Showing papers by "University of Electronic Science and Technology of China published in 2020"

Federated Learning in Mobile Edge Networks: A Comprehensive Survey

Abstract: In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications, e.g., for medical purposes and in vehicular networks. Traditional cloud-based Machine Learning (ML) approaches require the data to be centralized in a cloud server or data center. However, this results in critical issues related to unacceptable latency and communication inefficiency. To this end, Mobile Edge Computing (MEC) has been proposed to bring intelligence closer to the edge, where data is produced. However, conventional enabling technologies for ML at mobile edge networks still require personal data to be shared with external parties, e.g., edge servers. Recently, in light of increasingly stringent data privacy legislations and growing privacy concerns, the concept of Federated Learning (FL) has been introduced. In FL, end devices use their local data to train an ML model required by the server. The end devices then send the model updates rather than raw data to the server for aggregation. FL can serve as an enabling technology in mobile edge networks since it enables the collaborative training of an ML model and also enables DL for mobile edge network optimization. However, in a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved. This raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale. In this survey, we begin with an introduction to the background and fundamentals of FL. Then, we highlight the aforementioned challenges of FL implementation and review existing solutions. Furthermore, we present the applications of FL for mobile edge network optimization. Finally, we discuss the important challenges and future research directions in FL.

Design of robust superhydrophobic surfaces

Abstract: The ability of superhydrophobic surfaces to stay dry, self-clean and avoid biofouling is attractive for applications in biotechnology, medicine and heat transfer1–10. Water droplets that contact these surfaces must have large apparent contact angles (greater than 150 degrees) and small roll-off angles (less than 10 degrees). This can be realized for surfaces that have low-surface-energy chemistry and micro- or nanoscale surface roughness, minimizing contact between the liquid and the solid surface11–17. However, rough surfaces—for which only a small fraction of the overall area is in contact with the liquid—experience high local pressures under mechanical load, making them fragile and highly susceptible to abrasion18. Additionally, abrasion exposes underlying materials and may change the local nature of the surface from hydrophobic to hydrophilic19, resulting in the pinning of water droplets to the surface. It has therefore been assumed that mechanical robustness and water repellency are mutually exclusive surface properties. Here we show that robust superhydrophobicity can be realized by structuring surfaces at two different length scales, with a nanostructure design to provide water repellency and a microstructure design to provide durability. The microstructure is an interconnected surface frame containing ‘pockets’ that house highly water-repellent and mechanically fragile nanostructures. This surface frame acts as ‘armour’, preventing the removal of the nanostructures by abradants that are larger than the frame size. We apply this strategy to various substrates—including silicon, ceramic, metal and transparent glass—and show that the water repellency of the resulting superhydrophobic surfaces is preserved even after abrasion by sandpaper and by a sharp steel blade. We suggest that this transparent, mechanically robust, self-cleaning glass could help to negate the dust-contamination issue that leads to a loss of efficiency in solar cells. Our design strategy could also guide the development of other materials that need to retain effective self-cleaning, anti-fouling or heat-transfer abilities in harsh operating environments. Water-repellent nanostructures are housed within an interconnected microstructure frame to yield mechanically robust superhydrophobic surfaces.

A droplet-based electricity generator with high instantaneous power density

Abstract: Extensive efforts have been made to harvest energy from water in the form of raindrops1–6, river and ocean waves7,8, tides9 and others10–17. However, achieving a high density of electrical power generation is challenging. Traditional hydraulic power generation mainly uses electromagnetic generators that are heavy, bulky, and become inefficient with low water supply. An alternative, the water-droplet/solid-based triboelectric nanogenerator, has so far generated peak power densities of less than one watt per square metre, owing to the limitations imposed by interfacial effects—as seen in characterizations of the charge generation and transfer that occur at solid–liquid1–4 or liquid–liquid5,18 interfaces. Here we develop a device to harvest energy from impinging water droplets by using an architecture that comprises a polytetrafluoroethylene film on an indium tin oxide substrate plus an aluminium electrode. We show that spreading of an impinged water droplet on the device bridges the originally disconnected components into a closed-loop electrical system, transforming the conventional interfacial effect into a bulk effect, and so enhancing the instantaneous power density by several orders of magnitude over equivalent devices that are limited by interfacial effects. A device involving a polytetrafluoroethylene film, an indium tin oxide substrate and an aluminium electrode allows improved electricity generation from water droplets, which bridge the previously disconnected circuit components.

Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT

Abstract: The rapid increase in the volume of data generated from connected devices in industrial Internet of Things paradigm, opens up new possibilities for enhancing the quality of service for the emerging applications through data sharing. However, security and privacy concerns (e.g., data leakage) are major obstacles for data providers to share their data in wireless networks. The leakage of private data can lead to serious issues beyond financial loss for the providers. In this article, we first design a blockchain empowered secure data sharing architecture for distributed multiple parties. Then, we formulate the data sharing problem into a machine-learning problem by incorporating privacy-preserved federated learning. The privacy of data is well-maintained by sharing the data model instead of revealing the actual data. Finally, we integrate federated learning in the consensus process of permissioned blockchain, so that the computing work for consensus can also be used for federated training. Numerical results derived from real-world datasets show that the proposed data sharing scheme achieves good accuracy, high efficiency, and enhanced security.

Toward Smart Wireless Communications via Intelligent Reflecting Surfaces: A Contemporary Survey

Abstract: This paper presents a literature review on recent applications and design aspects of the intelligent reflecting surface (IRS) in the future wireless networks. Conventionally, the network optimization has been limited to transmission control at two endpoints, i.e., end users and network controller. The fading wireless channel is uncontrollable and becomes one of the main limiting factors for performance improvement. The IRS is composed of a large array of scattering elements, which can be individually configured to generate additional phase shifts to the signal reflections. Hence, it can actively control the signal propagation properties in favor of signal reception, and thus realize the notion of a smart radio environment. As such, the IRS’s phase control, combined with the conventional transmission control, can potentially bring performance gain compared to wireless networks without IRS. In this survey, we first introduce basic concepts of the IRS and the realizations of its reconfigurability. Then, we focus on applications of the IRS in wireless communications. We overview different performance metrics and analytical approaches to characterize the performance improvement of IRS-assisted wireless networks. To exploit the performance gain, we discuss the joint optimization of the IRS’s phase control and the transceivers’ transmission control in different network design problems, e.g., rate maximization and power minimization problems. Furthermore, we extend the discussion of IRS-assisted wireless networks to some emerging use cases. Finally, we highlight important practical challenges and future research directions for realizing IRS-assisted wireless networks in beyond 5G communications.

Cascaded Channel Estimation for Large Intelligent Metasurface Assisted Massive MIMO

Abstract: In this letter, we consider the problem of channel estimation for large intelligent metasurface (LIM) assisted massive multiple-input multiple-output (MIMO) systems. The main challenge of this problem is that the LIM integrated with a large number of low-cost metamaterial antennas can only passively reflect the incident signals by certain phase shifts, and does not have any signal processing capability. To deal with this, we introduce a general framework for the estimation of the transmitter-LIM and LIM-receiver cascaded channel, and propose a two-stage algorithm that includes a sparse matrix factorization stage and a matrix completion stage. Simulation results illustrate that the proposed method can achieve accurate channel estimation for LIM-assisted massive MIMO systems.

Weighted Sum-Rate Maximization for Reconfigurable Intelligent Surface Aided Wireless Networks

Abstract: Reconfigurable intelligent surfaces (RIS) is a promising solution to build a programmable wireless environment via steering the incident signal in fully customizable ways with reconfigurable passive elements. In this paper, we consider a RIS-aided multiuser multiple-input single-output (MISO) downlink communication system. Our objective is to maximize the weighted sum-rate (WSR) of all users by joint designing the beamforming at the access point (AP) and the phase vector of the RIS elements, while both the perfect channel state information (CSI) setup and the imperfect CSI setup are investigated. For perfect CSI setup, a low-complexity algorithm is proposed to obtain the stationary solution for the joint design problem by utilizing the fractional programming technique. Then, we resort to the stochastic successive convex approximation technique and extend the proposed algorithm to the scenario wherein the CSI is imperfect. The validity of the proposed methods is confirmed by numerical results. In particular, the proposed algorithm performs quite well when the channel uncertainty is smaller than 10%.

A vaccine targeting the RBD of the S protein of SARS-CoV-2 induces protective immunity.

Abstract: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes a respiratory disease called coronavirus disease 2019 (COVID-19), the spread of which has led to a pandemic. An effective preventive vaccine against this virus is urgently needed. As an essential step during infection, SARS-CoV-2 uses the receptor-binding domain (RBD) of the spike protein to engage with the receptor angiotensin-converting enzyme 2 (ACE2) on host cells1,2. Here we show that a recombinant vaccine that comprises residues 319-545 of the RBD of the spike protein induces a potent functional antibody response in immunized mice, rabbits and non-human primates (Macaca mulatta) as early as 7 or 14 days after the injection of a single vaccine dose. The sera from the immunized animals blocked the binding of the RBD to ACE2, which is expressed on the cell surface, and neutralized infection with a SARS-CoV-2 pseudovirus and live SARS-CoV-2 in vitro. Notably, vaccination also provided protection in non-human primates to an in vivo challenge with SARS-CoV-2. We found increased levels of RBD-specific antibodies in the sera of patients with COVID-19. We show that several immune pathways and CD4 T lymphocytes are involved in the induction of the vaccine antibody response. Our findings highlight the importance of the RBD domain in the design of SARS-CoV-2 vaccines and provide a rationale for the development of a protective vaccine through the induction of antibodies against the RBD domain.

Variability in the analysis of a single neuroimaging dataset by many teams

Abstract: Data analysis workflows in many scientific domains have become increasingly complex and flexible. Here we assess the effect of this flexibility on the results of functional magnetic resonance imaging by asking 70 independent teams to analyse the same dataset, testing the same 9 ex-ante hypotheses1. The flexibility of analytical approaches is exemplified by the fact that no two teams chose identical workflows to analyse the data. This flexibility resulted in sizeable variation in the results of hypothesis tests, even for teams whose statistical maps were highly correlated at intermediate stages of the analysis pipeline. Variation in reported results was related to several aspects of analysis methodology. Notably, a meta-analytical approach that aggregated information across teams yielded a significant consensus in activated regions. Furthermore, prediction markets of researchers in the field revealed an overestimation of the likelihood of significant findings, even by researchers with direct knowledge of the dataset2-5. Our findings show that analytical flexibility can have substantial effects on scientific conclusions, and identify factors that may be related to variability in the analysis of functional magnetic resonance imaging. The results emphasize the importance of validating and sharing complex analysis workflows, and demonstrate the need for performing and reporting multiple analyses of the same data. Potential approaches that could be used to mitigate issues related to analytical variability are discussed.

Reconfigurable Intelligent Surface-Based Wireless Communications: Antenna Design, Prototyping, and Experimental Results

Abstract: One of the key enablers of future wireless communications is constituted by massive multiple-input multiple-output (MIMO) systems, which can improve the spectral efficiency by orders of magnitude. In existing massive MIMO systems, however, conventional phased arrays are used for beamforming. This method results in excessive power consumption and high hardware costs. Recently, reconfigurable intelligent surface (RIS) has been considered as one of the revolutionary technologies to enable energy-efficient and smart wireless communications, which is a two-dimensional structure with a large number of passive elements. In this paper, we develop a new type of high-gain yet low-cost RIS that bears 256 elements. The proposed RIS combines the functions of phase shift and radiation together on an electromagnetic surface, where positive intrinsic-negative (PIN) diodes are used to realize 2-bit phase shifting for beamforming. This radical design forms the basis for the world's first wireless communication prototype using RIS having 256 two-bit elements. The prototype consists of modular hardware and flexible software that encompass the following: the hosts for parameter setting and data exchange, the universal software radio peripherals (USRPs) for baseband and radio frequency (RF) signal processing, as well as the RIS for signal transmission and reception. Our performance evaluation confirms the feasibility and efficiency of RISs in wireless communications. We show that, at 2.3 GHz, the proposed RIS can achieve a 21.7 dBi antenna gain. At the millimeter wave (mmWave) frequency, that is, 28.5 GHz, it attains a 19.1 dBi antenna gain. Furthermore, it has been shown that the RIS-based wireless communication prototype developed is capable of significantly reducing the power consumption.

Progress in the functional modification of graphene/graphene oxide: a review

Abstract: Graphene and graphene oxide have attracted tremendous interest over the past decade due to their unique and excellent electronic, optical, mechanical, and chemical properties. This review focuses on the functional modification of graphene and graphene oxide. First, the basic structure, preparation methods and properties of graphene and graphene oxide are briefly described. Subsequently, the methods for the reduction of graphene oxide are introduced. Next, the functionalization of graphene and graphene oxide is mainly divided into covalent binding modification, non-covalent binding modification and elemental doping. Then, the properties and application prospects of the modified products are summarized. Finally, the current challenges and future research directions are presented in terms of surface functional modification for graphene and graphene oxide.

COVID-19: immunopathogenesis and Immunotherapeutics.

Abstract: The recent novel coronavirus disease (COVID-19) outbreak, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is seeing a rapid increase in infected patients worldwide. The host immune response to SARS-CoV-2 appears to play a critical role in disease pathogenesis and clinical manifestations. SARS-CoV-2 not only activates antiviral immune responses, but can also cause uncontrolled inflammatory responses characterized by marked pro-inflammatory cytokine release in patients with severe COVID-19, leading to lymphopenia, lymphocyte dysfunction, and granulocyte and monocyte abnormalities. These SARS-CoV-2-induced immune abnormalities may lead to infections by microorganisms, septic shock, and severe multiple organ dysfunction. Therefore, mechanisms underlying immune abnormalities in patients with COVID-19 must be elucidated to guide clinical management of the disease. Moreover, rational management of the immune responses to SARS-CoV-2, which includes enhancing anti-viral immunity while inhibiting systemic inflammation, may be key to successful treatment. In this review, we discuss the immunopathology of COVID-19, its potential mechanisms, and clinical implications to aid the development of new therapeutic strategies against COVID-19.

Predictors of mortality in hospitalized COVID-19 patients: A systematic review and meta-analysis.

Abstract: Mortality rates of coronavirus disease-2019 (COVID-19) continue to rise across the world. Information regarding the predictors of mortality in patients with COVID-19 remains scarce. Herein, we performed a systematic review of published articles, from 1 January to 24 April 2020, to evaluate the risk factors associated with mortality in COVID-19. Two investigators independently searched the articles and collected the data, in accordance with PRISMA guidelines. We looked for associations between mortality and patient characteristics, comorbidities, and laboratory abnormalities. A total of 14 studies documenting the outcomes of 4659 patients were included. The presence of comorbidities such as hypertension (odds ratio [OR], 2.5; 95% confidence interval [CI], 2.1-3.1; P < .00001), coronary heart disease (OR, 3.8; 95% CI, 2.1-6.9; P < .00001), and diabetes (OR, 2.0; 95% CI, 1.7-2.3; P < .00001) were associated with significantly higher risk of death amongst patients with COVID-19. Those who died, compared with those who survived, differed on multiple biomarkers on admission including elevated levels of cardiac troponin (+44.2 ng/L, 95% CI, 19.0-69.4; P = .0006); C-reactive protein (+66.3 µg/mL, 95% CI, 46.7-85.9; P < .00001); interleukin-6 (+4.6 ng/mL, 95% CI, 3.6-5.6; P < .00001); D-dimer (+4.6 µg/mL, 95% CI, 2.8-6.4; P < .00001); creatinine (+15.3 µmol/L, 95% CI, 6.2-24.3; P = .001); and alanine transaminase (+5.7 U/L, 95% CI, 2.6-8.8; P = .0003); as well as decreased levels of albumin (-3.7 g/L, 95% CI, -5.3 to -2.1; P < .00001). Individuals with underlying cardiometabolic disease and that present with evidence for acute inflammation and end-organ damage are at higher risk of mortality due to COVID-19 infection and should be managed with greater intensity.

Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Joint Active and Passive Precoding Design

Abstract: Millimeter wave (MmWave) communications is capable of supporting multi-gigabit wireless access thanks to its abundant spectrum resource. However, severe path loss and high directivity make it vulnerable to blockage events, which can be frequent in indoor and dense urban environments. To address this issue, in this paper, we introduce intelligent reflecting surface (IRS) as a new technology to provide effective reflected paths to enhance the coverage of mmWave signals. In this framework, we study joint active and passive precoding design for IRS-assisted mmWave systems, where multiple IRSs are deployed to assist the data transmission from a base station (BS) to a single-antenna receiver. Our objective is to maximize the received signal power by jointly optimizing the BS's transmit precoding vector and IRSs’ phase shift coefficients. Although such an optimization problem is generally non-convex, we show that, by exploiting some important characteristics of mmWave channels, an optimal closed-form solution can be derived for the single IRS case and a near-optimal analytical solution can be obtained for the multi-IRS case. Our analysis reveals that the received signal power increases quadratically with the number of reflecting elements for both the single IRS and multi-IRS cases. Simulation results are included to verify the optimality and near-optimality of our proposed solutions. Results also show that IRSs can help create effective virtual line-of-sight (LOS) paths and thus substantially improve robustness against blockages in mmWave communications.

VerifyNet: Secure and Verifiable Federated Learning

Abstract: As an emerging training model with neural networks, federated learning has received widespread attention due to its ability to update parameters without collecting users’ raw data. However, since adversaries can track and derive participants’ privacy from the shared gradients, federated learning is still exposed to various security and privacy threats. In this paper, we consider two major issues in the training process over deep neural networks (DNNs): 1) how to protect user’s privacy (i.e., local gradients) in the training process and 2) how to verify the integrity (or correctness) of the aggregated results returned from the server. To solve the above problems, several approaches focusing on secure or privacy-preserving federated learning have been proposed and applied in diverse scenarios. However, it is still an open problem enabling clients to verify whether the cloud server is operating correctly, while guaranteeing user’s privacy in the training process. In this paper, we propose VerifyNet, the first privacy-preserving and verifiable federated learning framework. In specific, we first propose a double-masking protocol to guarantee the confidentiality of users’ local gradients during the federated learning. Then, the cloud server is required to provide the Proof about the correctness of its aggregated results to each user. We claim that it is impossible that an adversary can deceive users by forging Proof , unless it can solve the NP-hard problem adopted in our model. In addition, VerifyNet is also supportive of users dropping out during the training process. The extensive experiments conducted on real-world data also demonstrate the practical performance of our proposed scheme.

Reconfigurable Intelligent Surface Assisted UAV Communication: Joint Trajectory Design and Passive Beamforming

Abstract: Thanks to the line-of-sight (LoS) transmission and flexibility, unmanned aerial vehicles (UAVs) effectively improve the throughput of wireless networks. Nevertheless, the LoS links are prone to severe deterioration by complex propagation environments, especially in urban areas. Reconfigurable intelligent surfaces (RISs), as a promising technique, can significantly improve the propagation environment and enhance communication quality by intelligently reflecting the received signals. Motivated by this, the joint UAV trajectory and RIS’s passive beamforming design for a novel RIS-assisted UAV communication system is investigated to maximize the average achievable rate in this letter. To tackle the formulated non-convex problem, we divide it into two subproblems, namely, passive beamforming and trajectory optimization. We first derive a closed-form phase-shift solution for any given UAV trajectory to achieve the phase alignment of the received signals from different transmission paths. Then, with the optimal phase-shift solution, we obtain a suboptimal trajectory solution by using the successive convex approximation (SCA) method. Numerical results demonstrate that the proposed algorithm can considerably improve the average achievable rate of the system.

Outline of Fungi and fungus-like taxa

Abstract: This article provides an outline of the classification of the kingdom Fungi (including fossil fungi. i.e. dispersed spores, mycelia, sporophores, mycorrhizas). We treat 19 phyla of fungi. These are Aphelidiomycota, Ascomycota, Basidiobolomycota, Basidiomycota, Blastocladiomycota, Calcarisporiellomycota, Caulochytriomycota, Chytridiomycota, Entomophthoromycota, Entorrhizomycota, Glomeromycota, Kickxellomycota, Monoblepharomycota, Mortierellomycota, Mucoromycota, Neocallimastigomycota, Olpidiomycota, Rozellomycota and Zoopagomycota. The placement of all fungal genera is provided at the class-, order- and family-level. The described number of species per genus is also given. Notes are provided of taxa for which recent changes or disagreements have been presented. Fungus-like taxa that were traditionally treated as fungi are also incorporated in this outline (i.e. Eumycetozoa, Dictyosteliomycetes, Ceratiomyxomycetes and Myxomycetes). Four new taxa are introduced: Amblyosporida ord. nov. Neopereziida ord. nov. and Ovavesiculida ord. nov. in Rozellomycota, and Protosporangiaceae fam. nov. in Dictyosteliomycetes. Two different classifications (in outline section and in discussion) are provided for Glomeromycota and Leotiomycetes based on recent studies. The phylogenetic reconstruction of a four-gene dataset (18S and 28S rRNA, RPB1, RPB2) of 433 taxa is presented, including all currently described orders of fungi.

Blockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles

Abstract: In Internet of Vehicles (IoV), data sharing among vehicles for collaborative analysis can improve the driving experience and service quality. However, the bandwidth, security and privacy issues hinder data providers from participating in the data sharing process. In addition, due to the intermittent and unreliable communications in IoV, the reliability and efficiency of data sharing need to be further enhanced. In this paper, we propose a new architecture based on federated learning to relieve transmission load and address privacy concerns of providers. To enhance the security and reliability of model parameters, we develop a hybrid blockchain architecture which consists of the permissioned blockchain and the local Directed Acyclic Graph (DAG). Moreover, we propose an asynchronous federated learning scheme by adopting Deep Reinforcement Learning (DRL) for node selection to improve the efficiency. The reliability of shared data is also guaranteed by integrating learned models into blockchain and executing a two-stage verification. Numerical results show that the proposed data sharing scheme provides both higher learning accuracy and faster convergence.

Seroprevalence of immunoglobulin M and G antibodies against SARS-CoV-2 in China.

Abstract: Detection of asymptomatic or subclinical novel human coronavirus SARS-CoV-2 infection is critical for understanding the overall prevalence and infection potential of COVID-19. To estimate the cumulative prevalence of SARS-CoV-2 infection in China, we evaluated the host serologic response, measured by the levels of immunoglobulins M and G in 17,368 individuals, in the city of Wuhan, the epicenter of the COVID-19 pandemic in China, and geographic regions in the country, during the period from 9 March 2020 to 10 April 2020. In our cohorts, the seropositivity in Wuhan varied between 3.2% and 3.8% in different subcohorts. Seroposivity progressively decreased in other cities as the distance to the epicenter increased. Patients who visited a hospital for maintenance hemodialysis and healthcare workers also had a higher seroprevalence of 3.3% (51 of 1,542, 2.5-4.3%, 95% confidence interval (CI)) and 1.8% (81 of 4,384, 1.5-2.3%, 95% CI), respectively. More studies are needed to determine whether these results are generalizable to other populations and geographic locations, as well as to determine at what rate seroprevalence is increasing with the progress of the COVID-19 pandemic. Serologic surveillance has the potential to provide a more faithful cumulative viral attack rate for the first season of this novel SARS-CoV-2 infection.

Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence

Abstract: By leveraging deep learning-based technologies, industrial artificial intelligence (IAI) has been applied to solve various industrial challenging problems in Industry 4.0. However, for privacy reasons, traditional centralized training may be unsuitable for sensitive data-driven industrial scenarios, such as healthcare and autopilot. Recently, federated learning has received widespread attention, since it enables participants to collaboratively learn a shared model without revealing their local data. However, studies have shown that, by exploiting the shared parameters adversaries can still compromise industrial applications such as auto-driving navigation systems, medical data in wearable devices, and industrial robots’ decision making. In this article, to solve this problem, we propose an efficient and privacy-enhanced federated learning (PEFL) scheme for IAI. Compared with existing solutions, PEFL is noninteractive, and can prevent private data from being leaked even if multiple entities collude with each other. Moreover, extensive experiments with real-world data demonstrate the superiority of PEFL in terms of accuracy and efficiency.

A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images

Abstract: Segmentation of pneumonia lesions from CT scans of COVID-19 patients is important for accurate diagnosis and follow-up. Deep learning has a potential to automate this task but requires a large set of high-quality annotations that are difficult to collect. Learning from noisy training labels that are easier to obtain has a potential to alleviate this problem. To this end, we propose a novel noise-robust framework to learn from noisy labels for the segmentation task. We first introduce a noise-robust Dice loss that is a generalization of Dice loss for segmentation and Mean Absolute Error (MAE) loss for robustness against noise, then propose a novel COVID-19 Pneumonia Lesion segmentation network (COPLE-Net) to better deal with the lesions with various scales and appearances. The noise-robust Dice loss and COPLE-Net are combined with an adaptive self-ensembling framework for training, where an Exponential Moving Average (EMA) of a student model is used as a teacher model that is adaptively updated by suppressing the contribution of the student to EMA when the student has a large training loss. The student model is also adaptive by learning from the teacher only when the teacher outperforms the student. Experimental results showed that: (1) our noise-robust Dice loss outperforms existing noise-robust loss functions, (2) the proposed COPLE-Net achieves higher performance than state-of-the-art image segmentation networks, and (3) our framework with adaptive self-ensembling significantly outperforms a standard training process and surpasses other noise-robust training approaches in the scenario of learning from noisy labels for COVID-19 pneumonia lesion segmentation.

Compressed Channel Estimation for Intelligent Reflecting Surface-Assisted Millimeter Wave Systems

Abstract: In this letter, we consider channel estimation for intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) systems, where an IRS is deployed to assist the data transmission from the base station (BS) to a user. It is shown that for the purpose of joint active and passive beamforming, the knowledge of a large-size cascade channel matrix needs to be acquired. To reduce the training overhead, the inherent sparsity in mmWave channels is exploited. By utilizing properties of Katri-Rao and Kronecker products, we find a sparse representation of the cascade channel and convert cascade channel estimation into a sparse signal recovery problem. Simulation results show that our proposed method can provide an accurate channel estimate and achieve a substantial training overhead reduction.

Crystalline Carbon Nitride Supported Copper Single Atoms for Photocatalytic CO2 Reduction with Nearly 100% CO Selectivity

Abstract: Single metal atom photocatalysts have received widespread attention due to the rational use of metal resources and maximum atom utilization efficiency. Especially N-rich amorphous g-C3N4 is always ...

Fe-Based Electrocatalysts for Oxygen Evolution Reaction: Progress and Perspectives

Abstract: Electrocatalytic oxygen evolution reaction (OER) is a core reaction responsible for converting renewable electricity into storable fuels; yet, it is kinetically challenging, because of the complex ...