Browsing by Author "Khan, Muhammad Adnan"

Now showing 1 - 12 of 12
  • Thumbnail Image
    Item
    Classification of Skin Cancer empowered with convolutional neural network
    (Institute of Electrical and Electronics Engineers Inc., 2022) Atta, Ayesha; Khan, Muhammad Adnan; Asif, Muhammad; Issa, Ghassan F.; Said, Raed A.; Faiz, Tauqeer
  • Thumbnail Image
    Item
    Detection of Benign and Malignant Tumors in Skin Empowered with Transfer Learning
    (Hindawi Limited, 2022) Ghazal, Taher M.; Hussain, Sajid; Khan, Muhammad Farhan; Khan, Muhammad Adnan; Said, Raed A. T.; Ahmad, Munir
    Skin cancer is a major type of cancer with rapidly increasing victims all over the world. It is very much important to detect skin cancer in the early stages. Computer-developed diagnosis systems helped the physicians to diagnose disease, which allows appropriate treatment and increases the survival ratio of patients. In the proposed system, the classification problem of skin disease is tackled. An automated and reliable system for the classification of malignant and benign tumors is developed. In this system, a customized pretrained Deep Convolutional Neural Network (DCNN) is implemented. The pretrained AlexNet model is customized by replacing the last layers according to the proposed system problem. The softmax layer is modified according to binary classification detection. The proposed system model is well trained on malignant and benign tumors skin cancer dataset of 1920 images, where each class contains 960 images. After good training, the proposed system model is validated on 480 images, where the size of images of each class is 240. The proposed system model is analyzed using the following parameters: accuracy, sensitivity, specificity, Positive Predicted Values (PPV), Negative Predicted Value (NPV), False Positive Ratio (FPR), False Negative Ratio (FNR), Likelihood Ratio Positive (LRP), and Likelihood Ratio Negative (LRN). The accuracy achieved through the proposed system model is 87.1%, which is higher than traditional methods of classification. © 2022 Taher M.
  • No Thumbnail Available
    Item
    Edge AI-Based Automated Detection and Classification of Road Anomalies in VANET Using Deep Learning
    (Hindawi Limited, 2021) Bibi, Rozi; Saeed, Yousaf; Zeb, Asim; Ghazal, Taher M.; Rahman, Taj; Said, Raed A.; Abbas, Sagheer; Ahmad, Munir; Khan, Muhammad Adnan
    Road surface defects are crucial problems for safe and smooth traffic flow. Due to climate changes, low quality of construction material, large flow of traffic, and heavy vehicles, road surface anomalies are increasing rapidly. Detection and repairing of these defects are necessary for the safety of drivers, passengers, and vehicles from mechanical faults. In this modern era, autonomous vehicles are an active research area that controls itself with the help of in-vehicle sensors without human commands, especially after the emergence of deep learning (DNN) techniques. A combination of sensors and DNN techniques can be useful for unmanned vehicles for the perception of their surroundings for the detection of tracks and obstacles for smooth traveling based on the deployment of artificial intelligence in vehicles. One of the biggest challenges for autonomous vehicles is to avoid the critical road defects that may lead to dangerous situations. To solve the accident issues and share emergency information, the Intelligent Transportation System (ITS) introduced the concept of vehicular network termed as vehicular ad hoc network (VANET) for achieving security and safety in a traffic flow. A novel mechanism is proposed for the automatic detection of road anomalies by autonomous vehicles and providing road information to upcoming vehicles based on Edge AI and VANET. Road images captured via camera and deployment of the trained model for road anomaly detection in a vehicle could help to reduce the accident rate and risk of hazards on poor road conditions. The techniques Residual Convolutional Neural Network (ResNet-18) and Visual Geometry Group (VGG-11) are applied for the automatic detection and classification of the road with anomalies such as a pothole, bump, crack, and plain roads without anomalies using the dataset from different online sources. The results show that the applied models performed well than other techniques used for road anomalies identification. © 2021 Rozi Bibi et al.
  • Thumbnail Image
    Item
    Energy demand forecasting using fused machine learning approaches
    (Tech Science Press, 2022) Ghazal, Taher M.; Noreen, Sajida; Said, Raed A.; Khan, Muhammad Adnan; Siddiqui, Shahan Yamin; Abbas, Sagheer; Aftab, Shabib; Ahmad, Munir
    The usage of IoT-based smart meter in electric power consumption shows a significant role in helping the users to manage and control their electric power consumption. It produces smooth communication to build equitable electric power distribution for users and improved management of the entire electric system for providers. Machine learning predicting algorithms have been worked to apply the electric efficiency and response of progressive energy creation, trans-mission, and consumption. In the proposed model, an IoT-based smart meter uses a support vector machine and deep extreme machine learning techniques for professional energy management. A deep extreme machine learning approach applied to feature-based data provided a better result. Lastly, decision-based fusion applied to both datasets to predict power consumption through smart meters and get better results than previous techniques. The established model smart meter with automatic load control increases the effectiveness of energy management. The proposed EDF-FMLA model achieved 90.70 accuracy for predicting energy consumption with a smart meter which is better than the existing approaches. © 2022, Tech Science Press. All rights reserved.
  • No Thumbnail Available
    Item
    Energy-efficiency model for residential buildings using supervised machine learning algorithm
    (Tech Science Press, 2021) Aslam, Muhammad Shoukat; Ghazal, Taher M.; Fatima, Areej; Said, Raed A.; Abbas, Sagheer; Khan, Muhammad Adnan; Siddiqui, Shahan Yamin; Ahmad, Munir
    The real-time management and control of heating-system networks in residential buildings has tremendous energy-saving potential, and accurate load prediction is the basis for system monitoring. In this regard, selecting the appro-priate input parameters is the key to accurate heating-load forecasting. In existing models for forecasting heating loads and selecting input parameters, with an increase in the length of the prediction cycle, the heating-load rate gradually decreases, and the influence of the outside temperature gradually increases. In view of different types of solutions for improving buildings’ energy efficiency, this study proposed a Energy-efficiency model for residential buildings based on gradient descent optimization (E2B-GDO). This model can predict a building’s heating-load conservation based on a building energy performance dataset. The input layer includes area (distribution of the glazing area, wall area, and surface area), relative density, and overall elevation. The proposed E2B-GDO model achieved an accuracy of 99.98% for training and 98.00% for validation. © 2021, Tech Science Press. All rights reserved.
  • No Thumbnail Available
    Item
    An iomt-enabled smart healthcare model to monitor elderly people using machine learning technique
    (Hindawi Limited, 2021) Khan, Muhammad Farrukh; Ghazal, Taher M.; Said, Raed A.; Fatima, Areej; Abbas, Sagheer; Khan, M.A.; Issa, Ghassan F.; Ahmad, Munir; Khan, Muhammad Adnan
    The Internet of Medical Things (IoMT) enables digital devices to gather, infer, and broadcast health data via the cloud platform. The phenomenal growth of the IoMT is fueled by many factors, including the widespread and growing availability of wearables and the ever-decreasing cost of sensor-based technology. The cost of related healthcare will rise as the global population of elderly people grows in parallel with an overall life expectancy that demands affordable healthcare services, solutions, and developments. IoMT may bring revolution in the medical sciences in terms of the quality of healthcare of elderly people while entangled with machine learning (ML) algorithms. The effectiveness of the smart healthcare (SHC) model to monitor elderly people was observed by performing tests on IoMT datasets. For evaluation, the precision, recall, fscore, accuracy, and ROC values are computed. The authors also compare the results of the SHC model with different conventional popular ML techniques, e.g., support vector machine (SVM), K-nearest neighbor (KNN), and decision tree (DT), to analyze the effectiveness of the result. © 2021 Muhammad Farrukh Khan et al.
  • No Thumbnail Available
    Item
    Machine Learning Models for the Classification of Skin Cancer
    (Institute of Electrical and Electronics Engineers Inc., 2022) Arooj, Sahar; Khan, Muhammad Farhan; Khan, Muhammad Adnan; Khan, Muhammad Saleem; Taleb, Nasser
    Skin cancer is a serious illness that requires early identification in order to improve survival rates. Deep learning algorithms for computerized skin cancer detection have now become popular in recent years. These models may increase their performance by having access to additional data, and their prime objective is image categorization. This activity is extremely useful in the realm of health since it may help physicians and experts make the best decisions and accurately assess a patient's condition. Early detection of skin cancer helps patients to receive appropriate treatment and so enhance their survival rate. This proposed methodology is generated to detect and classify skin cancers. In this study, we employed four pre-trained deep learning models (Squeeze net, Alex net, Res net 101, VGG 19) for the classification of four types of skin cancers in more than 6000 skin images including actinic keratoses, intraepithelial carcinoma Bowen's disease (akiec), basal cell carcinoma (bcc), benign keratosis-like lesions (bkl) and melanocytic nevi (nv). The objective was the identification of the best model in the classification of these breast cancer images with highest accuracy. Experimental results reveal that the Squeeze net model achieved an accuracy of 92.5% which is highest when compared with all other models while Alex net, Res net 101, VGG 19 acquired 91.1%, 83.2%, and 90.4% respectively. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Modeling habit patterns using conditional reflexes in agency
    (Tech Science Press, 2021) Khan, Qura-Tul-Ain; Ghazal, Taher M.; Abbas, Sagheer; Khan, Wasim Ahmad; Khan, Muhammad Adnan; Said, Raed A.; Ahmad, Munir; Asif, Muhammad
    For decision-making and behavior dynamics in humans, the principal focus is on cognition. Cognition can be described using cognitive behavior, which has multiple states. This cognitive behavior can be incorporated with one of the internal mental states’ help, which includes desires, beliefs, emotions, intentions, different levels of knowledge, goals, skills, etc. That leads to habit development. Habits are highly refined patterns formed in the unconscious that evolve from conscious skill patterns in the human, and the same process can be implemented in the agency. These habit patterns are the outcomes of many internal values that may vary due to variations in parameter values forming these patterns. Fluctuations in the individual agent’s conditional reflexes may subject to strong habit patterns and leads to rationality. This paper presents the modeling of habit patterns in agency using conditional reflexes. Learning patterns, limited reflex patterns, skill patterns are working as main parameters for generating habit patterns. These input and output parameters will be validated using a scenario by applying fuzzy logic cascade techniques in which validation occurs at two levels. At the first level, conditional reflexes and initial patterns are applied, which form the output’s skill patterns. Then these skill patterns are interconnected with each other to form habit patterns. © 2021, Tech Science Press. All rights reserved.
  • No Thumbnail Available
    Item
    Performances of k-means clustering algorithm with different distance metrics
    (Tech Science Press, 2021) Ghazal, Taher M.; Hussain, Muhammad Zahid; Said, Raed A.; Nadeem, Afrozah; Hasan, Mohammad Kamrul; Ahmad, Munir; Khan, Muhammad Adnan; Naseem, Muhammad Tahir
    Clustering is the process of grouping the data based on their similar properties. Meanwhile, it is the categorization of a set of data into similar groups (clusters), and the elements in each cluster share similarities, where the similarity between elements in the same cluster must be smaller enough to the similarity between elements of different clusters. Hence, this similarity can be considered as a distance measure. One of the most popular clustering algorithms is K-means, where distance is measured between every point of the dataset and centroids of clusters to find similar data objects and assign them to the nearest cluster. Further, there are a series of distance metrics that can be applied to calculate point-to-point distances. In this research, the K-means clustering algorithm is evaluated with three different mathematical metrics in terms of execution time with different datasets and different numbers of clusters. The results indicate that the implementation of Manhattan distance measure metrics achieves the best results in most cases. These results also demonstrate that distance metrics can affect the execution time and the number of clusters created by the K-means algorithm. © 2021, Tech Science Press. All rights reserved.
  • Thumbnail Image
    Item
    Prediction of diabetes empowered with fused machine learning
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ahmed, Usama; Issa, Ghassan F.; Khan, Muhammad Adnan; Aftab, Shabib; Khan, Muhammad Farhan; Said, Raed A. T.; Ghazal, Taher M.; Ahmad, Munir
    In the medical field, it is essential to predict diseases early to prevent them. Diabetes is one of the most dangerous diseases all over the world. In modern lifestyles, sugar and fat are typically present in our dietary habits, which have increased the risk of diabetes. To predict the disease, it is extremely important to understand its symptoms. Currently, machine-learning (ML) algorithms are valuable for disease detection. This article presents a model using a fused machine learning approach for diabetes prediction. The conceptual framework consists of two types of models: Support Vector Machine (SVM) and Artificial Neural Network (ANN) models. These models analyze the dataset to determine whether a diabetes diagnosis is positive or negative. The dataset used in this research is divided into training data and testing data with a ratio of 70:30 respectively. The output of these models becomes the input membership function for the fuzzy model, whereas the fuzzy logic finally determines whether a diabetes diagnosis is positive or negative. A cloud storage system stores the fused models for future use. Based on the patient’s real-time medical record, the fused model predicts whether the patient is diabetic or not. The proposed fused ML model has a prediction accuracy of 94.87, which is higher than the previously published methods. Author
  • Thumbnail Image
    Item
    Single and Mitochondrial Gene Inheritance Disorder Prediction Using Machine Learning
    (Tech Science Press, 2022) Nasir, Muhammad Umar; Khan, Muhammad Adnan; Zubair, Muhammad; Ghazal, Taher M.; Said, Raed A.; Hamadi, Hussam Al
    One of the most difficult jobs in the post-genomic age is identifying a genetic disease from a massive amount of genetic data. Furthermore, the complicated genetic disease has a very diverse genotype, making it challenging to find genetic markers. This is a challenging process since it must be completed effectively and efficiently. This research article focuses largely on which patients are more likely to have a genetic disorder based on numerous medical parameters. Using the patient’s medical history, we used a genetic disease prediction algorithm that predicts if the patient is likely to be diagnosed with a genetic disorder. To predict and categorize the patient with a genetic disease, we utilize several deep and machine learning techniques such as Artificial neural network (ANN), K-nearest neighbors (KNN), and Support vector machine (SVM). To enhance the accuracy of predicting the genetic disease in any patient, a highly efficient approach was utilized to control how the model can be used. To predict genetic disease, deep and machine learning approaches are performed. The most productive tool model provides more precise efficiency. The simulation results demonstrate that by using the proposed model with the ANN, we achieve the highest model performance of 85.7%, 84.9%, 84.3% accuracy of training, testing and validation respectively. This approach will undoubtedly transform genetic disorder prediction and give a real competitive strategy to save patients’ lives. © 2022 Tech Science Press. All rights reserved.
  • No Thumbnail Available
    Item
    Software defect prediction using ensemble learning: A systematic literature review
    (Institute of Electrical and Electronics Engineers Inc., 2021) Matloob, Faseeha; Ghazal, Taher M.; Taleb, Nasser; Aftab, Shabib; Ahmad, Munir; Khan, Muhammad Adnan
    Recent advances in the domain of software defect prediction (SDP) include the integration of multiple classification techniques to create an ensemble or hybrid approach. This technique was introduced to improve the prediction performance by overcoming the limitations of any single classification technique. This research provides a systematic literature review on the use of the ensemble learning approach for software defect prediction. The review is conducted after critically analyzing research papers published since 2012 in four well-known online libraries: ACM, IEEE, Springer Link, and Science Direct. In this study, five research questions covering the different aspects of research progress on the use of ensemble learning for software defect prediction are addressed. To extract the answers to identified questions, 46 most relevant papers are shortlisted after a thorough systematic research process. This study will provide compact information regarding the latest trends and advances in ensemble learning for software defect prediction and provide a baseline for future innovations and further reviews. Through our study, we discovered that frequently employed ensemble methods by researchers are the random forest, boosting, and bagging. Less frequently employed methods include stacking, voting and Extra Trees. Researchers proposed many promising frameworks, such as EMKCA, SMOTE-Ensemble, MKEL, SDAEsTSE, TLEL, and LRCR, using ensemble learning methods. The AUC, accuracy, F-measure, Recall, Precision, and MCC were mostly utilized to measure the prediction performance of models. WEKA was widely adopted as a platform for machine learning. Many researchers showed through empirical analysis that features selection, and data sampling was necessary pre-processing steps that improve the performance of ensemble classifiers. © 2013 IEEE.