Faculty of Computing

Permanent URI for this communityhttps://repository.nileuniversity.edu.ng/handle/123456789/13

Browse

Start date: 2020End date: 2024

Search Results

Now showing 1 - 10 of 36
  • No Thumbnail Available
    Item
    Remote Sensing Image Classification for Land Cover Mapping in Developing Countries
    (IJCSNS International Journal of Computer Science and Network Security, 2022-02-05) Nwojo Agwu Nnanna; Moussa Mahamat Boukar
    Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.
  • No Thumbnail Available
    Item
    Test Case Generation Approach for Android Applications using Reinforcement Learning
    (Engineering, Technology & Applied Science Research, 2024-04-27) Moussa Mahamat Boukar; Muhammed Aliyu Suleiman; Ibrahim Anka Salihu
    Mobile applications can recognize their computational setting and adjust and respond to actions in the context. This is known as context-aware computing. Testing context-aware applications is difficult due to their dynamic nature, as the context is constantly changing. Most mobile testing tools and approaches focus only on GUI events, adding to the deficient coverage of applications throughout testing. Generating test cases for various context events in Android applications can be achieved using reinforcement learning algorithms. This study proposes an approach for generating Android application test cases based on Expected State-Action-Reward-State-Action (E-SARSA), considering GUI and context events for effective testing. The proposed method was experimentally evaluated on eight Android applications, showing 48- 96% line of code coverage across them, which was higher than Q-testing and SARSA.
  • No Thumbnail Available
    Item
    Evaluation of Collision Resolution Methods Using Asymptotic Analysis
    (IEEE, 2021-02-02) Saleh Abdullahi; Moussa Mahamat Boukar; Salisu Ibrahim Yusuf
  • No Thumbnail Available
    Item
    Graphic User Interface for Hausa Text-to-Speech System
    (IEEE, 2022-02-02) Umar Adam Ibrahim; Moussa Mahamat Boukar; Muhammed Aliyu Suleiman
    Natural language processing and Digital signal processing are broadly used methods used to enable systems to understand commands and manipulate speech or text. Most of the Text-to-speech done was for major languages such as English, French and others, with no or little for African languages like Hausa, which are termed under resource languages. In this paper, we developed a graphical user interface for the Hausa Text-to-Speech system. This system converts Hausa text to Hausa audio sound, by processing and analyzing it using natural language processing and Digital Signal Processing. Our graphical user interface, aid in converting entered Hausa language text into Hausa speech.
  • No Thumbnail Available
    Item
    Hepatitis C Stage Classification with hybridization of GA and Chi2 Feature Selection
    (IJCSNS International Journal of Computer Science and Network Security, 2022-02-02) Steve Adeshina; Moussa Mahamat Boukar
    In metaheuristic algorithms such as Genetic Algorithm (GA), initial population has a significant impact as it affects the time such algorithm takes to obtain an optimal solution to the given problem. In addition, it may influence the quality of the solution obtained. In the machine learning field, feature selection is an important process to attaining a good performance model; Genetic algorithm has been utilized for this purpose by scientists. However, the characteristics of Genetic algorithm, namely random initial population generation from a vector of feature elements, may influence solution and execution time. In this paper, the use of a statistical algorithm has been introduced (Chi2) for feature relevant checks where p-values of conditional independence were considered. Features with low p-values were discarded and subject relevant subset of features to Genetic Algorithm. This is to gain a level of certainty of the fitness of features randomly selected. An ensembled-based learning model for Hepatitis has been developed for Hepatitis C stage classification. 1385 samples were used using Egyptian-dataset obtained from UCI repository. The comparative evaluation confirms decreased in execution time and an increase in model performance accuracy from 56% to 63%.
  • No Thumbnail Available
    Item
    Improving the Accuracy of Animal Species Classification in Camera Trap Images Using Transfer Learning
    (International Conference on Artificial Intelligence, Computer, Data Sciences and Application, 2024-02-02) Moussa Mahamat Boukar
    Understanding biodiversity, monitoring endangered species, and estimating the possible effect of climate change on particular regions all rely on animal species identification. Closed-circuit television (CCTV) cameras, which can collect huge volumes of video data, are an excellent environmental monitoring tool. However, manually evaluating these massive datasets is time-consuming, difficult, and expensive, emphasizing the need for automated ecological analysis.Deep learning models have transformed computer vision, handling problems such as object and species detection. Their cutting-edge performance qualifies them for this application. The purpose of this work was to create and test machine learning models for distinguishing diverse animal species using camera trap images. On VGG19, GoogLeNet (InceptionV3), ResNet50, and DenseNet121, we used transfer learning. The best multi- classification accuracy was attained by GoogLeNet (87%), followed by ResNet50 (83%), DenseNet (81%), and VGG19 (53%). This evidence suggests that transfer learning outperforms training models from scratch for this task.
  • No Thumbnail Available
    Item
    The Impact of Artificial Intelligence (AI) on Content Management Systems (CMS)
    (International Journal of Intelligent Systems and Applications in Engineering, 2024-02-02) Moussa Mahamat Boukar
    The dynamic nature of the global environment is always changing, with technology playing a pivotal role in propelling these shifts. The emergence of artificial intelligence (AI) has fundamentally transformed the manner in which we oversee and engage with our digital data. The potential of integrating artificial intelligence (AI) with content management systems (CMS) holds significant promise for future advancements. Artificial intelligence (AI) has the potential to bring about substantial changes in the manner in which information is managed and shared on the internet. It can enhance search functionalities and streamline numerous processes via automation. Individuals engaged in website ownership, content generation, and marketing are required to acquaint themselves with the most recent advancements in content management systems (CMS) and artificial intelligence (AI). The objective of this article is to provide a comprehensive examination of the influence of artificial intelligence (AI) on content management systems (CMS), along with an analysis of emerging AI methodologies and their practical use within a corporate environment.
  • No Thumbnail Available
    Item
    TEGDroid: Test Case Generation Approach for Android Apps Considering Context and GUI Events
    (International Journal on Advanced Science Engineering Information Technology, 2020-02-02) Ibrahim Anka Salihu
    The advancement in mobile technologies has led to the production of mobile devices (e.g. smartphone) with rich innovative features. This has enabled the development of mobile applications that offer users an advanced and extremely localized context-aware content. The recent dependence of people on mobile applications for various computational needs poses a significant concern on the quality of mobile applications. In order to build a high quality and more reliable applications, there is a need for effective testing techniques to test the applications. Most existing testing technique focuses on GUI events only without sufficient support for context events. This makes it difficult to identify other defects in the changes that can be inclined by context in which an application runs. This paper presents an approach named TEGDroid for generating test case for Android Apps considering both context and GUI Events. The GUI and context events are identified through the static analysis of bytecode, and the analysis of app’s permission from the XML file. An experiment was performed on real world mobile apps to evaluate TEGDroid. Our experimental results show that TEGDroid is effective in identifying context events and had 65%-91% coverage across the eight selected applications. To evaluate the fault detection capability of this approach, mutation testing was performed by introducing mutants to the applications. Results from the mutation analysis shows that 100% of the mutants were killed. This indicates that TEGDroid have the capability to detect faults in mobile apps.
  • No Thumbnail Available
    Item
    Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications
    (MDPI, 2022-04-14) Bilkisu Muhammad-Bello; Ibrahim Anka Salihu
    Software and symmetric testing methodologies are primarily used in detecting software defects, but these testing methodologies need to be optimized to mitigate the wasting of resources. As mobile applications are becoming more prevalent in recent times, the need to have mobile applications that satisfy software quality through testing cannot be overemphasized. Testing suites and software quality assurance techniques have also become prevalent, which underscores the need to evaluate the efficacy of these tools in the testing of the applications. Mutation testing is one such technique, which is the process of injecting small changes into the software under test (SUT), thereby creating mutants. These mutants are then tested using mutation testing techniques alongside the SUT to determine the effectiveness of test suites through mutation scoring. Although mutation testing is effective, the cost of implementing it, due to the problem of equivalent mutants, is very high. Many research works gave varying solutions to this problem, but none used a standardized dataset. In this research work, we employed a standard mutant dataset tool called MutantBench to generate our data. Subsequently, an Abstract Syntax Tree (AST) was used in conjunction with a tree-based convolutional neural network (TBCNN) as our deep learning model to automate the classification of the equivalent mutants to reduce the cost of mutation testing in software testing of android applications. The result shows that the proposed model produces a good accuracy rate of 94%, as well as other performance metrics such as recall (96%), precision (89%), F1-score (92%), and Matthew’s correlation coefficients (88%) with fewer False Negatives and False Positives during testing, which is significant as it implies that there is a decrease in the risk of misclassification.
  • No Thumbnail Available
    Item
    Mutation Testing Techniques for Android Applications: A Comparative Study
    (International Conference on Multidisciplinary Engineering and Applied Science, 2023-02-02) Ibrahim Anka Salihu
    Mobile applications are becoming increasingly used to achieve various computing needs. Hence, it is essential to guarantee quality of the applications. Software testing has been the main activity for ensuring the quality of software, however, it is a critical and costly activity. Furthermore, code coverage is commonly used as metric for verifying the effectiveness of testing technique. However, numerous researchers and experts claimed that considering code coverage only to ascertain the testing quality is not enough to ensure quality of apps. In view of this, mutation testing has been introduced to complement the procedure by assuring that apps behave as expected and are released free of faults. Several techniques/tools were proposed based on different syntax and mutation operators. This study presents a comparative study of six (6) mutation techniques/tools for Android applications to highlight their strengths and weakness which will give an insight to researchers on the directions for further research