Pub Date : 2024-04-23DOI: 10.1109/JRFID.2024.3392682
Chai Yang;Xiaoxuan Hu;Qingli Zhu;Qiang Tu;Hongyang Geng;Jing Xu;Zhenfeng Liu;Yanjun Wang;Jing Wang
Individual medical costs prediction refers to the process of estimating the expenses associated with a patient’s medical care. Effective medical costs prediction helps in budgeting, resource allocation, and financial planning in healthcare settings, making it a crucial tool for both healthcare providers and patients. This study introduces an advanced method for predicting medical consumables costs, leveraging clinical notes and diagnosis related groups (DRGs). The approach employs Bidirectional Encoder Representations from Transformers (BERT) for text vectorization to enhance disease diagnosis and surgical procedure prediction within DRGs using Light Gradient Boosting Machine (LightGBM), and Random Forest Regression for accurate medical costs prediction. It achieves over 91% accuracy in predicting disease diagnosis and surgical procedures, and a Mean Absolute Error (MAE) of 2281.20 and an R-squared value of 0.8557. These metrics indicate a high level of accuracy and reliability, showcasing the model’s efficacy in predicting medical costs in a healthcare setting. This method improves hospital resource management and costs estimation by integrating semantic information with machine learning algorithms.
{"title":"Individual Medical Costs Prediction Methods Based on Clinical Notes and DRGs","authors":"Chai Yang;Xiaoxuan Hu;Qingli Zhu;Qiang Tu;Hongyang Geng;Jing Xu;Zhenfeng Liu;Yanjun Wang;Jing Wang","doi":"10.1109/JRFID.2024.3392682","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3392682","url":null,"abstract":"Individual medical costs prediction refers to the process of estimating the expenses associated with a patient’s medical care. Effective medical costs prediction helps in budgeting, resource allocation, and financial planning in healthcare settings, making it a crucial tool for both healthcare providers and patients. This study introduces an advanced method for predicting medical consumables costs, leveraging clinical notes and diagnosis related groups (DRGs). The approach employs Bidirectional Encoder Representations from Transformers (BERT) for text vectorization to enhance disease diagnosis and surgical procedure prediction within DRGs using Light Gradient Boosting Machine (LightGBM), and Random Forest Regression for accurate medical costs prediction. It achieves over 91% accuracy in predicting disease diagnosis and surgical procedures, and a Mean Absolute Error (MAE) of 2281.20 and an R-squared value of 0.8557. These metrics indicate a high level of accuracy and reliability, showcasing the model’s efficacy in predicting medical costs in a healthcare setting. This method improves hospital resource management and costs estimation by integrating semantic information with machine learning algorithms.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"412-418"},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141068931","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 : 2024-04-22DOI: 10.1109/JRFID.2024.3392152
Songlin Bai;Yunzhe Wang;Zhiyao Luo;Yonglin Tian
Diverse and large-high-quality data are essential to the deep learning algorithms for autonomous driving. However, manual data collection in intricate traffic scenarios is expensive, time-consuming, and hard to meet the requirements of quantity and quality. Though some generative methods have been used for traffic image synthesis and editing to tackle the problem of manual data collection, the impact of object relationships on data diversity is frequently disregarded in these approaches. In this paper, we focus on the occluded pedestrians within complex driving scenes and propose an occupancy-aided augmentation method for occluded humans in autonomous driving denoted as “Drive-CP“, built upon the foundation of parallel vision. Due to the flourishing development of AI Content Generation (AIGC) technologies, it is possible to automate the generation of diverse 2D and 3D assets. Based on AIGC technologies, we can construct our human library automatically, significantly enhancing the diversity of the training data. We experimentally demonstrate that Drive-CP can generate diversified occluded pedestrians in real complex traffic scenes and demonstrate its effectiveness in enriching the training set in object detection tasks.
{"title":"DriveCP: Occupancy-Assisted Scenario Augmentation for Occluded Pedestrian Perception Based on Parallel Vision","authors":"Songlin Bai;Yunzhe Wang;Zhiyao Luo;Yonglin Tian","doi":"10.1109/JRFID.2024.3392152","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3392152","url":null,"abstract":"Diverse and large-high-quality data are essential to the deep learning algorithms for autonomous driving. However, manual data collection in intricate traffic scenarios is expensive, time-consuming, and hard to meet the requirements of quantity and quality. Though some generative methods have been used for traffic image synthesis and editing to tackle the problem of manual data collection, the impact of object relationships on data diversity is frequently disregarded in these approaches. In this paper, we focus on the occluded pedestrians within complex driving scenes and propose an occupancy-aided augmentation method for occluded humans in autonomous driving denoted as “Drive-CP“, built upon the foundation of parallel vision. Due to the flourishing development of AI Content Generation (AIGC) technologies, it is possible to automate the generation of diverse 2D and 3D assets. Based on AIGC technologies, we can construct our human library automatically, significantly enhancing the diversity of the training data. We experimentally demonstrate that Drive-CP can generate diversified occluded pedestrians in real complex traffic scenes and demonstrate its effectiveness in enriching the training set in object detection tasks.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"235-240"},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140902522","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 novel heading angle detection and compensation method is presented with the aim of addressing the navigation and localization accuracy challenges that unmanned robots encounter in their daily inspection jobs, thereby significantly raising the bar for smart port building and promoting the development of ports of superior quality. The Extended Kalman Filter (EKF) algorithm and a Global Navigation Satellite System (GNSS) Inertial Navigation System (INS)/Magnetometer combination navigation technology form the basis of this strategy. The suggested deviation detection and compensating method greatly enhances the navigation system’s performance when compared to the conventional EKF algorithm. Furthermore, we improved the navigation system’s ability to adapt to complex surroundings and sudden changes by adding the Particle Swarm Optimization (PSO) algorithm to the process. This allowed us to further optimize the system parameters based on the original innovation. This development is critical to enhancing unmanned robot navigation accuracy at smart ports and providing robust technical support for the growth of port automation and intelligence.
{"title":"Application Research of Parameter Uncertainty Optimization Method in Steering Detection and Correction System","authors":"Jiahao Yang;Ming Xu;Longhua Ma;Fangle Chang;Wenxiang Wu","doi":"10.1109/JRFID.2024.3392444","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3392444","url":null,"abstract":"A novel heading angle detection and compensation method is presented with the aim of addressing the navigation and localization accuracy challenges that unmanned robots encounter in their daily inspection jobs, thereby significantly raising the bar for smart port building and promoting the development of ports of superior quality. The Extended Kalman Filter (EKF) algorithm and a Global Navigation Satellite System (GNSS) Inertial Navigation System (INS)/Magnetometer combination navigation technology form the basis of this strategy. The suggested deviation detection and compensating method greatly enhances the navigation system’s performance when compared to the conventional EKF algorithm. Furthermore, we improved the navigation system’s ability to adapt to complex surroundings and sudden changes by adding the Particle Swarm Optimization (PSO) algorithm to the process. This allowed us to further optimize the system parameters based on the original innovation. This development is critical to enhancing unmanned robot navigation accuracy at smart ports and providing robust technical support for the growth of port automation and intelligence.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"665-670"},"PeriodicalIF":2.3,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965996","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}
Federated learning is a distributed machine learning approach that achieves collaborative training while protecting data privacy. However, in distributed scenarios, the operational data of industrial equipment is dynamic and non-independently identically distributed (non-IID). This situation leads to poor performance of federated learning algorithms in industrial anomaly detection tasks. Personalized federated learning is a viable solution to the non-IID data problem, but it is not effective in responding to dynamic environmental changes. Implementing directed updates to the model, thereby effectively maintaining its stability, is one of the solutions for addressing dynamic challenges. In addition, even though federated learning has the ability to protect data privacy, it still has the risk of privacy leakage due to differential privacy attacks. In this paper, we propose a personalized federated learning based on hypernetwork and credible directed update of models to generate stable personalized models for clients with non-IID data in a dynamic environment. Furthermore, we propose a parameter-varying differential privacy mechanism to mitigate compromised differential attacks. We evaluate the capability of the proposed method to perform the anomaly detection task using real air conditioning datasets from three distinct factories. The results demonstrate that our framework outperforms existing personalized federated learning methods with an average accuracy improvement of 11.32%. Additionally, experimental results demonstrate that the framework can withstand differential attacks while maintaining high accuracy.
{"title":"A Personalized and Differentially Private Federated Learning for Anomaly Detection of Industrial Equipment","authors":"Zhen Zhang;Weishan Zhang;Zhicheng Bao;Yifan Miao;Yuru Liu;Yikang Zhao;Rui Zhang;Wenyin Zhu","doi":"10.1109/JRFID.2024.3390142","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3390142","url":null,"abstract":"Federated learning is a distributed machine learning approach that achieves collaborative training while protecting data privacy. However, in distributed scenarios, the operational data of industrial equipment is dynamic and non-independently identically distributed (non-IID). This situation leads to poor performance of federated learning algorithms in industrial anomaly detection tasks. Personalized federated learning is a viable solution to the non-IID data problem, but it is not effective in responding to dynamic environmental changes. Implementing directed updates to the model, thereby effectively maintaining its stability, is one of the solutions for addressing dynamic challenges. In addition, even though federated learning has the ability to protect data privacy, it still has the risk of privacy leakage due to differential privacy attacks. In this paper, we propose a personalized federated learning based on hypernetwork and credible directed update of models to generate stable personalized models for clients with non-IID data in a dynamic environment. Furthermore, we propose a parameter-varying differential privacy mechanism to mitigate compromised differential attacks. We evaluate the capability of the proposed method to perform the anomaly detection task using real air conditioning datasets from three distinct factories. The results demonstrate that our framework outperforms existing personalized federated learning methods with an average accuracy improvement of 11.32%. Additionally, experimental results demonstrate that the framework can withstand differential attacks while maintaining high accuracy.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"468-475"},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251133","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 : 2024-04-17DOI: 10.1109/JRFID.2024.3390624
Francesco Lestini;Gaetano Marrocco;Cecilia Occhiuzzi
Modern wireless communication systems are becoming increasingly necessary, emphasizing the need for electromagnetic devices that can flexibly operate under different conditions, e.g., under power constraints or in hostile environments where scattering objects randomly modify coverage areas and communication links. Due to their ability to dynamically change operating frequency, radiation pattern, bandwidth characteristics, and polarization, reconfigurable objects (especially antennas and backscattering surfaces) have received significant attention in this context. Electromagnetic features can be electronically selected by controlling the bias voltage of tunable elements adequately integrated into the layout. Usually, this is done by employing external programmable controllers that need power sources and wired connections, leading to unusable configurations for several scenarios. Thus, exploring alternative electronic tuning mechanisms becomes essential. This paper proposes RFID-Based Reconfigurable Electromagnetic Devices as a wireless, cost-effective, and low-power solution. The system’s operating principle, potential architectures, and applicability in practical scenarios are presented. Theoretical and experimental analysis validate the proposed architecture, whose capabilities are finally demonstrated by prototyping and testing two reconfigurable antenna arrays.
现代无线通信系统变得越来越必要，这强调了对能够在不同条件下灵活运行的电磁设备的需求，例如，在功率受限或散射物体随机改变覆盖区域和通信链路的恶劣环境中。可重构物体（尤其是天线和后向散射表面）能够动态改变工作频率、辐射模式、带宽特性和极化，因此在这方面受到极大关注。通过控制已充分集成到布局中的可调元件的偏置电压，可对电磁特性进行电子选择。通常情况下，这是通过采用外部可编程控制器来实现的，而外部控制器需要电源和有线连接，从而导致在多种情况下无法使用配置。因此，探索其他电子调谐机制变得至关重要。本文提出了基于 RFID 的可重构电磁设备，作为一种无线、经济、低功耗的解决方案。本文介绍了该系统的工作原理、潜在架构以及在实际场景中的适用性。理论和实验分析验证了所提出的架构，并通过两个可重构天线阵列的原型设计和测试，最终证明了该架构的能力。
{"title":"RFID-Based Reconfigurable Electromagnetic Devices","authors":"Francesco Lestini;Gaetano Marrocco;Cecilia Occhiuzzi","doi":"10.1109/JRFID.2024.3390624","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3390624","url":null,"abstract":"Modern wireless communication systems are becoming increasingly necessary, emphasizing the need for electromagnetic devices that can flexibly operate under different conditions, e.g., under power constraints or in hostile environments where scattering objects randomly modify coverage areas and communication links. Due to their ability to dynamically change operating frequency, radiation pattern, bandwidth characteristics, and polarization, reconfigurable objects (especially antennas and backscattering surfaces) have received significant attention in this context. Electromagnetic features can be electronically selected by controlling the bias voltage of tunable elements adequately integrated into the layout. Usually, this is done by employing external programmable controllers that need power sources and wired connections, leading to unusable configurations for several scenarios. Thus, exploring alternative electronic tuning mechanisms becomes essential. This paper proposes RFID-Based Reconfigurable Electromagnetic Devices as a wireless, cost-effective, and low-power solution. The system’s operating principle, potential architectures, and applicability in practical scenarios are presented. Theoretical and experimental analysis validate the proposed architecture, whose capabilities are finally demonstrated by prototyping and testing two reconfigurable antenna arrays.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"226-234"},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140902543","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 this paper, a 2.45/5.8 GHz circularly polarized RFID antenna backed with a dual-band artificial magnetic conductor (AMC) is presented for tagged-object detection in Internet of things (IoT) networks. RFID systems require a long-range reader to maintain energy-efficient communication with the tagged devices. An efficient reader antenna is presented to increase the interrogation distance of the reader, and decreasing the uncertainty of tagged-object detection. The proposed RFID antenna consists of two dipole pairs, are printed on both sides of the substrate to obtain 2.45 GHz and 5.8 GHz bands, connected by feed delay lines in a cross-dipole arrangement. To increase the range of the reader, the cross-dipole antenna is supported by a $5times5$ AMC surface placed $0.042{lambda }_{0}$ beneath the antenna, where ${lambda }_{0}$ is the wavelength calculated at the lowest resonant frequency. In measurement, the metasurface backing results in gain enhancements of 4.1 dBi in the 2.45 GHz band and 4.6 dBi in the 5.8 GHz band, which improves the read range of the reader. The measurement also shows an improvement in RFID band coverage in terms of impedance bandwidth, 2.32–2.57 GHz in the 2.45 GHz band and 5.48-6 GHz in the 5.8 GHz band, reducing tag-detection error. The axial ratio bandwidth of the reader antenna configuration is 2.385–2.485 GHz and 5.77–5.88 GHz in the 2.45 GHz and 5.8 GHz bands, respectively.
{"title":"Directional Energy-Efficient Metasurface-Backed RFID Reader Antenna for Minimizing Tag-Detection Uncertainty in IoT Networks","authors":"Chandni Bajaj;Dharmendra Kumar Upadhyay;Sachin Kumar;Binod Kumar Kanaujia","doi":"10.1109/JRFID.2024.3389737","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3389737","url":null,"abstract":"In this paper, a 2.45/5.8 GHz circularly polarized RFID antenna backed with a dual-band artificial magnetic conductor (AMC) is presented for tagged-object detection in Internet of things (IoT) networks. RFID systems require a long-range reader to maintain energy-efficient communication with the tagged devices. An efficient reader antenna is presented to increase the interrogation distance of the reader, and decreasing the uncertainty of tagged-object detection. The proposed RFID antenna consists of two dipole pairs, are printed on both sides of the substrate to obtain 2.45 GHz and 5.8 GHz bands, connected by feed delay lines in a cross-dipole arrangement. To increase the range of the reader, the cross-dipole antenna is supported by a \u0000<inline-formula> <tex-math>$5times5$ </tex-math></inline-formula>\u0000 AMC surface placed \u0000<inline-formula> <tex-math>$0.042{lambda }_{0}$ </tex-math></inline-formula>\u0000 beneath the antenna, where \u0000<inline-formula> <tex-math>${lambda }_{0}$ </tex-math></inline-formula>\u0000 is the wavelength calculated at the lowest resonant frequency. In measurement, the metasurface backing results in gain enhancements of 4.1 dBi in the 2.45 GHz band and 4.6 dBi in the 5.8 GHz band, which improves the read range of the reader. The measurement also shows an improvement in RFID band coverage in terms of impedance bandwidth, 2.32–2.57 GHz in the 2.45 GHz band and 5.48-6 GHz in the 5.8 GHz band, reducing tag-detection error. The axial ratio bandwidth of the reader antenna configuration is 2.385–2.485 GHz and 5.77–5.88 GHz in the 2.45 GHz and 5.8 GHz bands, respectively.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"88-97"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826058","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 : 2024-04-16DOI: 10.1109/JRFID.2024.3389870
Giulio Maria Bianco;Gaetano Marrocco
Microfluidic has been an enabling technology for over a decade, particularly in the field of medical and wearable devices, allowing for the manipulation of small amounts of fluid in confined spaces. Micro-channels can also be used for wireless sensing thanks to the variations in antenna properties when the fluid flows near it. However, up to now, microfluidic channels and sensing antennas have always been designed separately; instead, since the liquid flow and the antenna geometry both contribute to the overall performance, they should be considered simultaneously when optimizing the antenna-microfluidic system. In this paper, the joint design of the antenna and microfluidic channels is investigated for liquid quantification. Self-tuning RFID microchips are exploited to minimize communication degradation due to the increase of lossy liquid amount over the sensing antenna while digitalizing the impedance mismatch itself. To experimentally corroborate the joint design technique, two different geometries are obtained and prototyped starting from a given antenna-microfluidic layout by setting different goals for an optimization function. The two flexible RFID prototypes returned performance in agreement with the simulated ones, achieving a maximum sensitivity of about 20 units of the digital metric per milligram increase of water.
十多年来，微流体技术一直是一种赋能技术，尤其是在医疗和可穿戴设备领域，它允许在密闭空间内操作少量流体。微通道还可用于无线传感，这要归功于流体在其附近流动时天线特性的变化。然而，迄今为止，微流体通道和传感天线一直是分开设计的；相反，由于液体流动和天线几何形状都会影响整体性能，因此在优化天线-微流体系统时应同时考虑这两个因素。本文针对液体定量研究了天线和微流控通道的联合设计。在对阻抗失配本身进行数字化的同时，利用自调谐射频识别（RFID）微芯片最大限度地降低了因传感天线上方有损液体量增加而导致的通信质量下降。为了在实验中证实联合设计技术，通过为优化函数设定不同的目标，从给定的天线-微流体布局开始，获得了两种不同的几何形状并制作了原型。两个柔性 RFID 原型的性能与模拟的一致，每增加一毫克水的最大灵敏度约为 20 个数字度量单位。
{"title":"Joint Design of Self-Tuning UHF RFID Antenna and Microfluidic Channel for Liquid Sensing","authors":"Giulio Maria Bianco;Gaetano Marrocco","doi":"10.1109/JRFID.2024.3389870","DOIUrl":"10.1109/JRFID.2024.3389870","url":null,"abstract":"Microfluidic has been an enabling technology for over a decade, particularly in the field of medical and wearable devices, allowing for the manipulation of small amounts of fluid in confined spaces. Micro-channels can also be used for wireless sensing thanks to the variations in antenna properties when the fluid flows near it. However, up to now, microfluidic channels and sensing antennas have always been designed separately; instead, since the liquid flow and the antenna geometry both contribute to the overall performance, they should be considered simultaneously when optimizing the antenna-microfluidic system. In this paper, the joint design of the antenna and microfluidic channels is investigated for liquid quantification. Self-tuning RFID microchips are exploited to minimize communication degradation due to the increase of lossy liquid amount over the sensing antenna while digitalizing the impedance mismatch itself. To experimentally corroborate the joint design technique, two different geometries are obtained and prototyped starting from a given antenna-microfluidic layout by setting different goals for an optimization function. The two flexible RFID prototypes returned performance in agreement with the simulated ones, achieving a maximum sensitivity of about 20 units of the digital metric per milligram increase of water.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"58-67"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140711499","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 : 2024-04-16DOI: 10.1109/JRFID.2024.3389088
Lin Wang;Fenghua Zhu;Hui Zhang;Gang Xiong;Yunhu Huang;Dewang Chen
Semantic segmentation plays a fundamental role in computer vision, underpinning applications such as autonomous driving and scene analysis. Although dual-branch networks have marked advancements in accuracy and processing speed, they falter in the context extraction phase within the low-resolution branch. Traditionally, square pooling is used at this juncture, leading to the oversight of stripe-shaped contextual information. In response, we introduce a novel architecture based on a deep aggregation pyramid, engineered for both real-time processing and precise segmentation. Central to our approach is a pioneering contextual information extractor designed to expand the effective receptive fields and fuse multi-scale context from low-resolution feature maps. Additionally, we have developed a feature fusion module to enhance the integration and differentiation of high-level semantic information across branches. To further refine the fidelity of segmentation, we implement dual deep supervisions within the high-resolution branchs intermediate layer, concentrating on boundary delineation and global features to enrich spatial detail capture. Our comprehensive experimental analysis, conducted on the Cityscapes and CamVid datasets, affirms MSSINets superior performance, showcasing its competitiveness against existing leading methodologies across a variety of scenarios.
{"title":"MSSINet: Real-Time Segmentation Based on Multi-Scale Strip Integration","authors":"Lin Wang;Fenghua Zhu;Hui Zhang;Gang Xiong;Yunhu Huang;Dewang Chen","doi":"10.1109/JRFID.2024.3389088","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3389088","url":null,"abstract":"Semantic segmentation plays a fundamental role in computer vision, underpinning applications such as autonomous driving and scene analysis. Although dual-branch networks have marked advancements in accuracy and processing speed, they falter in the context extraction phase within the low-resolution branch. Traditionally, square pooling is used at this juncture, leading to the oversight of stripe-shaped contextual information. In response, we introduce a novel architecture based on a deep aggregation pyramid, engineered for both real-time processing and precise segmentation. Central to our approach is a pioneering contextual information extractor designed to expand the effective receptive fields and fuse multi-scale context from low-resolution feature maps. Additionally, we have developed a feature fusion module to enhance the integration and differentiation of high-level semantic information across branches. To further refine the fidelity of segmentation, we implement dual deep supervisions within the high-resolution branchs intermediate layer, concentrating on boundary delineation and global features to enrich spatial detail capture. Our comprehensive experimental analysis, conducted on the Cityscapes and CamVid datasets, affirms MSSINets superior performance, showcasing its competitiveness against existing leading methodologies across a variety of scenarios.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"241-251"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140906889","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 : 2024-04-16DOI: 10.1109/JRFID.2024.3389868
Erbo Shen;Weidong Yang;Xuyu Wang;Bo Kang;Shiwen Mao
Grain is a major source of food, while grain security has been considered as a strategic issue in many countries. Temperature and moisture as the two key properties affect the quality of stored grain. Most existing approaches for sensing these properties are expensive, time-consuming, and are difficult to deploy. In this paper, we design a TagSense system to sense the temperature and moisture level of stored wheat using commodity RFID devices, where tag’s impedance is exploited as a feature for target sensing at a low cost. Since impedance is sensitive to the signal propagation distance and incidence angle, we propose a distance-independent algorithm and an angle-agnostic approach to mitigate the impact of distance and angles on the sensing performance. Our extensive experiment results demonstrate that TagSense can achieve a satisfactory sensing performance at any distance and any angle within the sensing range.
谷物是粮食的主要来源，而谷物安全在许多国家都被视为一个战略问题。温度和水分是影响储藏谷物质量的两个关键属性。现有的感知这些属性的方法大多昂贵、耗时，而且难以部署。在本文中，我们设计了一种 TagSense 系统，利用商品 RFID 设备来感知储存小麦的温度和湿度水平，其中标签的阻抗被用作目标感知的一个特征，而且成本低廉。由于阻抗对信号传播距离和入射角度很敏感，我们提出了一种与距离无关的算法和一种与角度无关的方法，以减轻距离和角度对传感性能的影响。我们的大量实验结果表明，TagSense 可以在感应范围内的任何距离和任何角度实现令人满意的感应性能。
{"title":"TagSense: Robust Wheat Moisture and Temperature Sensing Using RFID","authors":"Erbo Shen;Weidong Yang;Xuyu Wang;Bo Kang;Shiwen Mao","doi":"10.1109/JRFID.2024.3389868","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3389868","url":null,"abstract":"Grain is a major source of food, while grain security has been considered as a strategic issue in many countries. Temperature and moisture as the two key properties affect the quality of stored grain. Most existing approaches for sensing these properties are expensive, time-consuming, and are difficult to deploy. In this paper, we design a TagSense system to sense the temperature and moisture level of stored wheat using commodity RFID devices, where tag’s impedance is exploited as a feature for target sensing at a low cost. Since impedance is sensitive to the signal propagation distance and incidence angle, we propose a distance-independent algorithm and an angle-agnostic approach to mitigate the impact of distance and angles on the sensing performance. Our extensive experiment results demonstrate that TagSense can achieve a satisfactory sensing performance at any distance and any angle within the sensing range.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"76-87"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826000","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 : 2024-04-12DOI: 10.1109/JRFID.2024.3387996
Rakiba Rayhana;Ling Bai;Gaozhi Xiao;Min Liao;Zheng Liu
In the rapidly evolving landscape of Industry 4.0, digital twins have emerged as a transformative technology across various industrial sectors. This paper presents a comprehensive, in-depth review of digital twin models in terms of the concept and evolution, fundamental components and frameworks, and existing digital twin models based on their functionalities. The paper also discusses how the existing digital twin models are used/adopted in different industries and highlights the existing challenges and potential solutions to address the current issues. This paper aims to provide researchers and industry professionals with a clear insight into the unique benefits and applications of different digital twin models. This review will help to comprehend their significance for specific industrial purposes and foster the advancement of state-of-the-art techniques in this field.
{"title":"Digital Twin Models: Functions, Challenges, and Industry Applications","authors":"Rakiba Rayhana;Ling Bai;Gaozhi Xiao;Min Liao;Zheng Liu","doi":"10.1109/JRFID.2024.3387996","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3387996","url":null,"abstract":"In the rapidly evolving landscape of Industry 4.0, digital twins have emerged as a transformative technology across various industrial sectors. This paper presents a comprehensive, in-depth review of digital twin models in terms of the concept and evolution, fundamental components and frameworks, and existing digital twin models based on their functionalities. The paper also discusses how the existing digital twin models are used/adopted in different industries and highlights the existing challenges and potential solutions to address the current issues. This paper aims to provide researchers and industry professionals with a clear insight into the unique benefits and applications of different digital twin models. This review will help to comprehend their significance for specific industrial purposes and foster the advancement of state-of-the-art techniques in this field.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"282-321"},"PeriodicalIF":0.0,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924754","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：