Sina Abdipoor

Dr. Sina Abdipoor

Data Science and Artificial Intelligence, Sunway University, Petaling Jaya, Selangor, Malaysia
+1
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 June 2023 in Intelligent Systems with Applications
Verified
Journal Article
Open access
Sina AbdipoorSina Abdipoor
Sina Abdipoor
RYRazali Yaakob
Razali Yaakob
SGSay Leng Goh
Say Leng Goh
SASalwani Abdullah
Salwani Abdullah

16 September 2023
Verified
Conference Paper
Closed access
SGSaeid Ghafouri
Saeid Ghafouri
Sina AbdipoorSina Abdipoor
Sina Abdipoor
JDJoseph Doyle
Joseph Doyle
One of the most challenging problems in the popular orchestration framework Kubernetes is assigning sufficient resources to containers to operate at a required level while also avoiding excessive resource allocation which can delay other jobs in the cluster. A variety of heuristic approaches have been proposed to tackle this problem but these require considerable manual adjustments which can be laborious. Reinforcement learning approaches have been proposed to address this issue but these proposals do not consider the energy consumption of the cluster. This is an important component of the problem due to the commitments of large cloud operators to carbon neutrality. We have proposed a system called Smart-Kube to achieve a target utilization on nodes while maintaining energy consumption at a reasonable level. An experimental framework is designed on top of real-world Kubernetes clusters and real-world traces of container jobs are used to evaluate the framework. Experimental results show that Smart-Kube can approach the target utilization and reduce energy consumption in a variety of ways depending on the preferences of the cluster operator for a variety of cluster sizes.

17 June 2023
Verified
Conference Paper
Closed access
Sina AbdipoorSina Abdipoor
Sina Abdipoor
RYRazali Yaakob
Razali Yaakob
SGSay Leng Goh
Say Leng Goh
SASalwani Abdullah
Salwani Abdullah
KKKhairul Azhar Kasmiran
Khairul Azhar Kasmiran
HHHazlina Hamdan
Hazlina Hamdan
The University Course Timetabling Problem is an active and complex field with broad implications at most educational institutions. The current gap between literature and real-world applications is among the foremost challenges in this domain. This gap can be attributed to the solvers’ lack of generality and/or inconsistency in problem definition. In an attempt to tackle this issue, the Student Sectioning Problem has been incorporated into the latest International Timetabling Competition benchmark dataset. This paper reviews, categorizes, and summarizes the approaches addressing the University Course Timetabling with Student Sectioning Problem. Furthermore, the strengths and limitations of these methods are analyzed. Challenges, gaps, and possible future work are also presented.

18 October 2024
Verified
Conference Paper
Closed access
HWHuijie Wang
Huijie Wang
YCYuanyuan Cai
Yuanyuan Cai
FYFabu Yue
Fabu Yue
HLHao Luo
Hao Luo
Sina AbdipoorSina Abdipoor
Sina Abdipoor
SGSay Leng Goh
Say Leng Goh
In an era where educational institutions are increasingly embracing technology to improve efficiency and enhance learning environments, the concept of smart campuses has emerged as a crucial development. The traditional approach of monitoring campus environments through video footage and manual inspections is becoming outdated as technology advances. To empower smarter campus management and enhance the educational experience, this study presents a systematic approach for smart campuses built on the foundation of digital twins. This technology creates a virtual replica of the physical campus, enabling real-time monitoring of various aspects like security, teaching, maintenance, environment, assets, and energy usage. We simulate real-world campus behavior by constructing this digital counterpart. The resulting digital twin image can be visualized through various user-friendly interfaces, including virtual reality and 3D models, empowering managers to make informed decisions for a more efficient and secure campus environment. Implementing a digital twin system in a smart campus setting demonstrates significant improvements in operational efficiency, security management, and environmental sustainability. By leveraging the power of digital twins, educational institutions can transition towards smarter, more responsive, and sustainable campus environments, ultimately enriching the educational experience for students and staff.

29 April 2025 in IEEE Access
Verified
Journal Article
Open access
Sina AbdipoorSina Abdipoor
Sina Abdipoor
RYRazali Yaakob
Razali Yaakob
SGSay Leng Goh
Say Leng Goh
SASalwani Abdullah
Salwani Abdullah
HHHAZLINA HAMDAN
HAZLINA HAMDAN
KKKhairul Azhar Kasmiran
Khairul Azhar Kasmiran
Educational timetabling, a principal branch of operations research, presents challenging combinatorial optimization problems widely encountered in educational institutions. Meta-heuristics have commonly been applied to these problems and managed to attain promising performance in terms of optimality. However, their general applicability has been overlooked, hindering their effectiveness as versatile solvers. The limited generalizability of current approaches is the primary hurdle between the literature and real-world applications. This paper addresses this gap by introducing a generality taxonomy and conducting comprehensive theoretical and empirical analyses. This study highlights the adverse impact of extreme parameter tuning on generality, emphasizing the need for more generalized approaches. Furthermore, it introduces a performance assessment framework, penalizing problem-tailored solutions. It also examines the optimality vs. generality performance of the state-of-the-art approaches of the latest university course timetabling benchmark to further reinforce our claim and validate the efficacy of our framework. Our findings indicate that the current literature prioritizes optimality over generality. We believe adopting the proposed assessment framework is crucial for bridging the gap between research and practical applications, enabling fairer comparisons, and encouraging more adaptable approaches.

20 August 2026 in Applied Computing and Informatics
Verified
Journal Article
Open access
KLKeong Kuon Lock
Keong Kuon Lock
RYRazali Yaakob
Razali Yaakob
Sina AbdipoorSina Abdipoor
Sina Abdipoor
MLMingxuan Li
Mingxuan Li
Purpose: Predicting stock prices is notoriously difficult because financial data is noisy and non-linear. This study proposes a model designed to overcome common limitations in both data quality and predictive architecture. Design/methodology/approach: We propose a framework that combines two methods. First, we use a Discrete Wavelet Transform (DWT) to clean the data, separating the underlying trends from market noise. Second, we feed this denoised data into a time-series recurrent neural network (TRNN). We optimized the TRNN by implementing the Swish activation function, which helps the model learn more effectively and mitigates the vanishing gradient problem. The model was validated using historical data from the Dow Jones Industrial Average (DJIA). Findings: Our results show that a single-hidden-layer network performs significantly better than deeper and more complex networks. Deeper models perform poorly because they overfit clean data. Activation function was the most important factor for the success of this study. The Swish function allowed the model to learn effectively, whereas the older functions did not. The final best model had a very low error rate of 0.71%. Originality/value: The proposed model achieves a 0.71% error rate, representing a 13-fold improvement over previous benchmarks. This study demonstrates that a streamlined, efficient model can outperform complex “deep” architectures when paired with robust data-cleaning techniques. These findings challenge the common belief that “deeper is better” in stock market forecasting.