The software project director has to keep estimating the required resources and planning the sche... more The software project director has to keep estimating the required resources and planning the schedule for deliverables. Unfortunately, such estimation and planning are not accurate unless careful monitoring and control plan is maintained because software development is risky. In this paper, an investigation was carried out by integrating a promising metaheuristic algorithm with an artificial neural network to optimize the network parameters to address predicting the size of a software test team. The target of this integration was to enhance the accuracy of network prediction. The proposed method has been evaluated on two datasets. These datasets have different characteristics and have been extracted from the industry repository. The comparative results proved the superiority of the proposed method over the other methods.
COVID-19 data analysis and prediction from patient data repository collected from hospitals and h... more COVID-19 data analysis and prediction from patient data repository collected from hospitals and health organizations. Users’ credentials and personal information are at risk; it could be an unrecoverable issue worldwide. A Homomorphic identification of possible breaches could be more appropriate for minimizing the risk factors in preventing personal data. Individual user privacy preservation is a must-needed research focus in various fields. Health data generated and collected information from multiple scenarios increasing the complexity involved in maintaining secret patient information. A homomorphic-based systematic approach with a deep learning process could reduce depicts and illegal functionality of unknown organizations trying to have relation to the environment and physical and social relations. This article addresses the homomorphic standard system functionality, which refers to all the functional aspects of deep learning system requirements in COVID-19 health management. Moreover, this paper spotlights the metric privacy incorporation for improving the Deep Learning System (DPLS) approaches for solving the healthcare system’s complex issues. It is absorbed from the result analysis Homomorphic-based privacy observation metric gradually improves the effectiveness of the deep learning process in COVID-19-health care management.
International Journal of Critical Infrastructure Protection, Sep 1, 2021
Abstract Network security is a mechanism of protecting the usability and integrity of any given n... more Abstract Network security is a mechanism of protecting the usability and integrity of any given network and its transmitted data. Network security's effectiveness is crucial to the network environment to ensure it is free from any threat, especially in the critical infrastructure (CI). The supervisory control and data acquisition systems in the CI are getting more connected to the internet, putting them in serious security concerns. Any malicious attack against these systems could cause considerable human, economic, and material damages. Thus, it leads to the emergence of the intrusion detection system (IDS). Theoretically, a modern IDS must handle a large amount of data with high accuracy. Ensemble-based, hybrid-based methods and their distinguished applications are a promising way to solve these issues. The efficiency of the IDS is mainly dependent on the selected data features and the used classification method. The artificial neural network (ANN) has been applied in various fields, but it requires adjustment on few parameters to work effectively. This study proposes a homogeneous ensemble based on single-class dynamic ANN (HOE-DANN). Each dynamic ANN (DANN) is optimized by a filter-wrapper method using a modified discrete cuttlefish algorithm based on rough set theory, and a migration-strategy based cuttlefish algorithm. Both algorithms simultaneously optimize the features, ANN structure, weights, and biases for creating the DANN. However, the threshold value of the ensemble model was set using the hill-climbing algorithm. The experiments were applied to well-known benchmark datasets, namely the KDD99, UNSW-NB15, and gas pipeline data logs (GPDL). The results show that the HOE-DANN outperforms the single model based on the DANN. Additionally, a comparison with several state-of-the-art methods has shown that the proposed method offers superior performance in terms of the detection rate (DR), false alarm rate (FAR), and classification accuracy (ACC). The HOE-DANN model was able to achieve DR of 97.47%, FAR of 2.25%, and ACC of 97.52% using the KDD99 dataset, DR of 99.93%, FAR of 13.13%, and ACC of 94.08% using the UNSW-NB15 dataset, and DR of 98.08%, FAR of 2.69%, and ACC of 94.50% using the GPDL dataset.
COMPUSOFT: An International Journal of Advanced Computer Technology, Apr 30, 2020
An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. Ho... more An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. However, developing an expert system for medical diagnose requires a robust reasoning capability. In the knowledge acquisition phase, a knowledge engineer faces several issues. For example, an eye disease may contain several similar symptoms to another eye disease. Even worse, a patient may input a set of symptoms that can be attributable to several diseases, and these symptoms may not be readily quantifiable. Dempster-Shafer Theory (DST) and Bayesian Network (BN) are two commonly used techniques for combining uncertain evidence. The literature review showed that there have been no studies, either using BNs or DST, to diagnose eye diseases with a comparative study about both methods, BNs and DST. This paper study the effectiveness and reliability of DST and BN as the reasoning engine of an expert system for early diagnose of eye disease. The primary sources of knowledge on eye diseases are the patient files and human experts. Data were collected from hospitals and ophthalmologists in Riau, Indonesia. BN and DST framework was used to model and estimate the probability of eye diseases in supporting decision making, i.e. diagnosis. Rule-Based Reasoning and the Forward Chaining methods are applied in developing the reasoning structure. The Expert System Development Life Cycle (ESDLC) methodology is used to structure, plan and control the process of developing the expert system. In this study, 20 physical symptoms of illness obtained from the patients' files are used for diagnosing six types of eye diseases. The result of this study is accomplished by comparing the expert system diagnostic results with a human expert diagnostic result. Based on the testing of 10 eye diseases cases, the accuracy of the BN is higher compared to DST.
The software project director has to keep estimating the required resources and planning the sche... more The software project director has to keep estimating the required resources and planning the schedule for deliverables. Unfortunately, such estimation and planning are not accurate unless careful monitoring and control plan is maintained because software development is risky. In this paper, an investigation was carried out by integrating a promising metaheuristic algorithm with an artificial neural network to optimize the network parameters to address predicting the size of a software test team. The target of this integration was to enhance the accuracy of network prediction. The proposed method has been evaluated on two datasets. These datasets have different characteristics and have been extracted from the industry repository. The comparative results proved the superiority of the proposed method over the other methods.
COVID-19 data analysis and prediction from patient data repository collected from hospitals and h... more COVID-19 data analysis and prediction from patient data repository collected from hospitals and health organizations. Users’ credentials and personal information are at risk; it could be an unrecoverable issue worldwide. A Homomorphic identification of possible breaches could be more appropriate for minimizing the risk factors in preventing personal data. Individual user privacy preservation is a must-needed research focus in various fields. Health data generated and collected information from multiple scenarios increasing the complexity involved in maintaining secret patient information. A homomorphic-based systematic approach with a deep learning process could reduce depicts and illegal functionality of unknown organizations trying to have relation to the environment and physical and social relations. This article addresses the homomorphic standard system functionality, which refers to all the functional aspects of deep learning system requirements in COVID-19 health management. Moreover, this paper spotlights the metric privacy incorporation for improving the Deep Learning System (DPLS) approaches for solving the healthcare system’s complex issues. It is absorbed from the result analysis Homomorphic-based privacy observation metric gradually improves the effectiveness of the deep learning process in COVID-19-health care management.
International Journal of Critical Infrastructure Protection, Sep 1, 2021
Abstract Network security is a mechanism of protecting the usability and integrity of any given n... more Abstract Network security is a mechanism of protecting the usability and integrity of any given network and its transmitted data. Network security's effectiveness is crucial to the network environment to ensure it is free from any threat, especially in the critical infrastructure (CI). The supervisory control and data acquisition systems in the CI are getting more connected to the internet, putting them in serious security concerns. Any malicious attack against these systems could cause considerable human, economic, and material damages. Thus, it leads to the emergence of the intrusion detection system (IDS). Theoretically, a modern IDS must handle a large amount of data with high accuracy. Ensemble-based, hybrid-based methods and their distinguished applications are a promising way to solve these issues. The efficiency of the IDS is mainly dependent on the selected data features and the used classification method. The artificial neural network (ANN) has been applied in various fields, but it requires adjustment on few parameters to work effectively. This study proposes a homogeneous ensemble based on single-class dynamic ANN (HOE-DANN). Each dynamic ANN (DANN) is optimized by a filter-wrapper method using a modified discrete cuttlefish algorithm based on rough set theory, and a migration-strategy based cuttlefish algorithm. Both algorithms simultaneously optimize the features, ANN structure, weights, and biases for creating the DANN. However, the threshold value of the ensemble model was set using the hill-climbing algorithm. The experiments were applied to well-known benchmark datasets, namely the KDD99, UNSW-NB15, and gas pipeline data logs (GPDL). The results show that the HOE-DANN outperforms the single model based on the DANN. Additionally, a comparison with several state-of-the-art methods has shown that the proposed method offers superior performance in terms of the detection rate (DR), false alarm rate (FAR), and classification accuracy (ACC). The HOE-DANN model was able to achieve DR of 97.47%, FAR of 2.25%, and ACC of 97.52% using the KDD99 dataset, DR of 99.93%, FAR of 13.13%, and ACC of 94.08% using the UNSW-NB15 dataset, and DR of 98.08%, FAR of 2.69%, and ACC of 94.50% using the GPDL dataset.
COMPUSOFT: An International Journal of Advanced Computer Technology, Apr 30, 2020
An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. Ho... more An accurate self-diagnosis expert system would prevent the progression of chronic eye disease. However, developing an expert system for medical diagnose requires a robust reasoning capability. In the knowledge acquisition phase, a knowledge engineer faces several issues. For example, an eye disease may contain several similar symptoms to another eye disease. Even worse, a patient may input a set of symptoms that can be attributable to several diseases, and these symptoms may not be readily quantifiable. Dempster-Shafer Theory (DST) and Bayesian Network (BN) are two commonly used techniques for combining uncertain evidence. The literature review showed that there have been no studies, either using BNs or DST, to diagnose eye diseases with a comparative study about both methods, BNs and DST. This paper study the effectiveness and reliability of DST and BN as the reasoning engine of an expert system for early diagnose of eye disease. The primary sources of knowledge on eye diseases are the patient files and human experts. Data were collected from hospitals and ophthalmologists in Riau, Indonesia. BN and DST framework was used to model and estimate the probability of eye diseases in supporting decision making, i.e. diagnosis. Rule-Based Reasoning and the Forward Chaining methods are applied in developing the reasoning structure. The Expert System Development Life Cycle (ESDLC) methodology is used to structure, plan and control the process of developing the expert system. In this study, 20 physical symptoms of illness obtained from the patients' files are used for diagnosing six types of eye diseases. The result of this study is accomplished by comparing the expert system diagnostic results with a human expert diagnostic result. Based on the testing of 10 eye diseases cases, the accuracy of the BN is higher compared to DST.
Uploads
Papers by Salwani Abdullah