C:\moje zbiory\viola\Enformatica_Praga_2006\Praga_2006.dvi

نویسندگان

  • Reinhold Decker
  • Christian Holsing
  • Sascha Lerke
چکیده

This paper presents a new growing neural network for cluster analysis and market segmentation, which optimizes the size and structure of clusters by iteratively checking them for multivariate normality. We combine the recently published SGNN approach [8] with the basic principle underlying the Gaussian-means algorithm [13] and the Mardia test for multivariate normality [18, 19]. The new approach distinguishes from existing ones by its holistic design and its great autonomy regarding the clustering process as a whole. Its performance is demonstrated by means of synthetic 2D data and by real lifestyle survey data usable for market segmentation. Keywords—Artificial neural network, clustering, multivariate normality, market segmentation, self-organization

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Three molecular structures cause rhesus D category VI phenotypes with distinct immunohematologic features.

Rhesus D category VI (DVI) is the clinically most important partial D. DVI red blood cells were assumed to possess very low RhD antigen density and to be caused by two RHD-CE-D hybrid alleles. Because there was no population-based work-up, we screened three populations in central Europe for DVI. Twenty-six DVI samples were detected and examined by exon-specific RHD polymerase chain reaction wit...

متن کامل

Comparison Of Direct Visual Inspection (DVI) With Pap Smear In Diagnosis Of Precancerous Lesion Of Cervix

The aim of this study was to compare direct visual inspection (DVI) with Pap smear in diagnosis of precancerous lesion of cervix. A total of 1500 women were screened cytologically as well as clinically with direct visual inspection of cervix after application of acetic acid (DVI). A total of 1500 women were screened cytologically as well as clinically with direct visual inspection of cervix aft...

متن کامل

specials for PDF generation

DVIPDFM(x) manages various PDF effects by means of DVI specials. Appropriate documentation of DVI specials, however, is not easy to find, and exact functionality is not simple to catch without reading the source code of DVI drivers. This paper deals with the DVI specials defined in DVIPDFM(x) that are mainly used for PDF generation. We discuss the features of those specials with some examples, ...

متن کامل

Forensic odontology in the disaster victim identification process.

Disaster victim identification (DVI) is an intensive and demanding task involving specialists from various disciplines. The forensic dentist is one of the key persons who plays an important role in the DVI human identification process. In recent years, many disaster incidents have occurred that challenged the DVI team with various kinds of difficulties related to disaster management and unique ...

متن کامل

Hacking DVI files: Birth of DVIasm

This paper is devoted to the first step of developing a new DVI editing utility, called DVIasm. Editing DVI files consists of three parts: disassembling, editing, and assembling. DVIasm disassembles a DVI file to a human-readable text format (more flexible than DTL), and assembles the output back to a DVI file. DVIasm is useful for people who have a DVI file without TEX source, but need to modi...

متن کامل

Electrolyte Disturbance and Kidney Dysfunction in Dengue Viral Infection.

Dengue virus infection (DVI) is endemic in tropical countries in both children and adults. The classical presentation includes fever, hepatomegaly, thrombocytopenia-related bleeding disorders, and plasma leakage. Multi-organ involvement, including kidneys is found in complex cases. Asymptomatic electrolyte disturbances, abnormal urinalysis, and more severe manifestation such as acute kidney inj...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012