2022 IEEE International Conference on Consumer Electronics (ICCE)最新文献_第8页

A Weakly-Supervised Anomaly Detection Method via Adversarial Training for Medical Images 基于对抗训练的医学图像弱监督异常检测方法

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730129

He Li, Y. Iwamoto, Xianhua Han, Lanfen Lin, Ruofeng Tong, Hongjie Hu, Akira Furukawa, S. Kanasaki, Yen-Wei Chen

{"title":"A Weakly-Supervised Anomaly Detection Method via Adversarial Training for Medical Images","authors":"He Li, Y. Iwamoto, Xianhua Han, Lanfen Lin, Ruofeng Tong, Hongjie Hu, Akira Furukawa, S. Kanasaki, Yen-Wei Chen","doi":"10.1109/ICCE53296.2022.9730129","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730129","url":null,"abstract":"Convolutional neural networks have been widely used for anomaly detection and one of their most common methods is autoencoder. The autoencoder is expected to produce lower reconstruction error for the normal data than the abnormal ones, and the reconstruction error is typically set as a measurement index for distinguishing anomalies. In practice, however, this notion is not always compatible. The autoencoder's reconstruction ability is sometimes so good that it can reconstruct anomalies with low error, resulting in the loss of anomaly detection. To address this limitation, we present a novel weakly-supervised learning method based on the generative adversarial network. The network learns the feature distribution of both normal and abnormal samples. The use of an autoencoder in the generator network allows the model to map the input image to a lower dimension vector and then remap it back to its reconstructions. The additional encoder discriminator network maps the real and generated images to their latent representations and determines whether the generated image is true or false. As a result, a higher error-index indicates that the sample is an anomaly. Experimentation on medical images from a publicly available liver dataset demonstrates the model's superiority over previous state-of-the-art approaches.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123084302","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}

引用次数: 1

Emerging Paradigm of IoT Enabled Smart Villages 物联网智能村庄的新兴范例

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730482

Rohani Rohan, Debajyoti Pal, B. Watanapa, Suree Funilkul

引用次数: 3

A Novel Balanced Routing Protocol for Lifetime Improvement in WSNs 一种改善无线传感器网络生存期的新型均衡路由协议

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730409

Chih-Min Yu, Meng-Lin Ku

引用次数: 2

GAN-Based Semantic-Aware Translation for Day-to-Night Images 基于gan的日夜图像语义感知翻译

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730532

Daiki Shiotsuka, Jinho Lee, Yuki Endo, E. Javanmardi, Kunio Takahashi, Kenta Nakao, S. Kamijo

引用次数: 3

FPGA Implementations of VVC Fractional Interpolation Using High-Level Synthesis 基于高级合成的VVC分数插值的FPGA实现

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730363

Ilker Hamzaoglu, Hossein Mahdavi, Elif Taskin

引用次数: 0

Using Maximum Deviation Method and Linguistic TOPSIS to Evaluate Competitive Ability of Line Marketing Platform Supplier 基于最大偏差法和语言TOPSIS的线上营销平台供应商竞争力评价

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730348

Chung-Chih Lee, H. Tseng, Chun-Chu Liu, Huei-Jeng Chou

引用次数: 1

A Material Selection Method for High Frequency Connectors 一种高频连接器材料选择方法

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730466

Harish Manjunath Navale, S. Agili, A. Morales, A. Attaluri

{"title":"A Material Selection Method for High Frequency Connectors","authors":"Harish Manjunath Navale, S. Agili, A. Morales, A. Attaluri","doi":"10.1109/ICCE53296.2022.9730466","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730466","url":null,"abstract":"Manufacturers of a high-frequency connectors consider their electrical performance based on the type of material used, in particular by its relative dielectric constant and loss tangent. In addition, manufacturers have to consider mechanical and molding properties as well as the cost of the material. This paper focuses on developing an optimal method for selecting a high frequency connector material based on electrical, mechanical, and molding properties. This method relies on modified Ashby plots and current industry standards to obtain an optimal region where possible polymers are placed and thereby a practicing signal integrity engineer can choose an appropriate material for a given application. The modified Ashby plot involve the use of sigmoid functions to modify the electrical properties axis as well normalization of the mechanical properties axis, to generate an optimal region. To verify the above method, a material, satisfying the Ashby plot requirements, is chosen. This material is further electrically characterized using the coaxial airline technique up to a frequency range of 18 GHz. The broadband characterization process involves acquiring the scattering parameters from a vector network analyzer and calculating the electrical properties such as dielectric constant and loss tangent. This method allows the practicing signal integrity engineer to efficiently choose polymers for a variety of connectors used in high frequency consumer electronics application such as USB, HDMI, and Thunderbolt.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124487933","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}

引用次数: 0

Multipath TCP Control Scheme for Low Latency and High Speed XR Real-Time M&S Devices 低延迟、高速XR实时M&S设备的多路径TCP控制方案

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730276

Jaewook Jung, Minsu Choi, Yunyeong Goh, Jong‐Moon Chung

{"title":"Multipath TCP Control Scheme for Low Latency and High Speed XR Real-Time M&S Devices","authors":"Jaewook Jung, Minsu Choi, Yunyeong Goh, Jong‐Moon Chung","doi":"10.1109/ICCE53296.2022.9730276","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730276","url":null,"abstract":"Advancements in metaverse modeling & simulation (M&S) are becoming possible due to realization of extended reality (XR) systems, which combines mixed reality (MR) with advanced human-computer interaction (HCI) devices. To use these technologies appropriately, high performing system requirements, such as, high data rate and low latency, are required. For this, fifth-generation (5G) New-Radio (NR) technology that achieves high data rate, low latency, and massive connectivity can be applied. Although the mmWave technology adopted in 5G can satisfy high data rates by using high frequencies, it has a disadvantage of easily being vulnerable to blockage. To alleviate this problem, multi-path Transmission Control Protocol (MPTCP) which uses multiple Transmission Control Protocol (TCP) subflows can be used. However, MPTCP has a problem with its reordering delay that occurs due to mixed up packet arrival orders. To overcome this issue, in this paper, extensions to the linked increases algorithm (LIA) scheme are made to form the minimized reordering delay LIA (MRLIA) scheme, which is a new MPTCP congestion control scheme that increases the data rate by minimizing the reordering delay while using network resources fairly. Through simulation, it is confirmed that the proposed method can provide an improved performance compared to existing methods in terms of goodput and latency.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123397330","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}

引用次数: 1

Deep Learning Approach for Smart Home Appliances Monitoring and Classification 智能家电监测与分类的深度学习方法

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730441

Jayroop Ramesh, A. Al-Ali, Ahmad Al Nabulsi, Ahmed E. Osman, M. Shaaban

{"title":"Deep Learning Approach for Smart Home Appliances Monitoring and Classification","authors":"Jayroop Ramesh, A. Al-Ali, Ahmad Al Nabulsi, Ahmed E. Osman, M. Shaaban","doi":"10.1109/ICCE53296.2022.9730441","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730441","url":null,"abstract":"With the global rise in the adoption of smart grids and smart homes, it is imperative to find approaches to efficiently monitor and manage load profiles across households. We consider aggregated load profiles during mutual operation, where the rationale is to provide a relatively robust and adaptable deep learning method that can perform appliance classification without constraints on the consumer behavior. We propose an enhanced real-time single-sensor home appliance classification and monitoring system leveraging convolutional neural networks and transfer learning. The real-time information obtained from smart meters is input into a pre-trained learning model which classifies multiple concurrently active home appliances. The convolutional neural network architectures of VGG16, ResNet50, and the InceptionV3 are trained individually by the transfer-learning paradigm with the image features of V-I trajectories, spectrograms, continuous wavelet transforms, and Fryze decomposed active components respectively. This approach effectively realizes end-to-end learning, and mitigates the need to disaggregate load before the identification process. Experimental results suggest that the utilization of transfer learning improves the multi-label classification performance of aggregate load. This model is made accessible to consumers through a mobile application, which is used to interface with smart meter data and provide subsequent appliance usage insights. This is one of of the first works to re-purpose pre-trained deep learning networks used for image processing high frequency concurrent load classification in the context of an Advanced Metering Infrastructure (AMI).","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121909748","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}

引用次数: 3

A PDR Method Using Smartglasses Reducing Accumulated Errors by Detecting User's Stop Motions 一种使用智能眼镜的PDR方法，通过检测用户的停止运动来减少累积误差

2022 IEEE International Conference on Consumer Electronics (ICCE) Pub Date : 2022-01-07 DOI: 10.1109/ICCE53296.2022.9730285

D. Sato, N. Togawa

{"title":"A PDR Method Using Smartglasses Reducing Accumulated Errors by Detecting User's Stop Motions","authors":"D. Sato, N. Togawa","doi":"10.1109/ICCE53296.2022.9730285","DOIUrl":"https://doi.org/10.1109/ICCE53296.2022.9730285","url":null,"abstract":"Pedestrian navigation using a smartglass is more intuitive and easier to use because various information is dis-played directly in the field of view, and there is no need to look down to see the screen. The global positioning system (GPS) is widely used for pedestrian navigation, but its positioning accuracy is significantly degraded in indoors, undergrounds, and the area surrounded by high-rise buildings. Instead, in indoor areas, pedestrian dead reckoning (PDR) can estimate user's current positions using his/her device's sensors. PDR requires no external infrastructure and can be implemented at low cost, but since it estimates relative positions based on its initial position, errors accumulate as the walking distance increases. Reducing the accumulated errors is important in realizing PDR. In this paper, we propose a PDR method to reduce the accumulated errors for pedestrian navigation using smartglasses. When a user wearing a smartglass stops at some point, its downward acceleration value approaches the value of gravity acceleration. By effectively utilizing this property, the proposed method reduces the accumulated errors. Experimental evaluations show the effectiveness of the proposed method.","PeriodicalId":350644,"journal":{"name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123837203","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}

引用次数: 0