The aim of emotion recognition is to establish grounds that work for different types of emotions.... more The aim of emotion recognition is to establish grounds that work for different types of emotions. However, majority of the classifiers have their base from balanced datasets. There are few works that attempts to address how to approach facial emotion recognition under imbalanced condition. This paper discusses the issues related to imbalanced data distribution problem and the common strategy to deal with imbalance datasets. We propose a model capable of handling imbalance emotion datasets well in which other typical classifiers failed to address. The model actively ranks the prototype (i.e. Prototype Ranking) of the facial expression image and adopted a derivation of support vector machines in its selection so that the problem of imbalanced data distribution can be relaxed. Then, we used an Emergent Self-Organizing Map (ESOM) to cluster the ranked features to provide clusters for unsupervised classification. This work progresses by examining the efficiency of the model in evaluating...
In this paper we target the motion vectors used to encode and reconstruct both the forward predic... more In this paper we target the motion vectors used to encode and reconstruct both the forward predictive (P)-frame and bidirectional (B)-frames in compressed video. The choice of candidate subset of these motion vectors are based on their associated macro block prediction error, which is different from the approaches based on the motion vector attributes such as the magnitude and phase angle, etc. A greedy adaptive threshold is searched for every frame to achieve robustness while maintaining a low prediction error level. The secret message bit stream is embedded in the least significant bit of both components of the candidate motion vectors. The method is implemented and tested for hiding data in natural sequences of multiple groups of pictures and the results are evaluated. The evaluation is based on two criteria: minimum distortion to the reconstructed video and minimum overhead on the compressed video size. Based on the aforementioned criteria, the proposed method is found to perfor...
International Journal for Research in Applied Science and Engineering Technology, 2018
The main purpose of this paper is to reduce the requirement of human resource by eliminating the ... more The main purpose of this paper is to reduce the requirement of human resource by eliminating the useless complications and simplifying the whole process to improve the output and making it more efficient. It involves the design and analysis in the horn division to the grouping of two processes in the assembly line and making it into a single machine which reduces man power and increasing production. The present setup which is located in the assembly line consists of a diaphragm and the tone disc that is assembly in the armature rod. The height measuring is done individually. To perform these operations two operators are necessary. Hence these two stages are united which reduces the requirement of human resource and the time of production. This paper is aimed to design a new fixture which would eliminate process analysis of the material and to increase the productivity. In this paper LVDT sensor is being implemented for the measurement of height instead of a dial gauge the normal pneumatic tighter is also replaced by a pneumatic torque gun where a pre-set torque value is given to the initial diaphragm tightening process and with the help of LVDT setup, where the height can be easily checked and dispatched to the next level of process. The height in between the armature rod and the diaphragm is an important factor that determines the frequency of the sound produced by the horn. When there is a variation in the desired frequency, then it means that desired height is varied. To measure the height in a effective and more accurate way LVDT is used.
International Journal of Research in Medical Sciences, 2015
According to Kibler et al., 11 core stability and strength is an important component to maximize ... more According to Kibler et al., 11 core stability and strength is an important component to maximize efficient balance ABSTRACT Background: The present study were undertaken to compare the static and dynamic postural stability among chronic low back pain and normal subjects. Most of the studies have been conducted on sports professionals. The present study focuses on recreationally active population, for which the activity levels are comparatively lesser. Methods: Thirty subjects (15 Chronic Low back Pain and 15 Normal subjects) were recruited randomly who's demographic are not varied. The static and dynamic postural stability test namely postural sway meter and Star excursion balance test were analyzed. Data were analyzed using test of homogeneity and Independent sample t test. Results: Descriptive statistics reflected homogeneity of the study population. Independent sample t-test was used to compare values for static and dynamic stability between chronic low back pain and Normal subjects. It showed a statistically significant (P<0.05) difference in posterior and left lateral direction with t-value of-2.720 and-1.601 respectively for static stability. On the other hand, dynamic postural stability (SEBT) showed significant difference in all direction except on right leg; anteromedial, anterolateral and right and left posterior direction. Conclusions: Chronic low back pain group showed reduction in static and dynamic postural stability as compared to normals'.
This paper delves into the problem of face recognition using color as an important cue in improvi... more This paper delves into the problem of face recognition using color as an important cue in improving recognition accuracy. To perform recognition of color images, we use the characteristics of a 3D color tensor to generate a subspace, which in turn can be used to recognize a new probe image. To test the accuracy of our methodology, we computed the recognition rate across two color face databases and also compared our results against a multi-class neural network model. We observe that the use of the color subspace improved recognition accuracy over the standard gray scale 2D-PCA approach [17] and the 2-layer feed forward neural network model with 15 hidden nodes. Additionally, due to the computational efficiency of this algorithm, the entire system can be deployed with a considerably short turn around time between the training and testing stages.
Software development life cycle involves requirement analysis, design, coding, testing and implem... more Software development life cycle involves requirement analysis, design, coding, testing and implementation. Software Quality is the most important one, since the success of a Software Engineer relies on the development of failure free software. One of the main quality factors is reliability. Reliability can improve through Software Reliability Models, analyze of reliability data, proper utilization of debuggers, internal quality factors and evaluating the measurement results. Currently, there are several software reliability allocation techniques, but schedule planning and effective resource use are unavailable because they do not support multi-objective optimization. It is an effective software reliability allocation technique that supports multi objective optimization. This approach assists schedule planning as well as effective resources allocation. This paper can aid to increase the effectiveness of resource uses and to establish schedule planning. It will lead to improve Software Reliability.
ABSTACT Present day power systems are being operated closer to their stability limits due to ever... more ABSTACT Present day power systems are being operated closer to their stability limits due to ever increasing load demand. In such a stressed condition, the system may enter into voltage instability problem and it has been found responsible for several line outages. At any point of time, a power system operating condition should be stable, meeting various operational criteria and it should also be secure in the event of any credible contingency. Insertion of FACTS devices is found to be highly effective in preventing voltage instability. A FACTS device in a power system improves the voltage stability, reduces the power loss and also improves the load ability of the system. Here SVC is used as a FACTS device and can be seen as a variable shunt reactance that adjusts automatically in response to changing system operative conditions. This paper proposes a Particle Swarm optimization (PSO) primarily based algorithmic program for the best location and setting of FACTS devices with cost ef...
In this paper, Assignment problem with crisp, fuzzy and intuitionistic fuzzy numbers as cost coef... more In this paper, Assignment problem with crisp, fuzzy and intuitionistic fuzzy numbers as cost coefficients is investigated. In conventional assignment problem, cost is always certain. This paper develops an approach to solve a mixed intuitionistic fuzzy assignment problem where cost is considered real, fuzzy and an intuitionistic fuzzy numbers. Ranking procedure of Annie Varghese and Sunny Kuriakose [4] is used to transform the mixed intuitionistic fuzzy assignment problem into a crisp one so that the conventional method may be applied to solve the assignment problem. The method is illustrated by a numerical example. The proposed method is very simple and easy to understand. Numerical examples show that an intuitionistic fuzzy ranking method offers an effective tool for handling an intuitionistic fuzzy assignment problem.
In recent days, Swarm Intelligence plays an important role in solving many real life optimization... more In recent days, Swarm Intelligence plays an important role in solving many real life optimization problems. Particle Swarm Optimization (PSO) is swarm intelligence based search and optimization algorithm which is used to solve global optimization problems. But due to lack of population diversity and premature convergence it is often trapped into local optima. We can increase diversity and prevent premature convergence by using some evolutionary operators in PSO. In this paper the blend crossover operator is used to increase the search ability of the swarm in the search space .Particle Swarm Optimization uses this crossover technique to converge optimum solution fast .Thus the blend crossover operator is combined with particle swarm optimization to enhance the performance and keep the diversity which guides the particles to the global optimum efficiently. In this paper a blended crossover based particle swarm optimization algorithm (BCPSO) has been proposed and the proposed algorithm...
International Journal of Contemporary Mathematical Sciences, 2013
In this paper, we investigate an optimal more-for-less solution of an intuitionistic fuzzy transp... more In this paper, we investigate an optimal more-for-less solution of an intuitionistic fuzzy transportation problems with mixed constraints in a single stage. An algorithm called intuitionistic fuzzy zero point method is used to find an optimalmore-for-less solution in terms of triangular intuitionistic fuzzy numbers.This method is very simple, easy to understand and apply. An optimal more-for-less solution procedure illustrated with the new relevant numerical example.
The present paper is an attempt through heuristic method to obtain the optimal sequence for n job... more The present paper is an attempt through heuristic method to obtain the optimal sequence for n jobs two stage open shop problem in which Set up time separated from processing times, each associated with respective probabilities.. The algorithm developed in this paper is very simple and easy to understand. A numerical illustration to clarify the algorithm is also given.
Proceedings of Irkutsk State Technical University, 2016
In this article, the crisp, fuzzy and intuitionistic fuzzy optimization problem is formulated. Th... more In this article, the crisp, fuzzy and intuitionistic fuzzy optimization problem is formulated. The basic definitions and notations related to optimization problems are given in the preliminaries section. Algorithms for solving the optimization problems using fuzzy and intuitionistic fuzzy set is presented in this article. Then, with the help of the proposed algorithm the optimal solution of the crisp, fuzzy and intuitionistic fuzzy optimization problems are determined. A new theorem related to type-2 fuzzy/type-2 intuitionistic fuzzy optimization problems is proposed and proved. Some new and concrete results related to type-2 fuzzy/type-2 intuitionistic fuzzy optimization problems are presented. To illustrate the proposed method, some real-life numerical examples are presented. The proposed article provides seven fully worked examples with screenshots of output summaries from the software used in the computations for better understanding. The advantages of the proposed approach as compared to other existing work are also specified. Detail analyses of the comparative study as well the discussion are given. To show the advantages of the proposed approach, superiority analysis is discussed. Comparison analysis and the advantages of the proposed operators are also discussed. Some managerial applications and the advantages of the proposed approach are given. Finally, conclusion and future research directions are also given. Keywords Fuzzy set Á Fuzzy number Á TFN Á TrFN Á Intuitionistic fuzzy set Á Intuitionistic fuzzy number Á TIFN Á TrIFN Á Type-2 FTP Á Type-2 IFTP Á Type-2 IFSTP Á FAP Á IFAP Á IFSAP Á Linear programming method Á Integer programming problem Á Optimal solution Á Optimal assignment Á PSK theorem Electronic supplementary material The online version of this article (
In this paper, we investigate an assignment problem in which cost coefficients are triangular int... more In this paper, we investigate an assignment problem in which cost coefficients are triangular intuitionistic fuzzy numbers. In conventional assignment problem, cost is always certain. This paper develops an approach to solve an intuitionistic fuzzy assignment problem where cost is not deterministic numbers but imprecise ones. Here, the elements of the costs (profits) matrix of the assignment problem are triangular intuitionistic fuzzy numbers. Then its triangular shaped membership and non-membership functions are defined. A new ranking procedure which can be found in [4] and is used to compare the intuitionistic fuzzy numbers so that an Intuitionistic Fuzzy Hungarian method may be applied to solve the intuitionistic fuzzy assignment problem. Numerical examples show that an intuitionistic fuzzy ranking method offers an effective tool for handling an intuitionistic fuzzy assignment problem.
The Transportation Problem in an Intuitionistic Fuzzy Environment
In this paper, we investigate transportation problem in which supplies and demands are intuitioni... more In this paper, we investigate transportation problem in which supplies and demands are intuitionistic fuzzy numbers. Intuitionistic Fuzzy Vogel’s Approximation Method is proposed to find an initial basic feasible solution. Intuitionistic Fuzzy Modified Distribution Method is proposed to find the optimal solution in terms of triangular intuitionistic fuzzy numbers. The solution procedure is illustrated with suitable numerical example.
Uploads
Papers by Senthil Kumar