scholarly journals KLASIFIKASI PENGGUNAAN PROTOKOL KOMUNIKASI PADA TRAFIK JARINGAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR

2016 ◽  
Vol 16 (1) ◽  
pp. 67
Author(s):  
Komang Kompyang Agus Subrata ◽  
I Made Oka Widyantara ◽  
Linawati Linawati

ABSTRACT—Network traffic internet is data communication in a network characterized by a set of statistical flow with the application of a structured pattern. Structured pattern in question is the information from the packet header data. Proper classification to an Internet traffic is very important to do, especially in terms of the design of the network architecture, network management and network security. The analysis of computer network traffic is one way to know the use of the computer network communication protocol, so it can be the basis for determining the priority of Quality of Service (QoS). QoS is the basis for giving priority to analyzing the network traffic data. In this study the classification of the data capture network traffic that though the use of K-Neaerest Neighbor algorithm (K-NN). Tools used to capture network traffic that wireshark application. From the observation of the dataset and the network traffic through the calculation process using K-NN algorithm obtained a result that the value generated by the K-NN classification has a very high level of accuracy. This is evidenced by the results of calculations which reached 99.14%, ie by calculating k = 3. Intisari—Trafik jaringan internet adalah lalu lintas ko­mu­nikasi data dalam jaringan yang ditandai dengan satu set ali­ran statistik dengan penerapan pola terstruktur. Pola ter­struktur yang dimaksud adalah informasi dari header paket data. Klasifikasi yang tepat terhadap sebuah trafik internet sa­ngat penting dilakukan terutama dalam hal disain perancangan arsitektur jaringan, manajemen jaringan dan keamanan jari­ngan. Analisa terhadap suatu trafik jaringan komputer meru­pakan salah satu cara mengetahui penggunaan protokol komu­nikasi jaringan komputer, sehingga dapat menjadi dasar pe­nen­tuan prioritas Quality of Service (QoS). Dasar pemberian prio­ritas QoS adalah dengan penganalisaan terhadap data trafik jaringan. Pada penelitian ini melakukan klasifikasi ter­hadap data capture trafik jaringan yang di olah menggunakan Algoritma K-Neaerest Neighbor (K-NN). Apli­kasi yang digu­nakan untuk capture trafik jaringan yaitu aplikasi wireshark. Hasil observasi terhadap dataset trafik jaringan dan melalui proses perhitungan menggunakan Algoritma K-NN didapatkan sebuah hasil bahwa nilai yang dihasilkan oleh klasifikasi K-NN memiliki tingkat keakuratan yang sangat tinggi. Hal ini dibuktikan dengan hasil perhi­tungan yang mencapai nilai 99,14 % yaitu dengan perhitungan k = 3. DOI: 10.24843/MITE.1601.10

Colegio de Sebastian (CDS), being a young academic and business entity, is in the process of developing its operations to serve its clients' satisfaction. This means that it must adapt itself to changes and improvements to survive the tough competition of private institutions. Effective communication in any business is a vital consideration that an owner must prioritize. Most growing businesses today are inclined to the use of technology to enhance the effectivity of their communication, and this entails the structuring of their computer network. In line with this, an assessment of the current network infrastructure was done at CDS to determine the need for new network topology. Through conducted surveys, CDS' network infrastructure was found out to have problems in terms of its topology that stems out to some issues like connectivity intermittence. To be able to provide a solution to such problem, a VLAN –based topology was proposed that includes topology that aims to achieve the four characteristics of good network architecture which are fault tolerance, scalability, quality of service and security. This research effort is to emphasize that properly planning an institution's network infrastructure is essential to serve its purpose optimally.


2014 ◽  
Vol 1044-1045 ◽  
pp. 338-343
Author(s):  
Shan Qiang Feng ◽  
Chun Chao Hu ◽  
Kai Ma ◽  
Xiao Yue Zhang ◽  
Wen Qing Lan ◽  
...  

Smart grid based on Ethernet technology is the development direction of power transmission network, power Ethernet carried different data communication service, which have different needs for network transmission time delay and bandwidth guarantee, which is reflected in the quality of service of network QoS (Quality of Service) requirements, in power Ethernet, QoS which can provided differentiated services (Diff-Serv) is essential. This paper outlines QoS implementation, QoS feature and related technologies in the power Ethernet switch, and analyses the flow characteristics of digital substation network, and proposes classification and scheduling scheme of service traffic based on network nodes, and elaborates an important effect that QoS has in ensuring substation communication network transmission of high quality service.


2016 ◽  
Vol 1 (2) ◽  
pp. 216
Author(s):  
Suela E.Shpuza

Performance is measured and done, the quality represents a key element to achieve the performance, especially customer service quality. In response to the pressure of globalization, the market increasingly competitive and volatile market dynamics that, many organizations actively seeking ways to add value to their services and improve their quality of service. Organizations usually tend to make their operations efficient priority. This process begins with the assessment of nevojave customers, their requirements and assessing the performance of domestic human resources in organization and performance depends on the outcome of the estimated earlier. Since this process can proceed in different directions. The causes of these results may be the lack of information and support of high-level management, performance standards unclear, inaccuracies assessors, very large number of forms to be completed and the use of software for the opposite purpose.


2020 ◽  
Vol 2 (1) ◽  
pp. 1-14
Author(s):  
Torkis Nasution

The selection was an attempt College to get qualified prospective students. Test data for new students able to describe the quality of academic and connect to graduate on time. Recognizing the academic quality of students is required in the implementation of the lecture to obtain optimal results. Real conditions today, timely graduation has not achieved optimally, need to be improved to reach the limits of reasonableness. Data that has no need to do a classification based on academic quality, in order to obtain predictions timely graduation. Therefore, proposed an effort to resolve the problem by applying the K-Nearest Neighbor algorithm to re-clustering the test result data for new students. The procedure is to determine the amount of data clusters, determining the center point of the cluster, calculate the distance of the object with the centroid, classifying objects. If the new data group calculation results together with the results of calculation of new data group then finished its calculations. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results.  


Author(s):  
Mincho Polimenov ◽  

The report focuses on the quality of service in tourism and in particular on the quality of blanks and work processes in the various issuing units and their coordination in the overall production process. Investments are focused not only on improved innovations in machine software and equipment, but also on such tricks and connections in the production cycle providing a high level of service and culture of consumption. Facilitating the processes provides a level of competition and creates an opportunity for affordability in quality and price. Emphasis is placed on the flexibility of tour operators and the tourist product and tourist service they offer, their quality, organization and management. Satisfying the modern "global tourist" requires not only knowledge of the structure of the offered tourist product and service, but also seeks an answer to the question "How" to be created and implemented.


2005 ◽  
Vol 02 (02) ◽  
pp. 167-180
Author(s):  
SEUNG-JOON OH ◽  
JAE-YEARN KIM

Clustering of sequences is relatively less explored but it is becoming increasingly important in data mining applications such as web usage mining and bioinformatics. The web user segmentation problem uses web access log files to partition a set of users into clusters such that users within one cluster are more similar to one another than to the users in other clusters. Similarly, grouping protein sequences that share a similar structure can help to identify sequences with similar functions. However, few clustering algorithms consider sequentiality. In this paper, we study how to cluster sequence datasets. Due to the high computational complexity of hierarchical clustering algorithms for clustering large datasets, a new clustering method is required. Therefore, we propose a new scalable clustering method using sampling and a k-nearest-neighbor method. Using a splice dataset and a synthetic dataset, we show that the quality of clusters generated by our proposed approach is better than that of clusters produced by traditional algorithms.


1998 ◽  
Vol 36 (8) ◽  
pp. 122-130 ◽  
Author(s):  
T. Hamada ◽  
S. Hogg ◽  
J. Rajahalme ◽  
C. Licciardi ◽  
L. Kristiansen ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document