In this paper, we propose using Spherical K-means algorithm as a preprocessing step to using Latent Semantic Indexing (LSI). LSI is a well known approach in Information Retrieval (IR). Spherical K-means is a fast clustering algorithm that puts similar documents together, thus forming K clusters. We propose using Spherical Kmeans to form the matrix of normalized concept vectors yields high reduc...

Mutual information (MI) based registration methods are susceptible to the variation of the intensity of the image. We present a multi-modality MRI-CT non-rigid registration method by combining Kmeans clustering technique with mutual information. This method makes use of K-means clustering to determine variant bin sizes in CT image. The resulting clustered (labeled) CT image is non-rigidly regis...

In this paper we investigate the clustering of web document collections using two variants of the popular kmeans clustering algorithm. The first variant is the global k-means method, which computes “good” initial cluster centers deterministically rather than relying on random initialization. The second variant allows for the use of graphs as fundamental representations of data items instead of ...

Data clustering has been applied in various fields like machine learning, data processing, wireless sensor network and pattern recognition. Association rule in data mining technique frequently plays a necessary role. Data mining has types of application areas like clustering in WSN, medical speciality and biological sequences. The disadvantages and advantages of K-means and PSO technique have b...

Clustering is one of the Data Mining tasks that can be used to cluster or group objects on the basis of their nearness to the central value. It has found many applications in the field of business, image processing, medical etc. K Means is one the method of clustering which is used widely because it is simple and efficient. The output of the K Means depends upon the chosen central values for cl...

This paper extends upon our previous work using i-vectors for speaker diarization. We examine the effectiveness of spectral clustering as an alternative to our previous approach using Kmeans clustering and adapt a previously-used heuristic to estimate the number of speakers. Additionally, we consider an iterative optimization scheme and experiment with its ability to improve both cluster assign...

In this paper we focus on image segmentation by proposing a new algorithm based on Haar wavelet decomposition and Kmeans algorithm. When Haar wavelet decomposition is applied to an image it gives an idea about high frequency components. If higher levels of decomposition are performed, different texture region information can be captured. The paper deals with the texture segmentation of an image...

This paper presents the Chinese word sense Induction system of Leshan Teachers’ College. The system participates in the Chinese word sense Induction of task 4 in Back offs organized by the Chinese Information Processing Society of China (CIPS) and SIGHAN. The system extracts neighbor words and their POSs centered in the target words and selected the best one of four cluster algorithms: Simple K...

The paper presents the possibility of 3-D reconstruction of the florid plaques obtained in Transmission ElectronMicroscopy. The TEM images registration process is quite different from Nuclear Magnetic Resonance and Computed Tomography on account to increasing amount of the image size and resolution together. The normalisation of image brightness and contrast, produced by differences in slices t...

ادغام داده‌ها بین حسگرهای مختلف می‌تواند موجب استخراج اطلاعات با دقت و کیفیت بالاتر گردد بهبود تشخیص تهدیدهای هسته‌ای را به همراه داشته باشد. در این تحقیق، ردیابی چشمه متحرک استفاده از تلفیق داده­های سیستم آشکارساز پرتوی دوربین نظارتی مورد مطالعه قرار گرفت است. بدین منظور الگوریتمی جهت ایجاد همبستگی تصاویر دریافتی توسط شمارش طراحی شده است تا مسیر حرکت جسمی که بیش­ترین ثبت آشکارسازی دارد عنوان ا...