PhD

Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/35

This collection archives the complete set of theses produced by students of the COMSATS University Islamabad, Lahore Campus.

Browse

Search Results

Now showing 1 - 10 of 10

Automatic Screening of Diabetic Retinopathy at Early Stage using Colored Fundus Images
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Muhammad Nadeem Ashraf; FA14-PCS-003; LHR TP 7864; Dr. Zulfiqar Habib
The research work in this thesis is about an automated diagnosis of diabetic retinopathy (DR) for screening of DR patients at an early stage by classifying both red lesions using color fundus images, through a deep convolutional neural network (DCNN). DR is an asymptotic and vision-threatening retinal complication among working-age adults. Computer-aided diagnosis (CAD) is useful in screening DR patients to assist ophthalmologists to prevent blindness. Researchers have focused on this area by proposing many automated systems to diagnose DR. A comprehensive literature search is conducted during this research. Early-stage diagnosis is challenging due to poor representation of less discriminative and small-sized red lesions of DR. Traditional handcrafted based methods are not usually recommended for clinical trials due to their various limitations. Modern DCNNs are popular to solve various computer vision problems accurately. However, the requirement of huge training data restricts training deep models from scratch to solve the problems in medical imaging. Transfer learning and fine-tuning are helpful alternatives, but overfitting and poor performance further demand the architectural amendments for effective use of the deep CNN models in medical imaging with smaller datasets. Various pre-trained CNN models (AlexNet, VGG16, GoogLeNet, Inception-v3, ResNet50, and DenseNet) are fine-tuned, on the augmented set of 200 × 200 small image patches from the lesion-level annotated images of e-Ophtha_MA dataset, through transfer learning and hyper-parameter tuning to analyze their performance to classify both red lesions of DR. The architecture of a high-performing deep ResNet50 model is selected to fine-tune further. Its baseline architecture is modified by introducing; i) the reinforced skip connections, ii) a Global Max pooling layer, and iii) the Sum-of-Squared Error (SSE) Loss function. The suggested modifications are robust and straightforward. Such alterations may help to enhance various CNN architectures to apply in other imaging domains with small datasets. The proposed framework is evaluated on five publically available datasets: e Ophtha_MA, DiaRetDB1 v2.1, ROC, IDRiD, and Messidor by computing many xi performance metrics. The highest scores (0.9851, 0.991, 0.991, 0.991, 0.991, 0.9939, 0.0029, 0.9879, and 0.9879) of the sensitivity, specificity, AUC, accuracy, precision, F1-score, false-positive rate, Matthews’s correlation coefficient, and kappa coefficient are obtained on unseen test instances from e-Ophtha_MA for DR detection, respectively. The cross-validation results obtained by the proposed method on Messidor and IDRiD datasets at the image level are also better than state-of-the-art techniques. The achieved results are promising and demonstrate the effectiveness of a suggested architecture. For qualitative assessments, the gradient of class activations mapping (Grad-CAM) is computed to visualize the decision for each classified instance. This visual interpretation gives more satisfaction to using the proposed framework for clinical validations. Due to performance, simplicity, and robustness, the suggested model is suitable for diagnosing DR at an early stage for the screening of DR patients. It would help to develop a reliable health care system.
Spam Review Detection through Behavioral and Linguistic Approaches
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Naveed Hussain; FA15-PCS-002; LHR TP 7730
Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are ex tremely concerned with customer reviews as these have a direct impact on their busi nesses. Unfortunately, to gain profits or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In last few years, the Spam Review Detection (SRD) problem has gained much attention from communities and researchers, but there is still a need to introduce new spam re view detection methods to improve accuracy results utilizing real-world datasets. To overcome these problems, three methods have been proposed. In the first framework, two different spam review detection methods have been pro posed: (i) Spam Review Detection using Behavioral Method (SRD-BM) utilizes thir teen different spammer’s behavioral features to calculate the review spam score which is then used to identify spammers and spam reviews, and (ii) Spam Review Detection using Linguistic Method (SRD-LM) works on the content of the reviews and utilizes transformation, feature selection and classification to identify the spam reviews. Exper imental evaluations are conducted on a real-world Amazon review dataset which ana lyzes 26.7 million reviews and 15.4 million reviewers. The evaluations show that both proposed methods have significantly improved the detection process of spam reviews. Specifically, SRD-BM achieved 93.1% accuracy whereas SRD-LM achieved 88.5% accuracy in spam review detection. Comparatively, SRD-BM achieved better accuracy because it works on utilizing a rich set of spammers’ behavioral features of review da taset which provides in-depth analysis of spammer behavior. Moreover, both proposed methods outperformed existing approaches when compared in terms of accurate iden tification of spam reviews. To the best of the researcher’ knowledge, this is the first study of its kind which uses a large-scale review dataset to analyze different spammers’ behavioral features and linguistic methods utilizing different available classifiers. xi The second method has been developed to analyze the Roman Urdu review dataset based on different classification techniques utilizing linguistic and behavioral features. The performance of each classifier is evaluated in several perspectives: (i) Linguistic features are used to calculate accuracy (F1 Score) of each classifier; (ii) Behavioral features combined with distributional and non-distributional aspects are used to evalu ate accuracy (F1 Score) of each classifier; and (iii) The combination of both linguistic and behavioral features (distributional and non-distributional aspects) are used to eval uate the accuracy of each classifier. The experimental evaluations demonstrated an im proved accuracy (F1 Score: 0.96), which is the result of combinations of linguistic fea tures and behavioral features with the distributional aspect of reviewers. Moreover, be havioral features using distributional characteristic achieved an accuracy (F1 Score) of 0.86 and linguistic features shows an accuracy (F1 Score) of 0.69. The outcome of this research can be used to increase customers’ confidence on online reviews in the South Asian region. It can also help to reduce spam reviews in the South Asian region, partic ularly in Pakistan. The third method proposed Spammer Group Detection (SGD) method, which iden tifies suspicious spammer groups based on the similarity of all reviewer’s activities. Deep learning classifiers are used for training and testing the proposed SGD method. The study also proposed the Diversified Set of Reviews (DSR) method which presents a diversified set of top-k non-spam reviews having positive, negative, and neutral sen timents. Furthermore, it covers all possible features about the product or service. Ex perimental evaluations are conducted on daraz.pk and yelp.com real-world review da tasets. It has been observed by experimental analysis that the proposed SGD method has achieved 89.41% accuracy for the Yelp dataset and 81.31% accuracy for the Daraz dataset in detecting suspicious spammer groups and spam reviews.
A Performance Centric Cloudlet Federation Paradigm
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Muhammad Zaid Nayyer; FA14-PcS-001; LHR TP 5915; Syed Asad Hussain
Computer Vision Based Pattern Matching and Displacement Detection During Fabric Printing
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2017) Muhammad Abdul Qayum; FA10-PCS-001; LHR TP 5799; Dr. Farooq Ahmad
There is an absolute need for the robust quality inspection system, which can take on the new challenges and overcome the human limitations to inspect the fabric production consistently. To address this gap, computer vision based techniques are employed by enterprises. Some of the beneficent manufacturers include ceramic, circuit board printer, paper printer and textiles. Excellent work has been done in the yarn and weaving production sections of textile industry, however fabric printing monitoring is being explored by the researchers. The referential approach is mostly adopted to monitor fabric printing for defect detection. It works by acquiring an error-free image and registering this image with subsequent images captured during the production. In this method, the major time-consuming problem is to find the design repeat in the sample image before further processing. The researchers suggested some methods like distance matching in RGB space, photo encoders, genetic algorithm along with recursive splitting, Fuzzy C-means clustering, and cross correlation algorithm. There are certain limitations with these methods, for instance, sensitive to small deformation, required extra hardware prone to mechanical fault and it is expensive in calculations. In this research, a method for finding the design repeat is proposed. The method is tuned up according to the textile printing domain. Since the fabric moves in one direction during printing process, therefore the image registration can be confined to the same direction. To further speed up the process, the image registration method is applied using few initial pixel columns of the reference image with the sample image. Such bunch of selected columns of the reference image is matched with the same number of columns selected from sample image by moving this bunch on the sample image column by column. The maximum matching position is marked as the start of the design repeat. As the repeat size is always fixed, therefore complete design can be extracted from acquired image for defect detection. The experimental results on different fabric designs using the above-mentioned method are promising. Moreover, xi this technique improves the image alignment speed which enhances defect detection system performance. The most common defect is the displacement or misregistration of a colour. This defect is caused by the misalignment of cylindrical screens of fabric printing machine. As every screen is responsible for a colour, the misaligned screen registers the colour on the incorrect position. It leads to defective production and contributes to a substantial loss of the material and time. Few researchers proposed the feature based solution which are either computationally expensive or do not provide detail information about the defect like location and colour. Further, some techniques depend on the additional algorithms to find defects. Mostly, these methods depend on the accuracy of reference and sample image alignment. So there is always a chance of wrong notification. An improved algorithm for the detection of displacement of a colour during fabric printing is proposed in this thesis. The algorithm concatenates red, green and blue pixel values of the RGB image to represent a colour and later produces a frequency distribution of different colours for both sample and reference images. The colours with low frequencies are removed considering noise. In the next step, colours are grouped depending upon their distances from each other. These colour groups are later used to detect any new colour in the sample image which is actually created by the displacement defect and colour variation. The proposed algorithm successfully detects displacement and colour variation defects when it is tested using different flawed printed fabric images. The result shows that the proposed method has almost same accuracy as stat of the art algorithm and more helpful to detect the colour displacement, and it can also overcome the shortcoming of repeat finding process.
Detection of Antipatterns from Service Oriented Architecture
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2018) Fatima Sabir; SP14-PCS-003; LHR TP 5603; Dr. Ghulam Rasool
Web-services have become a governing technology for Service Oriented Architectures due to reusability of services and their dependence on other services. The evolution in service-based systems demand frequent changes to provide quality of service to customers. It is realized by different authors that evolution in service-based systems may degrade design and quality of service and may generate poor solutions known as antipatterns. The detection of antipatterns from web services is an important research realm and it is continuously getting attention of researchers. There are several techniques and tools presented for detection of antipatterns from object-oriented software applications but only few approaches are presented for detection of antipatterns from SOA. The state of the art antipattern detection approaches presented for detection of antipatterns from SOA are not flexible. We present a flexible approach supplemented with a tool support named as SWAD (Specification of Webservice Antipatterns Detection) to detect antipatterns from different SOAP based applications. Service-based systems, in particular, RESTful APIs, need to meet both service consumers’ and providers’ requirements. Like other software systems, RESTful APIs face continuous maintenance and evolution. Antipatterns may hinder the maintenance and evolution of RESTful APIs, as compared to the good design principles, i.e., design patterns that facilitate maintenance and evolution. Antipatterns may also affect the usability of RESTful APIs. Major market players like Facebook and YouTube are already using REST architecture and their APIs are frequently evolving to meet the end users’ requirements. Although, a number of antipatterns are deﬁned in the literature and researchers performed their automatic detection but the evolution of RESTful APIs did not receive much attention. There is a need to track the evolution of antipatterns in the RESTful APIs that could assist service providers publishing well-designed and easy to consume RESTful APIs for their clients. We present the correction of eight REST antipatterns in RESTful APIs with a tool support called SOCAR (Service Oriented Correction of Antipatterns in REST) after analyzing their evolution history for two years. Our correction heuristics are validated by practitioners with an average precision of 100% and an average recall of 94%. Moreover, we propose a methodology for the correction of linguistic antipatterns with a tool support COLAR (Correction of Linguistic Antipatterns for RESTAPIs).
Automated Detection and Classification of Brain Tumor from MRI Images using Machine Learning Methods
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2018) Ghulam Gilanie; FA14-PCS-007; LHR TP 5805; Dr. Usama Ijaz Bajwa
The focus of this thesis is to report an automated, efficient, and robust method of brain tumor detection and classification from Magnetic Resonance Images (MRI) images. Clinically, it is a challenging issue faced by the researchers working in this domain. In routine health care units, Magnetic Resonance (MR) scanners are being used to generate a massive number of brain slices, underlying the anatomical details. Pathological assessment from this medical data is being carried out manually by the radiologists or neuro oncologists. Due to huge volume of brain anatomical data produced by MRI scanners, it is almost impossible to manually analyze every slice. Conclusively, if automated protocols are executed for auto-interpretation; not only the radiologist will be assisted but also a better pathological assessment process would be expected. Several methods have been suggested to address this problem, but still, accuracy, robustness and optimization is still an open issue to address. The development of such automated procedures is difficult due to complex organization of brain cells, several types of tumor, difference in medical traits of a specific ethnicity and many more factors. To achieve the target, research has been started from reviewing the most popular and prominent state-of-the-art methods. Based upon the reviewed literature, automated brain tumor detection and classification techniques have been reported with high computational cost, low classification rates, detection and classification of only one or a few of brain tumor types, lack of robustness, etc. Therefore, step wise research and experiments based upon empirical scientific methodology have been performed in order to achieve the objectives of brain tumor classification. In the first step, a research activity has been performed to report a colorization method with the aims to enhance the visualization, cell characterization and interpretation of brain cells. The high dimensional brain data scanned through MRI embodied in gray scale, if converted, represented, mapped and/or visualized in colored versions, irrefutably, more definitive and more accurate the pathological assessment process will be. Several methods have been reported to represent brain MRI data in color with high computational xii complexity. In this research activity, an efficient method of colorization using frequencies from visible range of color spectrum, has been proposed to embody the variations and sensitivity of the brain MRI images. The experiments have been performed on a locally developed dataset. Side by side visual comparison based on multiple MRI sequences of identical subjects by domain experts have proved the adequate success and fruitfulness of the story. The reported method of colorization as a protocol has also been deployed in Department of Radiology and Diagnostic Images, Bahawal Victoria, Hospital, Bahawalpur (BVHB), Pakistan. Radiologists are using this tool for visual interpretation and monitoring of the patients for their assessment and clinical decision making. In second step, an automated approach using Gabor filter and Support Vector Machines (SVMs), for the classification of brain MRI slices as normal or abnormal has been reported. Accuracy, sensitivity, specificity and AUC-value have been used as standard quantitative measures to evaluate the proposed algorithm. To the best of our knowledge, this is the first study in which experiments have been performed on The Whole Brain Atlas - Harvard Medical School (HMS) dataset, achieving an accuracy of 97.5%, sensitivity of 99%, specificity of 92% and AUC-value as 0.99. To test the robustness against medical traits based on ethnicity and to achieve optimization, a locally developed dataset has also been used for experiments and remarkable results with accuracy (96.5%), sensitivity (98%), specificity (92%) and AUC-value (0.97) were achieved. Comparison with state-of-the art methods proved the overall efficacy of the proposed method. In third step of the thesis, a method has been proposed to classify brain MRI image into brain related disease groups and further tumor types. The proposed method employed Gabor texture followed by a set of more distinguished statistical features. These features are then used by SVM to classify the brain disorder. K-fold strategy has been adapted for cross validation of the results to enhance generalization of SVM. Experiments have been performed to classify brain MRI images as normal or belonging to either of the common diseases, such as cerebrovascular, degenerative, inflammatory, and neoplastic. Neoplastic disease is further classified into glioma, meningioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma, or sarcoma. Standard quantitative evaluation measures, i.e., accuracy, specificity, sensitivity, and AUC-value have been used to test xiii performance of the developed system. The proposed system has been trained on complete dataset of HMS, so the trained model has the ability to deal with a wide range of brain abnormalities. Further, to achieve robustness, a locally developed dataset has also been used for experiments. Remarkable results on different orientations, sequences of both of these datasets as per accuracy (up-to 99.6%), sensitivity (up-to 100%), specificity (up-to 100%), precision (up-to 100%) and AUC-value (up-to 1.0) have been achieved. The proposed method classifies the brain MRI slices into defined abnormality groups. It can also classify the abnormal slices into tumorous or non-tumorous one. The major achievement of the developed system is its auto classification of tumorous slices into the slices having primary tumor or secondary tumor and their further types, which possibly could not be determined without biopsy. In fourth step of the thesis, results achieved through the proposed method of brain tumor classification have been validated on cross data set. The drive of this research activity is to verify the robustness of the reported approach. For this, the model has been trained completely on one data set, while tested completely on another one. A benchmarked dataset HMS and a locally developed dataset BVHB dataset has been used for this purpose. To ensure its robustness, complete HMS dataset was used to train the model and BVHB was used to test the trained model and vice versa. Standard evaluation measures, i.e., accuracy, specificity, sensitivity, precision and AUC-value have been used to evaluate the system. It has been established that the proposed method deals with multiformity and variability of brain MRI data. Overall, suppositions regarding robustness of the proposed method were attained with maximum measures as per accuracy as 92%, specificity as 92%, sensitivity as 93%, precision as 92%, and AUC-value as 0.93. The overall results achieved through the proposed method, manifests that it is robust, efficient and reliable. It has been trained on a large volume of multi-orientations, multi-sequences belonging to multi-datasets to deal with multiformity and to face variabilit
Robust Image Forgery Detection and Localization using Texture Information
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2018) Muhammad Khurshid Asghar; SP14-PCS-002; LHR TP 5604; Dr. Zulfiqar Habib
Forensic analysis of images has important applications in security, court of law, insurance agencies, medical imaging, and electronic media. To develop robust image forgery detection and localization methods, applicable to real scenarios are highly needed. The focus of this thesis is to develop automatic image forgery detection and localization techniques. In the image forgery detection and localization, the main challenge is the robust representation of tampering traces. First, to identify the research gaps for contribution, the state-of-the-art passive image forgery detection and localization techniques have been reviewed. The existing techniques are not robust in representing the tampering traces. To overcome this issue two techniques have been proposed. The first technique has been developed to detect copy-move forgery in images by estimating noise patterns. To represent noise patterns, a new descriptor FFT-DRLBP employing Fast Fourier Transformation (FFT) and Discriminative Robust Local Binary Patterns (DRLBP) is introduced. Noise patterns are estimated using FFT, then the discrepancies in the noise patterns due to tampering are encoded using DRLBP. Support Vector Machine (SVM) is used to classify images as authentic or forged. This technique detects authentic and forged images with 99.21 % accuracy. To localize the copy-move forgeries a robust FFT-SIFT descriptor based on FFT and Scale Invariant Feature Transform (SIFT) is proposed. Localization method based on FFT-SIFT descriptor outperforms state-of-the-art and achieves high true positive rate while maintaining low false positive rate. The second technique has been developed to detect splicing forgery in images by estimating noise inconsistencies. For this purpose, a new descriptor DWT-DRLBP is introduced based on Discrete Wavelet Transformation (DWT) and DRLBP. First image is decomposed using DWT, the texture variation in each DWT sub-band is encoded using DRLBP histograms. Cb and Cr components are used to extract features using DWT-DRLBP descriptor. For classification SVM is employed. The method offers excellent results (98.95 %) and outperforms the state-of-the-art methods. xi In addition, to validate the robustness of the proposed methods on real scenarios, a new dataset called Forged Real Images Throughout History (FRITH) is developed to validate the performance of the proposed methods. To further validate the robustness of the proposed methods, cross-dataset experiments are performed to analyze the applicability on unseen images
An Adaptive Trust-aware Brokerage Model for Cross-cloud Federation
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Usama Ahmed; FA14-PCS-004; LHR TP 5917; Syed Asad Hussain
Establishing trust in cloud computing has been a major concern for cloud users since the very beginning of pay-as-you-go service. In the recent years, cross-cloud federation has enabled cloud providers to share or lease resources from each other. Contrary to the hesitation of cloud users for cloud adoption, it is now the cloud providers that are reluctant to take part in federation due to lack of trust on their unknown counterparts. A recent void has been observed to address the challenges of trustworthy resource exchanges within the federation. This research has established that trust awareness among cloud providers requires a comprehensive trust framework that is aligned with the nature of federation. A detailed requirement analysis for trust in cross-cloud federation has been performed in this research. This analysis is based on four founding principles of cloud-to-cloud trust paradigm namely bi-directionality, composite trust, delegation control and resource aware trust evaluation. Afterwards, requirements originated from these principles are aligned with the attributes of trust and cloud federation with the help of a detailed requirement matrix. Keeping in view this requirement matrix, an adaptive trust-aware brokerage model has been developed. This model offers dynamic trust establishment approaches that are a function of relationship among service providers. Three different approaches i.e. Conjunctive Accumulation of Trust (ConAccT), Numerical Accumulation of Trust (NAccT) and Cooperation Threshold Estimation (CTE) are developed as part of the proposed model. ConAccT is based on belief calculus and may be useful in case of highly competitive collaborating scenarios where detailed analysis of trust is required to decide cooperation among Cloud Service Providers (CSPs). NAccT approach is based on numerical calculus and is useful in less competitive scenarios and can be combined with metrics other than trust i.e. performance, availability, resource specifications etc. CTE approach is an extension to NAccT and presents a use case of utilizing the performance metric of a CSP combined with its trust metric to evaluate risk of failure in a collaborative project. The significance of these approaches has been verified by implementing the adaptive trust-aware model as a trusted broker based Clouds4Coordination (C4C) system developed for Architecture/Engineering/Construction (AEC) industry. This C4C system is currently implemented in United Kingdom in collaboration with Cardiff University, UK and Rutgers Discovery Informatics Institute (RDI2), USA. Experimental evaluation of these approaches suggests their suitability in varying scenarios of collaborative computing in construction industry. It has been verified that trust-aware relationships within the federation stays for a longer duration of time during collaborative projects. Moreover, an in depth analysis of proposed approach has shown that trust awareness is beneficial in terms of successful service delivery, earlier project completion and reduction in uncertainty of collaboration. A comparative analysis with state-of-art approaches have demonstrated the efficiency of proposed approaches to identify participants of federation that can cause potential risks and unnecessary delays in the projects.
Software Measurement Programs: Evaluations and Solutions
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Touseef Tahir; SP13-PCS-002; LHR TP 5943; Dr. Ghulam Rasool
Every software development process either generates or uses measurement data that is essential to understand, evaluate, improve and predict the software processes, products, and resources. Software development organizations implement measurement programs (MPs) as part of their measurement processes. However, implementing successful MPs still remains a challenge. The aim of this thesis is to comprehensively evaluate and then contribute towards planning and implementation issues of MPs. This research is conducted in three phases: 1) problem identification 2) solution design and 3) industrial evaluation of solutions. A mix of qualitative and quantitative research methods is used appropriately for each phase. In the first phase, comprehensive literature reviews of the studies on MPs are conducted to enable a better understanding of the existing measurement planning models, tools, challenges, success factors, and metrics selection methods of implementing MPs in general and specifically for small and medium enterprises (SMEs). In addition, challenges of implementing MPs in large organizations and SMEs are analyzed. In the second phase, multiple solutions are proposed to improve the planning of MPs. The solutions are based on the analysis of research gaps involving the challenges and success factors of implementing MPs. First, a set of key components of MPs is identified for planning a MP. Second, a model of success factors for planning MPs in general is proposed. Third, a model of success factors for planning MPs specifically in SMEs is proposed. Fourth, a model called data-driven measurement for software prediction (D2MSP) is proposed to overcome the challenge of using already collected measurement data for prediction of software attributes e.g., defects. In the third phase, the solutions are evaluated in the software development industry with the help of surveys and empirical data of software projects. A set of key components and a model of success factors are evaluated based on a survey among 200 software professionals working in the Pakistani software development industry. A model of success for planning MPs specifically in SMEs is evaluated based on a survey among 217 software professionals working in SMEs of Pakistan. The D2MSP xi model is evaluated using a dataset of 760 projects and later applied in a software development organization as a case study. Overall, this research contributes to the theory and practice of software measurement by providing an improved understanding of planning software MPs and proposing and validating models of success factors and the D 2MSP model for planning MPs.
A Digital Twin Assisted Disease Detection for Leafy Green Vegetables Using Federated Learning in Smart Greenhouse
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Iqra Pervez; CIIT/SP23-RCS-016/LHR; Dr. Tariq Umer; LHR TP 9703
Agricultural production is seriously vulnerable to the rapid evolution of plant diseases in greenhouse environment. In modern agriculture, ensuring timely and accurate disease detection in leafy green vegetables is crucial for improving crop yield and sustainability. The effects of environmental temperature, humidity on plant’s health which restricts the efficacy of current disease management techniques in greenhouses. This research presents a Digital Twin-assisted model for disease detection in lettuce plants, leveraging Federated-based Learning to enable privacy-preserving and distributed model training within a smart greenhouse environment. The study integrates five pre-trained models AlexNet, MobileNet, ResNet50, EfficientNetB3, and VGG16 to evaluate their effectiveness in classifying plant diseases. This study utilise a lettuce diseases dataset from Kaggle. Among the tested models, VGG16 achieved the highest accuracy of 98%, demonstrating its superior capability for disease classification in resource-constrained settings. Additionally, a correlation analysis between humidity, temperature and disease occurrence was conducted using Unity 3D and Microsoft Azure, providing deeper insights into the environmental conditions influencing plant health. The proposed model is useful for monitoring crops in real time and shows that combining Digital Twin technology with Federated-based Learning can improve decision-making in smart farming systems.

PhD

Browse

Filters

Settings

Sort By

Results per page

Search Results