Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering International Journal of Advances in Applied Sciences TELKOMNIKA (Telecommunication Computing Electronics and Control) Indonesian Journal of electronics, electromedical engineering, and medical informatics Indonesian Journal of Electrical Engineering and Computer Science
Tsehay Admassu Assegie
Aksum University
Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Electrical & Electronics Engineering Engineering Environmental Science Materials Science & Nanotechnology Mathematics Physics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Handwritten digits recognition with decision tree classification: a machine learning approach Tsehay Admassu Assegie; Pramod Sekharan Nair
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 5: October 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (482.15 KB) | DOI: 10.11591/ijece.v9i5.pp4446-4451

Abstract

Handwritten digits recognition is an area of machine learning, in which a machine is trained to identify handwritten digits. One method of achieving this is with decision tree classification model. A decision tree classification is a machine learning approach that uses the predefined labels from the past known sets to determine or predict the classes of the future data sets where the class labels are unknown. In this paper we have used the standard kaggle digits dataset for recognition of handwritten digits using a decision tree classification approach. And we have evaluated the accuracy of the model against each digit from 0 to 9.
Software defined network emulation with OpenFlow protocol Tsehay Admassu Assegie
International Journal of Advances in Applied Sciences Vol 9, No 1: March 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (843.046 KB) | DOI: 10.11591/ijaas.v9.i1.pp70-76

Abstract

In software defined network the network infrastructure layer where the entire network devices, like switches and routers reside is connected with the separate controller layer with the help of standard called OpenFlow. The open flow standard enables different vendor devices like juniper, cisco and Huawei switch to connect to the controller or a software program. The software program controls and manages the network devices. Therefore, software defined network architecture makes the network flexible, cost effective and manageable, enables dynamic provisioning of bandwidth, dynamic scale out and dynamic scale in compared to the traditional network. In this study, the architectures and principles of software defined network is explored by emulating the software defined network employing a mininet.
A review on software defined network security risks and challenges Tsehay Admassu Assegie; Pramod Sekharan Nair
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 6: December 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i6.13119

Abstract

Software defined network is an emerging networking architecture that separates the traditional integrated control logic and data forwarding functionality into different planes, namely the control plane and data forwarding plane. The data plane does and end to end data delivery. And the control plane does the actual network traffic forwarding and routing between different network segments. In software defined network the networking infrastructure layer where the entire networking device, such as switches and routers reside is connected with the separate controller layer with the help of standard called OpenFlow protocol. It is a standard protocol that allows different vendor devices like juniper switches, cisco switches and huawei switches to be connected to the controller. The centralization of the SDN controller made the network more flexible, manageable and dynamic, such as provisioning of bandwidth, dynamic scale out and scale in compared to the traditional communication network, however the centralized SDN controller is more vulnerable to security risk factors such as DDOS and flow rule poisoning attack. In this paper we will explore the architectures and principles of software defined network and security risks with the centralized SDN controller and possible ways to mitigate these risks.
Support Vector Machine And K-Nearest Neighbor Based Liver Disease Classification Model Tsehay Admassu Assegie
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 3 No 1 (2021): February
Publisher : Department of electromedical engineering, Health Polytechnic of Surabaya, Ministry of Health Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v3i1.2

Abstract

Machine-learning approaches have become greatly applicable in disease diagnosis and prediction process. This is because of the accuracy and better precision of the machine learning models in disease prediction. However, different machine learning models have different accuracy and precision on disease prediction. Selecting the better model that would result in better disease prediction accuracy and precision is an open research problem. In this study, we have proposed machine learning model for liver disease prediction using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) learning algorithms and we have evaluated the accuracy and precision of the models on liver disease prediction using the Indian liver disease data repository. The analysis of result showed 82.90% accuracy for SVM and 72.64% accuracy for the KNN algorithm. Based on the accuracy score of SVM and KNN on experimental test results, the SVM is better in performance on the liver disease prediction than the KNN algorithm.
Improving network performance with an integrated priority queue and weighted fair queue scheduling Tsehay Admassu Assegie; Haymanot Derebe Bizuneh
Indonesian Journal of Electrical Engineering and Computer Science Vol 19, No 1: July 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v19.i1.pp241-247

Abstract

Quality of service (QoS) is the measure of network service availability and transmission. There are many factors influencing QoS among which one is the increasing number of network service users. The increase in the number of network service users and communication traffic causes network congestion. And the traffic congestion results in delay or packet loss and jitter variation. As a result, an organization’s network quality deteriorates and or even becomes unavailable. Therefore, to deliver a high quality network service to the users, a solution that avoids network traffic congestion is needed. In this study, the causes for network traffic congestion and the best solutions to eliminate traffic congestion in a network with congestion management and avoidance using an integrated priority queue (PQ) and weighted fair queue (WFQ) packet scheduling algorithms is proposed.
Co-Authors Haymanot Derebe Bizuneh Pramod Sekharan Nair