ETRI Journal最新文献_第6页

Automated deep-learning model optimization framework for microcontrollers 微控制器深度学习模型自动优化框架

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-06-09 DOI: 10.4218/etrij.2023-0522

Seungtae Hong, Gunju Park, Jeong-Si Kim

{"title":"Automated deep-learning model optimization framework for microcontrollers","authors":"Seungtae Hong, Gunju Park, Jeong-Si Kim","doi":"10.4218/etrij.2023-0522","DOIUrl":"10.4218/etrij.2023-0522","url":null,"abstract":"This paper introduces a framework for optimizing deep-learning models on microcontrollers (MCUs) that is crucial in today's expanding embedded device market. We focus on model optimization techniques, particularly pruning and quantization, to enhance the performance of neural networks within the limited resources of MCUs. Our approach combines automatic iterative optimization and code generation, simplifying MCU model deployment without requiring extensive hardware knowledge. Based on experiments with architectures, such as ResNet-8 and MobileNet v2, our framework substantially reduces the model size and enhances inference speed that are crucial for MCU efficiency. Compared with TensorFlow Lite for MCUs, our optimizations for MobileNet v2 reduce static random-access memory use by 51%–57% and flash use by 17%–62%, while increasing inference speed by approximately 1.55 times. These advancements highlight the impact of our method on performance and memory efficiency, demonstrating its value in embedded artificial intelligence and broad applicability in MCU-based neural network optimization.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 2","pages":"179-192"},"PeriodicalIF":1.3,"publicationDate":"2024-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0522","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141367640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient reduction of peak-to-average power ratio in multiple-input multiple-output orthogonal frequency-division multiplexing system by shuffling cluster sequences 通过洗牌簇序列有效降低多输入多输出正交频分复用系统中的峰均功率比

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-06-07 DOI: 10.4218/etrij.2023-0362

Si Sar Mi, Tanairat Mata, Pornpawit Boonsrimuang, Pisit Boonsrimuang

{"title":"Efficient reduction of peak-to-average power ratio in multiple-input multiple-output orthogonal frequency-division multiplexing system by shuffling cluster sequences","authors":"Si Sar Mi, Tanairat Mata, Pornpawit Boonsrimuang, Pisit Boonsrimuang","doi":"10.4218/etrij.2023-0362","DOIUrl":"10.4218/etrij.2023-0362","url":null,"abstract":"We propose a shuffling cluster sequence technique without separate side information (SI) for multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems. In the proposed technique, the active subcarriers over two consecutive OFDM symbols are divided into \u0000<math>\u0000 <mn>2</mn>\u0000 <mi>V</mi></math> clusters, and each cluster (packet frame) includes a header for ID#cluster and payload for \u0000<math>\u0000 <mi>D</mi>\u0000 <mi>a</mi>\u0000 <mi>t</mi>\u0000 <mi>a</mi>\u0000 <mi>#</mi>\u0000 <mi>c</mi>\u0000 <mi>l</mi>\u0000 <mi>u</mi>\u0000 <mi>s</mi>\u0000 <mi>t</mi>\u0000 <mi>e</mi>\u0000 <mi>r</mi></math>. The \u0000<math>\u0000 <mn>2</mn>\u0000 <mi>V</mi></math> clusters are shuffled to reduce the peak-to-average power ratio (PAPR) of the time-domain OFDM signal, which includes the information data and SI signals, with a low computational complexity. At the receiver, the information data can be correctly reconstructed by ID#cluster in the header of each cluster, achieving a smaller bit error rate than the conventional MIMO-OFDM system without PAPR reduction. Moreover, our technique is comparable with the conventional partial transmit sequence technique without the impact of a separate SI signal even when increasing the number of transmitter antennas in a nonlinear multipath fading channel.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"998-1006"},"PeriodicalIF":1.3,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0362","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141373517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Series-arc-fault diagnosis using feature fusion-based deep learning model 利用基于特征融合的深度学习模型进行串联电弧故障诊断

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-06-06 DOI: 10.4218/etrij.2023-0457

Won-Kyu Choi, Se-Han Kim, Ji-Hoon Bae

{"title":"Series-arc-fault diagnosis using feature fusion-based deep learning model","authors":"Won-Kyu Choi, Se-Han Kim, Ji-Hoon Bae","doi":"10.4218/etrij.2023-0457","DOIUrl":"10.4218/etrij.2023-0457","url":null,"abstract":"This paper describes the detection of series arc faults, which constitute the major cause of electrical fires, in a power distribution system. Because the characteristics of series arc faults change considerably depending on the load type, their accurate detection and analysis are difficult. We propose a series-arc-fault detector that uses a transfer learning (TL)-based feature fusion model. The model is trained stagewise for various features in the time and frequency domains using a one-dimensional convolutional neural network combined with a long short-term memory model that uses an attention mechanism to accurately detect arc-fault features. To enhance the reliability of the proposed model, we implement an arc-fault generator compliant with the UL1699 standard and acquire high-quality data that suitably reflect the real environment. Experimental results show that the proposed model achieves an accuracy of 99.99% in classifying series arc faults for five different loads. Hence, a performance improvement of approximately 1.7% in classification accuracy is reached compared with a feature fusion model that does not incorporate TL-based model transfer and the attention mechanism.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"1061-1074"},"PeriodicalIF":1.3,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large-area stretchable oxide thin-film transistor arrays with sandwiched molybdenum in serpentine structure 蛇形结构夹钼大面积可拉伸氧化物薄膜晶体管阵列

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-06-01 DOI: 10.4218/etrij.2023-0371

Jeho Na, Himchan Oh, Sujung Kim, Bock Soon Na, Ji Hun Choi, Ji-Young Oh, Chunwon Byun, Chan Woo Park

{"title":"Large-area stretchable oxide thin-film transistor arrays with sandwiched molybdenum in serpentine structure","authors":"Jeho Na, Himchan Oh, Sujung Kim, Bock Soon Na, Ji Hun Choi, Ji-Young Oh, Chunwon Byun, Chan Woo Park","doi":"10.4218/etrij.2023-0371","DOIUrl":"10.4218/etrij.2023-0371","url":null,"abstract":"Stretchable electronics are gaining attention with the development of skin-compatible health monitoring sensors and robotics applications. However, existing stretchable electronics show a tradeoff between reliability and stretchability when constructing transistor arrays. We aim to construct highly stretchable thin-film transistor (TFT) arrays with high reliability for large sensor backplanes. The fabricated structure comprises oxide TFTs and serpentine-shaped molybdenum interconnects that are sandwiched between top and bottom polyimide layers, achieving robustness under repeated tensile strain. Different materials for polyimide etch masks (i.e., aluminum, silicon nitride, and indium tin oxide) are tested. Within an 83.7 mm × 61 mm area, TFT arrays with a resolution of 25 pixels per inch can be stretched up to 30% without considerable performance degradation. As our TFTs are fabricated using common materials from display manufacturing, our development and findings may substantially benefit stretchable electronic industries where high reliability is required for large-area panels.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 1","pages":"134-143"},"PeriodicalIF":1.3,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0371","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141275011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Moment analysis on channel eigenvalue for DAS-to-DAS system das - das系统信道特征值的矩分析

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-28 DOI: 10.4218/etrij.2023-0367

Donghyuk Gwak, Youngil Jeon, Jemin Lee, Jee-Hyeon Na

引用次数: 0

An end-to-end joint learning scheme of image compression and quality enhancement with improved entropy minimization 基于改进熵最小化的图像压缩和质量增强的端到端联合学习方案

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-27 DOI: 10.4218/etrij.2023-0275

Jooyoung Lee, Seunghyun Cho, Munchurl Kim

{"title":"An end-to-end joint learning scheme of image compression and quality enhancement with improved entropy minimization","authors":"Jooyoung Lee, Seunghyun Cho, Munchurl Kim","doi":"10.4218/etrij.2023-0275","DOIUrl":"https://doi.org/10.4218/etrij.2023-0275","url":null,"abstract":"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.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"935-949"},"PeriodicalIF":1.3,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0275","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142862260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vehicle counting in drone images: An adaptive method with spatial attention and multiscale receptive fields 无人机图像中的车辆计数：一种具有空间注意和多尺度接受域的自适应方法

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-27 DOI: 10.4218/etrij.2023-0426

Yu Liu, Hang Shen, Tianjing Wang, Guangwei Bai

{"title":"Vehicle counting in drone images: An adaptive method with spatial attention and multiscale receptive fields","authors":"Yu Liu, Hang Shen, Tianjing Wang, Guangwei Bai","doi":"10.4218/etrij.2023-0426","DOIUrl":"https://doi.org/10.4218/etrij.2023-0426","url":null,"abstract":"We propose an altitude-adaptive vehicle counting method with an attention mechanism and multiscale receptive fields that optimizes the measurement accuracy and inference latency of unmanned aerial vehicle (UAV) images. An attention mechanism is used to aggregate horizontal and vertical feature weights to enhance spatial information and suppress background noise. The UAV flight altitude and shooting depression angle are considered for scale division and image segmentation to avoid acquiring distance measurements. Based on the dilation rate, we introduce a receptive field selection strategy for the trained model to exhibit scale generalization without redundant calculations. A distribution-aware block loss is optimized via \u0000<math>\u0000 <mi>k</mi></math> roots to balance the loss of sparse and crowded regions by dividing the density map. Experiments on three authoritative datasets demonstrate that compared with CSRNet, the proposed method improves the mean absolute error by 29.4%–54.0% and mean squared error by 28.6%–41.2% while reducing the inference latency. The proposed method exhibits higher counting accuracy than lightweight models including MCNN and MobileCount.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"47 1","pages":"7-19"},"PeriodicalIF":1.3,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0426","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143497410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved VoWiFi cell capacity using A-MPDU for frame aggregation in sixth-generation WLAN standard 在第六代无线局域网标准中使用 A-MPDU 进行帧聚合，提高 VoWiFi 小区容量

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-20 DOI: 10.4218/etrij.2023-0333

Ayes Chinmay, Hemanta Kumar Pati

{"title":"Improved VoWiFi cell capacity using A-MPDU for frame aggregation in sixth-generation WLAN standard","authors":"Ayes Chinmay, Hemanta Kumar Pati","doi":"10.4218/etrij.2023-0333","DOIUrl":"10.4218/etrij.2023-0333","url":null,"abstract":"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.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"965-976"},"PeriodicalIF":1.3,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0333","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141119983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Low-complexity patch projection method for efficient and lightweight point-cloud compression 用于高效、轻量级点云压缩的低复杂度补丁投影法

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-15 DOI: 10.4218/etrij.2023-0242

Sungryeul Rhyu, Junsik Kim, Gwang Hoon Park, Kyuheon Kim

{"title":"Low-complexity patch projection method for efficient and lightweight point-cloud compression","authors":"Sungryeul Rhyu, Junsik Kim, Gwang Hoon Park, Kyuheon Kim","doi":"10.4218/etrij.2023-0242","DOIUrl":"10.4218/etrij.2023-0242","url":null,"abstract":"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.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 4","pages":"683-696"},"PeriodicalIF":1.3,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0242","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140974659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design of high-efficiency rectenna for microwave power wireless transmission systems 设计用于微波功率无线传输系统的高效整流器天线

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-05-14 DOI: 10.4218/etrij.2023-0290

Jia-Xiang Chen, Zhong-Hua Ma, Chen Li, Meng-Nan Wang, Hai-Tao Xing, Wei-Qian Liang, Yan-Feng Jiang

{"title":"Design of high-efficiency rectenna for microwave power wireless transmission systems","authors":"Jia-Xiang Chen, Zhong-Hua Ma, Chen Li, Meng-Nan Wang, Hai-Tao Xing, Wei-Qian Liang, Yan-Feng Jiang","doi":"10.4218/etrij.2023-0290","DOIUrl":"10.4218/etrij.2023-0290","url":null,"abstract":"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.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"1103-1112"},"PeriodicalIF":1.3,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0290","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140980107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0