ETRI Journal最新文献

We introduce a machine learning-based web application to help travel agents plan a package tour schedule. K-nearest neighbor (KNN) classification predicts the optimal tourists' dwelling time based on a variety of information to automatically generate a convenient tour schedule. A database collected in collaboration with an established travel agency is fed into the KNN algorithm implemented in the Python language, and the predicted dwelling times are sent to the web application via a RESTful application programming interface provided by the Flask framework. The web application displays a page in which the agents can configure the initial data and predict the optimal dwelling time and automatically update the tour schedule. After conducting a performance evaluation by simulating a scenario on a computer running the Windows operating system, the average response time was 1.762 s, and the prediction consistency was 100% over 100 iterations.

Aerial base stations (ABSs) seem promising to enhance the coverage and capacity of fifth-generation and upcoming networks. With the flexible mobility of ABSs, they can be positioned in air to maximize the number of users served with a guaranteed quality of service (QoS). However, ABSs may be overloaded or underutilized given inefficient placement, and user association has not been well addressed. Hence, we propose a three-dimensional ABS placement scheme with a delay-QoS-driven user association to balance loading among ABSs. First, a load balancing utility function is designed based on proportional fairness. Then, an optimization problem for joint ABS placement and user association is formulated to maximize the utility function subject to statistical delay QoS requirements and ABS collision avoidance constraints. To solve this problem, we introduce an efficient modified gray wolf optimizer for ABS placement with a greedy user association strategy. Simulation results demonstrate that the proposed scheme outperforms baselines in terms of load balancing and delay QoS provisioning.

We propose a bandwidth prediction approach based on deep learning. The approach is intended to accurately predict the bandwidth of various types of mobile networks. We first use a machine learning technique, namely, the gradient boosting algorithm, to recognize the connected mobile network. Second, we apply a handover detection algorithm based on network recognition to account for vertical handover that causes the bandwidth variance. Third, as the communication performance offered by 3G, 4G, and 5G networks varies, we suggest a bidirectional long short-term memory model with time distribution for bandwidth prediction per network. To increase the prediction accuracy, pretraining and fine-tuning are applied for each type of network. We use a dataset collected at University College Cork for network recognition, handover detection, and bandwidth prediction. The performance evaluation indicates that the handover detection algorithm achieves 88.5% accuracy, and the bandwidth prediction model achieves a high accuracy, with a root-mean-square error of only 2.12%.

https://doi.org/10.4218/etrij.2021-0446

ETRI Journal, Volume 45, Issue 2, April 2023, pp. 318–328.

Misun Yu¹ | Yongin Kwon¹ | Jemin Lee¹ | Jeman Park¹ | Junmo Park² | Taeho Kim¹

¹Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea

²Samsung Electronics, Suwon, Republic of Korea

The authors regret that the original authorship list did not include the affiliation of author Junmo Park.

The authors would like to apologize for any inconvenience caused.

We propose a method to suppress the speckle noise and blur effects of the light field extracted from a hologram using a deep-learning technique. The light field can be extracted by bandpass filtering in the hologram's frequency domain. The extracted light field has reduced spatial resolution owing to the limited passband size of the bandpass filter and the blurring that occurs when the object is far from the hologram plane and also contains speckle noise caused by the random phase distribution of the three-dimensional object surface. These limitations degrade the reconstruction quality of the hologram resynthesized using the extracted light field. In the proposed method, a deep-learning model based on a generative adversarial network is designed to suppress speckle noise and blurring, resulting in improved quality of the light field extracted from the hologram. The model is trained using pairs of original two-dimensional images and their corresponding light-field data extracted from the complex field generated by the images. Validation of the proposed method is performed using light-field data extracted from holograms of objects with single and multiple depths and mesh-based computer-generated holograms.

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

The detection of all the symbols transmitted simultaneously in multiuser systems using limited wireless resources is challenging. Traditional model-based methods show high performance with perfect channel state information (CSI); however, severe performance degradation will occur if perfect CSI cannot be acquired. In contrast, data-driven methods perform slightly worse than model-based methods in terms of symbol error ratio performance in perfect CSI states; however, they are also able to overcome extreme performance degradation in imperfect CSI states. This study proposes a novel deep learning-based method by improving a state-of-the-art data-driven technique called deep soft interference cancellation (DSIC). The enhanced DSIC (EDSIC) method detects multiuser symbols in a fully sequential manner and uses an efficient neural network structure to ensure high performance. Additionally, error-propagation mitigation techniques are used to ensure robustness against channel uncertainty. The EDSIC guarantees a performance that is very close to the optimal performance of the existing model-based methods in perfect CSI environments and the best performance in imperfect CSI environments.

A dual-band bio-implantable compact antenna with a meander-line structure is presented. The proposed meander-line antenna resonates at the industrial, scientific, and medical (2.4 GHz) and wireless medical telemetry (1.4 GHz) bands. The meander-line structure is selected as a radiating patch given its versatile and effective design. With a dimension of only $�10��\mathrm{mm}�\times �10��\mathrm{mm}�\times �0.635��\mathrm{mm}$, the designed antenna is compact. Considering a skin phantom, the proposed antenna was designed, optimized, and simulated. The Rogers RT/duroid 6010 substrate material with high dielectric constant was used to fabricate the meander-line dual-band implantable antenna, which was validated experimentally. The superstrate was made of the same material. Experiments were conducted on skin-mimicking gel. The designed meander-line antenna has a high peak gain of −21 dBi at 2.4 GHz, and its maximum specific absorption rate is compliant with IEEE safety standards.

Authenticated multiple key agreement (AMKA) protocols provide participants with multiple session keys after one round of authentication. Many schemes use Diffie–Hellman or authenticated key agreement schemes that rely on hard integer factorizations that are vulnerable to quantum algorithms. Lattice cryptography provides quantum resistance to authenticated key agreement protocols, but the certificate always incurs excessive public key infrastructure management overhead. Thus, a lightweight lattice-based secure system is needed that removes this overhead. To answer this need, we provide a two-party lattice- and identity-based AMKA scheme based on bilateral short integer or computational bilateral inhomogeneous small integer solutions, and we provide a security proof based on the random oracle model. Compared with existing AMKA protocols, our new protocol has higher efficiency and stronger security.

A new method is proposed to generate a 32-tupling frequency millimeter wave (MMW) with eight Mach–Zehnder modulators (MZMs) connected in parallel. Theoretical analyses and simulation experiments are conducted. The optical sideband suppression ratio (OSSR) of the obtained ±16th order optical sidebands are 61.54 dB and 61.42 dB, and the radio frequency spurious suppression ratios (RFSSRs) of the generated 32-tupling frequency MMW are 55.52 dB and 55.27 dB based on the theoretical analysis and simulation experiments, respectively; these outcomes verified the feasibility of the new method. The main parameters used to affect the stability of the generated signal are the modulation index and extinction ratio of MZM. Their effects on the OSSR and RFSSR of the generated signals are investigated when they deviate from their designed values. Compared with the other proposed methods for the generation of 32-tupling frequency MMW by MZM, our method has the best spectral purity and stability, and it is expected to have important MMW over fiber applications.