Search

Most of existing mobile edge computing (MEC) studies consider the remote cloud server as a special edge server, the opportunity of edge-cloud collaboration has not been well exploited. We propose a dependency-aware offloading scheme in MEC with edge-cloud cooperation under task dependency constraints. Each mobile device has a limited budget and has to determine which sub-task should be computed locally or should be sent to the edge or remote cloud. We formulate two NP-hard task finishing time minimization sub-problems. We then devise one greedy algorithm with approximation ratio of ${1+\epsilon}$ for the first mode with edge-cloud cooperation without edge-edge cooperation. Then we design an efficient greedy algorithm for the second mode, considering both edge-cloud and edge-edge cooperations. Extensive simulation results show that for the first mode, the proposed greedy algorithm achieves near optimal performance for typical task topologies. On average, it outperforms the modified Hermes benchmark algorithm by about 23%~43.6% in terms of application finishing time with given budgets. By further exploiting collaborations among edge servers in the second cooperation mode, the proposed algorithm helps to achieve over 20.3% average performance gain on the application finishing time over the first mode under various scenarios. Real-world experiments comply with simulation results.

Multi-access edge computing (MEC) has been recently considered in challenging environments lacking available terrestrial infrastructures by extending the computing resources to the air for further enhancing the computation capability of the new aerial user equipment (AUE). Additionally, wireless power transfer (WPT) is a promising solution to prolong the battery lifetime of energy-constrained wireless devices like AUEs. In this paper, we investigate the integration of laser-beamed WPT in the high-altitude platform (HAP) aided MEC systems for the HAP-connected AUEs. By discretizing the three-dimensional coverage space of the HAP, we present a multi-tier tile grid-based spatial structure to provide aerial locations for laser charging. With this setup, we identify a new privacy vulnerability caused by the openness during the air-to-air transmission of WPT signaling messages in the presence of a terrestrial adversary. A privacy-aware laser-powered aerial MEC framework is developed that addresses this vulnerability and enhances the location privacy of AUEs for laser WPT. Specifically, the interaction between the HAP as a defender and the adversary in their tile grid allocation as charging locations to AUEs is formulated as a Colonel Blotto game, which models the competition of the players for limited resources over multiple battlefields for a finite time horizon. Moreover, we derive the mixed-strategy Nash equilibria of the tile grid allocation game for both symmetric and asymmetric tile grids between the defender and the adversary. Simulations results show that the proposed framework significantly outperforms the design baselines with a given privacy protection level in terms of system-wide expected total utilities.

In complex industrial processes, the technique of fault diagnosis has been playing an increasingly considerable role in ensuring the safety of life and property. Unfortunately, the process data of complex industrial processes have the features of high dimension. Feature extraction from high-dimensional data is promising to coping with the fault data with high dimension. Recently, one of manifold learning methods named discriminant locality preserving projection achieves excellent performance in feature extraction. However, the performance of discriminant locality preserving projection (DLPP) is subject to the problem of matrix decomposition in the denominator of the objection function caused by the small sample size (SSS) issue. To overcome this limitation, novel DLPP integrated with Monte Carlo sampling is proposed to enhance the performance of feature extraction through dimensionality reduction. In the proposed MC-DLPP, Monte Carlo sampling is first utilized to generate fault samples for each fault type. With the aid of the virtually generated fault samples, the rank of the matrix in the denominator of the objection function of DLPP increases, thus well addressing the SSS problem. The Softmax classifier is used for fault diagnosis. To test the performance of the improved DLPP-based fault diagnosis, case studies using the Tennessee Eastman process are carried out. Simulation results confirm the presented MC-DLPP achieves superior accuracy in fault diagnosis.

Background: This study aimed to clarify the mechanism of action of Qiangli Wuhu Mixture used in the treatment of pneumonia.Methods: The potential targets of Qiangli Wuhu Mixture in the treatment of pneumonia were predicted by network pharmacology. ICR male mice were randomly divided into 5 groups: normal control (Control), pneumonia model (Vehicle), low and high dose groups of Qiangli Wuhu Mixture, and dexamethasone positive control group with 12 mice in each. The model was established by tracheal instillation of lipopolysaccharide for 3 consecutive days. After the establishment of the animal model, Qiangli Wuhu Mixture was intragastrically administered for 5 days; the expression of inflammatory factors tumor necrosis factor-α (TNF-α), interleukin-1β (IL-1β), interleukin-6 (IL-6) and anti-inflammatory factor interleukin-10 (IL-10) in the serum of mice in each group was detected by ELISA kit; the protective effect of Qiangli Wuhu Mixture on the lung tissue of pneumonia mice was observed by staining; Western Blot was used to detect the expression of Toll-like receptor 4 (TLR4), nuclear factor kappa B (NF-κB) and NLRP3 signal pathway related proteins in lung tissue.Results: Network pharmacology predicted that the target of Qiangli Wuhu Mixture in treating pneumonia might be related to lipopolysaccharide reaction and Toll-like receptor signaling pathway. the in vivo results indicated that Qiangli Wuhu Mixture had a strong protective effect on acute pneumonia in mice induced by lipopolysaccharide, decreased the levels of inflammatory factors TNF-α, IL-1β and IL-6 in serum of model mice, and decreased the activation of TLR4, NF- κ B, and the expression of NLRP3 protein in lung tissue. Conclusion: Qiangli Wuhu Mixture has a strong protective effect on lipopolysaccharide-induced pneumonia in mice, and its mechanism of action may be related to reducing the pathological changes of lung tissue, reducing the level of inflammatory cytokines in blood, and inhibiting the inflammatory signal pathway of TLR4/NF-κB/NLRP3.

In recent years, voice interaction-based control systems have attracted considerable attention for industrial control systems implementing Industrial Internet of Things (IIoT) technologies. The development of automated semantic understanding relates to the industrial Internet equipment used to realize remote voice control as well as to its intelligent management and control. In these emerging voice interaction-enabled industrial central control systems, sorting technologies are considered critical. For complex user questions, the level of satisfaction regarding the answers given by such systems tends to be low. Driven by these challenges and opportunities, the optimization of conventional retrieval-based question answering through deep learning methods has become popular. In this study, we propose three deep semantic sorting models based on deep learning, including a multi-layer convolutional matching sorting model for single documents and two interactive pairwise BERT(Bidirectional Encoder Representations from Transformers) sorting models for document pairs. Two main network architectures are proposed to model document pairs, named Pairwise-Twin-BERT and Pairwise-Triple-BERT. Experimental results indicate that proposed models performed better than state-of-the-art methods based on text matching in a candidate document sorting task.

Glucagon-like peptide-1(GLP-1) is a multifunctional polypeptide throughout the lifespan via activating Glucagon-like peptide-1 receptor (GLP-1R).GLP-1 can affect food ingestion, enhance the secretion of insulin from pancreatic islets induced by glucose and be utilized to treat type 2 diabetes mellitus(T2DM).But, accumulating evidences from the decades suggest that activation GLP-1R can not only regulate the blood glucose, but also sustain the homeostasis of intracellular environment and protect neuron from various damaged responses such as oxidative stress, inflammation, excitotoxicity, ischemia and so on. And more and more pre-clinical and clinical studies identified that GLP-1 and its analogues may play a significant role in improving multiple central nervous system (CNS) diseases including neurodegenerative diseases, epilepsy, mental disorders, ischemic stroke, hemorrhagic stroke, traumatic brain injury, spinal cord injury, chronic pain, addictive disorders, other diseases neurological complications and so on. In order to better reveal the relationship between GLP-1/GLP-1R axis and the growth, development and survival of neurons, herein, this review is aimed to summarize the multi-function of GLP-1/GLP-1R axis in CNS diseases.

Background Secondary structural and functional abnormalities of the neurovascular unit are important pathological mechanisms following traumatic brain injury (TBI). The tumor necrosis factor α (TNF-α)/nuclear factor-κB (NF-κB) pathway regulates neuroinflammation and oxidative damage, which may act as triggers for pathological processes after TBI. However, the role of TNF-α/NF-κB in pericyte-mediated cerebral microcirculation are currently unknown. Methods We assessed the activity and mechanisms of the TNF-α/NF-κB signaling axis on pericyte-mediated microcirculation using the mouse controlled cortical impact model and BV2 cells. Immunofluorescent staining and western blot analysis were used to detect activation of the TNF-α/NF-κB signaling pathway and the expression of inducible nitric oxide synthase (iNOS) to evaluate the effects of the TNF-α specific inhibitor infliximab (IFX). Modified neurological severity scores, Garcia test, Nissl staining, and TUNEL staining were employed to determine the neuroprotective effects of IFX supplementation. The relative blood flow values in the capillary areas surrounding the impinging lesion were observed by Laser speckle contrast imaging. The impact of IFX on pericyte markers was assessed to evaluate whether pericyte damage was dependent on the TNF-α/NF-κB/iNOS axis to gain further insight into the mechanisms underlying the development of the microcirculation disturbance after TBI. Results Microglia were activated after TBI, and the expression of NF-κB, iNOS, a disintegrin and metalloproteinase 17, inflammatory factors, and free radicals increased around the injury areas. After lipopolysaccharide treatment, the expression of TNF-α and downstream NF-κB/iNOS in BV2 cells was significantly upregulated. Pharmacological inhibition of TNF-α via IFX significantly reduced NF-κB p65 phosphorylation and nuclear translocation and downregulated iNOS expression. Meanwhile, we found that specific inhibition of TNF-α reversed pericyte marker loss, and improved pericyte function and cerebral microcirculation perfusion after TBI, which could attenuate inflammation and oxidative damage, reduce neuronal cell damage and apoptosis, and play a neuroprotective role. Conclusion The results of this study suggested that microglia activated and released TNF-α after TBI, which promoted neuroinflammation and oxidative stress by activating downstream NF-κB/iNOS signals, and this led to pericyte-mediated disturbance of the cerebral microcirculation, which may be one of the vital mechanisms of secondary injury in TBI.

A common drawback of EEG-based emotion recognition is that volume conduction effects of the human head introduce interchannel dependence and result in highly correlated information among most EEG features. These highly correlated EEG features cannot provide extra useful information, and they actually reduce the performance of emotion recognition. However, the existing feature selection methods, commonly used to remove redundant EEG features for emotion recognition, ignore the correlation between the EEG features or utilize a greedy strategy to evaluate the interdependence, which leads to the algorithms retaining the correlated and redundant features with similar feature scores in the EEG feature subset. To solve this problem, we propose a novel EEG feature selection method for emotion recognition, termed global redundancy minimization in orthogonal regression (GRMOR). GRMOR can effectively evaluate the dependence among all EEG features from a global view and then select a discriminative and nonredundant EEG feature subset for emotion recognition. To verify the performance of GRMOR, we utilized three EEG emotional data sets (DEAP, SEED, and HDED) with different numbers of channels (32, 62, and 128). The experimental results demonstrate that GRMOR is a promising tool for redundant feature removal and informative feature selection from highly correlated EEG features.

Mobile Edge Computing (MEC) infrastructure raises security concerns when the shared resources involve sensitive and private data of users. This paper proposes a novel blockchain-based key management scheme for MEC that is essential for ensuring secure group communication among the devices. In the proposed scheme, when a mobile device joins a subnetwork, it first generates lightweight key pairs, and broadcasts its public key to neighbouring peer users. The blockchain miner in the subnetwork packs all the public key of mobile devices into a block that will be sent to other users. This enables the mobile device to communicate with its peers in the subnetwork by encrypting the data with the public key stored in the blockchain. When the mobile device moves to another subnetwork, all the mobile devices of the new subnetwork can quickly verify its identity by checking its record in the local or higher hierarchy subnetwork blockchain. Theoretical security analysis shows that the proposed scheme can defend against the 51% attack and malicious entities in the blockchain network. Moreover, the backward and forward secrecy is also preserved. Experimental results demonstrate that the proposed scheme outperforms two baselines in terms of computation, communication and storage.

Healthcare delivery systems are evolving with the advances in health information technology (HIT) development and its applications to coordinated or guided care for polychronic conditions. The design features of artificial intelligence in healthcare reflect the public interest in optimizing care coordination and communication between providers and patients. This article offers a practical evaluation and assessment of the relevance of theoretical frameworks and appropriate methodologies to formalize a multi-criteria optimization of a logic model applicable for achieving the system’s efficiency and effectiveness. In specifying theoretical constructs and evaluation methods for HIT evaluation, a three-fold purpose is to show the relevance of personal and behavioral determinants of HIT use, articulate the need for developing a transdisciplinary framework, and formulate appropriate multilevel modeling and causal analysis of the determinants of HIT use and its impacts on chronic care.

The faces and hands of caregivers and other social partners offer a rich source of social and causal information that is likely critical for infants' cognitive and linguistic development. Previous work using manual annotation strategies and cross-sectional data has found systematic changes in the proportion of faces and hands in the egocentric perspective of young infants. Here, we validated the use of a modern convolutional neural network (OpenPose) for the detection of faces and hands in naturalistic egocentric videos. We then applied this model to a longitudinal collection of more than 1,700 head-mounted camera videos from three children ages 6 to 32 months. Using these detections, we confirm and extend prior results from cross-sectional studies. First, we found a moderate decrease in the proportion of faces in children's view across age and a higher proportion of hands in view than previously reported. Second, we found variability in the proportion of faces and hands viewed by different children in different locations (e.g., living room vs. kitchen), suggesting that individual activity contexts may shape the social information that infants experience. Third, we found evidence that children may see closer, larger views of people, hands, and faces earlier in development. These longitudinal analyses provide an additional perspective on the changes in the social information in view across the first few years of life and suggest that pose detection models can successfully be applied to naturalistic egocentric video data sets to extract descriptives about infants' changing social environment. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Cold-formed steel members are usually used as purlins in buildings to support roof cladding and thus they can be treated as beams restrained fully or partially in the lateral and torsional directions. However, when these beams are subjected to wind suction loading, their free flange is in compression, which may cause web–flange distortional buckling (WFDB). This paper presents an analytical study on the WFDB of zed-section purlins when subjected to uplift bending. A simplified model is proposed to describe the WFDB of partially restrained purlins, from which the formula for calculating the critical stress of the WFDB is derived. The present model is validated by the results obtained from the finite strip analysis.

As Internet users interacting with their different friends in different social networks, the de-anonymization problem has been raising improving concern. Since the assailants may de-anonymize a social network by matching it with a correlated sanitized network and identifying anonymized user identities, multifarious arts study on the theoretical conditions or practical algorithms for correctly de-anonymizing a social network. Except for the structural information of these social networks, there has also been bounteous works taking advantage of some pre-identied seed nodes for reference in the anonymized network. In this paper, we systematically probe the theoretical conditions and algorithmic approaches for correctly matching two different-sized social networks by leveraging the multi-hop neighborhood relationships. A limited number of seeds are also taken into consideration as auxiliary information. To this end, we introduce the de-anonymization problem with the aid of the collectiveness and the collective adjacency disagreements, which are the collection of disagreements of different multi-hop adjacency matrices. We theoretically demonstrate that minimizing the collective adjacency disagreements can help match two social networks even in a very sparse circumstance, as it signicantly enlarges the difference between the mismatched node pairs and the correctly matched pairs. The seeds is proved to bring positive inuence in accuracy.

BACKGROUND Patients with pudendal neuralgia (PN) experience long-lasting chronic pain, hyperalgesia, and comorbid emotional disorders, such as depression and anxiety. Treatment via conventional pulsed radiofrequency (PRF) current carries a significantly high rate of failure. OBJECTIVE To determine the safety and clinical efficacy of high-voltage, long-duration PRF application to the pudendal nerve in patients with PN. STUDY DESIGN Observational retrospective design, self before-after controlled clinical trial. MATERIALS AND METHODS We analyzed the records of 70 patients of our hospital with diagnosed PN. Treatment consisted of PRF application to the pudendal nerve, using computed tomography guidance to target the pudendal nerve at the level of the ischial spine or ischial tuberosity of the affected side. PRF was applied with the following parameters: temperature 42°C, frequency 2 Hz, pulse width 20 ms, field intensity ramped gradually from 40 to 90 V, duration 900 sec. The therapeutic effect was evaluated by collecting patient scores for the visual analog scale (VAS), SF-36 health survey questionnaire (SF-36), and patient health questionnaire (PHQ-9) before treatment and at 1-, 4-, and 12-week follow-ups after PRF treatment. Data were analyzed by paired t-test with p

HIV prevalence is high among transgender women, but little is known about cisgender men who have sex with transgender women (MSTW). The objective of this study was to investigate characteristics and behavior of MSTW compared to transgender women and men who have sex with men (MSM) using a modified respondent-driven sampling design. Seed participants completed a survey and invited up to three sex partners. Forward recruitment continued in waves through the referral of sex partners. Cross-sectional data were assessed using mixed effects models. From February to July 2018, 479 participants in Lima, Peru enrolled (

A concern with the isolation transformer in a dual active bridge (DAB) dc–dc converter is the dc bias in magnetization. This article proposes a fluxgate-based current sensor to measure the dc component mixed with a large, high-frequency ac current. Compared with a commercial Hall effect current sensor, the proposed sensor significantly reduces measurement error. This article presents the working principle and design considerations. A prototype is demonstrated for dc bias elimination control in a DAB converter.\ud

Network measurement provides operators an efficient tool for many network management tasks such as performance diagnosis, traffic engineering and intrusion prevention. However, with the rapid and continuous growth of traffic speed, it needs more computing and memory resources to monitor traffic in per-flow or per-packet granularity. Sample-based measurement systems (e.g., NetFlow, sFlow) have been developed to perform coarse-grained measurement, but they may miss part of records, especially for mice flows, which are important for some network management tasks (e.g., anomaly detection, performance diagnosis). To address these issues, data streaming algorithms such as hash tables and sketches have been introduced to balance the trade-off among accuracy, speed, and memory usage. In this paper, we present a systematic survey of various data structures, algorithms and systems which have been proposed in recent years to perform fine-grained measurement for high-speed networks. We organize these methods and systems from a software-defined perspective. In particular, we abstract fine-grained network measurement into three-layer architecture. We introduce the responsibility of each layer and categorize existing state-of-the-art works into this architecture. Finally, we conclude the paper and discuss the future directions of fine-grained network measurement.

Deep neural networks have achieved breakthrough improvement in various application fields. Nevertheless, they usually suffer from a time-consuming training process because of the complicated structures of neural networks with a huge number of parameters. As an alternative, a fast and efficient discriminative broad learning system (BLS) is proposed, which takes the advantages of flat structure and incremental learning. The BLS has achieved outstanding performance in classification and regression problems. However, the previous studies ignored the reason why the BLS can generalize well. In this article, we focus on the interpretation from the viewpoint of the frequency domain. We discover the existence of the frequency principle in BLS, i.e., the BLS preferentially captures low-frequency components quickly and then fits the high frequencies during the incremental process of adding feature nodes and enhancement nodes. The frequency principle may be of great inspiration for expanding the application of BLS.

This article deals with the problem of secure distributed adaptive platooning control of automated vehicles over vehicular ad-hoc networks (VANETs) in the presence of intermittent denial-of-service (DoS) attacks. The platoon, which is wirelessly connected via directed vehicle-to-vehicle (V2V) communication, is composed of a group of following vehicles subject to unknown heterogeneous nonlinearities and external disturbance inputs, and a leading vehicle subject to unknown nonlinearity and external disturbance as well as an unknown control input. Under such a platoon setting, this article aims to accomplish secure distributed platoon formation tracking with the desired longitudinal spacing and the same velocities and accelerations guided by the leader regardless of the simultaneous presence of nonlinearities, uncertainties, and DoS attacks. First, a new logical data packet processor is developed on each vehicle to identify the intermittent DoS attacks via verifying the time-stamps of the received data packets. Then, a scalable distributed neural-network-based adaptive control design approach is proposed to achieve secure platooning control. It is proved that under the established design procedure, the vehicle state estimation errors and platoon tracking errors can be regulated to reside in small neighborhoods around zero. Finally, comparative simulation studies are provided to substantiate the effectiveness and merits of the proposed control design approach on maintaining the desired platooning performance and attack tolerance.

Multi-FPGA architecture has gained great interests in accelerating large-scale graph processing with great potential on high throughput and energy efficiency. As a beneficial complement, work stealing functions effectively to balance the computational workload on different FPGAs dynamically. Unfortunately, existing graph partitioning schemes originally designed in distributed settings potentially mismatch the work stealing-enabled multi-FPGA situations, where the computation is balanced while the communication overhead is unprecedentedly significant over otherwise. In this paper, we present a 2-dimension balanced graph partitioning for work stealing assisted graph system on multi-FPGAs, which can reduce communication overhead while preserving the optimal performance of work stealing. Our approach is novel by 1) exploring the tradeoff between load balance dimension and communication dimension in work-stealing-enabled graph processing system for the optimal performance, and 2) optimizing the memory access sequences to improve the granularity of graph partitioning for high-throughput graph analytics. Our experimental results show that our approach achieves 1.63∼2.56x speedups compared with state-of-the-art FPGA-based systems.

Most supervised learning-based pose estimation methods for stacked scenes are trained on massive synthetic datasets. In most cases, the challenge is that the learned network on the training dataset is no longer optimal on the testing dataset. To address this problem, we propose a pose regression network PPR-Net++. It transforms each scene point into a point in the centroid space, followed by a clustering process and a voting process. In the training phase, a mapping function between the network's critical parameter (i.e., the bandwidth of the clustering algorithm) and the compactness of the centroid distributions is obtained. This function is used to adapt the bandwidth between centroid distributions of two different domains. In addition, to further improve the pose estimation accuracy, the network also predicts the confidence of each point, based on its visibility and pose error. Only the points with high confidence have the right to vote for the final object pose. In experiments, our method is trained on the IPA synthetic dataset and compared with the state-of-the-art algorithm. When tested with the public synthetic Sileane dataset, our method is better in all eight objects, where five of them are improved by more than 5% in average precision (AP). On IPA real dataset, our method outperforms a large margin by 20%. This lays a solid foundation for robot grasping in industrial scenarios.

The structure stability of the diameter-expanded conductor with fewer inner wires is the principal limitation in its large-scale use at present. As the traditional design method cannot be adopted to solve this problem, the instability properties of the diameter-expanded conductors were studied in this paper. To perform this analysis, different typical diameter-expanded conductors with fewer inner wires were chosen for the sheave tests under different working conditions at first. Then the simulation model as well as the instability criterion was established to analyze the influence factors of the structure stability. Finally, the synchronous stringing tests were carried out to assess the correctness of the model proposed. The results showed that the weakened support of the inner layer(s) and the local buckling of the external wires are the main causes of the wire jumping phenomenon. Therefore, a reasonable increase in the outmost wires gap and decrease in the inner wires gap are feasible to improve the load-carrying ability of the diameter-expanded conductor.

Middle age is increasingly accepted as a key period during which individuals are susceptible to the effect of environmental and lifestyle factors. Emerging research indicates that dietary factors play a crucial role in brain health and cognitive function, and studies in both animals and humans have demonstrated that dietary interventions can mitigate cognitive impairment. Specifically, magnesium has been shown to enhance learning and memory, and magnesium deficiency is associated with impaired hippocampal-dependent memory formation in animal studies. The aim of this study was to examine if supplementation with a magnesium-rich marine mineral blend (MMB) could alter middle-age-related cognitive impairment. Young and middle-aged rats were given access to a control diet or an experimental diet formulated with an MMB for 4 weeks before undergoing a series of behavioral assessments. Supplementation of MMB to middle-aged rats rescued a deficit in cognitive impairment, specifically a pattern separation paradigm that is sensitive to alterations in a type of brain plasticity called neurogenesis. It had no effect on general activity in the open field or performance on other hippocampal-associated tasks. Changes in cognitive function occur as a predictable consequence of aging. Research into whether modification of dietary factors, such as this MMB, may play a role in the prevention of age-related cognitive impairment warrants further investigation.

In this paper, we propose to use production executions to improve the quality of testing for certain methods of interest for developers. These methods can be methods that are not covered by the existing test suite, or methods that are poorly tested. We devise an approach called PANKTI which monitors applications as they execute in production, and then automatically generates differential unit tests, as well as derived oracles, from the collected data. PANKTI's monitoring and generation focuses on one single programming language, Java. We evaluate it on three real-world, open-source projects: a videoconferencing system, a PDF manipulation library, and an e-commerce application. We show that PANKTI is able to generate differential unit tests by monitoring target methods in production, and that the generated tests improve the quality of the test suite of the application under consideration.

Objective To investigate whether epileptiform discharge burden can identify those at risk for delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH). Methods Retrospective analysis of 113 moderate to severe grade SAH patients who had continuous EEG (cEEG) recordings during their hospitalization. We calculated the burden of epileptiform discharges (ED), measured as number of ED per hour. Results We find that many SAH patients have an increase in ED burden during the first 3–10 days following rupture, the major risk period for DCI. However, those who develop DCI have a significantly higher hourly burden from days 3.5–6 after SAH vs. those who do not. ED burden is higher in DCI patients when assessed in relation to the onset of DCI (area under the receiver operator curve 0.72). Finally, specific trends of ED burden over time, assessed by group-based trajectory analysis, also help stratify DCI risk. Conclusions These results suggest that ED burden is a useful parameter for identifying those at higher risk of developing DCI after SAH. The higher burden rate associated with DCI supports the theory of metabolic supply-demand mismatch which contributes to this complication. Significance ED burden is a novel biomarker for predicting those at high risk of DCI.

Piezoelectric energy harvester (PEH) arrays are promising in many application scenarios. However, few interface circuits have been developed to manage the multiple AC inputs from PEHs. This paper proposes an extensible P-SSHI (parallel synchronized switch harvesting on inductor) array interface scheme to realize a multi-input conversion from PEH arrays. We develop a split-inductor-capacitor topology that can extract electrical energy from multiple PEHs. The proposed circuit topology effectively handles the inductor access conflict in the cases of PEHs with close, identical, and opposite vibration phases, insensitive to AC input phase changes. For demonstrating the capability of dealing with multiple AC inputs from PEHs and the enhancement effect on power output, we construct and test a self-powered three-channel array circuit with the passive peak detection function. Excited by sinusoidal vibrations, our circuit effectively avoids the energy return and efficiently achieves the power combination of the three PEHs. Compared with the classic full-bridge circuit, the proposed circuit helps increase the power output by 4.8 times. Also, to show the universality of the circuit, the circuits operation under various excitations is tested and analyzed.

Although cloud computing is one of the promising technologies for online business services, how to schedule real-time cloud jobs with high quality of service (QoS) is still challenging current techniques. With the advancing of machine learning, deep reinforcement learning (DRL) has demonstrated its outstanding capability in dispatching time-sensitive tasks. However, the reinforced rewards in DRL are typically unavailable until the completion of the scheduling for all the jobs. Considering the fact that the trajectory of jobs in cloud is always long, current DRL-based solutions will meet challenges in finding the trajectories with high rewards, and thus would have issues such that the finally trained scheduling policy is suboptimal. To improve the problem, in this article, we propose a more advanced approach called a deep adversarial imitation reinforcement learning (AIRL) framework for scheduling time-sensitive cloud jobs. Specifically, we focus on scheduling user requests in a way to maximize job successful rate along with a significant reduction on job response time. We present the detailed design of our method, and our experimental results demonstrate that AIRL can generally outperform the existing cloud job scheduling approaches, including the DRL-based method, in the presence of different real-time workload and computing resource configurations.

Underwater image enhancement has always been a hot spot in underwater vision research. However, due to complicated underwater environment, a lot of problems such as the color distortion and low brightness of underwater raw images are very likely to occur. In response to the above situation, we proposed a generative adversarial network that integrated multiple attention to enhance underwater images. In the generator, we introduced multi-layer dense connections and CSAM modules, of which the former could capture more detailed features and make use of previous features, while the latter could improve the utilization of the feature map. Meanwhile, we improved the enhancement effect of the generated image by combining VGG19 content loss function and SmoothL1 loss function. Finally, we verified the effectiveness of the proposed model through qualitative and quantitative experiments, and compared the results with the performance of several latest models. The results show that the methods proposed in this paper are superior to the existing methods.

In recent years, the incidence of skin diseases has increased significantly, and some malignant tumors caused by skin diseases have brought great hidden dangers to people’s health. In order to help experts perform lesion measurement and auxiliary diagnosis, automatic segmentation methods are very needed in clinical practice. Deep learning and contextual information extraction methods have been applied to many image segmentation tasks. However, their performance is limited due to insufficient training of a large number of parameters and these parameters sometimes fail to capture long-term dependencies. In addition, due to the many interfering factors of the skin disease image, the complex boundary and the uncertain size and shape of the lesion, the segmentation of the skin disease image is still a challenging problem. To solve these problems, we propose a long-distance contextual attention network(LCA-Net). By connecting the non-local module and the channel attention (CAM) in parallel to form a non-local operation, the long-term dependence is captured from the two dimensions of space and channel to enhance the network’s ability to extract features of skin diseases. Our method has an average Jaccard index of 0.771 on the ISIC2017 dataset, which represents a 0.6%improvement over the ISIC2017 Challenge Champion model. The average Jaccard index of 5-fold cross-validation on the ISIC2018 dataset is 0.8256. At the same time, we also compared with some advanced methods of image segmentation, the experimental results show our proposed method has a competitive performance.

Infection is a serious adverse event limiting left ventricular assist device (LVAD) therapy in advanced heart failure patients, but a reliable means to identify patients at increased risk of infection is still lacking. We hypothesized that preoperative elevated levels of plasma Oncostatin M (OSM), a cytokine marker of leukocyte activation and inflammation, would be predictive of subsequent infection. We measured plasma OSM in 41 LVAD patients one day before LVAD implantation and postoperatively over two months. Preoperative plasma OSM levels were normal in 27 patients (group A, 4.9 ± 3.2 pg/ml) but elevated in 14 patients (group B, 1649.0 ± 458.9 pg/ml) ( p = 0.003). Early postoperative levels rose in both groups and declined rapidly in group A, with group B declining slowly over two months. Significantly more infections developed in group B than group A patients over two months postimplantation ( p = 0.004). No other routine clinical assessment or laboratory testing afforded this differentiation. These findings suggest that preoperative plasma OSM levels may assist in identifying patients at increased risk of infections after LVAD implantation.

An adaptively smart wireless power transfer (WPT) system is proposed by using a 2-bit programmable metasurface (PMS), in which an in-door dynamic charging application scenario is described and near-field focused (NFF) technique is adopted to transmit wireless powers. Theoretical analyses of NFF PMS are presented to illustrate its WPT capabilities. To implement dynamic WPTs, digital phase-shift quantization of PMS element is investigated, indicating that 2-bit quantization scheme is a preferred solution. A 2-bit 1212 PMS operating at 5.8GHz is designed, fabricated and tested. High-power focal spots that can be regulated to focus at different near-field positions are measured in an anechoic chamber. We conduct multiple WPT experiments by using the 2-bit PMS as the transmitter and a 44 microstrip array antenna as the receiver. Experimental results show that the proposed 2-bit PMS can continuously transmit the wireless powers to the receiver even though the target is moving, and the WPT efficiency is maintained over 9.1%, which has about 16.3 dB improvement at the end of the trajectory compared to the fixed NFF beam. This work is one of attempts to thoroughly examine the possibility of the dynamic WPTs using PMS, offering a brand-new manner for the adaptively smart WPT systems.

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point--the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d., 13 pages, 5 figures

In this article, we study the consensus issues of multiagent systems (MASs) without any information of the system model by using the reinforcement learning (RL) method and event-based control strategy. First, we design an adaptive event-based consensus control protocol using the local sampled state information so that the consensus errors of all agents are uniformly ultimately bounded. The validity of the above event-triggered adaptive control protocol is confirmed by excluding the Zeno behavior within finite time. Then, based on the RL approach, we present a model-free algorithm to get the feedback gain matrix, and accomplish constructing the adaptive event-triggered control strategy without the knowledge of model information. Distinct with the existing related works, this RL-based event-triggered adaptive control algorithm only relies on the local sampled state information, irrelevant to any model information or global network information. Finally, we provide some examples to demonstrate the validity of the above adaptive event-based consensus algorithm.

Enhancing visual qualities for underexposed images is an extensively concerned task that plays important roles in various areas of multimedia and computer vision. Most existing methods often fail to generate high-quality results with appropriate luminance and abundant details. To address these issues, we in this work develop a novel framework, integrating both knowledge from physical principles and implicit distributions from data to solve the underexposed image correction task. More concretely, we propose a new perspective to formulate this task as an energy-inspired model with advanced hybrid priors. A propagation procedure navigated by the hybrid priors is well designed for simultaneously propagating the reflectance and illumination toward desired results. We conduct extensive experiments to verify the necessity of integrating both underlying principles (i.e., with knowledge) and distributions (i.e., from data) as navigated deep propagation. Plenty of experimental results of underexposed image correction demonstrate that our proposed method performs favorably against the state-of-the-art methods on both subjective and objective assessments. Additionally, we execute the task of face detection to further verify the naturalness and practical value of underexposed image correction. What's more, we employ our method to single image haze removal whose experimental results further demonstrate its superiorities., Submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Project page: http://dutmedia.org/HPNDP/

Automatic inspections of overhead contact lines (OCLs) are developed to implement anomaly detection during normal operation. It is an essential prerequisite for efficient maintenance of railway electrification system. This paper presents a comprehensive survey on the inspections of OCLs with an emphasis on computer vision technology, which has developed rapidly due to its ability to understand images. Our survey begins with a brief introduction on anomalies in OCL inspections and generic procedures of computer vision inspection for anomaly detection. Subsequently, for detecting deviations of parameters and defective components during OCL inspections, the existing techniques involving stereo vision and object vision, especially convolution neural networks are described in detail from two aspects: measurement of OCL parameters and identification of OCL conditions. Some interference factors in OCL inspection are analyzed. Actual cases of the inspections are also briefly shown. Challenges and suggestions for further research on OCL inspection are drawn toward the end of the paper.

Extra-corporeal membrane oxygenation (ECMO) can be used to treat patients with severe cardiac and/or pulmonary failure. ECMO has been used during pregnancy, at the time of delivery and in the post-partum period with favorable maternal and fetal outcomes.1 In our case, ECMO was initiated intra-operatively during hemorrhagic shock associated with a caesarean delivery, and accompanied by severe pulmonary edema, mitral regurgitation, hypoxia, and cardiac arrest. Research has shown that there is an optimal timing for ECMO initiation. Favorable outcomes are often seen with early initiation.2 This is especially true in pregnancy, when both maternal and fetal health are at stake.2

Infrastructure-to-vehicle (I2V) and vehicle-to-vehicle (V2V) communications are often combined to extend the connectivity and coverage in the Intelligent Transportation System (ITS) and its applications, e.g., augmented reality, real-time parking management and online shopping. Through multi-hop I2V and V2V communications, requesting vehicles are always connected to road side units (RSUs) even when they do not reside within the RSUs' coverage range. However, there may be not adequate network resource for several I2V and V2V links when multiple vehicles request services simultaneously. In this paper, we propose a joint frequency scheduling and power control scheme to enhance connectivity in multi-hop I2V/V2V networks. We associate I2V and V2V links with tuple-links, then formulate an NP-hard problem in which a frequency scheduler and a power controller are jointly designed for the tuple-links. The NP-hard problem is decomposed into two separate subproblems by employing the delayed column generation technique. Then, we employ a method for linear programming and a greedy algorithm to address these subproblems. Through numerical experiments with practical parameter settings, we demonstrate the proposed scheme outperforms several existing ones in terms of connectivity enhancement, measured by the service resumption number and average achieved throughput. Furthermore, the efficiency of our scheme is further enhanced when the number of available channels is high, and buffer size equipped to the requesting vehicles is large.

In this study, a distributed hybrid flow shop scheduling problem with variable speed constraints is considered. To solve it, a knowledge-based adaptive reference points multi-objective algorithm (KMOEA) is developed. In the proposed algorithm, each solution is represented with a three-dimensional vector, where the factory assignment, machine assignment, operation scheduling and speed setting are encoded. Then, four problem-specific lemmas are proposed, which are used as the knowledge to guide the main components of the algorithm, including the initialization, global and local search procedures. Next, an efficient initialization approach is presented, which embedded with several problem-related initialization rules. Furthermore, a novel Pareto-based crossover heuristic is designed to learn from more promising solutions. To enhance the local search abilities, a speed adjustment local search method is investigated. Finally, a set of instances generated based on the realistic prefabricated production system is tested to verify the efficiency and effectiveness of the proposed algorithm.

Purpose Anti-CD19 chimeric antigen receptor T-cell immunotherapy (19CAR-T) has achieved impressive clinical results in adult and pediatric relapsed/refractory (r/r) B-lineage acute lymphoblastic leukemia (B-ALL). However, the application and effect of CAR-T therapy in B-ALL patients with extramedullary relapse are rarely issued even disqualified in some clinical trials. Here, we examined the efficacy of 19CAR-T in patients with both bone marrow and extramedullary involvement. Materials and methods CAR-T cells were generated by transfection of primary human T lymphocytes with a lentiviral vector expressing anti-CD19 single chain antibody fragments (scFvs) with the cytoplasmic domains of 4-1BB and CD3ζ, and used to infuse patients diagnosed as having r/r B-ALL with extramedullary origination. Clinical responses were evaluated by the use of bone marrow aspiration, imaging, and flow cytometry. Results Eight patients received 19CAR-T infusion and all attained complete remission (CR). Only one patient was bridged to hematopoietic stem cell transplantation (HSCT). Although three patients relapsed after infusion, they received 19/22CAR-T infusion sequentially and attained a second remission. To date, five patients are in continuous CR and all eight patients are still alive. The mean follow-up time was 21.9 months, while the 24-month estimated event-free survival is 51.4%. Conclusion Anti-CD19 CAR-T therapy can lead to clinical remission for extramedullary relapsed pediatric B-ALL patients. However, the problem of CD19+ relapses after CAR-T remained to be solved. For patients relapsing after CAR-T, a second CAR-T therapy creates another opportunity for remission for subsequent HSCT.

Deep learning-based auto-driving systems are vulnerable to adversarial examples attacks which may result in wrong decision making and accidents. An adversarial example can fool the well trained neural networks by adding barely imperceptible perturbations to clean data. In this paper, we explore the mechanism of adversarial examples and adversarial robustness from the perspective of statistical mechanics, and propose an statistical mechanics-based interpretation model of adversarial robustness. The state transition caused by adversarial training based on the theory of fluctuation dissipation disequilibrium in statistical mechanics is formally constructed. Besides, we fully study the adversarial example attacks and training process on system robustness, including the influence of different training processes on network robustness. Our work is helpful to understand and explain the adversarial examples problems and improve the robustness of deep learning-based auto-driving systems.

In recent years, China's rural areas have undergone intense restructuring motivated by various flows derived from e-commerce, which has triggered a new wave of rural rejuvenation. Attempting to reveal the process and mechanism of rural economic restructuring driven by e-commerce, this paper takes Xiaying village in central China to conduct an empirical study by introducing the theory of “space of flows” and applying the method of semi-structured interview. The results show that e-commerce has become a technical catalyst to the variation of industry structure, employment pattern and household economy. Xiaying village has performed a leap from traditional agriculture to commercial service and constructed a complete e-commerce oriented industry chain, which is distinguished from the traditional path of rural modernization adhering to the gradual evolution of the primary, secondary and tertiary industry in China. In response, the employment pattern is diversified and tends to be de-agriculturalization, thus providing an economic advancement opportunity for rural households. As a matter of fact, rural elites, technology innovation (e-commerce platform), resource endowments and government support all contributed greatly to this restructuring process. What distinguishes it from others is the strong mobility and exchange of urban and rural elements, which functions as the initial engine. Essentially, this transition can be considered as the impact of the network on the geographic space restructuring rural economy.

Head-mounted loupes can increase the user's visual acuity to observe the details of an object. On the other hand, optical see-through head-mounted displays (OST-HMD) are able to provide virtual augmentations registered with real objects. In this article, we propose AR-Loupe, combining the advantages of loupes and OST-HMDs, to offer augmented reality in the user's magnified field-of-vision. Specifically, AR-Loupe integrates a commercial OST-HMD, Magic Leap One, and binocular Galilean magnifying loupes, with customized 3D-printed attachments. We model the combination of user's eye, screen of OST-HMD, and the optical loupe as a pinhole camera. The calibration of AR-Loupe involves interactive view segmentation and an adapted version of stereo single point active alignment method (Stereo-SPAAM). We conducted a two-phase multi-user study to evaluate AR-Loupe. The users were able to achieve sub-millimeter accuracy ( 0.82 mm) on average, which is significantly ( ) smaller compared to normal AR guidance ( 1.49 mm). The mean calibration time was 268.46 s. With the increased size of real objects through optical magnification and the registered augmentation, AR-Loupe can aid users in high-precision tasks with better visual acuity and higher accuracy.

In industrial applications, different abnormal conditions of a machine or a machinery fleet typically occur sequentially instead of becoming initially known. Therefore, one of the most challenging tasks for the machinery fault diagnosis is to incrementally classify unknown abnormal patterns. For this reason, an incremental novelty identification (INI) method is proposed, on the strength of deep learning-based representation learning, novelty detection and incremental learning. In the INI framework, a convolutional neural network autoencoder is first developed for high-level feature extraction from multiple monitoring signals. An online sequential-extreme learning machine (OS-ELM) is then proposed to learn healthy features of the normal condition initially known. The newly collected data are employed for updating the OS-ELM with the quantification of the model modification for novelty detection. An incremental learning procedure is implemented by adding a new OS-ELM model representing the novel abnormal pattern. The repository of OS-ELMs, each of which represents a specific condition, is employed for incrementally diagnosing known abnormal patterns with the identification of unknown ones. The performance of the proposed INI is validated under experimental scenarios considering both a benchmark bearing case study and a delta 3D printer, and the results are compared with other state-of-the-art approaches.

Alternative splicing enables a gene translating into different isoforms and into the corresponding proteoforms, which actually accomplish various biological functions of a living body. Isoform-isoform interactions (IIIs) provide a higher resolution interactome to explore the cellular processes and disease mechanisms than the canonically studied protein-protein interactions (PPIs), which are often recorded at the coarse gene level. The knowledge of IIIs is critical to map pathways, understand protein complexity and functional diversity, but the known IIIs are very scanty. In this paper, we propose a deep learning based method called DeepIII to systematically predict genome-wide IIIs by integrating diverse data sources, including RNA-seq datasets of different human tissues, exon array data, domain-domain interactions (DDIs) of proteins, nucleotide sequences and amino acid sequences. Particularly, DeepIII fuses these data to learn the representation of isoform pairs with a four-layer deep neural networks, and then performs binary classification on the learnt representation to achieve the prediction of IIIs. Experimental results show that DeepIII achieves a superior prediction performance to the state-of-the-art solutions and the III network constructed by DeepIII gives more accurate isoform function prediction. Case studies further confirm that DeepIII can differentiate the individual interaction partners of different isoforms spliced from the same gene. The code and datasets of DeepIII are available at http://mlda.swu.edu.cn/codes.php?name=DeepIII.

Understanding consumer preference for products or services is important for users (individuals, platforms, merchants, and so forth) to make decisions. However, the preference is difficult to observe. Based on the online ratings of consumers, we convert the ratings into pairwise comparisons and present an online optimization model to derive the ranking orders of the products or services. We employ a Continuous Exp strategy to develop a learning algorithm to solve the online optimization problem, which has almost the same performance as the best strategy ex-post. This approach can not only handle dynamic rating information with arbitrary rating distribution but is also efficient in computation. We also investigate the impact of the learning rate on the ranking order and provide a real-world application of a recommendation system for illustration.

Real-time inference of deep learning models on embedded and energy-efficient devices becomes increasingly desirable with the rapid growth of artificial intelligence on edge. Specifically, to achieve superb energy-efficiency and scalability, efficient parallelization of single-pass deep neural network (DNN) inference on chip multiprocessor (CMP) architectures is urgently required by many time-sensitive applications. However, as the number of processing cores scales up and the performance of cores has grown much fast, the on-chip inter-core data movement is prone to be a performance bottleneck for computation. To remedy this problem and further improve the performance of network inference, in this work, we introduce a communication-aware DNN parallelization technique called CAP, by exploiting the elasticity and noise-tolerance of deep learning algorithms on CMP. Moreover, in the hope that the conducted studies can provide new design values for real-time neural network inference on embedded chips, we also have evaluated the proposed approach on both multi-core Neural Network Accelerators (NNA) chips and general-purpose chip-multiprocessors. Our experimental results show that the proposed CAP can achieve 1.13x-1.65x speedups and 51%-90% on-chip communication energy reduction for different neural networks while maintaining the inference accuracy, compared to baseline approaches.

This paper proposes a generalized deep continual learning-based cybertwin (GDC) modeling framework for developing one wind turbine (WT) cybertwin serving multiple modeling tasks in the wind farm operations and maintenance (O&M). A generalized WT cybertwin modeling problem is first formulated. Fully connected deep neural networks (DNNs) are adopted as the backbone for developing the GDC. The online elastic weight consolidation (OEWC) method is incorporated to mitigate the catastrophic forgetting phenomenon among different modeling tasks. Computational experiments are conducted to validate the effectiveness of the proposed GDC framework based on the supervisory control and data acquisition (SCADA) data. Three classical tasks, the WT gearbox failure detection, WT blade breakage detection, and wind power prediction, studied in the wind farm O&M are considered in the experiment. Compared with considered benchmarking models, the proposed GDC can achieve high accuracies on new tasks while maintain high accuracies on previous tasks.

Background: Clinically significant post-traumatic stress symptoms (PTSS) have been reported in up to a quarter of paediatric intensive care unit (PICU) survivors. Ongoing PTSS negatively impacts children's psychological development and physical recovery. However, few data regarding associations between potentially modifiable PICU treatment factors, such as analgosedatives and invasive procedures, and children's PTSS have been reported. Objectives: We sought to investigate the medical treatment factors associated with children's PTSS after PICU discharge. Methods: A prospective longitudinal cohort study was conducted in two Australian tertiary referral PICUs. Children aged 2-16 y admitted to the PICU between June 2008 and January 2011 for >8 h and