Electrical Engineering
http://hdl.handle.net/10576/3337
2024-03-28T21:00:19ZReal-time Imitation of Autonomous MCG Node using Dual ECG Probing IoT Node Suitable for Delivery by UAV
http://hdl.handle.net/10576/53524
Real-time Imitation of Autonomous MCG Node using Dual ECG Probing IoT Node Suitable for Delivery by UAV
Tariq, Hasan; Abualsaud, Khalid; Yaacoub, Elias; Abualsaud, Rana; Khattab, Tamer; Gehani, Abdurrazzak
The gigantic increase in population, social isolation, and mobility constraint lifestyle since the COVID-19 era has resulted in challenges like remote availability of critical bio-instrumentation like magnetocardiography (MCG) and electrocardiography (ECG). This availability can only be made possible through portable hand-held bio-instrumentation systems. Unmanned aerial vehicles (UAVs) can be used to deliver these systems to remote areas. In cardiological bioinstrumentation, MCG and ECG are two major innovations-based field effect techno-scientific approaches. The MCG systems face several major challenges that have hampered their applications and utility for cardio patients and their inspection labs. In this work, the main challenges were addressed by using a novel ML-based probabilistic interpolation algorithm over a dual ECG probing system-on-chip (SoC) with IoT capabilities to generate the identical MCG signal from two ECG signals with a segmented translation of PR, QRS, ST, and QT characteristic patches at real-time. The implementation findings provided a rich resource for approximating wave-shaping filters, frequencies, mean, and variance whilst addressing redundancy.
2023-01-01T00:00:00ZNovel Task Allocation Method for Emergency Events under Delay-Cost Tradeoff
http://hdl.handle.net/10576/53529
Novel Task Allocation Method for Emergency Events under Delay-Cost Tradeoff
Aboualola, Mohamed; Abualsaud, Khalid; Khattab, Tamer; Zorba, Nizar
With the emergence of three new paradigms, namely the Internet of Things (IoT), cloud/edge computing and mobile social networks; Mobile Crowd Sensing (MCS) has emerged as a potential approach for data collecting in numerous applications, such as traffic management, infotainment, disaster management or public safety. MCS mechanisms are receiving a lot of attention, both from research and development areas, showing their impact and benefit. But their optimization is still under development, mainly due to the large number of involved parameters. A major field within MCS relates to crowd management for emergency situations, where the management and optimization mechanisms become crucial to local authorities. To tackle this problem, in this work, we propose an MCS hybrid worker selection scheme that operated various modes depending on the delay-cost requirements. Our scheme exploits the user behavior to achieve an optimal bi-objective for any delay-cost requirement. We use simulations to evaluate the performance of our proposal, and we show the optimal and different sub-optimal solutions that can match the delay-cost requirements.
2022-01-01T00:00:00ZIndoor Multi-Lingual Scene Text Database with Different Views
http://hdl.handle.net/10576/53522
Indoor Multi-Lingual Scene Text Database with Different Views
Akbari, Younes; Kunhoth, Jayakanth; Elharrouss, Omar; Al-Maadeed, Somaya; Abualsaud, Khalid; Mohamed, Amr; Khattab, Tamer
This paper introduces a database of multi-script (Arabic and English) for indoor scene text detection, taken from different angle-of-view. This database can be used in a variety of real-world applications, such as image search, robot navigation, and assisting the visually impaired. The database contains 944 images taken with smartphones in an indoor environment at Qatar University. These images were taken from at least three angles, making the database even more challenging. To evaluate the database, an OCR method based on multiple language detection is considered. The results show that multi-language detection should be given more attention in practice. The database is publicly available. https:/www.dropbox.com/s/7s7f936y4etzsu7/QU-door-dataset%20%282%29.zip?dl=0.
2023-01-01T00:00:00ZThe utility of a deep learning-based approach in Her-2/neu assessment in breast cancer
http://hdl.handle.net/10576/53087
The utility of a deep learning-based approach in Her-2/neu assessment in breast cancer
Saidul, Kabir; Vranic, Semir; Mahmood Al Saady, Rafif; Salman Khan, Muhammad; Sarmun, Rusab; Alqahtani, Abdulrahman; Abbas, Tariq O.; Chowdhury, Muhammad E.H.
IntroductionHER-2/neu is a protein present on the surface of specific cancer cells and has been linked to the development and progression of certain cancer types. It is present in 15 to 20% of breast cancers and is clinically significant due to the availability of multiple anti-Her2 treatment options. Immunohistochemistry (IHC) is the most commonly used method to evaluate and quantify the expression of Her-2/neu. Although IHC is well-standardized in clinical practice, it is still subjected to inter-observer variability. Automating Her-2/neu scoring can improve accuracy, efficiency, consistency, and cost-effectiveness while reducing pathologists' workload. Materials and MethodsA deep learning-based automatic framework was utilized for the automatic detection of Her-2/neu score from whole slide images (WSI). The framework consists of three phases: identification of tumor patches, scoring of tumor patches, and Her-2/neu score prediction for whole slide images (WSI) based on the distribution of each score. This work used the dataset from the University of Warwick HER2 challenge contest. Two expert pathologists evaluated all 86 WSIs and assigned Her-2/neu scores to them. In addition, patches were generated from 50 WSIs and annotated individually by the pathologists. A total of 6641 extracted patches were generated out of which, 947 were labeled as 0, 327 as 1+, 1401 as 2+, 2950 as 3+, and 1016 were marked for discarding. Four pre-trained image classification models, namely DenseNet201, GoogleNet, MobileNet_v2, and a Vision Transformer based model, were fine-tuned, and tested on the generated patches. In order to predict the Her-2/neu score of the entire WSI, a random forest classifier was trained to predict the Her-2/neu score from the percentages of patches of each score present in the whole slide image. ResultsIn patch classification performances, the vision transformer-based model outperformed the other models by achieving an accuracy of 92.6% on tumor patch classification and 91.15% on patch score classification. The random forest classifier achieved an accuracy of 88% on four score classification (0, 1+, 2 + and 3 + ) and 96% on three score classification (0/1+, 2 + and 3 + ). ConclusionThe proposed deep learning-based framework for the automatic detection and evaluation of Her-2/neu expression in breast cancer obtained encouraging results. This framework has the potential to be used as a prognostic tool, providing a cost-effective and time-efficient alternative for generating clinically relevant results. However, additional research is required to assess the applicability of this pipeline in different contexts.
2023-10-07T00:00:00Z