Yazar "Wazirali, Raniyah" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Adaptive Trust-Based Framework for Securing and Reducing Cost in Low-Cost 6LoWPAN Wireless Sensor Networks
    (Mdpi, 2022) Ahmad, Rami; Wazirali, Raniyah; Abu-Ain, Tarik; Almohamad, Tarik Adnan
    Wireless Sensor Networks (WSNs) are the core of the Internet of Things (IoT) technology, as they will be used in various applications in the near future. The issue of security and power consumption is still one of the most important challenges facing this type of network. 6LoWPAN protocol was developed to meet these challenges in networks with limited power and resources. The 6LoWPAN uses a hierarchical topology and the traditional method of encryption and key management, keeping power consumption levels high. Therefore, in this paper, a technique has been developed that helps in balancing security and energy consumption by exploiting the Trust technique between low-cost WSN nodes called Trust-Cluster Head (Trust-CH). Trust between nodes is built by monitoring the behavior of packet transmission, the number of repetitions and the level of security. The Trust-CH model provides a dynamic multi-level encryption system that depends on the level of Trust between WSN nodes. It also proposes a dynamic clustering system based on the absolute-trust level in the mobile node environment to minimize power consumption. Along with a set of performance metrics (i.e., power consumption and network lifetime), the Cooja simulator was used to evaluate the Trust-CH model. The results were compared to a static symmetric encryption model together with various models from previous studies. It has been proven that the proposed model increases the network lifetime by 40% compared to previous studies, as well as saves as much as 28% power consumption in the case of using a static encryption model. While maintaining the proposed model's resistance to many malicious attacks on the network.
  • Küçük Resim Yok
    Öğe
    Integrating object-based and pixel-based segmentation for building footprint extraction from satellite images
    (Elsevier, 2023) Abujayyab, Sohaib K. M.; Almajalid, Rania; Wazirali, Raniyah; Ahmad, Rami; Tasoglu, Enes; Karas, Ismail R.; Hijazi, Ihab
    Accurately delineating building footprints from optical satellite imagery presents a formidable challenge, particularly in urban settings characterized by intricate and diverse structures. Consequently, enhancing the utility of these images for geospatial data updates demands meticulous refinement. Machine learning algorithms have made notable contributions in this context, yet the pursuit of precision remains an ongoing challenge. This paper aims to enhance the accuracy of building footprint extraction through the integration of object-based and pixel-based segmentation techniques. Additionally, it evaluates the performance of machine learning methodologies, specifically LightGBM, XGBoost, and Neural Network (NN) approaches. The model's evaluation employed low spectral resolution optical images, widely accessible and cost-effective for acquisition. The study's outcomes demonstrate a substantial enhancement in extraction accuracy compared to extant literature. The proposed methodology attains an overall accuracy of 99.39%, an F1 measurement of 0.9935, and a Cohen Kappa index of 0.9870. Thus, the proposed approach signifies a noteworthy advancement over existing techniques for building footprint extraction from high-resolution optical imagery.
  • Küçük Resim Yok
    Öğe
    Productivity modelling of an inclined stepped solar still for seawater desalination using boosting algorithms based on experimental data
    (Desalination Publ, 2022) Wazirali, Raniyah; Abujazar, Mohammed Shadi S.; Abujayyab, Sohaib K. M.; Ahmad, Rami; Fatihah, Suja; Kabeel, A. E.; Karaagac, Sakine Ugurlu
    Solar energy has recently become a viable option for desalinating seawater, primarily in arid regions. However, increasing the productivity of solar still by integrating experimental base and modelling methods is still subject to prediction errors; therefore, the main objective of this research is to postulate and test boosting algorithms for predicting the efficiency and productivity of the system. Five boosting regressors were deployed and evaluated: categorical boosting, adaptive boosting, extreme gradient boosting, gradient boosting machine, and gradient boosting machine (LightGBM). The proposed regressors are implemented based on the system's actual recorded dataset (consisting of 720 observations). The dataset consists of input variables, which are the wind speed (V), cloud cover, humidity, ambient temperature (T), solar radiation (SR), (T-io), (T-w), (T-v), and (T-t). Also, the output variable is represented by the productivity of the system. The dataset was separated into training (70%) and testing (30%) sets. In order to decrease regressors errors, hyperparameter optimization was employed. GradientBoosting approach provided the best prediction, with 95% R-2 accuracy and 39.57 root mean square error (RMSE) error. The LightGBM technique achieved 94% R-2 accuracy and 40.07 RMSE error in the testing dataset. The results reveal that GradientBoosting outperforms the cascaded forward neural network in predicting system productivity (CFNN).
  • Küçük Resim Yok
    Öğe
    State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques
    (Elsevier Science Sa, 2023) Wazirali, Raniyah; Yaghoubi, Elnaz; Abujazar, Mohammed Shadi S.; Ahmad, Rami; Vakili, Amir Hossein
    Forecasting renewable energy efficiency significantly impacts system management and operation because more precise forecasts mean reduced risk and improved stability and reliability of the network. There are several methods for forecasting and estimating energy production and demand. This paper discusses the significance of artificial neural network (ANN), machine learning (ML), and Deep Learning (DL) techniques in predicting renewable energy and load demand in various time horizons, including ultra-short-term, short-term, mediumterm, and long-term. The purpose of this study is to comprehensively review the methodologies and applications that utilize the latest developments in ANN, ML, and DL for the purpose of forecasting in microgrids, with the aim of providing a systematic analysis. For this purpose, a comprehensive database from the Web of Science was selected to gather relevant research studies on the topic. This paper provides a comparison and evaluation of all three techniques for forecasting in microgrids using tables. The techniques mentioned here assist electrical engineers in becoming aware of the drawbacks and advantages of ANN, ML, and DL in both load demand and renewable energy forecasting in microgrids, enabling them to choose the best techniques for establishing a sustainable and resilient microgrid ecosystem.
  • Küçük Resim Yok
    Öğe
    Wildfire Susceptibility Mapping Using Five Boosting Machine Learning Algorithms: The Case Study of the Mediterranean Region of Turkey
    (Hindawi Ltd, 2022) Abujayyab, Sohaib K. M.; Kassem, Moustafa Moufid; Khan, Ashfak Ahmad; Wazirali, Raniyah; Ozturk, Ahmet; Toprak, Ferhat
    Forest fires caused by different environmental and human factors are responsible for the extensive destruction of natural and economic resources. Modern machine learning techniques have become popular in developing very accurate and precise susceptibility maps of various natural disasters to help reduce the occurrence of such calamities. The present study has applied and tested multiple algorithms to map the areas susceptible to wildfire in the Mediterranean Region of Turkey. Besides, the performance of XGBoost, CatBoost, Gradient Boost, AdaBoost, and LightGBM methods for wildfire susceptibility mapping is also examined. The results have revealed the higher testing accuracy of CatBoost (95.47%) algorithm, followed by LightGBM (94.70%), XGBoost (88.8%), AdaBoost (86.0%), and GBM (84.48%) algorithms. Resultant wildfire susceptibility maps provide proper inventories for forest engineers, planners, and local governments for future policies regarding disaster management in Turkey.