Muhammad Shahbaz Khan

Mr. Muhammad Shahbaz Khan

Edinburgh Napier University, Edinburgh, City of Edinburgh, UK
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Muhammad UmairMuhammad Umair
Muhammad Umair
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
FAFawad Ahmed
Fawad Ahmed
FBFatmah Baothman
Fatmah Baothman
FAFehaid Alqahtani
Fehaid Alqahtani
Jawad AhmadJawad Ahmad
Jawad Ahmad
The COVID-19 outbreak began in December 2019 and has dreadfully affected our lives since then. More than three million lives have been engulfed by this newest member of the corona virus family. With the emergence of continuously mutating variants of this virus, it is still indispensable to successfully diagnose the virus at early stages. Although the primary technique for the diagnosis is the PCR test, the non-contact methods utilizing the chest radiographs and CT scans are always preferred. Artificial intelligence, in this regard, plays an essential role in the early and accurate detection of COVID-19 using pulmonary images. In this research, a transfer learning technique with fine tuning was utilized for the detection and classification of COVID-19. Four pre-trained models i.e., VGG16, DenseNet-121, ResNet-50, and MobileNet were used. The aforementioned deep neural networks were trained using the dataset (available on Kaggle) of 7232 (COVID-19 and normal) chest X-ray images. An indigenous dataset of 450 chest X-ray images of Pakistani patients was collected and used for testing and prediction purposes. Various important parameters, e.g., recall, specificity, F1-score, precision, loss graphs, and confusion matrices were calculated to validate the accuracy of the models. The achieved accuracies of VGG16, ResNet-50, DenseNet-121, and MobileNet are 83.27%, 92.48%, 96.49%, and 96.48%, respectively. In order to display feature maps that depict the decomposition process of an input image into various filters, a visualization of the intermediate activations is performed. Finally, the Grad-CAM technique was applied to create class-specific heatmap images in order to highlight the features extracted in the X-ray images. Various optimizers were used for error minimization purposes. DenseNet-121 outperformed the other three models in terms of both accuracy and prediction.

17 June 2024 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
Jawad AhmadJawad Ahmad
Jawad Ahmad
AAAhmed Al-Dubai
Ahmed Al-Dubai
Nikolaos PitropakisNikolaos Pitropakis
Nikolaos Pitropakis
Baraq GhalebBaraq Ghaleb
Baraq Ghaleb
William Johnston BuchananWilliam Johnston Buchanan
William Johnston Buchanan
The rapid advancement in consumer technology has led to an exponential increase in the connected devices, resulting in an enormous and continuous flow of data, particularly the image data. This data needs to be processed, managed, and secured efficiently, especially in the quantum-enabled consumer technology era. This paper, in this regards, presents a quantum image encryption scheme featuring a novel two-phase chaotic confusion-diffusion architecture. The proposed architecture consists of four distinct confusion-diffusion modules that perform a simultaneous qubit and pixel-level encryption on both the position and intensity of quantum encoded pixels. Moreover, quantum circuits for ’qubit-level chaotic transformation’ and ’chaos-based selective perfect shuffle operation’ have been implemented, which collectively enhance the encryption strength of the proposed scheme. Extensive evaluation has been performed based on various statistical security parameters, such as entropy and correlation. When subjected to differential attacks, the proposed scheme proved its resilience exhibiting ideal results of average 99.6% NPCR (Number of Pixels Change Rate) and 33.5% UACI (Unified Average Changing Intensity). Besides, the proposed scheme also demonstrated resilience against occlusion attacks. Tests involving 50% data occlusion from encrypted images validated the proposed scheme’s capability to successfully decrypt the tampered images, recovering maximum information.

25 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
FAFawad Ahmed
Fawad Ahmed
MRMuneeb Ur Rehman
Muneeb Ur Rehman
Jawad AhmadJawad Ahmad
Jawad Ahmad
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
Wadii BoulilaWadii Boulila
Wadii Boulila
William Johnston BuchananWilliam Johnston Buchanan
William Johnston Buchanan
With the advancement in technology, digital images can easily be transmitted and stored over the Internet. Encryption is used to avoid illegal interception of digital images. Encrypting large-sized colour images in their original dimension generally results in low encryption/decryption speed along with exerting a burden on the limited bandwidth of the transmission channel. To address the aforementioned issues, a new encryption scheme for colour images employing convolutional autoencoder, DNA and chaos is presented in this paper. The proposed scheme has two main modules, the dimensionality conversion module using the proposed convolutional autoencoder, and the encryption/decryption module using DNA and chaos. The dimension of the input colour image is first reduced from N × M × 3 to P × Q gray-scale image using the encoder. Encryption and decryption are then performed in the reduced dimension space. The decrypted gray-scale image is upsampled to obtain the original colour image having dimension N × M × 3 . The training and validation accuracy of the proposed autoencoder is 97% and 95%, respectively. Once the autoencoder is trained, it can be used to reduce and subsequently increase the dimension of any arbitrary input colour image. The efficacy of the designed autoencoder has been demonstrated by the successful reconstruction of the compressed image into the original colour image with negligible perceptual distortion. The second major contribution presented in this paper is an image encryption scheme using DNA along with multiple chaotic sequences and substitution boxes. The security of the proposed image encryption algorithm has been gauged using several evaluation parameters, such as histogram of the cipher image, entropy, NPCR, UACI, key sensitivity, contrast, and so on. The experimental results of the proposed scheme demonstrate its effectiveness to perform colour image encryption.

16 August 2022 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
SASanam Aamir
Sanam Aamir
ARAqsa Rahim
Aqsa Rahim
ZAZain Aamir
Zain Aamir
SASaadullah Farooq Abbasi
Saadullah Farooq Abbasi
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
Jawad AhmadJawad Ahmad
Jawad Ahmad
Breast cancer is one of the leading causes of increasing deaths in women worldwide. The complex nature (microcalcification and masses) of breast cancer cells makes it quite difficult for radiologists to diagnose it properly. Subsequently, various computer-aided diagnosis (CAD) systems have previously been developed and are being used to aid radiologists in the diagnosis of cancer cells. However, due to intrinsic risks associated with the delayed and/or incorrect diagnosis, it is indispensable to improve the developed diagnostic systems. In this regard, machine learning has recently been playing a potential role in the early and precise detection of breast cancer. This paper presents a new machine learning-based framework that utilizes the Random Forest, Gradient Boosting, Support Vector Machine, Artificial Neural Network, and Multilayer Perception approaches to efficiently predict breast cancer from the patient data. For this purpose, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset has been utilized and classified using a hybrid Multilayer Perceptron Model (MLP) and 5-fold cross-validation framework as a working prototype. For the improved classification, a connection-based feature selection technique has been used that also eliminates the recursive features. The proposed framework has been validated on two separate datasets, i.e., the Wisconsin Prognostic dataset (WPBC) and Wisconsin Original Breast Cancer (WOBC) datasets. The results demonstrate improved accuracy of 99.12% due to efficient data preprocessing and feature selection applied to the input data.

2 July 2025 in Internet of Things
Verified
Journal Article
Closed access
Jawad AhmadJawad Ahmad
Jawad Ahmad
Shahid LatifShahid Latif
Shahid Latif
IKImdad Ullah Khan
Imdad Ullah Khan
MAMohammed Alshehri
Mohammed Alshehri
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
Weiwei JiangWeiwei Jiang
Weiwei Jiang

19 February 2021
Verified
Conference Paper
Closed access
HTHassam Tahir
Hassam Tahir
Muhammad Shahbaz KhanMuhammad Shahbaz Khan
Muhammad Shahbaz Khan
MTMuhammad Owais Tariq
Muhammad Owais Tariq
Traffic congestion is one of the major issues of urban cities. The conventional techniques used usually to control traffic via different types of sensors are less precise and expensive. Intelligent solutions using deep learning algorithms provide promising results in terms of better performance, prompt decision making and cost effectiveness. This article aims at providing an easy, more accurate and less expensive solution for the traffic control issues specifically at the traffic signals. Three deep neural network (DNN) frameworks i.e. Faster R-CNN, Mask R-CNN and ResNet-50 have been implemented and compared for vehicle detection, classification and counting. A dataset of 3200 images of different vehicles is used for the training of the models. The training is carried out on NVIDIA 1060TI 3GB GPU. Trained system is tested on indigenous recorded video data of 8 hours for two routes at a traffic signal. Results demonstrated that the overall detection accuracy of Faster R-CNN and Mask R-CNN is >80%, whereas detection accuracy of ResNet-50 is >75%. The counting accuracies of Faster R-CNN, Mask R-CNN and ResNet-50 are >75%, >70% and >62% respectively. Various error analysis have been carried out to validate the performance of the aforementioned frameworks. Furthermore, a prototype has also been developed by interconnecting the DNN results with Arduino via Serial communication.