efficient and outperforms the existing approach.
23 Sep 2011
TL;DR: Three different neural network based classifiers are used: Feed Forward Neural Network, Radial Basis Neural Network and Elman Back Propagation Neural Network to determine their ability to classify various categories of human spermatozoa images.
Abstract: This paper aims to evaluate the accuracy of artificial neural network based classifiers using human spermatozoa images. Three different neural network based classifiers are used: Feed Forward Neural Network, Radial Basis Neural Network and Elman Back Propagation Neural Network. These three different classifiers were investigated to determine their ability to classify various categories of human spermatozoa images. The investigation was performed on the basis of the different feature vectors. The feature vector includes first order statistics (FOS), textural and morphological features. The extracted features are then used to train and test the artificial neural network. Experimental results are presented on a dataset of 91 images consisting of 71 abnormal images and 20 normal images. The radial basis network produced the highest classification accuracy of 60%, 75% and 70% when trained with FOS, Combined and Morphological features. When feed forward neural network is trained with GLCM features, a classification accuracy of 75% is achieved.
20 Jul 2011
TL;DR: A new method for the secured exchange between an E-passport or E-driving license and the Inspection System is provided and elliptic curve based on biometric data to validate the identity of the user was created.
Abstract: Many countries begin to issue E-driving license and E-passports containing biometric data for their citizens. The ICAO specification for cryptography in E-passport is proven to be insecure and has many threats. The European Union has EAC mechanism for E-passports. But, even this solution presents many threats especially in security and privacy. Biometric template recognition is the challenging problem in the real world application. In this paper, a new method for the secured exchange between an E-passport or E-driving license and the Inspection System is provided. The main objective of this proposed method is to create an elliptic curve points from finger print using MATLAB environment. First, Minutiae from finger prints are extracted. From those minutiae, elliptic curve is generated by using elliptic curve cryptography generation algorithm. Thus, elliptic curve based on biometric data to validate the identity of the user was created. This analysis confirms that our solution corresponds to the security goals defined in the paper.
TL;DR: In this article, single crystals of semi-organic nonlinear optical material, dibromo bis(triphenylphosphine oxide) cadmium(II) (CdBr 2 (TPPO) 2 ) were grown by low temperature solution growth method.
05 Jul 2011
TL;DR: A novel approach based on fuzzy and rough set theory is described in this work for the selection of effective routing paths using minimum number of resources and to remove irrelevant attributes for evaluating the best routing paths.
Abstract: Mobile Ad Hoc Network (MANET) is a collection of wireless mobile nodes that dynamically forms a network. Many routing protocols exist to find the shortest path using various resources. A novel approach based on fuzzy and rough set theory is described in this work for the selection of effective routing paths using minimum number of resources. This paper shows the rough set technique that can be employed to generate simple rules and to remove irrelevant attributes (resources) for evaluating the best routing paths. An example is also given to illustrate the efficiency of the proposed method.
03 Jun 2011
TL;DR: This system is developed using SCADA software, PLC programs for controlling the real-time process and VBA / front page scripts for management information system and the system will be more secured with the use of XML encoding.
Abstract: In general the idea of remote monitoring of various equipments and devices over the Internet is becoming a desirable practice in the process plants industries over the few decades. Over the years, there has been constant increase in the development of industrial automation through remote monitoring and diagnosis virtually through computers and Internet. The strong emphasize on the automatic XML report generation for the real-time process in both online and offline mode is the main focus of this system. The Internet based automation is made possible by the use of PLCs (Programmable Logic Controllers), SCADA (Supervisory control and Data Acquisition), VPN (Virtual Private Networks) and other network elements. The system is developed using SCADA software, PLC programs for controlling the real-time process and VBA / front page scripts for management information system. As a result the system will be more secured with the use of XML encoding and the data is protected by using only VPN via GSM for connection between the server and client and the individual monitoring device. The Reporting of the real-time data corresponding to the process plants can therefore be of great use for future analysis as well as for the Management level Information Systems.
24 Mar 2011
TL;DR: RST enables the discovery of data dependencies and the reduction of the number of attributes contained in a dataset using the data alone, requiring no additional information.
Abstract: Data reduction is an important step in knowledge discovery from data. The high dimensionality of databases can be reduced using suitable techniques, depending on the requirements of the data mining processes. In this work, Rough set theory (RST) has been used as such a tool with much success. RST enables the discovery of data dependencies and the reduction of the number of attributes contained in a dataset using the data alone, requiring no additional information. Analyses more frequently used RST-based traditional feature selection algorithms Quick Reduct Algorithm, Entropy based Reduct Algorithm, Relative Reduct Algorithm. The texture description method GLCM is used to extract Haralick features from mammogram images in different directions. A comparative study is performed and classification has been carried out.
Abstract: In this work, a PI-P control strategy based on the coefficient diagram method (CDM) is proposed. The proposed CDM–PI-P control strategy is tested with the pH neutralization system. The system is modeled as first order plus time delay (FOPTD) transfer function using the experimental step test method. Closed loop simulations are carried out at two different critical operating points and the servo performance of the CDM–PI-P controller in terms of integral square error (ISE), integral absolute error (IAE), total variation (TV), and time domain specifications are reported. The results of the proposed control strategy are compared with other conventional PI control techniques.
01 Dec 2011
TL;DR: In this article, an analog control technique applied to the Cascaded Multilevel Inverter in order to ensure an efficient voltage utilization and better harmonic spectrum is presented, which can considerably reduce the switching losses, thereby improving the conversion efficiency and also brings down the Total harmonic distortions.
Abstract: The paper presents an analog control technique applied to the Cascaded Multilevel Inverter in order to ensure an efficient voltage utilization and better harmonic spectrum. The method presented shows a Multiple Carrier Phase Opposition Disposition PWM topology to control the cascaded multilevel inverter that is implemented with multiple DC sources, which can also be obtained using a single DC source and transformers to get 2n+1 levels. The hardware implementation has been carried out using operational amplifiers on a scaled down prototype to prove the effectiveness of the proposed topology. This topology of firing can be implemented on the inverters used for the renewable energy sources where it can considerably reduce the switching losses, thereby improving the conversion efficiency and also brings down the Total harmonic distortions.
TL;DR: A method is proposed to extract ECG from noisy signals based on Singular Value Decomposition (SVD) and Genetic Algorithm and it is found that the signal to noise ratio improvement is nearly double when compared to neural network methods.
Abstract: Electrocardiogram (ECG) signal analysis is a technique to diagnose the cardiac diseases. But, the desired electrocardiogram signals are often corrupted by baseline interference, power line interference and electromyogram. Here, a method is proposed to extract ECG from noisy signals based on Singular Value Decomposition (SVD) and Genetic Algorithm. The advantage of this method compared to conventional methods like adaptive filtering, neural networks is that, it does not require any prior knowledge of the signals. It is found that the signal to noise ratio improvement is nearly double when compared to neural network methods.
20 Jul 2011
TL;DR: The new concept of Fuzzy Classification Algorithm (FCA) with the hybrid of ID3 and SVM is introduced and the improved fast classification algorithm considerably reduces the computational complexity and improves the speed of classification particularly in the circumstances of the large database.
Abstract: There are different algorithms used in classification and these algorithm mainly used for classifying the algorithm accurately and the concept of fast classification is lagging behind in the previous algorithms. In this paper we introduce the new concept of Fuzzy Classification Algorithm (FCA) with the hybrid of ID3 and SVM. To make this algorithm with fast and accurate classification we use entropy to reduce the attributes which does not give more information and with use of lower and upper approximation for accuracy classification. The result of experiments shows that the improved fast classification algorithm considerably reduces the computational complexity and improves the speed of classification particularly in the circumstances of the large database.