10 results
Search Results
Now showing 1 - 10 of 10
Article Citation - WoS: 21Citation - Scopus: 36Deep Learning-Based Computer-Aided Diagnosis (cad): Applications for Medical Image Datasets(Mdpi, 2022) Kadhim, Yezi Ali; Khan, Muhammad Umer; Mishra, AlokComputer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the best optimal features while reducing the amount of data. Lastly, diagnosis prediction (classification) is achieved using learnable classifiers. The novel framework for the extraction and selection of features is based on deep learning, auto-encoder, and ACO. The performance of the proposed approach is evaluated using two medical image datasets: chest X-ray (CXR) and magnetic resonance imaging (MRI) for the prediction of the existence of COVID-19 and brain tumors. Accuracy is used as the main measure to compare the performance of the proposed approach with existing state-of-the-art methods. The proposed system achieves an average accuracy of 99.61% and 99.18%, outperforming all other methods in diagnosing the presence of COVID-19 and brain tumors, respectively. Based on the achieved results, it can be claimed that physicians or radiologists can confidently utilize the proposed approach for diagnosing COVID-19 patients and patients with specific brain tumors.Conference Object Citation - WoS: 4Sliding Mode Control for Autonomous Flight of Tethered Kite Under Varying Wind Speed Conditions(Ieee, 2020) Bari, Salman; Khan, Muhammad UmerHigh altitude wind is an energy-abundant source, representing the next generation of wind power technology. The power that can be extracted from wind grows cubically with wind speed, making higher altitudes a desirable choice to harvest wind energy. In this respect, large and fully-automated kites or planes can be used to capture such energy. Flight control is a key research area for using fully-automated kite power systems at utility scale. In this study, a novel control architecture is proposed for autonomous pattern 8 flight of tethered kites under varying wind speed conditions. The proposed scheme does not require a separate control system for turn maneuvers and straight flight path sections. Exponential reaching law-based Sliding Mode Control (SMC) and adaptive sliding mode control schemes are tested for flight control of a kite given a pre-specified trajectory. In this approach, the inversion of plant model is not required to address the problem of possible system instability, thus making the scheme proposed here more resilient towards system perturbations.Article Performance Investigation of ML Algorithms for Potato Blight Classification: The Role of Hyperparameter Tuning(Springer, 2026) Saeed, Sadia; Rehman, Hafiz Zia Ur; Hussain, Muhammad Ureed; Khan, Muhammad Umer; Saeed, Muhammad TallalPotato is the world's fourth most important food crop, consumed by over a billion people. Early and late blight diseases can reduce yields by up to 40%, leading to severe economic and food security challenges. While manual detection methods are prone to error, automated, image-based machine learning (ML) offers a promising alternative, though its performance depends strongly on proper optimization. This study investigates the role of hyperparameter tuning in improving ML algorithms for potato blight classification. We utilized two datasets: the PlantVillage dataset (500 images per class) and a region-specific Potato Leaf Dataset (PLD) from Pakistan (1628 early blight, 1424 late blight, 1020 healthy). All images were resized to 256 & times; 256 pixels and augmented. Features were extracted using the Bag-of-Features (BoF) technique, and four classic ML models-Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Linear Discriminant Analysis (LDA), and Random Forest (RF)-were trained. Hyperparameters were optimized via grid search with 5-fold cross-validation. This tuning led to measurable improvements; for instance, SVM accuracy increased from 93.0% to 95.9% on PlantVillage and from 85.0% to 87.0% on PLD. Evaluation using precision, recall, F1-score, and specificity confirmed SVM as the best-performing model. A confusion matrix analysis revealed that most misclassifications occurred between the two blight types due to visual similarity. To translate our findings into practice, we developed a MATLAB Graphical User Interface (GUI) that enables farmers to classify a leaf image in under three seconds and receive precautionary recommendations. This study demonstrates that systematic hyperparameter optimization is crucial for maximizing ML performance and is a key step in building accessible, real-time tools for precision agriculture. Future work will focus on extending the system to mobile and web platforms.Article Citation - WoS: 10Citation - Scopus: 13Escaping Local Minima in Path Planning Using a Robust Bacterial Foraging Algorithm(Mdpi, 2020) Abdi, Mohammed Isam Ismael; Khan, Muhammad Umer; Gunes, Ahmet; Mishra, DeeptiThe bacterial foraging optimization (BFO) algorithm successfully searches for an optimal path from start to finish in the presence of obstacles over a flat surface map. However, the algorithm suffers from getting stuck in the local minima whenever non-circular obstacles are encountered. The retrieval from the local minima is crucial, as otherwise, it can cause the failure of the whole task. This research proposes an improved version of BFO called robust bacterial foraging (RBF), which can effectively avoid obstacles, both of circular and non-circular shape, without falling into the local minima. The virtual obstacles are generated in the local minima, causing the robot to retract and regenerate a safe path. The proposed method is easily extendable to multiple robots that can coordinate with each other. The information related to the virtual obstacles is shared with the whole swarm, so that they can escape the same local minima to save time and energy. To test the effectiveness of the proposed algorithm, a comparison is made against the existing BFO algorithm. Through the results, it was witnessed that the proposed approach successfully recovered from the local minima, whereas the BFO got stuck.Article Citation - WoS: 6Citation - Scopus: 6Ensemble Transfer Learning Using Maizeset: a Dataset for Weed and Maize Crop Recognition at Different Growth Stages(Elsevier Sci Ltd, 2024) Das, Zeynep Dilan; Alam, Muhammad Shahab; Khan, Muhammad UmerMaize holds significant importance as a staple food source globally. Increasing maize yield requires the effective removal of weeds from maize fields, as they pose a detrimental threat to the growth of maize plants. In recent years, there has been a drive towards Precision Agriculture (PA), involving the integration of farming methods with artificial intelligence and advanced automation techniques. In the realm of PA, deep learning techniques present a promising solution for addressing the complex challenge of classifying maize plants and weeds. In this work, a deep learning method based on transfer learning and ensemble techniques is developed. The proposed method is implementable on any number of existing CNN models irrespective of their architecture and complexity. The developed ensemble model is trained and tested on our custom-built dataset, namely MaizeSet, comprising 3330 images of maize plants and weeds under varying environmental conditions. The performance of the ensemble model is compared against individual pre-trained VGG16 and InceptionV3 models using two experiments: the identification of weeds and maize plants, and the identification of the various vegetative growth stages of maize plants. VGG16 attained an accuracy of 83% in Experiment 1 and 71% in Experiment 2, while InceptionV3 showcased improved performance, boasting an accuracy of 98% in Experiment 1 and 81% in Experiment 2. With the proposed ensemble approach, VGG16 when combined with InceptionV3, achieved an accuracy of 90% for Experiment 1 and 80% for Experiment 2. The findings demonstrate that integrating a suboptimal pre-defined classifier, specifically VGG16, with a more proficient model like InceptionV3, yields enhanced performance across various analytical metrics. This underscores the efficacy of ensemble techniques in the context of maize classification and analogous applications within the agricultural domain.Conference Object Citation - WoS: 3Biomechanical Design and Control of Lower Limb Exoskeleton for Sit-to-Stand and Stand-to-Sit Movements(Ieee, 2018) Qureshi, Muhammad Hamza; Masood, Zeeshan; Rehman, Linta; Owais, Muhammad; Khan, Muhammad UmerIn this paper, we present design and development phase of lower limb robotic exoskeleton that can assist paralyzed individuals. Motion of the human wearing exoskeleton is introduced by actuators. Both exoskeleton legs are attached to the supporting frame by passive universal joints. The exoskeleton provides 3 DOFs per limb of which two joints are active and one passive. The control actions i.e., sit-to-stand and stand-to-sit movements are triggered using Double Pole Double Throw (DPDT) toggle switch. The control scheme is implement using Switch control method and the feedback is provided by means of current measurement. This assistive device can be utilized for the disabled persons. The simulation results are provided that evaluates the performance of the control actions on exoskeleton.Conference Object Citation - WoS: 8Attitude Control of Quad-Copter Using Deterministic Policy Gradient Algorithms (dpga)(Ieee, 2019) Ghouri, Usama Hamayun; Zafar, Muhammad Usama; Bari, Salman; Khan, Haroon; Khan, Muhammad UmerIn aerial robotics, intelligent control has been a buzz for the past few years. Extensive research efforts can be witnessed to produce control algorithms for stable flight operation of aerial robots using machine learning. Supervised learning has the tendency but training an agent using supervised learning can be a tedious task. Moreover, the data gathering could be expensive and always prone to inaccuracies due to parametric variations and system dynamics. An alternative approach is to ensure the stability of the aerial robots with the help of Deep Re-inforcement Learning (DRL). This paper deals with the intelligent control of quad-copter using deterministic policy gradient algorithms. In this research, state of the art Deep Deterministic Policy Gradient (DDPG) and Distributed Distributional Deep Deterministic Policy Gradient (D4PG) algorithms are employed for attitude control of quad-copter. An open source simulation environment GymFC is used for training of quad-copter. The results for comparative analysis of DDPG & D4PG algorithms are also presented, highlighting the attitude control performance.Conference Object Citation - WoS: 86Real-Time Machine-Learning Based Crop/Weed Detection and Classification for Variable-Rate Spraying in Precision Agriculture(Ieee, 2020) Alam, Mansoor; Alam, Muhammad Shahab; Roman, Muhammad; Tufail, Muhammad; Khan, Muhammad Umer; Khan, Muhammad TahirTraditional agrochemical spraying techniques often result in over or under-dosing. Over-dosing of spray chemicals is costly and pose a serious threat to the environment, whereas, under-dosing results in inefficient crop protection and thereby low crop yields. Therefore, in order to increase yields per acre and to protect crops from diseases, the exact amount of agrochemicals should be sprayed according to the field/crop requirements. This paper presents a real-time computer vision-based crop/weed detection system for variable-rate agrochemical spraying. Weed/crop detection and classification were performed through the Random Forest classifier. The classification model was first trained offline with our own created dataset and then deployed in the field for testing. Agrochemical spraying was done through application equipment consisting of a PWM-based fluid flow control system capable of spraying the desired amounts of agrochemical directed by the vision-based feedback system. The results obtained from several field tests demonstrate the effectiveness of the proposed vision-based agrochemical spraying framework in real-time.Article Citation - WoS: 26Citation - Scopus: 35Tobset: a New Tobacco Crop and Weeds Image Dataset and Its Utilization for Vision-Based Spraying by Agricultural Robots(Mdpi, 2022) Alam, Muhammad Shahab; Khan, Muhammad Umer; Alam, Mansoor; Tufail, Muhammad; Güneş, Ahmet; Khan, Muhammad Umer; Gunes, Ahmet; Salah, Bashir; Khan, Muhammad Tahir; Khan, Muhammad Umer; Güneş, Ahmet; Mechatronics Engineering; Department of Mechatronics Engineering; Mechatronics Engineering; Department of Mechatronics EngineeringSelective agrochemical spraying is a highly intricate task in precision agriculture. It requires spraying equipment to distinguish between crop (plants) and weeds and perform spray operations in real-time accordingly. The study presented in this paper entails the development of two convolutional neural networks (CNNs)-based vision frameworks, i.e., Faster R-CNN and YOLOv5, for the detection and classification of tobacco crops/weeds in real time. An essential requirement for CNN is to pre-train it well on a large dataset to distinguish crops from weeds, lately the same trained network can be utilized in real fields. We present an open access image dataset (TobSet) of tobacco plants and weeds acquired from local fields at different growth stages and varying lighting conditions. The TobSet comprises 7000 images of tobacco plants and 1000 images of weeds and bare soil, taken manually with digital cameras periodically over two months. Both vision frameworks are trained and then tested using this dataset. The Faster R-CNN-based vision framework manifested supremacy over the YOLOv5-based vision framework in terms of accuracy and robustness, whereas the YOLOv5-based vision framework demonstrated faster inference. Experimental evaluation of the system is performed in tobacco fields via a four-wheeled mobile robot sprayer controlled using a computer equipped with NVIDIA GTX 1650 GPU. The results demonstrate that Faster R-CNN and YOLOv5-based vision systems can analyze plants at 10 and 16 frames per second (fps) with a classification accuracy of 98% and 94%, respectively. Moreover, the precise smart application of pesticides with the proposed system offered a 52% reduction in pesticide usage by spotting the targets only, i.e., tobacco plants.Article Citation - WoS: 25Citation - Scopus: 33Hybrid Eeg-Fnirs Bci Fusion Using Multi-Resolution Singular Value Decomposition (msvd)(Frontiers Media Sa, 2020) Khan, Muhammad Umer; Hasan, Mustafa A. H.Brain-computer interface (BCI) multi-modal fusion has the potential to generate multiple commands in a highly reliable manner by alleviating the drawbacks associated with single modality. In the present work, a hybrid EEG-fNIRS BCI system-achieved through a fusion of concurrently recorded electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals-is used to overcome the limitations of uni-modality and to achieve higher tasks classification. Although the hybrid approach enhances the performance of the system, the improvements are still modest due to the lack of availability of computational approaches to fuse the two modalities. To overcome this, a novel approach is proposed using Multi-resolution singular value decomposition (MSVD) to achieve system- and feature-based fusion. The two approaches based up different features set are compared using the KNN and Tree classifiers. The results obtained through multiple datasets show that the proposed approach can effectively fuse both modalities with improvement in the classification accuracy.
