Search

Microbial oils produced by Yarrowia lipolytica offer an environmentally friendly and sustainable alternative to petroleum as well as traditional lipids from animals and plants. The accurate measurement of fermentation parameters, including the substrate concentration, dry cell weight, and lipid accumulation, is the foundation of process control, which is indispensable for industrial lipid production. However, it remains a great challenge to measure the complex parameters online during the lipid fermentation process, which is nonlinear, multivariate, and characterized by strong coupling. As a type of AI technology, the artificial neural network model is a powerful tool for handling extremely complex problems, and it can be employed to develop a soft sensor to monitor the microbial lipid fermentation process of Y. lipolytica. In this study, we first analyzed and emphasized the volume of sodium hydroxide and dissolved oxygen concentration as central parameters of the fermentation process. Then, a soft sensor based on a four-input artificial neural network model was developed, in which the input variables were fermentation time, dissolved oxygen concentration, initial glucose concentration, and additional volume of sodium hydroxide. This provides the possibility of online monitoring of dry cell weight, glucose concentration, and lipid production with high accuracy, which can be extended to similar fermentation processes characterized by the addition of bases or acids, as well as changes of the dissolved oxygen concentration.

Background: Cerebral ischemia reperfusion injury (CIRI) is the pathophysiological basis of various cerebrovascular diseases. The aim of this study was to explore the role of HIF-1α/BNIP3 in the alleviating effect of IL-4 on CIRI in mice. Methodology: Mice were randomly divided into sham operation (Sham), ischemia reperfusion (IR), IL-4, HIF-1α inhibitor 2ME2 and IL-4+2ME2 groups. Middle cerebral artery occlusion model was established. After 24-h reperfusion, neurologic deficit score (NDS) was given. Cerebral infarction volume and brain water content were measured by 2,3,5-triphenyltetrazolium chloride staining and dry-wet weights, respectively. Apoptosis was detected by TUNEL staining. SOD, MDA and ROS levels, and HIF-1α, BNIP3, LC3II and Beclin-1 expressions were detected through colorimetry and Western blotting, respectively. Results: Compared with IR group, NDS, cerebral infarction volume, brain water content, apoptosis rate, and MDA and ROS levels decreased, while SOD, HIF-1α, BNIP3, LC3-II and Beclin-1 levels increased in IL-4 group (P

Chronic actinic dermatitis (CAD) is a common debilitating photodermatosis. Patients often have to completely avoid outdoor activities, which severely impacts their quality of life. Phototherapy is effective for CAD and seems to increase patients' tolerance towards sunlight and consequently decrease the extent of disease. Unfortunately, the slower onset and time-consuming nature of phototherapy limits the clinical application. Considering the effectiveness and time-saving nature of ultraviolet (UV)-A rush hardening in solar urticaria, we performed a pilot study to determine whether UV-A rush hardening is effective in CAD. Six patients with CAD were exposed to multiple sessions of UV-A for 4-5 days at 1-h intervals/day. Subsequently, maintenance UV-A exposure was performed at 1-2-week intervals. Phototesting at baseline showed that three patients were sensitive to both UV-A and -B, and the other three patients only showed UV-A sensitivity. All of the patients responded well to UV-A rush hardening and four (67%) maintained a good remission status after 1 year. The results of this pilot study suggest that UV-A rush hardening phototherapy is effective and well tolerated in the treatment of CAD, while future larger prospective studies using objective scores of disease activity and quality of life are needed.

In conventional mobile crowdsensing (MCS) applications, the crowdsensing server (CS-server) needs mobile users’ precise locations for optimal task allocation, which raises privacy concerns. This paper proposes a privacy-preserving task allocation framework (called P2TA) for edge computing enhanced MCS, focusing on optimize task acceptance rate while protecting participants’ privacy by introducing edge nodes. The basic idea is that edge nodes act as task assignment agents with privacy protection that prevents an untrusted CS-server from accessing a user’s private data. We begin with a thorough analysis of the limitations of typical task allocation and obfuscation schemes. On this basis, the optimization problem about location obfuscation and task allocation is formulated in consideration of privacy constraints, travel distance and impact of location perturbation. Through problem decomposition, the location obfuscation subproblem is modeled as a leader-follower game between the designer of location obfuscation mechanism and the potential attacker. Against inference attack with background knowledge, a genetic algorithm is introduced to initialize an obfuscation matrix. With the matrix, an edge node makes task allocation decisions that maximize task acceptance rate subject to differential and distortion privacy constraints. The effectiveness and superiority of P2TA compared to exiting task allocation schemes are validated via extensive simulations.

While much research has been devoted to algorithm improvement of the machine learning model for multimedia applications, relatively little research has focused on the acquisition of massive multimedia datasets with strict data demands for model training. In this paper, we propose a Quality-of-Information (QoI) aware incentive mechanism in multimedia crowdsensing, with the objective of promoting the growth of an initial training model. We begin with a reverse auction incentive model to maximize social welfare while meeting the requirements in quality, timeliness, correlation, and coverage. Then, we discuss how to achieve the optimal social welfare in the presence of an NP-hard winner determination problem. Lastly, we design an effective incentive mechanism to solve the auction problem, which is shown to be truthful, individually rational and computationally efficient. Our evaluation study is carried out using a real multimedia dataset. Extensive simulation results demonstrate that the proposed incentive mechanism produces close-to-optimal social welfare noticeably, while accompanied by accelerating the growth of the machine learning model with a high-QoI dataset.

A fractional order moments-based detector is proposed for the detection of weak signals in additive impulsive noise environment assumed as generalized Gaussian distribution with properly selected parameter values. The asymptotic detection performance is derived and compared with some traditional detectors optimized for operations in Gaussian noise with Nakagami fading communication channels. The analytical and computer simulation results of the fractional order moment-based detector are shown for signal detection with fading channels in the impulsive noise.

Clustering organizes nodes into groups in order to enhance the connectivity and stability of cognitive radio sensor networks. Mainly depending on the channel availability, many existing spectrum-aware clustering algorithms may not achieve the most satisfactory clustering. Taking into account the various influence factors to establish the optimal clustering is a challenge to enhance the network performance. This paper proposes a novel spectrum-aware clustering algorithm based on weighted clustering metric to obtain the optimal clustering by solving an optimization model. The new weighted clustering metric, simultaneously evaluating temporal-spatial correlation, confidence level and residual energy, is used to elect clusterheads and ally member nodes. After clustering, the clusterheads sensing spectrum instead of all member nodes greatly reduces the energy consumption of spectrum sensing and increases the opportunity of data transmission. The performance comparison between the traditional spectrum-aware clustering algorithms and our proposed algorithm has been highlighted with the experiments.

The qualities of superconducting conductors are usually characterized by their critical current and n-value. In this paper, the critical current and the n-value of the second-generation (2G) high temperature superconducting (HTS) conductors considering the temperature-field dependence are predicted by a back propagation (BP) neural network as J c(B, θ, T) and n(B,θ,T). A correlation exists between the critical current and the n-value, thus in our BP neural network, the tasks of estimating the critical current and the n-value can be carried out in one network. The outputs used to predict the critical current and the n-value share the same hidden layers of the network, and therefore the critical current and the n-value can be calculated simultaneously. The critical current and the n-value of HTS conductors vary for different manufacturers and even for the same manufacturer but different production batches. In our BP network, we use an encoder structure to encode different manufacturers and production batches to ensure that the network can be adapted to the HTS conductors so produced. The predictions on three different samples of HTS conductors are carried out and the results are compared with those obtained from linear interpolation at different temperature-field conditions. In addition to the high accuracy, when compared with the linear interpolation, the proposed network can suppress the fluctuations existing in the experimental data and ensure the prediction results to be more reasonable. The time required for the proposed network to obtain the prediction results of the critical current and the n-value is also discussed, which is within 5 s. Therefore, the proposed network has the potential to be applied to the optimization and analysis of the superconducting related equipment.

Background Boxing programs designed specifically for people with Parkinson's disease (PD) can be beneficial in improving the physical, mental, and functional health of persons with PD. Purpose This study examined the effect of a boxing program, Rock Steady Boxing (RSB), on the health of people with PD from both the boxers' and their caregivers' perspectives as well as evaluated balance, quality of life (QoL), and depressive symptoms after 12 weeks of RSB. Methods A mixed methods, one-group experimental design with focus groups were embedded within an intervention study. Six boxers completed baseline and 12-week postassessments. Results The majority of boxers maintained or improved scores for balance, QoL, and reduced depressive symptoms. Findings indicate physical and mental benefits of RSB among persons with PD and this was further validated by qualitative data from boxers and caregivers, along with quantitative data of boxers. Caregivers and boxers reported that boxers' ability to perform activities of daily living (ADLs) improved and is supported by quantitative improvements in the Parkinson's disease Questionnaire-39 ADL subscale. All boxers reported reduced stigma, and caregivers and boxers valued the opportunity to work out in an environment free of stigma, a finding not previously reported. Conclusions It is important for nurse practitioners to recognize exercise benefits for people with PD and recommend the program to patients and include caregivers in their overall assessment of health and wellness. Implications for practice Nurse practitioners and other health practitioners may consider recommending a boxing program, such as RSB, for their PD patients as a sole or supplemental exercise program.

BackgroundSince late December 2019, a novel coronavirus (COVID-19) has emerged in Wuhan and rapidly spread throughout China. Fears were raised higher, effective policies for prevention and control were concerned.MethodsTill March 3, 91273 confirmed COVID-19 cases were included in. Using Mann-Whitney U test, the provinces that reported the life tracks of confirmed cases to public had lower increased in daily new confirmed cases.ResultsCompared with the paired province, Tianjin, Jilin, Gansu, Shanxi, Hainan and Guizhou had significant differences in the number of new confirmed cases and have lower mean rank (PConclusionsStrategies must be adjusted in real time according to the epidemic. Reporting the life tracks of confirmed cases was an effective way to control the epidemic. They may be suggestions to other counties with an outbreak of COVID-19.

Background ： Bladder cancer, originating from the epithelium of the urinary bladder, was the second most common malignancy in the urinary system with a high metastasis rate and poor post-metastasis prognosis. Alternative splicing events (ASEs) were regarded as important markers of tumor progression and prognosis, however, their roles in bladder cancer bone metastasis haven’t been recognized. Methods ： In order to explore the mechanism of ASEs in bladder cancer bone metastasis, we downloaded the RNA sequencing data and ASEs data of 412 samples of primary BLCAs from The Cancer Genome Atlas (TCGA) and TCGASpliceSeq databases. The Cox regression analysis was used to identify overall survival-related ASEs (OS-SEs), then, based on the OS-SEs screened by Lasso regression, we constructed the predict model. Finally, univariate and multivariate independent prognostic analysis were performed to prove it as an independent prognostic factor. Results ： In this study, a predict model of OS in BLCA was constructed and the Area Under Curve of the model was 0.581. Its risk score was also proved to be an independent predictor with the good accuracy (P < 0.001). Among identified 390 SFs, Junction plakoglobin (JUP) was significantly correlated with overall survival and bone metastasis. In co-expression analysis, the co-expression pathway of ITGB4 was the glycosphingolipid biosynthesis ganglio series. Conclusions ： We speculated that JUP regulating the ITGB4 might play a key role in bone metastasis of bladder cancer through the glycosphingolipid biosynthesis ganglio series pathway (R = 0.220, P < 0.001), which was also related to prognosis.

The power system rescheduling based on model-free methods has obvious defects in practical application, such as poor scenario transferability, long data training time, and waste of domain knowledge. To overcome the above defects, a transfer-reinforcement-learning-based rescheduling method of differential power grids considering security constraints is proposed. When constructing the Markov decision-making process of security-constrained rescheduling, both the off-limits of line power and node voltage are considered in the reward. The action space of deep reinforcement learning is narrowed by calculating the sensitivities of devices and mapped to control the active and reactive power regulating devices to reschedule active and reactive power simultaneously. According to the change degree of transfer object, the applications of transfer learning are divided into two scenarios. For the security-constrained rescheduling transfer scenario of different structures of the same power grid, a domain-adaption transfer learning method is formed, realizing good data adaptability after structure changes with the original model. Moreover, a policy-based transfer learning method is constructed for the security-constrained rescheduling transfer scenario of different power grids, enhancing the training speed and training effect of target power grid. Two standard systems and two actual power grids are utilized to verify the effectiveness of the method. For the actual power grids, the effects of the two scenarios are improved by 5.8% and 3.9% with transfer learning. Compared with other methods, this method not only has obvious advantages in transferability, but also has a shorter learning process and lower control cost.

To improve the scalability and elasticity of application deployment and operation in cloud computing environments, new architectures and techniques are developed and studied, e.g., microservice architecture, and Docker container. Especially, Docker container enables the sharing on operation system and supporting libraries, which is more lightweight, prompt and scalable than Hypervisor based virtualization. These features make it ideally suit for applications deployed in microservice architecture. However, existing models and schemes, which are mostly designed for Hypervisor based virtualization techniques, fall short to be efficiently used for Docker container based application deployment. To take the benefits of microservice architecture and Docker containers, we explore the optimization of application deployment in cloud data centers using microservice and Docker containers. Our goal is to minimize the application deployment cost as well as the operation cost while preserving service delay requirements for applications. In this paper, we first formulate the application deployment problem by examining the features of Docker, the requirements of microservice-based applications, and available resources in cloud data centers. We further propose a communication efficient framework and a suboptimal algorithm to determine the container placement and task assignment. The proposed algorithm works in a distributed and incremental manner, which makes it scalable to massive physical resources and diverse applications under the framework. We validate the efficiency of our solution through comparisons with three existing strategies in Docker Swarm using real traces from Google Cluster. The evaluation results show that the proposed framework and algorithm provide more flexibility and save more cost than existing strategies.

Target localization is one of the essential tasks in the applications of wireless sensor networks (WSNs). The traditional target localization based on received signal strength may fail to obtain satisfactory localization performance, especially when the number of the RSS measurements is limited. Compressed sensing (CS) has been shown to be an effective technique for target localization due to the intrinsic sparse nature of target localization in WSNs. The CS-based target localization can be formulated to a sparse recovery problem based on $l_{0} $ -norm or $l_{1} $ -norm minimization. Compared to $l_{0} $ -norm and $l_{1}$ -norm, $l_{p} $ -norm $(0 can provide the most effective sparsity measurement of a vector. Some traditional sparse recovery algorithms for $l_{p} $ -norm minimization, however, usually obtain suboptimal sparse solutions when the initial point is not in the convergence domain of the globally optimal sparse solution. In this paper, we propose a novel affine scaling steepest descent (ASSD) algorithm to find a satisfying sparse solution of $l_{p} $ -norm minimization. By setting an optimal stepsize at each iteration, our ASSD algorithm can avoid the iterative solutions concentrating on the attraction basin of the suboptimal sparse solution and move to the attraction basin of a sparser solution, so it has high opportunity to obtain the globally optimal sparse solution, and then accurately determine the locations of targets. The experimental results show that our ASSD algorithm performs much better than the traditional BP, OMP, GMP, ASM, IRL1, and ITM algorithms, especially when the number of measurements is insufficient.

In view of the problem of manpower and time consumption caused by unsolvable power flow in current AC / DC hybrid power grid with new energy, a power flow state assessment and solvability recovery adjustment method based on graph convolutional recurrent neural network (GCRNN) and deep double Q-learning network (DDQN) is proposed. First, active power balance degree, reactive power balance degree and channel transmission margin are defined and weighted together to evaluate the solvability of power flow. Then, a power flow state evaluation model based on GCRNN is proposed by combining graph convolution with recurrent neural network, where the input is tangent vector of power flow equations, and the output is comprehensive evaluation index of solvability. Next, the state space, action space and multiple rewards of deep reinforcement learning are formed. By introducing the search direction, learning information extraction and search space constraints, an automatic adjustment method to restore power flow solvability is designed. Finally, the simulation results show that the proposed method performs well both in New England 39-bus standard system and actual power grid of China. Compared with the results obtained by other methods, the superiority of the proposed method is verified.

Considering that traditional centralized scheduling cannot realize energy complementarity and benefit coordination between multi-energy hubs (EHs) and advantages of artificial intelligence technology in the application of integrated energy microgrid (IEM), a coordinated scheduling model and method of IEM with multi-EHs based on multi-agent deep deterministic policy gradient (MADDPG) is proposed. First, an IEM framework of multi-EHs is constructed, and the rationality of multi-EH construction is illustrated. Then, considering operation cost, environmental cost, and benefit of new energy, a two-layer economic optimal scheduling model of IEM is established. Furthermore, distributed deep reinforcement learning based on MADDPG and game theory is introduced, and a coordinated scheduling method of IEM with multi-EHs based on the algorithm is proposed. At the same time, based on the idea of transfer learning, an off-line training and online learning method is proposed, which can improve the training speed of online learning. Finally, a numerical example is constructed to verify the effectiveness of the proposed model and method.