Della Krachai Mohamed

Dr. Della Krachai Mohamed

University of science and technology of oran, Mohamed BOUDIAF, Oran, Algeria
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
10 October 2025 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
ABABDELALI BENALI
ABDELALI BENALI
HKHayet Kharbouch
Hayet Kharbouch
DMDella Krachai Mohamed
Della Krachai Mohamed
JSJuginder Pal Singh
Juginder Pal Singh
RBRiyadh Bouddou
Riyadh Bouddou
OROleksandr Rubanenko
Oleksandr Rubanenko
Reliable segmentation of surface water is crucial for monitoring hydrological dynamics, mitigating disaster impacts, and supporting climate-resilient infrastructure development. However, traditional approaches based on spectral indices—such as the Normalized Difference Water Index (NDWI)—often suffer from poor generalization in the presence of spectral ambiguity, seasonal variations, and urban or vegetated interference. Existing deep learning architectures (DeepLabv3+, SegNet) show a trade-off between accuracy and speed, without specific adaptation to the challenges of the domain. This observation justifies the design of a hybrid architecture combining these models to achieve high semantic accuracy, environmental robustness, and computational efficiency. We propose a hybrid deep learning (DL) architecture that integrates two encoder-decoder segmentation frameworks: DeepLabv3+ with residual networks (ResNet18 and ResNet50) and SegNet with Visual Geometry Group (VGG16 and VGG19) backbones. The proposed model seamlessly combines two well-established encoding–decoding architectures, DeepLabv3+ (with ResNet) and SegNet (with VGG), by fusing their segmentation outputs at a decision level to combine the high semantic accuracy of SegNet with the computational efficiency of DeepLabv3+. This hybrid integration thus simultaneously leverages the complementary strengths of both networks to improve the overall quality of water surface segmentation while optimizing training time. This formulation briefly explains that the integration is not limited to a simple choice between models but also involves decision-level fusion or synergistic combination of results, which justifies the term hybrid or dual-stream architecture. These models are optimized for both semantic accuracy and computational efficiency, and trained using multispectral Sentinel-2 satellite imagery sourced from a publicly available Kaggle dataset featuring diverse terrain and spectral complexity. All models were implemented in MATLAB and evaluated using multiple performance metrics: overall accuracy (OA), Intersection over Union (IoU), F1 score, precision, recall, producer accuracy (PA), and user accuracy (UA). Among all configurations, SegNet with VGG16 achieved the best results, delivering An OA of 91%, IoU of 79%, and F1 score of 75%, while effectively minimizing false positives. In contrast, DeepLabv3+ with ResNet18 demonstrated exceptional computational efficiency, completing training in only 95 min with a respectable OA of 78%. These results underscore a clear trade-off between segmentation quality and training speed. Compared to baseline DL architectures and conventional NDWI-based methods, the proposed hybrid framework achieved significant gains in segmentation performance: precision improved by 2.64–22.66%, recall by 1.03–29.87%, and F1 score by 1.33–37.33%, with a 25.31–32.91% increase in IoU and up to 80% reduction in training time. Furthermore, the models proved robust under real-world environmental complexities such as cloud occlusion, seasonal transitions, and mixed urban-land–water boundaries. This research presents a scalable and high-accuracy solution for water body extraction, supporting a range of applications including flood risk assessment, environmental monitoring, and water resource planning. Future work will explore the integration of artificial neural networks (ANNs) for enhanced classification, multimodal data fusion with synthetic aperture radar (SAR) for all-weather operation, and real-time deployment using cloud-based platforms for global water surveillance.

1 December 2019 in International Journal of Power Electronics and Drive Systems (IJPEDS)
Verified
Journal Article
Open access
PDF file
SKSaidia Della Krachai
Saidia Della Krachai
ASA. Boudghene Stambouli
A. Boudghene Stambouli
DMDella Krachai Mohamed
Della Krachai Mohamed
MBM. Bekhti
M. Bekhti
Nano-satellites are key features for sharing the space data and scientific researches. They embed subsystems that are fed from solar panels and batteries. Power generated from these panels is subject to environmental conditions, most important of them are irradiance and temperature. Optimizing the usage of this power versus environmental variations is a primary task. Synchronous DC-DC buck converter is used to control the power transferred from PV panels to the subsystems while maintaining operation at maximal power. In this paper, artificial intelligence techniques: neural networks and adaptive neural fuzzy inference systems (ANFIS) are used to accomplish the tracking task. Simulation and experimental results demonstrate their efficiency, robustness and tracking quality.

10 May 2022 in Energies
Verified
Journal Article
Open access
PDF file
MKMohamed Keddar
Mohamed Keddar
Mamadou Lamine DoumbiaMamadou Lamine Doumbia
Mamadou Lamine Doumbia
KBKarim Belmokhtar
Karim Belmokhtar
DMDella Krachai Mohamed
Della Krachai Mohamed
In this paper, power-sharing management control on an AC islanded microgrid is investigated to achieve accurate reactive power sharing. The droop control method is primarily used to manage the active and reactive power sharing among the DGs in the microgrid. However, the line impedance mismatch causes unbalanced reactive power sharing. As a solution a consensus-based adaptive virtual impedance controller is proposed, where the consensus algorithm is used to set the reactive power mismatch; then a virtual impedance correction term is generated through a proportional-integral controller to eliminate the line impedance mismatch. Thus, reactive power sharing is achieved without knowledge of the line impedances or using a central controller. Moreover, the consensus algorithm is used to restore the AC bus voltage to the nominal value by estimating the DGs average voltage using neighbor communication to compensate for the decreased magnitude of the voltage reference. Matlab/Simulink is used to validate the accuracy of reactive power sharing and voltage restauration achievement of the proposed solution through simulation of different scenarios. In addition, a dSPACE DS1104 is used within a developed experimental testbench based on two parallel DGs to validate the effectiveness of the proposed solution in the real world.

1 November 2018
Verified
Conference Paper
Closed access
MKM. Keddar
M. Keddar
MDM.L. Doumbia
M.L. Doumbia
KBK. Belmokhtar
K. Belmokhtar
DMDella Krachai Mohamed
Della Krachai Mohamed
AMA.H. Midoun
A.H. Midoun
Distributed energy resources (DER) became a suitable solution to meet part of energy demand and providing electricity in isolated sites. Photovoltaic (PV) energy generation is one of the solutions that presents several benefits for use as a distributed energy resource. This paper presents a PV grid connected system with a multilevel inverter. The later one offers several advantages by synthesizing the AC output terminal voltage from several levels of voltages, sinusoidal current waveforms with lower THD content, higher power quality and reduced stress on the switching devices. This provides higher efficiency in the power conversion stage and satisfies the grid's connection criteria. On the other hand, a maximum power point tracker (MPPT) is very important in such us system to increase the system performance. In this paper, a control algorithm has been developed for the three-level single-phase inverter based on neural network maximum power point tracker to ensure a fast dynamic response. The proposed system is modeled and simulated under MATLAB/SIMULINK. As well as experimental results are presented to verify the feasibility of the proposed approach. The design and realization of the proposed system are presented and each part of the system will be discussed in detail.

1 June 2021
Verified
Book Chapter
Closed access
PDF file
DMDella Krachai Mohamed
Della Krachai Mohamed
MKMelouk Kheira
Melouk Kheira

8 April 2022 in PRZEGLĄD ELEKTROTECHNICZNY
Verified
Journal Article
Closed access
ABAbed Bouadi
Abed Bouadi
HNHoucine Naim
Houcine Naim
DMDella Krachai Mohamed
Della Krachai Mohamed
RFRadouane Fares
Radouane Fares
GBGuelta Bouchiba
Guelta Bouchiba
W artykule zbadano nowy model PLL (Pętla Fazowa) z technologią neuronowego sterowania modelem indukcyjnego magnetycznego systemu grzewczego przy dużej mocy i wysokiej częstotliwości, przy użyciu sterownika neuronowego zastępującego tradycyjny filtr dolnoprzepustowy (LPF). PLL, które sterują falownikiem za pomocą zespołu SIT (Static Induction Transistor)-obciążenie-neural PLL, celem PLL jest śledzenie częstotliwości rezonansowej systemu. Kontynuacja częstotliwości przez konwencjonalny PLL ma pewne opóźnienie i dużą różnicę faz między sygnałem wejściowym PLL a wyjściem LPF. Dlatego, aby przezwyciężyć ten problem, sięgnęliśmy po sieci sztucznych neuronów w granicach tego, co nas dotyczy, zainteresowanie nimi jest uzasadnione posiadanymi przez nie cechami. Aby poprawić dokładność sterowania i czas reakcji. Co więcej, przeanalizowano i porównano sterowany neuronowo sterownik PLL do systemu zasilania nagrzewaniem indukcyjnym. Kompletny model symulacyjny układu sterowania nagrzewaniem indukcyjnym uzyskuje się za pomocą oprogramowania Matlab/Simulink 6.5. Wyniki symulacji pokazują skuteczność i wyższość proponowanego neuronowego systemu sterowania PLL. (Modelowanie i symulacja nowatorskiego sterownika neuronowego PLL dla obwodu szeregowego falownika rezonansowego w nagrzewaniu indukcyjnym wysokiej częstotliwości)