Pub Date : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10226718
Ardha Ardea Prisilla, Yori Pusparani, Wen-Thong Chang, B. Liau, Yih-Kuen Jan, Peter Ardhianto, Chih-Yang Lin, Chi-Wen Lung
The detection of lumbar disc herniation (LDH) through magnetic resonance imaging (MRI) poses a challenge due to the various shapes, sizes, angles, and regions associated with bulges, protrusions, extrusions, and sequestrations. One potential solution is using deep learning methods to identify lumbar abnormalities in MRI images automatically. The YOU ONLY LOOK ONCE (YOLO) model series has gained popularity for training deep learning algorithms for real-time biomedical image detection. This study aims to assess the performance of the latest YOLOv7 in detecting LDH across different regions of the lumbar intervertebral disc. The analysis revealed that YOLOv7 exhibits a poor performance and low detection rate of LDH across the L1-L2, L2-L3, L3-L4, L4-L5, and L5-S1 regions.
通过磁共振成像(MRI)检测腰椎间盘突出症(LDH)提出了一个挑战，因为与凸起、突出、挤压和隔离相关的各种形状、大小、角度和区域。一个潜在的解决方案是使用深度学习方法自动识别MRI图像中的腰椎异常。YOU ONLY LOOK ONCE (YOLO)模型系列在训练用于实时生物医学图像检测的深度学习算法方面获得了广泛的应用。本研究旨在评估最新的YOLOv7在检测腰椎间盘不同区域LDH方面的性能。分析表明，YOLOv7在L1-L2、L2-L3、L3-L4、L4-L5和L5-S1区域的LDH检测性能较差，检出率较低。
{"title":"Automatic Detection of Lumbar Disc Herniation Using YOLOv7","authors":"Ardha Ardea Prisilla, Yori Pusparani, Wen-Thong Chang, B. Liau, Yih-Kuen Jan, Peter Ardhianto, Chih-Yang Lin, Chi-Wen Lung","doi":"10.1109/ICCE-Taiwan58799.2023.10226718","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226718","url":null,"abstract":"The detection of lumbar disc herniation (LDH) through magnetic resonance imaging (MRI) poses a challenge due to the various shapes, sizes, angles, and regions associated with bulges, protrusions, extrusions, and sequestrations. One potential solution is using deep learning methods to identify lumbar abnormalities in MRI images automatically. The YOU ONLY LOOK ONCE (YOLO) model series has gained popularity for training deep learning algorithms for real-time biomedical image detection. This study aims to assess the performance of the latest YOLOv7 in detecting LDH across different regions of the lumbar intervertebral disc. The analysis revealed that YOLOv7 exhibits a poor performance and low detection rate of LDH across the L1-L2, L2-L3, L3-L4, L4-L5, and L5-S1 regions.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075244","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10227033
Hari Chandhana Varma M, Advaidh Swaminathan, Shu-Yen Lin
Deep Neural Networks (DNN) find its prominent presence in the AI world. The properties of its algorithms are very well exploited to make its computations power faster and more efficient. One such adaptation requires reduction in the bit width of the operations for DNN. This paper deals about a DNN architecture design with reconfigurable bitwidth accelerator without affecting the accuracy. This proposed architecture is a modified version of Bit Fusion architecture dealing with dynamic bit-level decomposition for accelerating complex DNN computations. The design make computations with less power consumption, and it is more suitable for the trade-offs among the latency, power, and temperature. The micro architecture design of the modified BitFusion using RTL simulations is carried out to evaluate the functionality.
{"title":"Multi-Mode AI Accelerator Architecture for Thermal-Aware 3D Stacked Deep Neural Network Design","authors":"Hari Chandhana Varma M, Advaidh Swaminathan, Shu-Yen Lin","doi":"10.1109/ICCE-Taiwan58799.2023.10227033","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10227033","url":null,"abstract":"Deep Neural Networks (DNN) find its prominent presence in the AI world. The properties of its algorithms are very well exploited to make its computations power faster and more efficient. One such adaptation requires reduction in the bit width of the operations for DNN. This paper deals about a DNN architecture design with reconfigurable bitwidth accelerator without affecting the accuracy. This proposed architecture is a modified version of Bit Fusion architecture dealing with dynamic bit-level decomposition for accelerating complex DNN computations. The design make computations with less power consumption, and it is more suitable for the trade-offs among the latency, power, and temperature. The micro architecture design of the modified BitFusion using RTL simulations is carried out to evaluate the functionality.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133804143","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10226811
S. Chiang, C. Tsuei
This study utilized an optimized YOLOv3 training model to improve the accuracy of image recognition technology to over 90% through the data results obtained from the grayscale image and personnel recognition technology of the surveillance system at the experimental field - Baoshan Library. In addition, the system's control screen, combined with the verification field's system architecture, achieved the function of detecting and lighting fixtures within 1.4 to 1.6 seconds when personnel appeared within the detection system range, and the system could turn off the lighting fixtures within 1.4 to 1.9 seconds when personnel disappeared from the detection system.
{"title":"Intelligent Lighting Control under AI Architecture","authors":"S. Chiang, C. Tsuei","doi":"10.1109/ICCE-Taiwan58799.2023.10226811","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226811","url":null,"abstract":"This study utilized an optimized YOLOv3 training model to improve the accuracy of image recognition technology to over 90% through the data results obtained from the grayscale image and personnel recognition technology of the surveillance system at the experimental field - Baoshan Library. In addition, the system's control screen, combined with the verification field's system architecture, achieved the function of detecting and lighting fixtures within 1.4 to 1.6 seconds when personnel appeared within the detection system range, and the system could turn off the lighting fixtures within 1.4 to 1.9 seconds when personnel disappeared from the detection system.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"739 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124398267","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10226707
Toshiro Nunome, Daiki Deguchi
This paper evaluates the QoE of video and audio transmission over a full-duplex wireless LAN with interference traffic through a computer simulation and a subjective experiment. We employ a simulation environment with a pair of audiovisual transmission and reception terminals and a pair of interference traffic transmission and reception ones. We investigate the effect of the transmission rate of interference traffic and communication distance in a wireless channel on the output quality of the video and audio stream at the reception terminal. We perform a subjective experiment with the output timing of video and audio obtained by the simulation.
{"title":"QoE Assessment of Audiovisual Streaming over a Full-Duplex Wireless LAN with Interference Traffic","authors":"Toshiro Nunome, Daiki Deguchi","doi":"10.1109/ICCE-Taiwan58799.2023.10226707","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226707","url":null,"abstract":"This paper evaluates the QoE of video and audio transmission over a full-duplex wireless LAN with interference traffic through a computer simulation and a subjective experiment. We employ a simulation environment with a pair of audiovisual transmission and reception terminals and a pair of interference traffic transmission and reception ones. We investigate the effect of the transmission rate of interference traffic and communication distance in a wireless channel on the output quality of the video and audio stream at the reception terminal. We perform a subjective experiment with the output timing of video and audio obtained by the simulation.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125593709","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10227056
Masaki Yoshida, Ren Togo, Takahiro Ogawa, M. Haseyama
We present a novel binaural audio generation method with data augmentation from 360° videos. Visually informed binaural audio generation requires ground truth pairs of video and binaural audio. However, collecting diverse ground truth requires a lot of effort, and low data diversity reduces the generalization performance of the model. Our method introduces the data generation from 360° videos to solve the low diversity of ground truth. Experimental results show that our method improves the generalization performance of the binaural audio generation model and that 360° video is effective in generating video and pseudo-binaural audio pairs.
{"title":"Binaural Audio Generation with Data Augmentation from 360° Videos","authors":"Masaki Yoshida, Ren Togo, Takahiro Ogawa, M. Haseyama","doi":"10.1109/ICCE-Taiwan58799.2023.10227056","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10227056","url":null,"abstract":"We present a novel binaural audio generation method with data augmentation from 360° videos. Visually informed binaural audio generation requires ground truth pairs of video and binaural audio. However, collecting diverse ground truth requires a lot of effort, and low data diversity reduces the generalization performance of the model. Our method introduces the data generation from 360° videos to solve the low diversity of ground truth. Experimental results show that our method improves the generalization performance of the binaural audio generation model and that 360° video is effective in generating video and pseudo-binaural audio pairs.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124319492","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10226765
Zhe-Xuan Su, Zeng Wei-chang, Pan Guo-Siang, Sun Chi-Chia
The modern idea of gunplay has its origins in games and TV shows, and survival games have emerged as a new form of competitive sport. To assist users in survival games, a system has been developed to help them gather enemy intelligence and gain an advantage for their team during gameplay. The system is designed to detect the enemy's position and transmit the information to the user, enabling them to respond quickly to the intelligence and significantly reduce the risk of being ambushed from behind.YOLOv4, a powerful object detection model, has found wide application in various industries, such as manufacturing and facial recognition. It is used to detect product defects and ensure the quality of products, and for comparing facial features to facilitate tasks such as face recognition and criminal tracking. In the pandemic, YOLOv4 has been employed for mask detection and social distancing monitoring in manufacturing facilities. Additionally, it has been customized for traffic management in the "Smart City Traffic Flow Solution" developed by Academia Sinica and Yilong. The modified YOLOv4 system uses real-time vehicle detection at intersections to regulate traffic flow and enforce speed limits.
{"title":"Survival Game Assisted Tactical Helmets","authors":"Zhe-Xuan Su, Zeng Wei-chang, Pan Guo-Siang, Sun Chi-Chia","doi":"10.1109/ICCE-Taiwan58799.2023.10226765","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226765","url":null,"abstract":"The modern idea of gunplay has its origins in games and TV shows, and survival games have emerged as a new form of competitive sport. To assist users in survival games, a system has been developed to help them gather enemy intelligence and gain an advantage for their team during gameplay. The system is designed to detect the enemy's position and transmit the information to the user, enabling them to respond quickly to the intelligence and significantly reduce the risk of being ambushed from behind.YOLOv4, a powerful object detection model, has found wide application in various industries, such as manufacturing and facial recognition. It is used to detect product defects and ensure the quality of products, and for comparing facial features to facilitate tasks such as face recognition and criminal tracking. In the pandemic, YOLOv4 has been employed for mask detection and social distancing monitoring in manufacturing facilities. Additionally, it has been customized for traffic management in the \"Smart City Traffic Flow Solution\" developed by Academia Sinica and Yilong. The modified YOLOv4 system uses real-time vehicle detection at intersections to regulate traffic flow and enforce speed limits.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134241350","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}
Obtaining high-resolution depth map from radar and lidar for training depth estimation network is a common approach in recent years, although the expensive price and high computational complexity cause it hard to be apply in real-world applications. In this research, we propose a novel concept that only requires low resolution depth map for training, but able to reach similar performance comparing to high-resolution depth map-based approaches. Refers to the experimental results, which evaluated on KITTI dataset, our proposed concept decreases 7% and 2% on the mAP of car and pedestrian comparing to the original approach in CaDDN, although it achieves similar performance on visualization result.
{"title":"3D object detection with low resolution depth map","authors":"Wei-Ting Huang, Xiu-Zhi Chen, Yen-Lin Chen, Chieh-Sheng Huang","doi":"10.1109/ICCE-Taiwan58799.2023.10226909","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226909","url":null,"abstract":"Obtaining high-resolution depth map from radar and lidar for training depth estimation network is a common approach in recent years, although the expensive price and high computational complexity cause it hard to be apply in real-world applications. In this research, we propose a novel concept that only requires low resolution depth map for training, but able to reach similar performance comparing to high-resolution depth map-based approaches. Refers to the experimental results, which evaluated on KITTI dataset, our proposed concept decreases 7% and 2% on the mAP of car and pedestrian comparing to the original approach in CaDDN, although it achieves similar performance on visualization result.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134515878","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 : 2023-07-17DOI: 10.1109/ICCE-Taiwan58799.2023.10227011
Ting-Hsu Lai, Tsung-Jung Liu, Kuan-Hsien Liu
Crowd counting is a computer vision task that focuses on accurately estimating the number of people present in a given scene. In the past few years, convolutional neural network-based deep learning techniques have achieved remarkable success in many computer vision tasks, including crowd counting. In the field of crowd counting, large-scale changes have always been a great challenge. To resolve this problem, previous work used multiple branches to obtain information at different scales and combined it. However, purely combining multi-branch features cannot effectively utilize multi-scale information. In this work, we modify the previous multi-branch architecture, which can reasonably select the appropriate scale information. Furthermore, we test our model on the ShanghaiTech dataset and demonstrate the competitive performance of our method.
{"title":"Adaptive Scale Selection Network for Crowd Counting","authors":"Ting-Hsu Lai, Tsung-Jung Liu, Kuan-Hsien Liu","doi":"10.1109/ICCE-Taiwan58799.2023.10227011","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10227011","url":null,"abstract":"Crowd counting is a computer vision task that focuses on accurately estimating the number of people present in a given scene. In the past few years, convolutional neural network-based deep learning techniques have achieved remarkable success in many computer vision tasks, including crowd counting. In the field of crowd counting, large-scale changes have always been a great challenge. To resolve this problem, previous work used multiple branches to obtain information at different scales and combined it. However, purely combining multi-branch features cannot effectively utilize multi-scale information. In this work, we modify the previous multi-branch architecture, which can reasonably select the appropriate scale information. Furthermore, we test our model on the ShanghaiTech dataset and demonstrate the competitive performance of our method.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132540040","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}
A comprehensive visual traits-based recommendation system is designed for proactive retailing in a physical store environment. The proposed system utilizes computer vision algorithms to analyze various visual traits of customers, including facial features, clothing and accessories, to provide targeted product recommendations. The system does not require customers to provide any personal information, making it a less intrusive and more hassle-free approach compared to the conventional membership approach. By providing tailored product suggestions, the system offers retailers the opportunity to enhance their customers’ shopping experience and increase sales. This paper provides a detailed description of the system's design and setup.
{"title":"Visual Traits-Based Recommendation System for Proactive Retailing in Physical Store Environment","authors":"X. Kh’ng, Boon Yaik Ooi, Sheng Kang Teoh, Boon Sheng Ooi, Yen-Lin Chen","doi":"10.1109/ICCE-Taiwan58799.2023.10226980","DOIUrl":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226980","url":null,"abstract":"A comprehensive visual traits-based recommendation system is designed for proactive retailing in a physical store environment. The proposed system utilizes computer vision algorithms to analyze various visual traits of customers, including facial features, clothing and accessories, to provide targeted product recommendations. The system does not require customers to provide any personal information, making it a less intrusive and more hassle-free approach compared to the conventional membership approach. By providing tailored product suggestions, the system offers retailers the opportunity to enhance their customers’ shopping experience and increase sales. This paper provides a detailed description of the system's design and setup.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"35 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131545930","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：