Person: Baba, Abdullatif
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Dr. Öğr. Üyesi
Last Name
Baba
First Name
Abdullatif
Name
Abdullatif BABA
11 results
Search Results
Now showing 1 - 10 of 11
Publication Electricity-consuming forecasting by using a self-tuned ANN-based adaptable predictor(ELSEVIER SCIENCE SA, 2022) Baba, Abdullatif; Baba, Abdullatif; Turkish Aeronautical Association; Turk Hava Kurumu UniversityAccurate forecasting of power consumption is an essential and modern approach for planning smart infrastructural projects that are required to overcome the future challenges of power markets. In this context, a new design of a self-tuned ANN-based adaptable predictor is presented in this paper. At first, the main design of the original adaptable predictor is clarified including its new architecture that partially relies on the Hebbian law, its training process is also explained as well as the dataset which is used for training. Then, all the details of the self-tuning-based technique are explained with all the relevant results that prove its high capability to produce more accurate forecasting outcomes. The impact of our suggested approach is introduced by explaining two different practical examples that employ the K-means clustering algorithm, and the genetic algorithm when it is used to optimize the operating/outage schedule for a group of local solar units, respectively.Publication Zaman Serisi Veri Kümeleri İçin Olasılığa Dayalı Tahmin Yöntemi(Duzce Universitesi Bilim ve Teknoloji Dergisi, 2023-04-30) Abdullatif BABA; Baba, AbdullatifIn this paper, a new probabilistic technique (a variant of Multiple Model Particle Filter-MMPF) will be used to predict time-series datasets. At first, the reliable performance of our method is proved using a virtual random scenario containing sixty successive days; a large difference between the predicted states and the real corresponding values arises on the second, third, and fourth day. The predicted states that are determined by using our method converge rapidly towards the real values while a classical linear model exhibits a large amount of divergence if used alone here. Then, the performance of our approach is compared with some other techniques that were already applied to the same time-series datasets: IEX (Istanbul Stock Exchange Index), TAIEX (Taiwan Stock Exchange), and ABC (The Australian Beer Consumption). The performance evaluation metrics that are utilized here are the correlation coefficient, the mean absolute percentage error, and the root mean squared error.Publication A new design of a flying robot, with advanced computer vision techniques to perform self-maintenance of smart grids(Elsevier BV, 2022-05) Abdullatif Baba; Baba, AbdullatifPublication Iris segmentation techniques to recognize the behavior of a vigilant driver(IEEE, 2020-02) Abdullatif BABA; Baba, AbdullatifPublication Neural networks from biological to artificial and vice versa(Elsevier BV, 2024-01) Abdullatif Baba; Baba, AbdullatifPublication A fuzzy logic-based stabilization system for a flying robot, with an embedded energy harvester and a visual decision-making system(Elsevier BV, 2023-09) Abdullatif Baba; Basil Alothman; Baba, AbdullatifPublication Flying Robots for a Smarter Life(Elsevier BV, 2023) Abdullatif Baba; Baba, AbdullatifPublication Advanced AI-based techniques to predict daily energy consumption: A case study(PERGAMON-ELSEVIER SCIENCE LTD, 2021) Baba, Abdullatif; Baba, Abdullatif; Turkish Aeronautical Association; Turk Hava Kurumu UniversityIn this paper, we compare the efficiency of three different techniques used to predict the daily power consumption for a local industrial region (the studied case). At first, a variant of the Multiple Model Particle Filter is suggested as a probabilistic approach. Then, two different ANNs with one and two hidden layers respectively are designed and tested. Finally, we demonstrate a developed ANN-based design that has the ability to adapt its own structure according to the historical fluctuations provided by a given dataset that contains the consumed power for the same regarded region between 2011 and 2015; 1825 days. The potential of AI-based techniques will be emphasized by summarizing a complement heuristic study that employs the genetic algorithm to suggest an optimal outage schedule for the generators supplying the upper-mentioned region to accomplish maintenance activities that could be needed from time to time or to rest some of the units if the predicted consumption for a given period doesn't require the total produced power.Publication Voice encryption using a unified hyper-chaotic system(SPRINGER, 2023) Bonny, Talal; Al Nassan, Wafaa; Baba, Abdullatif; Baba, Abdullatif; University of Sharjah; Turk Hava Kurumu University; Turkish Aeronautical AssociationA Chaos-based cryptosystem is a vital method to enhance information protection in communication systems. The previous works have addressed this topic either by using highly complicated algorithms that are difficult to apply in practice or have a few encryption keys. This paper presents a new, highly secure chaos-based secure communication system that combines a conventional cryptography algorithm with two levels of chaotic masking technique. Furthermore, to enhance the security level, we employ the characteristic of a unified hyper-chaotic system to generate three different types of attractors. A Simulink of the stated system is implemented using MATLAB SIMULINK (R2013) to transmit a voice signal. Several testing methods such as power spectral density, spectrogram, histogram analysis, key sensitivity, correlation coefficient, signal to noise ratio (SNR), Percent Residual Deviation (PRD) are carried out to evaluate the quality of the proposed algorithm in several domains, time, frequency, and statistics. The simulation and comparison results demonstrate the high efficiency of the suggested cryptosystem and robustness against various cryptographic attacks.Publication FPGA-based parallel implementation to classify Hyperspectral images by using a Convolutional Neural Network(ELSEVIER, 2023) Baba, Abdullatif; Bonny, Talal; Baba, Abdullatif; Kuwait College Science & Technology; Turkish Aeronautical Association; Turk Hava Kurumu University; University of SharjahThanks to its richness in extractable features, Hyperspectral images (HSI) find an accelerated use in medical, industrial, agricultural, and environmental fields. In this paper, we present a wavelet-based reduction technique that creates a Hypercube containing the most significant features extracted from the original HSI and representing a multi-dimensional array that is utilized for training a Convolutional Neural Network (CNN), which is designed here to classify different types of surfaces or materials. The performance of this approach is tested and proved using two distinct datasets. Then, we compare the same approach with the PCA, a widely used reduction method. The most important contribution of this paper is the implementation of an FPGA-based parallel accelerator to train the same suggested CNN in only 10% of the computational time compared to the classical CPU-based techniques. The Microblaze will be explained and exploited here to play the role of an embedded microprocessor.