Search

A novel paradigm that combines federated learning with blockchain to empower edge intelligence over vehicular networks (FBVN) can enable latency-sensitive deep neural network-based applications to be executed in a distributed pattern. However, the complex environments in FBVN make the system latency much harder to minimize by traditional methods. In this paper, we model the training and transmission latency of each autonomous vehicle (AV) and consensus latency of the blockchain in-edge side in FBVN. Considering the dynamic and time-varying wireless channel conditions, unpredictable packet error rate, and unstable datasets quality, we adopt duel deep Q-learning (DDQL) as the solving approach. We propose a federated DDQL algorithm, in which the learning agent is deployed on each AV side, and the sensing states on each AV do not need to be shared so that increases scalability and flexibility for practical implementation. Simulation results show that the proposed algorithm has better performance in reducing system latency compared with the other schemes.

Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a big challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN model placement are flexibly coordinated. Specifically, the DNN models, trained and pre-stored in the cloud, are properly placed at the end and edge to perform DNN inference. To achieve efficient DNN inference, a multi-dimensional resource management problem is formulated to maximize the average inference accuracy while satisfying the strict delay requirements of inference tasks. Due to the mix-integer decision variables, it is difficult to solve the formulated problem directly. Thus, we transform the formulated problem into a Markov decision process which can be solved efficiently. Furthermore, a deep reinforcement learning based resource management scheme is proposed to make real-time optimal resource allocation decisions. Simulation results are provided to demonstrate that the proposed scheme can efficiently allocate the available spectrum, caching, and computing resources, and improve average inference accuracy by 31.4 $\%$ compared with the deep deterministic policy gradient benchmark.

Background The increasing occurrence of multidrug-resistant organisms (MDROs) infections has posed major challenge to solid organ transplantation (SOT). For SOT recipients, high-dose immunosuppressants and broad-spectrum antibiotics can markedly increase the risk of early postoperative MDRO infections and thus have adverse effects on the outcomes of SOT. Here, we analyzed the incidence and clinical features of early MDRO infections after SOT, in an attempt to provide new evidence for the control and treatment of early MDROs. Methods The clinical data of 133 patients with MDRO infections after SOT in our department from 2017 to 2020 were retrospectively collected, and clinical features including incidence, etiologies, infection sites, and complications, were analyzed. Results The incidence of MDRO infections after SOT was 9.9%. Simultaneous liver and kidney transplantation patients had the highest incidence of MDRO infections, followed by the recipients of liver transplantation and simultaneous pancreas-kidney transplantation; patients undergoing renal transplantation had the lowest incidence of MDRO infections. The most common pathogen was extended spectrum beta-lactamase (ESBL)-producing organisms (n=88, 66.2%), the most common infection site was the urinary system (n=58, 43.6%), and the main postoperative complications were urinary tract infections (n=44, 33.1%) and lung infections (n=41, 30.8%). MDRO infections were cured in most cases. Conclusions A sound knowledge of the clinical features of MDRO infection after SOT is important for the successful prevention and treatment of these infections.

Background To establish a dietary self-management evaluation indicators scale for kidney transplant recipients and to test the reliability and validity of the scale. Methods Based on the knowledge attitude practice model (KAP model) of health-related behavior changes, an evaluation indicators scale of dietary self-management ability of kidney transplant recipients was constructed through a literature review, expert consultation and group discussion. A questionnaire survey was carried out with 102 kidney transplant recipients from a large tertiary hospital to test the reliability and validity of the constructed scale. Results The dietary self-management ability scale for kidney transplant recipients had 29 items in 3 dimensions. The content validity at the scale level was 0.969, and the content validity at the item level was 0.778-1.000. Exploratory factor analysis extracted 3 common factors, and the cumulative variance contribution rate was 68.610%; the correlation coefficient between each dimension was 0.467-0.629, and the correlation coefficient between each dimension and the total score of the scale was 0.648-0.845. Cronbach's α for the scale was 0.831, and the test-retest reliability of the scale was 0.910. Conclusions The constructed dietary self-management ability scale for kidney transplant recipients has good reliability and validity and can be used as a tool to evaluate the dietary self-management ability of kidney transplant recipients.

This paper proposes a patent citation classification model based on deep learning, and collects the patent datasets in text analysis and communication area from Google patent database to evaluate the classification effect of the model. At the same time, considering the technical relevance between the examiners’ citations and the pending patent, this paper proposes a hypothesis to take the output value of the model as the technology similarity of two patents. The rationality of the hypothesis is verified from the perspective of machine statistics and manual spot check. The experimental results show that the model effect based on deep learning proposed in this paper is significantly better than the traditional text representation and classification method, while having higher robustness than the method combining Doc2vec and traditional classification technology. In addition, we compare between the proposed method based on deep learning and the traditional similarity method by a triple verification. It shows that the proposed method is more accurate in calculating technology similarity of patents. And the results of manual sampling show that it is reasonable to use the output value of the proposed model to represent the technology similarity of patents.

This study investigated the sex-specific differences in the correlation between intestinal microbiota and end-stage renal disease. Here, we compared the differences in the gut microbiota of male and female healthy controls (HC) and patients with end-stage renal disease (ESRD) caused by immunoglobulin A (IgA) nephropathy (ESRD-IgAN) or type-2 diabetes mellitus (ESRD-T2DM) using high-throughput sequencing of the 16S rRNA gene. We also analyzed the correlation between gut microbiota and clinical immune indicators. We assigned 8, 10, 5, 7, 11, and 20 volunteers to female HC, ESRD-IgAN, and ESRD-T2DM, and male HC, ESRD-IgAN, and ESRD-T2DM, respectively. The results showed sex-specific differences in both physiological and biochemical indices and intestinal microbiota composition, as well as the correlation between them. The correlations between physiological and biochemical indices in men were significantly lower than those in women, especially for indices related to immunity, blood glucose, and cardiac color sonography. Urine output, lymphocyte ratio, serum albumin, blood calcium, dialysis status, serum urea nitrogen, urine protein, and diabetes significantly correlated with male fecal microbiota composition, whereas only creatinine and 2-h post-prandial blood glucose significantly correlated with female fecal microbiota composition. The top 50 dominant operational taxonomic units showed a stronger correlation with physiological and biochemical indices in samples obtained from females than from males. These differences highlight sex-specific differences in the effectiveness of ESRD prevention and treatments via regulating intestinal microbiota.

With the tremendous revival of artificial intelligence, predictive maintenance (PdM) based on data-driven methods has become the most effective solution to address smart manufacturing and industrial big data, especially for performing health perception (e.g., fault diagnosis and remaining life assessment). Moreover, because the existing PdM research is still in primary experimental stage, most works are conducted utilizing several open-datasets, and the combination with specific applications such as rotating machinery is especially rare. Hence, in this paper, we focus on data-driven methods for PdM, present a comprehensive survey on its applications, and attempt to provide graduate students, companies, and institutions with the preliminary understanding of the existing works recently published. Specifically, we first briefly introduce the PdM approach, illustrate our PdM scheme for automatic washing equipment , and demonstrate the challenges encountered when we conduct a PdM research. Second, we classify the specific industrial applications based on six algorithms of machine learning and deep learning (DL), and compare five performance metrics for each classification. Furthermore, the accuracy (a metric to evaluate the algorithm performance) of these PdM applications is analyzed in detail. There are some important conclusions: 1) the data used in the summarized literature are mostly from public datasets, such as case western reserve university (CWRU)/intelligent maintenance systems (IMS); and 2) in recent years, researchers seem to focus more on DL algorithms for PdM research. Finally, we summarize the common features regarding our surveyed PdM applications and discuss several potential directions.

Accurate and real-time perception of the operating status of rolling bearings, which constitute a key component of rotating machinery, is of vital significance. However, most existing solutions not only require substantial expertise to conduct feature engineering, but also seldom consider the temporal correlation of sensor sequences, ultimately leading to complex modeling processes. Therefore, we present a novel model, named Attention-based Equitable Segmentation Gated Recurrent Unit Networks (AESGRU), to improve diagnostic accuracy and model-building efficiency. Specifically, our proposed AESGRU consists of two modules, an equitable segmentation approach and an improved deep model. We first transform the original dataset into time-series segments with temporal correlation, so that the model enables end-to-end learning from the strongly correlated data. Then, we deploy a single-layer bidirectional GRU network, which is enhanced by attention mechanism, to capture the long-term dependency of sensor segments and focus limited attention resources on those informative sampling points. Finally, our experimental results show that the proposed approach outperforms previous approaches in terms of the accuracy. NIIT

Background To investigate the application of the superior mesenteric artery (SMA) for the in vitro reconstruction of the hepatic artery for liver transplantation, and to improve the success rate and safety of donor liver transplantation. Methods The donor liver and the pancreas were obtained, and the SMA and its branches were used to reconstruct the hepatic artery. Liver transplantation was performed after reconstruction to understand the intraoperative situation after donor liver opening, as well as postoperative liver function. Color Doppler ultrasound of the transplanted liver was also performed. Results During the period from September 2016 to March 2020, a total of 98 pancreases were obtained. The common hepatic artery and gastroduodenal artery loop (CHA-GDA) were preserved to the donor pancreas, and only the proper hepatic artery (PHA) or left/right hepatic artery (LHA/RHA) were preserved to the donor liver. If the PHA of the donor liver was short or absent, the SMA was used for lengthening the PHA or in vitro reconstruction of the LHA/RHA, followed by implantation of the donor liver after reconstruction. A total of 17 cases of this type of donor liver required mesenteric artery lengthening or reconstruction. After opening, the donor liver was well-filled, bile secretion was normal, and liver function recovered as scheduled after surgery. Color Doppler ultrasound and CT angiography (CTA) of the transplanted liver revealed that hepatic arteries were normal without complications such as hepatic artery embolism. Conclusions In vitro reconstruction of the hepatic artery with the SMA is an effective new method of vascular reconstruction, which ensures the blood flow of the hepatic artery, reduces the anastomosis difficulty of the arteries of the donor liver, and reduces the occurrence of vascular complications.

In this paper, we investigate the joint task assignment and resource allocation for deep neural network (DNN) inference in the device-edge-cloud based industrial Internet of things (IIoT) networks. To efficiently orchestrate the limited spectrum and computing resources in IIoT networks for massive DNN inference tasks, a resource management problem is formulated with the objective of maximizing the average inference accuracy while satisfying the quality-of-service of DNN inference tasks. Considering the strict delay requirements of inference tasks, we transform the formulated problem into a Markov decision process, and propose a deep deterministic policy gradient based learning algorithm to obtain the solution rapidly. Simulation results show that the proposed algorithm can achieve high average inference accuracy.

Apache Kafka, which is a high-throughput distributed message processing system, has been leveraged by the majority of enterprise for its outstanding performance. Unlike common cloud-based access control architectures, Kafka service providers often need to build their systems on other enterprises' high-performance cloud platforms. However, since the cloud platform belongs to a third party, it is not necessarily reliable. Paradoxically, it has been demonstrated that Kafka's data is stored in the cloud in the plaintext form, and thus poses a serious risk of user privacy leakage. In this paper, we propose a secure fine-grained data transmission scheme called Secure Door on Cloud (SDoC) to protect the data from being leaked in Kafka. SDoC is not only more secure than Kafka's built-in security mechanism, but also can effectively prevent third-party cloud from stealing plaintext data. To evaluate the performance of the SDoC, we simulate normal inter-entity communication and show that Kafka with SDoC integration has a lower data transfer time overhead than that of Kafka with built-in security mechanism opened.

Vaccine development utilizing various platforms is one of the strategies that has been proposed to address the coronavirus disease 2019 (COVID-19) pandemic. Adjuvants are critical components of both subunit and certain inactivated vaccines because they induce specific immune responses that are more robust and long-lasting. A review of the history of coronavirus vaccine development demonstrates that only a few adjuvants, including aluminum salts, emulsions, and TLR agonists, have been formulated for the severe acute respiratory syndrome-associated coronavirus (SARS-CoV), Middle East respiratory syndrome-related coronavirus (MERS-CoV), and currently the SARS-CoV-2 vaccines in experimental and pre-clinical studies. However, there is still a lack of evidence regarding the effects of the adjuvants tested in coronavirus vaccines. This paper presents an overview of adjuvants that have been formulated in reported coronavirus vaccine studies, which should assist with the design and selection of adjuvants with optimal efficacy and safety profiles for COVID-19 vaccines.

This paper uses resting-state functional magnetic resonance imaging (rs-FMRI) to construct a whole-brain binary functional network through a complex brain network analysis theory based on graph theory to explore the functional network of patients with type 2 diabetes (T2DM). Changes in topological properties and their potential relationships with fasting blood glucose (FBG), glycated haemoglobin (HbAlc), and cognitive function scale, and further explore the diagnostic value of rs-FMRI technology for central nervous system damage in T2DM patients, for clinical diagnosis and treatment Provide objective radiological evidence. In the range of sparsity (Sp) of 0.05 to 0.50 and a step size of 0.01, compared with the random network, the resting brain functional networks in the T2DM group and the HC group have larger clustering coefficients and similar shortest paths. Length and small world index greater than 1, that is, both groups of resting brain functional networks have small world characteristics. The MoCA score of the T2DM group was positively correlated with the node degree (r = 0.400, p = 0.043) and the node efficiency (r = 0.452, p = 0.021) of the right straight back. FBG is positively correlated with the node degree of the left occipital gyrus (r = 0.422, p = 0.023); HbAlc is related to the node degree of the left occipital gyrus (r = 0.372, p = 0.043) and the node degree of the left occipital gyrus (r = 0.382, p = 0.037) was positively correlated with the node intermediary (r = 0.388, p = 0.034) at the back of the right cingulate gyrus. The topological properties of the resting brain function network of T2DM patients with negative MRI findings have changed compared with normal people, indicating that T2DM is an important factor leading to brain function damage, further explaining the rs-fMRI technology and complex brain networks based on graph theory Analysis theory can be used as an effective method to study the changes of brain function in T2DM patients.

Background The COVID-19 epidemic is still spreading globally. Contact tracing is a vital strategy in epidemic emergency management; however, traditional contact tracing faces many limitations in practice. The application of digital technology provides an opportunity for local governments to trace the contacts of individuals with COVID-19 more comprehensively, efficiently, and precisely. Objective Our research aimed to provide new solutions to overcome the limitations of traditional contact tracing by introducing the organizational process, technical process, and main achievements of digital contact tracing in Hainan Province. Methods A graph database algorithm, which can efficiently process complex relational networks, was applied in Hainan Province; this algorithm relies on a governmental big data platform to analyze multisource COVID-19 epidemic data and build networks of relationships among high-risk infected individuals, the general population, vehicles, and public places to identify and trace contacts. We summarized the organizational and technical process of digital contact tracing in Hainan Province based on interviews and data analyses. Results An integrated emergency management command system and a multi-agency coordination mechanism were formed during the emergency management of the COVID-19 epidemic in Hainan Province. The collection, storage, analysis, and application of multisource epidemic data were realized based on the government’s big data platform using a centralized model. The graph database algorithm is compatible with this platform and can analyze multisource and heterogeneous big data related to the epidemic. These practices were used to quickly and accurately identify and trace 10,871 contacts among hundreds of thousands of epidemic data records; 378 closest contacts and a number of public places with high risk of infection were identified. A confirmed patient was found after quarantine measures were implemented by all contacts. Conclusions During the emergency management of the COVID-19 epidemic, Hainan Province used a graph database algorithm to trace contacts in a centralized model, which can identify infected individuals and high-risk public places more quickly and accurately. This practice can provide support to government agencies to implement precise, agile, and evidence-based emergency management measures and improve the responsiveness of the public health emergency response system. Strengthening data security, improving tracing accuracy, enabling intelligent data collection, and improving data-sharing mechanisms and technologies are directions for optimizing digital contact tracing.

Microarray image processing plays an important role among array analysis and its precision will affect the application of gene chip. However, real microarray images drawn from various experimental procedures may contain noises and other artifacts, which result in a lower image processing accuracy. Hence, in this paper, we propose a novel image denoising method by introducing the compressed sensing theory into microarray image noise reduction. To improve the matching pursuit efficiency, the correlation coefficient is adopted. Experiments on 17 simulated images and 59 real microarray images obtained from the DeRisi, SIB and BCM data sets are conducted. Qualitative and quantitative results compared with the Donoho threshold, generalized wavelet and adaptive thresholding algorithm, reveal that our proposed method performs better on reducing the noises.

In this work, we provide a proof-of-concept experimental demonstration of the wave control capabilities of cellular metamaterials endowed with populations of tunable electromechanical resonators. Each independently tunable resonator comprises a piezoelectric patch and a resistor-inductor shunt, and its resonant frequency can be seamlessly re-programmed without interfering with the cellular structure's default properties. We show that, by strategically placing the resonators in the lattice domain and by deliberately activating only selected subsets of them, chosen to conform to the directional features of the beamed wave response, it is possible to override the inherent wave anisotropy of the cellular medium. The outcome is the establishment of tunable spatial patterns of energy distillation resulting in a non-symmetric correction of the wavefields.

The optimal scheduling of multi-energy hub systems plays an important role in the safety, stability, and economic operation of the system. However, due to the strong uncertainty of renewable energy access, serious coupling, and the interaction among energy hubs of multi-energy hub systems, it is difficult for the traditional optimal scheduling method to solve these problems. Therefore, game theory was used to solve the optimal scheduling problem of multi-energy hub systems. According to the internal connection mode and energy conversion relationship of energy hubs, along with the competitive and cooperative relationship between multi-energy hubs, the game theoretic optimal scheduling model of the multi-energy hub system was established. Then, two cases and 50 groups of wind speed series were used to test the robustness of the proposed method. Simulation results show that the total power injection is &minus, 16,805.8, 104.1847, and &minus, 865.561 and the natural gas injection is 46,046.81, 27,727.65, and 63,039.54 in spring/autumn, summer, and winter, respectively, which is consistent with the characteristics of the four seasons. Furthermore, the optimal scheduling method using game theory has a strong robustness in multi-energy hub systems.