TELKOMNIKA (Telecommunication Computing Electronics and Control)
Not a member yet
3120 research outputs found
Sort by
Adaptive DICOM images encryption using quadtree and lightweight ITUBee algorithm
Full text linkThe encryption of medical images protects the privacy of patient information transmitted over networks and communications. In this paper, a lightweight encryption method for medical images is proposed, combining a quadtree-based segmentation and a modified ITUBee algorithm for encryption. A digital imaging and communications in medicine (DICOM) image is divided into variable-size blocks using the Quadtree technique, and the key is generated through a two-dimensional Henon map; the first dimension is used in the confusion process (bit permutation) of the pixel values, and the second sequence is used to generate the key schedule through the application round function. Different numbers of rounds are applied to the ITUBee method based on the size of the segments in the Quadtree, making the algorithm adaptive by increasing the round number when the block size is reduced. The method is used as a lightweight encryption method for encrypting all blocks, utilizing different round numbers for each block size to balance the degree of complexity with the total time consumption of the DICOM image. The result reinforces the proposed method, which produced a high mean squared error (MSE) between the DICOM image and the Encrypted One, and a lower peak signal-to-noise ratio (PSNR). The proposed generated numbers were also tested using national institute of standards and technology (NIST) to evaluate the randomness
Business intelligence through data visualization: a case study using marketing campaign dataset
Full text linkIn today’s competitive business environment, data-driven marketing strategies are essential for successful campaign outcomes. This study presents a comprehensive analysis of marketing campaign data, emphasizing its role in enhancing customer engagement, improving decision-making, and increasing conversion rates. It explores the complexity of campaign dynamics and consumer behavior, demonstrating how business intelligence and data visualization techniques support informed marketing decisions and actionable insights. Advanced data science methods such as data cleaning, feature engineering, and cross-validation enhance predictive accuracy and campaign optimization. Visualization plays a central role in transforming raw data into interpretable insights, enabling businesses to identify trends in customer preferences and purchasing behavior. Key findings reveal that customers aged 51–70, particularly those with higher education and income levels, show the greatest purchasing power, especially for wine and meat products. These insights help align marketing strategies with data-driven understanding to design personalized campaigns that resonate with target audiences. By combining analytical methods with effective visualization, businesses can develop impactful campaigns that drive engagement, boost conversions, and foster revenue growth. The study concludes with directions for future research, including real-time data processing and automated decision-making systems to ensure continuous improvement in digital marketing strategies
Dual band antenna design for 4G/5G application and prediction of gain using machine learning approaches
Full text linkIn this research, we disclose our findings from exploring a machine learning (ML) approach to enhancing the antenna’s performance in Industrial and Innovation contexts, particularly for4G and 5G (n77, n78) contexts. Methods for evaluating antenna performance utilizing simulation, the resistor, inductor, and capacitor (RLC) equivalent circuit model, and ML are discussed. Gain is a maximum of 6.56 dB and efficiency is about 97% for this antenna. The predicted antenna gain is calculated using an alternative supervised regression ML technique. Multiple measures, including as the variance score, R-square (R2), mean square error (MSE), and mean absolute error (MAE), can be used to assess an ML model’s performance. The linear regression (LR) model predicts profit with the fewest errors and highest accuracy of the five ML models. Finally, computer simulation technology (CST) and advanced design system (ADS) modeling findings, along with ML results, show that the proposed antenna is a promising option for 4G and 5G applications
1×2 microstrip patch antennas array for mm-waves 5G application
Full text linkIn this paper we present the design of an antenna array for 5G applications. The proposed prototype of the antenna array is design to function at both 24 GHz and 27 GHz frequencies, utilizing Rogers RT5880 with a permittivity equal to 2.2 and a loss tangent of 0.0009. The CST Studio Suite software is employed for simulating the suggested. The primary goals of this research encompass achieving a notable return loss, increased gain, minimized voltage standing wave ratio (VSWR), enhanced directivity, and an overall improvement in operational efficiency. The results of the simulation showcase encouraging performance metrics, including a return loss of -68.70 dB, a bandwidth larger 7.369 GHz (ranging from 22.191 GHz to 29.56 GHz), a gain of 10.52 dB. Furthermore, the microstrip patch antennas (MPA) array system showcases an impressive efficiency rating of 95.63%
A wideband microstrip antenna employing ring and hexadecagonal slots with parasitic elements for W-band applications
Full text linkThis article presents a monopole patch antenna, designed for operation in the W-band. The antenna is constructed on Rogers/RT 5880 dielectric material with dimensions of 3.4×4×0.16 mm³, a loss tangent of 0.0009, and a relative permittivity of 2.2. The initial design features a simple rectangular patch measuring 1.3542×1.0306 mm², powered by a microstrip line using an inset feed. To enhance the bandwidth and gain, two parasitic rectangular elements were added on both sides of the patch in addition to the incorporation of a circular ring slot with the ground plane. Further improvements in bandwidth and return loss were achieved by etching a hexadecagonal-shaped slot on the patch. Simulation results indicate that the optimized design achieves an impedance bandwidth of 28.54 GHz, ranging from 79.67 GHz to 108.21 GHz, centered at 88 GHz. The antenna also shows a maximum return loss of 59 dB and a voltage standing wave ratio (VSWR) of 1.0022. The radiation pattern is directional, with a peak gain of approximately 8.57 dBi, and a maximum directivity of about 8.6 dB, as predicted by the computer simulation technology (CST) frequency-domain solver. These advantageous characteristics make the proposed antenna a suitable choice for point-to-point transmission applications
Fire detection and surveillance system with cloud-based alert to enhance safety in commercials and home
Full text linkThis study presents a comprehensive internet of things (IoT) solution for improving home automation and fire safety. It describes the design and construction of an all-inclusive house fire extinguishing system using an ESP8266 microcontroller to supply water, detect fires in real time, and monitor them remotely. The IoT fire safety system is currently under investigation for its potential to prevent fires. The system includes a servo motor for precise water distribution, an ESP8266 microcontroller for smooth performance and networking, a water pump for timely fire suppression, and a fire sensor for detecting heat and flames. The system architecture, software integration, and hardware parts are detailed. Field testing has shown that fire detection and suppression systems can effectively detect fires, reducing risks and damages associated with fires. The discussion section discusses the pros and cons of the recommended strategy, implications for home fire safety and automation, and areas for further research and development. The IoT-based domestic fire extinguishing system combines modern technologies with quick response time, real-time monitoring, and fast action capacity, addressing the urgent need for increased home fire safety measures
Enhanced torque control for horizontal-axis wind turbines via disturbance observer assistance
Full text linkThis paper presents an enhanced control strategy for optimizing energy capture in horizontal axis wind turbines operating in the partial-load region (region 2). The proposed approach builds upon conventional standard torque control (STC) by incorporating a generalized extended state observer (GESO) that follows the active-disturbance-rejection paradigm. Although traditional torque control methods have proven effective under steady wind conditions, they often lack robustness against disturbances, system faults, and model uncertainties inherent in wind energy systems. The proposed observer-assisted control scheme addresses these limitations by estimating and compensating for total disturbance signals, including non-modeled dynamics, parameter uncertainties, and actuator faults. The effectiveness of the proposed control strategy is validated through comprehensive simulations using a 5 MW wind turbine model subjected to realistic operational conditions. Simulation scenarios include turbulent wind speed profiles and actuator degradation to assess controller performance. The results demonstrate improved robustness and energy capture efficiency compared to the conventional control approach, while maintaining the simplicity of the implementation. This work contributes to the development of more reliable wind energy conversion systems (WECSs) by offering a practical solution that improves both performance and fault tolerance in partial load operation
Deep transfer learning based disease detection and classification of tomato leaves - a comparative analysis
Full text linkA wide variety of diseases have a significant impact on tomato plants. To avoid crop quality issues, a prompt and precise diagnosis is crucial. Classifying plant diseases is one of the numerous applications where deep transfer learning models have recently produced remarkable results. This study dealt with fine-tuning by contrasting the most advanced architectures, including Inception V3, ResNet-18, ResNet-50, VGG-16, VGG-19, GoogLeNet, and AlexNet. In the end, a comparison evaluation is conducted. Nine distinct tomato disease classes and one healthy class from PlantVillage make up the dataset used in this study. Precision, recall, F1-score, and accuracy were the basis for a multiclass statistical analysis that assessed the models. The ResNet-50 approach yielded significant results with precision: 82%, recall: 81%, F1-score: 81%, and accuracy: 85%. With this high success rate, it is reasonable to say that mobile applications or IoT-compatible gadgets implemented with the ResNet-50 model can assist farmers in identifying and safeguarding tomatoes against the aforementioned diseases
Three-position gearshifts remote control for agricultural tractors
Full text linkThis research presents the development and evaluation of a three-position gearshifts remote control system for agricultural tractors, designed to improve operational efficiency and reduce operator fatigue. The system utilizes a programmable logic controller to remotely control a linear actuator, enabling seamless gear shifting between three predetermined positions. The primary objective is to provide operators with a convenient, ergonomic alternative to traditional manual gear shifting, particularly in challenging or confined working environments. The system was tested under two conditions: first, with a programmable logic controller controlling the linear actuator via a remote transmitter; second, with the system installed on an actual tractor and tested in a road scenario. Results from both tests demonstrate the system’s effectiveness in enhancing ease of operation, reducing physical strain, and maintaining gearshifts precision. The findings suggest that the remote control system offers significant potential for improving tractor operation, particularly for tasks requiring frequent gear changes or when working in difficult terrain. This research contributes to the ongoing development of automation in agricultural machinery, offering insights into remote control applications and the integration of electromechanical systems in agricultural vehicles
Oversampling vs. undersampling in TF-IDF variations for imbalanced Indonesian short texts classification
Full text linkEven though it is considered a more traditional method compared to more modern algorithms, term frequency inversed document frequency (TF-IDF) nevertheless produces good results in a range of text mining tasks. This study assesses the effectiveness of several TF-IDF modifications for short text classification. Imbalanced datasets are another issue that is addressed in this research. To rectify the imbalanced issue, we integrate standard, log-scaled, and boolean TF-IDF in short text classification with undersampling and oversampling methods. Precision, recall, and f-measure metrics are used to evaluate each experiment. The best result is obtained when applying boolean TF-IDF with the oversampling method. Oversampling methods outperform the undersampling methods in every experiment, although there are some cases where experiments with undersampling methods are considerable. Additionally, our conducted study reveals that employing modified TF-IDF, such as boolean or log-scaled versions, provides greater advantages to classification performance, particularly in handling imbalanced datasets, when compared to solely relying on the standard TF-IDF approach