TELKOMNIKA (Telecommunication Computing Electronics and Control)
Not a member yet
3120 research outputs found
Sort by
BER performance in NOMA downlink transmission using AWGN, Rayleigh, and Rician fading channels
Full text link5G wireless technology is accessible to a much larger user base compared to previous cellular networks. Users can connect to base stations (BSs) in a variety of methods, including of frequency division multiplexing (FDM), orthogonal frequency division multiplexing (OFDM), orthogonal multiple access (OMA), and non-orthogonal multiple access (NOMA). NOMA is considered to be the best one for 5G. Additionally, NOMA employs radio resource optimization and interference control techniques to enhance spectrum network efficiency and support extremely large connections, such as successive interference cancellation (SIC). Users can be divided into two categories: strong and weak. While weak users may experience a low data rate, strong users need a high one. In this paper, we examine the two users in relation to transmit power, the indicative bit error rate (BER), outage probability (OP), and rate attainable capacity using additive white gaussian noise (AWGN) channel. Moreover, we compare the BER and signal-to-noise ratio (SNR) per bit for two users, showing that the Rician fading channel performs better than the Rayleigh fading channel. The use of NOMA technology is the optimal choice and indicates an improvement in the precision of data transmission within the communication system, particularly in the presence of noise and interference
PV solar anomaly detection using low-cost data logger and ANN algorithm
Full text linkThis 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
A stacking ensemble model with SMOTE for improved imbalanced classification on credit data
Full text linkThis research is based on a significant problem in credit risk analysis in the banking sector caused by class imbalance. We face the problem of the model’s inability to accurately identify risks in the ‘‘Charged Off’’ class. As a solution, we propose a stacked ensemble approach that utilizes synthetic minority over-sampling technique (SMOTE) to balance the class distribution. Experiments were conducted by applying SMOTE to the training data before training the credit model using gradient boosting (XGBoost) and random forest (RF) algorithms in a single ensemble. The results show significant improvements in precision, recall, and F1-score after applying SMOTE on the unbalanced classes. The updated model achieved a striking accuracy rate of 0,97 on resampled training data. This re-search clearly identifies the problem of class imbalance as a major challenge in credit risk analysis. The application of SMOTE in a stacked ensemble was found to be effective in improving model performance, making a valuable contribution to the development of more reliable credit models for better risk management and revenue generation in financial institutions
Classifying date fruits using the transfer learning model
Full text linkDate palm trees originate in many tropical regions of the world and produce dates. Each variety can be differentiated through the shape, texture, size, and colour of the fruits. People have difficulties visualising and recognising the types of date fruits because they have many varieties and species. An Android-based mobile application is being proposed to help users quickly identify the dates based on their images and expand their knowledge of dates. The date fruit species classification mobile application categorises nine different varieties of date fruits, namely Ajwa, Medjool, Rutab, Nabtat Ali, Meneifi, Galaxy, Sugaey, Shaishe, and Sokari. The classification, which is based on a transfer learning technique from a pre-trained neural network, achieved a 94.2% accuracy rate. The mobile application features a user-friendly graphical interface that makes it easy to use and understand. Users can learn about different date fruit varieties and improve knowledge retention through a mini game. The application’s usability, usefulness, and interface design were confirmed through the user acceptance survey
Navigating the digital shift: a service blueprint for coopetition technology-enabled networks
Full text linkThis study addresses the gap in applying traditional service blueprint methodologies to technology-enabled coopetition networks characterized by simultaneous collaboration and competition among actors. Leveraging service science insights, it proposes an enhanced service blueprint framework designed for the complexities of digital coopetition. This framework introduces the cyber. Frontstage lane, physical backstage lane, and support stage lane aim to provide a holistic view of interactions, value co-creation processes, and resource allocations. Empirical validation within the Portuguese stone sector-a key player in the national economy-demonstrates the framework’s effectiveness in identifying network dysfunctions and its ease of use by industry professionals. Feedback confirms its relevance in capturing today’s coopetition environments’ multifaceted engagements and digital nuances. The study emphasizes adapting service blueprint methodology to better manage and innovate service processes in digital ecosystems. Future research should extend this framework’s application across various sectors and explore the integration of emerging technologies to optimize service delivery and value co-creation
Fall incidence prediction system for elderly people based on IoT and classification techniques
Full text linkHealth monitoring systems based on the internet of things (IoT) improve patient well-being and reduce mortality risks. Machine learning techniques are most helpful in early fall prediction and detection. In this paper, fall prediction analysis and decision-making are done with existing benchmark clinical records. Classification techniques are incorporated to track the consistency and precision of data acquired by the IoT-based remote health monitoring for elderly people, especially those who are living alone. This work undertakes two approaches to early predicting a patient’s acute illness. The first approach has analyzed the existing benchmark patient activity data with different features. This approach builds the classification model for fall incidence with the help of machine learning models. In second approach, we collect real-time sensor data such as blood pressure and heart rate from IoT sensor gadgets which are transmitted to the prediction model for early prediction. Experimental results prove that the random forest (RF) classifiers and XGBoost provides the maximum accuracy
Gilbert cell down-conversion mixer for THz wireless communication with passive baluns
Full text linkThis article presents the design of an active down-conversion mixer for the superheterodyne receiver system for 6G wireless communications. This mixer is developed based on the Gilbert cell in the terahertz frequency band, using the PH15 transistor from United Monolithic Semiconductors (UMS) Foundry in monolithic microwave integrated circuit (MMIC) technology. We used the charge injection method to increase our mixer’s conversion gain. In addition, we integrated a buffer stage at the mixer outputs to facilitate impedance matching and improve linearity. The power dividers used in this chapter are based on transmission lines from Agilent's advanced design system (ADS) tool, connected to the input and output ports of the circuit. The proposed architecture offers a high conversion gain of 15.2 dB, with a low local oscillator (LO) power of 0 dBm, a low double sideband (DSB) noise figure (NF) of around 7.1 dB, a 1\ dB compression point of -16 dBm, and good radio frequency (RF)-LO port isolation of 63.2 dB, at a RF of 0.14 THz
Design and implementation of a cryptographic algorithm based on the AES advanced encryption standard for UHF RFID systems
Full text linkIn this paper, a proposal is made for a cryptographic algorithm designed for passive ultra-high-frequency (UHF) radio frequency identification systems. The algorithm relies on the advanced encryption standard (AES) as its fundamental encryption technique, augmented by two supplementary steps: the initial step involves generating a random key and the second is the randomization of data, this introduces an extra level of security to encryption process against attacks. The developed architecture has been optimized to minimize hardware resource consumption with faster execution speed. The algorithm has been simulated, synthesized and implemented in an xtreme digital signal processing (DSP) starter kit equipped with xilinx’s spartan-3A DSP 1800A edition and it serves the purpose of encrypting and decrypting user data on a radio frequency identification (RFID) passive tag. The main objective is to make it difficult to break the algorithm because of its multiple steps. The experimental results showed that the speed, functionality and cost of encryption and decryption make this a perfectly practical solution, providing a satisfactory level of security for today’s communications systems, or other electronic data transfer processes where security is required
Highly selective dual-band interdigital bandpass filter for C-band applications
Full text linkMiniaturization in the telecommunications field is deemed a current challenge and a critical demand in order to improve communication quality between the transmitter and the receiver while avoiding clutter issues. The main objective of this work is to design a miniature interdigital bandpass filter (IBF) using planar technology. The proposed bandpass filter is made up of three equidistant parallel-coupled lines carefully deposited on a small Rogers-5880 substrate possessing a full dimension of 10×10×1.6 mm3, a relative permittivity =2.2, and a loss tangen of 0.0009. The proposed IBF has been designed and simulated using the HFSS software, which is a simulator that studies the electromagnetic behavior of radio frequency structures using cutting-edge finite element solvers. The reached outcomes present good electrical performance in terms of insertion loss , reflection coefficient , voltage standing wave ratio (VSWR), and selectivity, making the proposed IBF suitable for integration in small electronic devices for C-band applications (4 GHz to 8 GHz)
Malaysian fibre internet service provider: a naïve Bayes classification Twitter sentiment analysis
Full text linkIn the highly competitive landscape of Malaysian internet service providers (ISPs), users seek efficient ways to assess service quality. While various websites allow visual comparisons of fiber ISPs, a direct side-by-side evaluation remains elusive. A survey of 101 respondents revealed that 92.1% found researching a company’s reputation time-consuming. Additionally, relying on English-centric online ratings may lead to skewed outcomes, disregarding reviews in diverse languages. In response, we developed a web-based dashboard utilizing Twitter sentiment analysis (SA) and the naïve Bayes (NB) algorithm to classify Malaysia’s best fiber ISPs. The SA focused on four key factors: package price, internet speed, coverage area, and customer service, simplifying the comparison process. The system’s usability and functionality tests showed that both the English and Malay models could classify scraped Twitter data with an accuracy of 80%. The system’s remarkable usability score of 94.58% on the system usability scale (SUS) confirms its acceptability and excellent performance in achieving research goals