Application of Firefly Algorithm for Optimizing the Available Transfer Capability in the Sulbagsel Electricity System of Indonesia

Melanoma is one of the most aggressive forms of skin cancer, with a high mortality rate when not detected early. This public health challenge underscores the need for accurate and efficient diagnostic tools. Convolutional Neural Networks have shown strong performance in medical image analysis. However, their effectiveness relies heavily on optimal architectural and hyperparameter configurations, which are often designed without alignment to the target domain or transferred from unrelated domains, limiting adaptability to specific medical datasets. Existing hybrid CNN-metaheuristic approaches typically optimize only fixed network parameters. They often fail to explore how metaheuristics can adaptively shape the CNN architectures themselves.In this study, a comprehensive hybrid optimization framework is proposed that integrates CNNs with six nature-inspired metaheuristic algorithms that mimic biological or physical phenomena to solve complex problems. These include Cuckoo Search, Firefly Algorithm, Whale Optimization Algorithm, Particle Swarm Optimization, Grey Wolf Optimizer, and Crow Search Algorithm. Rather than tuning a predefined architecture, each optimizer searches the architectural and training space to identify high-performing CNN configurations, enabling emergent and data-driven network design. This unified framework allows a systematic cross-algorithm comparison under identical conditions, providing new insights into convergence stability, exploration-exploitation dynamics, and generalization behavior. A robust preprocessing and data augmentation pipeline, including brightness normalization, hair artifact removal, and geometric transformations, is incorporated to improve model generalization and enhance the optimizer's search landscape. Experiments on the HAM10000 dataset demonstrate that the metaheuristic-optimized CNNs outperform the baseline, achieving accuracies up to 91.25%. These findings confirm that population-based optimization is an efficient and reliable mechanism for guiding CNN architecture design. This approach achieves superior performance compared to traditional manual or other optimization-based strategies.

Power system deregulation has made significant changes to the power grid through various technologies, privatization of entities, and improved efficiency and reliability. This work mainly focuses on different combinations of distributed generation (DG) and capacitor banks (CBs) integration to cater to multiple technical, economic, environmental, and reliable concerns. A new optimal planning framework is proposed for optimally allocating the DG units and CBs to achieve multiple objectives. In this work, an augmented objective function is formulated by considering active power losses, voltage deviation, and voltage stability index objectives. This objective function is solved considering various equality and inequality constraints. This work proposes a novel approach for allocation of DGs and CBs in the radial distribution systems (RDSs) using an evolutionary-based self-adaptive firefly algorithm (SAFA). The effectiveness of the developed planning approach is demonstrated on IEEE 33 bus RDS in MATLAB software. The obtained results indicate that proposed planning approach resulted in reduced power losses, voltage deviations, and improved voltage stability.

Optimizing Gas Sensor Array in an Electronic Nose Using Firefly Algorithm with VGG-1D for Cookie Cooking Level Classification

The Firefly Algorithm (FA) offers excellent search capability for optimization problems but often gets trapped in local optima due to the lack of mutation mechanisms. To address this issue, this study proposes a novel hybrid algorithm, which introduces Black-Winged Kite (BWK) population into the firefly algorithm, named BWK-FA. Inspired by the predatory behavior of BWK and the evasive response of fireflies, the proposed BWK-FA integrates four biologicallyinspired strategies into the classical light-seeking movement. If the predation probability is satisfied, BWKs prey on the brightest firefly within the predation radius, while surrounding fireflies execute evasive movements; otherwise, BWKs are guided by the globally brightest firefly to sustain exploration. In addition, a population information exchange mechanism and an elite-guided strategy are introduced to further enhance search capability. The proposed algorithm is evaluated using benchmark test functions with different dimensional settings through multiple independent runs. Experimental results demonstrate that BWK-FA achieves superior solution quality, stable convergence behavior, and strong robustness compared with representative algorithms. BWK-FA is further validated on standard RFID network planning instances, significantly improving network performance in terms of coverage, interference suppression, power efficiency, and load balance. These findings highlight the proposed BWKFA for addressing complex industrial optimization problems.

Beamforming-Assisted Artificial Noise-Based Transmission for Enhanced PLS-NOMA Systems Using Improved Salp Swarm and Firefly Algorithms

Breast cancer remains a major health challenge, affecting approximately 1.7 million individuals annually and often leading to severe complications. Predicting survival outcomes is difficult due to highly imbalanced data, with 3,408 death cases compared to only 616 survival cases. To address this issue, we applied the Firefly Algorithm–based under-sampling (FAUS) to balance the dataset and combined it with three machine learning classifiers: Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbor (KNN). Experimental results show that FAUS substantially improves predictive performance compared to conventional under-sampling. Among the tested models, RF achieved the highest F1-score of 0.79, while DT and KNN reached 0.72 and 0.68, respectively. The results indicate that FAUS is effective in preserving representative samples, thereby enhancing model performance in breast cancer survival prediction.

Mobile edge computing (MEC) reduces latency for delay-sensitive applications by bringing computations closer to end users. However, this technology is vulnerable to security threats, notably Distributed Denial of Service (DDoS) attacks. DDoS attacks are characterised by distributed malicious nodes that flood the target with data packets, causing system unavailability or performance degradation. This contradicts the objective of the MEC, which is to reduce delay and latency. To address this, we propose a feature selection technique to improve the detection of DDoS attacks in MEC using machine learning techniques. The proposed approach employs quasi-opposite-based learning (QOBL), a concept often utilised in differential evolution algorithms, to modify the Firefly Algorithm (FA) to form a Quasi-Opposite Firefly Algorithm (QOFA) to optimise feature selection. FA excels at navigating complex feature spaces for global optimisation but suffers from premature convergence to local optima. QOBL mitigates this by guiding FA toward local solutions, improving efficiency and detection accuracy. By selecting only the most relevant features, the QOFA reduces computational complexity while maintaining robust performance. Simulations in MATLAB demonstrated that QOFA outperformed traditional FA, achieving a higher detection accuracy (up to 95%). This approach enhances the efficiency of machine learning models for DDoS detection in MEC, ensuring a reliable and low-latency network performance that is critical for real-time applications.

In the field of digital media, intelligent extraction and layout optimization of visual elements face challenges such as inaccurate semantic understanding of elements and low efficiency in generating layout strategies. This study proposes an extraction and layout optimization model that integrates visual semantic understanding with intelligent optimization strategies, based on a segmentation Vision Transformer and Multi-Objective Firefly Algorithm. The model also utilizes the improved optical flow methods to efficiently capture dynamic information during the design process. Experimental results show that the segmentation Vision Transformer algorithm achieves an extraction accuracy of 98.8±0.2% for different categories of visual elements. As the training progresses to 50 iterations, the average Intersection-Over-Union stabilizes at 0.95, and the harmonic mean of recall reaches 98.17±0.38\%. The evaluation of the integrated model shows that it achieves 99% accuracy in extracting visually similar elements. After layout optimization using the model, the aesthetic score increases to 95.6, and the spatial occupancy rate improves to 97.2%. The above results indicate that the model proposed by the research institute can effectively enhance the accuracy of visual element extraction and the quality of layout optimization, significantly reducing the reliance of traditional methods on manual rules, and providing an efficient and adaptive solution for the automated design of digital media.

Cancer microarray datasets are distinguished by their high dimensionality and a relatively small sample sizes, which presents significant challenges for accurate cancer classification. Gene selection therefore becomes essential to eliminate irrelevant genes and improve classification accuracy. This paper presents a hybrid approach combining filter and wrapper techniques for gene selection, integrating an improved binary firefly algorithm and the support vector machine classifier. The objective is to select the most cancer-related genes to decrease computation time and enhance classification model performance. Three filter methods (Information Gain Ratio, ReliefF, and Correlation-based Feature Selection) are used in ensemble with the enhanced binary firefly algorithm. The firefly algorithm’s exploration and exploitation capabilities are improved through opposition-based learning during initialization and movement of the fireflies. Additionally, a mutation step is added to improve the diversification of fireflies. To validate our approach, we conducted an experimental study on eight public benchmark datasets and compared it to several recent gene selection methods used for cancer gene expression data classification. The results reveal that the suggested methodology enhances classifier performance while reducing data volume by finding a limited group of genes with strong predictive power for cancer classification.

Malware detection is a significant factor in establishing effective cybersecurity in the face of constantly increasing cyber threats. This research article aims to investigate the field of machine learning (ML) techniques for malware detection. More specifically, the paper focuses on the Customized K-Nearest Neighbors (C-KNN) classifier and the Firefly Algorithm (FA). The work aims to assess the effectiveness of C-KNN and C-KNN with FA (C-KNN/FA) in malware identification using the MalMem-2022 dataset. The novelty of the proposed method lies in the synergistic integration of the C-KNN algorithm with the FA for metaheuristic optimization. The use of FA to select the most relevant features enables the C-KNN to train on a small and high-quality feature set. Therefore, the performance of malware detection will be improved. We compare the performance of both methods to understand the influence of KNN parameter adjustment and feature selection on malware classification. The C-KNN and C-KNN/FA have produced remarkable results in malware identification, reaching an accuracy of 99.98%. This accomplishment is quite encouraging. With regard to multiclass and binary classification methods, C-KNN and C-KNN/FA both perform better than their alternatives.

Despite DC-DC converters are currently extensively utilized within power electronics for their effectiveness in generating a stable DC output with high efficiency, the fact that they are inherently nonlinear makes the selection of advanced converter components and control techniques indispensable for their improvement. In the context of overcoming the performance constraints of DC-DC boost converters, the purpose of the current research work is to use the concept of optimization, which targets the critical parameters of the continuous conduction mode. During the optimization procedure, the objective is to identify the best possible parameters for the inductor, the capacitor, as well as the frequency of switching. In addition to that, the adjustment of the parameters of the Proportional-Integral (PI) controller is carried out to improve the performance characteristics of the DC-DC boost converter circuit. The use of the Golden Eagle Optimization algorithm functions as the basis of the presented optimization approach. The validity of the current technique using the Golden Eagle Optimization algorithm for the design of the DC-DC boost converter circuit is demonstrated through a MATLAB/Simulink simulation. From the results, it can be seen that the proposed design using GEO outperforms various classical optimal techniques such as Grey Wolf Optimizer, Firefly Algorithm, Simulated Annealing, Particle Swarm Optimization, and Moth Flame Optimization. This proposed design using GEO results in a power loss reduction of over 6% and has 10% improvement in output voltage over the latest techniques proposed by Grey Wolf Optimizer. This again manifests the potential of GEO in developing boost converters in terms of power electronics and renewable energy sources

The project cycle of complex construction projects covers the whole process from project decision-making, design, bidding, construction, completion acceptance, and the initial stage of operation. Among them, the investment risk assessment of complex construction projects focuses on the early decision-making stage of the project, aiming to provide a basis for investment feasibility analysis. The investment risk of complex construction projects is highly nonlinear and uncertain, and the traditional risk assessment methods have limitations in model generalization ability and prediction accuracy. To improve the accuracy and reliability of quantitative risk assessment, this study proposed a novel investment risk assessment model based on the perspective of investors. Firstly, through literature research, a multi-dimensional comprehensive risk assessment index system covering policies and regulations, economic environment, technical management, construction safety, and financial cost was systematically identified and constructed. Subsequently, the Least Squares Support Vector Machine (LSSVM) was used to establish a nonlinear mapping relationship between risk indicators and final risk levels. Aiming at the problem that the parameter selection of the standard LSSVM model has a significant impact on the performance, this paper proposed an improved Firefly Algorithm (IFA) to automatically optimize the penalty factor and kernel function parameters of LSSVM, so as to overcome the blindness of artificial parameter selection and improve the convergence speed and generalization ability of the model. Compared with the classical Firefly Algorithm, IFA strengthens learning and adaptive strategies by adding depth. The conclusions are as follows. (1) Compared with the Backpropagation Neural Network (BPNN), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost), this model showed higher prediction accuracy on the test set, and its accuracy was reduced by about 3%. (2) Compared with FA, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO), IFA had a stronger global retrieval ability. (3) The model could effectively fit the complex risk nonlinear relationship, and the risk assessment results were highly consistent with the actual situation. Therefore, the risk assessment model based on the improved LSSVM constructed in this study not only provides a more scientific and accurate quantitative tool for investment decision-making of construction projects, but also has important theoretical and practical significance for preventing and resolving significant investment risks.

Cloud computing has transformed Information Technology infrastructure by enabling scalable and efficient resource management through virtualization. Moreover, the allocation and migration of VMs are complex processes because of varying workloads, power management, and SLA constraints. Proper allocation policies are very important since they will improve system performance, fragment less, and provide energy-efficient solutions. This review and analytical study investigates the most popular VM allocation policies, i.e., BFD, WFD, MBFD, and MM, assessing their performance effects on resource utilization and system stability. Then, insights into SI-theoretical affairs (ABC, PSO, and the Firefly algorithm) and machine-learning-based decisions for adaptive management are discussed. By optimizing computation time and energy consumption, this study is a guiding strategy for building the future of hybrid AI-driven optimization for sustainable cloud computing.

Rice is the main food source for Indonesians, with consumption continuing to increase in line with population growth. To meet this growing demand, the use of modern technology is important to increase rice production. However, rice plants are highly susceptible to various diseases that can reduce yields and lower the quality of rice crops. Diseases such as leaf blight, blast, leaf rot, brown spot, stripe spot, and tungro are threats to rice productivity, requiring rapid and accurate prevention. This study applies a classification system to detect diseases in rice plants using an artificial neural network (ANN) with the Backpropagation method. Backpropagation, although effective, has weaknesses, such as long convergence time and sensitivity to initial weight values, which often cause the model to get stuck at local minimum values, thereby reducing its overall performance. To overcome these weaknesses, the Firefly Algorithm (FA) is used as an optimization technique to improve the performance of Backpropagation. The results show that the use of the Backpropagation method produces an accuracy of 43%. However, when combined with the Firefly Algorithm (BPP-FA), the accuracy increases significantly, producing a value of 90%. This increase shows that BPP-FA improves accuracy in detecting diseases in rice plants. This combination of methods is expected to provide a reliable and efficient solution for detecting diseases in rice plants, thereby improving the quality and productivity of rice cultivation.

Whole-body vibration exposure is a critical factor affecting human health and comfort, particularly for individuals operating on/off-road vehicles. Prior studies have focused on male biomechanical models. This study intentions to develop a new female-specific biomechanical model to analyze and optimize biodynamic responses under vertical vibration conditions. The objective is to introduce a ten degrees-of-freedom (dofs) biomechanical model tailored for the female body, considering the average weight of human beings. The new model has compared against existing male-oriented models to evaluate its effectiveness. The female body is divided into ten key segments: head, pelvis thorax, abdomen, left upper arm, left hand, left forearm, right upper arm, right forearm, and right hand. Mechanical properties are adjusted based on female-specific mass distribution, stiffness, and damping characteristics. The Firefly Algorithm is used for parameter optimization. The biodynamic responses, including seat-to-head transmissibility, apparent mass, and driving point mechanical impedance, are evaluated and compared with previous male models. The optimized female model exhibits distinct biodynamic response characteristics due to anatomical and biomechanical differences. The goodness of fit analysis indicates improved predictive accuracy for female subjects, suggesting the necessity for gender-specific modelling in vibration analysis.

ABSTRACT With more than two billion devices in use worldwide, Android devices have become favorite targets for cybercriminals. Kaspersky recently stated that mobile malwares mainly came from Android devices. Therefore, developing effective methods for detecting android malwares turn out to be an urgent need. Intelligent methods such as Data Mining and Machine Learning proved their merits in developing malware detection models and tools in different cybersecurity domains. However, as an established fact, Data Mining and Machine Learning models significantly affected by the quality of the training dataset. The number of features in the dataset plays an important role in developing intelligent models that balance discriminative power and low computational costs during both the training phase and the implementation (prediction) phase. In this research, we introduce a novel hybrid metaheuristic feature selection algorithm that leverages the exploration capacity of the Firefly Algorithm and the extrapolation capability of the Binary Bat Algorithm. Such an algorithm is called Binary Firefly Bat Algorithm (BFBA). In order to assess the performance of BFBA, a dataset containing an equal number of malware and benign Android applications is collected from different dependable sources. An initial feature set of 6292 attributes derived from API calls, opcodes, permissions, intents, and system commands was produced through static reverse engineering and analysis. Preliminary feature engineering using discrimination scoring and variance-threshold filtering reduced the feature space to 545 attributes while preserving discriminative information. Later, Random Forest and Support Vector Machine classifiers were trained using selected feature subsets produced by BFBA. Experimental results show that models created using BFBA-selected feature outperformed the models created using the feature subsets produced by several well-known metaheuristics like the Flower Pollination Algorithm, Grasshopper Optimization Algorithm, and Ant Colony Optimization. Such results confirm that exploration and exploitation were traded at an optimal trade-off in BFBA. Overall, experiments confirmed that BFBA positively participated in developing robust and efficient Android malware detection systems.

Rapidly expanding smart-city ecosystems require energy-efficient, transparent, and citizen-centric governance frameworks, particularly for surveillance-intensive infrastructures such as intelligent traffic monitoring and urban safety systems. This study proposes a Governance-Oriented Smart City Energy Management Framework powered by a Bio-Inspired Quantum Firefly Particle Swarm Optimization (QF-PSO) algorithm, engineered for large-scale urban environments with complex, heterogeneous sensing architectures. By integrating Firefly Algorithm exploration dynamics with quantum-enhanced PSO convergence, the framework jointly optimizes sensor duty cycling, adaptive routing, and workload allocation across distributed edge–cloud layers. The system is evaluated using real-time surveillance streams and IoT telemetry sourced from publicly available smart-city open-data repositories widely used for mobility analytics, traffic modeling, and public-safety applications. Experimental results show that QF-PSO delivers 29–42% energy savings, 23–36% latency reduction, and a 33% extension in wireless sensor-network lifetime, outperforming conventional PSO, FA, GA, ACO, and QPSO with 25–28% faster convergence and improved robustness. Additionally, packet delivery ratio increases by 11%, and anomaly detection accuracy improves by 8–10%, enhancing reliability under dense urban deployment conditions. From a governance perspective, the framework ensures 5% higher service uptime, 17–20% faster fault recovery, and improved transparency through policy-aware real-time monitoring dashboards. These outcomes demonstrate that embedding quantum-enhanced bio-inspired optimization within governance-first architecture can substantially advance the sustainability, resilience, and accountability of modern smart-city digital infrastructures.

ABSTRACT Determining the shear strength of steel fiber-reinforced concrete (SFRC) beams is a persistent challenge in structural engineering, especially when aiming to balance precision with practical applicability in real-world projects. Although numerous design codes and empirical equations are available, they often fall short in delivering both accuracy and simplicity. The present study proposes a novel hybrid machine learning model – FOA-ANN – which combines an artificial neural network (ANN) with the optimization power of the firefly algorithm (FOA). The model was trained and validated using a comprehensive experimental dataset of SFRC beams to derive a user-friendly closed-form equation for shear strength prediction. A high-accuracy FOA – ANN model to overcome the limitations of existing design codes in predicting the shear strength of SFRC beams developed, providing a more reliable and practical tool for structural design. Extensive comparisons were made between the FOA-ANN model and several widely accepted prediction methods to evaluate its performance. While conventional equations showed varying degrees of reliability, the FOA-ANN model achieved high accuracy with a more concise mathematical formulation. This integrated approach not only enhances predictive performance but also provides engineers with a practical and effective tool for assessing SFRC beam behavior during both design and retrofitting phases in civil infrastructure projects.

To deal with issues such as background noise and partial information loss that arise during the process of dividing the Yuan blue porcelain pattern, a two-dimensional entropy multi-threshold method for segmenting blue-and-white porcelain patterns based on the firefly algorithm is proposed. Based on the characteristics of the patterns on the Yuan blue porcelain pattern, a median filtering matrix equation is designed to perform noise reduction on the Yuan blue porcelain pattern, and the background noise is weakened. By initializing the coefficients of fireflies, a two-dimensional entropy multi-threshold objective function is constructed, and the optimal threshold for the patterns is calculated to achieve the precise segmentation of the Yuan blue porcelain pattern. The results show that this method can effectively get rid of noise interference and missing patterns during the segmentation process. The segmentation index intersection over union of the Yuan blue porcelain patterns is 0.982, and the precision reaches 0.998. This effectively improves the accuracy rate of the segmentation of Yuan blue porcelain patterns and promotes the restoration and protection of Yuan blue porcelain cultural relics.