Muthiah A.,PSR Engineering College |
Rajkumar R.,Mepco Schlenk Engineering College, Sivakasi
International Journal of Computer Aided Engineering and Technology | Year: 2017
Scheduling is an important tool for manufacturing and engineering, where it can have a major impact on the productivity of a process. In manufacturing, the purpose of scheduling is to minimise the production time and costs. Production scheduling aims to maximise the efficiency of the operation and reduce costs. The following approaches are used to solve the job shop problem. We keep all of our machines well-maintained to prevent any problems, but there is on way to completely prevent down-time. We can work to get our batch sizes as small as is reasonably possible while also reducing the setup time of each batch. This allows us to eliminate a sizable portion of each part waiting while the rest of the parts in the batch are being machined. In this paper, we propose the production scheduling problem solving using genetic and greedy algorithms with sequence dependant setup times considering the minimisation of the maximum completion time. Copyright © 2017 Inderscience Enterprises Ltd.
Soundar K.R.,PSR Engineering College |
Murugesan K.,Bharathiyar Institute of Engineering for Women
International Journal of Pattern Recognition and Artificial Intelligence | Year: 2011
Computer face recognition promises to be a powerful tool and is becoming important in our security-heightened world. Several research works on face recognition based on appearance, features like intensity, color, textures or shape have been done over the last decade. In those works, mostly the classification is achieved by finding the minimum distance or maximum variance among the training and testing feature set. This leads to the wrong classification when presenting the untrained image or unknown image, since the classification process locates at least one winning cluster having minimum distance or maximum variance among the existing clusters. But for the security related applications, these new facial image should be reported and necessary action has to be taken accordingly. In this paper, we propose the following two techniques for this purpose: (i) Use a threshold value calculated by finding the average of the minimum matching distances of the wrong classifications encountered during the training phase. (ii) Use the fact that the wrong classification increases the ratio of within-class distance and between-class distance. Experiments have been conducted using the ORL facial database and a fair comparison is made with the conventional feature spaces to show the efficiency of these techniques. © 2011 World Scientific Publishing Company.
Ruba Soundar K.,PSR Engineering College |
Murugesan K.,Bharathiyar Institute of Engineering for Women
IET Computer Vision | Year: 2010
Face recognition can significantly impact authentication, monitoring and indexing applications. Much research on face recognition using global and local information has been done earlier. By using global feature preservation techniques like principal component analysis (PCA) and linear discriminant analysis (LDA), the authors can effectively preserve only the Euclidean structure of face space that suffers lack of local features, but which may play a major role in some applications. On the other hand, the local feature preservation technique namely locality preserving projections (LPP) preserves local information and obtains a face subspace that best detects the essential face manifold structure; however, it also suffers loss in global features which may also be important in some of the applications. A new combined approach for recognising faces that integrates the advantages of the global feature extraction technique LDA and the local feature extraction technique LPP has been introduced here. Xiaofei He et al. in their work used PCA to extract similarity features from a given set of images followed by LPP. But in the proposed method, the authors use LDA (instead of PCA) to extract discriminating features that yields improved facial image recognition results. This has been verified by making a fair comparison with the existing methods. © 2010 The Institution of Engineering and Technology.
Siva S.,Thiagarajar College of Engineering |
Sudharsan S.,PSR Engineering College |
Sayee Kannan R.,Thiagarajar College of Engineering
RSC Advances | Year: 2015
Silver nanoparticles (AgNPs) were synthesized by a biological reduction method using Cyperus rotundus grass extract (CRGE) and were found to have a regular diameter of 1-100 nm. Polymer nanocomposites (PFR-AgNPs) were then prepared by encapsulating the green synthesized AgNPs within a phenol-formaldehyde resin (PFR) as a cross linking agent using a polycondensation method. The composites were then applied to the sorption of Co(ii) from aqueous solution in a batch adsorption system with an initial concentration of 30-150 mg L-1, a contact time of 10-50 min and a temperature of 303-333 K. The non-diffusible negatively charged sulfonic acid groups bound to the PFR template should significantly develop the penetration and preconcentration of the goal metal cations from the aqueous solution to the interior plane of the polymeric matrix and also create favorable conditions for Co(ii) removal by the AgNP particles. Then, column adsorption studies were carried out for the Co(ii) retention in the presence of alkali and alkaline earth metals (Na+, Ca2+ and Mg2+). Compared to PFR, PFR-AgNPs demonstrated extremely penetrative cobalt removal from wastewater in the presence of competing Ca2+, Mg2+, and Na+ ions, which were present in larger amounts than the target heavy metal. Pseudo-first order reaction, pseudo-second order reaction and Weber-Morris intraparticle diffusion models were used to analyze the data. The adsorption equilibrium data was explored by the Freundlich and Langmuir adsorption isotherm models and the reaction was found to show a good relationship with the Freundlich adsorption model. Free PFR-AgNPs and Co2+ loaded PFR-AgNPs were characterized using FT-IR spectroscopy, scanning electron microscopy (SEM), energy-dispersive microanalysis, thermogravimetric analysis (TGA), and differential thermal analysis (DTA). The regenerant used for the regeneration of the cation-exchange resin was 5% (w/w) NaCl. The experimental results verified that the PFR-AgNP cation exchange resin can be applied effectively for the removal of Co(ii) from aqueous media. © The Royal Society of Chemistry. 2015.
Swaminathen A.N.,Sree Sakthi Engineering College |
Robert Ravi S.,PSR Engineering College
International Journal of Applied Engineering Research | Year: 2016
In recent years, the usage of Rice husk ash (RHA) and Metakaoilin (MK) as a pozzolonic material for the preparation of cement concrete had become more important than any other material. The manufacture of Portland cement (PC) is not eco friendly; the content of pozzolonic material in cement mortar exhibits a considerable increase in strength and durability properties. This paper gives a review about the use of RHA and MK as not only a partial replacement for cement but also a replacement for the influence of toxic waste. The collection of literature survey report elaborated that the usage of RHA and MK is an efficacious mineral admixtures, which cause a large betterment in the filling of pore structures. In addition to this it increases the resistance of the concrete to environmental effects, and gives better solutions for the abundant waste of RHA produced from Agricultural product in India. © Research India Publications.
Ruba Soundar K.,PSR Engineering College |
Murugesan K.,Salem College
International Journal of Pattern Recognition and Artificial Intelligence | Year: 2010
Face recognition technologies can significantly impact authentication, monitoring and image indexing applications. Much research has been done on face recognition using global and local features over the last decade. By using global feature preservation techniques like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), we can effectively preserve only the Euclidean structure of face space, that are devoid of the lack of local features which may play a major role in some applications. On the other hand, the local feature preservation technique namely Locality Preserving Projections (LPP) preserves local information and obtains a face subspace that best detects the essential face manifold structure; however, it also suffers loss in global features which could be important in some of the applications. In this work, a new combined approach for recognizing faces which preserve both global and local information has been introduced. The proposed technique generates Combined Global and Local Preserving Features (CGLPF) that integrates the advantages of the global feature extraction technique LDA and the local feature extraction technique LPP. He et al. in their work used PCA to extract similarity features from a given set of images in order to reduce the dimensions followed by LPP. But in our method, we use LDA (instead of PCA) to extract discriminating features to reduce the dimension that yields improved facial image recognition results. This has been verified by making a fair comparison of the above two methods by the use of ORL, UMIST and 600 images formed by combining both databases. © 2010 World Scientific Publishing Company.
Ramar C.,PSR Engineering College |
Rubasoundar K.,PSR Engineering College
International Journal of Mobile Network Design and Innovation | Year: 2015
Wireless sensor networks (WSNs) are self-organised, low cost and low power utilising network, which senses, calculates and communicates the data from the source to sink. The data collection at sensor nodes consumes more energy, but the sensor nodes have only limited energy. Hence, most of the data-aggregation techniques aim to prolong the lifetime of the network by minimising power consumption and optimised data transmission. In this paper, an extensive survey of various data aggregation techniques in WSN is performed by categorising the techniques as structured, structure-free, flat and hierarchical. These techniques are analysed in terms of energy conservation, network lifetime, packet delivery ratio, latency and various other parameters. A comparison of these data aggregation techniques is also presented along with their advantages and issues. © 2015 Inderscience Enterprises Ltd.
Bhuvaneswari R.,PSR Engineering College |
Bejoy B.J.,PSR Engineering College
Proceedings of National Conference on Innovations in Emerging Technology, NCOIET'11 | Year: 2011
Wireless sensor network is a special form of wireless networks dedicated to surveillance and monitoring applications. Reliability in wireless sensor network is application specific. That is the specific form of reliability might change from application to application. Our idea is to generate a reliability based transport protocol that is customizable to meet the needs of emerging reliable data applications in sensor networks and is also adaptive when the nodes are highly mobile. In our approach, clusters are formed for minimizing energy dissipation. Nodes maintain a neighbor list to forward data. If a node senses any topological change, it can trigger updates to its neighbor list and it can spontaneously re-send all of its data thus providing reliable transport even in mobility conditions. This approach has five phases namely-setup, relaying, relay initiated error recovery, selective status reporting and node supervising. Simulation results reveals that the proposed approach outperforms the existing related techniques and is highly responsive to the various errors and mobility conditions experienced in sensor networks. © 2011 IEEE.
Priya M.,Smart Electrotech |
Ranjith Kumar P.,PSR Engineering College
International Journal of Production Research | Year: 2015
Atherosclerosis is a condition in human circulatory, where the arteries become narrowed and hardened due to accumulation of plaque around artery wall. The growth of the disease is slow and asymptomatic. Currently, imaging methods are applied for predicting the disease progression; however, they are deficient in the required resolution and sensitivity for detection. In this work, clinical observations and habits of individuals are considered for assorting the pathologic community. Intelligent machine learning technique, decision tree forest is used for assorting the individuals. A case study was made in this work regarding the atherosclerosis disease progression and crucial features were extracted. Optimised missing value imputation strategy, iterative principal component analysis for STULONG data-set and efficient feature subset selection method, hybrid fast correlation-based filter (FCBF) have been employed for extracting the relevant features and ignoring the redundant features. Further proceeding with the methodology, our work has outperformed with extreme overall accuracy of about 99.47% compared with other state-of-the-art machine learning techniques. © 2015 Taylor & Francis
Kumar P.R.,PSR Engineering College |
Priya M.,PSR Engineering College
Technology and Health Care | Year: 2014
OBJECTIVE: To build an effective model which assorts the individuals, whether they belong to the normal group, risk group and pathologic group regarding atherosclerosis in real time by doing necessary preprocessing techniques and to compare the performance with other state-of-the-art machine learning techniques.BACKGROUND: Coronary artery disease due to atherosclerosis is an epidemic in India. An estimated 1.3 million Indians died from this in 2000. The projected death from coronary artery disease by 2016 is 2.98 million.METHODS: In this work we have employed STULONG dataset. We have made a deep case study in selecting the attributes which contributes for higher accuracy in predicting the target. The selected attributes includes missing values. Initially our work includes imputation of missing values using Iterative Principal Component Analysis (IPCA). The second step includes selecting best features using Fast Correlation Based Filter (FCBF). Finally the classifier Multiclass Support Vector Machine (SVM) with kernel Radial Basis Function (RBF) is used for classification of atherosclerotic community.RESULTS: For the subjects belonging to the classes of normal, risk and pathologic, our methodology has outperformed with an accuracy of 99.85%, 99.80% and 99.46% respectively.CONCLUSION: The combined optimization methods such as Iterative Principal Component Analysis (IPCA) for missing value imputation, Multiclass SVM for classifying normal, risk and pathologic community in real time has performed with overall accuracy of about 98.97%. The essential pre-processing technique, Fast Correlation Based Filter (FCBF) was employed to further intensifying the target. © 2014-IOS Press and the authors.