AUS Repository (American University of Sharjah)
Not a member yet
2669 research outputs found
Sort by
Detection of Traffic Incidents Using Machine Learning Techniques
No full textA Doctor of Philosophy Dissertation in Engineering Systems Management by Osama Mohamed ElSahly entitled, “Detection of Traffic Incidents Using Machine Learning Techniques”, submitted in April 2023. Dissertation advisor is Dr. Akmal Abdelfatah. Soft copy is available (Dissertation, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).This dissertation proposes new models for detecting traffic incidents on freeways using machine learning algorithms to classify traffic data collected from the freeway system. These models are generic and consider multiple factors that affect incident detectability simultaneously. The models were trained and tested on simulated traffic data that represent normal and incident conditions using the well-known microsimulation software VISSIM. The proposed models, which include the Random Forest (RF) and Multilayer Feedforward Artificial Neural Network (MLF), consider four factors: the congestion level, the distance between the upstream and downstream detector stations, the location of the incident relative to the detector stations, and the severity of the incident. The results showed that the developed models achieved excellent performance, surpassing existing models in the literature. During training, the MLF model achieved a detection rate (DR) of 95.96%, a mean time to detect (MTTD) of 0.89 minutes, and a false alarm rate (FAR) of 1.01%. During testing, the MLF model achieved a DR of 100%, MTTD of 1.6 minutes, and FAR of 1.29%. Similarly, the RF model achieved a DR of 96.97%, MTTD of 1.05 minutes, and FAR of 0.62% during training, and a DR of 100%, MTTD of 1.17 minutes, and FAR of 0.862% during testing. The results revealed that incident detection systems may have difficulty detecting incidents with minor severity during low traffic volumes. The FAR decreased with the increase in the Demand to Capacity ratio (D/C), while the MTTD increased with the increase in D/C. Additionally, higher incident severity resulted in lower MTTD values, while the distance between the incident location and upstream detector had the opposite effect. The FAR decreased as the incident moved farther from the upstream detector but increased with the distance between detectors. Larger detector spacings were associated with longer detection times. The proposed models can significantly improve traffic performance on freeways, especially during incidents, and benefit both local and international transportation agencies. The study's contribution lies in developing efficient and reliable incident detection models that consider multiple variables simultaneously, improving traffic safety, reducing congestion, saving lives and properties, and reducing pollution.College of EngineeringDepartment of Industrial EngineeringPhD in Engineering - Engineering Systems Management (PhD-ESM
Nanoparticle-based materials in anticancer drug delivery: Current and future prospects
No full textThe past decade has witnessed a breakthrough in novel strategies to treat cancer. One of the most common cancer treatment modalities is chemotherapy which involves administering anti-cancer drugs to the body. However, these drugs can lead to undesirable side effects on healthy cells. To overcome this challenge and improve cancer cell targeting, many novel nanocarriers have been developed to deliver drugs directly to the cancerous cells and minimize effects on the healthy tissues. The majority of the research studies conclude that using drugs encapsulated in nanocarriers is a much safer and more effective alternative than delivering the drug alone in its free form. This review provides a summary of the types of nanocarriers mainly studied for cancer drug delivery, namely: liposomes, polymeric micelles, dendrimers, magnetic nanoparticles, mesoporous nanoparticles, gold nanoparticles, carbon nanotubes and quantum dots. In this review, the synthesis, applications, advantages, disadvantages, and previous studies of these nanomaterials are discussed in detail. Furthermore, the future opportunities and possible challenges of translating these materials into clinical applications are also reported.Qatar National Librar
Acoustically-Activated Liposomal Nanocarriers to Mitigate the Side Effects of Conventional Chemotherapy with a Focus on Emulsion-Liposomes
No full textTo improve currently available cancer treatments, nanomaterials are employed as smart drug delivery vehicles that can be engineered to locally target cancer cells and respond to stimuli. Nanocarriers can entrap chemotherapeutic drugs and deliver them to the diseased site, reducing the side effects associated with the systemic administration of conventional anticancer drugs. Upon accumulation in the tumor cells, the nanocarriers need to be potentiated to release their therapeutic cargo. Stimulation can be through endogenous or exogenous modalities, such as temperature, electromagnetic irradiation, ultrasound (US), pH, or enzymes. This review discusses the acoustic stimulation of different sonosensitive liposomal formulations. Emulsion liposomes, or eLiposomes, are liposomes encapsulating phase-changing nanoemulsion droplets, which promote acoustic droplet vaporization (ADV) upon sonication. This gives eLiposomes the advantage of delivering the encapsulated drug at low intensities and short exposure times relative to liposomes. Other formulations integrating microbubbles and nanobubbles are also discussed.Dana Gas Endowed Chair for Chemical EngineeringAmerican University of SharjahSheikh Hamdan Award for Medical SciencesFriends of Cancer Patients (FoCP
A Study of the Impact of the Climate and Land-use/Land-cover (LULC) Changes on the UAE Mangrove Forests over the Period 1990-2020
No full textA Master of Science thesis in Civil Engineering by Asif Raihan entitled, “A Study of the Impact of the Climate and Land-use/Land-cover (LULC) Changes on the UAE Mangrove Forests over the Period 1990-2020”, submitted in June 2023. Thesis advisor is Dr. Tarig Ali and thesis co-advisor is Dr. Md. Maruf Mortula. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Mangroves are integral part of coastal ecosystem, demonstrating resiliency against adverse anthropogenic and environmental effects. They provide blue carbon stock and security against coastal erosion and act as a nutrient source for many aquatic inhabitants along with providing raw materials for human consumption. However, mangroves continue to perish due to climate factors and land-use/land-cover (LULC) changes. Past research has indicated some environmental factors influencing the growth and sustenance of mangrove forests. This thesis aims at studying the impact of the climate and LULC changes on the UAE mangrove forests during the period 1990-2020. The studied climate change related factors include surface temperature, sea-level rise, salinity, and coastal inundation. LULC changes were assessed by creating LULC maps over the period of study through supervised classifications of Landsat images. Then, remote sensing techniques and supervised machine learning methods were utilized to derive the climatic factors. The correlations between mangrove and these factors were investigated. Finally, forest-based classification and regression analysis was conducted to study the impact of land surface temperature, vegetation extent, slope, and salinity on mangrove biomass. It was found that Land Surface Temperature is closely related to mangrove and that mangrove biomass was highest in the land surface temperature range 30-35 °C. LULC changes showed a positive correlation with total vegetation cover (i.e., including mangrove) in terms of area. Results have not shown clear correlation between tidal inundation and mangrove. Furthermore, results showed that mangrove biomass was negatively affected by sea-level rise. In the study area, analysis showed that mangroves tended to thrive in flat slope (e.g., around 2%). The analysis results showed a general positive relationship between mangrove and salinity corresponding to increase in mangrove biomass, however site-specific analysis showed an increase in mangrove density with decrease in salinity. A model with coefficient of determination is 0.85 is developed in this thesis for the relationship between land surface temperature, slope, salinity, and mangroves using random forest classification and regression analysis.College of EngineeringDepartment of Civil EngineeringMaster of Science in Civil Engineering (MSCE
Smart Farming Using Artificial Intelligence and IoT
No full textA Master of Science thesis in Mechatronics Engineering by Lina Adnan Al Barri entitled, “Smart Farming Using Artificial Intelligence and IoT”, submitted in August 2023. Thesis advisor is Dr. Shayok Mukhopadhyay and thesis co-advisor is Dr Abdulrahman Al-Ali. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).College of EngineeringMultidisciplinary ProgramsMaster of Science in Mechatronics Engineering (MSMTR
Machine Learning Model for a Sustainable Drilling Process
No full textA Master of Science thesis in Engineering Systems Management by Ola Alsaidi entitled, “Machine Learning Model for a Sustainable Drilling Process”, submitted in November 2023. Thesis advisor is Dr. Noha Hussein. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).Drilling process is one of the most performed machining processes. Across many industries, drilling process directly influences the product quality as it is usually used in the final production steps before assembly. Drilling quality depends on the process parameters such as the spindle speed and feed. Improper selection of these parameters can lead to several defects like high surface roughness and burr formation. Consequently, the final product will not function properly, resulting in higher wastage of material, cost, and time. Additionally, reworking results in the loss of many resources. From a sustainability point of view, rework has a negative environmental impact as it increases electricity consumption and carbon emissions. Thus, the optimization of drilling process parameters is essential to produce high-quality products and make the process more cost-effective, efficient, and sustainable. Many experiments have been done to model the drilling process responses in terms of the input parameters. As a result, there is large amount of data available in the literature for drilling input parameters and their responses. This project aims to use big data analytics to make use of the data gathered from previous studies to model and optimize the responses. The collected data have some missing values because of the different input parameters and responses chosen for each experiment. To handle these missing values, deletion and imputation methods are used. For data analysis, various machine learning algorithms are used to model the process responses. The analysed responses are the surface roughness, thrust force, and drilling time. Further analyses are done including features selection and partial dependence. Moreover, several optimization runs are performed to assess different drilling cases. According to the results, the best algorithms for predicting the surface roughness, thrust force, and drilling time are bagged trees with 6 parameters, exponential GPR with 6 parameters, and fine trees with 5 parameters, respectively. The obtained accuracies are 92.91% for the surface roughness model, 81.33% for the thrust force model, and 90.61% for the time model. The obtained models can be used to find the optimal values of the input parameters that will give the minimum surface roughness, thrust force, or time without the need to conduct any experiments which leads to time, money, and resources savings.College of EngineeringDepartment of Industrial EngineeringMaster of Science in Engineering Systems Management (MSESM
Comparison of shear behavior of normal and recycled aggregates beams strengthened with CFRP U-Wraps
No full textIn recent years recycled aggregates, from construction demolition waste, has been used as a replacement to normal (natural) aggregates in concrete. This is to preserve the depletion of natural resources and to further reduce carbon footprints in terms of energy depletion and waste disposition. Mechanical properties, such as compressive and tensile strengths, of recycled aggregates concrete (RAC) have been investigated by several researchers and were compared with that of normal aggregate concrete (NAC). In this investigation, the shear strengths and modes of failure of RAC and NAC beams have been investigated. In addition, the behavior of RAC and NAC beams strengthened with carbon-fiber-reinforced-polymer (CFRP) U-wrapped laminates have been examined. Four RAC and NAC shear-deficient rectangular beams were cast, two of which were strengthened in shear with CFRP U-wraps. The beams were tested to failure under four-point bending. The test results indicate that the shear capacity of all specimens strengthened with CFRP composites increased significantly compared to the control beam specimens. The performance of the RAC and NAC beams before and after strengthening were compared. It was observed that the RAC specimens provided similar shear strength as that of the NAC beams. The percentage increase in the shear capacity of RAC beams reached almost 60% of the control beam for the beams with U-wraps. The ACI 318-19 and ACI440.2R-17 codes are also used to predict the shear strength of the tested RAC and NAC beams and it was observed that the predicted capacities were close to the experimentally measured ones.Riad Sadek Endowed Chair in Civil Engineering at the American University of SharjahMAPEIChemcreteEmirates Recycling LL
IoT-Based Sustainable Parking Lot
No full textThis paper aims to eliminate the loophole that unregistered vehicles abuse to avoid fines and park illegally by devolving an IoT-based smart parking access control system. The proposed system utilizes a single-board computer with a set of sensors, cameras and actuators. The access control system employs a combination of vehicle detection and plate recognition algorithms to identify and authenticate vehicles entering and exiting the parking lot. Moreover, a carbon emissions sensor at the gate is used to detect the generated emission rates by vehicles entering the parking lot. Furthermore, deep learning neural network was used to predict the congestion of the parking lot at any day or time. Moreover, a website was developed to enable administrators and users to access and interact with the system. Experimental results showed that the system was able to perform the functionality with high accuracy. The coefficient of determination (R²) achieved of the car congestion prediction module was 0.97. A survey was conducted to measure the users’ satisfaction with the proposed system. The survey results indicated that the majority of respondents (90.6%) reported an overall positive attitude towards the user interface and expressed their satisfaction with the system. The benefits of this work include the well-being and convenience of the paying participants in addition to tremendously reducing the workload required of the parking security guards and creating a more environmentally friendly parking lot. The proposed system can be utilized in public parking, residential towers and compounds, and shopping malls.American Iniversity of Sharja
A machine learning approach on chest X-rays for pediatric pneumonia detection
No full textAccording to the World Health Organization (WHO), pneumonia is the leading infectious cause of death in children below 5 years old. Hence, the early detection of pediatric pneumonia is crucial to reduce its morbidity and mortality rates. Even though chest radiography is the most commonly employed modality for pneumonia detection, recent studies highlight the existence of poor interobserver agreement in the chest X-ray interpretation of healthcare practitioners when it comes to diagnosing pediatric pneumonia. Thus, there is a significant need for automating the detection process to minimize the potential human error. Since Artificial Intelligence tools such as Deep Learning (DL) and Machine Learning (ML) have the potential to automate disease detection, many researchers explored how such tools can be implemented to detect pneumonia in chest X-rays. Notably, the majority of efforts tackled this problem from a DL point of view. However, ML has shown a higher potential for medical interpretability while being less computationally demanding than DL.American University of Sharja