ETRI Journal最新文献

Recently, learned image compression methods based on entropy minimization have achieved superior results compared with conventional image codecs such as BPG and JPEG2000. However, they leverage single Gaussian models, which have a limited ability to approximate various irregular distributions of transformed latent representations, resulting in suboptimal coding efficiency. Furthermore, existing methods focus on constructing effective entropy models, rather than utilizing modern architectural techniques. In this paper, we propose a novel joint learning scheme called JointIQ-Net that incorporates image compression and quality enhancement technologies with improved entropy minimization based on a newly adopted Gaussian mixture model. We also exploit global context to estimate the distributions of latent representations precisely. The results of extensive experiments demonstrate that JointIQ-Net achieves remarkable performance improvements in terms of coding efficiency compared with existing learned image compression methods and conventional codecs. To the best of our knowledge, ours is the first learned image compression method that outperforms VVC intra-coding in terms of both PSNR and MS-SSIM.

The rapid progress in wireless communication technology and proliferation of multimedia applications, including voice over WiFi (VoWiFi), demand exploration of innovative approaches to enhance the network performance and quality of service. We propose a technique for enhancing the cell capacity of wireless local area network (WLAN) access point that provides VoWiFi service in the sixth-generation WLAN standard. The proposed technique uses the aggregate media access control protocol data unit (A-MPDU) for frame aggregation with constant bit rate (CBR) traffic in the WiFi 6 standard (i.e., IEEE 802.11ax). On the other hand, the retransmission of voice packets substantially deteriorates the VoWiFi cell capacity. We compare the results obtained from the use of WiFi 6 with currently existing WLAN standards, such as IEEE 802.11b/g/n/ac. This comparison focuses on distributed coordination function interframe spacing (DIFS) and arbitration interframe spacing (AIFS) using CBR traffic. Using our technique, we can increase the VoWiFi cell capacity for CBR traffic by 24.25% and 25.20% when using DIFS and AIFS, respectively, while considering the A-MPDU frame aggregation technique.

The point cloud provides viewers with intuitive geometric understanding but requires a huge amount of data. Moving Picture Experts Group (MPEG) has developed video-based point-cloud compression in the range of 300–700. As the compression rate increases, the complexity increases to the extent that it takes 101.36 s to compress one frame in an experimental environment using a personal computer. To realize real-time point-cloud compression processing, the direct patch projection (DPP) method proposed herein simplifies the complex patch segmentation process by classifying and projecting points according to their geometric positions. The DPP method decreases the complexity of the patch segmentation from 25.75 s to 0.10 s per frame, and the entire process becomes 8.76 times faster than the conventional one. Consequently, this proposed DPP method yields similar peak signal-to-noise ratio (PSNR) outcomes to those of the conventional method at reduced times (4.7–5.5 times) at the cost of bitrate overhead. The objective and subjective results show that the proposed DPP method can be considered when low-complexity requirements are required in lightweight device environments.

Radio power transmission is studied herein. A rectenna with high-efficiency microwave power transmission is proposed. Improvement on the traditional Yagi antenna structure is implemented by using a rectenna. In this design, the antenna is fed by a coplanar waveguide, and the impedance bandwidth is widened by adding a set of radiation dipoles. A set of parasitic directors is used to enhance the directionality of the antenna. A rectifier circuit based on a power-recovery network is designed using an open branch-line network with harmonic rejection characteristics as a low-pass filter. The rectifier network topology is adopted with a diode in parallel connection to increase the output voltage of the circuit. The reflected power generated by the impedance mismatch can be recycled by the power-recovery network. Thus, the rectifying efficiency can be improved. Finally, experimental data show that the radiofrequency–direct current power conversion efficiency of the rectenna can be as high as 77.5% at the operating frequency 2.45 GHz and the input power 12 dBm. The proposed rectenna can be potentially used for the power supply of various wireless sensor nodes with high efficiency.

In wireless sensor network (WSN) monitoring systems, redundant data from sluggish environmental changes and overlapping sensing ranges can increase the volume of data sent by nodes, degrade the efficiency of information collection, and lead to the death of sensor nodes. To reduce the energy consumption of sensor nodes and prolong the life of WSNs, this study proposes a dual layer intracluster data fusion scheme based on ring buffer. To reduce redundant data and temporary anomalous data while guaranteeing the temporal coherence of data, the source nodes employ a binarized similarity function and sliding quartile detection based on the ring buffer. Based on the improved support degree function of weighted Pearson distance, the cluster head node performs a weighted fusion on the data received from the source nodes. Experimental results reveal that the scheme proposed in this study has clear advantages in three aspects: the number of remaining nodes, residual energy, and the number of packets transmitted. The data fusion of the proposed scheme is confined to the data fusion of the same attribute environment parameters.

Author verification is challenging because of the diversity in writing styles. We propose an enhanced handwriting verification method that combines handcrafted and automatically extracted features. The method uses a genetic algorithm to reduce the dimensionality of the feature set. We consider offline Bangla handwriting content and evaluate the proposed method using handcrafted features with a simple logistic regression, radial basis function network, and sequential minimal optimization as well as automatically extracted features using a convolutional neural network. The handcrafted features outperform the automatically extracted ones, achieving an average verification accuracy of 94.54% for 100 writers. The handcrafted features include Radon transform, histogram of oriented gradients, local phase quantization, and local binary patterns from interwriter and intrawriter content. The genetic algorithm reduces the feature dimensionality and selects salient features using a support vector machine. The top five experimental results are obtained from the optimal feature set selected using a consensus strategy. Comparisons with other methods and features confirm the satisfactory results.

Self-supervised learning is a method that learns the data representation through unlabeled data. It is efficient because it learns from large-scale unlabeled data and through continuous research, performance comparable to supervised learning has been reached. Contrastive learning, a type of self-supervised learning algorithm, utilizes data similarity to perform instance-level learning within an embedding space. However, it suffers from the problem of false-negatives, which are the misclassification of data class during training the data representation. They result in loss of information and deteriorate the performance of the model. This study employed cosine similarity and temperature simultaneously to identify false-negatives and mitigate their impact to improve the performance of the contrastive learning model. The proposed method exhibited a performance improvement of up to 2.7% compared with the existing algorithm on the CIFAR-100 dataset. Improved performance on other datasets such as CIFAR-10 and ImageNet was also observed.

Music identification is widely regarded as a solved problem for music searching in quiet environments, but its performance tends to degrade in TV broadcast audio owing to the presence of dialogue or sound effects. In addition, constructing an accurate dataset for measuring the performance of background music monitoring in TV broadcast audio is challenging. We propose a framework for monitoring background music by automatic identification and introduce a background music cue sheet. The framework comprises three main components: music identification, music–speech separation, and music detection. In addition, we introduce the Cue-K-Drama dataset, which includes reference songs, audio tracks from 60 episodes of five Korean TV drama series, and corresponding cue sheets that provide the start and end timestamps of background music. Experimental results on the constructed and existing datasets demonstrate that the proposed framework, which incorporates music identification with music–speech separation and music detection, effectively enhances TV broadcast audio monitoring.