Refine Search

New Search

Results: 4,920,318

(searched for: publisher_group_id:50)
Save to Scifeed
Page of 98,407
Articles per Page
by
Show export options
  Select all
, Taneli Riihonen, Sahan Damith Liyanaarachchi, Mikko Heino, Nuria González-Prelcic, Mikko Valkama
Abstract:
In this article, we study the joint communication and sensing (JCAS) paradigm in the context of millimeter-wave (mm-wave) mobile communication networks. We specifically address the JCAS challenges stemming from the full-duplex operation and from the co-existence of multiple simultaneous beams for communications and sensing purposes. To this end, we first formulate and solve beamforming optimization problems for hybrid beamforming based multiuser multiple-input and multiple-output JCAS systems. The cost function to be maximized is the beamformed power at the sensing direction while constraining the beamformed power at the communications directions, suppressing interuser interference and cancelling full-duplexing related self-interference (SI). We then also propose new transmitter and receiver beamforming solutions for purely analog beamforming based JCAS systems that maximize the beamforming gain at the sensing direction while controlling the beamformed power at the communications direction(s), cancelling the SI as well as eliminating the potential reflection from the communication direction and optimizing the combined radar pattern (CRP). Both closed-form and numerical optimization based formulations are provided. We analyze and evaluate the performance through extensive simulations, and show that substantial gains and benefits in terms of radar transmit gain, CRP, and SI suppression can be achieved with the proposed beamforming methods.
, Mingyao Xia, Xingyue Guo
Abstract:
Partial-structure-oriented work-energy theorem (WET) governing the work-energy transformation process of Yagi-Uda array antennas is derived. Driving power as the source to sustain a steady work-energy transformation is introduced. Employing WET and driving power, the essential difference between the working mechanisms of scattering objects and Yagi-Uda array antennas is revealed. The difference exposes that the conventional characteristic mode theory (CMT) for scattering objects cannot be directly applied to Yagi-Uda array antennas. Under WET framework, this paper proposes a generalized CMT for Yagi-Uda antennas. By orthogonalizing driving power operator (DPO), the WET-based CMT can construct a set of energy-decoupled characteristic modes (CMs) for an objective Yagi-Uda antenna, and then can provide an effective modal analysis for the Yagi-Uda antenna. In addition, a uniform interpretation for the physical meaning of the characteristic values / modal significances (MSs) of metallic, material, and metal-material composite Yagi-Uda antennas is also obtained by employing the WET-based modal decomposition and the field-current interaction expression of driving power.
Abstract:
Taking a cue from the Internet of Things, the Internet of Bodies (IoB) can be defined as a network of smart objects placed in, on, and around the human body, allowing for intra- and inter-body communications. This position paper aims to provide a glimpse into the opportunities created by implantable, injectable, ingestible, and wearable IoB devices. The paper starts with a thorough discussion of application-specific design goals, technical challenges, and enabling of communication standards. We discuss the reason that the highly radiative nature of radio frequency (RF) systems results in inefficient systems due to over-extended coverage that causes interference and becomes susceptible to eavesdropping. Body channel communication (BCC) presents an attractive, alternative wireless technology by inherently coupling signals to the human body, resulting in highly secure and efficient communications. The conductive nature of body tissues yields a better channel quality, while the BCC's operational frequency range (1-100 kHz) eliminates the need for radio front-ends. State-of-the-art BCC transceivers can reach several tens of Mbps data rates at pJ/b energy efficiency levels that support IoB devices and applications. Furthermore, as the cyber and biological worlds meet, security risks and privacy concerns take center stage, leading to a discussion of the multi-faceted legal, societal, ethical, and political issues related to technology governance.
, Taneli Riihonen, Sahan Damith Liyanaarachchi, Mikko Heino, Nuria González-Prelcic, Mikko Valkama
Abstract:
In this article, we study the joint communication and sensing (JCAS) paradigm in the context of millimeter-wave (mm-wave) mobile communication networks. We specifically address the JCAS challenges stemming from the full-duplex operation and from the co-existence of multiple simultaneous beams for communications and sensing purposes. To this end, we first formulate and solve beamforming optimization problems for hybrid beamforming based multiuser multiple-input and multiple-output JCAS systems. The cost function to be maximized is the beamformed power at the sensing direction while constraining the beamformed power at the communications directions, suppressing interuser interference and cancelling full-duplexing related self-interference (SI). We then also propose new transmitter and receiver beamforming solutions for purely analog beamforming based JCAS systems that maximize the beamforming gain at the sensing direction while controlling the beamformed power at the communications direction(s), cancelling the SI as well as eliminating the potential reflection from the communication direction and optimizing the combined radar pattern (CRP). Both closed-form and numerical optimization based formulations are provided. We analyze and evaluate the performance through extensive simulations, and show that substantial gains and benefits in terms of radar transmit gain, CRP, and SI suppression can be achieved with the proposed beamforming methods.
Abstract:
Taking a cue from the Internet of Things, the Internet of Bodies (IoB) can be defined as a network of smart objects placed in, on, and around the human body, allowing for intra- and inter-body communications. This position paper aims to provide a glimpse into the opportunities created by implantable, injectable, ingestible, and wearable IoB devices. The paper starts with a thorough discussion of application-specific design goals, technical challenges, and enabling of communication standards. We discuss the reason that the highly radiative nature of radio frequency (RF) systems results in inefficient systems due to over-extended coverage that causes interference and becomes susceptible to eavesdropping. Body channel communication (BCC) presents an attractive, alternative wireless technology by inherently coupling signals to the human body, resulting in highly secure and efficient communications. The conductive nature of body tissues yields a better channel quality, while the BCC's operational frequency range (1-100 kHz) eliminates the need for radio front-ends. State-of-the-art BCC transceivers can reach several tens of Mbps data rates at pJ/b energy efficiency levels that support IoB devices and applications. Furthermore, as the cyber and biological worlds meet, security risks and privacy concerns take center stage, leading to a discussion of the multi-faceted legal, societal, ethical, and political issues related to technology governance.
IEEE Transactions on Plasma Science, Volume 49, pp 2624-2624; https://doi.org/10.1109/tps.2021.3111670

Abstract:
Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
, Mirko van der Baan
IEEE Transactions on Geoscience and Remote Sensing, pp 1-11; https://doi.org/10.1109/tgrs.2021.3110303

Abstract:
Ground-roll attenuation is very challenging because of its high amplitudes and overlapping frequency content with desired signals. A particular challenge is to recover weak reflections underneath strong masking ground-roll. We propose a dual-filter bank setup combined with two convolutional neural networks (CNNs) to realize ground-roll attenuation. The rationale for using a dual-filter bank strategy is that it permits using two CNNs with different input kernel sizes and different complexities to recognize and extract broad-scale (low-wavelength) and narrow-scale (high-wavelength) features separately. We also apply a frequency filter to create a preliminary separation between the signal and the noise. In addition, we use a radial trace transform that focuses desired signal to a smaller area, facilitating separation of the reflections and ground-roll and accelerating training. The network training strategy combines synthetic and field data examples, in addition to noise injection to augment the number of available training samples. Tests on synthetic and field datasets show that the proposed strategy achieves superior ground-roll attenuation compared with standard methods, even in the case of data with irregular spatial spacing or ground-roll characteristics not contained in the training data.
IEEE Transactions on Plasma Science, Volume 49; https://doi.org/10.1109/tps.2021.3111929

Abstract:
Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
Aqsa Rashid, Asif Masood, Haider Abbas, Yin Zhang
Abstract:
Public Key Infrastructure (PKI) has been considered to be an enabler of secure communication, while, due to its complex and centralized design, there have been instances in the past for Certification Authority's (CA) misbehaving and publishing rogue certificates for targeted attacks. This research aims to present a blockchain-based mechanism that lays down a concrete foundation for creating a transparent and secure blockchain-based mechanism for the issuance and management of digital certificates that enables prevention against CA misbehaving. A prototype is deployed and tested on the Ethereum test network, and the results are made publicly available for verification and validation. As a result, the proposed Ethereum blockchain-based PKI mechanism enables secure, transparent, and auditable issuance and management of digital certificates together with the solution of Sybil, Spoofing, and Man-in-the-Middle (MITM) attacks.
, Yanhong Zhou, Peng Liu, ,
IEEE Transactions on Neural Networks and Learning Systems, pp 1-7; https://doi.org/10.1109/tnnls.2021.3110885

Abstract:
Current state-of-the-art class-imbalanced loss functions for deep models require exhaustive tuning on hyperparameters for high model performance, resulting in low training efficiency and impracticality for nonexpert users. To tackle this issue, a parameter-free loss (PF-loss) function is proposed, which works for both binary and multiclass-imbalanced deep learning for image classification tasks. PF-loss provides three advantages: 1) training time is significantly reduced due to NO tuning on hyperparameter(s); 2) it dynamically pays more attention on minority classes (rather than outliers compared to the existing loss functions) with NO hyperparameters in the loss function; and 3) higher accuracy can be achieved since it adapts to the changes of data distribution in each mini-batch instead of the fixed hyperparameters in the existing methods during training, especially when the data are highly skewed. Experimental results on some classical image datasets with different imbalance ratios (IR, up to 200) show that PF-loss reduces the training time down to 1/148 of that spent by compared state-of-the-art losses and simultaneously achieves comparable or even higher accuracy in terms of both G-mean and area under receiver operating characteristic (ROC) curve (AUC) metrics, especially when the data are highly skewed.
Shoma Nishibori, Tutomu Murase,
IEEE Internet of Things Journal, pp 1-1; https://doi.org/10.1109/jiot.2021.3112711

Abstract:
As the Internet of Things (IoT) has become a widespread phenomenon, promising sensor applications at the nanoscale have begun to emerge. One example is imaging via distributed massive nanoscale nodes (NSNs), which can be used to implement “invisible surveillance cameras” by, for example, painting liquids containing nanoscale sensors onto walls. This imaging method requires periodic data transfer from thousands of NSNs to a data collection node (DCN). An essential technique for handling such transfers is the media access control (MAC) protocol. However, existing protocols cannot support periodic transfer from numerous NSNs because of inefficient communication caused by a large amount of headers in the packets. In this paper, we introduce an original MAC protocol and discuss its capability in terms of implementing imaging applications. The proposed protocol applies a time-division access feature to reduce the amount of headers and a two-layered protocol to enable simultaneous transmission among nodes. Slot assignment is an essential function in time-division access and requires communication among nodes. Unlike existing methods, our simple approach enables communication by exploiting the unique features of the focused application. The results of the numerical simulation reveal that the proposed MAC protocol allows for periodic imaging with more than three thousand nodes and produces high-quality images very close to those obtained using ideal communication. These results are achieved by employing an original design framework to determine appropriate key parameters, such as number of clusters and frame rate.
Xian Wu, Chen Li, Shi-Min Hu,
IEEE Transactions on Image Processing, pp 1-1; https://doi.org/10.1109/tip.2021.3108023

Abstract:
Human pose transfer has been becoming one of the emerging research topics in recent years. However, state-of-the-art results are still far from satisfactory. One main reason is that these end-to-end methods are often blindly trained without the semantic understanding of its content. In this paper, we propose a novel method for human pose transfer with consideration of the semantic part-based representation of a human. In particular, we propose to segment the human body into multiple parts, and each of them represents a semantic region of a human. With the proposed part-based layer generators, a high-quality result is guaranteed for each local semantic region. We design a three-stage hierarchical framework to fuse local representations into the final result in a coarse-to-fine manner, which provides adaptive attention for global consistency and local details, respectively. Via exploiting spatial guidance from 3D human model through the framework, our method can naturally handle the ambiguity of self-occlusions which always causes artifacts in previous methods. With semantic-aware and spatial-aware representations, our method outperforms previous approaches quantitatively and qualitatively in better handling self-occlusions, fine detail preservation/synthesis and a higher resolution result.
, Mingyao Xia, Xingyue Guo
Abstract:
Partial-structure-oriented work-energy theorem (WET) governing the work-energy transformation process of Yagi-Uda array antennas is derived. Driving power as the source to sustain a steady work-energy transformation is introduced. Employing WET and driving power, the essential difference between the working mechanisms of scattering objects and Yagi-Uda array antennas is revealed. The difference exposes that the conventional characteristic mode theory (CMT) for scattering objects cannot be directly applied to Yagi-Uda array antennas. Under WET framework, this paper proposes a generalized CMT for Yagi-Uda antennas. By orthogonalizing driving power operator (DPO), the WET-based CMT can construct a set of energy-decoupled characteristic modes (CMs) for an objective Yagi-Uda antenna, and then can provide an effective modal analysis for the Yagi-Uda antenna. In addition, a uniform interpretation for the physical meaning of the characteristic values / modal significances (MSs) of metallic, material, and metal-material composite Yagi-Uda antennas is also obtained by employing the WET-based modal decomposition and the field-current interaction expression of driving power.
Jingzhou Chen,
IEEE Transactions on Geoscience and Remote Sensing, pp 1-13; https://doi.org/10.1109/tgrs.2021.3111117

Abstract:
Hierarchical multilabel classification (HMC) assigns multiple labels to each instance with the labels organized under hierarchical relations. In ship classification in remote sensing images, depending on the expert knowledge and image quality, the same type of ships in different remote sensing images may be annotated with different class labels from coarse to fine levels such as merchant ship (MS) or container ship (CTS). In this article, we propose a novel deep network with two output channels and their associated loss functions to learn an HMC classifier using samples labeled at different levels in the hierarchy. In the proposed network, a hierarchy and exclusion (HEX) graph is introduced to model the label hierarchy, which satisfies hierarchical constraints by encoding semantic relations between any two labels. The output nodes of the first channel are organized according to the HEX graph, and its corresponding probabilistic classification loss is built to reflect the hierarchical structure of the HEX graph. On the other hand, the output nodes of the second channel only represent the finest grained (last level in the hierarchy) classes, and its multiclass cross-entropy loss is designed to enhance the discriminative power of the HMC classifier on the last level labels, which is also compatible with constraints in the HEX graph. The combination of these two losses from two output channels can effectively transfer the hierarchical information of ship taxonomy during network training. Experimental results on two commonly used ship datasets demonstrate that the proposed method outperforms the state-of-the-art HMC approaches, and is especially advantageous when trained with fewer fine-grained samples.
Yule Duan, , Tao Wang
IEEE Transactions on Geoscience and Remote Sensing, pp 1-15; https://doi.org/10.1109/tgrs.2021.3110855

Abstract:
Recently, the sparse representation (SR)-based graph embedding method has been extensively used in feature extraction (FE) tasks, but it is hard to reveal the complex manifold structure and multivariate relationship of samples in the hyperspectral image (HSI). Meanwhile, the small size sample problem in HSI data also limits the performance of the traditional SR approach. To tackle this problem, this article develops a new semisupervised FE algorithm called a geodesic-based sparse manifold hypergraph (GSMH). The presented method first utilizes the geodesic distance to measure the nonlinear similarity between samples lying on manifold space and further constructs the manifold neighborhood of each sample. Then, a geodesic-based neighborhood SR (GNSR) model is designed to explore the multivariate sparse correlations of different manifold neighborhoods. Considering the multivariate sparse manifold correlations among samples, a pair of semisupervised hypergraphs (HGs) is constructed to effectively incorporate the labeled and unlabeled training information in the embedding process and obtain the nonlinear discriminative feature representation for HSI. Experimental results on three HSI datasets indicate that the proposed method not only achieves satisfying FE performance with limited labeled training samples but also shows superiority compared with other state-of-the-art methods.
IEEE Transactions on Geoscience and Remote Sensing, pp 1-15; https://doi.org/10.1109/tgrs.2021.3108751

Abstract:
Here, we present an enhanced algorithm to correct interferometric synthetic aperture radar (InSAR) phase unwrapping errors by incorporating iterative spatial bridging between islands and phase closure among interferograms. We use rapid repeat airborne synthetic aperture radar acquisitions from NASA's airborne uninhabited aerial vehicle synthetic aperture radar (UAVSAR) instrument to estimate short-term changes in water level within coastal wetlands from a stack of consecutive interferograms acquired with very short temporal separation (~30 min). The algorithm is applied to six consecutive UAVSAR images collected in tidal wetlands of the Wax Lake Delta, Louisiana, USA. Validation of our water level change retrievals with in situ field observations was conclusive with high correlation and an RMSE generally smaller than 3 cm. Comparison of our algorithm with other phase unwrapping error correction methods shows significant improvement (30%-35% increase in the number of correctly unwrapped pixels) when applied to rapid changes in water level. The set of corrections presented in this work enables measurement of water level change in deltas and other areas where tides drive highly dynamic flooding of inland vegetated areas. Although demonstrated for water level change, the method is applicable to other InSAR datasets with large spatial gradients or observed discontinuities between coherent but spatially isolated areas.
, Jin Pan, Deqiang Yang, Yong-Xin Guo
IEEE Transactions on Antennas and Propagation, pp 1-1; https://doi.org/10.1109/tap.2021.3111290

Abstract:
The homogenization theory for stacked dielectric resonator antennas (DRAs) on planar and curved ground planes is investigated. The commonly used static capacitance models are re-evaluated more comprehensively to reveal and analyze their deficiencies. For improvement, the effective medium theory is introduced to provide superior empirical equations. Furthermore, a resonance-based homogenization methodology with explicit physical intension is developed. All the presented methods are tested with sets of DRA samples where the layer thickness, permittivity ratio, stacking order, and resonant mode are under consideration. Performances of each method are discussed based on error analysis.
, Wenhan Zhao, , Bin Li, Xiaobing Sun
IEEE Transactions on Neural Networks and Learning Systems, pp 1-10; https://doi.org/10.1109/tnnls.2021.3108050

Abstract:
Controlling and processing of time-variant problem is universal in the fields of engineering and science, and the discrete-time recurrent neural network (RNN) model has been proven as an effective method for handling a variety of discrete time-variant problems. However, such model usually originates from the discretization research of continuous time-variant problem, and there is little research on the direct discretization method. To address the aforementioned problem, this article introduces a novel discrete-time RNN model for solving the discrete time-variant problem in a pioneering manner. Specifically, a discrete time-variant nonlinear system, which originates from the mathematical modeling of serial robot manipulator, is presented as a target problem. For solving the problem, first, the technique of second-order Taylor expansion is used to deal with the discrete time-variant nonlinear system, and the novel discrete-time RNN model is proposed subsequently. Second, the theoretical analyses are investigated and developed, which shows the convergence and precision of the proposed discrete-time RNN model. Furthermore, three distinct numerical experiments verify the excellent performance of the proposed discrete-time RNN model. In addition, a robot manipulator example further verifies the effectiveness and practicability of the proposed novel discrete-time RNN model.
, Xingmeng Lu, Yanjie Yin, Weixing Yang,
IEEE Transactions on Geoscience and Remote Sensing, pp 1-12; https://doi.org/10.1109/tgrs.2021.3110772

Abstract:
Recently, a novel design scheme of low-earth-orbit spaceborne mini-synthetic aperture radar (MiniSAR) system is proposed to exploit the integrated transceiver to collect the azimuth periodic block sampling data by using alternated transmitting and receiving operations. Because such collected data are downsampled, the images recovered by the typical matched filtering (MF)-based methods have the problems of obvious azimuth ambiguities, ghosts, and energy dispersion. To find a suitable method for such data, with the help of sparse signal processing technique, we first introduce sparse synthetic aperture radar (SAR) imaging with ℓ₁-norm regularization-based approximated observation method to recover the large-scale considered scene. To further improve the imaging performance, a novel approximated observation unambiguous sparse SAR imaging method via ℓ $_{2,1}$ -norm is proposed. Compared with ℓ₁-norm-based method, the recovered image by the proposed one achieves better imaging quality with reduced azimuth ambiguities and ghosts. Experimental results on simulated and real data validate the proposed method.
Liyuan Ren, , Jianguo Zhou
IEEE Transactions on Instrumentation and Measurement, pp 1-1; https://doi.org/10.1109/tim.2021.3112792

Abstract:
Steel wire rope (SWR) is widely utilized in scenarios such as goods transmission, elevators, and dams. However, SWR defects are unavoidable, so the surface health condition of SWRs should be tested to avoid accidents. After introducing the magnetic flux leakage (MFL) method to detect local flaws (LFs) in multiple channels, we find that shaking noise, like strand noise, is inevitable. Although shaking noise is pointed out, the representation of shaking noise and its phenomenological model are not studied. This paper is focused on analyzing the influence of shaking noise on LF detection. The mathematical model of shaking noise is constructed based on its relation to lift-off distance, and shaking noise is simulated to test the performance of shaking noise elimination (SNE) methods. Then, a new SNE method, which retrieves the spatial information of multi-channel MFL signals, is proposed to filter out shaking noise. In comparison with the existing SNE methods, the proposed method improves LF detection in the presence of strong shaking noise. Furthermore, this paper also raises awareness of the effects of lift-off distance on LF detection.
, Patrick Ebel,
IEEE Transactions on Geoscience and Remote Sensing, pp 1-10; https://doi.org/10.1109/tgrs.2021.3109957

Abstract:
Most change detection (CD) methods assume that prechange and postchange images are acquired by the same sensor. However, in many real-life scenarios, e.g., natural disasters, it is more practical to use the latest available images before and after the occurrence of incidence, which may be acquired using different sensors. In particular, we are interested in the combination of the images acquired by optical and synthetic aperture radar (SAR) sensors. SAR images appear vastly different from the optical images even when capturing the same scene. Adding to this, CD methods are often constrained to use only target image-pair, no labeled data, and no additional unlabeled data. Such constraints limit the scope of traditional supervised machine learning and unsupervised generative approaches for multisensor CD. The recent rapid development of self-supervised learning methods has shown that some of them can even work with only few images. Motivated by this, in this work, we propose a method for multisensor CD using only the unlabeled target bitemporal images that are used for training a network in a self-supervised fashion by using deep clustering and contrastive learning. The proposed method is evaluated on four multimodal bitemporal scenes showing change, and the benefits of our self-supervised approach are demonstrated. Code is available at https://gitlab.lrz.de/ai4eo/cd/-/tree/main/sarOpticalMultisensorTgrs2021.
, Jiao Liu, , Zongqing Chen, ,
IEEE Transactions on Geoscience and Remote Sensing, pp 1-12; https://doi.org/10.1109/tgrs.2021.3110060

Abstract:
Remote sensing image scene classification aims to automatically assign semantic labels for remote sensing images. Recently, to overcome the distribution discrepancy of training data and test data, domain adaptation has been applied to remote sensing image scene classification. Most domain adaptation approaches usually explore transferability under the assumption that the source domain and target domain have common classes. However, in real applications, new categories may appear in the target domain. Besides, only considering the transferability will degrade the classification performance due to the strong interclass similarity of remote sensing images. In this article, we present an open set domain adaptation algorithm via exploring transferability and discriminability (OSDA-ETD) for remote sensing image scene classification. To be specific, we propose the transferability technology, which aims at the high interdomain variations and high intraclass diversity of remote sensing images. The purpose of transferability is to reduce the global distribution difference of domains and the local distribution discrepancy of the same classes in different domains. For high interclass similarity in remote sensing images, we adopt the discriminability strategy. The discriminability intends to enlarge the distribution discrepancy of different classes in different domains. To further promote the effectiveness of scene classification, we integrate the transferability and the discriminability into a framework. Moreover, we prove that the algorithm has a unique optimizer.
IEEE Transactions on Industrial Electronics, pp 1-1; https://doi.org/10.1109/tie.2021.3111562

Abstract:
Resistance emulating control is attractive due to the advantages of ease to use and less voltage sensor. However, it is only suitable for rectification mode. This letter presents a simple stabilized negative resistance emulating control for inverter mode, which overcomes the limitation of the conventional resistance emulating control. To stabilize the converter, a stabilizer based on negative inductance emulating is designed. Moreover, the unity power factor is realized by the steady-state inductance emulating technique. Since only the input current information is required, this control scheme is cost-effective and robust. Experimental results verify the effectiveness of the proposed method.
Zhengqiang Li, , , , , Jin Hong, Yan Ma, Zongren Peng, Wei Fang, Dongying Zhang, et al.
IEEE Transactions on Geoscience and Remote Sensing, pp 1-14; https://doi.org/10.1109/tgrs.2021.3110320

Abstract:
Obtaining accurate atmospheric parameters, e.g., aerosol optical depth (AOD) and column water vapor (CWV), is important for the quantitative atmospheric correction (AC) of the high-spatial resolution remote sensing images. However, due to the strong temporal and spatial changes of the atmospheric parameters, it will be a challenge to ensure spatiotemporal registration of the satellite images given the AC parameters obtained separately from ground-based or other satellite products, which affects significantly the accuracy of the AC. The China National Space Administration launched a high resolution and multimode imaging satellite [Gao Fen Duo Mo (GFDM)] in July 2020, which has multifunctional observation modes and flexible mobility, with a high-spatial resolution imaging sensor (0.42 m in panchromatic and 1.6 m in multispectrum) and equipped the synchronization monitoring atmospheric corrector (SMAC) sensor. As the first atmospheric corrector with polarization detection capability on-board high-spatial resolution satellite, SMAC is designed to obtain multispectral intensity and polarized data and to retrieve synchronously AC parameters in the same field of view with main sensor. Based on the SMAC in-orbit test data, a lookup table method using the optimized inversion framework and a dual-channel ratio retrieval method are developed to derive AOD and CWV, respectively, in this article. The AOD and CWV results are validated against the AERosol RObotic NETwork (AERONET). The preliminary test of AC performance on the multispectral images of GFDM satellite indicates that SMAC is of great potential to improve the quality of the main sensor's image.
Sahil Garg, Kuljeet Kaur, Georges Kaddoum, Prasad Garigipati, Gagangeet Singh Aujla
Abstract:
With the exponential growth in the number of connected devices, in recent years there has been a paradigm shift toward mobile edge computing. As a promising edge technology, it pushes mobile computing, network control, and storage to the network edges so as to provide better support to computation-intensive Internet of Things (IoT) applications. Although it enables offloading latency-sensitive applications at the resource-limited mobile devices, decentralized architectures and diversified deployment environments bring new security and privacy challenges. This is due to the fact that, with wireless communications, the medium can be accessed by both legitimate users and adversaries. Though cloud computing has helped in substantial transformation of global business, it falls short in provisioning distributed services, namely, security of IoT systems. Thus, the ever-evolving IoT applications require robust cyber-security measures particularly at the network's edge, for widespread adoption of IoT applications. In this vein, the classic machine learning models devised during the last decade, fall short in terms of low accuracy and reduced scalability for real-time attack detection across widely dispersed edge nodes. Thus, the advances in areas of deep learning, federated learning, and transfer learning could mark the evolution of more sophisticated models that can detect cyberattacks in heterogeneous IoT-driven edge networks without human intervention. We provide a SecEdge-Learn Architecture that uses deep learning and transfer learning approaches to provided a secure MEC environment. Moreover, we utilized blockchain to store the knowledge gained from the MEC clusters and thereby realizing the transfer learning approach to utilize the knowledge for handling different attack scenarios. Finally, we discuss the industry relevance of the MEC environment.
Haiyang Shi, , , Chunbo Chen, Huili He, Friday Uchenna Ochege, Tim Van de Voorde, , Philippe de Maeyer
IEEE Transactions on Geoscience and Remote Sensing, pp 1-15; https://doi.org/10.1109/tgrs.2021.3109819

Abstract:
Despite the growing interest among researchers, satellite-based prediction of soil salinity remains highly uncertain. The improvements in prediction accuracy reported in previous studies are usually limited to a single area. We performed a meta-analysis of regional satellite-based soil salinity predictions combined with in situ soil sampling and machine learning. Based on R² and root-mean-square error (RMSE) collected, we evaluated the effects of various features on the model accuracy and established a Bayesian network to evaluate the joint causal effect of multifeatures. Most significant differences were found in soil sampling schemes and characteristics of the study area, including the mean and variability (averaged R² of 0.75 for soil sample sets with lower salinity variation and 0.62 for others) of the salinity, climate type (R² of 0.64 in arid areas and 0.74 in others), soil texture (R² of 0.66 in sandy areas and 0.57 in others), and the interval between sampling date and satellite data acquisition date (R² of 0.53 under the condition of over 15 days and 0.65 in others). Generally, using different satellite data has limited effects on model performance among which Sentinel-2 performed better (R² = 0.72) than Landsat (R² = 0.66). The sampling of subsamples for each sample should focus on their subpixel-scale spatial heterogeneity across satellite data rather than the number of subsamples. It is also necessary to select appropriate vegetation and salinity indices for different satellite data under different vegetation conditions. Among algorithms, random forests (R² = 0.70) and support vector machines (R² = 0.71) performed best.
, Emmihenna Jaaskelainen, Annalea Lohila, Mika Korkiakoski, Aleksi Rasanen, Tarmo Virtanen, Filip Muhic, Hannu Marttila, Pertti Ala-Aho, Mira Markovaara-Koivisto, et al.
IEEE Transactions on Geoscience and Remote Sensing, pp 1-17; https://doi.org/10.1109/tgrs.2021.3109695

Abstract:
A soil moisture estimation method was developed for Sentinel-1 synthetic aperture radar (SAR) ground range detected high resolution (GRDH) data to analyze moisture conditions in a gently undulating and heterogeneous subarctic area containing forests, wetlands, and open orographic tundra. In order to preserve the original 10-m pixel spacing, PIMSAR (pixel-based multitemporal nonlocal averaging) nonlocal mean filtering was applied. It was guided by multitemporal statistics of SAR images in the area. The gradient boosted trees (GBT) machine learning method was used for the soil moisture algorithm development. Discrete and continuous in situ soil moisture values were used for training and validation of the algorithm. For surface soil moisture, the root mean square error (RMSE) of the method was 6.5% and 8.8% for morning and evening images, respectively. The corresponding maximum errors were 34.1% and 33.8%. The pixelwise sensitivity to the training set and method choice was estimated as the variance of the soil moisture values derived using the algorithms for the three best methods with respect to the criteria: the smallest maximum error, the smallest RMSE value, and the highest coefficient of determination (R²) value. It was, on average, 6.3% with a standard deviation of 5.7%. Our approach successfully produced instantaneous high-resolution soil moisture estimates on daily basis for the subarctic landscape and can further be applied to various hydrological, biogeochemical, and management purposes.
Woo June Choi, Jung-Ki Yoon, Bjorn Paulson, Chang-Hoon Lee, Jae-Joon Yim, Jong-Il Kim, Jun Ki Kim
IEEE Transactions on Medical Imaging, pp 1-1; https://doi.org/10.1109/tmi.2021.3112992

Abstract:
Ciliary movements within the human airway are essential for maintaining a clean lung environment. Motile cilia have a characteristic ciliary beat frequency (CBF). However, CBF measurement with current video microscopic techniques can be error-prone due to the use of the single-point Fourier transformation, which is often biased for ciliary measurements. Herein, we describe a new video microscopy technique that harnesses a metric of motion-contrast imaging and image correlation for CBF analysis. It can provide objective and selective CBF measurements for individual motile cilia and generate CBF maps for the imaged area. The measurement performance of our methodology was validated with in vitro human airway organoid models that simulated an actual human airway epithelium. The CBF determined for the region of interest (ROI) was equal to that obtained with manual counting. The signal redundancy problem of conventional methods was not observed. Moreover, the obtained CBF measurements were robust to optical focal shifts, and exhibited spatial heterogeneity and temperature dependence. This technique can be used to evaluate ciliary movement in respiratory tracts and determine whether it is non-synchronous or aperiodic in patients. Therefore, our observations suggest that the proposed method can be clinically adapted as a screening tool to diagnose ciliopathies.
IEEE Transactions on Knowledge and Data Engineering, pp 1-1; https://doi.org/10.1109/tkde.2021.3112520

Abstract:
Feature selection refers to choose an optimal non-redundant feature subset with minimal degradation of learning performance and maximal avoidance of data overfitting. The appearance of large data explosion leads to the sequential execution of algorithms are extremely time-consuming, which necessitates the scalable parallelization of algorithms by efficiently exploiting the distributed computational capabilities. In this paper, we present parallel feature selection algorithms underpinned by a rough hypercuboid approach in order to scale for the growing data volumes. Metrics in terms of rough hypercuboid are highly suitable to parallel distributed processing, and fits well with the Apache Spark cluster computing paradigm. Two data parallelism strategies, namely, vertical partitioning and horizontal partitioning, are implemented respectively to decompose the data into concurrent iterative computing streams. Experimental results on representative datasets show that our algorithms significantly faster than its original sequential counterpart while guaranteeing the quality of the results. Furthermore, the proposed algorithms are perfectly capable of exploiting the distributed-memory clusters to accomplish the computation task that fails on a single node due to the memory constraints. Parallel scalability and extensibility analysis have confirmed that our parallelization extends well to process massive amount of data and can scales well with the increase of computational nodes.
IEEE Transactions on Power Delivery, pp 1-1; https://doi.org/10.1109/tpwrd.2021.3112382

Abstract:
Differing from a two-level voltage source converter (TL-VSC), the internal dynamics of a modular multilevel converter (MMC) are much more complicated. Since the fluctuation of submodule capacitor voltage is unavoidable when transmitting power, the MMCs output voltages cannot track the references perfectly. The interaction between the time-varying capacitor dynamics and controllers may lead to self-instability of the MMCs. In order to address this self-instability issue, this paper first establishes the small-signal closed loop transfer function matrices (TFMs) of the external and internal control loop by the harmonic linearization method. Further, a novel design principle of MMC controllers is proposed. Then, the critical impact factors on the stability of circulating current controller and AC voltage controller are investigated based on the generalized Nyquist criterion(GNC). The proposed models and analysis methods are validated by time-domain simulations in PSCAD/EMTDC.
IEEE Transactions on Computers, pp 1-1; https://doi.org/10.1109/tc.2021.3112262

Abstract:
In DNN processors, main memory consumes much more energy than arithmetic operations. Therefore, many memory-oriented network scheduling (MONS) techniques are introduced to exploit on-chip data reuse opportunities and reduce accesses to memory. However, to derive the theoretical lower bound of memory overhead for DNNs is still a significant challenge, which also sheds light on how to reach memory-level optimality by means of network scheduling. Prior work on MONS mainly focused on disparate optimization techniques or missed some of the data reusing opportunities in diverse network models, thus their results are likely to deviate from the true memory-optimality that can be achieved in processors. This paper introduces Olympus, which comprehensively considers the entire memory-level DNN scheduling space, formally analyzes the true memory-optimality and also how to reach the memory-optimal schedules for an arbitrary DNN running on a DNN processor. The key idea behind Olympus is to derive a true memory lower-bound regarding both the intra-layer and inter-layer reuse opportunities, which has not been simultaneously explored by prior works. Evaluation on SOTA DNN processors of different architectures shows that Olympus can guarantee the minimum off-chip memory access, and it reduces 12.3-85.6% DRAM access and saves 7.4-70.3% energy on the latest network models.
, Hongyi Wu, Mohamed Azab, Chun Sheng Xin, Qiao Zhang
IEEE Internet of Things Journal, pp 1-1; https://doi.org/10.1109/jiot.2021.3112537

Abstract:
In a ubiquitous environment enclosing cooperative Internet of Things (IoT) devices, individuals, and entities, Digital Identity Management (DIM) becomes critical and challenging. DIM pertains to device identities authentication and verification to enable trustworthy service exchange, data collection, and decision making. DIM is the supporting pillar for all online services and the foundation for security and authentication mechanisms. Due to the extreme heterogeneity, scale, and configuration complexity of such environments, enabling trustworthy DIM is crucial and seriously challenging. In an IoT context, devices use local (Digital Identities) DIs stored within a tamper-proof unit and verified by a centralized authority for authentication. The recent attacks on IoT systems showed how vulnerable such a design is. It is also an inherent problem that influences humans. From that, Self-Sovereign Identity (SSI) has emerged as a decentralized DIM approach embracing the concept of portable selfpossession identity. SSI was presented to decouple the DI from the owner to enable large-scale cooperation. However, DI storage and verification still occur on the device and in a centralized manner. Utilizing a local single-point-of-failure storage memory for verifiable credentials is one of the considerable drawbacks in contemporary SSI. In this regard, this paper introduces DTSSIM, a novel Decentralized Trustworthy Self-Sovereign Identity Management framework. DT-SSIM integrates the secret share scheme with the Blockchain-based smart contracts technologies to provide transparent and trustworthy SSI-based digital identity management services for IoT. Storing IoT identity credentials outside the devices’ local storage preserves the identity credentials from being tampered with or misused. Evaluations and discussions show the resiliency assessment of the system and the cost and estimated running times for verification processes in DTSSIM.
IEEE Transactions on Fuzzy Systems, pp 1-1; https://doi.org/10.1109/tfuzz.2021.3112226

Abstract:
The issue of mining influential nodes in complex networks is a topic of immense interest. Recently, many methods have been proposed, but they suffer from certain limitations. In this paper, a novel centrality measure based on Local Fuzzy Information Centrality (LFIC) is proposed. LFIC puts forward the concept that the inner structure of a node's box contains information about the node's importance. LFIC uses the amount of information contained in the node's box as a measure of its importance. In LFIC, the uncertainty of information contained in nodes' boxes is measured by the improved Shannon entropy. Most importantly, fuzzy logic is applied to deal with the uncertainty of neighbor nodes' contributions to the center node's importance, which is neglected by most existing methods. To verify the effectiveness of our proposed method, six existing methods are used for comparison and five experiments are conducted using six real-world complex networks. The experimental results indicate that the influential nodes identified by LFIC can cause a wider scope of infection in networks and have a larger effect on the network connectivity, thereby proving the effectiveness and accuracy of LFIC. The correlation between nodes' LFIC values and their real infection ability is highly positive according to Kendall's tau coefficient, proving LFIC's credibility and superiority. The extension of LFIC, namely the Bi-directional Local Fuzzy Information Centrality (Bd-LFIC), is also proposed to explore its feasibility in weighted directed complex networks.
, Shengtao Wang, Liuping Liu
Abstract:
This paper deals with the problem of large number of parameters and complex calculation in video abstract generation of Fully Connected Network and Convolutional Neural Network. At the same time, the training and testing of such model need a lot of time and computer resources. We came up with a deep learning network parameter compression method based on Singular Value Decomposition(SVD) and Trucker Decomposition (TD) is proposed to generate the video summaries. The experiment was compared with other methods on TVSum and SumMe dataset, and the F1 value was 55.3% in TVSum dataset and 46.8% in SumMe dataset. At the same time, the degree of test time shortening under the same data volume is taken as the evaluation basis. The experimental results show that the proposed method achieves 1.04 times of acceleration in the SVD forward calculation, and 1.29 times of acceleration in the TD forward calculation. In a conclusion, the neural network model based on low-rank decomposition can effectively save computer resources and the time consumed by running programs.
IEEE Transactions on Fuzzy Systems, pp 1-1; https://doi.org/10.1109/tfuzz.2021.3112222

Abstract:
This paper investigates the feasibility of applying the broad learning system (BLS) to realize a novel TakagiSugenoKang (TSK) neuro-fuzzy model, namely a broad learning-based dynamic fuzzy inference system (BL-DFIS). It not only improves the accuracy and interpretability of neuro-fuzzy models but also solves the challenging problem that models are incapable of determining the optimal architecture autonomously. BL-DFIS firstly accomplish a TSK fuzzy system under the framework of BLS, in which extreme learning machine auto-encoder (ELM-AE) is employed to obtain feature representation in a fast and analytical way, and an interpretable linguistic fuzzy rule (ILFR) is integrated into the enhancement node to ensure the high interpretability of the system. Meanwhile, the extended-enhancement unit (EEU) is designed to achieve the first-order TSK fuzzy system. On the other hand, a dynamic incremental learning algorithm with internal pruning and updating mechanism is developed for the learning of BL-DFIS, which enables the system to automatically assemble the optimal structure to obtain a compact rule base and an excellent classification performance. Experiments on benchmark datasets demonstrate that the proposed BL-DFIS can achieve a better classification performance than some state-of-the-art nonfuzzy and neuro-fuzzy methods, simultaneously using the most parsimonious model structure.
IEEE Transactions on Aerospace and Electronic Systems, pp 1-1; https://doi.org/10.1109/taes.2021.3112556

Abstract:
Because the maximum radiation direction of the end-fire array antenna points to the axis of the array and the small element spacing required to suppress the grating lobes, the mutual coupling effect between the arrays is more serious than that of the broadside array. The paper first established the end-fire array antenna pattern model and clutter signal model with the effect of mutual coupling. The clutter signal model includes two cases, ideal mutual coupling effect and mutual coupling error. On this basis, we take a 10-element uniform linear array (ULA) using CST Microwave Studio to validate our model. Then we analyze the clutter distribution characteristics of the end-fire array airborne radar and the effect of mismatch on the spatial steering vector. Finally, an adaptive mutual coupling compensation method based on covariance matrix reconstruction is proposed. In general, clutter suppression methods with end-fire array take no account of the mutual coupling error changing over time, but the proposed method first adaptively estimates the mutual coupling error based on the airborne radar echo data, and uses the estimated normalized impedance matrix to compensate the spatial steering vector, then combines the system parameters to construct the clutter covariance matrix. The simulations indicate that this method accurately estimate the impedance matrix, and it eliminates the clutter power reduction and spatial steering vector mismatch caused by mutual coupling error. Moreover, it also solves the serious non-stationary clutter problem of the end-fire array airborne radar.
, L. A. Chung
IEEE Sensors Journal, pp 1-1; https://doi.org/10.1109/jsen.2021.3111903

Abstract:
The performance of a thermoelectric energy generator (TEG) can be improved by having thermocouple materials with higher Seebeck coefficient, thermocouple configuration with better thermal isolation, and thin-film layer deposition/etching with effective electrical insulation. A TEG design by the 1P6M (1 polysilicon layer and 6 metal layers) standard CMOS process in semiconductor foundry service (TSMC) is proposed in this work to achieve better energy harvesting performance. The in-plane thermocouple has higher Seebeck effect by the single polysilicon layer at different doping rates. The TEG configuration is with double cavity design to seal the thermocouples above-and-below for better thermal isolation, and the deposition layers are in mask-less design for better electrical insulation. Measurement results of a 5 × 5 mm2 TEG chip show that higher thermoelectric conversion, better thermal isolation and electrical insulation can be realized. The voltage factor 15.604 V/cm2K and power factor 0.105 μW/cm2K2 are about 5.40 x and 2.34 x, respectively, of those of the previous work by the CMOS process with two polysilicon layers. This design, implementation, and experiment have achieved the best performance in all TEGs by CMOS process in semiconductor foundry.
IEEE Signal Processing Letters, pp 1-1; https://doi.org/10.1109/lsp.2021.3112314

Abstract:
Fusion of multimodal features is a momentous problem for video emotion recognition. As the development of deep learning, directly fusing feature matrixes of each mode through neural networks at feature level becomes mainstream method. However, unlike unimodal issues, for multimodal analysis, finding the correlations between different modal is as important as discovering effective unimodal features. To make up the deficiency in unearthing the intrinsic relationships between multimodal, a novel modularized multimodal emotion recognition model based on deep canonical correlation analysis (MERDCCA) is proposed in this letter. In MERDCCA, four utterances are gathered as a new group and each utterance contains text, audio and visual information as multimodal input. Gated recurrent unit layers are used to extract the unimodal features. Deep canonical correlation analysis based on encoder-decoder network is designed to extract cross-modal correlations by maximizing the relevance between multimodal. The experiments on two public datasets show that MERDCCA achieves the better results.
, Lei Qiu, Kai Tang, Yuanjin Zheng
IEEE Transactions on Circuits and Systems II: Express Briefs, pp 1-1; https://doi.org/10.1109/tcsii.2021.3112501

Abstract:
A novel mismatch error shaping (MES) method is proposed in noise-shaping (NS) SAR ADCs to break the SNDR limitation caused by DAC mismatch induced non-linearity. Through sampling the signal twice for one conversion, the input range of the ADC is increased to 2Vref. After the first sampling, only the MSB is resolved and the results feed back to the opposite side of the DAC. After the second sampling, the MSB result is reversed and a +Vref /2 reference is generated at the side of the DAC which has low input while a -Vref /2 reference is generated at the other side. Through this method, the dynamic range deduction caused by the MES technique is solved. The proposed SAR ADC is implemented in TSMC 65nm CMOS technology. The simulation results show that the new MES method improves the SFDR from 54 dB to 104.5 dB. The SNDR in 20kHz bandwidth is 98.6dB while power consumption is 513.2μW under a 1 V power supply at 20MS/s sampling rate.
Yuxuan Zhou, Yining Dong, Hongkuan Zhou, Gang Tang
IEEE Transactions on Instrumentation and Measurement, pp 1-1; https://doi.org/10.1109/tim.2021.3112800

Abstract:
The research of intelligent fault diagnosis method has made great progress. The prerequisite for the effectiveness of most intelligent diagnosis models is to have abundant labeled data, which is difficult to satisfy in practice. Fortunately, we can obtain a large amount of rolling bearing failure data under laboratory conditions. Inspired by the idea of transfer learning, we propose a deep dynamic adaptive transfer network (DDATN) for intelligent fault diagnosis of rolling bearings. In addition to performing transfer diagnosis under different working conditions and failure degrees of the same type of bearing, it is also able to accomplish the task of cross-machine fault diagnosis from bearings under laboratory conditions to the bearings in practical applications. In the DDATN, the marginal probability distribution and conditional probability distribution of the data are aligned by dynamic domain adaptation using weight factor. Firstly, the original vibration signal of the bearing is first processed to establish the source and target domains. Then, pseudo-label learning on target domain unlabeled data is performed and the transferable features between domains are extracted through the deep parameter-shared neural networks. Next, by performing dynamic adaptation on the extracted transferable features, and optimizing the intelligent fault diagnosis model through backpropagation, the complete transfer diagnosis task in the target domain is accomplished. The effectiveness of the proposed DDATN method is demonstrated through variable working conditions and cross-machine transfer fault diagnosis tasks. Compared with other intelligent fault diagnosis methods, the proposed method shows clear advantages.
IEEE Transactions on Computational Imaging, pp 1-1; https://doi.org/10.1109/tci.2021.3111580

Abstract:
In this paper, we present an approach for ground moving target imaging (GMTI) and velocity recovery using synthetic aperture radar. We formulate the GMTI problem as the recovery of a phase-space reflectivity (PSR) function which represents the strengths and velocities of the scatterers in a scene of interest. We show that the discretized PSR matrix can be decomposed into a rank-one, and a highly sparse component corresponding to the stationary and moving scatterers, respectively. We then recover the two distinct components by solving a constrained optimization problem that admits computationally efficient convex solvers within the proximal gradient descent and alternating direction method of multipliers frameworks. Using the structural properties of the PSR matrix, we alleviate the computationally expensive steps associated with rank-constraints, such as singular value thresholding. Our optimization-based approach has several advantages over state-of-the-art GMTI methods, including computational efficiency, applicability to dense target environments, and arbitrary imaging configurations. We present extensive simulations to assess the robustness of our approach to both additive noise and clutter, with increasing number of moving targets. We show that both solvers perform well in dense moving target environments, and low-signal-to-clutter ratios without the need for additional clutter suppression techniques.
Muhammad Naveed Jafar, Muhammad Saeed, Muhammad Saqlain,
Abstract:
Cosine and cotangent similarity measurements are critical in applications for determining degrees of difference and similarity between objects. In the literature, numerous similarity measures for various extensions of fuzzy set, soft set, Intuitionistic Fuzzy Sets (IFSs), Pythagorean Fuzzy Sets (PFSs) and HyperSoft Sets (HSSs) have been explored. Neutrosophic HyperSoft Sets (NHSSs), on the other hand, has fewer cosine and cotangent similarity measures. In this paper, we propose the trigonometric similarity measures of NHSSs. We further investigate the basic operators, theorems, and propositions for the proposed similarity measures. We know that global warming causes environmental problems. One of applications for solving global warming is the concept of renewable energy. To show the effectiveness of the proposed similarity measures, we apply them to renewable energy source selection problems. The study reveals the best geographical area to install the energy production units, under some technical attributive factors. To check the validity and superiority of the proposed work, it is compared with some existing techniques which reveal that, decision-making problems with further bifurcated attributes, have more accurate and precise results and can only be solved with this technique. In the future, the proposed techniques can be applied to case studies, in which attributes are more than one and further bifurcated along with more than one decision-maker. Also, this proposed work can be extended for several existing hybrids of hypersoft sets, intuitionistic hypersoft, neutrosophic hypersoft set, bi-polar hypersoft, m-polar hypersoft sets, and Pythagorean hypersoft set to solve Multi-Criteria Decision Making (MCDM) problems.
, , Jialu Fan, Patrik Kolaric, ,
IEEE Transactions on Neural Networks and Learning Systems, pp 1-14; https://doi.org/10.1109/tnnls.2021.3106635

Abstract:
In inverse reinforcement learning (RL), there are two agents. An expert target agent has a performance cost function and exhibits control and state behaviors to a learner. The learner agent does not know the expert's performance cost function but seeks to reconstruct it by observing the expert's behaviors and tries to imitate these behaviors optimally by its own response. In this article, we formulate an imitation problem where the optimal performance intent of a discrete-time (DT) expert target agent is unknown to a DT Learner agent. Using only the observed expert's behavior trajectory, the learner seeks to determine a cost function that yields the same optimal feedback gain as the expert's, and thus, imitates the optimal response of the expert. We develop an inverse RL approach with a new scheme to solve the behavior imitation problem. The approach consists of a cost function update based on an extension of RL policy iteration and inverse optimal control, and a control policy update based on optimal control. Then, under this scheme, we develop an inverse reinforcement Q-learning algorithm, which is an extension of RL Q-learning. This algorithm does not require any knowledge of agent dynamics. Proofs of stability, convergence, and optimality are given. A key property about the nonunique solution is also shown. Finally, simulation experiments are presented to show the effectiveness of the new approach.
IEEE Transactions on Services Computing, pp 1-1; https://doi.org/10.1109/tsc.2021.3112659

Abstract:
In this paper, we propose [email protected], a new architecture for location-based services (LBSs) facilitated by the mobile edge computing paradigm. [email protected] tackles the location privacy problem innovatively by delocalizing LBSs so that mobile users of LBSs implemented based on [email protected] do not have to reveal their locations. They retrieve local information from nearby edge servers around them instead of the cloud. In this way, we resolve the root cause of the conventional location privacy problem. However, [email protected] raises new challenges to location privacy. A mobile user can still be localized to a particular privacy area co-covered by the edge servers accessed by the mobile user. A small privacy area puts the mobile users location at the risk of being approximated. In the meantime, the size of the utility area, which determines the amount of local information retrievable for the mobile user, is positively correlated with the number of edge servers accessed by the mobile user. We model this problem as a constrained optimization problem and propose an optimal approach for solving it based on integer programming. Extensive experiments are conducted on a widely-used real-world dataset to demonstrate effectiveness and efficiency.
Haoran Wang, , , Lingling Li, Xu Liu, Deyi Ji,
IEEE Transactions on Neural Networks and Learning Systems, pp 1-14; https://doi.org/10.1109/tnnls.2021.3110682

Abstract:
Social relations are ubiquitous and form the basis of social structure in our daily life. However, existing studies mainly focus on recognizing social relations from still images and movie clips, which are different from real-world scenarios. For example, movie-based datasets define the task as the video classification, only recognizing one relation in the scene. In this article, we aim to study the problem of social relation recognition in an open environment. To close the gap, we provide the first video dataset collected from real-life scenarios, named social relation in the wild (SRIW), where the number of people can be huge and vary, and each pair of relations needs to be recognized. To overcome new challenges, we propose a spatio-temporal relation graph convolutional network (STRGCN) architecture, utilizing correlative visual features to recognize social relations intuitively. Our method decouples the task into two classification tasks: person-level and pair-level relation recognition. Specifically, we propose a person behavior and character module to encode moving and static features in two explicit ways. Then we take them as node features to build a relation graph with meaningful edges in a scene. Based on the relation graph, we introduce the graph convolutional network (GCN) and local GCN to encode social relation features which are used for both recognitions. Experimental results demonstrate the effectiveness of the proposed framework, achieving 83.1% and 40.8% mAP in person-level and pair-level classification. Moreover, the study also contributes to the practicality in this field.
, Ying Han, Yanan Wang, , , Zhumu Fu, Peng Li,
IEEE Transactions on Intelligent Transportation Systems, pp 1-14; https://doi.org/10.1109/tits.2021.3106545

Abstract:
The Internet of Vehicles (IoV) has always attracted attention as the emerging communication network with the most development potential in the 5G era. However, the performance of IoV under 5G ultra-dense networks is an open issue, especially in practice the outage probability and ergodic capacity of the relay cooperative IoV network under aggregate interference are still unclear. Therefore, an opportunistic Decoding and Forwarding (DF) relay cooperative transmission algorithm was proposed in this paper when the destination node of IoV has aggregated interference. In addition, based on mathematical theoretical knowledge such as numerical analysis, the closed expressions of the outage probability and ergodic capacity of the IoV system under aggregated interference was derived. Finally, simulation experiments verify the effectiveness of the proposed scheme and the correctness of the theoretical analysis, which improves the transmission rate of the system.
Zhan Li,
IEEE Transactions on Neural Networks and Learning Systems, pp 1-15; https://doi.org/10.1109/tnnls.2021.3109953

Abstract:
Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the performance of existing autoencoder approaches for manipulator control may be still largely dependent on the quality of data, and for extreme cases with noisy data it may even fail. How to incorporate the model knowledge into the autoencoder controller design with an aim to increase the robustness and reliability remains a challenging problem. In this work, a sparse autoencoder controller for kinematic control of manipulators with weights obtained directly from the robot model rather than training data is proposed for the first time. By encoding and decoding the control target though a new dynamic recurrent neural network architecture, the control input can be solved through a new sparse optimization formulation. In this work, input saturation, which holds for almost all practical systems but usually is ignored for analysis simplicity, is also considered in the controller construction. Theoretical analysis and extensive simulations demonstrate that the proposed sparse autoencoder controller with input saturation can make the end-effector of the manipulator system track the desired path efficiently. Further performance comparison and evaluation against the additive noise and parameter uncertainty substantiate robustness of the proposed sparse autoencoder manipulator controller.
Page of 98,407
Articles per Page
by
Show export options
  Select all
Back to Top Top