Publication Search

Software development effort estimation is crucial as it is one of the key factors for successful software development. This research employs Random Forest to estimate software development effort. To achieve better results, the study combines the Random Forest method with Genetic Algorithm. The results show that the China dataset provides more accurate estimation compared to the Desharnais dataset, because the China dataset uses relevant feature selection for estimation.

The selection of a thesis topic that aligns with students’ interests and competencies often poses a challenge in academic environments. Inappropriate topic selection can lead to decreased motivation and delays in completing the final project. This study aims to develop a thesis topic recommendation system based on a genetic algorithm that considers students’ interests and academic abilities. The data used include grades from core courses, results of research interest questionnaires, and a list of thesis topics provided by academic supervisors. Each topic is represented as a chromosome, while the fitness function is calculated based on the level of compatibility between student attributes and topics. The selection process employs the roulette wheel method, with single-point crossover and random mutation to generate an optimal solution population. The test results show that the recommendation system based on the genetic algorithm achieves an accuracy rate of 86.7%, higher than the keyword-matching method, which only reaches 71.2%. Therefore, this approach is proven effective in assisting students to determine thesis topics that are suitable, objective, and efficient.

Information system security faces serious challenges due to increasingly complex cyber attacks. Intrusion Detection Systems (IDS) require efficient approaches to handle high-dimensional data such as the NSL-KDD dataset with 41 features. This study aims to implement the Genetic Algorithm (GA) for feature selection on the NSL-KDD dataset to improve the efficiency and accuracy of network attack detection. The method used is computational experimental research, involving data preprocessing, GA implementation for feature selection, building a classification model using Random Forest, and performance evaluation based on accuracy, precision, recall, F1-score, and computation time. The results show that GA successfully reduced features from 41 to 12 features (70.7% reduction), significantly improving computational efficiency. However, model accuracy slightly decreased from 0.4973 to 0.4951, indicating that while GA is effective for feature selection, the elimination of certain features may reduce classification capability. The implication of this study is that GA can be used as a tool to simplify intrusion detection models, but it should be combined with parameter optimization and data imbalance handling to achieve more optimal performance.  

The daily exchange of informatics over the Internet has both eased the widespread proliferation of resources to ease accessibility, availability and interoperability of accompanying devices. In addition, the recent widespread proliferation of smartphones alongside other computing devices has continued to advance features such as miniaturization, portability, data access ease, mobility, and other merits. It has also birthed adversarial attacks targeted at network infrastructures and aimed at exploiting interconnected cum shared resources. These exploits seek to compromise an unsuspecting user device cum unit. Increased susceptibility and success rate of these attacks have been traced to user's personality traits and behaviours, which renders them repeatedly vulnerable to such exploits especially those rippled across spoofed websites as malicious contents. Our study posits a stacked, transfer learning approach that seeks to classify malicious contents as explored by adversaries over a spoofed, phishing websites. Our stacked approach explores 3-base classifiers namely Cultural Genetic Algorithm, Random Forest, and Korhonen Modular Neural Network – whose output is utilized as input for XGBoost meta-learner. A major challenge with learning scheme(s) is the flexibility with the selection of appropriate features for estimation, and the imbalanced nature of the explored dataset for which the target class often lags behind. Our study resolved dataset imbalance challenge using the SMOTE-Tomek mode; while, the selected predictors was resolved using the relief rank feature selection. Results shows that our hybrid yields F1 0.995, Accuracy 0.997, Recall 0.998, Precision 1.000, AUC-ROC 0.997, and Specificity 1.000 – to accurately classify all 2,764 cases of its held-out test dataset. Results affirm that it outperformed bench-mark ensembles. Result shows the proposed model explored UCI Phishing Website dataset, and effectively classified phishing (cues and lures) contents on websites.

The integration of Internet of Things (IoT) with cloud computing has revolutionized healthcare systems, offering scalable and real-time patient monitoring. However, optimizing response times and energy consumption remains crucial for efficient healthcare delivery. This research evaluates various algorithmic approaches for workload migration and resource management within IoT cloud-based healthcare systems. The performance of the implemented algorithm in this research, Hybrid Dynamic Programming and Long Short-Term Memory (Hybrid DP+LSTM), was analyzed against other six key algorithms, namely Gradient Optimization with Back Propagation to Input (GOBI), Deep Reinforcement Learning (DRL), improved GOBI (GOBI2), Predictive Offloading for Network Devices (POND), Mixed Integer Linear Programming (MILP), and Genetic Algorithm (GA) based on their average response time and energy consumption. Hybrid DP+LSTM achieves the lowest response time (82.91ms) with an energy consumption of 2,835,048 joules per container. The outcome of the analysis showed that Hybrid DP+LSTM have significant response times improvement, with percentage increases of 89.3%, 79.0%, 83.8%, 97.0%, 99.8%, and 99.94% against GOBI, GOBI2, DRL, POND, MILP, and GA, respectively. In terms of energy consumption, Hybrid DP+LSTM outperforms other approaches, with GOBI2 (3,664,337 joules) consuming 29.3% more energy, DRL (2,973,238 joules) consuming 4.9% more, GOBI (4,463,010 joules) consuming 57.4% more, POND (3,310,966 joules) consuming 16.8% more, MILP (3,005,498 joules) consuming 6.0% more, and the GA (3,959,935 joules) consuming 39.7% more. The result of ablation of the Hybrid DP+LSTM model achieves a 47.05% improvement over DP-only (156.57ms) and a 70.64% improvement over LSTM-only (282.41ms) in response time. On the energy efficiency side, Hybrid DP+LSTM shows 22.80% improvement over LSTM-only (3,671,51 joules), but 7.34% underperformance compared to DP-only (2,640,93). These research findings indicate that the Hybrid DP+LSTM technique provides the best trade-off between response time and energy efficiency. Future research should further explore hybrid approaches to optimize these metrics in IoT cloud-based healthcare systems.

This research explores the effectiveness of heuristic techniques for solving combinatorial optimization problems, with a particular focus on the Traveling Salesman Problem (TSP). Combinatorial optimization is a critical area of study, especially in fields like computer science, engineering, and economics, where finding optimal solutions from a finite set of possibilities is crucial. However, the NP-hard nature of many combinatorial problems, such as the TSP, makes traditional exact methods like Branch-and-Bound and Dynamic Programming computationally expensive and inefficient for larger problem sizes. The primary objective of this research is to evaluate the performance of heuristic methods, including Simulated Annealing (SA), Genetic Algorithms (GA), and Iterative Computation techniques, such as Tabu Search (TS) and Particle Swarm Optimization (PSO). These methods are tested for their ability to provide approximate solutions efficiently. The findings reveal that while ACO provided the best solution quality, it had the longest runtime. TS was the fastest, though with slightly lower solution quality. SA and GA demonstrated a balance between solution quality and computational efficiency, but their performance heavily depended on parameter tuning. The hybridization of SA and GA showed potential for improving solution quality but introduced additional complexity. The research concludes that heuristic methods, especially when combined, offer viable solutions for large-scale combinatorial optimization problems, though the trade-off between solution quality and computational time must be considered when selecting an algorithm.

Penelitian ini bertujuan untuk menganalisis optimasi parameter Photovoltaic (PV) serta daya keluaran dari pembangkit listrik tenaga surya berbasis Genetic Algorithm. Penelitian ini menggunakan metode pengumpulan data melalui studi literatur, simulasi perangkat lunak, serta pengujian model matematis. Penelitian ini menggunakan pendekatan analisis kuantitatif dan komputasional yang berfokus pada pencarian nilai optimal dari parameter-parameter utama sistem PV, seperti tegangan, arus, dan resistansi. Hasil penelitian menunjukkan bahwa dalam proses optimasi sistem PV, tahapan yang dilakukan meliputi pemodelan karakteristik PV, penyusunan fungsi objektif untuk memaksimalkan daya, penerapan algoritma genetika dalam mencari nilai parameter optimal, serta analisis hasil optimasi. Hasil penelitian memperlihatkan bahwa algoritma genetika mampu meningkatkan efisiensi daya keluaran PV dibandingkan metode konvensional, serta menghasilkan parameter yang lebih sesuai terhadap kondisi iradiasi tertentu. Namun, dalam implementasi metode ini juga ditemukan beberapa kendala, seperti kompleksitas perhitungan dan kebutuhan waktu komputasi yang relatif tinggi. Selain itu, diperlukan penyesuaian lebih lanjut untuk penerapan algoritma ini dalam skala sistem pembangkit yang lebih besar.

Pendistribusian bantuan yang efisien menjadi tantangan utama dalam proses penyaluran. Penelitian ini bertujuan untuk merancang sistem cerdas yang mampu memetakan dan menyalurkan bantuan secara optimal dengan pendekatan algoritmik. Metodologi yang digunakan meliputi pemodelan sistem dengan menggunakan Unified Modeling Language (UML), perancangan struktur basis data relasional, dan perancangan algoritma penyaluran berdasarkan kriteria prioritas dan efisiensi logistik. UML digunakan untuk menggambarkan arsitektur sistem secara visual, meliputi use case, class, dan diagram aktivitas. Perancangan basis data dilakukan untuk memastikan integritas data dan kemudahan pengelolaan informasi bantuan, lokasi, dan kebutuhan penerima. Algoritma yang dikembangkan memanfaatkan pendekatan heuristik untuk menentukan rute penyaluran dan prioritas penerima berdasarkan parameter lokasi geografis. Hasil penelitian ini berupa prototipe model konseptual yang dapat digunakan sebagai dasar pengembangan sistem cerdas berbasis teknologi untuk mendukung proses penyaluran bantuan yang adaptif dan responsif.

This paper explores the application of quantum-inspired optimization algorithms in the training of large-scale Graph Neural Networks (GNNs) within distributed cloud-edge environments. GNNs have gained significant attention due to their ability to model complex relationships in graph-structured data, yet their training presents challenges such as high computational demand, inefficient resource allocation, and slow convergence, especially for large datasets. Traditional meta-heuristic algorithms, while useful, often face scalability and performance issues when applied to such large-scale tasks. To address these challenges, we propose a quantum-inspired meta-heuristic algorithm that leverages quantum principles, such as superposition and entanglement, to enhance optimization processes. The algorithm was integrated into a hybrid cloud-edge system, where computational tasks are dynamically distributed between edge nodes and the cloud, optimizing resource utilization and reducing latency. Our experimental results demonstrate significant improvements in training speed, resource efficiency, and convergence rate when compared to traditional optimization methods such as Genetic Algorithms and Simulated Annealing. The quantum-inspired algorithm not only accelerates the training process but also reduces memory usage, making it well-suited for large-scale GNN applications. Furthermore, the system's scalability was enhanced by the hybrid cloud-edge architecture, which balances computational load and enables real-time data processing. The findings suggest that quantum-inspired optimization algorithms can significantly improve the training of GNNs in distributed systems, opening new avenues for real-time applications in areas such as social network analysis, anomaly detection, and recommendation systems. Future work will focus on refining these algorithms to handle even larger datasets and more complex GNN architectures, with potential integration into edge devices for enhanced real-time decision-making.

Efficient resource allocation is a major challenge in various sectors, especially when faced with limitations in quantity, time, and cost. This study aims to examine the application of linear programming as an optimization method in solving assignment problems, where a number of resources must be optimally allocated to a number of specific tasks. Through a literature study approach, this study examines various relevant previous study results, especially in the Indonesian context. The results of the study indicate that linear programming is able to improve operational efficiency, reduce costs, and produce a more balanced task distribution. However, this model has limitations in dealing with non-linear conditions and data uncertainty, so integration with other methods such as fuzzy logic or genetic algorithms is needed. This study is expected to broaden the understanding of the benefits of linear programming and encourage its wider application in quantitative-based decision making.

Task scheduling in cloud computing environments is a crucial aspect in optimizing resource allocation and improving system efficiency. This research aims to analyze trends in task scheduling algorithms in cloud computing using a Systematic Literature Review (SLR) approach on various scientific publications published between 2018 and 2025. The results of the study show that Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Genetic Algorithm (GA) algorithms are the most commonly used methods in solving task scheduling problems. PSO stands out as an effective algorithm due to its ability to find global optimal solutions, handle non-linear and multimodal problems, and its efficiency in managing computational resources. Additionally, various studies have shown that optimization of scheduling algorithms can be achieved through a combination or modification of existing methods to improve system performance. This study provides in-depth insights into the development of scheduling algorithms in cloud computing and opens up opportunities for further research in developing more innovative and adaptive approaches.

Natural resource management involves complex decision-making processes that often result in non-linear optimization problems. This study explores the application of genetic algorithms (GA) and particle swarm optimization (PSO) to manage resources like water and forest reserves more efficiently. We compare the effectiveness of these algorithms in achieving sustainable utilization while minimizing environmental impact. The results show that GA outperforms PSO in forest management scenarios, while PSO is more suitable for water resource distribution.

This paper explores the use of genetic algorithms (GAs) for optimizing nonlinear systems in resource allocation. By simulating various allocation scenarios, we demonstrate the efficiency of GAs in finding near-optimal solutions in complex environments. The study provides a comparison of GA performance against traditional optimization methods and identifies scenarios where GAs outperform. The results emphasize the utility of GAs in real-world applications, especially when conventional approaches struggle with large solution spaces.

This paper introduces a hybrid optimization approach that combines genetic algorithms with gradient descent for effective nonlinear function approximation in highdimensional data. Traditional methods struggle with computational efficiency and accuracy in such complex spaces. By integrating genetic algorithms to provide a global search strategy with gradient descent for finetuning, the proposed method achieves faster convergence and improved accuracy. Simulations and case studies demonstrate its effectiveness in applications like data mining, image recognition, and financial modeling.

This paper presents an optimization approach for a hybrid photovoltaic (PV)-wind-battery energy system tailored for remote areas in Indonesia. Due to the archipelagic nature of the country, many remote areas lack access to the national power grid, making renewable energy solutions crucial. This study utilizes a genetic algorithm to optimize system configurations, balancing energy production, storage requirements, and cost efficiency. Results indicate that the proposed hybrid system can meet local demand with high reliability and at lower costs compared to diesel generators. The study also addresses environmental and social impacts, proposing sustainable energy strategies for Indonesia's underserved regions.

The advent of the Internet as an effective means for resource sharing has consequently, led to proliferation of adversaries, with unauthorized access to network resources. Adversaries achieved fraudulent activities via carefully crafted attacks of large magnitude targeted at personal gains and rewards. With the cost of over $1.3Trillion lost globally to financial crimes and the rise in such fraudulent activities vis the use of credit-cards, financial institutions and major stakeholders must begin to explore and exploit better and improved means to secure client data and funds. Banks and financial services must harness the creative mode rendered by machine learning schemes to help effectively manage such fraud attacks and threats. We propose HyGAMoNNE – a hybrid modular genetic algorithm trained neural network ensemble to detect fraud activities. The hybrid, equipped with knowledge to altruistically detect fraud on credit card transactions. Results show that the hybrid effectively differentiates, the benign class attacks/threats from genuine credit card transaction(s) with model accuracy of 92%.