ETRI Journal最新文献_第4页

Effects of parasitic gate capacitance and gate resistance on radiofrequency performance in LG = 0.15 μm GaN high-electron-mobility transistors for X-band applications 用于 X 波段应用的 LG = 0.15 μm 氮化镓高电子迁移率晶体管中寄生栅极电容和栅极电阻对射频性能的影响

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-04-05 DOI: 10.4218/etrij.2023-0250

Sung-Jae Chang, Hyeon-Seok Jeong, Hyun-Wook Jung, Su-Min Choi, Il-Gyu Choi, Youn-Sub Noh, Seong-Il Kim, Sang-Heung Lee, Ho-Kyun Ahn, Dong Min Kang, Dae-Hyun Kim, Jong-Won Lim

{"title":"Effects of parasitic gate capacitance and gate resistance on radiofrequency performance in LG = 0.15 μm GaN high-electron-mobility transistors for X-band applications","authors":"Sung-Jae Chang, Hyeon-Seok Jeong, Hyun-Wook Jung, Su-Min Choi, Il-Gyu Choi, Youn-Sub Noh, Seong-Il Kim, Sang-Heung Lee, Ho-Kyun Ahn, Dong Min Kang, Dae-Hyun Kim, Jong-Won Lim","doi":"10.4218/etrij.2023-0250","DOIUrl":"10.4218/etrij.2023-0250","url":null,"abstract":"The effects of the parasitic gate capacitance and gate resistance (Rg) on the radiofrequency (RF) performance are investigated in LG = 0.15 μm GaN high-electron-mobility transistors with T-gate head size ranging from 0.83 to 1.08 μm. When the device characteristics are compared, the difference in DC characteristics is negligible. The RF performance in terms of the current-gain cut-off frequency (fT) and maximum oscillation frequency (fmax) substantially depend on the T-gate head size. For clarifying the T-gate head size dependence, small-signal modeling is conducted to extract the parasitic gate capacitance and Rg. When the T-gate head size is reduced from 1.08 to 0.83 μm, Rg increases by 82%, while fT and fmax improve by 27% and 26%, respectively, because the parasitic gate–source and gate–drain capacitances reduce by 19% and 43%, respectively. Therefore, minimizing the parasitic gate capacitance is more effective that reducing Rg in our transistor design and fabrication, leading to improved RF performance when reducing the T-gate head size.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"1090-1102"},"PeriodicalIF":1.3,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0250","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140596732","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

Small dataset augmentation with radial basis function approximation for causal discovery using constraint-based method 使用基于约束的方法，用径向基函数近似法增加小数据集以发现因果关系

IF 1.4 4区计算机科学

ETRI Journal Pub Date : 2024-04-02 DOI: 10.4218/etrij.2023-0397

Chan Young Jung, Yun Jang

{"title":"Small dataset augmentation with radial basis function approximation for causal discovery using constraint-based method","authors":"Chan Young Jung, Yun Jang","doi":"10.4218/etrij.2023-0397","DOIUrl":"https://doi.org/10.4218/etrij.2023-0397","url":null,"abstract":"Causal analysis involves analysis and discovery. We consider causal discovery, which implies learning and discovering causal structures from available data, owing to the significance of interpreting causal relationships in various fields. Research on causal discovery has been primarily focused on constraint- and score-based interpretable methods rather than on methods based on complex deep learning models. However, identifying causal relationships in real-world datasets remains challenging. Numerous studies have been conducted using small datasets with established ground truths. Moreover, constraint-based methods are based on conditional independence tests. However, such tests have a lower statistical power when applied to small datasets. To solve the small sample size problem, we propose a model that generates a continuous function from available samples using radial basis function approximation. We address the problem by extracting data from the generated continuous function and evaluate the proposed method on both real and synthetic datasets generated by structural equation modeling. The proposed method outperforms constraint-based methods using only small datasets.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"18 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140596642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance analysis of transmit antenna selection and maximum-ratio combining in overlay networks powered by harvested energy 利用采集能量供电的重叠网络中发射天线选择和最大比率组合的性能分析

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-22 DOI: 10.4218/etrij.2023-0389

Khuong Ho-Van

引用次数: 0

Anomaly-based Alzheimer's disease detection using entropy-based probability Positron Emission Tomography images 利用基于熵概率的正电子发射断层扫描图像进行基于异常的阿尔茨海默病检测

IF 1.4 4区计算机科学

ETRI Journal Pub Date : 2024-03-22 DOI: 10.4218/etrij.2023-0123

Husnu Baris Baydargil, Jangsik Park, Ibrahim Furkan Ince

{"title":"Anomaly-based Alzheimer's disease detection using entropy-based probability Positron Emission Tomography images","authors":"Husnu Baris Baydargil, Jangsik Park, Ibrahim Furkan Ince","doi":"10.4218/etrij.2023-0123","DOIUrl":"10.4218/etrij.2023-0123","url":null,"abstract":"Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 3","pages":"513-525"},"PeriodicalIF":1.4,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0123","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140197528","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

Enhancing spectral efficiency with low complexity filtered-orthogonal frequency division multiplexing in visible light communication system 在可见光通信系统中利用低复杂度滤波正交频分复用技术提高频谱效率

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-22 DOI: 10.4218/etrij.2023-0300

Hayder S. R. Hujijo, Muhammad Ilyas

{"title":"Enhancing spectral efficiency with low complexity filtered-orthogonal frequency division multiplexing in visible light communication system","authors":"Hayder S. R. Hujijo, Muhammad Ilyas","doi":"10.4218/etrij.2023-0300","DOIUrl":"10.4218/etrij.2023-0300","url":null,"abstract":"The filtered-orthogonal frequency division multiplexing (F-OFDM) scheme has gained attention as a promising solution in the field of visible light communication (VLC) systems. One crucial aspect in VLC is the conversion of the complex F-OFDM signal into a real signal that corresponds with direct detection and intensity modulation. Traditionally, achieving a real F-OFDM signal has involved imposing Hermitian symmetry (HS) on the samples of the Inverse Fast Fourier transform (IFFT), which requires 2N-point IFFT and obtains an N-point FFT, thus adding complexity. In this study, a novel approach is presented and implemented, aiming to enhance spectral efficiency and reduce system complexity by generating a real F-OFDM signal without relying on HS. This approach is then compared with HS-free (HSF)-OFDM, direct current biased optical OFDM, and asymmetrically clipped optical OFDM. The suggested method offers a remarkable improvement of ~50% in the required IFFT/FFT volume. Consequently, this method reduces hardware complexity and power usage compared with the traditional F-OFDM method. Moreover, regarding error rates, the proposed method demonstrates better spectral efficiency than HSF-OFDM.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"1007-1019"},"PeriodicalIF":1.3,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0300","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140197524","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

Multiobjective, trust-aware, artificial hummingbird algorithm-based secure clustering and routing with mobile sink for wireless sensor networks 基于多目标、信任感知、人工蜂鸟算法的无线传感器网络安全聚类和路由选择（带移动汇

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-20 DOI: 10.4218/etrij.2023-0330

Anil Kumar Jemla Naik, Manjunatha Parameswarappa, Mohan Naik Ramachandra

{"title":"Multiobjective, trust-aware, artificial hummingbird algorithm-based secure clustering and routing with mobile sink for wireless sensor networks","authors":"Anil Kumar Jemla Naik, Manjunatha Parameswarappa, Mohan Naik Ramachandra","doi":"10.4218/etrij.2023-0330","DOIUrl":"10.4218/etrij.2023-0330","url":null,"abstract":"Wireless sensor networks (WSNs) are composed of numerous nodes distributed in geographical regions. Security and energy efficiency are challenging tasks due to an open environment and a restricted battery source. The multiobjective trust-aware artificial hummingbird algorithm (M-TAAHA) is proposed to achieve secure and reliable transmission over a WSN with a mobile sink (MS). The M-TAAHA selects secure cluster head (SCH) nodes based on trust, energy, interspace between sensors, interspace between SCH and MS, and the CH balancing factor. A secure route is found by M-TAAHA with trust, energy, and interspace between SCH and MS. The M-TAAHA avoids the malicious nodes to improve data delivery and avoid unwanted energy consumption. The M-TAAHA is analyzed using energy consumption, alive nodes, life expectancy, delay, data packets received in MS, throughput, packet delivery ratio, and packet loss ratio. Existing techniques (LEACH-TM, EATMR, FAL, Taylor-spotted hyena optimization [Taylor-SHO], TBEBR, and TEDG) are used for comparison with the M-TAAHA. Findings show that the energy consumption of the proposed M-TAAHA for 1000 rounds is 0.56 J (1.78 × smaller than that of the Taylor-SHO).","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 6","pages":"950-964"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0330","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140197530","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

Amazon product recommendation system based on a modified convolutional neural network 基于修正卷积神经网络的亚马逊产品推荐系统

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-19 DOI: 10.4218/etrij.2023-0162

Yarasu Madhavi Latha, B. Srinivasa Rao

{"title":"Amazon product recommendation system based on a modified convolutional neural network","authors":"Yarasu Madhavi Latha, B. Srinivasa Rao","doi":"10.4218/etrij.2023-0162","DOIUrl":"10.4218/etrij.2023-0162","url":null,"abstract":"In e-commerce platforms, sentiment analysis on an enormous number of user reviews efficiently enhances user satisfaction. In this article, an automated product recommendation system is developed based on machine and deep-learning models. In the initial step, the text data are acquired from the Amazon Product Reviews dataset, which includes 60 000 customer reviews with 14 806 neutral reviews, 19 567 negative reviews, and 25 627 positive reviews. Further, the text data denoising is carried out using techniques such as stop word removal, stemming, segregation, lemmatization, and tokenization. Removing stop-words (duplicate and inconsistent text) and other denoising techniques improves the classification performance and decreases the training time of the model. Next, vectorization is accomplished utilizing the term frequency–inverse document frequency technique, which converts denoised text to numerical vectors for faster code execution. The obtained feature vectors are given to the modified convolutional neural network model for sentiment analysis on e-commerce platforms. The empirical result shows that the proposed model obtained a mean accuracy of 97.40% on the APR dataset.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 4","pages":"633-647"},"PeriodicalIF":1.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0162","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140197526","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

MixFace: Improving face verification with a focus on fine-grained conditions MixFace：改进人脸验证，关注细粒度条件

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-16 DOI: 10.4218/etrij.2023-0167

Junuk Jung, Sungbin Son, Joochan Park, Yongjun Park, Seonhoon Lee, Heung-Seon Oh

引用次数: 0

Violent crowd flow detection from surveillance cameras using deep transfer learning–gated recurrent unit 利用深度迁移学习门控递归单元从监控摄像头检测暴力人流

IF 1.3 4区计算机科学

ETRI Journal Pub Date : 2024-03-14 DOI: 10.4218/etrij.2023-0222

Elly Matul Imah, Riskyana Dewi Intan Puspitasari

{"title":"Violent crowd flow detection from surveillance cameras using deep transfer learning–gated recurrent unit","authors":"Elly Matul Imah, Riskyana Dewi Intan Puspitasari","doi":"10.4218/etrij.2023-0222","DOIUrl":"10.4218/etrij.2023-0222","url":null,"abstract":"Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 4","pages":"671-682"},"PeriodicalIF":1.3,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0222","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140147864","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

CR-M-SpanBERT: Multiple embedding-based DNN coreference resolution using self-attention SpanBERT CR-M-SpanBERT：利用自关注 SpanBERT 进行基于多重嵌入的 DNN 核心参照解析

IF 1.4 4区计算机科学

ETRI Journal Pub Date : 2024-02-28 DOI: 10.4218/etrij.2023-0308

Joon-young Jung

{"title":"CR-M-SpanBERT: Multiple embedding-based DNN coreference resolution using self-attention SpanBERT","authors":"Joon-young Jung","doi":"10.4218/etrij.2023-0308","DOIUrl":"https://doi.org/10.4218/etrij.2023-0308","url":null,"abstract":"This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"46 1","pages":"35-47"},"PeriodicalIF":1.4,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2023-0308","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139987396","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