Mahtem Mengstu

Mr. Mahtem Mengstu

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 February 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
ATAlper Taner
Alper Taner
MMMahtem Mengstu
Mahtem Mengstu
KEMALCAGATAY SELVIKEMALCAGATAY SELVI
KEMALCAGATAY SELVI
HDHüseyin Duran
Hüseyin Duran
İGİbrahim Gür
İbrahim Gür
Nicoleta UngureanuNicoleta Ungureanu
Nicoleta Ungureanu
Having the advantages of speed, suitability and high accuracy, computer vision has been effectively utilized as a non-destructive approach to automatically recognize and classify fruits and vegetables, to meet the increased demand for food quality-sensing devices. Primarily, this study focused on classifying apple varieties using machine learning techniques. Firstly, to discern how different convolutional neural network (CNN) architectures handle different apple varieties, transfer learning approaches, using popular seven CNN architectures (VGG16, VGG19, InceptionV3, MobileNet, Xception, ResNet150V2 and DenseNet201), were adopted, taking advantage of the pre-trained models, and it was found that DenseNet201 had the highest (97.48%) classification accuracy. Secondly, using the DenseNet201, deep features were extracted and traditional Machine Learning (ML) models: support vector machine (SVM), multi-layer perceptron (MLP), random forest classifier (RFC) and K-nearest neighbor (KNN) were trained. It was observed that the classification accuracies were significantly improved and the best classification performance of 98.28% was obtained using SVM algorithms. Finally, the effect of dimensionality reduction in classification performance, deep features, principal component analysis (PCA) and ML models was investigated. MLP achieved an accuracy of 99.77%, outperforming SVM (99.08%), RFC (99.54%) and KNN (91.63%). Based on the performance measurement values obtained, our study achieved success in classifying apple varieties. Further investigation is needed to broaden the scope and usability of this technique, for an increased number of varieties, by increasing the size of the training data and the number of apple varieties.

29 June 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ATAlper Taner
Alper Taner
MMMahtem Mengstu
Mahtem Mengstu
KEMALCAGATAY SELVIKEMALCAGATAY SELVI
KEMALCAGATAY SELVI
HDHüseyin Duran
Hüseyin Duran
Onder KabasOnder Kabas
Onder Kabas
NGNeluș Evelin Gheorghiță
Neluș Evelin Gheorghiță
It is critically necessary to maximize the efficiency of agricultural methods while concurrently reducing the cost of production. Varieties, types, and fruit classification grades are crucial to fruit production. High expenditure, inconsistent subjectivity, and tedious labor characterize traditional and manual varieties classification. This study developed machine learning (ML) models to classify ten apple varieties, extracting the histogram of oriented gradient (HOG) and color moments from RGB apple images. Support vector machine (SVM), random forest classifier (RFC), multilayer perceptron (MLP), and K-nearest neighbor (KNN) classification models were trained with 10-fold stratified cross-validation (Skfold) by using the textural and color features, and a GridSearch was implemented to fine-tune the hyperparameters. The trained models, SVM, RFC, MLP, and KNN were tested with separate test data and performed well, having an accuracy of 98.17%, 96.67%, 98.62%, and 91.28%, respectively. Having the top results, the MLP and SVM models demonstrated the potential of applying HOG and color moments to train ML models for classifying apple varieties. This study suggests conducting further research to thoroughly examine additional image features and determine the impact of combining features and utilizing different classifiers.

1 October 2021 in Black Sea Journal of Agriculture
Verified
Journal Article
Closed access
Gurkan Alp Kagan GurdilGurkan Alp Kagan Gurdil
Gurkan Alp Kagan Gurdil
MMMahtem Mengstu
Mahtem Mengstu
AOAko K Omer
Ako K Omer
AKAko Kakarash
Ako Kakarash
Embracing the idea of recycling wastes or changing waste to energy and other materials is an indispensable choice for sustainable development, and it is also a principal waste management mechanism. This study principally focuses on the utilization of agricultural wastes for sustainable development in areas related to organic manure usage, bioenergy production from the agricultural residues, and manufacturing of biocomposites. This article also addresses the potential of agricultural wastes in particular regions and the extent of their utilization to come up with a broader understanding of their effectiveness and practicality.

24 May 2025 in Journal of the Science of Food and Agriculture
Verified
Journal Article
Open access
MMMahtem Mengstu
Mahtem Mengstu
ATAlper Taner
Alper Taner
BACKGROUND: Computer vision and the use of image‐based solutions are gaining traction as non‐destructive food assessment methods because of the low costs of computational equipment. Research conducted on the development of wheat classification models has been based on limited data and a smaller number of classes compared to the availability of wheat varieties. To assess the applicability of convolutional neural network (CNN) models, the present study prepared multi‐view images of 124 wheat varieties. Using deep learning (DL) methods, a four‐layered CNN model was developed from scratch, and popular architectures, DenseNet201, MobileNet and InceptionV3 were trained using transfer learning.RESULTS: The proposed CNN model, DenseNet201, MobileNet and InceptionV3 models achieved classification accuracies of 95.40%, 92.41%, 90.54% and 83.47%, respectively, and they were found to be both promising and successful. Despite the challenges related to high computational resource demands, the newly proposed CNN model outperformed the pretrained models. It can be inferred that the multi‐view, large‐image dataset contributed significantly to the model's success in achieving promising accuracy in the challenging task of classifying 124 wheat varieties.CONCLUSION: The present study recommends further fine‐tuning of hyperparameters to improve the accuracy of the proposed CNN model and to identify better configurations. Besides, other popular models should be evaluated. Moreover, by freezing specific early layers, fine‐tuning should be performed to maximize accuracy. Additionally, the image datasets used will be publicly available to allow researchers to discover new methodologies to classify wheat varieties. © 2025 The Author(s). Journal of the Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

1 July 2021 in Black Sea Journal of Agriculture
Verified
Journal Article
Closed access
PDF file
Gurkan Alp Kagan GurdilGurkan Alp Kagan Gurdil
Gurkan Alp Kagan Gurdil
MMMahtem Mengstu
Mahtem Mengstu
TMTesfit Medhn
Tesfit Medhn
This study aimed to estimate the amount of biomass energy that can be acquired from crop residues in Eritrea, a country in the horn of Africa with a population of 6 million and having a national income per capita is around 150 US dollars. It’s an agricultural country. The energy potential of crop residues was calculated by considering the calorific values and the amount of available residue. For the year 2015, the total calorific value of agricultural residues was estimated approximately 1332.34TJ. According to the amount of agricultural residues, the most contributing crops were sorghum (50%) and millet (27%). Thus, it can be inferred that knowing the particular and general biomass energy potential of agricultural residues could help in managing energy sources and planning projects.

9 January 2024 in BIO Web of Conferences
Verified
Journal Article
Open access
PDF file
MMMahtem Mengstu
Mahtem Mengstu
ATAlper Taner
Alper Taner
HDHüseyin Duran
Hüseyin Duran
For food safety, quality control from the foodstuff production to the tasting of foods is needed and should be simple and non-destructive. Recent and notable non-destructive measurements of food and agricultural products are based on optical and spectroscopic techniques. Spectroscopy, meets the requirements of industrial applications for continuous quality control and process monitoring. Hence, this article covers a survey of recent research works, highlighting the application of spectroscopy and machine learning in food processing from bibliographic database. The survey was based on relevant articles, obtained from scientific database and evaluated selected research works based on survey inquires, the assessment included food processing problem addressed (varieties classification, origin identification, adulteration and quality control), types of spectroscopy used, machine learning models applied to solve the particular problem and keyword analysis to show the perspective of the research.