Eshete Emiru

Dr. Eshete Emiru

Wuhan University of Technology
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
25 January 2021 in Information
Verified
Journal Article
Open access
PDF file
AWET ABERHAAWET ABERHA
AWET ABERHA
SXShengwu Xiong
Shengwu Xiong
Eshete EmiruEshete Emiru
Eshete Emiru
Moussa DialloMoussa Diallo
Moussa Diallo
ADAbdelghani Dahou
Abdelghani Dahou
This article studies convolutional neural networks for Tigrinya (also referred to as Tigrigna), which is a family of Semitic languages spoken in Eritrea and northern Ethiopia. Tigrinya is a “low-resource” language and is notable in terms of the absence of comprehensive and free data. Furthermore, it is characterized as one of the most semantically and syntactically complex languages in the world, similar to other Semitic languages. To the best of our knowledge, no previous research has been conducted on the state-of-the-art embedding technique that is shown here. We investigate which word representation methods perform better in terms of learning for single-label text classification problems, which are common when dealing with morphologically rich and complex languages. Manually annotated datasets are used here, where one contains 30,000 Tigrinya news texts from various sources with six categories of “sport”, “agriculture”, “politics”, “religion”, “education”, and “health” and one unannotated corpus that contains more than six million words. In this paper, we explore pretrained word embedding architectures using various convolutional neural networks (CNNs) to predict class labels. We construct a CNN with a continuous bag-of-words (CBOW) method, a CNN with a skip-gram method, and CNNs with and without word2vec and FastText to evaluate Tigrinya news articles. We also compare the CNN results with traditional machine learning models and evaluate the results in terms of the accuracy, precision, recall, and F1 scoring techniques. The CBOW CNN with word2vec achieves the best accuracy with 93.41%, significantly improving the accuracy for Tigrinya news classification.

3 February 2021 in Information
Verified
Journal Article
Open access
PDF file
Eshete EmiruEshete Emiru
Eshete Emiru
SXShengwu Xiong
Shengwu Xiong
YLYaxing Li
Yaxing Li
AWET ABERHAAWET ABERHA
AWET ABERHA
Moussa DialloMoussa Diallo
Moussa Diallo
Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end speech recognition systems are performed at word and character levels of a language. Amharic is a poorly resourced but morphologically rich language. This paper proposes hybrid connectionist temporal classification with attention end-to-end architecture and a syllabification algorithm for Amharic automatic speech recognition system (AASR) using its phoneme-based subword units. This algorithm helps to insert the epithetic vowel እ[ɨ], which is not included in our Grapheme-to-Phoneme (G2P) conversion algorithm developed using consonant–vowel (CV) representations of Amharic graphemes. The proposed end-to-end model was trained in various Amharic subwords, namely characters, phonemes, character-based subwords, and phoneme-based subwords generated by the byte-pair-encoding (BPE) segmentation algorithm. Experimental results showed that context-dependent phoneme-based subwords tend to result in more accurate speech recognition systems than the character-based, phoneme-based, and character-based subword counterparts. Further improvement was also obtained in proposed phoneme-based subwords with the syllabification algorithm and SpecAugment data augmentation technique. The word error rate (WER) reduction was 18.38% compared to character-based acoustic modeling with the word-based recurrent neural network language modeling (RNNLM) baseline. These phoneme-based subword models are also useful to improve machine and speech translation tasks.

11 March 2025 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
Eshete EmiruEshete Emiru
Eshete Emiru
DWDesalegn Mamo Wendyifraw
Desalegn Mamo Wendyifraw
The goal of natural language processing (NLP), which has recently gained popularity, is to improve the capacity of computers to comprehend and interact with human language. Consequently, to converse using natural language, it is crucial that spoken language be grammatically correct, especially for Geéz language. Geéz language sentences must follow certain norms of agreement in terms of number, person, gender, tense, and other factors to be considered grammatically correct. If the input sentence in Geéz language is improper, then it can have problems with subject-verb agreement, object-verb agreement, adjective-noun agreement, and adverb-verb agreement. The goal of the proposed work is to provide a neural machine translation approach for detecting and correcting grammar errors in Geéz sentences. We have prepared manually 11,490 Geéz parallel corpuses (Geéz language grammatically incorrect and grammatically correct sentences). After we have prepared a parallel Geéz sentence, we have used normalization, tokenization, padding, and one hot encoding as preprocesses. We have used two deep learning algorithms, including a bidirectional long short-term memory encoder-decoder and a long short-term memory encoder-decoder, for training the proposed model. Keras and TensorFlow were used for importing the required libraries, and we used the Python 3.7 environment for implementation. Two test cases are used for the evaluation technique. The first one is for the long short-term memory encoder-decoder model, and the second one is for the bidirectional long short-term memory encoder-decoder model. Finally, the bidirectional long short-term memory encoder-decoder model achieved best results with an accuracy of 82%, recall of 82%, precision of 85%, and F1-measure of 83% with balanced error type classes.

22 July 2021 in Information
Verified
Journal Article
Open access
PDF file
Moussa DialloMoussa Diallo
Moussa Diallo
SXShengwu Xiong
Shengwu Xiong
Eshete EmiruEshete Emiru
Eshete Emiru
AWET ABERHAAWET ABERHA
AWET ABERHA
AAAminu Onimisi Abdulsalami
Aminu Onimisi Abdulsalami
Mohamed Abd ElazizMohamed Abd Elaziz
Mohamed Abd Elaziz
Classification algorithms have shown exceptional prediction results in the supervised learning area. These classification algorithms are not always efficient when it comes to real-life datasets due to class distributions. As a result, datasets for real-life applications are generally imbalanced. Several methods have been proposed to solve the problem of class imbalance. In this paper, we propose a hybrid method combining the preprocessing techniques and those of ensemble learning. The original training set is undersampled by evaluating the samples by stochastic measurement (SM) and then training these samples selected by Multilayer Perceptron to return a balanced training set. The MLPUS (Multilayer perceptron undersampling) balanced training set is aggregated using the bagging ensemble method. We applied our method to the real-life Niger_Rice dataset and forty-four other imbalanced datasets from the KEEL repository in this study. We also compared our method with six other existing methods in the literature, such as the MLP classifier on the original imbalance dataset, MLPUS, UnderBagging (combining random under-sampling and bagging), RUSBoost, SMOTEBagging (Synthetic Minority Oversampling Technique and bagging), SMOTEBoost. The results show that our method is competitive compared to other methods. The Niger_Rice real-life dataset results are 75.6, 0.73, 0.76, and 0.86, respectively, for accuracy, F-measure, G-mean, and ROC with our proposed method. In contrast, the MLP classifier on the original imbalance Niger_Rice dataset gives results 72.44, 0.82, 0.59, and 0.76 respectively for accuracy, F-measure, G-mean, and ROC.

31 August 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
GTGetaneh Awoke Tegegne
Getaneh Awoke Tegegne
Eshete EmiruEshete Emiru
Eshete Emiru
MMMetages Molla
Metages Molla
BABaye Atnafu
Baye Atnafu
DADaniel Addis
Daniel Addis
ASAbebu Sintayehu
Abebu Sintayehu
Driver distraction is one of the major causes of road traffic accidents worldwide, resulting in significant economic losses, injuries, and fatalities. Intelligent driver monitoring systems have emerged as effective solutions for improving road safety through real-time detection of unsafe driving behaviors. This study proposes a deep learning-based framework for driver activity detection and classification using YOLO object detection architectures. A real-world driver activity dataset containing 5,422 annotated images was collected from drivers under natural driving conditions. The dataset consists of eight driver activity classes, including safe driving, drinking, eating, phoning, operating vehicle components, makeup/hair adjustment, object management, and talking to passengers. Four YOLO models, including YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv8n, were trained using transfer learning and evaluated based on precision, recall, AP, mAP@0.5. The results showed a consistent improvement in detection performance as model complexity increased. YOLOv5s achieved 90.1% precision, 88.7% recall, and 90.0% mAP@0.5, while YOLOv5m improved these values to 91.9%, 90.5%, and 92.5%, respectively. YOLOv5l further increased performance with 93.3% precision, 92.1% recall, and 95.0% mAP@0.5. YOLOv8n achieved the highest accuracy with 96.0% precision, 95.2% recall, and 96.3% mAP@0.5, demonstrating superior detection capability and computational efficiency. The findings indicate that advanced YOLO architectures provide accurate and efficient solutions for real-time driver activity recognition and can significantly contribute to intelligent transportation systems and road safety enhancement.