Pub Date : 2024-06-04DOI: 10.1109/JRFID.2024.3409362
Sayan Sarkar
This paper presents three dual-band, dual-linearly polarized antenna configurations for UHF-RFID and WLAN applications. The first configuration consists of a square patch with outer ring which exhibits two resonances at 865MHz and 2.45GHz respectively. At both these frequencies, the antenna has its main beam along the +z axis (broadside direction). Two superstrates, S3 and S4, are designed to be used separately with this antenna. Both S3 and S4, when placed above the antenna separately, shift the first resonance from 865MHz to 905MHz without affecting the 2.45GHz resonance. Placing S3 5mm above the antenna gives rise to a bi-directional radiation pattern (±z-axis) while replacing S3 with S4 generates a main beam along the -z axis (opposite broadside direction) at 905MHz. The radiation pattern remains unperturbed at 2.45GHz for both configurations. The first antenna configuration works within the European UHF-RFID band whereas the antenna + S3 and antenna + S4 configurations work within the North-American UHF-RFID band. Additionally, all three configurations also operate within the 2.45GHz WLAN band. Both the antenna-superstrate configurations have very low profiles of $lambda _{0}$ / $24.4~(lambda _{0} ,, {=}$ free space wavelength at 2.45GHz). The antenna can thus be used with/without the superstrates as an RFID reader depending upon requirements. The information received from the tags can then be transmitted via the WLAN channel.
{"title":"Three Dual-Band and Dual-Linearly Polarized Antenna Configurations for UHF-RFID and WLAN Applications","authors":"Sayan Sarkar","doi":"10.1109/JRFID.2024.3409362","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3409362","url":null,"abstract":"This paper presents three dual-band, dual-linearly polarized antenna configurations for UHF-RFID and WLAN applications. The first configuration consists of a square patch with outer ring which exhibits two resonances at 865MHz and 2.45GHz respectively. At both these frequencies, the antenna has its main beam along the +z axis (broadside direction). Two superstrates, S3 and S4, are designed to be used separately with this antenna. Both S3 and S4, when placed above the antenna separately, shift the first resonance from 865MHz to 905MHz without affecting the 2.45GHz resonance. Placing S3 5mm above the antenna gives rise to a bi-directional radiation pattern (±z-axis) while replacing S3 with S4 generates a main beam along the -z axis (opposite broadside direction) at 905MHz. The radiation pattern remains unperturbed at 2.45GHz for both configurations. The first antenna configuration works within the European UHF-RFID band whereas the antenna + S3 and antenna + S4 configurations work within the North-American UHF-RFID band. Additionally, all three configurations also operate within the 2.45GHz WLAN band. Both the antenna-superstrate configurations have very low profiles of \u0000<inline-formula> <tex-math>$lambda _{0}$ </tex-math></inline-formula>\u0000/\u0000<inline-formula> <tex-math>$24.4~(lambda _{0} ,, {=}$ </tex-math></inline-formula>\u0000 free space wavelength at 2.45GHz). The antenna can thus be used with/without the superstrates as an RFID reader depending upon requirements. The information received from the tags can then be transmitted via the WLAN channel.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"571-579"},"PeriodicalIF":2.3,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141447993","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 : 2024-04-30DOI: 10.1109/JRFID.2024.3394062
James D. Rosenthal;Matthew S. Reynolds
Delta-sigma modulation (DSM) enables the use of all-digital switched impedance modulators to generate arbitrary backscatter signals. For example, a DSM-based backscatter modulator having only two or four impedance states can generate quadrature amplitude modulation (QAM) with e.g., 64 states, or multicarrier orthogonal frequency division multiplexed (OFDM) signals having many subcarriers. This paper describes potential improvements to in-channel spectral characteristics by adding single sideband (SSB) and double sideband (DSB) noise shaping to the DSM signal path. Using numerical simulation and hardware validation, we demonstrate that noise-shaped DSM can improve the spurious-free dynamic range (SFDR) of OFDM subcarriers generated by a low-resolution two-state or four-state impedance digital-to-analog converter. The noise shaping approaches are validated using a prototype OFDM backscatter uplink based on an FPGA driving a single-pole-four-throw (SP4T) CMOS RF switch that serves as the backscatter modulator. The SSB and DSB noise shaping techniques are compared by over-the-air transmission of five-subcarrier OFDM backscatter symbols with a four-times oversampling DSM at up to 1.25 Mbps. With this approach, we find that DSB noise shaping yielded a 6.2 dB improvement in SFDR relative to SSB noise shaping, at the cost of 9.8 dB higher peak out-of-band quantization noise. These results confirm that an all-digital modulation approach with noise-shaped DSM can be used to balance in-band vs. out-of-band quantization noise and thus optimize the spectral characteristics of hardware-efficient, all-digital backscatter modulators for low-power wireless communication.
{"title":"Single Sideband Noise Shaping for All-Digital Delta-Sigma OFDM Backscatter Modulators","authors":"James D. Rosenthal;Matthew S. Reynolds","doi":"10.1109/JRFID.2024.3394062","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3394062","url":null,"abstract":"Delta-sigma modulation (DSM) enables the use of all-digital switched impedance modulators to generate arbitrary backscatter signals. For example, a DSM-based backscatter modulator having only two or four impedance states can generate quadrature amplitude modulation (QAM) with e.g., 64 states, or multicarrier orthogonal frequency division multiplexed (OFDM) signals having many subcarriers. This paper describes potential improvements to in-channel spectral characteristics by adding single sideband (SSB) and double sideband (DSB) noise shaping to the DSM signal path. Using numerical simulation and hardware validation, we demonstrate that noise-shaped DSM can improve the spurious-free dynamic range (SFDR) of OFDM subcarriers generated by a low-resolution two-state or four-state impedance digital-to-analog converter. The noise shaping approaches are validated using a prototype OFDM backscatter uplink based on an FPGA driving a single-pole-four-throw (SP4T) CMOS RF switch that serves as the backscatter modulator. The SSB and DSB noise shaping techniques are compared by over-the-air transmission of five-subcarrier OFDM backscatter symbols with a four-times oversampling DSM at up to 1.25 Mbps. With this approach, we find that DSB noise shaping yielded a 6.2 dB improvement in SFDR relative to SSB noise shaping, at the cost of 9.8 dB higher peak out-of-band quantization noise. These results confirm that an all-digital modulation approach with noise-shaped DSM can be used to balance in-band vs. out-of-band quantization noise and thus optimize the spectral characteristics of hardware-efficient, all-digital backscatter modulators for low-power wireless communication.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"270-276"},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924688","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}
For the first time, a novel low-profile top-loaded monopole antenna is proposed for on-metal omnidirectional tag design. Here, a square patch is loaded on top of a short monopole antenna to improve its input impedance and radiation efficiency. Subsequently, the tag antenna is shunt-fed (using both the direct-feeding and proximity-coupled-feeding methods) to further enhance its input impedance and omnidirectionality. As a result, the antenna impedance, radiation resistance, and radiation efficiency have all been enhanced significantly, as compared with a typical short monopole antenna. A C-shaped feedline, which is to shunt-feed the tag antenna, is also introducing additional inductance to the antenna impedance for attaining good impedance matching level. Despite having a profile of not more than one hundredth of the operating wavelength, the proposed tag antenna is still able to exhibit a strong and stable omnidirectional radiation pattern when attached on a metal. The proposed tag antenna, which has a size of $0.1069 lambda times 0.1069 lambda times 0.0098~lambda $ , can provide a constant read range of ~9.2 m in all azimuthal directions, with a minimal fluctuation of 0.5 m at 0.910 GHz. The tag’s resonance remains stable and independent of the size and shape of the backing conductive platform.
首次提出了一种用于金属全向标签设计的新型扁平顶部单极天线。在这里，一个方形贴片被加载到一个短单极天线的顶部，以改善其输入阻抗和辐射效率。随后，对标签天线进行并联馈电（采用直接馈电和近距离耦合馈电两种方法），以进一步提高其输入阻抗和全向性。因此，与典型的短单极天线相比，天线阻抗、辐射阻抗和辐射效率都得到了显著提高。C 形馈线用于对标签天线进行分流馈电，也为天线阻抗引入了额外的电感，以达到良好的阻抗匹配水平。尽管标签天线的轮廓不超过工作波长的百分之一，但当它贴在金属上时，仍能显示出强大而稳定的全向辐射模式。拟议的标签天线尺寸为 0.1069 lambda times 0.1069 lambda times 0.0098~lambda $，可以在所有方位角方向提供约 9.2 米的恒定读取范围，在 0.910 GHz 频率下波动最小为 0.5 米。标签的共振保持稳定，与背衬导电平台的尺寸和形状无关。
{"title":"A Low-Profile Top-Loaded Monopole Antenna for On-Metal RFID Tag Design","authors":"Jiun-Ian Tan;Yong-Hong Lee;Eng-Hock Lim;Fwee-Leong Bong;Boon-Kuan Chung","doi":"10.1109/JRFID.2024.3393994","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3393994","url":null,"abstract":"For the first time, a novel low-profile top-loaded monopole antenna is proposed for on-metal omnidirectional tag design. Here, a square patch is loaded on top of a short monopole antenna to improve its input impedance and radiation efficiency. Subsequently, the tag antenna is shunt-fed (using both the direct-feeding and proximity-coupled-feeding methods) to further enhance its input impedance and omnidirectionality. As a result, the antenna impedance, radiation resistance, and radiation efficiency have all been enhanced significantly, as compared with a typical short monopole antenna. A C-shaped feedline, which is to shunt-feed the tag antenna, is also introducing additional inductance to the antenna impedance for attaining good impedance matching level. Despite having a profile of not more than one hundredth of the operating wavelength, the proposed tag antenna is still able to exhibit a strong and stable omnidirectional radiation pattern when attached on a metal. The proposed tag antenna, which has a size of \u0000<inline-formula> <tex-math>$0.1069 lambda times 0.1069 lambda times 0.0098~lambda $ </tex-math></inline-formula>\u0000, can provide a constant read range of ~9.2 m in all azimuthal directions, with a minimal fluctuation of 0.5 m at 0.910 GHz. The tag’s resonance remains stable and independent of the size and shape of the backing conductive platform.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"448-457"},"PeriodicalIF":0.0,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073616","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 : 2024-04-26DOI: 10.1109/JRFID.2024.3394063
Anish Kumar Gupta;Punitkumar Bhavsar
This article proposes incorporation of reconfigurable intelligent surfaces (RIS) with ambient backscatter (AmBc) communication. The aim is to strengthen the radio links between ambient source to backscatter device (BD) and from BD to cooperative receiver (CR). The analysis considers correlated Rician channels and incorporates hardware imperfection (HWI) modeled by von-Mises distribution. We derive a closed form expression of the outage probability which is validated through Monte Carlo (MC) simulations. The findings show improvement in outage probability for a deliberate selection of parameters of the proposed RIS assisted AmBc communication system. In addition, the importance of correlated-channel behavior is considered and analyzed for its effect on the outage probability performance of the proposed system.
{"title":"RIS Assisted AmBc Communication Over Spatially Correlated Channels","authors":"Anish Kumar Gupta;Punitkumar Bhavsar","doi":"10.1109/JRFID.2024.3394063","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3394063","url":null,"abstract":"This article proposes incorporation of reconfigurable intelligent surfaces (RIS) with ambient backscatter (AmBc) communication. The aim is to strengthen the radio links between ambient source to backscatter device (BD) and from BD to cooperative receiver (CR). The analysis considers correlated Rician channels and incorporates hardware imperfection (HWI) modeled by von-Mises distribution. We derive a closed form expression of the outage probability which is validated through Monte Carlo (MC) simulations. The findings show improvement in outage probability for a deliberate selection of parameters of the proposed RIS assisted AmBc communication system. In addition, the importance of correlated-channel behavior is considered and analyzed for its effect on the outage probability performance of the proposed system.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"262-269"},"PeriodicalIF":0.0,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140906890","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 : 2024-04-24DOI: 10.1109/JRFID.2024.3392943
Sheng Liu;Xiaotian Zhuang;Liang Yan;Yu Wang;Shengnan Wu;Yisheng Lv;Fenghua Zhu;Fei-Yue Wang
In order to solve the problems of package delivery delay and package loss caused by the sudden increase of package transportation demand during large-scale promotion activities such as 11.11 and 6.18, this paper proposes a parallel logistic network method, aiming at the logistic network of large logistic enterprises, establishes its equivalent virtual logistic network, senses the package transportation demand and network state of the actual logistic network, circularly simulates the operation in advance, finds the delayed and lost packages, analyzes the reasons, and adjust the parameters of network nodes and transportation lines to ensure that packages are delivered on time at low cost. Then the adjusted virtual network parameters are fed back to the actual logistic network, so as to realize the efficient operation of logistic enterprises. A simulation engine ensures that the simulation of 400 million package distribution in 30 days can be completed in half an hour on a personal computer. The application results show that the parallel logistic network reduces the package transportation time by about 10%. The transportation distance is reduced by 7%. Reduce transportation costs by 15%.
{"title":"A Parallel Logistic Network Simulation Method and System to Improve Logistics Efficiency","authors":"Sheng Liu;Xiaotian Zhuang;Liang Yan;Yu Wang;Shengnan Wu;Yisheng Lv;Fenghua Zhu;Fei-Yue Wang","doi":"10.1109/JRFID.2024.3392943","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3392943","url":null,"abstract":"In order to solve the problems of package delivery delay and package loss caused by the sudden increase of package transportation demand during large-scale promotion activities such as 11.11 and 6.18, this paper proposes a parallel logistic network method, aiming at the logistic network of large logistic enterprises, establishes its equivalent virtual logistic network, senses the package transportation demand and network state of the actual logistic network, circularly simulates the operation in advance, finds the delayed and lost packages, analyzes the reasons, and adjust the parameters of network nodes and transportation lines to ensure that packages are delivered on time at low cost. Then the adjusted virtual network parameters are fed back to the actual logistic network, so as to realize the efficient operation of logistic enterprises. A simulation engine ensures that the simulation of 400 million package distribution in 30 days can be completed in half an hour on a personal computer. The application results show that the parallel logistic network reduces the package transportation time by about 10%. The transportation distance is reduced by 7%. Reduce transportation costs by 15%.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"580-591"},"PeriodicalIF":2.3,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141453461","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 : 2024-04-24DOI: 10.1109/JRFID.2024.3393242
Kai Huang;Yongtao Ma;Yicheng Chu;Zemin Wang
As the global population ages, the prevalence of elderly individuals living independently has risen. As one of the main threats to the health of the elderly, falling seriously reduces the happiness of the elderly and imposes a burden on the medical system. Therefore, the exploration of automatic fall detection systems is crucial. However, proposed fall detection systems exhibit varying degrees of shortcomings. In this paper, we propose a new fall detection method utilizing Doppler shift with RFID passive tags. The motion of the passive tag induces a Doppler shift in the reflected signal. This method is the first to use Doppler frequency shift for fall detection in RFID. Additionally, a velocity-position iteration algorithm is applied to ascertain the tag’s position and velocity over time. The combination of velocity and position for fall detection yields higher accuracy compared to individual parameters. The proposed method demonstrates the capability to differentiate between sudden and soft falls, aiding medical professionals in identifying the cause of a user’s fall. The experimental results demonstrate that the system achieves an accuracy rate of 91.7% in detecting sudden falls, and this accuracy remains at 86.8% even after incorporating soft falls into the analysis. Consequently, the proposed method proves to be an effective and reliable approach for fall detection.
随着全球人口老龄化的加剧，独立生活的老年人越来越多。作为老年人健康的主要威胁之一，跌倒严重降低了老年人的幸福感，也给医疗系统带来了负担。因此，探索自动跌倒检测系统至关重要。然而，目前提出的跌倒检测系统都存在不同程度的缺陷。在本文中，我们提出了一种利用多普勒频移和 RFID 无源标签的新型跌倒检测方法。无源标签的运动会引起反射信号的多普勒频移。该方法首次将多普勒频移用于 RFID 的跌倒检测。此外，还采用了速度-位置迭代算法来确定标签随时间变化的位置和速度。与单个参数相比，结合速度和位置进行跌倒检测的准确度更高。所提出的方法证明了区分突然跌倒和软跌倒的能力，有助于医疗专业人员识别用户跌倒的原因。实验结果表明，该系统检测突然跌倒的准确率达到 91.7%，即使将软跌倒纳入分析，准确率也保持在 86.8%。因此，所提出的方法被证明是一种有效、可靠的跌倒检测方法。
{"title":"Tag-Fall: A Doppler Shift-Based Fall Detection Method Using RFID Passive Tags","authors":"Kai Huang;Yongtao Ma;Yicheng Chu;Zemin Wang","doi":"10.1109/JRFID.2024.3393242","DOIUrl":"https://doi.org/10.1109/JRFID.2024.3393242","url":null,"abstract":"As the global population ages, the prevalence of elderly individuals living independently has risen. As one of the main threats to the health of the elderly, falling seriously reduces the happiness of the elderly and imposes a burden on the medical system. Therefore, the exploration of automatic fall detection systems is crucial. However, proposed fall detection systems exhibit varying degrees of shortcomings. In this paper, we propose a new fall detection method utilizing Doppler shift with RFID passive tags. The motion of the passive tag induces a Doppler shift in the reflected signal. This method is the first to use Doppler frequency shift for fall detection in RFID. Additionally, a velocity-position iteration algorithm is applied to ascertain the tag’s position and velocity over time. The combination of velocity and position for fall detection yields higher accuracy compared to individual parameters. The proposed method demonstrates the capability to differentiate between sudden and soft falls, aiding medical professionals in identifying the cause of a user’s fall. The experimental results demonstrate that the system achieves an accuracy rate of 91.7% in detecting sudden falls, and this accuracy remains at 86.8% even after incorporating soft falls into the analysis. Consequently, the proposed method proves to be an effective and reliable approach for fall detection.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"252-261"},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140905330","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 : 2024-04-23DOI: 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}
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：