Browsing by Author "MISHRA, Alok"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
Item A NEW METHOD FOR SOFTWARE DEFECT PREDICTION BASED ON OPTIMIZED MACHINE LEARNING TECHNIQUES(2022-03-01) HASSEN, SHAHO ISMAEL HASSEN; YAZICI, Ali; MISHRA, AlokIn this thesis a novel and robust heuristic driven neuro-computing model was developed for software defect prediction. Unlike other classical machine learning models, neuro-computing, especially Levenberg Marquardt Neural Network (LM ANN), is considered to be more robust in terms of adaptive learning, which can be vital towards non-linear feature learning and hence defect data. However, similar to the other machine learning models, the likelihood of local minima and convergence could not be avoided due to exceedingly high weight estimation for 17 input features. Considering this fact, this research contributed a novel improved genetic algorithm, say heuristic model was developed to assist ANN for adaptive weight estimation and update during learning. Here, the key purpose of heuristic model was to help LM-ANN gaining superior weight estimation, update and hence learning without undergoing any local minima and convergence problem. This as a result helped the proposed neuro computing model to achieve higher accuracy than the classical neural network over targeted software fault datasets. In addition to the classifier or machine learning improvement, in this research the focus was made on feature engineering as well that helped alleviating any probability of class imbalance, over-fitting and convergence.Item A STUDY OF DEVOPS ADOPTION IN SOFTWARE DEVELOPMENT ORGANIZATIONS: QUALITY, PRODUCTIVITY, AND SECURITY PERSPECTIVE(2023-01-30) OTAIWI, Ziadoon Abdullah; YAZICI, Ali; MISHRA, AlokThese days, many software organizations are competing with each other to rapidly develop and deliver high-quality, reliable software. DevOps is the Development (Dev) and Operation (Ops) methodology in software development organizations and has become one of the favored methodologies in many leading companies; consequently, many organizations want to adopt this methodology. However, adopting DevOps in the software industry is a big challenge because it requires new tools, technologies, methods, culture, and experienced work teams to design reliable and deployable applications. Most of the current academic research surrounding DevOps seeks answers for how to adapt to this new methodology and how to improve performance in the organization; its focus is on velocity, quality, and productivity to produce these applications. This study aims to conduct an empirical study to fill the research gaps related to quality, productivity, and security issues in implementing the DevOps methodology in organizations. This quantitative study found that software quality, productivity, and security are improved when DevOps was adopted following the CALMS (Culture, Automation, Lean, Measurement, and Sharing) framework. However, according to quantitative data collected, there are some challenges and negative impacts on security when DevOps is adopted. This study also proposes the development of best practices, recommendations, and a model to facilitate the adoption of DevOps in organizations.Item AGILE SOFTWARE MAINTENANCE AND DEVELOPMENT USING CLOUD COMPUTING FRAMEWORK(2023-01-26) ALMASHHADANI, Mohammed; YAZICI, Ali; MISHRA, AlokAgile methods have emerged to overcome the obstacles faced in traditional software methodologies, such as the Waterfall, Prototype, Spiral, etc. There have been many studies that show the numerous features of the Agile methodologies, making them useful for software development. However, many studies have also proposed a framework to adapt the Agile methods to Cloud Computing to leverage the benefits from this environment. The existing studies focus on the adaptive development life cycle for Agile with the Cloud, but have so far been unable to include the maintenance process in a detailed manner. Among these attempts and as further contribution, the present work intends to introduce Agile software maintenance and development using Cloud Computing framework (ASMDCC) as a reference for developing software with the Cloud in respect of maintenance activities. The case study findings reveal that the combination of Agile with Cloud Computing can resolve the major issues faced in traditional software maintenance, making the role of this approach significant in globally/distributed software maintenance. Furthermore, it is shown that Cloud Computing services play a vital part in resolving software maintenance. Finally, the results indicate that using the ASMDCC framework improves the challenges faced by the maintenance team compared to the traditional environment regarding management, infrastructure, collaboration, and transparency.Item CONCEPTUAL DESIGN OF E- GOVERNANCE IN DISASTER MANAGEMENT SYSTEM(2022-01-25) IBRAHIM, Thaer; MISHRA, Alok; BOSTAN, AtilaDisasters pose a real threat to the lives and property of citizens; therefore, it is necessary to reduce their impact to the minimum possible. In order to achieve this goal, a framework for enhancing the current DMS was proposed, called Smart Disaster Management System (SDMS). The smart aspect of this system is due to the application of the principles of Information and Communication Technology (ICT), especially the Internet of Things (IoT). All participants and activities of the proposed system were clarified by preparing a conceptual design by using The Unified Modeling Language (UML) diagrams (both, use-case and activity diagrams). This effort was made to overcome the lack of citizens’ readiness towards the use of ICT as well as increase their readiness towards disasters. Iraq was chosen as a case study for this research. The lack of readiness on part of Iraqi citizen was inferred by using two different methods, interviews with experts in the field of disasters and experts in the field of ICT. The other method was based on distributing a questionnaire form to the target sample.Item LOGISTICS SYSTEM TRANSITION TOWARDS ENTERPRISE RESOURCE PLANNING: A CASE STUDY(2022-01-25) Alansari, Saeeda; MISHRA, AlokToday, in order to achieve a competitive advantage organization should implement supply chain effectively and have such a product in logistics services. Otherwise, the traditional way of this process causes a problem of not covering everything and it is releasing the risk in organization of missing invoices yearly and not recording it. The director needs to have statistics recorded and accounting payment for every purchase and inventory. In the traditional way, the clerk enroll the data by using excel sheet and count manually by hand with old calculation methods which is very risky for he company. Further more, old machine can be damaged or crash from different reasons an example of that, viruses‘ issues in hard disk that crash the machine then all the data will be lost. Moreover, only one clerk is responsible so if the clerk gets sick the all works for purchases and inventory risk to be delayed. To perform activities effectively and value chain for organization competitiveness it is required to run supply chain in best manner by logistic services information system. Supply chain management has two purposes, firstly product reaches to the end users for multiple departments of the organization, secondly to deliver product to the final customer because it provides many benefits in managing product with coordination and monitoring everyday materials management. To improve the departments in terms of best strategic information system and avoid all the associated risks it is required to have a specific system for inventory control system. Therefore, the main objective of this thesis is to illustrate transition of existing system towards Enterprise Resource Planning Systems (ERP). It also explains inception plan to develop the software and search towards the best system keeping in view many organizational constraints. This also include survey outcome to measure the relationship between management models and organizational innovation in internal processes as part of management efforts towards new system planning.Item MEDICAL DATASET CLASSIFICATION BASED ON DIFFERENT DEEP LEARNING TECHNIQUES AND META-HEURISTIC ALGORITHMS(2023-01-30) KADHIM, Yezi Ali; MISHRA, Alok; DORUK, Reşat ÖzgürMedicine is one of the fields where computer science advancement is making significant progress. The usage of Computers in Medical improves precision and accelerates data processing and diagnosis. There are currently a variety of computer assisted diagnostic systems, with deep-learning algorithms playing an important role. Systems that are more precise and faster are required. Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This study 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. In this thesis, several combinations of different deep learning techniques with the meta-heuristic algorithm, each of the deep learning methods either the convolutional neural network or the auto-encoder were applied to extract the effective features from two different medical datasets COVID-19, and the brain tumor with the aid of the meta-heuristic method to select the optimal features in order to cover a several medical datasets detections. The first combination of several pre-trained convolutional neural networks (CNN) AlexNet, GoogleNet, ResNet 50, and DenseNet 201 was used with three types of Meta-Heuristic Algorithms Ant Colony Optimization algorithm (ACO), Particle Swarm Optimization algorithm (PSO), and Genetic Algorithm (GA). The second combination was Auto-encoder with three types Meta-Heuristic Algorithms ACO, PSO, and GA which was an innovative method, that seeks to reduce the size of the dataset while maintaining the original performance of the data. The employing of 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 ACO or PSO, or GA. 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 combination is evaluated with classifiers like decision tree (DT), support vector machine (SVM), k-nearest neighbors (KNN), ensemble, Naive Bayes, and discriminant 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. Also, in this thesis, a combination of different deep learning techniques with the meta-heuristic algorithm, each of the deep learning methods either the convolutional neural network or the auto-encoder were applied to extract the effective features from two different medical datasets, with the aid of the meta heuristic method to select the optimal features obtained by the particle swarm optimization algorithm (PSO) this combination is considered as an innovative method, seeks to reduce the size of the dataset while maintaining the original performance of the data. The covid-19 dataset found that the highest accuracy by the combination of CNN-PSO-SVM was 99.76%, and for the common brain tumor dataset, the accuracy of 99.51% as the highest was obtained by the combination method autoencoder-PSO KNN. We notice that the combination model of the deep learning method with the PSO feature selection algorithm takes a consuming time much longer than the same method with the ACO algorithm at the same time the accuracy of PSO is near to ACO accuracy.Item MEDICAL DATASET CLASSIFICATION BASED ON DIFFERENT DEEP LEARNING TECHNIQUES AND META-HEURISTIC ALGORITHMS(2023-01-30) KADHIM, Yezi Ali; MISHRA, Alok; DORUK, Reşat ÖzgürMedicine is one of the fields where computer science advancement is making significant progress. The usage of Computers in Medical improves precision and accelerates data processing and diagnosis. There are currently a variety of computer assisted diagnostic systems, with deep-learning algorithms playing an important role. Systems that are more precise and faster are required. Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This study 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. In this thesis, several combinations of different deep learning techniques with the meta-heuristic algorithm, each of the deep learning methods either the convolutional neural network or the auto-encoder were applied to extract the effective features from two different medical datasets COVID-19, and the brain tumor with the aid of the meta-heuristic method to select the optimal features in order to cover a several medical datasets detections. The first combination of several pre-trained convolutional neural networks (CNN) AlexNet, GoogleNet, ResNet 50, and DenseNet 201 was used with three types of Meta-Heuristic Algorithms Ant Colony Optimization algorithm (ACO), Particle Swarm Optimization algorithm (PSO), and Genetic Algorithm (GA). The second combination was Auto-encoder with three types Meta-Heuristic Algorithms ACO, PSO, and GA which was an innovative method, that seeks to reduce the size of the dataset while maintaining the original performance of the data. The employing of 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 ACO or PSO, or GA. 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 combination is evaluated with classifiers like decision tree (DT), support vector machine (SVM), k-nearest neighbors (KNN), ensemble, Naive Bayes, and discriminant 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. Also, in this thesis, a combination of different deep learning techniques with the meta-heuristic algorithm, each of the deep learning methods either the convolutional neural network or the auto-encoder were applied to extract the effective features from two different medical datasets, with the aid of the meta heuristic method to select the optimal features obtained by the particle swarm optimization algorithm (PSO) this combination is considered as an innovative method, seeks to reduce the size of the dataset while maintaining the original performance of the data. The covid-19 dataset found that the highest accuracy by the combination of CNN-PSO-SVM was 99.76%, and for the common brain tumor dataset, the accuracy of 99.51% as the highest was obtained by the combination method autoencoder-PSO KNN. We notice that the combination model of the deep learning method with the PSO feature selection algorithm takes a consuming time much longer than the same method with the ACO algorithm at the same time the accuracy of PSO is near to ACO accuracy.Item NOVEL SOFTWARE DEFECT PREDICTION METHOD BASED ON PCA AND OPTIMIZED LSTM(2022-01-10) AL-OBAIDI, ANMAR SADEQ JASIM; MISHRA, Alok; YAZICI, AliIn this thesis, new approach presented for software defect prediction applying PCA based LSTM. This study consists from two parts feature selection executed by PCA and classification part executed by LSTM. The aim applying PCA as feature selection is to reduce the size of input features to decrease the computation time by removing unaffected features. Then, the output of PCA wired to the LSTM that is time series classifier which classify the input software defect features to the two classes (defect and normal). The PSO applied to optimize the performance of the LSTM by updating the weight and basis of the LSTM to obtain best accuracy. The obtained results compared with common studies presented in this field.Item Software engineering education: some important dimensions(European Journal of Engineering Education, 2007-06-22) MISHRA, Alok; ÇAĞILTAY, Nergiz; KILIÇ, ÖzkanSoftware engineering education has been emerging as an independent and mature discipline. Accord ingly, various studies are being done to provide guidelines for curriculum design. The main focus of these guidelines is around core and foundation courses. This paper summarizes the current problems of software engineering education programs. It also proposes some important dimensions as integral parts of software engineering education: interdisciplinary skills, practice experience, communication, skills on continuing education and professionalism. In the current guidelines and studies these dimensions are not addressed specifically. Although there could be other dimensions to be considered in software engineering education, we believe that the proposed ones are very crucial as software engineering is evolving more rapidly than any other engineering discipline. This study also provides a survey of some major universities’ undergraduate software engineering programs to evaluate these dimensions.