Lamya Albraheem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lamya Albraheem has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Afnan A. Aljaser
Information Technology Department, King Saud University, Riyadh, Saudi Arabia
1 shared publicationAfnan Aljaser
Department of Information Technology, College of Computer and Information Science, King Saud University, Riyadh, Saudi Arabia
1 shared publication- Alnashwan
Information Technology Department, College of Computer and Information Science, King Saud University, Saudi Arabia
1 shared publication - Areej Alotaibi
College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia
1 shared publication - Fahad Almutlaq
Department of Geography, College of Humanities and Social Sciences, King Saud University, Riyadh 11451, Saudi Arabia
1 shared publication Ghada Ba-Hliwah
Information Technology Department, King Saud University, Riyadh, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 30 October 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (11) , 495
A GeoAI Framework for Offshore Wind Farm Site Suitability Prediction Using Ensemble Machine Learning
The integration of artificial intelligence (AI) with geospatial analysis, commonly referred to as GeoAI, provides new opportunities for renewable-energy planning and site-suitability assessment. However, limited attention has been given to integrating Multi-Criteria Decision Analysis (MCDA) with machine learning (ML) for offshore wind farm suitability assessment. This study proposes a GeoAI framework to predict offshore wind farm suitability using ensemble machine-learning techniques. A pooled technology-aware ML model was developed using nine predictors, including a turbine type to account for fixed-bottom and floating technologies. Gradient Boosting, XGBoost, LightGBM, Random Forest, Decision Tree, and Logistic Regression were evaluated, with a majority-class classifier included as a baseline. Model development and hyperparameter optimization were conducted using five-fold stratified group cross-validation based on geographic blocks, with weighted F1-score used as the primary model-selection metric. Gradient Boosting achieved the best model, with a weighted F1-score of 0.8077, followed closely by XGBoost (0.8031), and was therefore selected for final evaluation. SHapley Additive exPlanations (SHAP) analysis further revealed that wind power density, wind speed, and water depth were the most influential factors governing offshore wind farm suitability predictions.
- 30 October 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (11) , 495
Open AccessA GeoAI Framework for Offshore Wind Farm Site Suitability Prediction Using Ensemble Machine Learning
The integration of artificial intelligence (AI) with geospatial analysis, commonly referred to as GeoAI, provides new opportunities for renewable-energy planning and site-suitability assessment. However, limited attention has been given to integrating Multi-Criteria Decision Analysis (MCDA) with machine learning (ML) for offshore wind farm suitability assessment. This study proposes a GeoAI framework to predict offshore wind farm suitability using ensemble machine-learning techniques. A pooled technology-aware ML model was developed using nine predictors, including a turbine type to account for fixed-bottom and floating technologies. Gradient Boosting, XGBoost, LightGBM, Random Forest, Decision Tree, and Logistic Regression were evaluated, with a majority-class classifier included as a baseline. Model development and hyperparameter optimization were conducted using five-fold stratified group cross-validation based on geographic blocks, with weighted F1-score used as the primary model-selection metric. Gradient Boosting achieved the best model, with a weighted F1-score of 0.8077, followed closely by XGBoost (0.8031), and was therefore selected for final evaluation. SHapley Additive exPlanations (SHAP) analysis further revealed that wind power density, wind speed, and water depth were the most influential factors governing offshore wind farm suitability predictions.
- 27 December 2024
- Published by Springer Nature
- p. 91-103
Design and Implementation of Site Suitability Model of Solar Energy in Riyadh Using GIS-AHP Approach
- 27 December 2024
- Published by Springer Nature
- p. 91-103
Design and Implementation of Site Suitability Model of Solar Energy in Riyadh Using GIS-AHP Approach
- Open Access
- 20 November 2024
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 13 (11) , 416
A Geographic Information System-Based Model and Analytic Hierarchy Process for Wind Farm Site Selection in the Red Sea
The wind is one of the most important sources of renewable energy. However, it is associated with many challenges, with one of the most notable being determining suitable locations for wind power farms based on different evaluation criteria. In this study, we investigated the suitability of wind farm sites in the Red Sea off the coast of Saudi Arabia using the analytical hierarchy process (AHP) and a Geographic Information System (GIS). We assessed the suitability of offshore locations for wind energy projects, differentiating between fixed and floating turbines, and identified a 4180 km2 area as less suitable, whereas the 33,094 km2, 20,618 km2, and 11,077 km2 areas were deemed suitable, very suitable, and extremely suitable, respectively. These findings highlight the differences in suitability levels based on specific geographical features. Moreover, the extremely suitable location, which has the largest area of 3032 km2, has the capacity to generate an annual energy output of 56,965,410 MWh/year.
- 20 November 2024
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 13 (11) , 416
Open AccessA Geographic Information System-Based Model and Analytic Hierarchy Process for Wind Farm Site Selection in the Red Sea
The wind is one of the most important sources of renewable energy. However, it is associated with many challenges, with one of the most notable being determining suitable locations for wind power farms based on different evaluation criteria. In this study, we investigated the suitability of wind farm sites in the Red Sea off the coast of Saudi Arabia using the analytical hierarchy process (AHP) and a Geographic Information System (GIS). We assessed the suitability of offshore locations for wind energy projects, differentiating between fixed and floating turbines, and identified a 4180 km2 area as less suitable, whereas the 33,094 km2, 20,618 km2, and 11,077 km2 areas were deemed suitable, very suitable, and extremely suitable, respectively. These findings highlight the differences in suitability levels based on specific geographical features. Moreover, the extremely suitable location, which has the largest area of 3032 km2, has the capacity to generate an annual energy output of 56,965,410 MWh/year.
- Open Access
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 179-188
IoT Based Accident Prevention System using Machine Learning techniques
The likelihood of car accidents increases during extreme weather conditions, such as fog, winds, snow, rain, etc. While it may not be possible to prevent all such accidents, their incidence can be reduced by taking proper measures. Therefore, an intelligent accident-avoidance system is necessary to predict the severity of accidents based on weather and road conditions. This research paper suggests three machine learning (ML) methods for an Internet of Things (IoT)-based accident severity prediction system. The methods are Random Forest, LightGBM, and XGBoost.The aim is to predict the severity of car accidents based on various weather features using a machine learning model. However, considering the previous work, we observed that the size of datasets is frequently minimal, and some of the research discusses the influence of the weather on the number of accidents. Therefore, we used the Countrywide Traffic Accident Dataset, which covers 2.8 million vehicle accidents in the United States from 2016 to 2021. In conclusion, our methodology appears to be efficient in predicting the severity of car accidents. Among the three methods, LightGBM achieved the highest prediction accuracy (72%), precision (70%), recall (70%), F1-scores (70%), and area curve (AUC) (0.86) of the receiver operating characteristic (ROC) curve.
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 179-188
Open AccessIoT Based Accident Prevention System using Machine Learning techniques
The likelihood of car accidents increases during extreme weather conditions, such as fog, winds, snow, rain, etc. While it may not be possible to prevent all such accidents, their incidence can be reduced by taking proper measures. Therefore, an intelligent accident-avoidance system is necessary to predict the severity of accidents based on weather and road conditions. This research paper suggests three machine learning (ML) methods for an Internet of Things (IoT)-based accident severity prediction system. The methods are Random Forest, LightGBM, and XGBoost.The aim is to predict the severity of car accidents based on various weather features using a machine learning model. However, considering the previous work, we observed that the size of datasets is frequently minimal, and some of the research discusses the influence of the weather on the number of accidents. Therefore, we used the Countrywide Traffic Accident Dataset, which covers 2.8 million vehicle accidents in the United States from 2016 to 2021. In conclusion, our methodology appears to be efficient in predicting the severity of car accidents. Among the three methods, LightGBM achieved the highest prediction accuracy (72%), precision (70%), recall (70%), F1-scores (70%), and area curve (AUC) (0.86) of the receiver operating characteristic (ROC) curve.
- Open Access
A Hybrid Indoor Positioning System Based on Visible Light Communication and Bluetooth RSS Trilateration
Indoor positioning has become an attractive research topic because of the drawbacks of the global navigation satellite system (GNSS), which cannot detect accurate locations within indoor areas. Radio-based positioning technologies are one major category of indoor positioning systems. Another major category consists of visible light communication-based solutions, as they have become a revolutionary technology for indoor positioning in recent years. The proposed study intends to make use of both technologies by creating a hybrid indoor positioning system that uses VLC and Bluetooth together. The system first collects the initial location information based on VLC proximity, then collects the strongest Bluetooth signals to determine the receiver’s location using Bluetooth RSS (received signal strength) trilateration. This has been inspired by the fact that there have not been any studies that make use of both technologies with the same positioning algorithm, which can lead to pretty high accuracy of up to 0.03 m.
Open AccessA Hybrid Indoor Positioning System Based on Visible Light Communication and Bluetooth RSS Trilateration
Indoor positioning has become an attractive research topic because of the drawbacks of the global navigation satellite system (GNSS), which cannot detect accurate locations within indoor areas. Radio-based positioning technologies are one major category of indoor positioning systems. Another major category consists of visible light communication-based solutions, as they have become a revolutionary technology for indoor positioning in recent years. The proposed study intends to make use of both technologies by creating a hybrid indoor positioning system that uses VLC and Bluetooth together. The system first collects the initial location information based on VLC proximity, then collects the strongest Bluetooth signals to determine the receiver’s location using Bluetooth RSS (received signal strength) trilateration. This has been inspired by the fact that there have not been any studies that make use of both technologies with the same positioning algorithm, which can lead to pretty high accuracy of up to 0.03 m.
- Open Access
- 24 May 2023
- Published by Elsevier in Energy Reports
- Vol. 9, 5878-5898
Geospatial analysis of wind energy plant in Saudi Arabia using a GIS-AHP technique
- 24 May 2023
- Published by Elsevier in Energy Reports
- Vol. 9, 5878-5898
Open AccessGeospatial analysis of wind energy plant in Saudi Arabia using a GIS-AHP technique
- Open Access
- 29 September 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (9) , e0274452
Hybrid asset localization using light fidelity and Bluetooth Low Energy
Recently, there has been increasing interest in the field of indoor localization. This field of research can facilitate building and asset management. Although there are different technologies that can be used for localization, there are many limitations that need to be improved, and therefore there is a need to explore new technologies and alternatives that can improve indoor localization. It has been proven that visible light can be used to transfer data. A German physicist, Harald Haas, introduced the term “Li-Fi”, which stands for “light fidelity”, as a new technology that uses light as a medium to deliver data. Accordingly, in this study, we have proposed a hybrid asset localization system using Li-Fi and Bluetooth Low Energy (BLE). This system utilizes light-emitting diodes (LEDs) and BLE tags to detect the locations of assets in a smart building with the support of crowdsourcing technology. The system can make the management, maintenance, and localization process of equipment inside the buildings more easier. To achieve the required, the paper provides a comparison between different applications that have been developed for indoor localization using Li-Fi technology in order to highlight the limitations that need more improvement. The proposed system consists of a web-based administrator panel that allows the administrator to manage maps, assets, tags, LED lamps, and maintenance requests, as well as a mobile application that enables the user to locate, search and view asset information. In addition, the mobile application performs the process of crowdsourcing to update the assets’ locations. We experimentally explore the system’s functionalities and the results show that the system can accurately localize assets, and can detect Li-Fi signals from 55 lx and above within a range of 1.5 m. In addition, the BLE stickers can be detected up to 7 meters away, however, the crowdsourcing process to update the asset location is performed if the distance between the mobile application and the asset is less than or equal 1 m which gives accurate results.
- 29 September 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (9) , e0274452
Open AccessHybrid asset localization using light fidelity and Bluetooth Low Energy
Recently, there has been increasing interest in the field of indoor localization. This field of research can facilitate building and asset management. Although there are different technologies that can be used for localization, there are many limitations that need to be improved, and therefore there is a need to explore new technologies and alternatives that can improve indoor localization. It has been proven that visible light can be used to transfer data. A German physicist, Harald Haas, introduced the term “Li-Fi”, which stands for “light fidelity”, as a new technology that uses light as a medium to deliver data. Accordingly, in this study, we have proposed a hybrid asset localization system using Li-Fi and Bluetooth Low Energy (BLE). This system utilizes light-emitting diodes (LEDs) and BLE tags to detect the locations of assets in a smart building with the support of crowdsourcing technology. The system can make the management, maintenance, and localization process of equipment inside the buildings more easier. To achieve the required, the paper provides a comparison between different applications that have been developed for indoor localization using Li-Fi technology in order to highlight the limitations that need more improvement. The proposed system consists of a web-based administrator panel that allows the administrator to manage maps, assets, tags, LED lamps, and maintenance requests, as well as a mobile application that enables the user to locate, search and view asset information. In addition, the mobile application performs the process of crowdsourcing to update the assets’ locations. We experimentally explore the system’s functionalities and the results show that the system can accurately localize assets, and can detect Li-Fi signals from 55 lx and above within a range of 1.5 m. In addition, the BLE stickers can be detected up to 7 meters away, however, the crowdsourcing process to update the asset location is performed if the distance between the mobile application and the asset is less than or equal 1 m which gives accurate results.
- Open Access
- 21 July 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e1009
Towards smart sustainable cities using Li-Fi technology: geo-location infrastructure utilizing LED street lights
Background: Cities are shifting toward providing more efficient services and the Internet of Things (IoT) becoming the future of things. The shift toward using eco-friendlier LED lights in lighting cities is another genuine game-changer in the future of Light Fidelity technology (Li-Fi). Li-Fi is a visible light communication (VLC) technology that uses Light Emitting Diodes (LED) bulbs for communication. The utilisation of thousands of light sources around a city acting as wireless access points and delivering location-based content will shift cities towards being smart sustainable cities. Recently, this technology got huge attention from the research community and different research has been conducted to improve this filed. However, there is a noticeable need to develop real-world systems that utilise Li-Fi technology. Methods: This article aims to contribute to developing a Geo-Li-Fi system that uses LED lights to provide the services for collecting contextual data and delivering location-based services (LBS) in different areas of the city. The system is described along with details of its design, implementation and development. Moreover, the overall set-up of the testbed that used to evaluate the proposed system is presented. In addition, an experiment is conducted using a real-world scenario to test the functionality of the system and report the outputs. Results: The effect of the system is discussed according to different aspects of sustainability which include economic, social and environmental aspects. The system was tested in indoor and outdoor environments, and it can be seen that the sunlight does not affect the ability of LEDs to deliver the content during the daytime. Regarding the transmission range of the LED lamp, it can be seen that it is affected by different factors. It depends mainly on the power of lamp, so it will be increased significantly when the power of LED is increased. Also, an increase in the beam angle will result in wider coverage area which affected by the intensity.
- 21 July 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e1009
Open AccessTowards smart sustainable cities using Li-Fi technology: geo-location infrastructure utilizing LED street lights
Background: Cities are shifting toward providing more efficient services and the Internet of Things (IoT) becoming the future of things. The shift toward using eco-friendlier LED lights in lighting cities is another genuine game-changer in the future of Light Fidelity technology (Li-Fi). Li-Fi is a visible light communication (VLC) technology that uses Light Emitting Diodes (LED) bulbs for communication. The utilisation of thousands of light sources around a city acting as wireless access points and delivering location-based content will shift cities towards being smart sustainable cities. Recently, this technology got huge attention from the research community and different research has been conducted to improve this filed. However, there is a noticeable need to develop real-world systems that utilise Li-Fi technology. Methods: This article aims to contribute to developing a Geo-Li-Fi system that uses LED lights to provide the services for collecting contextual data and delivering location-based services (LBS) in different areas of the city. The system is described along with details of its design, implementation and development. Moreover, the overall set-up of the testbed that used to evaluate the proposed system is presented. In addition, an experiment is conducted using a real-world scenario to test the functionality of the system and report the outputs. Results: The effect of the system is discussed according to different aspects of sustainability which include economic, social and environmental aspects. The system was tested in indoor and outdoor environments, and it can be seen that the sunlight does not affect the ability of LEDs to deliver the content during the daytime. Regarding the transmission range of the LED lamp, it can be seen that it is affected by different factors. It depends mainly on the power of lamp, so it will be increased significantly when the power of LED is increased. Also, an increase in the beam angle will result in wider coverage area which affected by the intensity.
- Open Access
- 3 May 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (5) , 291
Geospatial Analysis of Solar Energy in Riyadh Using a GIS-AHP-Based Technique
In recent years, spatial multi-criteria decision analysis (MCDA) has been applied to different types of spatial problems, such as solar power site suitability. MCDA can be used to support the process of identifying suitable regions for solar energy projects. To the best of our knowledge, no study has addressed the problem of site evaluation for solar photovoltaic PV systems in the Riyadh region. Therefore, a spatial MCDA framework is proposed to perform a geospatial analysis of solar energy in the Riyadh region, which includes data collection, spatial analysis, a spatial decision support system and visualization. The methodology that was used to solve the site suitability problem is described. It involved the combination of a Geographical Information System (GIS) and the Analytic Hierarchy Process (GIS-AHP). The results show that the most suitable sites are in the north and northwest of the Riyadh region, with an area that represents 16,748 Km2 with an 80% suitability degree. In addition, it was proven that Afif is the largest suitable city. It has high solar radiation, at an average of 2.631687 MWh/m2/year, and low temperatures, at an average of 26.3 °C, as well as having flat areas with a slope under 5°. The results were validated using a sensitivity analysis model and also compared with those for ground-based stations.
- 3 May 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (5) , 291
Open AccessGeospatial Analysis of Solar Energy in Riyadh Using a GIS-AHP-Based Technique
In recent years, spatial multi-criteria decision analysis (MCDA) has been applied to different types of spatial problems, such as solar power site suitability. MCDA can be used to support the process of identifying suitable regions for solar energy projects. To the best of our knowledge, no study has addressed the problem of site evaluation for solar photovoltaic PV systems in the Riyadh region. Therefore, a spatial MCDA framework is proposed to perform a geospatial analysis of solar energy in the Riyadh region, which includes data collection, spatial analysis, a spatial decision support system and visualization. The methodology that was used to solve the site suitability problem is described. It involved the combination of a Geographical Information System (GIS) and the Analytic Hierarchy Process (GIS-AHP). The results show that the most suitable sites are in the north and northwest of the Riyadh region, with an area that represents 16,748 Km2 with an 80% suitability degree. In addition, it was proven that Afif is the largest suitable city. It has high solar radiation, at an average of 2.631687 MWh/m2/year, and low temperatures, at an average of 26.3 °C, as well as having flat areas with a slope under 5°. The results were validated using a sensitivity analysis model and also compared with those for ground-based stations.
- Open Access
- 19 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 40811-40825
Toward Designing a Li-Fi-Based Hierarchical IoT Architecture
Current wireless communication technologies such as wireless-fidelity (Wi-Fi) and Bluetooth use radio waves as the basic medium in transferring information. Even though these technologies are widely spread, the need of exploring alternatives to transmit data wirelessly and more efficiently is a must. The reason behind that relies on the current limitations of the radio frequency (RF) band, which include overcrowding and interference with other RF applications. To explore alternatives, much research has been conducted to prove the possibility of using visible light as a wireless medium for transferring data. As a result, a new technology was presented by a German physicist Harald Haas, called light-fidelity (Li-Fi), which is a wireless technology that utilizes visible light as a communication medium instead of using the basic radio wave. Recently, Li-Fi technology has attracted the research community. Various studies have been conducted to improve the technology. However, there is still a noticeable need to support the research field due the modernity of the technology. Hence, this paper presents an extensive survey of the previous studies and projects conducted on the technology, besides multiple leading companies working on the manufacture of Li-Fi-compatible products. In addition, a Li-Fi-based IoT architecture is proposed in this paper, which relies on the collection of data from multiple environments where Li-Fi is installed. Li-Fi-generated data are analyzed and processed to make intelligent decisions to enhance services in many sectors.
- 19 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 40811-40825
Open AccessToward Designing a Li-Fi-Based Hierarchical IoT Architecture
Current wireless communication technologies such as wireless-fidelity (Wi-Fi) and Bluetooth use radio waves as the basic medium in transferring information. Even though these technologies are widely spread, the need of exploring alternatives to transmit data wirelessly and more efficiently is a must. The reason behind that relies on the current limitations of the radio frequency (RF) band, which include overcrowding and interference with other RF applications. To explore alternatives, much research has been conducted to prove the possibility of using visible light as a wireless medium for transferring data. As a result, a new technology was presented by a German physicist Harald Haas, called light-fidelity (Li-Fi), which is a wireless technology that utilizes visible light as a communication medium instead of using the basic radio wave. Recently, Li-Fi technology has attracted the research community. Various studies have been conducted to improve the technology. However, there is still a noticeable need to support the research field due the modernity of the technology. Hence, this paper presents an extensive survey of the previous studies and projects conducted on the technology, besides multiple leading companies working on the manufacture of Li-Fi-compatible products. In addition, a Li-Fi-based IoT architecture is proposed in this paper, which relies on the collection of data from multiple environments where Li-Fi is installed. Li-Fi-generated data are analyzed and processed to make intelligent decisions to enhance services in many sectors.