Masreshaw Demelash Bayleyegn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Masreshaw Demelash Bayleyegn has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Zia Ur Rahman
Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Guntur, India
5 shared publications Arnaud Dubois
2 shared publicationsC. Crotti
Lab. d'Optique Appliquée, CNRS, ENSTA ParisTech, École Polytechnique (France)
2 shared publicationsHoussine Makhlouf
2 shared publicationsKarsten Plamann
2 shared publicationsM. V. S. Ramprasad
Department of EECE, GITAM School of Technology, GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, India
2 shared publications
Latest Publications
- 30 March 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Development of optical coherence tomography for monitoring the glaucoma laser surgery
Tomographie par cohérence optique pour la chirurgie laser du glaucome: La capacité de la tomographie par cohérence optique (OCT) à délivrer des images tomographiques de tissus biologiques in vivo, de manière non invasive et en temps réel, a suscité un intérêt croissant pour de nombreuses applications biomédicales, principalement en ophtalmologie pour l’imagerie de la rétine et du segment antérieur de l’œil. Toutefois, pour l’imagerie à haute résolution de tissus biologiques fortement diffusants, comme la sclérotique et la cornée œdémateuse, la technique nécessitait des améliorations technologiques. Dans cette thèse, un système d’OCT « Fourier-domain » (FD-OCT) à très haute résolution spatiale (< 4 µm), à la longueur d’onde de 1,3 µm, a été développé dans la Laboratoire Charles Fabry – Institute d’Optique Graduate School. Avec ce système original, nous avons réussi, pour la première fois, à visualiser correctement le canal de Schlemm de l’œil humain qui se trouve à une profondeur d’environ 0,8 mm dans le limbe de la cornée, milieu fortement diffusant. L’imagerie du canal de Schlemm est capitale afin d’envisager la chirurgie par laser du glaucome, qui consiste à inciser cette partie de l’œil afin d’améliorer l’écoulement de l’humeur aqueuse. Par ailleurs, en collaboration avec le Laboratoire d’Optique Appliquée de l’ENSTA ParisTech, nous avons démontré la possibilité de contrôler en temps réel par OCT des découpes par laser femtoseconde pratiquées dans la cornée humaine in vitro. Ces travaux ont montré que l’opération du Glaucome par laser femtoseconde, contrôlée par OCT, devrait être possible.
- 30 March 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Development of optical coherence tomography for monitoring the glaucoma laser surgery
Tomographie par cohérence optique pour la chirurgie laser du glaucome: La capacité de la tomographie par cohérence optique (OCT) à délivrer des images tomographiques de tissus biologiques in vivo, de manière non invasive et en temps réel, a suscité un intérêt croissant pour de nombreuses applications biomédicales, principalement en ophtalmologie pour l’imagerie de la rétine et du segment antérieur de l’œil. Toutefois, pour l’imagerie à haute résolution de tissus biologiques fortement diffusants, comme la sclérotique et la cornée œdémateuse, la technique nécessitait des améliorations technologiques. Dans cette thèse, un système d’OCT « Fourier-domain » (FD-OCT) à très haute résolution spatiale (< 4 µm), à la longueur d’onde de 1,3 µm, a été développé dans la Laboratoire Charles Fabry – Institute d’Optique Graduate School. Avec ce système original, nous avons réussi, pour la première fois, à visualiser correctement le canal de Schlemm de l’œil humain qui se trouve à une profondeur d’environ 0,8 mm dans le limbe de la cornée, milieu fortement diffusant. L’imagerie du canal de Schlemm est capitale afin d’envisager la chirurgie par laser du glaucome, qui consiste à inciser cette partie de l’œil afin d’améliorer l’écoulement de l’humeur aqueuse. Par ailleurs, en collaboration avec le Laboratoire d’Optique Appliquée de l’ENSTA ParisTech, nous avons démontré la possibilité de contrôler en temps réel par OCT des découpes par laser femtoseconde pratiquées dans la cornée humaine in vitro. Ces travaux ont montré que l’opération du Glaucome par laser femtoseconde, contrôlée par OCT, devrait être possible.
- Open Access
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 115657-115671
EECS-GT: Energy-Efficient Collaborative Sensing Model Using Game Theory for Wireless Sensor Networks
Wireless Sensor Networks (WSNs) play an instrumental role in monitoring and data collection across a plethora of domains. As these networks expand and get more intricate, the need for energy-efficient and smart sensing models becomes paramount. This paper introduces the energy-efficient collaborative sensing model using game theory for WSNs. This model is unique in its approach, amalgamating game theory and reinforced learning to ensure optimal energy consumption without compromising the quality of service. A cornerstone of this model is the introduction of the Selection Propensity Index (SPI), which helps in the decision-making process of choosing the right sensors for specific tasks. Moreover, the model employs a Distributed Anticipatory Time-slot selection Algorithm (DATA), an RL-based algorithm that facilitates collaborative communication. This aspect ensures that the sensors while communicating, select the time slots that would result in minimal energy expenditure and optimal data transmission. Simulations are performed over the proposed model and the results obtained showcase that the proposed model outperforms the existing similar methods in terms of energy efficiency, packet drop ratio, and throughout. The proposed model exhibits an enhancement in terms of network lifetime by 202%, throughput by 30%, and is faster by more than 60% compared to the existing methods running on full load, thereby providing an innovative approach to energy efficiency in sensor networks.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 115657-115671
Open AccessEECS-GT: Energy-Efficient Collaborative Sensing Model Using Game Theory for Wireless Sensor Networks
Wireless Sensor Networks (WSNs) play an instrumental role in monitoring and data collection across a plethora of domains. As these networks expand and get more intricate, the need for energy-efficient and smart sensing models becomes paramount. This paper introduces the energy-efficient collaborative sensing model using game theory for WSNs. This model is unique in its approach, amalgamating game theory and reinforced learning to ensure optimal energy consumption without compromising the quality of service. A cornerstone of this model is the introduction of the Selection Propensity Index (SPI), which helps in the decision-making process of choosing the right sensors for specific tasks. Moreover, the model employs a Distributed Anticipatory Time-slot selection Algorithm (DATA), an RL-based algorithm that facilitates collaborative communication. This aspect ensures that the sensors while communicating, select the time slots that would result in minimal energy expenditure and optimal data transmission. Simulations are performed over the proposed model and the results obtained showcase that the proposed model outperforms the existing similar methods in terms of energy efficiency, packet drop ratio, and throughout. The proposed model exhibits an enhancement in terms of network lifetime by 202%, throughput by 30%, and is faster by more than 60% compared to the existing methods running on full load, thereby providing an innovative approach to energy efficiency in sensor networks.
- Open Access
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 115905-115925
Proof of Trust and Expertise (PoTE): A Novel Consensus Mechanism for Enhanced Security and Scalability in Electronic Health Record Management
This paper proposes a paradigm that combines edge computing and blockchain technology in the healthcare field, providing a groundbreaking method to handle, analyze, and safeguard medical data. The method effectively decreases the time delay, addresses problems related to data transmission capacity, and improves the protection of sensitive patient data by processing it locally. The blockchain network is essential to the system since it offers a secure and unchangeable record for storing processed data. The integration of this novel system guarantees that patient data, once recorded, is unable to be modified in a way that affects previous entries, thereby preserving the integrity of the data. This approach prominently incorporates the innovative Proof of Trust and Expertise (PoTE) consensus process, which utilizes the reliability and specialized knowledge of users in the network. This approach not only guarantees the secure and efficient validation of transactions, but also conforms to the essential demands of managing healthcare data. The proposed model provides efficient environment that is scalable and reliable with average block processing time of 0.25 sec, transactional throughput of 140 transactions per second (tps) and a success rate of 97% while operating over larger number of nodes in the network. The incorporation of edge computing and blockchain in healthcare is positioned to establish a novel benchmark in the management, processing, and security of medical data, consequently augmenting the overall caliber of healthcare services.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 115905-115925
Open AccessProof of Trust and Expertise (PoTE): A Novel Consensus Mechanism for Enhanced Security and Scalability in Electronic Health Record Management
This paper proposes a paradigm that combines edge computing and blockchain technology in the healthcare field, providing a groundbreaking method to handle, analyze, and safeguard medical data. The method effectively decreases the time delay, addresses problems related to data transmission capacity, and improves the protection of sensitive patient data by processing it locally. The blockchain network is essential to the system since it offers a secure and unchangeable record for storing processed data. The integration of this novel system guarantees that patient data, once recorded, is unable to be modified in a way that affects previous entries, thereby preserving the integrity of the data. This approach prominently incorporates the innovative Proof of Trust and Expertise (PoTE) consensus process, which utilizes the reliability and specialized knowledge of users in the network. This approach not only guarantees the secure and efficient validation of transactions, but also conforms to the essential demands of managing healthcare data. The proposed model provides efficient environment that is scalable and reliable with average block processing time of 0.25 sec, transactional throughput of 140 transactions per second (tps) and a success rate of 97% while operating over larger number of nodes in the network. The incorporation of edge computing and blockchain in healthcare is positioned to establish a novel benchmark in the management, processing, and security of medical data, consequently augmenting the overall caliber of healthcare services.
- Open Access
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 97990-98004
Brain Epileptic Seizure Detection Using Joint CNN and Exhaustive Feature Selection With RNN-BLSTM Classifier
Brain Epilepsy seizure is a critical disorder, which is an uncontrolled burst of electrical activity of brain. The early detection of brain seizure can save the life of humans. The electroencephalogram (EEG) signals may be used to automatically identify brain seizures, which is one of the most prominent solutions for this issue. However, the conventional methods are failed to classify the brain seizure effectively. So, this work implemented the Brain Epilepsy Seizure-Detection-Network (BESD-Net) using deep learning, recurrent learning properties. Initially, the dataset pre-processing is performed, which eliminates the noise, unwanted data from EEG dataset. Then, the deep learning based customized convolution neural network (CCNN) is trained on pre-processed EEG data for precise extraction of disease correlated features. The machine learning based exhaustive random forest (ERF) feature selection is used to optimize features from the CCNN features, which are highly correlated with disease dependent properties. In conclusion, the recurrent neural network (RNN) based bi-directional long short-term memory (BLSTM) is used in order to detect brain seizures from chosen ERF features. Training and testing of suggested methodology had made use of CHB-MIT Scalp EEG Database. The aforementioned model has achieved the values of 98.36%, 97.54%, 97.91%, 98% and 95.08% respectively for precision, sensitivity, F1-Score, accuracy and specificity. The findings of the simulations demonstrate that the suggested BESD-Net led to superior performance when compared to the technologies that are already in use.
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 97990-98004
Open AccessBrain Epileptic Seizure Detection Using Joint CNN and Exhaustive Feature Selection With RNN-BLSTM Classifier
Brain Epilepsy seizure is a critical disorder, which is an uncontrolled burst of electrical activity of brain. The early detection of brain seizure can save the life of humans. The electroencephalogram (EEG) signals may be used to automatically identify brain seizures, which is one of the most prominent solutions for this issue. However, the conventional methods are failed to classify the brain seizure effectively. So, this work implemented the Brain Epilepsy Seizure-Detection-Network (BESD-Net) using deep learning, recurrent learning properties. Initially, the dataset pre-processing is performed, which eliminates the noise, unwanted data from EEG dataset. Then, the deep learning based customized convolution neural network (CCNN) is trained on pre-processed EEG data for precise extraction of disease correlated features. The machine learning based exhaustive random forest (ERF) feature selection is used to optimize features from the CCNN features, which are highly correlated with disease dependent properties. In conclusion, the recurrent neural network (RNN) based bi-directional long short-term memory (BLSTM) is used in order to detect brain seizures from chosen ERF features. Training and testing of suggested methodology had made use of CHB-MIT Scalp EEG Database. The aforementioned model has achieved the values of 98.36%, 97.54%, 97.91%, 98% and 95.08% respectively for precision, sensitivity, F1-Score, accuracy and specificity. The findings of the simulations demonstrate that the suggested BESD-Net led to superior performance when compared to the technologies that are already in use.
- Open Access
- 11 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 88193-88208
SBTC-Net: Secured Brain Tumor Segmentation and Classification Using Black Widow With Genetic Optimization in IoMT
The people around the globe are suffering from different types of brain tumors. So, early prediction of brain tumors can save human lives. This work focused on implementation of secured brain tumor classification network (SBTC-Net) using transfer learning methods. Initially, security is achieved by performing the medical image watermarking (MIW) operation using translation invariant wavelet transform (TIWT). Here, the watermarking process covers the source MRI brain tumor image of patient with unknown medical image (cover image). Then, this watermarked image is transmitted over the Internet of Medical Things (IoMT) environment. Here, the attackers are unable to visualize the source image. So, the source brain tumor image is transmitted over a secured environment. At receiver of IoMT, the segmentation operation is performed using transfer learning-based Recurrent U-Net (RU-Net) model, which localizes exact area of tumor. In addition, multilevel features are extracted using black widow optimization-genetic algorithm (BWO-GA), which selects the best features using natural inspired properties. Further, transfer learning based AlexNet is used to train with the optimal features, which classifies the benign and malignant tumors. Finally, the simulation results show that the proposed SBTC-Net resulted in superior watermarking, segmentation, and classification performance in terms subjective visualization and objective metrics as compared to state of art approaches. The proposed SBTC-Net achieved 99.97% of segmentation accuracy, 99.98% of classification accuracy on BraTS-2020 dataset.
- 11 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 88193-88208
Open AccessSBTC-Net: Secured Brain Tumor Segmentation and Classification Using Black Widow With Genetic Optimization in IoMT
The people around the globe are suffering from different types of brain tumors. So, early prediction of brain tumors can save human lives. This work focused on implementation of secured brain tumor classification network (SBTC-Net) using transfer learning methods. Initially, security is achieved by performing the medical image watermarking (MIW) operation using translation invariant wavelet transform (TIWT). Here, the watermarking process covers the source MRI brain tumor image of patient with unknown medical image (cover image). Then, this watermarked image is transmitted over the Internet of Medical Things (IoMT) environment. Here, the attackers are unable to visualize the source image. So, the source brain tumor image is transmitted over a secured environment. At receiver of IoMT, the segmentation operation is performed using transfer learning-based Recurrent U-Net (RU-Net) model, which localizes exact area of tumor. In addition, multilevel features are extracted using black widow optimization-genetic algorithm (BWO-GA), which selects the best features using natural inspired properties. Further, transfer learning based AlexNet is used to train with the optimal features, which classifies the benign and malignant tumors. Finally, the simulation results show that the proposed SBTC-Net resulted in superior watermarking, segmentation, and classification performance in terms subjective visualization and objective metrics as compared to state of art approaches. The proposed SBTC-Net achieved 99.97% of segmentation accuracy, 99.98% of classification accuracy on BraTS-2020 dataset.
- Open Access
- 25 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 3, 178-188
A Deep Probabilistic Sensing and Learning Model for Brain Tumor Classification With Fusion-Net and HFCMIK Segmentation
Goal: Implementation of an artificial intelligencebased medical diagnosis tool for brain tumor classification, which is called the BTFSC-Net. Methods: Medical images are preprocessed using a hybrid probabilistic wiener filter (HPWF) The deep learning convolutional neural network (DLCNN) was utilized to fuse MRI and CT images with robust edge analysis (REA) properties, which are used to identify the slopes and edges of source images. Then, hybrid fuzzy c-means integrated k-means (HFCMIK) clustering is used to segment the disease affected region from the fused image. Further, hybrid features such as texture, colour, and low-level features are extracted from the fused image by using gray-level cooccurrence matrix (GLCM), redundant discrete wavelet transform (RDWT) descriptors. Finally, a deep learning based probabilistic neural network (DLPNN) is used to classify malignant and benign tumors. The BTFSC-Net attained 99.21% of segmentation accuracy and 99.46% of classification accuracy. Conclusions: The simulations showed that BTFSC-Net outperformed as compared to existing methods.
- 25 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 3, 178-188
Open AccessA Deep Probabilistic Sensing and Learning Model for Brain Tumor Classification With Fusion-Net and HFCMIK Segmentation
Goal: Implementation of an artificial intelligencebased medical diagnosis tool for brain tumor classification, which is called the BTFSC-Net. Methods: Medical images are preprocessed using a hybrid probabilistic wiener filter (HPWF) The deep learning convolutional neural network (DLCNN) was utilized to fuse MRI and CT images with robust edge analysis (REA) properties, which are used to identify the slopes and edges of source images. Then, hybrid fuzzy c-means integrated k-means (HFCMIK) clustering is used to segment the disease affected region from the fused image. Further, hybrid features such as texture, colour, and low-level features are extracted from the fused image by using gray-level cooccurrence matrix (GLCM), redundant discrete wavelet transform (RDWT) descriptors. Finally, a deep learning based probabilistic neural network (DLPNN) is used to classify malignant and benign tumors. The BTFSC-Net attained 99.21% of segmentation accuracy and 99.46% of classification accuracy. Conclusions: The simulations showed that BTFSC-Net outperformed as compared to existing methods.
- 1 November 2012
- Published by Elsevier in Optics Communications
- Vol. 285 (24) , 5564-5569
Ultrahigh resolution spectral-domain optical coherence tomography at 1.3 μm using a broadband superluminescent diode light source
- 1 November 2012
- Published by Elsevier in Optics Communications
- Vol. 285 (24) , 5564-5569
Ultrahigh resolution spectral-domain optical coherence tomography at 1.3 μm using a broadband superluminescent diode light source
- 1 June 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8427, 84271E
Guiding glaucoma laser surgery using Fourier-domain optical coherence tomography at 1.3 μm
Glaucoma is a disease of the optic nerve that is usually associated with an increased internal pressure of the eye and can lead to a decreased vision and eventually blindness. It is the second leading cause of blindness worldwide with more than 80 million people affected and approximately 6 million blind. The standard clinical treatment for glaucoma, after unsuccessful administration of eyedrops and other treatments, is performing incisional surgery. However, due to post-surgical complications like scarring and wound healing, this conventional method has a global success rate of only about 60%. In comparison, as femtosecond laser surgery may be performed in volume and is a priori less invasive and less susceptible of causing scarring, glaucoma laser surgery could be a novel technique to supplement the conventional glaucoma surgery. We have been working on the development of a new tool for glaucoma treatment that uses an optimized femtosecond laser source centered at 1.65 μm wavelength for making the surgery and an imaging system based on optical coherence tomography (OCT) for guiding the laser surgery. In this proceeding, we present the results obtained so far on the development and utilization of Fourier-domain OCT imaging system working at 1.3 μm center wavelength for guiding the laser incision. Cross-sectional OCT image of pathological human cornea showing the Schlemm's canal, where the surgery is intended to be done, is presented. By coupling OCT imaging system with the laser incision system, we also demonstrate real-time imaging of femtosecond laser incision of cornea.
- 1 June 2012
- Published by SPIE-Intl Soc Optical Eng
- Vol. 8427, 84271E
Guiding glaucoma laser surgery using Fourier-domain optical coherence tomography at 1.3 μm
Glaucoma is a disease of the optic nerve that is usually associated with an increased internal pressure of the eye and can lead to a decreased vision and eventually blindness. It is the second leading cause of blindness worldwide with more than 80 million people affected and approximately 6 million blind. The standard clinical treatment for glaucoma, after unsuccessful administration of eyedrops and other treatments, is performing incisional surgery. However, due to post-surgical complications like scarring and wound healing, this conventional method has a global success rate of only about 60%. In comparison, as femtosecond laser surgery may be performed in volume and is a priori less invasive and less susceptible of causing scarring, glaucoma laser surgery could be a novel technique to supplement the conventional glaucoma surgery. We have been working on the development of a new tool for glaucoma treatment that uses an optimized femtosecond laser source centered at 1.65 μm wavelength for making the surgery and an imaging system based on optical coherence tomography (OCT) for guiding the laser surgery. In this proceeding, we present the results obtained so far on the development and utilization of Fourier-domain OCT imaging system working at 1.3 μm center wavelength for guiding the laser incision. Cross-sectional OCT image of pathological human cornea showing the Schlemm's canal, where the surgery is intended to be done, is presented. By coupling OCT imaging system with the laser incision system, we also demonstrate real-time imaging of femtosecond laser incision of cornea.