Intelligent and Converged Networks最新文献_第7页

Emma: An accurate, efficient, and multi-modality strategy for autonomous vehicle angle prediction Emma：一种准确、高效、多模态的自动驾驶汽车角度预测策略

Intelligent and Converged Networks Pub Date : 2023-03-01 DOI: 10.23919/ICN.2023.0004

Keqi Song;Tao Ni;Linqi Song;Weitao Xu

{"title":"Emma: An accurate, efficient, and multi-modality strategy for autonomous vehicle angle prediction","authors":"Keqi Song;Tao Ni;Linqi Song;Weitao Xu","doi":"10.23919/ICN.2023.0004","DOIUrl":"10.23919/ICN.2023.0004","url":null,"abstract":"Autonomous driving and self-driving vehicles have become the most popular selection for customers for their convenience. Vehicle angle prediction is one of the most prevalent topics in the autonomous driving industry, that is, realizing real-time vehicle angle prediction. However, existing methods of vehicle angle prediction utilize only single-modal data to achieve model prediction, such as images captured by the camera, which limits the performance and efficiency of the prediction system. In this paper, we present Emma, a novel vehicle angle prediction strategy that achieves multi-modal prediction and is more efficient. Specifically, Emma exploits both images and inertial measurement unit (IMU) signals with a fusion network for multi-modal data fusion and vehicle angle prediction. Moreover, we design and implement a few-shot learning module in Emma for fast domain adaptation to varied scenarios (e.g., different vehicle models). Evaluation results demonstrate that Emma achieves overall 97.5% accuracy in predicting three vehicle angle parameters (yaw, pitch, and roll), which outperforms traditional single-modalities by approximately 16.7%–36.8%. Additionally, the few-shot learning module presents promising adaptive ability and shows overall 79.8% and 88.3% accuracy in 5-shot and 10-shot settings, respectively. Finally, empirical results show that Emma reduces energy consumption by 39.7% when running on the Arduino UNO board.","PeriodicalId":100681,"journal":{"name":"Intelligent and Converged Networks","volume":"4 1","pages":"41-49"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/9195266/10134533/10134535.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48516124","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

Cover 封面

Intelligent and Converged Networks Pub Date : 2023-03-01 DOI: 10.23919/TUP-ICN.2023.10134540

引用次数: 0

Optimal transmit beamforming for near-field integrated sensing and wireless power transfer systems 近场集成传感和无线电力传输系统的最佳发射波束成形

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0028

Ping Sun;Haibo Dai;Baoyun Wang

引用次数: 2

Enhancing active reconfigurable intelligent surface 增强主动可重构智能表面

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0029

Muhammad I. Khalil

{"title":"Enhancing active reconfigurable intelligent surface","authors":"Muhammad I. Khalil","doi":"10.23919/ICN.2022.0029","DOIUrl":"10.23919/ICN.2022.0029","url":null,"abstract":"A Reconfigurable Intelligent Surface (RIS) panel comprises many independent Reflective Elements (REs). One possible way to implement an RIS is to use a binary passive load impedance connected to an antenna element to achieve the modulation of reflected radio waves. Each RE reflects incoming waves (incident signal) by using on/off modulation between two passive loads and adjusting its phase using a Phase Shifter (PS). However, this modulation process reduces the amplitude of the reflected output signal to less than unity. Therefore, recent RIS works have employed Reflection Amplifiers (RAs) to compensate for the losses incurred during the modulation process. However, these systems only improve the reflection coefficient for a single modulation state, resulting in suboptimal RE efficacy. Thus, this paper proposes a strategy for optimising RE by continuously activating the RA regardless of the switching load state. The performance of the proposed scheme is evaluated in two scenarios: (1) In the first scenario (Sc1), the RA only operates to compensate for high-impedance loads, and (2) in the second scenario (Sc2), the RA runs continuously regardless of the RE loads. To benchmark the performance of Sc1 and Sc2, various metrics are compared, including signal-to-noise ratio, insertion loss, noise figure, communication range, and power-added efficiency. Numerical examples are provided to demonstrate the effectiveness of the proposed scheme. It is found that the proposed system in Sc2 leads to better overall performance compared to Sc1 due to the increased gain of the RIS reflection.","PeriodicalId":100681,"journal":{"name":"Intelligent and Converged Networks","volume":"3 4","pages":"351-363"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/9195266/10026509/10026524.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44631668","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: 2

Combining random forest and graph wavenet for spatial-temporal data prediction 随机森林与图波网络相结合的时空数据预测

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0024

Chong Chen;Yanbo Xu;Jixuan Zhao;Lulu Chen;Yaru Xue

{"title":"Combining random forest and graph wavenet for spatial-temporal data prediction","authors":"Chong Chen;Yanbo Xu;Jixuan Zhao;Lulu Chen;Yaru Xue","doi":"10.23919/ICN.2022.0024","DOIUrl":"10.23919/ICN.2022.0024","url":null,"abstract":"The prosperity of deep learning has revolutionized many machine learning tasks (such as image recognition, natural language processing, etc.). With the widespread use of autonomous sensor networks, the Internet of Things, and crowd sourcing to monitor real-world processes, the volume, diversity, and veracity of spatial-temporal data are expanding rapidly. However, traditional methods have their limitation in coping with spatial-temporal dependencies, which either incorporate too much data from weakly connected locations or ignore the relationships between those interrelated but geographically separated regions. In this paper, a novel deep learning model (termed RF-GWN) is proposed by combining Random Forest (RF) and Graph WaveNet (GWN). In RF-GWN, a new adaptive weight matrix is formulated by combining Variable Importance Measure (VIM) of RF with the long time series feature extraction ability of GWN in order to capture potential spatial dependencies and extract long-term dependencies from the input data. Furthermore, two experiments are conducted on two real-world datasets with the purpose of predicting traffic flow and groundwater level. Baseline models are implemented by Diffusion Convolutional Recurrent Neural Network (DCRNN), Spatial-Temporal GCN (ST-GCN), and GWN to verify the effectiveness of the RF-GWN. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) are selected as performance criteria. The results show that the proposed model can better capture the spatial-temporal relationships, the prediction performance on the METR-LA dataset is slightly improved, and the index of the prediction task on the PEMS-BAY dataset is significantly improved. These improvements are extended to the groundwater dataset, which can effectively improve the prediction accuracy. Thus, the applicability and effectiveness of the proposed model RF-GWN in both traffic flow and groundwater level prediction are demonstrated.","PeriodicalId":100681,"journal":{"name":"Intelligent and Converged Networks","volume":"3 4","pages":"364-377"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/9195266/10026509/10026523.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48730157","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: 1

Multi-features fusion for short-term photovoltaic power prediction 基于多特征融合的短期光伏功率预测

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0025

Ming Ma;Xiaorun Tang;Qingquan Lv;Jun Shen;Baixue Zhu;Jinqiang Wang;Binbin Yong

{"title":"Multi-features fusion for short-term photovoltaic power prediction","authors":"Ming Ma;Xiaorun Tang;Qingquan Lv;Jun Shen;Baixue Zhu;Jinqiang Wang;Binbin Yong","doi":"10.23919/ICN.2022.0025","DOIUrl":"10.23919/ICN.2022.0025","url":null,"abstract":"In recent years, in order to achieve the goal of “carbon peaking and carbon neutralization”, many countries have focused on the development of clean energy, and the prediction of photovoltaic power generation has become a hot research topic. However, many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation, and they rarely consider the multi-features fusion methods for power prediction. This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China, and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation. Next, the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets. Finally, traditional time series prediction methods, such as Recurrent Neural Network (RNN), Convolution Neural Network (CNN) combined with eXtreme Gradient Boosting (XGBoost), are applied to study the impact of different feature fusion methods on power prediction. The results show that the prediction accuracy of Long Short-Term Memory (LSTM), stacked Long Short-Term Memory (stacked LSTM), Bi-directional LSTM (Bi-LSTM), Temporal Convolutional Network (TCN), and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features. Therefore, the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.","PeriodicalId":100681,"journal":{"name":"Intelligent and Converged Networks","volume":"3 4","pages":"311-324"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/9195266/10026509/10026522.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44725396","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: 1

IoT data cleaning techniques: A survey 物联网数据清理技术:调查

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0026

Xiaoou Ding;Hongzhi Wang;Genglong Li;Haoxuan Li;Yingze Li;Yida Liu

引用次数: 2

Joint association and beamforming optimization in reconfigurable intelligent surface-enhanced user-centric networks 可重构智能表面增强用户中心网络中的联合关联和波束成形优化

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/ICN.2022.0027

Ye Yao;Zhong Tian;Zhengchuan Chen;Min Wang;Yunjian Jia

{"title":"Joint association and beamforming optimization in reconfigurable intelligent surface-enhanced user-centric networks","authors":"Ye Yao;Zhong Tian;Zhengchuan Chen;Min Wang;Yunjian Jia","doi":"10.23919/ICN.2022.0027","DOIUrl":"10.23919/ICN.2022.0027","url":null,"abstract":"Fully coordinated Cell-Free (CF) networks can alleviate the Inter-Cell Interference (ICI) for the cell-edge users in cellular networks. Due to the complex topology of the association between the Access Points (APs) and the users in CF networks, it is challenging to deploy CF networks in practical scenarios. In order to make CF networks feasible, we introduce User-Centric (UC) networks enabling each user served by a limited number of APs. As a low-cost and energy-efficient technology, Reconfigurable Intelligent Surface (RIS) can be embedded in UC networks to further improve the system performance. First, we provide a brief survey on the prior works in UC networks for clear comprehension. Then, we formulate a Spectral Efficiency (SE) maximization problem for RIS-enhanced UC networks. For solving the non-convex problem, we divide it into three subproblems and propose a joint optimization framework for optimizing AP-user association, active beamforming of multiple antennas at the APs, and the passive beamforming of the RIS. Besides, a channel gain based association method coupled with the design of RIS is proposed to construct a dynamic and efficient association. The subproblems about optimizing active and passive beamforming are solved with the fractional programming. Simulation results show that the proposed joint optimization framework for RIS-enhanced UC networks can obtain good SE compared with other benchmark schemes.","PeriodicalId":100681,"journal":{"name":"Intelligent and Converged Networks","volume":"3 4","pages":"340-350"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/9195266/10026509/10026525.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43171651","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

Total Contents 全部内容

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/TUP-ICN.2022.10026517

引用次数: 0

Cover 封面

Intelligent and Converged Networks Pub Date : 2022-12-01 DOI: 10.23919/TUP-ICN.2022.10026514

引用次数: 0