@uskt.edu.pk
Lecturer in Department of Software Engineering
University of Sialkot
MS Software Engineering From NUST
Ai in Medicine, Applied Machine Learning, Pure Software Engineering,
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Mishal Waqar, Attique Ur Rehman, Sabeen Javaid, Tahir Muhammad Ali, and Ali Nawaz
IEEE
Among Women, Breast cancer is one of the maximum occurring diseases. Many women die every year because of breast cancer globally. Early prediction and diagnosis of this disease can prevent death in the end. The survival rate increases on detecting breast cancer early as better treatment can be provided. Development in prediction and diagnosis is necessary for the life of people. A higher amount of accuracy in the prediction of breast cancer is necessary for the treatment aspects and also for the survivability of patients. It is apparent that there are different techniques available in breast cancer detection but machine learning algorithms can bring a large contribution to the process of prediction and early diagnosis of breast cancer. In this study, we use a Wisconsin dataset which was collected from a scientific dataset of 569 breast cancer. Out of 569 patients, 63% were diagnosed with benign and 37% were diagnosed with malignant cancer. The benign tumor grows slowly and does not spread. We apply five machine learning algorithms to this dataset and train a model for predicting malignant and benign tissues (BCs). Algorithms are K-Nearest neighbor, Support vector machine, Decision tree, Deep learning, and Random-forest respectively. The effectiveness of these algorithms is evaluated in terms of accuracy, F measure, confusion matrix, and specificity. By comparing the results deep learning classifier gives the highest accuracy and outclass all the other classifiers by attaining an accuracy of 9S.l3%. SVM gives an accuracy of 97.66% whereas KNN gives an accuracy of 95.79% etc.
Azka Mir, Attique Ur Rehman, Sabeen Javaid, and Tahir Muhammad Ali
IEEE
Monkey pox is a viral disease that spreads from animals especially monkey to human beings. Monkey pox outbreak has been increasing at a concerning rate. The outbreak of monkey pox has infected several people around the world. The extent and intensity of the disease can be determined by the occurrence of the symptoms. The objective of this paper is to predict monkeypox virus so that outbreak can be administered before monkeypox looms as a viral health hazard. The monkeypox case has been classified as confirmed, discarded and suspected. This paper uses a supervised machine learning model to predict the status of monkey pox case. To diagnose monkeypox virus case, clinical parameters are required. The selected dataset contains the parameters of monkey pox virus from April 2022 onwards. It is necessary to predict the monkey pox outbreak before it effects more valuable lives. For the purpose of this paper, supervised machine learning techniques have been used to determine the performance of the dataset through experimental analysis. The experiment has been performed using various classifiers such as Decision tree, Naïve Bayes etc. to compare the accuracy rate. After the comparative analysis of the resulting accuracy percentage of different classifiers, we have proposed the model with the classifier with the highest accuracy. Our proposed model has achieved an accuracy rate of 93.51% using K-NN classifier with k=5 neighbors. Rapid miner platform is used for the application of the machine learning tools and techniques for the purpose of this research. This paper highlights the effective machine learning steps for the development of highly accurate model using machine learning techniques on monkey pox outbreak dataset.
Tahir Mohammad Ali, Ali Nawaz, Attique Ur Rehman, Rana Zeeshan Ahmad, Abdul Rehman Javed, Thippa Reddy Gadekallu, Chin-Ling Chen, and Chih-Ming Wu
Frontiers Media SA
Magnetic resonance imaging is the most generally utilized imaging methodology that permits radiologists to look inside the cerebrum using radio waves and magnets for tumor identification. However, it is tedious and complex to identify the tumorous and nontumorous regions due to the complexity in the tumorous region. Therefore, reliable and automatic segmentation and prediction are necessary for the segmentation of brain tumors. This paper proposes a reliable and efficient neural network variant, i.e., an attention-based convolutional neural network for brain tumor segmentation. Specifically, an encoder part of the UNET is a pre-trained VGG19 network followed by the adjacent decoder parts with an attention gate for segmentation noise induction and a denoising mechanism for avoiding overfitting. The dataset we are using for segmentation is BRATS’20, which comprises four different MRI modalities and one target mask file. The abovementioned algorithm resulted in a dice similarity coefficient of 0.83, 0.86, and 0.90 for enhancing, core, and whole tumors, respectively.
Sibgha Islam, Attique Ur Rehman, Sabeen Javaid, Tahir Muhammad Ali, and Ali Nawaz
IEEE
Hepatitis C is an ailment that causes inflammation of the liver and leads to serious liver damage. In previous research, the accuracy of the model wasn't that accurate but the differences this paper made model worked well for the prediction of Hepatitis C disease. In the dataset, there are mainly four categories (Blood Donor, Suspected Blood Donor, Fibrosis, and Cirrhosis) used that are labeled. Its data type is polynomial with 0 missing values. The minimum value in the category is 7 for suspect blood donors and the most value is 533 for a blood donor. The machine learning algorithms used in medical approaches are increasing day by day for prediction tools, diagnosis tools, and detection of diseases such as the hepatitis C virus. We used the rapid miner Software for the application of machine learning algorithms. Firstly, took the dataset of the hepatitis C virus from the UCI machine learning site and then applied the five Machine Learning Algorithms, which include Naive Bayes, Random Forest, KNN, Decision Tree & Deep Learning (ANN). On applying feature selection, the attributes Age, ALB, ALP, AST, CHE, GGT, and PROT were selected. After applying different algorithms, the best results are shown by deep learning (ANN) with an accuracy of 95.50%. Rest all algorithms showed minimum accuracy as a Decision tree with 93.09%, Naïve Bayes with 91.89%, KNN with 93.09%, and Random Forest showed 94.29% of high accuracy.
Faiza Mehreen, Attique Ur Rehman, Tahir Muhammad Ali, Sabeen Javaid, and Ali Nawaz
IEEE
Diabetes is a chronic disease that occurs when the sugar level is too high in the body or when the body doesn't make enough insulin and it impacts each individual of all age groups. It has a captivating history that has increased significantly in recent years as a result of urbanization and affected millions of people worldwide. Undiagnosed diabetes can cause many life-threatening diseases which usually lead to the death of a person. So, the early detection of diabetes is very vital to maintain a healthy life and it can help to prevent complications and reduce patients' health risks. This paper undertakes to design a model which gives maximum accuracy by using different machine learning algorithms that help detect the disease in its early stage. For this purpose, used five classifiers which are Random Forest, Decision Tree, K-Nearest Neighbor, Naïve Bayes, and Deep learning, then apply the Vote ensemble approach that is considered “best practice” and is a part of the workflow and provides the best possible outcomes with the highest accuracy percentage. The informational data employed as a part of this analysis is taken from the Kaggle dataset of Early Diabetes Classification and preprocessed this all data on the RapidMiner Tool. The main point of this research is the implementation of the different ML based classification models to show their comparative analysis. Thus, by using these algorithms the diagnosis of diabetes is statistically evaluated and compared. The experimental outcomes show that in the vote ensemble, Random Forest with K-NN gives optimum results with the highest accuracy of 97.97% along with parameters like precision, f-measure, and sensitivity.
Laiba Rana, Attique Ur Rehman, Sabeen Javaid, and Tahir Muhammad Ali
IEEE
People having visual impairment can't perform routine tasks on their own such that they are obliged to perform even the simplest task with assistance. Since their issue can't be resolved with visual glasses or lenses, the various mode of advancing technologies is playing an immense role in aiding them. Plenty of research work and development of gadgets have been proposed regarding the assistance of visually impaired people. From deep learning along with sensor-based initiative systems to various ranges of software have been developed but until now every system or software heeds on a particular feature. This article is based on purposing the idea of developing a cross-platform application named Optic Ally, intelligent assistance for visually impaired people that will provide all salient features in it regarding their assistance. For this idea of Optic Ally application, a novel model-driven framework is introduced that comprises a meta-model, tree editor, and graphical modeling tool that is Sirius based with drag and drop palette. The modeling and visualization of the features of this app are done using the Sirius-based graphical modeling tool. Moreover, a case study has been demonstrated for the validity of the proposed framework. The outcome of the case study proves that the proposed framework is competent in modeling and visualizing features effectively. The initial developed stage of the application is also shown in this article. Optic Ally application features include object detection, object finder, location, voice assistance, guardian help, link account and profile setup for the visually impaired user whereas for the guardian user the features include location, profile setup and guardian help
Abdul Saboor, Attique Ur Rehman, Tahir Muhammad Ali, Sabeen Javaid, and Ali Nawaz
IEEE
Diabetes Mellitus is a common issue all over the world. There are many cases of diabetes that are recorded on daily bases. This chronic disease takes the entire life of a patient to recover from his health. The doctor can save it only in the early stages of the disease because if it is the last stage, it would be almost impossible for patients to recover from diabetes. The system is proposed to provide the best solution for the early prediction of diabetes. So that the doctor detects the disease in an early stage. The main purpose of research on early diabetes is to go ahead and improve the detection system of diabetes in the model for doctors to predict the patient's disease efficiently. Many research papers are public about different types to predict in different stages. But this work aims to predict the symptom in early-stage to stop the disease from the root so that it would not cause harm in the future. If the problem is solved at the early stage of the disease, it will be easy for patients to recover easily saving them from a big loss in the future. This research applied severer Machine Learning and Deep Learning algorithm to check the model's performance. In return, K Nearest Neighbor and Decision Tree provide the best accuracy in the applied dataset. The highest accuracy KNN model got 93.66% and the Decision Tree got 90.10% accuracy. KNN is the best algorithm in this case which provides good accuracy for the provided dataset. The Dataset used in this research was built by a Bangladesh hospital with a direct survey form with different patients. It has 17 attributes and a collection of 520 instances. The KNN algorithm is handy and has got 93.66% accuracy to apply the medical professional treatment.
Muhammad Owais Butt, Attique Ur Rehman, Sabeen Javaid, Tahir Muhammad Ali, and Ali Nawaz
IEEE
The purpose of this study is to develop a reliable decision support system for predicting the survival of heart failure patients. Over time, heart disease (CVD) has become one of the most visible diseases in the world. The major factors of Heart failure are Sex, cholesterol, high blood pressure, stress, age, Exercise Angina, and Resting ECG. Many researchers have proposed several methods for early diagnosis on the bases of these features. However, due to the hereditary critique of heart disease and the life-threatening risks, it is important to improve the accuracy of the proposed techniques and methods. In this article, a machine learning framework with high accuracy is proposed for the effective diagnosis of heart failure. Specifically, the framework deals with handling missing values through the first Example filter. In the second stage, the data imbalance problem is solved through the Synthetic Minority Over-sampling Technique (SMOTE Upsampling). In the third step, the feature selection is done using (Optimized Feature Selection). The fourth is to normalize the data using the normalization technique, the fifth is to split the data into portions using split operators (30% and 70%). In the final step, the Decision Tree and K-Nearest Neighbor (KNN) classifiers are introduced for effective forecasting as these classifiers achieve the best accuracy (84.11%). The dataset validation has been performed in the background using four types of datasets. (i.e. Failure Prediction Dataset, Cardiovascular Disease, Stroke Prediction Dataset, heart disease). Comparative analysis proves that (Heart Failure Prediction) Dataset achieves better accuracy (84.11%) with fewer sets of features.
Amad Rizwan Ali, Attique Ur Rehman, Ali Nawaz, Tahir Muhammad Ali, and Muhammad Abbas
IEEE
Software testing is one of the important ways to ensure the quality of software. It is found that testing cost more than 50% of overall project cost. Effective and efficient software testing utilizes the minimum resources of software. Therefore, it is important to construct the procedure which is not only able to perform the efficient testing but also minimizes the utilization of project resources. The goal of software testing is to find maximum defects in the software system. As world is continuously moving toward data driven approach for making important decision. Therefore, in this research paper we performed the machine learning analysis on the publicly available datasets and tried to achieve the maximum accuracy. The major focus of the paper is to apply different machine learning techniques on the datasets and find out which technique produce efficient result. Particularly, we proposed an ensemble learning models and perform comparative analysis among KNN, Decision tree, SVM and Naïve Bayes on different datasets and it is demonstrated that performance of Ensemble method is more than other methods in term of accuracy, precision, recall and F1-score. The classification accuracy of ensemble model trained on CM1 is 98.56%, classification accuracy of ensemble model trained on KM2 is 98.18% similarly, the classification accuracy of ensemble learning model trained on PC1 is 99.27%. This reveals that ensemble learning is more efficient method for making the defect prediction as compared other techniques.
Ali Nawaz, Attique Ur Rehman, Tahir Mohammad Ali, Farooque Azam, Yawar Rasheed, and Muhammad Waseem Anwar
IEEE
The autonomous vehicle is one of the significant efforts toward the luxurious life. The process involves several technical difficulties like synchronized communication between different sensors, efficient response time etc. In this regard, route prediction is one of the critical tasks which requires the extensive knowledge of complex concepts due to its real time nature. Although there exist several studies in this area, most of them are focusing on accuracy while ignoring the importance of simplicity. Therefore, the research community is likely to be benefited through a route prediction approach that focuses on simplicity while preserving good level of accuracy. For this purpose, a model-driven approach is proposed in this paper for automating the complex process of trajectory-based route prediction of a fully autonomous vehicle. Particularly, a metamodel which is M2 level Ecore Model of standard meta-object facility is proposed for trajectory- based route prediction. Subsequently, a complete modeling tool is developed using Sirius platform. Finally, Model-to-Text transformations are applied to generate low level Java implementations with simplicity. The validation is performed through real world case study where autonomous vehicle gain data from different sensors and store that data in the cloud for route prediction by applying an autonomous multiple model algorithm. The results are highly encouraging for the efficient route prediction in autonomous vehicle with simplicity.
Tahir Mohammad Ali, Ali Nawaz, and Attique Ur Rehman
IEEE
Twitter is an open, freely available and widely used social media platform for sharing emotions, political and social opinions without hesitation. With the passage of time data generated by Twitter is increasing tremendously and due to availability of the such a huge amount of data, there is an opportunity for industry giants to analyze their current product reviews and made a better business making for the future and to conformance needs of customers. Similarly, there is an opportunity for research aspirants to explore the data to provide a better solution for modern problems. Therefore, in this research paper, we perform a detailed sentiment analysis of the three beverage giants (Pepsi Vs Fanta Vs Coca-cola). Specifically, we perform the classification of extracted tweeter data into three classes (positive, negative and neutral) then the visualization of the data is performed and at the end, naïve Bayes, decision tree and LSTM algorithm is applied to perform the prediction of tweets. Particularly, we use machine learning libraries and natural language toolkits for data extraction, data visualization, sentiment analysis and prediction task. The maximum accuracy obtained on Pepsi, Fanta and Coca-Cola is 89%, 92% and 91% respectively by applying the LSTM algorithm. The experimental result reveals that LSTM is a better technique for continuous data
Ali Nawaz, Usman Akram, Anum Abdul Salam, Amad Rizwan Ali, Attique Ur Rehman, and Jahan Zeb
IEEE
Brain tumor is the spread of abnormal cells in the brain. Out of several kinds of brain tumor gliomas is the most dangerous with low survival rate and difficult to detect manually due to irregular form and confusing boundaries. Magnetic Resonance Imaging is the most widely used imaging modality that allows radiologist to look inside brain by utilizing radio waves and magnet but the manual identification of tumor region is tedious task. Therefore, a reliable and automatic segmentation and prediction is necessary for segmentation of brain tumor and prediction. However due to complexity and unavailability of resources to train deep learning algorithms, it is complex to identify the tumorous and non-tumorous region. So, in this paper, a reliable and efficient variant of UNET i.e., VGG19-UNET for segmentation of brain tumor and ensemble learning model for survival prediction is proposed. Specifically, an encoder part of the UNET is a pretrained VGG19 followed by the adjacent decoder part. Meanwhile, the ensemble voting classifier of Naïve Bayes and Random Forest was trained for survival prediction. The datasets we are using for segmentation is BRATS’20 which comprises of four different MRI modalities and one target mask file. Whereas, the datasets of survival prediction is also BTARS’20 which is comma separated file containing different features. Above mentioned algorithm resulted in dice coefficient score of 0.81, 0.86 and 0.88 for enhancing, core and whole tumor whereas the accuracy of overall survival is 62.7%
Ali Nawaz, Attique Ur Rehman, Tahir Mohammad Ali, Zara Hayat, Aqsa Rahim, Uzair Khaleeq Uz Zaman, and Amad Rizwan Ali
Informa UK Limited
ABSTRACT Functional Magnetic Resonance Imaging (FMRI) is a noninvasive test to analyze several medical ailments by using magnetic resonance imaging (MRI) to detect the abnormalities in the active part of the brain and evaluate the minute changes in the blood flow, which cannot otherwise be accomplished with other imaging techniques. With its vast applications in healthcare, it has become one of the most explored studies by the researcher’s community, therefore, the current paper aims to address a comprehensive systematic literature review (SLR) of the application of FMRI in healthcare. The SLR scrutinized and assessed the currently available literature using inclusion and exclusion criteria. The chief motive of conducting SLR on the current research was to eradicate the biases and make it more systematic as compared to the informal literature review. The outcomes of the review state that due to accessibility of the public datasets and the data augmentation practices, the application of FMRI in Healthcare has remarkably raised from the last five years and its application is practically available for every disease diagnosis. The performance of the diagnosis of the disease is more effectual and proficient as equal to the human experts performing it manually.
Attique Ur Rehman, Ali Nawaz, Mohammad Tahir Ali, and Muhammad Abbas
IEEE
Agile development is conventional these days and with the passage of time software developers are rapidly moving from Waterfall to Agile development. Agile methods focus on delivering executable code quickly by increasing the responsiveness of software companies while decreasing development overhead and consider people as the strongest pillar of software development. As agile development overshadows Waterfall methodologies for software development, it comes up with some distinct challenges related to testing of such software. Our study is going to discuss the challenges this approach has stirred up. Some of the challenges are discussed in this paper with possible solutions and approaches used for resolving these challenges. Also, the tools in practice are mentioned to improve the efficiency of the process. (Abstract)