Qazi Mudassar Ilyas

Dr. Qazi Mudassar Ilyas

King Faisal University, Al Hufūf, Ash Sharqīyah, Saudi Arabia
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
14 May 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
ASAyesha Shoukat
Ayesha Shoukat
SAShahzad Akbar
Shahzad Akbar
Syed Ale HassanSyed Ale Hassan
Syed Ale Hassan
SISajid Iqbal
Sajid Iqbal
Abid MehmoodAbid Mehmood
Abid Mehmood
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
Glaucoma is characterized by increased intraocular pressure and damage to the optic nerve, which may result in irreversible blindness. The drastic effects of this disease can be avoided if it is detected at an early stage. However, the condition is frequently detected at an advanced stage in the elderly population. Therefore, early-stage detection may save patients from irreversible vision loss. The manual assessment of glaucoma by ophthalmologists includes various skill-oriented, costly, and time-consuming methods. Several techniques are in experimental stages to detect early-stage glaucoma, but a definite diagnostic technique remains elusive. We present an automatic method based on deep learning that can detect early-stage glaucoma with very high accuracy. The detection technique involves the identification of patterns from the retinal images that are often overlooked by clinicians. The proposed approach uses the gray channels of fundus images and applies the data augmentation technique to create a large dataset of versatile fundus images to train the convolutional neural network model. Using the ResNet-50 architecture, the proposed approach achieved excellent results for detecting glaucoma on the G1020, RIM-ONE, ORIGA, and DRISHTI-GS datasets. We obtained a detection accuracy of 98.48%, a sensitivity of 99.30%, a specificity of 96.52%, an AUC of 97%, and an F1-score of 98% by using the proposed model on the G1020 dataset. The proposed model may help clinicians to diagnose early-stage glaucoma with very high accuracy for timely interventions.

18 December 2020 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
MAMuneer Ahmad
Muneer Ahmad
The farmers of agricultural farms manage and monitor different types of livestock. The manual inspection and monitoring of livestock are tedious since the cattle do not stay at fixed locations. Fencing many cattle requires a considerable cost and involves farmers’ physical intervention to keep an eye to stop them from crossing beyond the access points. Visual tracking of livestock and fencing is a time-consuming and challenging job. This research proposes a smart solution for livestock tracking and geofencing using state-of-the-art IoT technology. The study creates a geographical safe zone for cattle based on IoT and GPRS, where the cattle are assigned dedicated IoT sensors. The cattle can be easily remotely monitored and controlled without having any need for farmers to intervene for livestock management physically. The smart system collects the data regarding the location, well-being, and health of the livestock. This kind of livestock management may help prevent the spread of COVID-19, lower the farming costs, and enable remote monitoring.

17 January 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
MAMuneer Ahmad
Muneer Ahmad
Abid MehmoodAbid Mehmood
Abid Mehmood
Agriculture is the backbone of any country, and plays a viable role in the total gross domestic product (GDP). Healthy and fruitful crops are of immense importance for a government to fulfill the food requirements of its inhabitants. Because of land diversities, weather conditions, geographical locations, defensive measures against diseases, and natural disasters, monitoring crops with human intervention becomes quite challenging. Conventional crop classification and yield estimation methods are ineffective under unfavorable circumstances. This research exploits modern precision agriculture tools for enhanced remote crop yield estimation, and types classification by proposing a fuzzy hybrid ensembled classification and estimation method using remote sensory data. The architecture enhances the pooled images with fuzzy neighborhood spatial filtering, scaling, flipping, shearing, and zooming. The study identifies the optimal weights of the strongest candidate classifiers for the ensembled classification method adopting the bagging strategy. We augmented the imagery datasets to achieve an unbiased classification between different crop types, including jute, maize, rice, sugarcane, and wheat. Further, we considered flaxseed, lentils, rice, sugarcane, and wheat for yield estimation on publicly available datasets provided by the Food and Agriculture Organization (FAO) of the United Nations and the Word Bank DataBank. The ensemble method outperformed the individual classification methods for crop type classification on an average of 13% and 24% compared to the highest gradient boosting and lowest decision tree methods, respectively. Similarly, we observed that the gradient boosting predictor outperformed the multivariate regressor, random forest, and decision tree regressor, with a comparatively lower mean square error value on yield years 2017 to 2021. Further, the proposed architecture supports embedded devices, where remote devices can adopt a lightweight classification algorithm, such as MobilenetV2. This can significantly reduce the processing time and overhead of a large set of pooled images.

13 July 2023 in Cancers
Verified
Journal Article
Open access
PDF file
Abid MehmoodAbid Mehmood
Abid Mehmood
Yonis GulzarYonis Gulzar
Yonis Gulzar
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
AJABDOH JABBARI
ABDOH JABBARI
MAMuneer Ahmad
Muneer Ahmad
SISajid Iqbal
Sajid Iqbal
Skin cancer is a major public health concern around the world. Skin cancer identification is critical for effective treatment and improved results. Deep learning models have shown considerable promise in assisting dermatologists in skin cancer diagnosis. This study proposes SBXception: a shallower and broader variant of the Xception network. It uses Xception as the base model for skin cancer classification and increases its performance by reducing the depth and expanding the breadth of the architecture. We used the HAM10000 dataset, which contains 10,015 dermatoscopic images of skin lesions classified into seven categories, for training and testing the proposed model. Using the HAM10000 dataset, we fine-tuned the new model and reached an accuracy of 96.97% on a holdout test set. SBXception also achieved significant performance enhancement with 54.27% fewer training parameters and reduced training time compared to the base model. Our findings show that reducing and expanding the Xception model architecture can greatly improve its performance in skin cancer categorization.

18 April 2025 in IEEE Access
Verified
Journal Article
Open access
Muhammad AkramMuhammad Akram
Muhammad Akram
Sibghat Ullah BazaiSibghat Ullah Bazai
Sibghat Ullah Bazai
MGMuhammad Imran Ghafoor
Muhammad Imran Ghafoor
SASaira Akram
Saira Akram
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
MRMuhammad Asim Rafique
Muhammad Asim Rafique
Wireless Sensor Networks (WSNs) offer a powerful technology for sensing and transmitting data across vast geographical regions. However, limitations inherent to WSNs, such as low-power sensor units, communication constraints, and limited processing capabilities, can significantly impact their lifespan. To address these limitations and enhance the energy efficiency of WSNs, it is often necessary to divide sensors into clusters and establish routing to conserve energy. Machine learning algorithms can potentially automate these processes, minimizing energy consumption and extending network lifetime. This research investigates the application of machine learning algorithms, specifically Q-learning and K-means clustering, to propose the Energy-Efficient Machine Learning-based Clustering and Routing (EEMLCR) method for WSNs. This method facilitates cluster formation and routing path selection. The proposed method is compared with the well-established LEACH algorithm and two multi-hop variants, DMHT LEACH and EDMHT LEACH to validate its effectiveness. Our experimental results demonstrate the effectiveness of EEMLCR compared to LEACH and its multi-hop variants (DMHT LEACH and EDMHT LEACH). After 600 rounds in networks comprising 400 nodes, EEMLCR showed significant improvements in key performance metrics. These include increased alive nodes, reduced average energy consumption, higher remaining energy levels, and improved packet reception. Additionally, we compared EEMLCR with recent state-of-the-art algorithms such as EECDA and CMML, where our method demonstrated comparable or superior performance in terms of network lifetime and energy efficiency. By optimizing clustering and routing strategies, WSNs can reduce energy consumption, leading to more efficient utilization of the limited energy resources available to sensor nodes. The primary objective of this research is to contribute to the development of energy-efficient WSNs by leveraging machine learning algorithms for data routing and the cluster-based organization of sensor nodes.

5 January 2021 in IEEE Access
Verified
Journal Article
Open access
Qazi Mudassar IlyasQazi Mudassar Ilyas
Qazi Mudassar Ilyas
MAMuneer Ahmad
Muneer Ahmad
Cervical cancer is a potentially life-threatening disease marked by health practitioners. The late diagnosis and treatment, being quite challenging, stake the precious lives of patients. In both developed and undeveloped states, the formal screening for disease identification suffers due to its medical cost, unavailable health facilities, society norms, and late appearance of symptoms. Machine intelligence is cost-effective, computationally inexpensive, and early diagnosis of several types of diseases, including cervical cancer. The patients are not required to pass through contemporary and tedious medical procedures, and early diagnosis of cervical cancer is quite handy with machine-intelligent solutions. The problem with the current machine classification methods for disease identification is the reliance on a single classifier’s prediction accuracy. The adoption of single classification methods doesn’t ensure the optimum prediction due to bias, over-fitting, mishandling of noisy data, and outliers. This research study proposes an Ensemble classification method based on majority voting for an accurate diagnosis addressing the patient’s medical conditions or symptoms. The study experiments a wide range of available classifiers, namely Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB), Multiple Perceptron (MP), J48 Trees, and Logistic Regression (LR) classifiers. The study records a significant enhancement in prediction accuracy of 94% that outperforms the prediction accuracies of single classification methods tested on the same benchmarked datasets. Thus, the proposed model bestows a second opinion to health practitioners for disease identification and timely treatment.