Abdijalil Abdullahi | SIMAD University (original) (raw)

Uploads

Papers by Abdijalil Abdullahi

Research paper thumbnail of A comparative analysis of cervical cancer diagnosis using machine learning techniques

Indonesian journal of electrical engineering and computer science, May 1, 2024

This study undertakes a comprehensive analysis of cervical cancer diagnosis using machine learnin... more This study undertakes a comprehensive analysis of cervical cancer diagnosis using machine learning (ML) techniques. We start by introducing the critical importance of early and accurate diagnosis of cervical cancer, a significant health issue globally. The objective of this research is to compare the effectiveness of three ML algorithms: K-nearest neighbors (KNN), linear support vector machine (SVM), and Naive Bayes classifier, in predicting biopsy results for cervical cancer. Our methodology involves utilizing a substantial dataset to train and test these algorithms, focusing on performance measures like accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUC). The findings reveal that KNN demonstrates superior performance, with high precision, recall, accuracy, and F1 score, alongside a notable AUC. This suggests KNN's potential utility in clinical applications for cervical cancer prognosis. Meanwhile, linear SVM and Naive Bayes exhibit certain limitations, indicating a need for further optimization. This study highlights the promising role of ML in enhancing medical diagnostic processes, particularly in oncology.

Research paper thumbnail of A machine learning approach to cardiovascular disease prediction with advanced feature selection

Indonesian Journal of Electrical Engineering and Computer Science, Jan 31, 2024

Cardiovascular diseases (CVDs) pose a significant global public health challenge, necessitating p... more Cardiovascular diseases (CVDs) pose a significant global public health challenge, necessitating precise risk assessment for proactive treatment and optimal utilization of healthcare resources. This study employs machine learning algorithms and sophisticated feature selection techniques to enhance the accuracy and comprehensibility of CVD prediction models. While traditional risk assessment tools are valuable, they frequently fail to consider the myriad intricate factors that contribute to the heightened risk of CVD. Our methodology employs machine learning algorithms to analyze diverse healthcare data sources and produce advanced predictive models. The salient feature of this research lies in the meticulous application of advanced feature selection techniques, enabling the identification of pivotal factors within heterogeneous datasets. Optimizing feature selection enhances the interpretability of the model, reduces dimensionality, and improves predictive accuracy. The area under the ROC curve (AUC-ROC) score of the wrapper method model significantly decreased from 95.1% to 75.1% after tuning, based on empirical tests that supported the suggested method. This showcases its capacity as a tool for assessing premature CVD susceptibility and developing tailored healthcare strategies. The study highlights the significance of integrating machine learning with feature selection due to the widespread influence of cardiovascular diseases. Integrating this system has the potential to enhance patient care and optimize the utilization of healthcare resources.

Research paper thumbnail of A Review of Scalability Issues in Software-Defined Exchange Point (SDX) Approaches: State-of-the-Art

IEEE Access, 2021

Internet Exchange Points (IXPs) interconnect heterogeneous networks and transfer substantial traf... more Internet Exchange Points (IXPs) interconnect heterogeneous networks and transfer substantial traffic volumes. In the past decade, the number of IXPs has seen tremendous growth, with more operators connecting to these IXPs even though these IXPs faced various inter-domain routing limitations. Routers based on Border Gateway Protocol (BGP) forwards packets only based on destination IP prefix and selects only routes learned from their neighbors. IXPs designed using Software-Defined Network (SDN), called SDX, offer solutions for existing inter-domain routing problems. This paper presents the existing scalability limitations of inter-domain routing at IXP and how traditional IXP structural design can be transformed into a highly scalable SDX design by exploiting the SDN platform's functionalities in different use cases of SDX. The paper then reviewed how the SDX improved various IXP operators' scalability by reviewing and analyzing the latest SDX models and approaches, which provide enhanced policies to enhance providers' management operations and offer good quality of services (QoS) to the various participating members. Finally, we discussed the open issues and challenges in this area that need further study and a solution to tackle them. INDEX TERMS Internet exchange point, border gateway protocol, software-defined network, software-defined exchange, inter-domain routing, peering.

Research paper thumbnail of Proposed enhanced link failure rerouting mechanism for software-defined exchange point

Indonesian Journal of Electrical Engineering and Computer Science

Internet eXchange point (IXP) is a way to optimize network bandwidth. It enables a platform in th... more Internet eXchange point (IXP) is a way to optimize network bandwidth. It enables a platform in the different providers like internet service providers (ISPs) and content delivery providers (CDNs) to share their traffic through a common point. A software defined exchange point (SDX) is an IXP comprising of a programmable deployed software defined network (SDN) switching fabric to enhance the management of their services, but they met the performance issues. The previous studies proposed various mechanisms and frameworks that tackled with these issues, but they don’t overcome overall challenges like link failure recovery for multi-hop-based SDX particularly packet processing delay and switch memory overhead. To cope with these issues, this paper proposed an enhanced link failure rerouting (ELFR) mechanism for multi-hop-based SDX. The objective of the proposed ELFR mechanism is to reduce the delay of packet processing to recover the link failure quickly and improve the path computation...

Research paper thumbnail of Cybersecurity awareness among university students in Mogadishu: a comparative study

Indonesian Journal of Electrical Engineering and Computer Science, 2023

This study aimed to assess the level of cyber security awareness among graduate and undergraduate... more This study aimed to assess the level of cyber security awareness among graduate and undergraduate students in five universities in Mogadishu. The study used a one-way analysis of variance (ANOVA) to examine the difference in cyber security awareness levels between graduate and undergraduate students across five reputable universities. The questionnaire method was used to collect data from 250 graduate and undergraduate students from SIMAD, SIU, UNISO, Jamhuriya, and Mogadishu universities. The cross-tabulation result showed that there was a significant difference in cyber security awareness levels between the universities. Specifically, the results showed that students from SIMAD and Jamhuriya universities suffered from virus attacks, while SIU students struggled with password strength and social network misuse. Mogadishu students faced phishing and virus attacks, and UNISO students dealt with both virus attacks and password strength issues. The study recommended that universities educate their students and parents on safe internet usage and cybersecurity and monitor and secure their internet and computer services. Additionally, the authors recommended the development of cybersecurity software to help students use their data confidently and securely.

Research paper thumbnail of A comparative analysis of cervical cancer diagnosis using machine learning techniques

Indonesian journal of electrical engineering and computer science, May 1, 2024

This study undertakes a comprehensive analysis of cervical cancer diagnosis using machine learnin... more This study undertakes a comprehensive analysis of cervical cancer diagnosis using machine learning (ML) techniques. We start by introducing the critical importance of early and accurate diagnosis of cervical cancer, a significant health issue globally. The objective of this research is to compare the effectiveness of three ML algorithms: K-nearest neighbors (KNN), linear support vector machine (SVM), and Naive Bayes classifier, in predicting biopsy results for cervical cancer. Our methodology involves utilizing a substantial dataset to train and test these algorithms, focusing on performance measures like accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUC). The findings reveal that KNN demonstrates superior performance, with high precision, recall, accuracy, and F1 score, alongside a notable AUC. This suggests KNN's potential utility in clinical applications for cervical cancer prognosis. Meanwhile, linear SVM and Naive Bayes exhibit certain limitations, indicating a need for further optimization. This study highlights the promising role of ML in enhancing medical diagnostic processes, particularly in oncology.

Research paper thumbnail of A machine learning approach to cardiovascular disease prediction with advanced feature selection

Indonesian Journal of Electrical Engineering and Computer Science, Jan 31, 2024

Cardiovascular diseases (CVDs) pose a significant global public health challenge, necessitating p... more Cardiovascular diseases (CVDs) pose a significant global public health challenge, necessitating precise risk assessment for proactive treatment and optimal utilization of healthcare resources. This study employs machine learning algorithms and sophisticated feature selection techniques to enhance the accuracy and comprehensibility of CVD prediction models. While traditional risk assessment tools are valuable, they frequently fail to consider the myriad intricate factors that contribute to the heightened risk of CVD. Our methodology employs machine learning algorithms to analyze diverse healthcare data sources and produce advanced predictive models. The salient feature of this research lies in the meticulous application of advanced feature selection techniques, enabling the identification of pivotal factors within heterogeneous datasets. Optimizing feature selection enhances the interpretability of the model, reduces dimensionality, and improves predictive accuracy. The area under the ROC curve (AUC-ROC) score of the wrapper method model significantly decreased from 95.1% to 75.1% after tuning, based on empirical tests that supported the suggested method. This showcases its capacity as a tool for assessing premature CVD susceptibility and developing tailored healthcare strategies. The study highlights the significance of integrating machine learning with feature selection due to the widespread influence of cardiovascular diseases. Integrating this system has the potential to enhance patient care and optimize the utilization of healthcare resources.

Research paper thumbnail of A Review of Scalability Issues in Software-Defined Exchange Point (SDX) Approaches: State-of-the-Art

IEEE Access, 2021

Internet Exchange Points (IXPs) interconnect heterogeneous networks and transfer substantial traf... more Internet Exchange Points (IXPs) interconnect heterogeneous networks and transfer substantial traffic volumes. In the past decade, the number of IXPs has seen tremendous growth, with more operators connecting to these IXPs even though these IXPs faced various inter-domain routing limitations. Routers based on Border Gateway Protocol (BGP) forwards packets only based on destination IP prefix and selects only routes learned from their neighbors. IXPs designed using Software-Defined Network (SDN), called SDX, offer solutions for existing inter-domain routing problems. This paper presents the existing scalability limitations of inter-domain routing at IXP and how traditional IXP structural design can be transformed into a highly scalable SDX design by exploiting the SDN platform's functionalities in different use cases of SDX. The paper then reviewed how the SDX improved various IXP operators' scalability by reviewing and analyzing the latest SDX models and approaches, which provide enhanced policies to enhance providers' management operations and offer good quality of services (QoS) to the various participating members. Finally, we discussed the open issues and challenges in this area that need further study and a solution to tackle them. INDEX TERMS Internet exchange point, border gateway protocol, software-defined network, software-defined exchange, inter-domain routing, peering.

Research paper thumbnail of Proposed enhanced link failure rerouting mechanism for software-defined exchange point

Indonesian Journal of Electrical Engineering and Computer Science

Internet eXchange point (IXP) is a way to optimize network bandwidth. It enables a platform in th... more Internet eXchange point (IXP) is a way to optimize network bandwidth. It enables a platform in the different providers like internet service providers (ISPs) and content delivery providers (CDNs) to share their traffic through a common point. A software defined exchange point (SDX) is an IXP comprising of a programmable deployed software defined network (SDN) switching fabric to enhance the management of their services, but they met the performance issues. The previous studies proposed various mechanisms and frameworks that tackled with these issues, but they don’t overcome overall challenges like link failure recovery for multi-hop-based SDX particularly packet processing delay and switch memory overhead. To cope with these issues, this paper proposed an enhanced link failure rerouting (ELFR) mechanism for multi-hop-based SDX. The objective of the proposed ELFR mechanism is to reduce the delay of packet processing to recover the link failure quickly and improve the path computation...

Research paper thumbnail of Cybersecurity awareness among university students in Mogadishu: a comparative study

Indonesian Journal of Electrical Engineering and Computer Science, 2023

This study aimed to assess the level of cyber security awareness among graduate and undergraduate... more This study aimed to assess the level of cyber security awareness among graduate and undergraduate students in five universities in Mogadishu. The study used a one-way analysis of variance (ANOVA) to examine the difference in cyber security awareness levels between graduate and undergraduate students across five reputable universities. The questionnaire method was used to collect data from 250 graduate and undergraduate students from SIMAD, SIU, UNISO, Jamhuriya, and Mogadishu universities. The cross-tabulation result showed that there was a significant difference in cyber security awareness levels between the universities. Specifically, the results showed that students from SIMAD and Jamhuriya universities suffered from virus attacks, while SIU students struggled with password strength and social network misuse. Mogadishu students faced phishing and virus attacks, and UNISO students dealt with both virus attacks and password strength issues. The study recommended that universities educate their students and parents on safe internet usage and cybersecurity and monitor and secure their internet and computer services. Additionally, the authors recommended the development of cybersecurity software to help students use their data confidently and securely.