Amin Tuni Gure
Amin Tuni Gure has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Mario Alessandro Bochicchio
University of Bari Aldo Moro
1 shared publication - Mohammed Abebe Yimer
Arba Minch University
1 shared publication Selamu Shamore
Wachemo University,Department of Computer Science,Hossana,Ethiopia
1 shared publication
Latest Publications
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3442-3451
Federated Learning with Homomorphic Encryption for Secure Healthcare Applications
Federated learning (FL) with homomorphic encryption (HE) enables privacy-preserving machine learning (ML) across hospitals without centralizing sensitive health data. This work presents a secure FL framework for collaborative brain tumor classification using public MRI datasets. Each hospital trains a local model, encrypts gradient updates with a trusted HE schema (eg BFV, CKKS) algorithms, and sends the encrypted global model. No raw patient data leaves local sites, preserving confidentiality in compliance with GDPR and HIPAA. We evaluate the proposed framework using public brain tumor MRI datasets and simulate with multiple (3) clients (institutions). Encryption overheads, convergence behavior, accuracy, and communication cost are measured. Our results demonstrate that classification accuracy remains on par with conventional FL while providing robust data privacy guarantees. Computational overhead is manageable with parameter tuning, and communication remains practical across realistic network conditions. We highlight key trade-offs between privacy, utility, and efficiency. The findings show that HE-enabled FL is a viable approach for multi-center medical AI development without exposing sensitive medical images. The proposed FLHE framework for privacy preservation promised the way for scalable, secure collaboration across healthcare institutions, fostering innovation in diagnosis while preserving patient privacy and model performance.
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3442-3451
Federated Learning with Homomorphic Encryption for Secure Healthcare Applications
Federated learning (FL) with homomorphic encryption (HE) enables privacy-preserving machine learning (ML) across hospitals without centralizing sensitive health data. This work presents a secure FL framework for collaborative brain tumor classification using public MRI datasets. Each hospital trains a local model, encrypts gradient updates with a trusted HE schema (eg BFV, CKKS) algorithms, and sends the encrypted global model. No raw patient data leaves local sites, preserving confidentiality in compliance with GDPR and HIPAA. We evaluate the proposed framework using public brain tumor MRI datasets and simulate with multiple (3) clients (institutions). Encryption overheads, convergence behavior, accuracy, and communication cost are measured. Our results demonstrate that classification accuracy remains on par with conventional FL while providing robust data privacy guarantees. Computational overhead is manageable with parameter tuning, and communication remains practical across realistic network conditions. We highlight key trade-offs between privacy, utility, and efficiency. The findings show that HE-enabled FL is a viable approach for multi-center medical AI development without exposing sensitive medical images. The proposed FLHE framework for privacy preservation promised the way for scalable, secure collaboration across healthcare institutions, fostering innovation in diagnosis while preserving patient privacy and model performance.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 144-149
Hadiyyissa Automatic Speech Recognition Using Deep Learning Approach
Speech Recognition focuses on developing advanced technologies that can recognize and translate spoken language into text. Automatic Speech Recognition (ASR) is an Artificial Intelligence (AI) technology that captures human voice from a mi-crophone and analyzes it based on spoken words to comprehend natural language. In Ethiopia, ASR models have been developed for specific local languages such as Amharic, Tigrigna, Wolaytta, and Afaan Oromo, but there has been a lack of research on ASR models for the Hadiyyisa language, which is also spoken in Ethiopia. The research study designed and developed an ASR model for the Hadiyyisa language. The researchers collected data from native speakers of the Hadiyyisa language and used Python programming to design and develop the deep learning model for the Hadiyissa ASR model. Different methods and techniques were used in the study to achieve the research objectives and complete the entire research process. The proposed model utilized deep learning algorithms including RNN, LSTM, BiLSTM, and CNN, along with suitable feature extraction techniques such as Mel Frequency Cepstral Coefficients (MFCC). The accuracy of the proposed ASR model was evaluated through experimentation, which demonstrated that the BiLSTM model outperformed the other deep learning models with an overall accuracy of 90.95 % Based on the experimental evidence, the proposed model was found to be better suited for ASR for the Hadiyyisa language.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 144-149
Hadiyyissa Automatic Speech Recognition Using Deep Learning Approach
Speech Recognition focuses on developing advanced technologies that can recognize and translate spoken language into text. Automatic Speech Recognition (ASR) is an Artificial Intelligence (AI) technology that captures human voice from a mi-crophone and analyzes it based on spoken words to comprehend natural language. In Ethiopia, ASR models have been developed for specific local languages such as Amharic, Tigrigna, Wolaytta, and Afaan Oromo, but there has been a lack of research on ASR models for the Hadiyyisa language, which is also spoken in Ethiopia. The research study designed and developed an ASR model for the Hadiyyisa language. The researchers collected data from native speakers of the Hadiyyisa language and used Python programming to design and develop the deep learning model for the Hadiyissa ASR model. Different methods and techniques were used in the study to achieve the research objectives and complete the entire research process. The proposed model utilized deep learning algorithms including RNN, LSTM, BiLSTM, and CNN, along with suitable feature extraction techniques such as Mel Frequency Cepstral Coefficients (MFCC). The accuracy of the proposed ASR model was evaluated through experimentation, which demonstrated that the BiLSTM model outperformed the other deep learning models with an overall accuracy of 90.95 % Based on the experimental evidence, the proposed model was found to be better suited for ASR for the Hadiyyisa language.