IEEE Journal of Selected Areas in Sensors最新文献_第3页

Robust Beamforming Design for Integrated Sensing and Communication Systems 综合传感与通信系统的鲁棒波束成形设计

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-07-02 DOI: 10.1109/JSAS.2024.3421391

Yongjun Xu;Na Cao;Yi Jin;Haibo Zhang;Chongwen Huang;Qianbin Chen;Chau Yuen

{"title":"Robust Beamforming Design for Integrated Sensing and Communication Systems","authors":"Yongjun Xu;Na Cao;Yi Jin;Haibo Zhang;Chongwen Huang;Qianbin Chen;Chau Yuen","doi":"10.1109/JSAS.2024.3421391","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3421391","url":null,"abstract":"Integrated sensing and communication (ISAC) can improve spectral, energy, and transmission efficiency. To overcome the impact of channel uncertainties, we investigate a robust beamforming design problem for a multiple-input single-output based ISAC system with imperfect channel state information (CSI), where a multiantenna base station (BS) serves multiple wireless users and obtains state information of a point target. Based on bounded CSI error models, a total throughput maximization problem is formulated under the constraints of the minimum rate threshold of each communication user, sensing performance based on Cramér–Rao lower bound thresholds, and the maximum transmit power of the BS. The formulated problem with parameter perturbations belongs to a nonconvex one that is challenging to solve. To address this complexity, an iterative robust beamforming algorithm is designed by employing S-procedure, semidefinite relaxation technique, Schur complementarity conditions, and successive convex approximation. Simulation results demonstrate that the proposed algorithm exhibits better convergence and stronger robustness.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"114-123"},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10582401","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141729937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Point Cloud Densification Based on Scene Flow Estimation and Kalman Refinement 基于场景流估计和卡尔曼细化的点云致密化

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-06-20 DOI: 10.1109/JSAS.2024.3417309

Yufei Que;Luqin Ye;Jie Xie;Jin Zhang;Junzhe Ding;Cheng Wu

{"title":"Point Cloud Densification Based on Scene Flow Estimation and Kalman Refinement","authors":"Yufei Que;Luqin Ye;Jie Xie;Jin Zhang;Junzhe Ding;Cheng Wu","doi":"10.1109/JSAS.2024.3417309","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3417309","url":null,"abstract":"Point cloud densification is an effective measure to alleviate the sparseness of point clouds. In 3-D vision, the positional relationship of multiframe point clouds is applied to point cloud densification research to explain the rationality of the source of supplementary points. Among them, scene flow estimation is effective for dynamic scenes. However, scene flow estimation of long-sequence dynamic point clouds is prone to cumulative positioning errors. In order to solve this problem, this article proposes to correct the scene flow estimation results from a timing perspective based on Kalman filtering. Specifically, the scene flow estimation model is first optimized according to the pyramid structure to improve the reliability of point cloud feature extraction. Then, combined with the temporal relationship of the point clouds in the previous and later frames, the point cloud is reconstructed uniformly to complete the densification of the point cloud. Finally, the densified point cloud is applied to the 3-D detection task. Results on the KITTI 3-D tracking dataset show that the point cloud densification method based on scene flow estimation can effectively improve the performance of LiDAR-only detectors.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"190-197"},"PeriodicalIF":0.0,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10566020","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Deep Nonconnectionist Learning Framework for Industrial Data Modeling 工业数据建模的深度非连接学习框架

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-06-05 DOI: 10.1109/JSAS.2024.3404416

Yongxuan Chen;Dianhui Wang

{"title":"A Deep Nonconnectionist Learning Framework for Industrial Data Modeling","authors":"Yongxuan Chen;Dianhui Wang","doi":"10.1109/JSAS.2024.3404416","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3404416","url":null,"abstract":"Despite the extensive applications of deep neural networks in data modeling filed, there are still some obvious deficiencies for the implementation in modern industrial cases. There are mainly reflected in the following aspects: first, the architectures are difficult to configure; second, the modeling process is time-consuming; third, the training procedure easily falls into the local optimum situation. To overcome these problems, exploring the nonconnectionist learning model has become a popular topic recently. This article proposes a deep nonconnectionist learning model based on kernel principal component regression (KPCR), which is referred to as stacked KPCR (SKPCR). By stacking multiple KPCR modules, a multilayer learning model is constructed by adopting hierarchical feature extraction. In SKPCR, the model structure is determined incrementally and there is only one parameter needed to be configured for each layer. Furthermore, an enhanced learning strategy is designed for alleviating the information loss problem in the training process. An actual industrial case is used to validate the effectiveness, including the prediction performance and modeling efficiency, of our proposed method.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"105-113"},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10549772","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141474932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Tuned Microwave Resonator on Flexible Substrate for Nondestructive Water Content Sensing in Fruits 用于无损检测水果含水量的柔性基底调谐微波谐振器

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-06-04 DOI: 10.1109/JSAS.2024.3409229

Sen Bing;Khengdauliu Chawang;Jung-Chih Chiao

{"title":"A Tuned Microwave Resonator on Flexible Substrate for Nondestructive Water Content Sensing in Fruits","authors":"Sen Bing;Khengdauliu Chawang;Jung-Chih Chiao","doi":"10.1109/JSAS.2024.3409229","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3409229","url":null,"abstract":"This work aims to develop a planar microwave sensor fabricated on a flexible polyimide substrate to monitor the water content of fruits nondestructively. The sensor is based on a planar loop resonator tuned with a concentric metal pad that features improved resonance, compact size, and flexibility to conform to the curved surface of the fruit. The sensing mechanism is to detect electromagnetic resonance that is susceptible to dielectric property changes by water content variations. The robust resonance provides electric fields that penetrate deeper into the fruit tissues, compared with an untuned one, with a sufficient spectral resolution to reach high sensitivity. Experiments were conducted, including long-term continuous water content monitoring and total water content measurements. The sensors demonstrated clear frequency shifting trends when fresh apples became dehydrated, and their initial resonant frequencies indicated total water contents. Simulations were conducted to examine measurement discrepancies induced by inhomogeneous water evaporation and surface curvatures. The feasibility of sensing the watercore defects inside apples was demonstrated with simulations. In addition, the sensor was used to demonstrate the feasibility of measuring water content in potatoes. The promising results show the great potential of the noninvasive and continuous water-content sensor applications in agriculture to study the growth, maturity, anomaly, and storage of fruits and in food processing applications to achieve optimal quality.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"93-104"},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10547410","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141435267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A 24-GHz Frequency-Locked Loop-Based Microwave Microfluidic Sensor for Concentration Detection 用于浓度检测的基于 24 GHz 锁频环的微波微流控传感器

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-04-30 DOI: 10.1109/JSAS.2024.3395424

Hsiu-Che Chang;Chung-Tse Michael Wu;Chao-Hsiung Tseng

{"title":"A 24-GHz Frequency-Locked Loop-Based Microwave Microfluidic Sensor for Concentration Detection","authors":"Hsiu-Che Chang;Chung-Tse Michael Wu;Chao-Hsiung Tseng","doi":"10.1109/JSAS.2024.3395424","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3395424","url":null,"abstract":"This article presents a 24-GHz microfluidic sensor using frequency-locked loop (FLL) technology for detecting liquid concentrations. The sensor, based on FLL, features a microfluidic channel placed over an asymmetrical coplanar waveguide resonator (ACPWR) that functions as a sensing device. For testing purposes, we use ethanol–water mixtures and glucose–water solutions as the liquid under test. Due to the electric field distribution in media with varying dielectric constants, the phase of the signal undergoes different phase deviations. The FLL-based sensor is capable of detecting these phase deviations and, in response, produces a frequency-modulated signal. This signal is subsequently demodulated into a corresponding voltage with the aid of a frequency demodulator, realized through a phase detector. Consequently, the sensor demonstrates the capability to differentiate between tested liquids of varying concentrations and offers a linear response that correlates the output voltage with the liquid concentration. The proposed 24-GHz FLL microfluidic sensor offers advantages, such as cost effective, high sensitivity, and compact size. It has a great possibility to implement this sensor using the system-on-chip technology. As it combined with Internet of Things technologies, it may have a capability of real-time biomedical specimen sensing for daily life.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"20-28"},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10510576","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141078789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stub-Loaded Patch Antenna for Development of High Sensitivity Crack Monitoring Sensor 用于开发高灵敏度裂缝监测传感器的存根负载贴片天线

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-04-29 DOI: 10.1109/JSAS.2024.3394393

Nan-Wei Chen;Chih-Ying Chen;Ren-Rong Guo

{"title":"Stub-Loaded Patch Antenna for Development of High Sensitivity Crack Monitoring Sensor","authors":"Nan-Wei Chen;Chih-Ying Chen;Ren-Rong Guo","doi":"10.1109/JSAS.2024.3394393","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3394393","url":null,"abstract":"This article proposes the use of a wireless sensor developed with a microstrip patch antenna in conjunction with an open-circuited stub for remote, real-time monitoring of crack width expansion. Technically, the open-circuited stub is exploited as a sensing structure with excellent sensitivity, and the crack growth is able to be mechanically mapped to the stub length extension via an incorporation of a mirrored stub structure placed right on top of the open-circuited stub. Thanks to a very strong relationship between the stub input admittance and its electrical length, the operating frequency of the patch is able to be significantly downshifted as the stub is mechanically lengthened (i.e., the crack grows). With the proposed wireless sensing scheme, the crack width expansion can be determined by identifying the dominant frequency component of the sensing signal received at remote data stations in a real-time manner. The sensor operating at 4 GHz was developed for experimental verification and as a demonstration of effectiveness. The experimental results show that the wireless sensor is able to identify the crack expansion of up to 2 mm with a resonant frequency downshift of 110 MHz. Furthermore, the maximum expansion and the finest increment can be simply specified with the sensor operating frequency regime. Moreover, a stable wireless link can be sustained as the patch radiation patterns remain unaffected while crack grows, and the sensor can be reused since the proposed monitoring does not result in any structure destruction or deformation.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"29-35"},"PeriodicalIF":0.0,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10509741","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141078757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive Age of Information Optimization in Rateless Coding-Based Multicast-Enabled Sensor Networks 基于无鼠编码的多播传感器网络中的自适应信息优化时代

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-03-30 DOI: 10.1109/JSAS.2024.3407689

Hung-Chun Lin;Kuang-Hsun Lin;Hung-Yu Wei

{"title":"Adaptive Age of Information Optimization in Rateless Coding-Based Multicast-Enabled Sensor Networks","authors":"Hung-Chun Lin;Kuang-Hsun Lin;Hung-Yu Wei","doi":"10.1109/JSAS.2024.3407689","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3407689","url":null,"abstract":"As the demand for real-time information in Internet of Things and wireless sensor networks (WSN) scenarios grows with the evolution of bandwidth-intensive 5G applications, multicast transmission becomes increasingly vital. This article delves into the significant role of multicast in WSN, exploring a novel perspective of using rateless codes over the traditionally employed hybrid automatic repeat request for eliminating retransmissions in a wireless multicast system. We aim to optimize data freshness, quantified by the age of information (AoI), and analyze strategies to minimize time-average AoI in a multicast environment with diverse channel conditions. Specifically, our policy focuses on optimizing the time-average AoI based on sensor devices' feedback. We transform the problem into a Markov decision process to locate optimal and low-complexity suboptimal policies. We present the first age-minimum scheme for rateless code-based wireless multicast systems. Our numerical simulations reveal that the proposed policies, developed considering unique system structural properties, consistently surpass baseline strategies. We are thus able to preempt updates at the most beneficial time, thereby addressing the issue of the bottleneck device's adverse impact on overall performance.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"73-92"},"PeriodicalIF":0.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10542217","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141430052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Circular Polarized Antennas With Harmonic Radar: Passive Nonlinear Tag Localization 带谐波雷达的圆极化天线：无源非线性标签定位

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-03-18 DOI: 10.1109/JSAS.2024.3378157

Vishal G Yadav;Leya Zeng;Changzhi Li

{"title":"Circular Polarized Antennas With Harmonic Radar: Passive Nonlinear Tag Localization","authors":"Vishal G Yadav;Leya Zeng;Changzhi Li","doi":"10.1109/JSAS.2024.3378157","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3378157","url":null,"abstract":"This research proposes a high performance, low-profile planar design, and demonstration of circularly polarized harmonic antenna arrays for 4 and 8 GHz harmonic radar system, which is equipped, and the antenna's circular polarization (CP) performance is tested using a passive nonlinear harmonic tag (snowflake) in a noisy environment. This work mainly concentrates on investigation of the wave polarization (circular), gain estimation and impedance matching of the antenna arrays that will be potentially assembled to the second-order harmonic radar system operating at 4 and 8 GHz, which plays a critical role in 2-D tag localization and post processing methods. The passive snowflake tag design is implemented in the simulation to determine the current distribution and gain plot patterns in comparison to a classic dipole antenna tag structure. In experiments: a combination of fundamental circular polarized (left-hand) antennas were demonstrated to find axial ratio \u0000<inline-formula><tex-math>$ leq $</tex-math></inline-formula>\u0000 3 dB band. A novel tag 2-D localization measurement, combination of CP harmonic antenna arrays is utilized to perform and obtain the circular polarized received signal power in dBm versus angle rotation by every 10° on a rotating platform setup. Finally, the wireless tag tracking result is achieved by using the designed circularly polarized antennas and the passive nonlinear tag orientation setup.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"9-19"},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10474130","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140641639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Iterative Vector-Based Localization in a Large Heterogeneous Sensor Network 大型异构传感器网络中基于矢量的迭代定位

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-03-07 DOI: 10.1109/JSAS.2024.3397769

Insung Kang;Haewoon Nam

{"title":"Iterative Vector-Based Localization in a Large Heterogeneous Sensor Network","authors":"Insung Kang;Haewoon Nam","doi":"10.1109/JSAS.2024.3397769","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3397769","url":null,"abstract":"This article proposes a novel iterative vector-based localization method in a large heterogeneous sensor network, where a subset of nodes possesses the capability to measure both distance and angle information, while the others are only limited to distance measurements. Unlike conventional vector-based positioning methods that assume all nodes can measure both distance and angle, our approach tackles a more realistic scenario where some nodes are limited to distance-only measurements. To address the challenges of the node localization in a heterogeneous sensor network, the proposed positioning method calculates vector information between the nodes that are not directly communicated and aligns it with a reference coordinate. In addition, the proposed method employs an iterative calculation, such as least-squares minimization, thereby achieving high positioning accuracy. Simulation results demonstrate that the proposed positioning method outperforms the conventional distance-based positioning method in environments with low angle measurement errors, exhibiting up to 44% higher positioning accuracy. Furthermore, the proposed positioning method shows 24% higher positioning accuracy compared with the conventional vector-based positioning method.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"60-72"},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521718","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141292483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0 MASTER：面向工业 4.0 的无服务器边缘计算环境中基于机器学习的冷启动延迟预测框架

IEEE Journal of Selected Areas in Sensors Pub Date : 2024-03-02 DOI: 10.1109/JSAS.2024.3396440

Muhammed Golec;Sukhpal Singh Gill;Huaming Wu;Talat Cemre Can;Mustafa Golec;Oktay Cetinkaya;Felix Cuadrado;Ajith Kumar Parlikad;Steve Uhlig

{"title":"MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0","authors":"Muhammed Golec;Sukhpal Singh Gill;Huaming Wu;Talat Cemre Can;Mustafa Golec;Oktay Cetinkaya;Felix Cuadrado;Ajith Kumar Parlikad;Steve Uhlig","doi":"10.1109/JSAS.2024.3396440","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3396440","url":null,"abstract":"The integration of serverless edge computing and the Industrial Internet of Things (IIoT) has the potential to optimize industrial production. However, cold start latency is one of the main challenges in this area, resulting in resource waste. To address this issue, we propose a new machine learning-based resource management framework called MASTER which utilizes an extreme gradient boosting (XGBoost) model to predict the cold start latency for Industry 4.0 applications for performance optimization. Furthermore, we created a new cold start dataset using an IIoT scenario (i.e. predictive maintenance) to validate the proposed MASTER framework in serverless edge computing environments. We have evaluated the performance of the MASTER framework using a real-world serverless platform, Google Cloud Platform for single-step prediction (SSP) and multiple-step prediction (MSP) operations and compared it with existing frameworks that used deep deterministic policy gradient (DDPG) and long short-term memory (LSTM) models. The experimental results show that the XGBoost-based resource management framework is the most successful model in predicting cold start with mean absolute percentage error (MAPE) values of 0.23 in SSP and 0.12 in MSP. It has been also identified that the Linear Regression model (utilized in the MASTER framework) has the least computational time (0.03 seconds) as compared to other deep learning and machine learning models considered in this work. Finally, we compare the energy consumption and \u0000<inline-formula><tex-math>$text{CO}_{2}$</tex-math></inline-formula>\u0000 emissions of all models to emphasize resource awareness.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"36-48"},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517641","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141084810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0