TELKOMNIKA JOURNAL - Profile on Academia.edu (original) (raw)

Papers by TELKOMNIKA JOURNAL

Research paper thumbnail of PV solar anomaly detection using low-cost data logger and ANN algorithm

TELKOMNIKA Telecommunication, Computing, Electronics and Control

This paper presents an innovative edge device architecture that significantly enhances solar ener... more This paper presents an innovative edge device architecture that significantly enhances solar energy management systems. By integrating advanced functionalities such as generation prediction, maintenance alerts, and solar anomaly detection, this architecture transforms solar energy management. Through edge computing, it enables real-time analysis and decision-making at the network edge. Leveraging machine learning algorithms and accurate predictive models, these edge devices provide precise energy generation forecasts, facilitating optimal energy utilization and strategic planning for stakeholders. Additionally, the architecture incorporates anomaly detection techniques to proactively identify deviations from normal operation, minimizing downtime, and enabling timely maintenance. This approach ensures uninterrupted energy generation, enhancing the reliability and efficiency of the entire monitoring system. The integration of these features within edge devices improves the performance and reliability of energy monitoring systems. Implementing this cutting-edge architecture empowers stakeholders to achieve superior energy management, substantial cost reductions, and unparalleled system reliability.

Research paper thumbnail of Power system frequency control: instantaneous discrete testing for numerical relay using wavelet transform

TELKOMNIKA Telecommunication Computing Electronics and Control

With today's advanced technology and rapidly growing energy demands, the reliability of electrica... more With today's advanced technology and rapidly growing energy demands, the reliability of electrical power systems has reached an important level. With extensive monitoring and protection, system issues like voltage drops, power irregularities, and frequency variations can have destructive consequences on the power network. Therefore, as frequency relays play a critical role in protecting power generators and load equipment from power frequency shifts, relays have evolved from electromechanical to solid-state devices with ongoing optimization to handle integrated modern networks. Traditional numerical relays use Fourier transform to identify frequency changes, which necessitates numerous data samples and has limitations with transient waveform data. To address these challenges, this work proposes a new relay algorithm based on instantaneous discrete testing and wavelet transform for frequency analysis, aimed at enhancing relay performance. This new approach demonstrates promising advantages, including significant reductions in data sample requirements, compilation complexity, decision-making time, and improved handling of transient waveforms.

Research paper thumbnail of Enhanced fuzzy logic control for overcoming intrinsic resistance in inverted pendulum systems

TELKOMNIKA Telecommunication Computing Electronics and Control

The paper delves into an in-depth analysis of the intrinsic resistance of the inverted pendulum s... more The paper delves into an in-depth analysis of the intrinsic resistance of the inverted pendulum system which causes the modeling of the system to differ from the actual system. Our primary objective revolves around the implementation and subsequent optimization of fuzzy logic controllers (FLC), drawing inspiration from human perceptual assessments. The processing comprises comprehensive mathematical system modeling, intrinsic resistance examination, and improved fuzzy logic control with detailed membership function and rule design. In addition, we conduct a comparative analysis with the widely recognized linear quadratic regulator (LQR) algorithm, which is considered the conventional control algorithm. The result demonstrates that the improved FLC outperforms the conventional LQR algorithm overshoot mitigation, thereby underscoring its superior efficacy and optimality.

Research paper thumbnail of Adaptive diving depth control system for the drifting autonomous underwater vehicle

TELKOMNIKA Telecommunication Computing Electronics and Control

This article considers the system for controlling the diving depth of a drifting autonomous under... more This article considers the system for controlling the diving depth of a drifting autonomous underwater vehicle (DAUV), which navigates underwater under the influence of sea currents in order to collect scientific information. The paper solves the problem of identifying non-stationary hydrodynamic parameters of the DAUV with the aim of adaptive adjustment of the DAUV control algorithm to increase the accuracy of bringing the DAUV to a given depth and minimizing the consumption of electricity consumed by power actuators. The solution to the problem is based on the use of parametric identification apparatus and adaptive control principles. The high quality of the DAUV diving depth control is achieved through the use of the method of adaptive adjustment of the parameters of the DAUV program model. The use of parametric identification of the hydrodynamic parameters of the DAUV made it possible to quickly adjust the corrective link in the control chain of the executing mechanism of the DAUV. The developed computer models and a set of semi-realistic tests made it possible to choose the most acceptable identification algorithm and configure the software implementation of the DAUV diving depth control law.

Research paper thumbnail of Identification of working memory status in children from EEG signal features using discrete wavelet transform

TELKOMNIKA Telecommunication Computing Electronics and Control

The conventional method for assessing the working memory performance of children is time-consumin... more The conventional method for assessing the working memory performance of children is time-consuming and potentially inaccurate, especially when dealing with many samples. Therefore, an automated system that can produce swift and accurate results is required. Electroencephalograms (EEG) can be used to analyse the working memory status of children by extracting specific features from the EEG signal, which can be incorporated into an automatic system to reduce manpower and processing time for analysis. This project used EEG recording to identify children's working memory status while they were performing working memory tasks. EEG signals were acquired from both children and adults using an automated computer-based working memory assessment tool, processed, and analyzed. The discrete wavelet transform (DWT) was then employed to identify five distinct working memory statuses: distracted, confused, daydreaming, losing focus, and active. DWT was also used to extract features that demonstrate these various statuses. The results showed that DWT could accurately identify the working memory status of both children and adults from their EEGs. This work has thus provided a more efficient method for extracting features from EEG signals to identify working memory statuses in both children and adults.

Research paper thumbnail of Hybrid optimization algorithm for resource-efficient and datadriven performance in agricultural

TELKOMNIKA Telecommunication Computing Electronics and Control

The agricultural sector is undergoing a significant transformation with the adoption of the agric... more The agricultural sector is undergoing a significant transformation with the adoption of the agricultural internet of things (IoT), yet it faces persistent challenges in optimizing resource efficiency and data-driven performance due to limitations in current optimization algorithms. This research assesses the effectiveness of four prominent algorithms such as ant colony optimization (ACO), genetic algorithms (GA), particle swarm optimization (PSO), and artificial bee colony (ABC) in addressing these challenges within agricultural IoT (AIoT). Introducing a novel hybrid optimization algorithm (HOA), we aim to overcome these limitations by prioritizing both resource efficiency and data-driven performance. Through a thorough evaluation, HOA demonstrates its superiority in enhancing both aspects, thereby establishing itself as a compelling solution for AIoT applications. The introduction of HOA sets the stage for sustainable, cost-effective, and data-driven precision agriculture, significantly enhancing resource efficiency and data accuracy within the IoT network.

Research paper thumbnail of Predicting big data analytics adoption intention among small and medium enterprises in the Philippines

TELKOMNIKA Telecommunication Computing Electronics and Control

Big data analytics (BDA) has increasingly become popular both in theory and practice in recent ye... more Big data analytics (BDA) has increasingly become popular both in theory and practice in recent years. Globally, larger businesses have used BDA to collect, study, and evaluate vast volumes of data to identify market trends and insights that lead to sound and intelligent business decisions. However, its adoption in small and medium enterprises (SMEs) is not fully maximized because of a variety of factors, including a lack of expertise and financial repercussions. As such, this paper seeks to delve into the predictors of BDA adoption intention among SMEs in a developing nation by extending the technology acceptance model (TAM). The quantitative surveys obtained from 438 SMEs were analyzed using partial least squares and structural equation modeling (PLS-SEM). The results revealed that perceived benefits, namely system quality, information quality, and predictive analytics accuracy, had positive relationships with perceived ease of use and usefulness, subsequently leading to attitude towards using BDA. Likewise, perceived security significantly influences perceived benefits, perceived ease of use, and attitude towards use of BDA. Further, attitude towards use was the most significant predictor of intention to adopt BDA among SMEs. Generally, the study indicates a positive interest in adopting BDA among Philippine SMEs.

Research paper thumbnail of Fire detection and surveillance system with cloud-based alert to enhance safety in commercials and home

TELKOMNIKA Telecommunication Computing Electronics and Control

This study presents a comprehensive internet of things (IoT) solution for improving home automati... more This 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.

Research paper thumbnail of Simple RNN-LSTM hybrid deep learning model for Bitcoin and EUR_USD forecasting

TELKOMNIKA Telecommunication Computing Electronics and Control

The popularity of deep learning in time series prediction has significantly increased compared to... more The popularity of deep learning in time series prediction has significantly increased compared to the past. In this article, we utilize deep learning methods, which encompass long short term memory (LSTM) networks, simple recurrent neural network (SimpleRNN) networks, and gated recurrent units (GRU) networks. This research introduces a hybrid foundational model for forecasting future closing prices of EUR_USD in financial time series and Bitcoin, combining SimpleRNN with LSTM, referred to as SimpleRNN-LSTM. To improve the precisions of our hybrid model, we incorporate twenty-one technical indicators into the training data. Then, we compute four measures to evaluate the performance of various prediction models. When predicting currency pairs EUR_USD and Bitcoin, our hybrid foundational model outperforms SimpleRNN, LSTM, and GRU models.

Research paper thumbnail of Rainfall prediction using support vector regression in Udupi region Karnataka, India

TELKOMNIKA Telecommunication Computing Electronics and Control

The hydromatereological processes are examined through analysis of temporal rainfall variability.... more The 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.

Research paper thumbnail of Deep learning-based palm tree detection in unmanned aerial vehicle imagery with Mask R-CNN

TELKOMNIKA Telecommunication Computing Electronics and Control

Oil palm is highly valuable in tropical regions like Southeast Asia, including Indonesia. Therefo... more Oil palm is highly valuable in tropical regions like Southeast Asia, including Indonesia. Therefore, accurate monitoring of oil palm trees is necessary for operational efficiency and reducing its environmental impact. Geospatial data, such as orthomosaic imagery from the unmanned aerial vehicle (UAV), can facilitate this goal. This research aims to integrate UAV data with deep learning algorithms, specifically Mask region-based convolutional neural network (R-CNN), to detect oil palm trees in Indonesia. We utilized Resnet-50 as the backbone and trained the model using data sampled from the template matching tool in eCognition. Considering factors like cloud shadows and other features, such as other plants, buildings, and road segments, we divided the study area into three containing different feature combinations in each. The Mask R-CNN model achieved an accuracy exceeding 80%, which is sufficient and makes it suitable for large-scale oil palm tree detection using high resolution images from UAV.

Research paper thumbnail of Electroencephalography-based wheelchair navigation control using convolutional neural network method

TELKOMNIKA Telecommunication Computing Electronics and Control

Artificial intelligence refers to a computer-based system capable of learning human activities. F... more Artificial intelligence refers to a computer-based system capable of learning human activities. For instance, in medical technology, AI can be used for a thought-controlled wheelchair. This study discusses the use of deep learning, specifically convolutional neural network (CNN), in predictiong of the user intention to navigate a wheelchair. The training data was collected from an EEG sensor and included the wheelchair's movements -turning right, turning left, moving forward, moving backward, and idle. The signals were then sampled and feature-extracted using root mean square (RMS). In CNN classification, both raw and RMS data were used. This study compared two different CNN architectures. The first architecture has three convolutional layers and three pooling layers, while the second has two of each. The research compares the accuracy and loss values of CNN predictions using architecture 1 and 2 on both raw and RMS data. The experimental results indicate that when using raw data, the first CNN architecture achieved an accuracy of 85.12%, and the second model achieved 91.04%. However, when using RMS data, the first architecture achieved an accuracy of 76.47%, and the second achieved 73.74%. The study concludes that the movement of the wheelchair is better in real-time when using raw data compared to using RMS data.

Research paper thumbnail of Enhanced sentiment analysis and emotion detection in movie reviews using support vector machine algorithm

TELKOMNIKA Telecommunication Computing Electronics and Control

Films evoke diverse responses and reactions from audiences, captured through their reviews. These... more Films evoke diverse responses and reactions from audiences, captured through their reviews. These reviews serve as platforms for audiences to express opinions, evaluations, and emotions about films, reflecting the personal experiences and unique perceptions of the viewers. Given the vast volume of reviews and the distinctiveness of each perspective, automated analysis is essential for efficiently extracting valuable insights. This study employs the support vector machine (SVM) algorithm for classifying movie reviews into positive and negative categories. The dataset includes 50,000 IMDb movie reviews, split evenly between positive and negative sentiments. Each review is analyzed using the National Research Council Canada (NRC) emotion lexicon (NRCLex) to assign scores for emotions such as anger, disgust, fear, joy, sadness, and surprise. Subsequently, these reviews are further analyzed using term frequency-inverse document frequency (TF-IDF) for classification. The proposed algorithm achieves 90% accuracy, indicating its effectiveness in classifying sentiments in movie reviews. The study's findings confirm the potential of the SVM algorithm for broader applications in sentiment analysis and natural language processing. Additionally, integrating emotion detection enhances understanding of nuanced emotional content, providing a comprehensive approach to sentiment classification in large datasets.

Research paper thumbnail of Prediction of heart disease using random forest algorithm, support vector machine, and neural network

TELKOMNIKA Telecommunication Computing Electronics and Control

The heart is a vital organ responsible for pumping blood throughout the human body. Machine learn... more The heart is a vital organ responsible for pumping blood throughout the human body. Machine learning has become an increasingly important tool in medical forecasting, improving diagnostic accuracy and reducing human errors. This study focuses on detecting heart disease using machine learning algorithms. It aims to compare the performance of three key algorithms random forest (RF), support vector machine (SVM), and neural networks (NN), in predicting heart disease. Using a patient dataset with both nominal and numeric attributes, record mining techniques were applied through Orange software. The target classes indicated the absence (0) or presence (1) of heart disorders. The evaluation was based on the prediction accuracy of each algorithm. Results show that SVM achieved the highest accuracy, with a rate of 85%, outperforming RF and NN. The findings suggest that the SVM algorithm is a reliable tool for heart disease prediction, helping reduce diagnostic errors and improve medical decision-making.

Research paper thumbnail of Customer segmentation in e-commerce: K-means vs hierarchical clustering

TELKOMNIKA Telecommunication Computing Electronics and Control

Customer segmentation is important for e-commerce companies to understand and target different cu... more Customer segmentation is important for e-commerce companies to understand and target different customers. The primary focus of this work is the application and comparison of K-means clustering and hierarchical clustering, unsupervised machine learning techniques, in customer segmentation for ecommerce platforms. Clustering leverages customer search behavior, reflecting brand preferences, and identifying distinct customer segments. The proposed work explores the K-means algorithm and hierarchical clustering. It uses them to classify customers in a standard e-commerce customer dataset, mainly focused on frequently searched brands. Both techniques are compared based on silhouette scores and cluster visualizations. K-means clustering yielded well-separated segments compared to hierarchical clustering. Then, using the K-means algorithm, customers are classified into different segments based on brand search patterns. Further, targeted marketing strategies are discussed for each segment. Results show three customer segments: high searchers-low buyers, loyal customers, and moderate engagers. The proposed work provides valuable insights into customers that could be used for developing targeted marketing campaigns, product recommendations, and customer engagement strategies to enhance the conversion rate, customer satisfaction, and, in turn, the growth of an e-commerce platform.

Research paper thumbnail of Comparative analysis of cross-platform development methodologies: a comprehensive study

TELKOMNIKA Telecommunication Computing Electronics and Control

In an era marked by the proliferation of devices and operating systems, delivering native-feeling... more In an era marked by the proliferation of devices and operating systems, delivering native-feeling applications across platforms has become indispensable. This paper scrutinizes native development through the lens of cross-platform frameworks, investigating their merits, major contenders such as React Native, Flutter, Xamarin, and the nascent .NET MAUI, and their practical implementations. By dissecting the distinct strengths and considerations of each framework, we provide developers with insights to make judicious decisions commensurate with their requirements and proficiencies. This inquiry underscores how cross-platform frameworks empower developers to broaden their audience reach while upholding native performance standards, thereby shaping the trajectory of app development through sustained innovation and integration with emergent technologies.

Research paper thumbnail of Designing a marketplace system to assist incubators in higher education in fostering technopreneurship

TELKOMNIKA Telecommunication Computing Electronics and Control

Technology-based startups play a vital role in boosting the Indonesian economy. However, many fac... more Technology-based startups play a vital role in boosting the Indonesian economy. However, many face sustainability challenges due to misalignment with market needs and a lack of comprehensive understanding of business processes. This condition demands the application of academic theories related to increasing productivity and highlights the need for innovative solutions. Universities can significantly support the development of these startups by leveraging business incubators to enhance competitiveness in the digital era. This research aims to propose a marketplace system architecture incorporating a business incubator unit (BIU), integrating scientific knowledge with societal business interests and talents in a university. The system is developed by the enterprise architecture (EA) methodology with the the open group architecture framework (TOGAF). This approach ensures a systematic design process that aligns with best practices. This study results in several strategic artefacts that provide guidance for creating a practical environment for entrepreneurs and translating theoretical insights into actionable business strategies. The artefacts can be rigorously tested and applied in real-world business incubator settings. The proposed system addresses critical challenges startup businesses face, such as enhancing business understanding and providing a fair foundation before entering the competitive market.

Research paper thumbnail of Swarm intelligence for intrusion detection systems in internet of things environments

TELKOMNIKA Telecommunication Computing Electronics and Control

The rise of the internet of things (IoT) technology has brought new security challenges, necessit... more The rise of the internet of things (IoT) technology has brought new security challenges, necessitating robust intrusion detection systems (IDS). This research applies swarm intelligence (SI) principles, specifically the pigeon inspired optimization (PIO) algorithm, to enhance IDS effectiveness in IoT environments. Drawing on the behavior of social species, SI fosters decentralized control and emergent behavior from simple rules. These principles guide the PIO algorithm, making it apt for optimizing IDS. We utilize two comprehensive IoT datasetsthe Canadian Institute for Cybersecurity (CIC) IoT dataset 2023 and the IoT dataset for IDS, aiming to boost the IDS's capability to detect illicit attacks. By adapting the PIO algorithm, our IDS learns from the environment, adapts to evolving threats, and mitigates false-positive rates. Preliminary tests show that our SI-based IDS outperforms traditional systems' accuracy, speed, and adaptability. This research advances SI applications in IoT security, contributing to developing more resilient IDS and ultimately enhancing IoT network security against a range of cyber threats.

Research paper thumbnail of NAT64 vs SIIT: performance and scalability study for VoIP services

TELKOMNIKA Telecommunication Computing Electronics and Control

The growing demand for IP addresses, driven by the proliferation of devices, has depleted the int... more The growing demand for IP addresses, driven by the proliferation of devices, has depleted the internet protocol (IP) version 6 (IPv6) reserves of some regional internet registries (RIRs). It is imperative to migrate to IPv6, offering an extended addressing space. This transition is no longer a choice but a necessity due to the exhaustion of IP version 4 (IPv4) addresses. The internet engineering task force (IETF) has implemented various transition strategies, such as the use of dual stack, IPv6-in-IPv4 tunnels, and address translation, due to the inconsistency between the two versions of the IP (IPv4 and IPv6). IPv4/IPv6 address translation mechanisms are crucial for the coexistence of networks using both protocols, with scalability playing a central role. Although these mechanisms offer advantages such as optimizing addressing space, their ability to scale effectively must be evaluated, especially in demanding scenarios such as voice over IP (VoIP). This article examines the scalability of two mechanisms, network address translation 64 (NAT64) and stateless IP/internet control message protocol (ICMP) translation (SIIT), in terms of VoIP clients in the graphical network simulator 3 (GNS3) environment. The results indicate that the SIIT mechanism is more performant and scalable than NAT64 in all measured parameters.

Research paper thumbnail of Effects of atmospheric turbulence and reconfigurable intelligent surfaces on near terrestrial optical link for internet of things

TELKOMNIKA Telecommunication Computing Electronics and Control

Near terrestrial free-space optical (NT-FSO) communication refers to the use of light to transmit... more Near terrestrial free-space optical (NT-FSO) communication refers to the use of light to transmit data wirelessly through the atmosphere over relatively short distances, typically within the earth's atmosphere. It is an alternative to traditional radio frequency (RF) communication and fiber optics, providing high-speed data transmission without the need for physical cables. NT-FSO is an attractive solution for high-speed, short-distance wireless communications where physical infrastructure like fiber is impractical. Reconfigurable intelligent surfaces (RIS) are a cutting-edge technology that enhances wireless communication systems by dynamically controlling how electromagnetic waves propagate through an environment. RIS technology is increasingly relevant in modern communication systems like 5G and beyond, aiming to improve the efficiency, coverage, and energy usage of wireless networks. This study investigates the effects of atmospheric turbulence and RIS on near terrestrial optical link for internet of things. Several numerical outcomes obtained for different link distance and average electrical signal signal-to-noise ratio (SNR) are shown to quantitatively illustrate the average spectral efficiency.

Research paper thumbnail of PV solar anomaly detection using low-cost data logger and ANN algorithm

TELKOMNIKA Telecommunication, Computing, Electronics and Control

This paper presents an innovative edge device architecture that significantly enhances solar ener... more This paper presents an innovative edge device architecture that significantly enhances solar energy management systems. By integrating advanced functionalities such as generation prediction, maintenance alerts, and solar anomaly detection, this architecture transforms solar energy management. Through edge computing, it enables real-time analysis and decision-making at the network edge. Leveraging machine learning algorithms and accurate predictive models, these edge devices provide precise energy generation forecasts, facilitating optimal energy utilization and strategic planning for stakeholders. Additionally, the architecture incorporates anomaly detection techniques to proactively identify deviations from normal operation, minimizing downtime, and enabling timely maintenance. This approach ensures uninterrupted energy generation, enhancing the reliability and efficiency of the entire monitoring system. The integration of these features within edge devices improves the performance and reliability of energy monitoring systems. Implementing this cutting-edge architecture empowers stakeholders to achieve superior energy management, substantial cost reductions, and unparalleled system reliability.

Research paper thumbnail of Power system frequency control: instantaneous discrete testing for numerical relay using wavelet transform

TELKOMNIKA Telecommunication Computing Electronics and Control

With today's advanced technology and rapidly growing energy demands, the reliability of electrica... more With today's advanced technology and rapidly growing energy demands, the reliability of electrical power systems has reached an important level. With extensive monitoring and protection, system issues like voltage drops, power irregularities, and frequency variations can have destructive consequences on the power network. Therefore, as frequency relays play a critical role in protecting power generators and load equipment from power frequency shifts, relays have evolved from electromechanical to solid-state devices with ongoing optimization to handle integrated modern networks. Traditional numerical relays use Fourier transform to identify frequency changes, which necessitates numerous data samples and has limitations with transient waveform data. To address these challenges, this work proposes a new relay algorithm based on instantaneous discrete testing and wavelet transform for frequency analysis, aimed at enhancing relay performance. This new approach demonstrates promising advantages, including significant reductions in data sample requirements, compilation complexity, decision-making time, and improved handling of transient waveforms.

Research paper thumbnail of Enhanced fuzzy logic control for overcoming intrinsic resistance in inverted pendulum systems

TELKOMNIKA Telecommunication Computing Electronics and Control

The paper delves into an in-depth analysis of the intrinsic resistance of the inverted pendulum s... more The paper delves into an in-depth analysis of the intrinsic resistance of the inverted pendulum system which causes the modeling of the system to differ from the actual system. Our primary objective revolves around the implementation and subsequent optimization of fuzzy logic controllers (FLC), drawing inspiration from human perceptual assessments. The processing comprises comprehensive mathematical system modeling, intrinsic resistance examination, and improved fuzzy logic control with detailed membership function and rule design. In addition, we conduct a comparative analysis with the widely recognized linear quadratic regulator (LQR) algorithm, which is considered the conventional control algorithm. The result demonstrates that the improved FLC outperforms the conventional LQR algorithm overshoot mitigation, thereby underscoring its superior efficacy and optimality.

Research paper thumbnail of Adaptive diving depth control system for the drifting autonomous underwater vehicle

TELKOMNIKA Telecommunication Computing Electronics and Control

This article considers the system for controlling the diving depth of a drifting autonomous under... more This article considers the system for controlling the diving depth of a drifting autonomous underwater vehicle (DAUV), which navigates underwater under the influence of sea currents in order to collect scientific information. The paper solves the problem of identifying non-stationary hydrodynamic parameters of the DAUV with the aim of adaptive adjustment of the DAUV control algorithm to increase the accuracy of bringing the DAUV to a given depth and minimizing the consumption of electricity consumed by power actuators. The solution to the problem is based on the use of parametric identification apparatus and adaptive control principles. The high quality of the DAUV diving depth control is achieved through the use of the method of adaptive adjustment of the parameters of the DAUV program model. The use of parametric identification of the hydrodynamic parameters of the DAUV made it possible to quickly adjust the corrective link in the control chain of the executing mechanism of the DAUV. The developed computer models and a set of semi-realistic tests made it possible to choose the most acceptable identification algorithm and configure the software implementation of the DAUV diving depth control law.

Research paper thumbnail of Identification of working memory status in children from EEG signal features using discrete wavelet transform

TELKOMNIKA Telecommunication Computing Electronics and Control

The conventional method for assessing the working memory performance of children is time-consumin... more The conventional method for assessing the working memory performance of children is time-consuming and potentially inaccurate, especially when dealing with many samples. Therefore, an automated system that can produce swift and accurate results is required. Electroencephalograms (EEG) can be used to analyse the working memory status of children by extracting specific features from the EEG signal, which can be incorporated into an automatic system to reduce manpower and processing time for analysis. This project used EEG recording to identify children's working memory status while they were performing working memory tasks. EEG signals were acquired from both children and adults using an automated computer-based working memory assessment tool, processed, and analyzed. The discrete wavelet transform (DWT) was then employed to identify five distinct working memory statuses: distracted, confused, daydreaming, losing focus, and active. DWT was also used to extract features that demonstrate these various statuses. The results showed that DWT could accurately identify the working memory status of both children and adults from their EEGs. This work has thus provided a more efficient method for extracting features from EEG signals to identify working memory statuses in both children and adults.

Research paper thumbnail of Hybrid optimization algorithm for resource-efficient and datadriven performance in agricultural

TELKOMNIKA Telecommunication Computing Electronics and Control

The agricultural sector is undergoing a significant transformation with the adoption of the agric... more The agricultural sector is undergoing a significant transformation with the adoption of the agricultural internet of things (IoT), yet it faces persistent challenges in optimizing resource efficiency and data-driven performance due to limitations in current optimization algorithms. This research assesses the effectiveness of four prominent algorithms such as ant colony optimization (ACO), genetic algorithms (GA), particle swarm optimization (PSO), and artificial bee colony (ABC) in addressing these challenges within agricultural IoT (AIoT). Introducing a novel hybrid optimization algorithm (HOA), we aim to overcome these limitations by prioritizing both resource efficiency and data-driven performance. Through a thorough evaluation, HOA demonstrates its superiority in enhancing both aspects, thereby establishing itself as a compelling solution for AIoT applications. The introduction of HOA sets the stage for sustainable, cost-effective, and data-driven precision agriculture, significantly enhancing resource efficiency and data accuracy within the IoT network.

Research paper thumbnail of Predicting big data analytics adoption intention among small and medium enterprises in the Philippines

TELKOMNIKA Telecommunication Computing Electronics and Control

Big data analytics (BDA) has increasingly become popular both in theory and practice in recent ye... more Big data analytics (BDA) has increasingly become popular both in theory and practice in recent years. Globally, larger businesses have used BDA to collect, study, and evaluate vast volumes of data to identify market trends and insights that lead to sound and intelligent business decisions. However, its adoption in small and medium enterprises (SMEs) is not fully maximized because of a variety of factors, including a lack of expertise and financial repercussions. As such, this paper seeks to delve into the predictors of BDA adoption intention among SMEs in a developing nation by extending the technology acceptance model (TAM). The quantitative surveys obtained from 438 SMEs were analyzed using partial least squares and structural equation modeling (PLS-SEM). The results revealed that perceived benefits, namely system quality, information quality, and predictive analytics accuracy, had positive relationships with perceived ease of use and usefulness, subsequently leading to attitude towards using BDA. Likewise, perceived security significantly influences perceived benefits, perceived ease of use, and attitude towards use of BDA. Further, attitude towards use was the most significant predictor of intention to adopt BDA among SMEs. Generally, the study indicates a positive interest in adopting BDA among Philippine SMEs.

Research paper thumbnail of Fire detection and surveillance system with cloud-based alert to enhance safety in commercials and home

TELKOMNIKA Telecommunication Computing Electronics and Control

This study presents a comprehensive internet of things (IoT) solution for improving home automati... more This 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.

Research paper thumbnail of Simple RNN-LSTM hybrid deep learning model for Bitcoin and EUR_USD forecasting

TELKOMNIKA Telecommunication Computing Electronics and Control

The popularity of deep learning in time series prediction has significantly increased compared to... more The popularity of deep learning in time series prediction has significantly increased compared to the past. In this article, we utilize deep learning methods, which encompass long short term memory (LSTM) networks, simple recurrent neural network (SimpleRNN) networks, and gated recurrent units (GRU) networks. This research introduces a hybrid foundational model for forecasting future closing prices of EUR_USD in financial time series and Bitcoin, combining SimpleRNN with LSTM, referred to as SimpleRNN-LSTM. To improve the precisions of our hybrid model, we incorporate twenty-one technical indicators into the training data. Then, we compute four measures to evaluate the performance of various prediction models. When predicting currency pairs EUR_USD and Bitcoin, our hybrid foundational model outperforms SimpleRNN, LSTM, and GRU models.

Research paper thumbnail of Rainfall prediction using support vector regression in Udupi region Karnataka, India

TELKOMNIKA Telecommunication Computing Electronics and Control

The hydromatereological processes are examined through analysis of temporal rainfall variability.... more The 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.

Research paper thumbnail of Deep learning-based palm tree detection in unmanned aerial vehicle imagery with Mask R-CNN

TELKOMNIKA Telecommunication Computing Electronics and Control

Oil palm is highly valuable in tropical regions like Southeast Asia, including Indonesia. Therefo... more Oil palm is highly valuable in tropical regions like Southeast Asia, including Indonesia. Therefore, accurate monitoring of oil palm trees is necessary for operational efficiency and reducing its environmental impact. Geospatial data, such as orthomosaic imagery from the unmanned aerial vehicle (UAV), can facilitate this goal. This research aims to integrate UAV data with deep learning algorithms, specifically Mask region-based convolutional neural network (R-CNN), to detect oil palm trees in Indonesia. We utilized Resnet-50 as the backbone and trained the model using data sampled from the template matching tool in eCognition. Considering factors like cloud shadows and other features, such as other plants, buildings, and road segments, we divided the study area into three containing different feature combinations in each. The Mask R-CNN model achieved an accuracy exceeding 80%, which is sufficient and makes it suitable for large-scale oil palm tree detection using high resolution images from UAV.

Research paper thumbnail of Electroencephalography-based wheelchair navigation control using convolutional neural network method

TELKOMNIKA Telecommunication Computing Electronics and Control

Artificial intelligence refers to a computer-based system capable of learning human activities. F... more Artificial intelligence refers to a computer-based system capable of learning human activities. For instance, in medical technology, AI can be used for a thought-controlled wheelchair. This study discusses the use of deep learning, specifically convolutional neural network (CNN), in predictiong of the user intention to navigate a wheelchair. The training data was collected from an EEG sensor and included the wheelchair's movements -turning right, turning left, moving forward, moving backward, and idle. The signals were then sampled and feature-extracted using root mean square (RMS). In CNN classification, both raw and RMS data were used. This study compared two different CNN architectures. The first architecture has three convolutional layers and three pooling layers, while the second has two of each. The research compares the accuracy and loss values of CNN predictions using architecture 1 and 2 on both raw and RMS data. The experimental results indicate that when using raw data, the first CNN architecture achieved an accuracy of 85.12%, and the second model achieved 91.04%. However, when using RMS data, the first architecture achieved an accuracy of 76.47%, and the second achieved 73.74%. The study concludes that the movement of the wheelchair is better in real-time when using raw data compared to using RMS data.

Research paper thumbnail of Enhanced sentiment analysis and emotion detection in movie reviews using support vector machine algorithm

TELKOMNIKA Telecommunication Computing Electronics and Control

Films evoke diverse responses and reactions from audiences, captured through their reviews. These... more Films evoke diverse responses and reactions from audiences, captured through their reviews. These reviews serve as platforms for audiences to express opinions, evaluations, and emotions about films, reflecting the personal experiences and unique perceptions of the viewers. Given the vast volume of reviews and the distinctiveness of each perspective, automated analysis is essential for efficiently extracting valuable insights. This study employs the support vector machine (SVM) algorithm for classifying movie reviews into positive and negative categories. The dataset includes 50,000 IMDb movie reviews, split evenly between positive and negative sentiments. Each review is analyzed using the National Research Council Canada (NRC) emotion lexicon (NRCLex) to assign scores for emotions such as anger, disgust, fear, joy, sadness, and surprise. Subsequently, these reviews are further analyzed using term frequency-inverse document frequency (TF-IDF) for classification. The proposed algorithm achieves 90% accuracy, indicating its effectiveness in classifying sentiments in movie reviews. The study's findings confirm the potential of the SVM algorithm for broader applications in sentiment analysis and natural language processing. Additionally, integrating emotion detection enhances understanding of nuanced emotional content, providing a comprehensive approach to sentiment classification in large datasets.

Research paper thumbnail of Prediction of heart disease using random forest algorithm, support vector machine, and neural network

TELKOMNIKA Telecommunication Computing Electronics and Control

The heart is a vital organ responsible for pumping blood throughout the human body. Machine learn... more The heart is a vital organ responsible for pumping blood throughout the human body. Machine learning has become an increasingly important tool in medical forecasting, improving diagnostic accuracy and reducing human errors. This study focuses on detecting heart disease using machine learning algorithms. It aims to compare the performance of three key algorithms random forest (RF), support vector machine (SVM), and neural networks (NN), in predicting heart disease. Using a patient dataset with both nominal and numeric attributes, record mining techniques were applied through Orange software. The target classes indicated the absence (0) or presence (1) of heart disorders. The evaluation was based on the prediction accuracy of each algorithm. Results show that SVM achieved the highest accuracy, with a rate of 85%, outperforming RF and NN. The findings suggest that the SVM algorithm is a reliable tool for heart disease prediction, helping reduce diagnostic errors and improve medical decision-making.

Research paper thumbnail of Customer segmentation in e-commerce: K-means vs hierarchical clustering

TELKOMNIKA Telecommunication Computing Electronics and Control

Customer segmentation is important for e-commerce companies to understand and target different cu... more Customer segmentation is important for e-commerce companies to understand and target different customers. The primary focus of this work is the application and comparison of K-means clustering and hierarchical clustering, unsupervised machine learning techniques, in customer segmentation for ecommerce platforms. Clustering leverages customer search behavior, reflecting brand preferences, and identifying distinct customer segments. The proposed work explores the K-means algorithm and hierarchical clustering. It uses them to classify customers in a standard e-commerce customer dataset, mainly focused on frequently searched brands. Both techniques are compared based on silhouette scores and cluster visualizations. K-means clustering yielded well-separated segments compared to hierarchical clustering. Then, using the K-means algorithm, customers are classified into different segments based on brand search patterns. Further, targeted marketing strategies are discussed for each segment. Results show three customer segments: high searchers-low buyers, loyal customers, and moderate engagers. The proposed work provides valuable insights into customers that could be used for developing targeted marketing campaigns, product recommendations, and customer engagement strategies to enhance the conversion rate, customer satisfaction, and, in turn, the growth of an e-commerce platform.

Research paper thumbnail of Comparative analysis of cross-platform development methodologies: a comprehensive study

TELKOMNIKA Telecommunication Computing Electronics and Control

In an era marked by the proliferation of devices and operating systems, delivering native-feeling... more In an era marked by the proliferation of devices and operating systems, delivering native-feeling applications across platforms has become indispensable. This paper scrutinizes native development through the lens of cross-platform frameworks, investigating their merits, major contenders such as React Native, Flutter, Xamarin, and the nascent .NET MAUI, and their practical implementations. By dissecting the distinct strengths and considerations of each framework, we provide developers with insights to make judicious decisions commensurate with their requirements and proficiencies. This inquiry underscores how cross-platform frameworks empower developers to broaden their audience reach while upholding native performance standards, thereby shaping the trajectory of app development through sustained innovation and integration with emergent technologies.

Research paper thumbnail of Designing a marketplace system to assist incubators in higher education in fostering technopreneurship

TELKOMNIKA Telecommunication Computing Electronics and Control

Technology-based startups play a vital role in boosting the Indonesian economy. However, many fac... more Technology-based startups play a vital role in boosting the Indonesian economy. However, many face sustainability challenges due to misalignment with market needs and a lack of comprehensive understanding of business processes. This condition demands the application of academic theories related to increasing productivity and highlights the need for innovative solutions. Universities can significantly support the development of these startups by leveraging business incubators to enhance competitiveness in the digital era. This research aims to propose a marketplace system architecture incorporating a business incubator unit (BIU), integrating scientific knowledge with societal business interests and talents in a university. The system is developed by the enterprise architecture (EA) methodology with the the open group architecture framework (TOGAF). This approach ensures a systematic design process that aligns with best practices. This study results in several strategic artefacts that provide guidance for creating a practical environment for entrepreneurs and translating theoretical insights into actionable business strategies. The artefacts can be rigorously tested and applied in real-world business incubator settings. The proposed system addresses critical challenges startup businesses face, such as enhancing business understanding and providing a fair foundation before entering the competitive market.

Research paper thumbnail of Swarm intelligence for intrusion detection systems in internet of things environments

TELKOMNIKA Telecommunication Computing Electronics and Control

The rise of the internet of things (IoT) technology has brought new security challenges, necessit... more The rise of the internet of things (IoT) technology has brought new security challenges, necessitating robust intrusion detection systems (IDS). This research applies swarm intelligence (SI) principles, specifically the pigeon inspired optimization (PIO) algorithm, to enhance IDS effectiveness in IoT environments. Drawing on the behavior of social species, SI fosters decentralized control and emergent behavior from simple rules. These principles guide the PIO algorithm, making it apt for optimizing IDS. We utilize two comprehensive IoT datasetsthe Canadian Institute for Cybersecurity (CIC) IoT dataset 2023 and the IoT dataset for IDS, aiming to boost the IDS's capability to detect illicit attacks. By adapting the PIO algorithm, our IDS learns from the environment, adapts to evolving threats, and mitigates false-positive rates. Preliminary tests show that our SI-based IDS outperforms traditional systems' accuracy, speed, and adaptability. This research advances SI applications in IoT security, contributing to developing more resilient IDS and ultimately enhancing IoT network security against a range of cyber threats.

Research paper thumbnail of NAT64 vs SIIT: performance and scalability study for VoIP services

TELKOMNIKA Telecommunication Computing Electronics and Control

The growing demand for IP addresses, driven by the proliferation of devices, has depleted the int... more The growing demand for IP addresses, driven by the proliferation of devices, has depleted the internet protocol (IP) version 6 (IPv6) reserves of some regional internet registries (RIRs). It is imperative to migrate to IPv6, offering an extended addressing space. This transition is no longer a choice but a necessity due to the exhaustion of IP version 4 (IPv4) addresses. The internet engineering task force (IETF) has implemented various transition strategies, such as the use of dual stack, IPv6-in-IPv4 tunnels, and address translation, due to the inconsistency between the two versions of the IP (IPv4 and IPv6). IPv4/IPv6 address translation mechanisms are crucial for the coexistence of networks using both protocols, with scalability playing a central role. Although these mechanisms offer advantages such as optimizing addressing space, their ability to scale effectively must be evaluated, especially in demanding scenarios such as voice over IP (VoIP). This article examines the scalability of two mechanisms, network address translation 64 (NAT64) and stateless IP/internet control message protocol (ICMP) translation (SIIT), in terms of VoIP clients in the graphical network simulator 3 (GNS3) environment. The results indicate that the SIIT mechanism is more performant and scalable than NAT64 in all measured parameters.

Research paper thumbnail of Effects of atmospheric turbulence and reconfigurable intelligent surfaces on near terrestrial optical link for internet of things

TELKOMNIKA Telecommunication Computing Electronics and Control

Near terrestrial free-space optical (NT-FSO) communication refers to the use of light to transmit... more Near terrestrial free-space optical (NT-FSO) communication refers to the use of light to transmit data wirelessly through the atmosphere over relatively short distances, typically within the earth's atmosphere. It is an alternative to traditional radio frequency (RF) communication and fiber optics, providing high-speed data transmission without the need for physical cables. NT-FSO is an attractive solution for high-speed, short-distance wireless communications where physical infrastructure like fiber is impractical. Reconfigurable intelligent surfaces (RIS) are a cutting-edge technology that enhances wireless communication systems by dynamically controlling how electromagnetic waves propagate through an environment. RIS technology is increasingly relevant in modern communication systems like 5G and beyond, aiming to improve the efficiency, coverage, and energy usage of wireless networks. This study investigates the effects of atmospheric turbulence and RIS on near terrestrial optical link for internet of things. Several numerical outcomes obtained for different link distance and average electrical signal signal-to-noise ratio (SNR) are shown to quantitatively illustrate the average spectral efficiency.