Yazar "Rokne, Jon G." seçeneğine göre listele
Listeleniyor 1 - 9 / 9
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Enhanced potato pest identification: a deep learning approach for identifying potato pests(2024) Sohel, Amir; Shakil, Md. Shahriar; Siddiquee, Shah Md. Tanvir; Marouf, Ahmed Al; Rokne, Jon G.; Alhajj, RedaPotato crops and their salability are influenced by potato pests in that both crop yield and quality are reduced. This in turn reduces the income for potato farmers due to lower prices for the crop, lower crop yield, trade restriction and reduced market access. Agricultural viability over the long run therefore depends on sustainable pest management. In order to efficiently detect potato pests, a dataset was constructed which contains eight prevalent potato species that were taken from several sources. Image pre-processing techniques were employed enhance image quality for compatibility with deep learning models. Among InceptionV3, VGG-16, and MobileNetV2 models, VGG-16 attained the highest accuracy of 94.44%, outperforming others. Inception-V3 achieved 58% accuracy, while MobileNetV2 reached 75%. Pre-processing has a major influence on improving result accuracy, which emphasizes its significance in enhancing model performance, according to an evaluation of its effects. These findings might lead to the development of pest management strategies for potato farming that are more effective. The efficient use of VGG-16 in potato pest identification systems is demonstrated by its excellent performance. Using deep learning models can therefore reduce financial losses and promote sustainable potato production. This study provides an approach for further investigation into the best ways to control pests in potato production, allowing farmers to overcome the obstacles and take advantage of valuable market prospects even in the face of pest threats.Öğe Exploring gene expression and clinical data for identifying prostate cancer severity levels using machine learning methods(Institute of Electrical and Electronics Engineers Inc., 2023) Marouf, Ahmed Al; Alhajj, Reda; Rokne, Jon G.; Ghose, Sunita; Bismar, Tarek A.Prostate cancer (PCa) is the most common type of cancer in men worldwide. It is a cancer that starts in the small walnut-shaped male gland called the prostate. From the prostate, it can form a metastasis into other organs. If detected and diagnosed early the survival rate may increase to 95%. Therefore, early detection and diagnosis are important tasks performed by a pathologist. The pathologist identifies the severity levels using a scale called the Gleason grading group (GGG). The GGG is found by pathologists by looking at a biopsy sample and assigning a grade of low, intermediate, or high to the sample. The pathologist then assesses a second sample in the same manner. The GGG is found by adding these two scores provides the total Gleason score. In this paper, we have explored tissue microarray (TMA) and clinical data collected by pathologists of Alberta Precision Laboratory, for predicting the severity level of prostate cancer using various machine learning methods. Traditional classifiers, such as Naïve Bayes, Decision Tree, Support Vector Machine with Radial basis function (RBF), Logistic Regression, and ensemble classifiers, such as Random Forest, and Bagging with k-nearest neighbors have been applied through the machine learning pipeline containing imputation and sampling techniques. An integrated SMOTE-Tomek Links method is adopted for handling the class imbalance problem. The highest accuracy obtained is 99.64% from the Random Forest method.Öğe Genomic biomarker discovery in disease progression and therapy response in bladder cancer utilizing machine learning(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Liosis, Konstantinos Christos; Marouf, Ahmed Al; Rokne, Jon G.; Ghosh, Sunita; Bismar, Tarek A.; Alhajj, RedaCancer in all its forms of expression is a major cause of death. To identify the genomic reason behind cancer, discovery of biomarkers is needed. In this paper, genomic data of bladder cancer are examined for the purpose of biomarker discovery. Genomic biomarkers are indicators stemming from the study of the genome, either at a very low level based on the genome sequence itself, or more abstractly such as measuring the level of gene expression for different disease groups. The latter method is pivotal for this work, since the available datasets consist of RNA sequencing data, transformed to gene expression levels, as well as data on a multitude of clinical indicators. Based on this, various methods are utilized such as statistical modeling via logistic regression and regularization techniques (elastic-net), clustering, survival analysis through Kaplan–Meier curves, and heatmaps for the experiments leading to biomarker discovery. The experiments have led to the discovery of two gene signatures capable of predicting therapy response and disease progression with considerable accuracy for bladder cancer patients which correlates well with clinical indicators such as Therapy Response and T-Stage at surgery with Disease Progression in a time-to-event manner.Öğe MCNN-LSTM: Combining CNN and LSTM to classify multi-class text in imbalanced news data(Institute of Electrical and Electronics Engineers Inc., 2023) Hasib, Khan Md; Azam, Sami; Karim, Asif; Marouf, Ahmed Al; Shamrat, F. M. Javed Mehedi; Montaha, Sidratul; Yeo, Kheng Cher; Jonkman, Mirjam; Alhajj, Reda; Rokne, Jon G.Searching, retrieving, and arranging text in ever-larger document collections necessitate more efficient information processing algorithms. Document categorization is a crucial component of various information processing systems for supervised learning. As the quantity of documents grows, the performance of classic supervised classifiers has deteriorated because of the number of document categories. Assigning documents to a predetermined set of classes is called text classification. It is utilized extensively in a wide range of data-intensive applications. However, the fact that real-world implementations of these models are plagued with shortcomings begs for more investigation. Imbalanced datasets hinder the most prevalent high-performance algorithms. In this paper, we propose an approach name multi-class Convolutional Neural Network (MCNN)-Long Short-Time Memory (LSTM), which combines two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Time Memory, for text classification in news data. CNN's are used as feature extractors for the LSTMs on text input data and have the spatial structure of words in a sentence, paragraph, or document. The dataset is also imbalanced, and we use the Tomek-Link algorithm to balance the dataset and then apply our model, which shows better performance in terms of F1-score (98%) and Accuracy (99.71%) than the existing works. The combination of deep learning techniques used in our approach is ideal for the classification of imbalanced datasets with underrepresented categories. Hence, our method outperformed other machine learning algorithms in text classification by a large margin. We also compare our results with traditional machine learning algorithms in terms of imbalanced and balanced datasets.Öğe SNF-CVAE: Computational method to predict drug-disease interactions using similarity network fusion and collective variational autoencoder(Elsevier, 2021) Jarada, Tamer N.; Rokne, Jon G.; Alhajj, RedaDrug repositioning is an emerging approach to identify novel therapeutic potentials for approved drugs and discover therapies for previously untreatable diseases. Drug repositioning has also attracted considerable attention in the pharmaceutical industry due to its time and cost efficiency in the drug development process compared to the traditional de novo drug discovery process. Recent advances in genomics, the tremendous growth of large-scale publicly available data, the availability of high-performance computing capabilities, along with the rise of machine learning, have further motivated the development of computational drug repositioning approaches. Investigating the relationship between different biomedical entities (e.g., drugs, diseases, genes) is one vital part of most recent studies in the drug repositioning field. Drug-disease interaction (R-DI) prediction is another main issue in drug repositioning research. Combining these relationships and interactions when introducing computational methods to identify novel drug-disease interactions with high accuracy is very challenging. In this study, we propose a robust approach, SNF-CVAE, for predicting novel drug-disease interactions using drug-related similarity information and known drug-disease interactions. SNF-CVAE integrates similarity measures, similarity selection, similarity network fusion (SNF), and collective variational autoencoder (CVAE) to conduct a non-linear analysis and improve the drug-disease interaction prediction accuracy. We evaluated the robustness of SNF-CVAE using different information models, drug similarity calculation measures, and drug similarity information. Moreover, we compared SNF-CVAE performance with four state-of-the-art machine learning models. SNF-CVAE achieved outstanding performance in stratified 5-fold cross-validation (Prec = 0.902, Rec = 0.883, F1 = 0.893, AUC-ROC = 0.958, and AUC-PR=0.970). Furthermore, we showed the efficiency of SNF-CVAE in predicting novel drug-disease interactions by validating the top-ranked interactions against pharmaceutical indications and clinical trial studies, which resulted in substantial pieces of evidence for almost all of RDIs predicted by our proposed model. To further demonstrate the reliability and robustness of SNF-CVAE, we conducted two case studies on the top predicted drug candidates for potentially treating Alzheimer's disease and Juvenile rheumatoid arthritis, which were successfully validated against clinical trials and published studies. In conclusion, we strongly believe that computational drug repurposing research could significantly benefit from integrating similarity measures and deep learning models to predict novel drug-disease interactions in heterogeneous networks.Öğe SNF-NN: Computational method to predict drug-disease interactions using similarity network fusion and neural networks(BioMed Central Ltd., 2021) Jarada, Tamer N.; Rokne, Jon G.; Alhajj, Reda S.Background: Drug repositioning is an emerging approach in pharmaceutical research for identifying novel therapeutic potentials for approved drugs and discover therapies for untreated diseases. Due to its time and cost efficiency, drug repositioning plays an instrumental role in optimizing the drug development process compared to the traditional de novo drug discovery process. Advances in the genomics, together with the enormous growth of large-scale publicly available data and the availability of high-performance computing capabilities, have further motivated the development of computational drug repositioning approaches. More recently, the rise of machine learning techniques, together with the availability of powerful computers, has made the area of computational drug repositioning an area of intense activities. Results: In this study, a novel framework SNF-NN based on deep learning is presented, where novel drug-disease interactions are predicted using drug-related similarity information, disease-related similarity information, and known drug-disease interactions. Heterogeneous similarity information related to drugs and disease is fed to the proposed framework in order to predict novel drug-disease interactions. SNF-NN uses similarity selection, similarity network fusion, and a highly tuned novel neural network model to predict new drug-disease interactions. The robustness of SNF-NN is evaluated by comparing its performance with nine baseline machine learning methods. The proposed framework outperforms all baseline methods (AUC- ROC = 0.867, and AUC- PR=0.876) using stratified 10-fold cross-validation. To further demonstrate the reliability and robustness of SNF-NN, two datasets are used to fairly validate the proposed framework’s performance against seven recent state-of-the-art methods for drug-disease interaction prediction. SNF-NN achieves remarkable performance in stratified 10-fold cross-validation with AUC- ROC ranging from 0.879 to 0.931 and AUC- PR from 0.856 to 0.903. Moreover, the efficiency of SNF-NN is verified by validating predicted unknown drug-disease interactions against clinical trials and published studies. Conclusion: In conclusion, computational drug repositioning research can significantly benefit from integrating similarity measures in heterogeneous networks and deep learning models for predicting novel drug-disease interactions. The data and implementation of SNF-NN are available at http://pages.cpsc.ucalgary.ca/ tnjarada/snf-nn.php.Öğe Transfer learning through weighted loss function and group normalization for vessel segmentation from retinal images(Institute of Electrical and Electronics Engineers Inc., 2021) Sarhan, Abdullah; Rokne, Jon G.; Alhajj, Reda; Crichton, Andrew C.S.The vascular structure of blood vessels is important in diagnosing retinal conditions such as glaucoma and diabetic retinopathy. Accurate segmentation of these vessels can help in detecting retinal objects such as the optic disc and optic cup and hence determine if there are damages to these areas. Moreover, the structure of the vessels can help in diagnosing glaucoma. The rapid development of digital imaging and computer-vision techniques has increased the potential for developing approaches for segmenting retinal vessels. In this paper, we propose an approach for segmenting retinal vessels that uses deep learning along with transfer learning. We adapted the U-Net structure to use a customized InceptionV3 as the encoder and used multiple skip connections to form the decoder. Moreover, we used a weighted loss function to handle the issue of class imbalance in retinal images. Furthermore, we contributed a new dataset to this field. We tested our approach on six publicly available datasets and a newly created dataset. We achieved an average accuracy of 95.60% and a Dice coefficient of 80.98%. The results obtained from comprehensive experiments demonstrate the robustness of our approach to the segmentation of blood vessels in retinal images obtained from different sources. Our approach results in greater segmentation accuracy than other approaches.Öğe Utilizing a responsive web portal for studying disc tracing agreement in retinal images(Public Library of Science, 2021) Sarhan, Abdullah; Swift, Andrew J.; Gorner, Adam T.; Rokne, Jon G.; Alhajj, Reda; Docherty, Gavin; Crichton, Andrew C.S.Glaucoma is a leading cause of blindness worldwide whose detection is based on multiple factors, including measuring the cup to disc ratio, retinal nerve fiber layer and visual field defects. Advances in image processing and machine learning have allowed the development of automated approached for segmenting objects from fundus images. However, to build a robust system, a reliable ground truth dataset is required for proper training and validation of the model. In this study, we investigate the level of agreement in properly detecting the retinal disc in fundus images using an online portal built for such purposes. Two Doctors of Optometry independently traced the discs for 159 fundus images obtained from publicly available datasets using a purpose-built online portal. Additionally, we studied the effectiveness of ellipse fitting in handling misalignments in tracing. We measured tracing precision, interobserver variability, and average boundary distance between the results provided by ophthalmologists, and optometrist tracing. We also studied whether ellipse fitting has a positive or negative impact on properly detecting disc boundaries. The overall agreement between the optometrists in terms of locating the disc region in these images was 0.87. However, we found that there was a fair agreement on the disc border with kappa = 0.21. Disagreements were mainly in fundus images obtained from glaucomatous patients. The resulting dataset was deemed to be an acceptable ground truth dataset for training a validation of models for automatic detection of objects in fundus images.Öğe Utilizing transfer learning and a customized loss function for optic disc segmentation from retinal images(Springer Science and Business Media Deutschland GmbH, 2021) Sarhan, Abdullah; Al-Khaz’Aly, Ali; Gorner, Adam; Swift, Andrew J.; Rokne, Jon G.; Alhajj, Reda S.; Crichton, Andrew C.S.Accurate segmentation of the optic disc from a retinal image is vital to extracting retinal features that may be highly correlated with retinal conditions such as glaucoma. In this paper, we propose a deep-learning based approach capable of segmenting the optic disc given a high-precision retinal fundus image. Our approach utilizes a UNET-based model with a VGG16 encoder trained on the ImageNet dataset. This study can be distinguished from other studies in the customization made for the VGG16 model, the diversity of the datasets adopted, the duration of disc segmentation, the loss function utilized, and the number of parameters required to train our model. Our approach was tested on seven publicly available datasets augmented by a dataset from a private clinic that was annotated by two Doctors of Optometry through a web portal built for this purpose. We achieved an accuracy of 99.78% and a Dice coefficient of 94.73% for a disc segmentation from a retinal image in 0.03 s. The results obtained from comprehensive experiments demonstrate the robustness of our approach to disc segmentation of retinal images obtained from different sources.
