Papers by Madhusmita Mishra
Since it was first proposed, it is amazing to notice how K-Means algorithm has survive over the y... more Since it was first proposed, it is amazing to notice how K-Means algorithm has survive over the years. It has been one among the well known algorithms for data clustering in the field of data mining. Day in and day out new algorithms are evolving for data clustering purposes but none can be as fast and accurate as the K-Means algorithm. But in spite of its huge speed, accuracy and simplicity K-Means has suffered from some of its own problem. Such as, the exact number of cluster is not known prior to clustering. The other thing that is causing problem is that it is quite sensitive to initial centroids. Not just that, K-Means fails to give optimum result when it comes to clustering high dimensional data set because its complexity tends to make things more complicated when more number of dimensions are added. In Data Mining this problem is known as “Curse of High Dimensionality”. Here in our paper we proposed a new Modified K-Means algorithm that will overcome the problem faced by the ...
Weighted Clustering Based Preemptive Scheduling For Real Time System
In this paper a new improved clustering based scheduling algorithm for a single processor environ... more In this paper a new improved clustering based scheduling algorithm for a single processor environment is proposed. In the proposed method, processes are organized into non-overlapping clusters. For each process the variance from the median, is calculated and compared with the variance from the means of other clusters. Each process is assigned to the cluster associated with the closest median. The new median of each cluster is calculated and the procedure is repeated until the medians are fixed. Weight is assigned to each cluster using the externally assigned priorities and the burst time. The cluster with highest weight is executed first and jobs are scheduled using the Round Robin algorithm with calculated dynamic time slice.. The experimental study of the proposed scheduling algorithm shows that the high priority jobs can be executed first to meet the deadlines and also prevents starvation of processes at the same time which is crucial in a real time system.
Nonparametric Estimation of Linear Multiplier for Fractional Diffusion Processes
Stochastic Analysis and Applications, 2011
We study the problem of nonparametric estimation of linear multiplier function θ(t) for processes... more We study the problem of nonparametric estimation of linear multiplier function θ(t) for processes satisfying stochastic differential equations of the type where is a standard fractional Brownian motion with known Hurst index H ∈ (1/2, 3/4) and study the asymptotic behaviour of the estimator as ε → 0.
Clustering is a widely used concept in data mining which finds interesting pattern hidden in the ... more Clustering is a widely used concept in data mining which finds interesting pattern hidden in the dataset that are previously unknown. K-means is the most efficient partitioning based clustering algorithm because it is easy to implement. However, due to rapid growth of datasets in practical life, the computational time, accuracy and efficiency decreases while performing data mining task. Hence an efficient dimensionality reduction technique should be used. Due to sensitiveness to initial partition k-means clustering can generate a local optimal solution. Particle Swarm Optimization (PSO) is a globalized search methodology but suffers from slow convergence near optimal solution. In this paper, a PSO optimized Hybridized K-Means is proposed to cluster high dimensional dataset. The proposed algorithm generates more accurate, robust and better clustering with reduced computational time.
Uploads
Papers by Madhusmita Mishra