Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457181
Seonghwa Choi, Sanghoon Lee
Photographs taken under improper exposures can appear either excessively dark or excessively bright. Most existing methods attempt to correct exposure in continuous representation, which often leads to low-quality results. In this paper, we introduce a novel exposure correction framework known as the Discretizing Exposure Network (DICE), which is designed to learn discrete exposure representations. To achieve this, our proposed framework is comprised of two key components: Exposure Discretization Module (EDM) and Color Condition Module (CCM). The EDM initially separates the feature into detail and exposure representations, subsequently learning discrete exposure features through vector quantization. Meanwhile, the CCM models the color distribution inherent in natural scenes, as improper exposure images lack color or detail information. Ex-tensive experiments demonstrate the effectiveness of the proposed method against state-of-the-art approaches both quantitatively and qualitatively.
{"title":"Exposure Correction Framework via Vector Quantization for Image Enhancement","authors":"Seonghwa Choi, Sanghoon Lee","doi":"10.1109/ICEIC61013.2024.10457181","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457181","url":null,"abstract":"Photographs taken under improper exposures can appear either excessively dark or excessively bright. Most existing methods attempt to correct exposure in continuous representation, which often leads to low-quality results. In this paper, we introduce a novel exposure correction framework known as the Discretizing Exposure Network (DICE), which is designed to learn discrete exposure representations. To achieve this, our proposed framework is comprised of two key components: Exposure Discretization Module (EDM) and Color Condition Module (CCM). The EDM initially separates the feature into detail and exposure representations, subsequently learning discrete exposure features through vector quantization. Meanwhile, the CCM models the color distribution inherent in natural scenes, as improper exposure images lack color or detail information. Ex-tensive experiments demonstrate the effectiveness of the proposed method against state-of-the-art approaches both quantitatively and qualitatively.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"149 1-2","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457203
Jae-Hyeon Yeo, Dong-Kyu Lee, Bong-Jik Kim, Gyu-Sik Kim
The shaded pole induction motor is simply a selfstarting single-phase induction motor whose one of the poles is shaded by the copper ring. Even though it has poor efficiency and the starting torque is very low, it is widely used, because of low cost and easy starting. The shaded pole induction motors used in cooling fans in refrigerators are generally well used, but in areas where the power supply is unstable, it sometimes leads to the faults such as motor coil disconnection. In this paper, the fan load tests and the locked rotor tests were performed in order to determine the operation status of the motor in overvoltage conditions. Through some experimental studies, it was found that the durability of the motor would be improved if the coil diameter became reduced and the coil lengthened even in overvoltage conditions.
{"title":"Study on Improving the Durability of Shaded Pole Induction Motors Used for Refrigerator Fans","authors":"Jae-Hyeon Yeo, Dong-Kyu Lee, Bong-Jik Kim, Gyu-Sik Kim","doi":"10.1109/ICEIC61013.2024.10457203","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457203","url":null,"abstract":"The shaded pole induction motor is simply a selfstarting single-phase induction motor whose one of the poles is shaded by the copper ring. Even though it has poor efficiency and the starting torque is very low, it is widely used, because of low cost and easy starting. The shaded pole induction motors used in cooling fans in refrigerators are generally well used, but in areas where the power supply is unstable, it sometimes leads to the faults such as motor coil disconnection. In this paper, the fan load tests and the locked rotor tests were performed in order to determine the operation status of the motor in overvoltage conditions. Through some experimental studies, it was found that the durability of the motor would be improved if the coil diameter became reduced and the coil lengthened even in overvoltage conditions.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"409 3","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457270
Sohyeon Jeon, Jeawook Jeon, Yubin Lee, Youngmin Kim
Approximate computing plays a key role in building energy-efficient high-performance digital systems, as much data and computation are required recently. This paper proposes a new approximate compressor that improves accuracy with faster computation performance. Through analyzing the error occurring cases in the truth table of the compressor, patterns were identified to extract a simplified logic. As a result of evaluating the performance through Vivado simulation, the proposed approximate compressor is operating 16% faster using 43% less power compared to the exact computation and the approximate multiplier using the compressor shows higher accuracy with reduced delay than other multiples.
{"title":"New Approximate 4:2 Compressor for High Accuracy and Small Area Using MUX Logic","authors":"Sohyeon Jeon, Jeawook Jeon, Yubin Lee, Youngmin Kim","doi":"10.1109/ICEIC61013.2024.10457270","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457270","url":null,"abstract":"Approximate computing plays a key role in building energy-efficient high-performance digital systems, as much data and computation are required recently. This paper proposes a new approximate compressor that improves accuracy with faster computation performance. Through analyzing the error occurring cases in the truth table of the compressor, patterns were identified to extract a simplified logic. As a result of evaluating the performance through Vivado simulation, the proposed approximate compressor is operating 16% faster using 43% less power compared to the exact computation and the approximate multiplier using the compressor shows higher accuracy with reduced delay than other multiples.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"408 26","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457218
Da-Min Shin, Do-Hyun Park, Hyoung-Nam Kim
In contemporary electronic warfare, the importance of accurate signal detection continues to grow. Recently, detection techniques using convolutional neural network (CNN) have been applied to effectively detect signals. In this paper, we analyze the CNN-based signal detection model using an explainable artificial intelligence (XAI) technique. By employing the XAI technique, we can determine the specific regions within the network's input data that exert a significant impact on prediction through the heatmap. Simulation analysis shows that high weights of heatmap are distributed to areas where signals exist in all layers. In particular, in the layers close to the input, the heatmap significantly reflects the features of the data. In the layers close to the output, the heatmap resolution decreases due to sampling. In addition, analysis results showed that the noise area is flattened due to the activation function.
{"title":"Analysis of Explainable Convolutional Neural Network for Weak Radar Signal Detection","authors":"Da-Min Shin, Do-Hyun Park, Hyoung-Nam Kim","doi":"10.1109/ICEIC61013.2024.10457218","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457218","url":null,"abstract":"In contemporary electronic warfare, the importance of accurate signal detection continues to grow. Recently, detection techniques using convolutional neural network (CNN) have been applied to effectively detect signals. In this paper, we analyze the CNN-based signal detection model using an explainable artificial intelligence (XAI) technique. By employing the XAI technique, we can determine the specific regions within the network's input data that exert a significant impact on prediction through the heatmap. Simulation analysis shows that high weights of heatmap are distributed to areas where signals exist in all layers. In particular, in the layers close to the input, the heatmap significantly reflects the features of the data. In the layers close to the output, the heatmap resolution decreases due to sampling. In addition, analysis results showed that the noise area is flattened due to the activation function.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"18 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the domain of computer vision, object detection serves as a fundamental perceptual task with critical implications. Traditional object detection frameworks are limited by their inability to recognize object classes not present in their training datasets, a significant drawback for practical applications where encountering novel objects is commonplace. To address the inherent lack of adaptability, more sophisticated paradigms such as zero-shot and open-vocabulary object detection have been introduced. Open-vocabulary object detection, in particular, often necessitates auxiliary image-text paired data to enhance model training. Our research proposes an innovative approach that refines the training process by mining potential unlabeled objects from negative sample pools. Leveraging a large-scale vision-language model, we harness the entropy of classification scores to selectively identify and annotate previously unlabeled samples, subsequently incorporating them into the training regimen. This novel methodology empowers our model to attain competitive performance benchmarks on the challenging MSCOCO dataset, matching state-of-the-art outcomes, while obviating the need for additional data or supplementary training procedures.
{"title":"Language-Guided Negative Sample Mining for Open-Vocabulary Object Detection","authors":"Yu-Wen Tseng, Hong-Han Shuai, Ching-Chun Huang, Yung-Hui Li, Wen-Huang Cheng","doi":"10.1109/ICEIC61013.2024.10457133","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457133","url":null,"abstract":"In the domain of computer vision, object detection serves as a fundamental perceptual task with critical implications. Traditional object detection frameworks are limited by their inability to recognize object classes not present in their training datasets, a significant drawback for practical applications where encountering novel objects is commonplace. To address the inherent lack of adaptability, more sophisticated paradigms such as zero-shot and open-vocabulary object detection have been introduced. Open-vocabulary object detection, in particular, often necessitates auxiliary image-text paired data to enhance model training. Our research proposes an innovative approach that refines the training process by mining potential unlabeled objects from negative sample pools. Leveraging a large-scale vision-language model, we harness the entropy of classification scores to selectively identify and annotate previously unlabeled samples, subsequently incorporating them into the training regimen. This novel methodology empowers our model to attain competitive performance benchmarks on the challenging MSCOCO dataset, matching state-of-the-art outcomes, while obviating the need for additional data or supplementary training procedures.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"233 2","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457283
B. Kang, Dahun Choi, Hyun Kim
As hardware devices have advanced recently, various artificial intelligence tasks including convolutional neural networks (CNNs) have achieved high accuracy. Especially in computer vision tasks, vision transformer (ViT) based models have achieved unprecedented progress, and CNN + ViT hybrid models have also been proposed that take advantage of both CNNs and ViTs. However, the numerous parameters of hybrid ViTs are unsuitable for resource-constrained mobile/edge environments. In addition, the nonlinear activation functions in hybrid ViTs (e.g., GeLU and Swish) require more resources and computational cost compared to integer operation functions (e.g., ReLU) when using dedicated hardware accelerators. To address these issues, we propose a technique to efficiently compress the prominent hybrid ViT model, MobileViT, by applying the mixed precision quantization and the Shift-Swish activation function. Compressing the MobileViT-s, MobileViT-xs, and MobileViT-xxs models with the proposed method on the ImageNet dataset resulted in minimal accuracy drops of 0.41%, 0.18%, and 0.86%, respectively, while achieving effective quantization and activation function approximation at the average 7.9-bit level.
随着近年来硬件设备的发展，包括卷积神经网络（CNN）在内的各种人工智能任务都取得了很高的精度。特别是在计算机视觉任务中，基于视觉变换器（ViT）的模型取得了前所未有的进展，同时还提出了利用 CNN 和 ViT 的优势的 CNN + ViT 混合模型。然而，混合 ViT 的参数繁多，不适合资源有限的移动/边缘环境。此外，与使用专用硬件加速器的整数运算函数（如 ReLU）相比，混合 ViT 中的非线性激活函数（如 GeLU 和 Swish）需要更多的资源和计算成本。为解决这些问题，我们提出了一种技术，通过应用混合精度量化和 Shift-Swish 激活函数，高效压缩著名的混合 ViT 模型 MobileViT。在 ImageNet 数据集上使用所提出的方法对 MobileViT-s、MobileViT-xs 和 MobileViT-xxs 模型进行压缩后，准确率分别下降了 0.41%、0.18% 和 0.86%，同时实现了平均 7.9 位级别的有效量化和激活函数近似。
{"title":"Mixed Precision Quantization with Hardware-Friendly Activation Functions for Hybrid ViT Models","authors":"B. Kang, Dahun Choi, Hyun Kim","doi":"10.1109/ICEIC61013.2024.10457283","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457283","url":null,"abstract":"As hardware devices have advanced recently, various artificial intelligence tasks including convolutional neural networks (CNNs) have achieved high accuracy. Especially in computer vision tasks, vision transformer (ViT) based models have achieved unprecedented progress, and CNN + ViT hybrid models have also been proposed that take advantage of both CNNs and ViTs. However, the numerous parameters of hybrid ViTs are unsuitable for resource-constrained mobile/edge environments. In addition, the nonlinear activation functions in hybrid ViTs (e.g., GeLU and Swish) require more resources and computational cost compared to integer operation functions (e.g., ReLU) when using dedicated hardware accelerators. To address these issues, we propose a technique to efficiently compress the prominent hybrid ViT model, MobileViT, by applying the mixed precision quantization and the Shift-Swish activation function. Compressing the MobileViT-s, MobileViT-xs, and MobileViT-xxs models with the proposed method on the ImageNet dataset resulted in minimal accuracy drops of 0.41%, 0.18%, and 0.86%, respectively, while achieving effective quantization and activation function approximation at the average 7.9-bit level.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"50 2","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457224
Shingo Yamaguchi
This paper proposes a new Mesa-based simulator for the Botnet Defense System (BDS). The BDS is a system that uses white-hat botnets to exterminate malicious botnets. Its effectiveness is expected to be affected by white-hat botnet characteristics such as primary and secondary infection rates, and lifespan. In conventional Petri net-based simulators, only some characteristics have been modeled to avoid modeling complexity. The proposed new simulator was developed using the Python-based modeling framework, Mesa, which allows for more faithful and efficient modeling of white-hat botnets using the Python ecosystem. The evaluation with the simulator showed quantitatively that the effectiveness of BDS depends on the characteristics of the white-hat botnet and the relationship between these characteristics.
{"title":"Mesa-Based Simulator of Botnet Defense System and Impact Evaluation of Botnet Infection Rates","authors":"Shingo Yamaguchi","doi":"10.1109/ICEIC61013.2024.10457224","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457224","url":null,"abstract":"This paper proposes a new Mesa-based simulator for the Botnet Defense System (BDS). The BDS is a system that uses white-hat botnets to exterminate malicious botnets. Its effectiveness is expected to be affected by white-hat botnet characteristics such as primary and secondary infection rates, and lifespan. In conventional Petri net-based simulators, only some characteristics have been modeled to avoid modeling complexity. The proposed new simulator was developed using the Python-based modeling framework, Mesa, which allows for more faithful and efficient modeling of white-hat botnets using the Python ecosystem. The evaluation with the simulator showed quantitatively that the effectiveness of BDS depends on the characteristics of the white-hat botnet and the relationship between these characteristics.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"8 2","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457153
Jin Young Choi, Dong-Goo Kang, Minhye Chang, Kye Young Jeong, Byung Cheol Song
This paper proposes a deep learning-based algorithm that converts near-infrared (NIR) images to long-wave infrared (LWIR) images to solve the problem of lack of LWIR datasets. Experimental results qualitatively show excellent translation performance of the proposed method. We hope that this study contributes to various computer vision tasks in the LWIR domain.
{"title":"NIR to LWIR Image Translation for Generating LWIR Image Datasets","authors":"Jin Young Choi, Dong-Goo Kang, Minhye Chang, Kye Young Jeong, Byung Cheol Song","doi":"10.1109/ICEIC61013.2024.10457153","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457153","url":null,"abstract":"This paper proposes a deep learning-based algorithm that converts near-infrared (NIR) images to long-wave infrared (LWIR) images to solve the problem of lack of LWIR datasets. Experimental results qualitatively show excellent translation performance of the proposed method. We hope that this study contributes to various computer vision tasks in the LWIR domain.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"389 2","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457142
Junil Kim, S. Kim, Seon Wook Kim
The memory bandwidth between a processor and memory limits the performance, especially in emerging data-intensive applications. To solve this problem, supporting in-memory processing has been actively studied. Most PIM platforms prepare all the input data before computation because of the significant overhead in the data preparation, which is much higher in multi-channel memory systems due to data duplication. In this paper, we developed a cost-effective DMA offloading methodology to support PIM computation in the multi-channel memory system. We minimized the data sharing overhead between channels and achieved a performance improvement of up to 1.79x compared to our baseline one-channel PIM architecture in the execution of DNN applications.
{"title":"Supporting Multi-Channels to DRAM-based PIM Execution for Boosting the Performance","authors":"Junil Kim, S. Kim, Seon Wook Kim","doi":"10.1109/ICEIC61013.2024.10457142","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457142","url":null,"abstract":"The memory bandwidth between a processor and memory limits the performance, especially in emerging data-intensive applications. To solve this problem, supporting in-memory processing has been actively studied. Most PIM platforms prepare all the input data before computation because of the significant overhead in the data preparation, which is much higher in multi-channel memory systems due to data duplication. In this paper, we developed a cost-effective DMA offloading methodology to support PIM computation in the multi-channel memory system. We minimized the data sharing overhead between channels and achieved a performance improvement of up to 1.79x compared to our baseline one-channel PIM architecture in the execution of DNN applications.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"208 4","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-28DOI: 10.1109/ICEIC61013.2024.10457120
Gi-Kryang Kim, Jaehyun Park, Seong-Ook Jung
In this paper, we proposed parasitic capacitance prediction methodology using Bayesian optimization to accelerate the iterative design process. The layout process while circuit design is inevitable since the effect of parasitic RC after layout increases as technology scaled down. However, the layout process consumes many time and human resources. To overcome this problem, we present Bayesian optimization based parasitic capacitance estimation methodology with parasitic capacitance modelling. Our proposed methodology can predict the parasitic capacitance of various inverter and NAND2 with less than 3.1% of error.
{"title":"Post-Layout Parasitic Capacitance Prediction Methodology Using Bayesian Optimization","authors":"Gi-Kryang Kim, Jaehyun Park, Seong-Ook Jung","doi":"10.1109/ICEIC61013.2024.10457120","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457120","url":null,"abstract":"In this paper, we proposed parasitic capacitance prediction methodology using Bayesian optimization to accelerate the iterative design process. The layout process while circuit design is inevitable since the effect of parasitic RC after layout increases as technology scaled down. However, the layout process consumes many time and human resources. To overcome this problem, we present Bayesian optimization based parasitic capacitance estimation methodology with parasitic capacitance modelling. Our proposed methodology can predict the parasitic capacitance of various inverter and NAND2 with less than 3.1% of error.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"230 5","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：