Hemin Sardar Abdulla

Mr. Hemin Sardar Abdulla

Computer Science, Charmo University, Sulaymaniyah, Iraq
orcid
Life Full of Ups And Downs

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 September 2024 in Algorithms
Verified
Journal Article
Open access
PDF file
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
Azad Abdullah AmeenAzad Abdullah Ameen
Azad Abdullah Ameen
SSSarwar Saeed
Sarwar Saeed
IMIsmail Asaad Mohammed
Ismail Asaad Mohammed
Tarik RashidTarik Rashid
Tarik Rashid
The rapid advancement of intelligent technology has led to the development of optimization algorithms that leverage natural behaviors to address complex issues. Among these, the Rat Swarm Optimizer (RSO), inspired by rats’ social and behavioral characteristics, has demonstrated potential in various domains, although its convergence precision and exploration capabilities are limited. To address these shortcomings, this study introduces the Modified Rat Swarm Optimizer (MRSO), designed to enhance the balance between exploration and exploitation. The MRSO incorporates unique modifications to improve search efficiency and robustness, making it suitable for challenging engineering problems such as Welded Beam, Pressure Vessel, and Gear Train Design. Extensive testing with classical benchmark functions shows that the MRSO significantly improves performance, avoiding local optima and achieving higher accuracy in six out of nine multimodal functions and in all seven fixed-dimension multimodal functions. In the CEC 2019 benchmarks, the MRSO outperforms the standard RSO in six out of ten functions, demonstrating superior global search capabilities. When applied to engineering design problems, the MRSO consistently delivers better average results than the RSO, proving its effectiveness. Additionally, we compared our approach with eight recent and well-known algorithms using both classical and CEC-2019 benchmarks. The MRSO outperformed each of these algorithms, achieving superior results in six out of 23 classical benchmark functions and in four out of ten CEC-2019 benchmark functions. These results further demonstrate the MRSO’s significant contributions as a reliable and efficient tool for optimization tasks in engineering applications.
1

8 February 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
Aso Mohammed AladdinAso Mohammed Aladdin
Aso Mohammed Aladdin
Multilevel security (MLS) is particularly intended to secure information against unauthorized access. An MLS security DBMS allows users with different security levels to access and share a database. For this purpose, the study creates a model that includes a restricted access authentication prototype with multilevel security in a database management system (MLS/DBMS). Accordingly, the model has been designed to emphasize the highest level of authorized security. The system ensures that users can only access information that they are permitted to view, fully adhering to the newly established MLS framework. In addition, the model also integrates cryptographic algorithms, such as RSA and AES, to enhance its functionality and demonstrate the scalability and security of the model. These criteria are defined based on the perspective of the database provided to users, determined by their respective authorization levels. An informal security framework for a multilevel secure DBMS is defined. It includes a classification strategy and explains the implementation of operations like insertion and deletion, addressing the complexity of models with novel methods. The metric evaluation of this model assesses the performance of the authentication process and how operations are implemented across three authentication group types. It also calculates the key generation time and encryption types in cryptographic algorithms. The results confirm that the RSA model requires less time for evaluation while maintaining multilevel security. Furthermore, the type 2 authentication group is more complex and requires more memory and time for generation. Based on the classification, the results highlight notable differences, which designers should consider when selecting authentication methods. Lastly, the study presents various conclusions, explores possible future directions, and discusses its limitations.
1

16 November 2025 in InfoTech Spectrum: Iraqi Journal of Data Science
Verified
Journal Article
Open access
PDF file
Aso Mohammed AladdinAso Mohammed Aladdin
Aso Mohammed Aladdin
rebwar khalid muhammedrebwar khalid muhammed
rebwar khalid muhammed
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
Tarik RashidTarik Rashid
Tarik Rashid
Artificial Intelligence (AI) has made advancements, among other things, OpenAI created the sophisticated model ChatGPT. Conversational, ChatGPT supports natural interactions, providing human-like responses to queries across myriad topics. But it is not infallible, and the degree of accuracy also depends on the complexity of the queries, the context, and how often the prompts are repeated. This work thus proposes a new model, the Precision Answer Comparison and Evaluation Model (PACEM), to systematically address these types of questions and assess ChatGPT's performance. PACEM assesses the correctness and coherence of ChatGPT's answers across numerous fields, including literature, history, law, ethics, and sports. By providing these analyses and comparisons, PACEM goes on record with a detailed understanding of what ChatGPT does well and poorly as a source of reliable information. On top of that, it includes an assessment of response time, considering ChatGPT's speed in producing answers in relation to real or expected ones. The findings show that ChatGPT's answers are usually substantially accurate and often of superior quality compared to those written by the user and other alternatives. Response time generally increases with the complexity or length of the answer. Finally, the study reviews notable takeaways from PACEM's deployment and offers suggestions for future research to address the evolving challenges in AI-driven response assessment.

7 October 2024 in TechRxiv
Verified
Preprint
Open access
AAAso M Aladdin
Aso M Aladdin
RMRebwar Khalid Muhammed
Rebwar Khalid Muhammed
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
Tarik RashidTarik Rashid
Tarik Rashid
Artificial Intelligence has made significant strides, leading to the creation of advanced models like ChatGPT, developed by OpenAI. ChatGPT interacts with users in a conversational style, generating human-like responses across various domains. Despite its versatility, the accuracy of ChatGPT's responses can vary depending on the context, the complexity of the queries, and the repetition of prompts within a short time frame. To address these challenges and highlight potential issues, propose the Precision Answer Comparison and Evaluation Model (PACEM), which is designed to thoroughly assess and evaluate ChatGPT's performance. PACEM focuses on evaluating ChatGPT's accuracy and consistency across diverse domains, including literature, history, law or ethics, and sports or athletics. By systematically comparing responses and measuring performance, PACEM provides a comprehensive analysis of ChatGPT's capabilities and limitations in delivering reliable information. Additionally, this model is equipped to measure the processing time during evaluation, considering the time taken by ChatGPT to generate responses compared to the actual answers. The model reveals that ChatGPT generally delivers high-performance and accurate responses, often surpassing those generated by humans or composed from alternative ideas. However, the evaluation also indicates that the processing time may increase when the responses are lengthy, despite the accuracy of the answers provided by ChatGPT. Finally, this study concludes with key findings and suggests future work to address new challenges that may arise in similar contexts.
1

1 July 2025 in UHD Journal of Science and Technology
Verified
Journal Article
Open access
AHAlla Ahmad Hassan
Alla Ahmad Hassan
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
TMTara Yousif Mawlood
Tara Yousif Mawlood
RMRebwar Khalid Muhammed
Rebwar Khalid Muhammed
AAAso M. Aladdin
Aso M. Aladdin
TRTarik A. Rashid
Tarik A. Rashid
This research analyzes the strengths and weaknesses of ChatGPT in responding to questions posed in the Kurdish language, specifically its Sorani dialect, by evaluating its responses to a structured dataset of 50 multiple-choice questions across multiple topics such as language, history, culture, and general knowledge. Using four independent user accounts, each subjected to ten repeated testing cycles, the research assesses accuracy, consistency, and variation influenced by account identity, session timing, and model behavior. This study evaluates the multilingual capabilities of ChatGPT by comparing its performance in Kurdish (Sorani) and Arabic languages. The research establishes a framework to examine how artificial intelligence chatbots, such as ChatGPT, function as applied tools for language understanding and educational use. The analysis demonstrates that ChatGPT achieved an overall average accuracy rate of approximately 70%, indicating satisfactory performance in multilingual contexts. However, significant variations were observed across different user accounts, suggesting that factors such as user profile and temporal dynamics can considerably influence output consistency. The comparative findings highlight the developmental challenges in Arabic and Kurdish language processing, emphasizing the need for further refinement of ChatGPT’s linguistic performance and its effective integration into academic and technological applications. While ChatGPT exhibited proficiency in answering general knowledge questions, it demonstrated a limited understanding of specialized topics in Kurdish, particularly classical literature and historical content. The research presents the strengths and limitations of ChatGPT for under-resourced languages and provides feedback to developers, educators, and researchers. Observing patterns in accuracy, question difficulty, and error behavior, this research also contributes to ongoing efforts toward improving the linguistic and cultural adequacy of AI models for under-resourced languages.

30 March 2026 in InfoTech Spectrum: Iraqi Journal of Data Science
Verified
Journal Article
Open access
PDF file
rebwar khalid muhammedrebwar khalid muhammed
rebwar khalid muhammed
Aso Mohammed AladdinAso Mohammed Aladdin
Aso Mohammed Aladdin
SHShilan Abdullah Hassan
Shilan Abdullah Hassan
Hemin Sardar AbdullaHemin Sardar Abdulla
Hemin Sardar Abdulla
MAMohammed Abubakr Ahmed
Mohammed Abubakr Ahmed
SSShaida Jumaah Sayda
Shaida Jumaah Sayda
With the expansion of AI applications into new horizons, security issues have become a top priority. Traditional AI systems are not very secure and are vulnerable to attacks and data breaches. The interconnected world we live in requires data to be kept private, protected, and verified, which can be achieved through modern security measures that incorporate cryptographic algorithms. This study evaluates the efficacy of five cryptographic algorithms, ARIA, ZUC, Advanced Encryption Standard (AES), Camellia, and HC256, regarding key generation duration, encryption and decryption speeds, and memory consumption to identify the optimal solution for practical implementations. Results show HC256 achieving the fastest encryption and decryption times of 105.6 ms and 75.6 ms, respectively, and the lowest memory usage of 1.28 MB for encryption and 1.38 MB for decryption, proving it is the most efficient in performance-sensitive settings. AES demonstrated balanced performance with moderate encryption and decryption times (116.6 ms and 115.6 ms, respectively) and relatively low memory consumption (6.36 MB), while maintaining strong cryptographic robustness. Camellia demonstrated strong cryptographic robustness according to previous literature; however, it exhibited the lowest computational efficiency in the present experimental evaluation, with the highest encryption and decryption times among the tested algorithms, but was found to yield the lowest efficiency for real-time applications, with the greatest encryption and decryption times of 1886.8 ms and 687 ms, respectively. ARIA and ZUC also exhibit different trade-offs, with ZUC showing moderate efficiency and ARIA requiring greater resources.