ETRI Journal最新文献

This paper presents a radio-frequency (RF) signal modeling technology that builds a fingerprinting database for indoor localization quickly and accurately. Fingerprinting-based localization technology uses location-specific signal characteristics as a database; therefore, it is less sensitive to multipath problems. The proposed approach predicts signal propagation paths and calculates attenuation based on an indoor map, reducing infrastructure installation and data collection time. Because the indoor map lacks accurate information about all structures, the modeling results contain errors when compared to measurements. To address this, measurements from a partial area improve modeling accuracy by accounting for received signal strength changes caused by indoor structures. In experiments with seven beacons, the proposed database construction method achieves an average error of 5.16 dBm and a localization error of 1.61 m, comparable to the 1.14-m error in measurement-based databases, while reducing database construction time by 41.06%. These results demonstrate the effectiveness of the proposed technology in rapidly and accurately building databases for indoor localization.

Transfer learning in large language models adapts pretrained models to new tasks by leveraging their existing linguistic knowledge for domain-specific applications. A fine-tuned XLNet, base-cased model is proposed for classifying Amazon product reviews. Two datasets are used to evaluate the approach: Amazon earphone and Amazon personal computer reviews. Model performance is benchmarked against transformer models including ELECTRA, BERT, RoBERTa, ALBERT, and DistilBERT. In addition, hybrid models such as CNN-LSTM and CNN-BiLSTM are considered in conjunction with single models such as CNN, BiGRU, and BiLSTM. The XLNet model achieved accuracies of 95.2% for Amazon earphone reviews and 95% for Amazon personal computer reviews. The accuracy of ELECTRA is slightly lower than that of XLNet. The exact match ratio values for XLNet on the AE and AP datasets are 0.95 and 0.94, respectively. The proposed model achieved exceptional accuracy and F1 scores, outperforming all other models. The XLNet model was fine-tuned with different learning rates, optimizers (such as Nadam and Adam), and batch sizes (4, 8, and 16). This analysis underscores the effectiveness of the XLNet approach for sentiment analysis tasks.

The Internet of Things (IoT) is an intelligent network paradigm created by interconnected device networks. Although the importance of IoT systems has increased in various applications, the increasing number of connected devices has made security even more critical. This study presents the ROUT-4-2023 dataset, which represents a step toward the security of IoT networks. This dataset simulates potential attacks on RPL-based IoT networks and provides a new platform for researchers in this field. Using artificial intelligence and machine-learning techniques, a performance evaluation was performed on four different artificial neural network models (convolutional neural network, deep neural network, multilayer perceptron structure, and routing attack detection-fed forward neural network [RaD-FFNN]). The results show that the RaD-FFNN model has high accuracy, precision, and retrieval rates, indicating that it can be used as an effective tool for the security of IoT networks. This study contributes to the protection of IoT networks from potential attacks by presenting ROUT-4-2023 and RaD-FFNN models, which will lead to further research on IoT security.

Unmanned aerial vehicles (UAVs) are highly mobile and easily deployable devices that have become an important component of wireless communication countermeasures. Covert communication, the main method used to ensure wireless communication security, has been extensively studied in recent years. However, existing research primarily uses UAVs as auxiliary tools for covert communications, to improve communication performance, ignoring situations in which the detector utilizes UAVs for interference suppression. In this study, we propose a UAV-assisted jamming detection covert communication game model. Specifically, the UAV actively transmits noise to Alice's transmission channels to disrupt covert transmission when Willie detects a covert communication transmission. Furthermore, we analyze the adversarial process between the detector and Alice under UAV-assisted jamming based on game theory, theoretically verify the conditions for the existence of a Nash equilibrium, and formulate optimal strategies for both sides.

We address the challenge of jointly representing uplink (UL) and downlink (DL) channels for a massive multiple-input multiple-output satellite system. We employ dictionary learning for sparse representation with the goal of minimizing the number of UL/DL pilots and improving accuracy. Additionally, by considering the angular reciprocity, a common dictionary support can be established to enhance the performance. However, what type of dictionary model is suited for UL/DL channel representation remains an unknown field. Previous research has utilized predefined dictionaries, such as DFT or ODFT bases, which are unable to adapt to dynamic scenarios. Training dictionaries have demonstrated the potential to significantly improve accuracy; however, a lack of analysis regarding dictionary constraints exists. To address this issue, we analyze the conditional constraints of the dictionary for joint UL/DL channel representation, aiming to quantify the maximum boundary while proposing a constrained dictionary learning algorithm with singular value decomposition to obtain an effective representation and conduct an adaptability analysis in dynamic satellite communication scenarios.

Several peak-to-average power ratio (PAPR) reduction methods have been used in orthogonal frequency division multiplexing (OFDM) applications. Among the available methods, partial transmit sequence (PTS) is an efficient PAPR reduction method but can be computationally expensive while determining optimal phase factors (OPFs). Therefore, an optimization algorithm, namely, the improved salp swarm optimization algorithm (ISSA), is incorporated with the PTS to reduce the PAPR of the OFDM signals with limited computational cost. The ISSA includes a dynamic weight element and Lévy flight process to improve the global exploration ability of the optimization algorithm and to control the global and local search ability of the population with a better convergence rate. Three evaluation measures, namely, the complementary cumulative distribution function (CCDF), bit error rate (BER), and symbol error rate (SER), demonstrate the efficacy of the PTS-ISSA model, which achieves a lower PAPR of 3.47 dB and is superior to other optimization algorithms using the PTS method.

The prolonged sitting inherent in modern work and study environments poses significant health risks, necessitating effective monitoring solutions. Traditional human activity recognition systems often fall short in these contexts owing to their reliance on structured data, which may fail to capture the complexity of human movements or accommodate the often incomplete or unstructured nature of healthcare data. To address this gap, our study introduces a novel application of graph neural networks (GNNs) for detecting prolonged sitting periods using point cloud data from smartphone sensors. Unlike conventional methods, our GNN model excels at processing the unordered, three-dimensional structure of sensor data, enabling more accurate classification of sedentary activities. The effectiveness of our approach is demonstrated by its superior ability to identify sitting, standing, and walking activities—critical for assessing health risks associated with prolonged sitting. By providing real-time activity recognition, our model offers a promising tool for healthcare professionals to mitigate the adverse effects of sedentary behavior.

Existing spatial feature recognition and layout methods primarily identify spatial components manually, which is time-consuming and inefficient, and the constraint relationship between objects in space can be difficult to observe. Consequently, this study introduces an advanced spatial feature recognition and layout methodology employing enhanced CenterNet and LSTM (Long Short-Term Memory) frameworks, which is bifurcated into two major components—first, HCenterNet-based feature recognition enhances feature extraction through an attention mechanism and feature fusion technology, refining the identification of small targets within complex background areas; second, a GA-BiLSTM (Genetic Algorithm - Bidirectional LSTM)-based spatial layout model uses a bidirectional LSTM network optimized with a genetic algorithm (GA), aimed at fine-tuning the network parameters to yield more accurate spatial layouts. Experiments verified that compared with the CenterNet model, the recognition performance of the proposed HCenterNet-DIoU model improved by 7.44%. Moreover, the GA-BiLSTM model improved the overall layout accuracy by 10.08% compared with the LSTM model. Time cost analysis also confirmed that the proposed model could meet the real-time requirements.

The massive multiple-input multiple-output (mMIMO) approach is promising for the Internet of Things (IoT) owing to its massive connectivity and high data rate. We introduce a wireless-powered cell-free mMIMO system, in which ground IoT devices transmit pilot and uplink information by harvesting downlink power from multiantenna access points. Considering the spatial correlation, we derive closed-form expressions for the average harvested power with a nonlinear energy-harvesting model per IoT device and achievable data rate according to the random matrix theory. The analytical expressions show that spatial correlation has a negative effect on the data rate owing to the increasing interference power. In contrast, the average received power improves with increasing spatial correlation. Simulation results demonstrate that the derived analytical expressions are consistent with results from the Monte Carlo method.

Detecting defective multi-layer ceramic capacitors (MLCCs) during the inspection stage is a crucial production task to effectively manage production yield and maintain quality. However, this task presents two challenges: the necessity of pixel-level segmentation in high-resolution images and unexplored defect patterns. To address these challenges, this paper introduces an MLCC defect-detection framework based on deep learning with an MLCC dataset we constructed and a comprehensive analysis of MLCC images. Our framework employs an object-detection model to identify dielectric regions in input MLCC images, followed by a semantic segmentation model to create dielectric masks for calculating the margin ratio. This approach follows the traditional inspection process but can be performed without specialized personnel. Furthermore, we generated pseudo-defect images using generative adversarial networks to obtain sufficient training data. Experiments demonstrate the effectiveness of our framework, which achieved a defect-detection accuracy of 93.1%, as revealed by an in-depth error analysis.