Abrham Debasu Mengistu
Bahir Dar University

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

Soil Characterization and Classification: A Hybrid Approach of Computer Vision and Sensor Network Abrham Debasu Mengistu; Dagnachew Melesew Alemayehu
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 2: April 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (7308.155 KB) | DOI: 10.11591/ijece.v8i2.pp989-995

Abstract

This paper presents soil characterization and classification using computer vision & sensor network approach. Gravity Analog Soil Moisture Sensor with arduino-uno and image processing is considered for classification and characterization of soils. For the data sets, Amhara regions and Addis Ababa city of Ethiopia are considered for this study. In this research paper the total of 6 group of soil and each having 90 images are used. That is, form these 540 images were captured. Once the dataset is collected, pre-processing and noise filtering steps are performed to achieve the goal of the study through MATLAB, 2013. Classification and characterization is performed through BPNN (Back-propagation neural network), the neural network consists of 7 inputs feature vectors and 6 neurons in its output layer to classify soils. 89.7% accuracy is achieved when back-propagation neural network (BPNN) is used.
The effects of multiple layers feed-forward neural network transfer function in digital based Ethiopian soil classification and moisture prediction Belete Biazen Bezabeh; Abrham Debasu Mengistu
International Journal of Electrical and Computer Engineering (IJECE) Vol 10, No 4: August 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (378.485 KB) | DOI: 10.11591/ijece.v10i4.pp4073-4079

Abstract

In the area of machine learning performance analysis is the major task in order to get a better performance both in training and testing model. In addition, performance analysis of machine learning techniques helps to identify how the machine is performing on the given input and also to find any improvements needed to make on the learning model. Feed-forward neural network (FFNN) has different area of applications, but the epoch convergences of the network differs from the usage of transfer function. In this study, to build the model for classification and moisture prediction of soil, rectified linear units (ReLU), Sigmoid, hyperbolic tangent (Tanh) and Gaussian transfer function of feed-forward neural network had been analyzed to identify an appropriate transfer function. Color, texture, shape and brisk local feature descriptor are used as a feature vector of FFNN in the input layer and 4 hidden layers were considered in this study. In each hidden layer 26 neurons are used. From the experiment, Gaussian transfer function outperforms than ReLU, sigmoid and tanh transfer function. But the convergence rate of Gaussian transfer function took more epoch than ReLU, Sigmoid and tanh.
The Effects of Segmentation Techniques in Digital Image Based Identification of Ethiopian Coffee Variety Abrham Debasu Mengistu
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 2: April 2018
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v16i2.8419

Abstract

This paper presents the effects of segmentation techniques in the identification of Ethiopian coffee variety. In Ethiopia, coffee varieties are classified based on their growing region. The most widely coffee growing regions in Ethiopia are Bale, Harar, Jimma, Limu, Sidamo and Welega. Coffee beans of these regions very in color shape and texture. We investigated various segmentation techniques for efficient coffee beans variety identification system. Images of six different coffee beans varieties in Oromia and Southern Ethiopia were acquired and analyzed. For this study Otsu, Fuzzy-C-Means (FCM) and Kmeans segmentation techniques are considered. For classification of the varieties of Ethiopian coffee beans back propagation neural network (BPNN) is used. From the experiment 94.54% accuracy is achieved when BPNN is used on FCM segmentation technique.
Computer vision for Ethiopian agricultural crop pest identification Dagnachew Melesew Alemayehu; Abrham Debasu Mengistu; Seffi Gebeyehu Mengistu
Indonesian Journal of Electrical Engineering and Computer Science Vol 3, No 1: July 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v3.i1.pp209-214

Abstract

Crop pest is an organism that creates damage on to the agriculture by feeding crops. The research focuses on four major types of crop pest which occurs on teff, wheat, sorghum, barley and maize these are Black tef beetles, Ageda korkur, Degeza and Yesinde Kish Kish. The aim of this paper is identification of the four types of agricultural crop pest using a computer vision technique. The image of crop pest were taken from Amhara regions of Ethiopia i.e. Adiet, Dejen, Gonder, Debremarkos (places where images were taken).  In this paper, artificial neural network (ANN), a hybrid of self organizing map (SOM) with Radial basis function (RBF) and a hybrid of support vector machine (SVM) with Radial basis function (RBF) are used, and also we used Otsu and Kmeans segmentation techniques. Finally we selected Kmeans techniques for segmenting crop pest. In general, the overall result showed that using kmeans segmentation in RBF and SVM perform better than using otsu method in the other algorithm and the recognition performance of the combination of RBF (Radial basis function) and SVM (support vector machine) is 93.33%.
Speech Processing for Text Independent Amharic Language Dialect Recognition Abrham Debasu Mengistu; Dagnachew Melesew Alemayehu
Indonesian Journal of Electrical Engineering and Computer Science Vol 5, No 1: January 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v5.i1.pp115-122

Abstract

Dialect is a difference of verbal communication spoken by people from a particular society or geographic area so the paper focuses on Amharic language dialect recognition. In this paper,  the authors have used backpropagation artificial neural network, VQ(vector quantization), (Gaussian Mixture Models) and a combination of GMM and backpropagation artificial neural network for classifying dialects of Amharic language speakers. In this research, a total of 100 speakers for each group of dialects are considered each having about 10 seconds duration is collected. The feature vectors of Mel frequency cepstral coefficients (MFCC) had been used to recognize the dialects of speakers. In this research paper the recognition model that uses a tanh activation function have a better result instead of using the Logistic Sigmoid activation function in backpropagation artificial neural network. After conducting the above experiments 95.7% accuracy achieved when GMM and backpropagation artificial neural network with tanh activation function are combined.
Text Independent Amharic Language Speaker Identification in Noisy Environments using Speech Processing Techniques Abrham Debasu Mengistu; Dagnachew Melesew Alemayehu
Indonesian Journal of Electrical Engineering and Computer Science Vol 5, No 1: January 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v5.i1.pp109-114

Abstract

In Ethiopia, the largest ethnic and linguistic groups are the Oromos, Amharas and Tigrayans. This paper presents the performance analysis of text-independent speaker identification system for the Amharic language in noisy environments. VQ (Vector Quantization), GMM (Gaussian Mixture Models), BPNN (Back propagation neural network), MFCC (Mel-frequency cepstrum coefficients), GFCC (Gammatone Frequency Cepstral Coefficients), and a hybrid approach had been use as techniques for identifying speakers of Amharic language in noisy environments. For the identification process, speech signals are collected from different speakers including both sexes; for our data set, a total of 90 speakers’ speech samples were collected, and each speech have 10 seconds duration from each individual. From these speakers, 59.2%, 70.9% and 84.7% accuracy are achieved when VQ, GMM and BPNN are used on the combined feature vector of MFCC and GFCC.