280 hasil
Menampilkan 1–20 · 0,59 detik · RSS
Journal of Information and Telecommunication, Pp 1-33 (2026)
Scopus
ISSN 2475-1847 · Taylor & Francis Group · 280 artikel di indeks
-
Artikel Jurnal
A deep learning-based IDS for IoT: model proposal and comparative study of dataset balancing techniques
Intrusion detection in Internet of Things (IoT) environments presents challenges due to the diversity of connected devices and their resource limitations. IoT networks generate complex, imbalanced traffic where benign activity predominates over attack instances. This imbalance hampers the…
-
Artikel Jurnal
A hybrid of machine learning based early termination and optimal scaling factor scheme for 5G LDPC codes
Machine Learning (ML) has proven to be an effective tool for optimizing several aspects of channel codes in communication systems. In this work, ML-based schemes have been adapted to the 5G New Radio (NR) Low-Density Parity Check (LDPC) codes to help them meet the stringent requirements of…
-
Artikel Jurnal
ML-based agglomerative hierarchical clustering and MMSE precoding for fair user scheduling in LEO MU-MIMO systems
This paper addresses the problem of user scheduling in Low Earth Orbit (LEO) High Throughput Satellite (HTS) multi-user (MU) Multiple-Input-Multiple-Output (MIMO) systems. We propose a Machine Learning (ML)-based hierarchical clustering approach i.e. AGNES (Agglomerative Nesting), where the…
-
Artikel Jurnal
Predictive dynamic multi-flow routing (PD-MFR) algorithm towards sixth generation (6G) software-defined networks
We develop a dynamic Quality of Service (QoS) routing algorithm based on network traffic prediction for Sixth Generation (6G) SDNs. First, we formulate a mixed integer optimization model that incorporates the key constraints for Ultra-Reliable Low Latency Communication (URLLC), enhanced Mobile…
-
Artikel Jurnal
BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
Sentiment analysis on social media is vital but challenged by language complexity and context dependency. Existing methods often fall short. This paper presents BERT-OntoSent, a hybrid approach synergizing BERT's contextual power with ontology-based structured knowledge. We provide a detailed…
-
Artikel Jurnal
Combining enhanced EfficientNet architectures and threshold-based pixels filtering for guava disease identification
The traditional methods of monitoring and detecting diseases in crops are being replaced by automated techniques that have the potential to revolutionize the innovative agriculture industry. Guava, a crop of paramount importance in Asian countries, is unfortunately susceptible to disease and fungal…
-
Artikel Jurnal
A comprehensive survey on customer churn analysis studies
This paper presents a comprehensive survey of customer churn analysis studies. It begins by examining the customer journey and touchpoints, emphasizing their influence on churn behaviour. The survey then reviews a range of machine learning algorithms used for churn prediction and explores the…
-
Artikel Jurnal
Stochastic channel modelling of cooperative STAR-RIS-assisted wireless channels
Insight into a wireless channel using a geometry-based three-dimensional (3D) channel model and its stochastic characterization is given in this paper. It is considered that the outdoor wireless channel is equipped with cooperative double (CODE), simultaneously transmitting and reflecting a…
-
Artikel Jurnal
A low-complexity eigenvalue decomposition based-GFDM transceiver for self-interference elimination in next-generation wireless systems
Generalized Frequency Division Multiplexing (GFDM) is a flexible multi-carrier scheme and has a potential to overcome some of the limitations of orthogonal frequency division multiplexing (OFDM) specifically for diverse use cases of beyond 5G (B5G)/ 6G systems. However, as a non-orthogonal…
-
Artikel Jurnal
A benchmarking framework and its validation on all evasion attacks on image classifiers listed in the adversarial robustness toolbox
What is an efficient attack against image classifiers? First, this paper defines a generic benchmarking framework to evaluate the effectiveness of evasion attacks against image classification models with relevant key performance indicators. The framework assesses attacks on 12 classifiers, for 4…
-
Artikel Jurnal
FAN-enhanced vision transformer and distributed bidirectional optical flow for heart failure detection from echocardiography videos
Heart failure (HF) is a major cardiovascular condition that requires early and accurate diagnosis to improve patient outcomes. Echocardiography is widely used for cardiac assessment, however, the analysis of echocardiography videos using deep learning models often suffers from high computational…
-
Artikel Jurnal
Scalable attribute encryption of semi-structured data in IoT based on improved recurrent neural networks
Attribute encryption technology presents increasing challenges to the scalability of IoT systems as the number of devices and data volume grow. This study designs a scalable attribute encryption method for IoT semi-structured data using an enhanced recurrent neural network (RNN). The ant colony…
-
Artikel Jurnal
Edge-AI enabled smishing and suspicious SMS detection: a cost-sensitive and lightweight deep learning architecture
Smishing attacks pose an asymmetric-risk problem, where missing a threat causes significantly greater damage than false alarms. While transformer-based models achieve robust classification performance, their computational cost hinders continuous inference on resource-constrained edge devices. This…
-
Artikel Jurnal
Enhancing handwritten mathematical expression recognition with convolutional block attention refinement module and multi-task learning
Handwritten Mathematical Expression Recognition (HMER) is challenging due to complex structural relationships, implicit symbols, and variations in handwriting styles. Therefore, this paper presents a novel approach combining multi-task learning (MTL) with advanced attention mechanisms, including…
-
Artikel Jurnal
Security enhancement of a correlated MISO multicast network with best transmit antenna selection
A secure correlated MISO multicast network is modelled with best transmit antenna selection (BTAS) over the Rayleigh fading channel under the influence of multiple wiretappers. It consists of a transmitter, Tx equipped with [Formula: see text] number of antennas, M single-antenna receivers and N…
-
Artikel Jurnal
Multi-objective dynamic community detection algorithm for complex networks improved by adaptive mutation strategy
Dynamic network communities evolve over time. Traditional methods suffer from declining partition quality and trajectory discontinuities, compromising the decision accuracy and real-time performance of critical applications such as social recommendation and anomaly detection. Addressing this issue…
-
Artikel Jurnal
IoT network performance enhancement with intelligent reflecting surfaces and relay
This article explores the integration of a relay station with two intelligent reflecting surfaces (IRSs) to enhance energy efficiency (EE) and system throughput (ST) in low-power wide-area networks (LPWAN) modelled for Internet of Things (IoT) applications. By leveraging IRS technology, the system…
-
Artikel Jurnal
Intelligent system to detect software defects in autonomous vehicles
Autonomous vehicles have become increasingly popular from the last few years because of their numerous benefits, such as minimum travel time, enhanced safety, and improved fuel economy. Many vehicle manufacturing companies and tech giants are working on this technology to make fully autonomous…
-
Artikel Jurnal
Digital painting image quality evaluation based on visual reasoning and multi-layer perception
With the popularization of digital painting, image quality evaluation has become a crucial topic. To improve the accuracy and efficiency of digital image quality evaluation, an innovative digital painting image evaluation model is proposed. The proposed method designs a parallel network structure…
-
Artikel Jurnal
Intelligent model for target identification from Urdu threatening tweets in low-resource language using deep learning and fine-tuning of language models
The rise of social media sites like Twitter, which is one of the most widely used venues for expressing thoughts, is a result of the development of technology. However, these opinions may sometimes contain threatening text that can disturb other users. As a result, it's critical to spot harmful…