Demissie Jobir Gelmecha

Dr. Demissie Jobir Gelmecha

Electronics and Communication Engineering, Adama Science and Technology University, Nazrēt, Oromīya, Ethiopia
orcid
Associate Professor

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
19 August 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SRSmitanjali Rout
Smitanjali Rout
SSSudhansu Kumar Samal
Sudhansu Kumar Samal
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
SMSatyasis Mishra
Satyasis Mishra
Accurate estimation of the State of Health (SOH) is crucial for ensuring the performance, safety, and longevity of lithium-ion batteries in electric vehicles. Traditional methods, such as Coulomb Counting and the Extended Kalman Filter, often lack the accuracy and computational efficiency required for modern applications. This study proposes an advanced framework that leverages machine learning models to model the nonlinear degradation patterns of lithium-ion batteries by focusing on key features such as voltage, current, internal resistance, and temperature. The proposed framework incorporates optimized pre-processing techniques, including normalization, to improve data quality and ensure consistency across varying battery conditions. Advanced machine learning models, including Adaboost, Xgboost, Ridge Regression, Decision Trees, Random Forests, Artificial Neural Networks, and Long Short-Term Memory Networks (LSTM), are employed to analyze battery performance. Among these, the LSTM network demonstrates outstanding capability in capturing long-term dependencies in sequential battery data, achieving a mean squared error of 0.000115 and an R2 score of 0.9982. It also accurately predicts the remaining life cycle of the battery using temporal patterns derived from MATLAB model datasheets, significantly reducing estimation errors. A comprehensive comparison using performance metrics such as root mean squared error, mean absolute error, and R2 scores highlights the LSTM model’s superiority while evaluating the suitability of other approaches. The proposed method not only improves estimation accuracy but also reduces computational demands through optimized feature selection and model training strategies, making it highly suitable for real-time applications in lightweight electric vehicles with limited computational resources. This research bridges the gap between theoretical advancements in data-driven techniques and their practical deployment in real-world battery management systems.

17 April 2017 in Applied Physics Letters
Verified
Journal Article
Closed access
QZQiang Zhang
Qiang Zhang
JLJunqing Li
Junqing Li
XLXingguang Liu
Xingguang Liu
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
Chiral media that exist ubiquitously in both nature and artificial metamaterials have exotic optical properties. The influence of chirality on the features of surface plasmon polaritons (SPPs) in a metal-chiral-metal plasmonic waveguide is revealed under realistic material parameters. A universal dispersion relation is derived, which covers the achiral metal-insulator-metal case. When the core of a symmetric waveguide is sufficiently thin, the introduction of chirality will weaken the cutoff effect which usually occurs in the antisymmetric surface plasmon mode. It is found that in the chiral case, the surface plasmon resonance frequency is slightly raised and that the propagation is enhanced. It is also demonstrated that chirality might modulate the transverse spin effect of SPPs in the waveguide. This work may enrich the plasmonics theory which is of great importance for nanophotonic devices.

29 January 2024 in Journal of Engineering
Verified
Journal Article
Open access
PDF file
SDSuvashisa Dash
Suvashisa Dash
MSMohammed Siddique
Mohammed Siddique
SMSatyasis Mishra
Satyasis Mishra
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
SSSunita Satapathy
Sunita Satapathy
RSRam Sewak Singh
Ram Sewak Singh
Brain cancer deaths are significantly increased in all categories of aged persons due to the abnormal growth of brain tumor tissues in the brain. The death rate can be controlled by accurate early stage brain tumor diagnosis. The detection and classification of brain tumors play a crucial role in early diagnosis and treatment planning. Brain tumor detection and classification have become challenging and time‐consuming for domain‐specific radiologists and pathologists in medical image analysis. So, automatic detection and classification are essential to reduce the time of diagnosis. In recent years, machine learning classifiers have played an essential role in automatically classifying brain tumors. In this research, an approach based on an improved fuzzy factor fuzzy local information C means (IFF‐FLICM) segmentation and hybrid modified harmony search and sine cosine algorithm (MHS‐SCA) optimized extreme learning machine (ELM) is proposed for brain tumor detection and classification. The IFF‐FLICM algorithm is utilized to accurately segment the brain’s magnetic resonance (MR) images to identify the tumor regions. The Mexican hat wavelet transform is employed for feature extraction from the segmented images. The extracted features from the segmented regions are fed into the MHS‐SCA‐ELM classifier for classification. The MHS‐SCA is proposed to optimize the weights of the ELM model to improve the classification performance. Five distinct multimodal and unimodal benchmark functions are considered for optimization to demonstrate the robustness of the proposed MHS‐SCA optimization technique. The image Dataset‐255 is considered for this study. The quality measures such as SSIM and PSNR are considered for segmentation. The proposed IFF‐FLICM segmentation achieved a peak signal‐to‐noise ratio (PSNR) of 37.24 dB and a structural similarity index (SSIM) of 0.9823. The proposed MHS‐SCA‐based ELM model achieved a sensitivity, specificity, and accuracy of 98.78%, 99.23%, and 99.12%. The classification performance results of the proposed MHS‐SCA‐ELM model are compared with MHS‐ELM, SCA‐ELM, and PSO‐ELM models, and the comparison results are presented.

24 March 2017 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
TBTeklu Merhawit Berhane
Teklu Merhawit Berhane
WMWeixiao Meng
Weixiao Meng
LCLei Chen
Lei Chen
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
CLCheng Li
Cheng Li
Full-duplex multiuser multiple-input-multiple-output (FD-MU-MIMO) systems are key technologies for the next generation wireless communication systems due to their ability in improving spectral efficiency. The major hurdle of the systems is in suppressing interferences such as the self-interference from downlink to uplink and multiuser interferences in both channels. Thus, it is required to depend on precoding schemes. This paper proposes signal-to-leakage-and-noise ratio (SLNR) precoding for downlink channel and self-interference plus noise covariance matrix aware SLNR precoding for the uplink channel to improve the spectral efficiency of FD mode systems in the Rician fading environment. Unlike zero-forcing and block diagonalization precoding schemes, it has tradeoffs between interference and noise, and again simultaneously support multiple numbers of users and antennas. The problem is formulated as maximizing SLNR to obtain the precoder that optimized the total spectral efficiency of the system. Numerical results confirm that for a given SNR values FD outperforms half duplex as a number of antennas per user in both channels increase, for fixed number of antennas at the base station, for a small power of the self-interference and for all Rician factor.

27 November 2018 in Physical Review A
Verified
Journal Article
Closed access
PDF file
XLXingguang Liu
Xingguang Liu
JLJunqing Li
Junqing Li
QZQiang Zhang
Qiang Zhang
GPGuotao Pang
Guotao Pang
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
We reveal an interesting phenomenon of the acceleration and deceleration of the phase rotation for an orbital-angular-momentum-carrying Laguerre-Gaussian beam in a chiral medium. Under this circumstance, the differences between the optical force and optical torque exerted on a dielectric spherical particle for chiral and achiral cases are demonstrated. The optical force and torque are exerted on the particle simultaneously, which makes the particle revolve and spin simultaneously, as a planet in the solar system. We hope the results may point to a unique routine of optical manipulation.

16 January 2018 in Physical Review A
Verified
Journal Article
Closed access
PDF file
QZQiang Zhang
Qiang Zhang
JLJunqing Li
Junqing Li
XLXingguang Liu
Xingguang Liu
Demissie Jobir GelmechaDemissie Jobir Gelmecha
Demissie Jobir Gelmecha
WZWeigang Zhang
Weigang Zhang
We reveal a behavior of screwdriving of a surface plasmonic field formed near a surface of strongly chiral material, where lateral force and torque can be provided by the quantum spin Hall effect of light simultaneously. We study the role of chirality strength of the material in optical manipulating a particle with electric and magnetic dipole and demonstrate the effect of the size and chirality strength of the particle on manipulation. We hope these results may point out a unique routine to sort and separate chiral particles and biomolecules optically.