TELKOMNIKA (Telecommunication Computing Electronics and Control)
Not a member yet
3120 research outputs found
Sort by
Advancements in wind farm layout optimization: a comprehensive review of artificial intelligence approaches
Full text linkThis article provides a detailed evaluation of cutting-edge artificial intelligence (AI) approaches and metaheuristic algorithms for optimizing wind turbine location inside wind farms. The growing need for renewable energy sources has fueled an increase in research towards efficient and sustainable wind farm designs. To address this challenge, various AI techniques, including genetic algorithms (GA), particle swarm optimization (PSO), simulated annealing, artificial neural networks (ANNs), convolutional neural networks (CNNs), and reinforcement learning, have been explored in combination with metaheuristic algorithms. The goal is to discover optimal sites for turbine placement based on a variety of parameters such as energy output, cost-effectiveness, environmental impact, and geographical restrictions. The paper examines the advantages and disadvantages of each strategy and highlights current breakthroughs in the area. This assessment adds to continuing efforts to optimize wind farm design and promote the use of clean and sustainable energy sources by offering significant insights into current advances
Integration of PSO-based advanced supervised learning techniques for classification data mining to predict heart failure
Full text linkHeart failure (HF) is a global health threat, requiring urgent research in its classification. This study proposes a novel approach for HF classification by integrating advanced supervised learning (ASL) and particle swarm optimization (PSO). ASL techniques like bagging and AdaBoost are employed within the PSO+ASL optimization model to enhance prediction accuracy. PSO optimizes model weights and bias, while ASL addresses overfitting or underfitting issues. Split validation and cross-validation (70:30, 80:20, 90:10 with k-fold=10) are used for further optimization. The testing phase involves 12 classifiers in five groups: decision tree models (DTM), support vector machines (SVM), Naïve Bayes classifiers models (NBCM), logistic regression models (LRM), and lazy model (LM). Evaluating the proposed approach with an HF patient dataset from https://www.kaggle.com, results are compared against the standard model, PSO optimization, and PSO+ASL. Experimental findings demonstrate the superiority of the proposed approach, achieving higher accuracy in HF prediction. The PSO+ASL optimization model with the k-nearest neighbor (k-NN) method exhibits the best classification performance. It consistently achieves the highest accuracy across all tests on dataset composition ratios, with 100% accuracy, f-measure, sensitivity, specificity values, and area under cover (AUC) of 1. The proposed approach serves as a reliable tool for early detection and prevention of HF
Optimal placement of distributed generations on distribution network for reducing power loss and improving feeder balance
Full text linkThe suitable placement and power of distributed generation (DG) can bring technical benefits to the distribution network. This paper applies the Coot optimization algorithm to the DG placement problem with the goal of minimizing power loss and feeder balancing load (LBF). The weight method is used to combine the membership objectives. The evaluation results on the network of 70 nodes for different weight values of the objective function show that the optimal power and installation location of DGs significantly reduces power loss and improves LBF index. In this study, eleven cases were considered. As the weight of power loss part 1 increases from 0 to 1, the power loss gradually decreases, the LBF index gradually increases, the maximum current gradually decreases, and the minimum voltage amplitude gradually improves. Comparing the results of Coot with particle swarm optimization (PSO) shows that the indicators are improved. In the three cases where 1 is 0, 0.5, and 1, power loss gained by Coot compared to PSO is less than 47.2663 kW, 73.2725 kW, 30.8708 kW, respectively. LBF index of Coot compared to PSO is less than 98.2%, 88.2%, 81.9%, respectively. The maximum, minimum, average, standard deviation, and CPU time of Coot are smaller than those of PSO. So, Coot is one of the promising methods for this problem
Rainfall prediction using support vector regression in Udupi region Karnataka, India
Full text linkThe hydromatereological processes are examined through analysis of temporal rainfall variability. India is an agricultural land and its economy is mainly dependent on timely rains to produce good harvest. The amount of rainfall varies with regional and temporal variation in distribution. The present research has been conducted to predict the temporal variations in rainfall in Udupi district, Karnataka, India using support vector regression (SVR) model and to validate the findings using actual rainfall records. The data has been collected from the statistical department, Udupi district, Government of Karnataka, India. The prediction accuracy of SVR based rainfall prediction model depends on tuning of algorithmic-based parameters. The parameter optimization is performed using grid search to select the optimal values of hyperparameters. The analysis was performed for the year 2018 based on the training dataset from 2000-2017. It is observed that there is a decreasing trend in total annual rainfall in 2018 and it is concluded that the average yearly rainfall has declined during the years 2018 and 2019. The rainfall predicted results were validated with actual records. The SVR based rainfall prediction model will predicts the rainfall accurately for application in agricultural sector
The causal loop diagram model of traceability system rental equipment in oil and gas supporting companies
Full text linkTraceability in equipment rental systems enhances security, reliability, and operational transparency by providing the ability to accurately track leased equipment. Challenges in implementing traceability include difficulties in collecting accurate data, the absence of standardized recording practices, and the complexities of integrating technology to ensure complete tracking. This research aims to identify variables affecting the traceability system thinking to improve its efficiency in ongoing business processes. A qualitative descriptive approach is used to offer comprehensive insights into implementing traceability in equipment rental systems, focusing on oil and gas support companies. The study employs the causal loop diagram (CLD) method to dynamically map and identify traceability process variables. Findings show that traceability enables more precise tracking of equipment movement and usage, enhancing inventory management and streamlining maintenance. The CLD method reveals the dynamic relationships between system variables such as equipment availability, maintenance needs, and customer satisfaction, which guide continuous improvement. These results provide stakeholders with valuable insights for optimizing efficiency and service quality in equipment rental operations, particularly in oil and gas support companies. Enhanced traceability can significantly boost operational effectiveness and customer satisfaction
Class-G series audio power amplifier for subwoofer
Full text linkAn audio power amplifier is an electronic device used to amplify a small signal source power at the input into a large signal power at the output that is speaker. In general, audio power amplifiers use class-AB amplifiers. In the process of amplifying the signal power, there will be power losses in the amplifiers which results in relatively lower amplifier power efficiency because there is a difference between the supply and output voltage levels. In this paper a class-G series audio power amplifier for subwoofers is designed to minimize these power losses and increase the power efficiency of the amplifier. The designed amplifier voltage supply is 40 V with a maximum output power of 80 W at an 8 Ω load. The amplifier has frequency response from 20–200 Hz and gain twice. Realization of the power amplifier and measurements were carried out using the circuit maker simulator, and the measurement results of the class-G power amplifier were compared with the class-AB power amplifier. The measurement results show that both power amplifiers meet the design specifications. The proposed class-G amplifier has 0.14% larger total harmonic distortion (THD) but has 10.4% greater power efficiency advantages over the class-AB amplifier
Hybrid unipolar-bipolar system with quasi-polarized code for free-space optical communication
Full text linkIn this study, the hybrid unipolar-bipolar (U-B) optical code division multiple access (OCDMA) with mixed unipolar-bipolar scheme in free-space optical communication was proposed. Additionally, the codeword assigned introduced the quasi-polarized code, which could be used to transmit both the unipolar and bipolar section. Using OptiSystem simulations, the model was studied. According to the results from the simulation, the proposed hybrid UB OCDMA can correctly decode the original optical signal from its matching encoder. Further testing of the hybrid U-B OCDMA system was conducted in turbulence conditions. According to the simulation results, walsh-zero cross correlation (ZCC) performs better than all other codes for the unipolar segment whereas walsh-hadamard (W-H) code performs best for the bipolar section. The simulations also showed that the performance deterioration of the walsh-ZCC algorithm was the greatest
Augmented reality in customer experience: systematic review
Full text linkAugmented reality (AR) is an emerging technology that offers the opportunity to explore a new way of shopping in the customer experience, showcasing its benefits, such as the superimposition of virtual elements in a physical environment or the high degree of interactivity provided by this technology. Despite its great potential to satisfy customer needs, the evaluation of the customer experience has not been fully studied. The main of this study is to identify the constructs that influence customer experience using the systematic review technique. A total of 88 studies published between 2016 and 2021, which relate to customer experience, were identified. Relevant information, such as the definitions of AR and customer experience, and the constructs that various authors use to assess customer experience, was extracted. The results of the review indicate that five fundamental constructs–attitude, interactivity, customer satisfaction, purchase intention, and hedonic value–are used to assess customer experience. These results contribute to a better understanding of the customer experience with AR
Deep learning ensemble framework for multiclass diabetic retinopathy classification
Full text linkDiabetic retinopathy (DR) is the leading cause of blindness among adults and has no visible symptoms. Early detection is the key to prevent vision loss. Computer-aided deep learning using convolutional neural networks (CNN) have recently gained momentum for DR diagnosis as the cost can be significantly reduced while making the diagnosis more accessible. In this work, we present a fully automated framework DR network (DRNET) that fuses both image texture features and deep learning features to train the CNN model. The framework aggregates predictions from three CNN models using ensemble learning for more precise and accurate DR diagnosis when compared to standalone CNN. To strengthen the confidence of medical practitioners in acceptance of automated DR diagnosis, we extend the DRNET framework by producing model uncertainty scores and explainability maps along with the classification results
Design of high gain and wideband circular patch antenna based on DGS for 28 GHz 5G applications
Full text linkIn this study, a single band 28 GHz antenna with defected ground structure (DGS) has been proposed. The integration of a DGS is explored to exploit ground plane defects for achieving wideband operation. Through systematic design and optimization, our approach achieves remarkable bandwidth enhancement, expanding from 0.75 GHz to 5.78 GHz, covering frequencies from 26.43 GHz to 32.21 GHz, resulting in an impressive impedance bandwidth of 20.5%. Notably, the proposed methodology significantly improves the reflection coefficient, reducing it from -16 dB to -57 dB. Furthermore, the antenna demonstrates a gain of 5.123 dBi and an enhanced voltage standing wave ratio (VSWR) of 1.0056348. Comparative analysis against existing works underscores the superior performance of our antenna design, affirming its potential for various applications. This work presents a novel DGS featuring a circular microstrip patch antenna (MPA) with dimensions of 8×8×0.5 m³, utilizing Rogers RT5880LZ substrate (E=2) with a thickness of 0.5 mm