Putu Wira Buana

Combination of K-Nearest Neighbor and K-Means based on Term Re-weighting for Classify Indonesian News

KNN is one of the accepted classification tool, it used all training samples in the classification which cause to a high level of computation complexity.To resolve this problem, it is necessary to combine traditional KNN algorithm and K-Means cluster algorithm that is proposed in this paper.After completing the preprocessing step, the first thing to do is weighting the word (term) by usingTerm Frequency-Inverse Document Frequency (TF-IDF). TF-IDF weightedthe words calculating the number of words that appear in a document. Second, grouping all the training samples of each category of K-means algorithm, and take all the cluster centers as the new training sample. Third, the modified training samples are used for classification with KNN algorithm. Finally, calculate the accuracy of the evaluation using precision, recall and f-measure. The simulation results show that the combination of the proposed algorithm in this study has a percentage accuracy reached 87%, an average value of f-measure evaluation= 0.8029 with the best k-values= 5 and the computation takes 55 second for one document. General Terms Data Mining, Text Classification, Clustering

Pembentukan Data Mart Menggunakan Metode Generalization

Technology today causing the data needs of an agency or company to process the data or analyze data quickly, dense and higher. Companies or institutions want the data analysis processcan save time as much as possible. The data warehouse is a data analysis technology that is useful to resolve the issue. The data warehouse is a repository of data that is useful to accommodate all the history data held by agencies or companies. Data marts are part kacil of the data warehouse. Data mart is focused on a single subject. This study uses a generalization method to perform the process of establishing a data mart. Generalization is a useful method to reduce or narrow the differences in the data based Subclass. Subclasswere integrated into a Superclass useful to collect some data from the Subclass. Subclassis the data that is more descriptive. Superclass is more general in nature of data. The result obtained is a collection of some Subclasspredetermined or selected later formed a Superclass useful to accommodate the resources of the Subclass.

Sistem Komunikasi Modul Sensor Jamak Berbasiskan Mikrokontroler Menggunakan Serial Rs-485 Mode Multi Processor Communication (Mpc)

Multi-sensor communication system uses RS-485 standard communication connecting each microcontroller-based data processing unit to form BUS topology network. The advantages of this communication system are: connectivity (easy to connecting devices on a network), scalability (flexibility to expand the network), more resistant to noise, andeasier maintenance. The System is built using Master-Slave communication approach model. This system need to filter every data packet on communication channel because every device that connect in this network can hear every data packet across this network. Multi Processor Communication (MPC) modelis applied to reduce processor’s burden in inspecting every data packet, so the processor that work in slave side only need to inspect the message for itself without inspecting every data packet across the communication chanel.