BSTFNet:An Encrypted Malicious Traffic Classification Method Integrating Global Semantic and Spatiotemporal Features

While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning methods relying on expert experience and the insufficient representation capabilities of existing deep learning methods for encrypted malicious traffic,we propose an encrypted malicious traffic classification method that integrates global semantic features with local spatiotemporal features,called BERT-based Spatio-Temporal Features Network(BSTFNet).At the packet-level granularity,the model captures the global semantic features of packets through the attention mechanism of the Bidirectional Encoder Representations from Transformers(BERT)model.At the byte-level granularity,we initially employ the Bidirectional Gated Recurrent Unit(BiGRU)model to extract temporal features from bytes,followed by the utilization of the Text Convolutional Neural Network(TextCNN)model with multi-sized convolution kernels to extract local multi-receptive field spatial features.The fusion of features from both granularities serves as the ultimate multidimensional representation of malicious traffic.Our approach achieves accuracy and F1-score of 99.39%and 99.40%,respectively,on the publicly available USTC-TFC2016 dataset,and effectively reduces sample confusion within the Neris and Virut categories.The experimental results demonstrate that our method has outstanding representation and classification capabilities for encrypted malicious traffic.

Diet with high content of advanced glycation end products induces oxidative stress damage and systemic inflammation in experimental mice: protective effect of peanut skin procyanidins

Non-enzymatic glycation reaction in food can produce diet-derived advanced glycation end products(dAGEs),which have potential health risks.Thus,it is of great significance to find efficient substances to improve the negative effects induced by dAGEs on human health.This study investigated the intervening effects of peanut skin procyanidins(PSP)on the dAGEs-induced oxidative stress and systemic inflammation in experimental mice model.Results showed that the accumulation of AGEs in serum,liver,and kidney was significantly increased after mice were fed dAGEs(P<0.05).The expression of advanced glycation product receptor(RAGE)was also significantly increased in liver and kidney(P<0.05).PSP could not only effectively reduce the accumulation of AGEs in serum,liver and kidney of mice,but also reduce the expression of RAGE in liver and kidney of mice.And the levels of pro-inflammatory cytokines interleukin-6(IL-6),tumor necrosis factor(TNF-α),and IL-1βin serum of mice were significantly decreased(P<0.05),while the levels of antiinflammatory factor IL-10 were increased,and the inflammatory injury in mice was improved.In addition,the levels of superoxide dismutase(SOD),glutathione(GSH),catalase(CAT)in liver and kidney of mice were increased(P<0.05),and the level of malondialdehyde(MDA)was decreased(P<0.05),which enhanced the antioxidant capacity of mice in vivo,and improved the oxidative damage of liver and kidney.Molecular docking technique was used to confirm that the parent compound of procyanidins and its main metabolites,such as 3-hydroxyphenylacetic acid,could interact with RAGE,which might inhibit the activation of nuclear transcription factor(NF-κB),and ultimately reduce oxidative stress and inflammation in mice.

A Scenario-Based Evaluation of COVID-19-Related Essential Clinical Resource Demands in China

The coronavirus disease 2019(COVID-19)pandemic is a global crisis,and medical systems in many countries are overwhelmed with supply shortages and increasing demands to treat patients due to the surge in cases and severe illnesses.This study aimed to assess COVID-19-related essential clinical resource demands in China,based on different scenarios involving COVID-19 spreads and interventions.We used a susceptible–exposed–infectious–hospitalized/isolated–removed(SEIHR)transmission dynamics model to estimate the number of COVID-19 infections and hospitalizations with corresponding essential healthcare resources needed.We found that,under strict non-pharmaceutical interventions(NPIs)or mass vaccination of the population,China would be able to contain community transmission and local outbreaks rapidly.However,under scenarios involving a low intensity of implemented NPIs and a small proportion of the population vaccinated,the use of a peacetime–wartime transition model would be needed for medical source stockpiles and preparations to ensure a normal functioning healthcare system.The implementation of COVID-19 vaccines and NPIs in different periods can influence the transmission of COVID-19 and subsequently affect the demand for clinical diagnosis and treatment.An increased proportion of asymptomatic infections in simulations will not reduce the demand for medical resources;however,attention must be paid to the increasing difficulty in containing COVID-19 transmission due to asymptomatic cases.This study provides evidence for emergency preparations and the adjustment of prevention and control strategies during the COVID-19 pandemic.It also provides guidance for essential healthcare investment and resource allocation.

Microstructure evolution and oxidation states of Co in perovskite-type oxide Ba_(1.0)Co_(0.7)Fe_(0.2)Nb_(0.1)O_(3-δ) annealed in CO_2 atmosphere

Ba1.0Co0.7Fe0.2Nb0.1O3-γ（BCFN） oxide with perovskite cubic structure was synthesized by solid state reaction method. COa corrosion of BCFN membrane was investigated by X-ray diffraction （XRD）, scanning electron microscopy （SEM）, diffuse reflectance infrared Fourier- transformed spectroscopy （DRIFT） and X-ray absorption fine structure spectroscopy （XAFS）. Cobalt （Co） K-edge absorption spectra of BCFN annealed in COa reveal that the oxidation states of Co in all the samples were larger than ＋3 and they decreased with the increase of calcination time. At 800 ℃, 1% CO2 introduced into He could speed up the reduction of Co cations in comparison with pure He. In addition, sulfate ions in the bulk of BCFN membrane preferred to migrate to the surface under CO2 calcination and form monoclinic Ba（CO3）0.9（SO4）0.1 besides orthorhombic witherite. Moreover, SEM results indicate that the nucleation and growth of carbonates grains started at the grain boundary of the membrane.

Predicting Genotype Information Related to COVID-19 for Molecular Mechanism Based on Computational Methods

Novel coronavirus disease 2019(COVID-19)is an ongoing health emergency.Several studies are related to COVID-19.However,its molecular mechanism remains unclear.The rapid publication of COVID-19 provides a new way to elucidate its mechanism through computational methods.This paper proposes a prediction method for mining genotype information related to COVID-19 from the perspective of molecular mechanisms based on machine learning.The method obtains seed genes based on prior knowledge.Candidate genes are mined from biomedical literature.The candidate genes are scored by machine learning based on the similarities measured between the seed and candidate genes.Furthermore,the results of the scores are used to perform functional enrichment analyses,including KEGG,interaction network,and Gene Ontology,for exploring the molecular mechanism of COVID-19.Experimental results show that the method is promising for mining genotype information to explore the molecular mechanism related to COVID-19.

Characterization of expressed genes in the establishment of arbuscular mycorrhiza between Amorpha fruticosa and Glomus mosseae

Arbuscular mycorrhiza （AM） formed between plant roots and fungi is one of the most widespread symbiotic associations in nature. To understand the molecular mechanisms of AM formation, we profiled 30 symbiosis-related genes expressed in Amorpha fruticosa roots colonized by Glomus mosseae and in non-mycorrhizal roots at different stages using differential-display RT-PCR （DDRT-PCR）. The expressed genes were confirmed by reverse Northern blotting. Eleven fragments were sequenced and putatively identified by homologous alignment. Of the eleven AM-related genes, five were obtained at the early-stage of plant-fungus interaction and six at the later stage. Three expressed se-quence tag （ESTs） sequences were found to originate from the fungi and eight from the host plant by use of PCR evaluation of gDNA of both plant and fungi. The target genes included an ATP-binding cassette sub-family transporter gene, a transposon-insertion display band, and a photosynthesis-related gene. The results provided information on the molecular mechanisms underlying the development of mycorrhizal sym-biosis between woody plants and AM fungi.

Distributed Filtering Algorithm Based on Tunable Weights Under Untrustworthy Dynamics

Aiming at effective fusion of a system state estimate of sensor network under attack in an untrustworthy environment, distributed filtering algorithm based on tunable weights is proposed. Considering node location and node influence over the network topology, a distributed filtering algorithm is developed to evaluate the certainty degree firstly. Using the weight reallocation approach, the weights of the attacked nodes are assigned to other intact nodes to update the certainty degree, and then the weight composed by the certainty degree is used to optimize the consensus protocol to update the node estimates. The proposed algorithm not only improves accuracy of the distributed filtering, but also enhances consistency of the node estimates. Simulation results demonstrate the effectiveness of the proposed algorithm. © 2014 Chinese Association of Automation.

One-dimensional mass transport with dynamic external potentials

Using non-equilibrium molecular dynamics and the Monte Carlo method, we simulated mass transport in a onedimensional channel with dynamic external potentials. This study focuses on the influence of the dynamic external potential field on the mass transport. Traveling wave and standing wave potential fields have been employed as our dynamic potential field. We found that mass transport can be promoted by the traveling wave field when the external potential moves along the direction of the mass current. When the standing wave field is exerted on the channel, the channel is found to work like a switch. The mass current can be "on" or "off" by adjusting the standing wave frequency. The effects of the period number,the amplitude and the velocity of the external potential on the mass transport are also discussed. Our research provides valuable advice for the control o particle transport through one-dimensional channels.

Evaluation of roof cutting by directionally single cracking technique in automatic roadway formation for thick coal seam mining

Automatic roadway formation by roof cutting is a sustainable nonpillar mining method that has the potential to increase coal recovery,reduce roadway excavation and improve mining safety.In this method,roof cutting is the key process for stress relief,which significantly affects the stability of the formed roadway.This paper presents a directionally single cracking(DSC)technique for roof cutting with considerations of rock properties.The mechanism of the DSC technique was investi-gated by explicit finite element analyses.The DSC technique and roof cutting parameters were evaluated by discrete element simulation and field experiment.On this basis,the optimized DSC technique was tested in the field.The results indicate that the DSC technique could effectively control the blast-induced stress distribution and crack propagation in the roof rock,thus,achieve directionally single cracking on the roadway roof.The DsC technique for roof cutting with optimized parameters could effectively reduce the deformation and improve the stability of the formed roadway.Field engineering application verified the feasibility and effectiveness of the evaluated DSC technique for roof cutting.

A new approach to natural capital sustainable development

The three-dimension(3D) ecological footprint makes the analysis of the relationships between the demand and supply of natural capital more credible by importing footprint depth and footprint size.This article used China's regions as the object to analyze the high-level sustainability of the natural capital from the view of "ecology-efficiency-fairness" multidimensional framework.Research showed that China's ecological footprint has risen while bio-capacity per capita has descended in recent 20 years.This paper also discusses the spatial distribution of China's natural capital ecological sustainability,efficiency sustainability and fairness sustainability.Finally,it builds multi-criteria evaluation(MCE) models to get multidimensional sustainability framework taking ecological sustainability,efficiency sustainability,and fairness sustainability into consideration.

Predicting influenza-like illness trends based on sentinel surveillance data in China from 2011 to 2019:A modelling and comparative study

Background Influenza is an acute respiratory infectious disease with a significant global disease burden.Additionally,the coronavirus disease 2019 pandemic and its related non-pharmaceutical interventions(NPIs)have introduced uncertainty to the spread of influenza.However,comparative studies on the performance of innovative models and approaches used for influenza prediction are limited.Therefore,this study aimed to predict the trend of influenza-like illness(ILI)in settings with diverse climate characteristics in China based on sentinel surveillance data using three approaches and evaluate and compare their predictive performance.Methods The generalized additive model(GAM),deep learning hybrid model based on Gate Recurrent Unit(GRU),and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA—GARCH)model were established to predict the trends of ILI 1-,2-,3-,and 4-week-ahead in Beijing,Tianjin,Shanxi,Hubei,Chongqing,Guangdong,Hainan,and the Hong Kong Special Administrative Region in China,based on sentinel surveillance data from 2011 to 2019.Three relevant metrics,namely,Mean Absolute Percentage Error(MAPE),Root Mean Squared Error(RMSE),and R squared,were calculated to evaluate and compare the goodness of fit and robustness of the three models.Results Considering the MAPE,RMSE,and R squared values,the ARMA—GARCH model performed best,while the GRU-based deep learning hybrid model exhibited moderate performance and GAM made predictions with the least accuracy in the eight settings in China.Additionally,the models’predictive performance declined as the weeks ahead increased.Furthermore,blocked cross-validation indicated that all models were robust to changes in data and had low risks of overfitting.Conclusions Our study suggested that the ARMA—GARCH model exhibited the best accuracy in predicting ILI trends in China compared to the GAM and GRU-based deep learning hybrid model.Therefore,in the future,the ARMA—GARCH model may be used to predict ILI trends in public health practice across diverse climatic zones,thereby contributing to influenza control and prevention efforts.

Optimizing anaerobic digestion: Benefits of mild temperature transition from thermophilic to mesophilic conditions

Anaerobic digestion(AD)plays a significant role in renewable energy recovery.Upgrading AD from thermophilic(50e57C)to mesophilic(30e38C)conditions to enhance process stability and reduce energy input remains challenging due to the high sensitivity of thermophilic microbiomes to temperature fluctuations.Here we compare the effects of two decreasing-temperature modes from 55 to 35C on cell viability,microbial dynamics,and interspecies interactions.A sharp transition(ST)is a one-step transition by 20C d1,while a mild transition(MT)is a stepwise transition by 1C d1.We find a greater decrease in methane production with ST(88.8%)compared to MT(38.9%)during the transition period.ST mode overproduced reactive oxygen species by 1.6-fold,increased membrane permeability by 2.2-fold,and downregulated microbial energy metabolism by 25.1%,leading to increased apoptosis of anaerobes by 1.9-fold and release of intracellular substances by 2.9-fold,further constraining methanogenesis.The higher(1.6 vs.1.1 copies per gyrA)metabolic activity of acetate-dependent methanogenesis implied more efficient methane production in a steady mesophilic,MT-mediated system.Metagenomic binning and network analyses indicated that ST induced dysbiosis in keystone species and greatly enhanced microbial functional redundancy,causing loss of microbial syntrophic interactions and redundant metabolic pathways.In contrast,the greater microbial interconnections(average degrees 44.9 vs.22.1)in MT at a steady mesophilic state suggested that MT could better maintain necessary system functionality and stability through microbial syntrophy or specialized pathways.Adopting MT to transform thermophilic digesters into mesophilic digesters is feasible and could potentially enhance the further optimization and broader application of practical anaerobic engineering.

Influenza time series prediction models in a megacity from 2010 to 2019:Based on seasonal autoregressive integrated moving average and deep learning hybrid prediction model

To the Editor:Influenza viruses are constantly evolving and have the ability to infect a wide range of hosts,leading to recurrent infections and ongoing morbidity.[1]In China,the surveillance for respiratory infectious diseases has been specifically performed for influenza and other respiratory infectious diseases.However,the current surveillance system relies heavily on the analysis of clinically confirmed influenza cases,which has lagged behind the times.[2]It is very important to establish a more accurate influenza prediction model,particularly in densely populated megacities.Our research aims to explore and develop more accurate and sensitive models for predicting influenza outbreaks.

A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development

The lighting system accounts for 8%of the total electricity consumption in commercial buildings in the United States and 12%of the total electricity consumption in public buildings globally.This consumption share can be effectively reduced using the demand-response control.The traditional lighting system control method commonly depends on the real-time occupancy data collected using the passive infrared(PIR)sensor.However,the detection inaccuracy of the PIR sensor usually results in false-offs.To diminish the false-error frequency,the existing lighting system control simply deploys a delayed reaction period(e.g.,5 to 20 min),which is not sufficiently accurate for the demand-response operation.Therefore,in this research,a novel data-driven model predictive control(MPC)method that is based on the temporal sequential-based artificial neural network(TS-ANN)is proposed to overcome this challenge using an updated historical occupancy status.Using an office as case study,the proposed model is also compared with the traditional lighting system control method.In the proposed model,the occupancy data was trained to predict the occupancy pattern to improve the control.It was found that the occupancy prediction mainly correlates with the historical occupancy ratio and the time sequential feature.The simulation results indicated that the proposed method achieved higher accuracy(97.4%)and fewer false-offs(from 79.5 with traditional time delay method to 0.6 times per day)are achieved by the MPC model.The proposed TS-ANN-MPC method integrates the analysis of the occupant behavior routine into on-site control and has the potential to further enhance the control performance practice for maximum energy conservation.

Molecular engineering of ultra-sensitive fluorescent probe with large Stokes shift for imaging of basal HOCl in tumor cells and tissues

Fluorescent probes have been widely employed in biological imaging and sensing.However,it is always a challenge to design probes with high sensitivity.In this work,based on rhodamine skeleton,we developed a general strategy to construct sensitivity-enhanced fluorescent probe with the help of theoretical calculation for the first time.As a proof of concept,we synthesized a series of HOCl probes.Experiment results showed that with the C-9 of pyronin moiety of rhodamine stabilized by an electron donor group,probe DQF-S exhibited an importantly enhanced sensitivity(LOD:0.2 nmol/L)towards HOCl together with fast response time(<10 s).Moreover,due to the breaking symmetrical electron distribution by another electron donor group,the novel rhodamine probe DQF-S displayed a far red to near-infrared emission(>650 nm)and large Stokes shift.Bioimaging studies indicated that DQF-S can not only effectively detect basal HOCl in various types of cells,but also be successfully applied to image tumor tissue in vivo.These results demonstrate the potential of our design as a useful strategy to develop excellent fluorescent probes for bioimaging.

Evolving a novel red-emitting two-photon dye with optically tunable amino group for monitoring the degree of hypoxia during liver fibrosis

Two-photon imaging has attracted increasing attention owing to its deep tissue imaging capabilities.Therefore,many fluorophores have been developed to satisfy its requirements.However,long-wavelength emission fluorophores with an optically tunable group are rarely developed.In this study,two longwavelength emission fluorophores with an optically tunable amino group were successfully developed by introducing strong electron acceptor and large conjugated group to the TPQL dye.TPCO_(2)displayed a bright red emission(λem=638 nm,Φ=0.15)together with high two-photon action cross section and good water solubility,which enabled higher signal-to-background ratios and deep tissue imaging.The proof-of-concept probe(TPCO-NO_(2))was successfully applied to the high signal-to-background ratio imaging of nitroreductase in liver fibrosis,further realizing diagnosis of the degree of hypoxia during liver fibrosis.

Rational design of far red to near-infrared rhodamine analogues with huge Stokes shifts for single-laser excitation multicolor imaging

Rhodamine dyes have been widely employed in biological imaging and sensing. However, it is always a challenge to design rhodamine derivatives with huge Stokes shift to address the draconian requirements of single-excitation multicolor imaging. In this work, we described a generally strategy to enhance the Stokes shift of rhodamine dyes by completely breaking their electronic symmetry. As a result, the Stokes shift of novel rhodamine dye DQF-RB-Cl is up to 205 nm in PBS, which is the largest in all the reported rhodamine derivatives. In addition, we successfully realized the single excitation trichromatic imaging of mitochondria, lysosomes and cell membranes by combining DQF-RB-Cl with commercial lysosomal targeting probe Lyso-Tracker Green and membrane targeting dye Dil. This is the organic synthetic dyes for SLE-trichromatic imaging in cells for the first time. These results demonstrate the potential of our design as a useful strategy to develop huge Stokes shift fluorophore for bioimaging.

Evaluating multiple parameters dependency of base temperature for heating degree-days in building energy prediction

To improve the prediction accuracy of heating demand, an appropriate base temperature should be estimated before using the heating degree-days (HDD) approach. This study collected the measured data for gas consumption at half-hourly resolution and the building physical characteristics from 89 educational buildings over four years. To determine the base temperature, in addition to the ambient temperature, more detailed independent variables, i.e. solar insolation, relative humidity, wind speed, and one-day ahead residual temperature, were incorporated into a three-parameter change-point multi-variable regression (3PH-MVR) for heating. The mean base temperature using the 3PH-MVR approach was about 0.4℃ lower than the results from the 3PH method only. The relationships between base temperature and annual HDD (based on 15.5℃), building location, and mean daily solar insolation were evaluated. It is found that the annual HDD and the daily insolation had clear impacts on base temperature, while there was a plausible relationship between base temperature and building location. Compared with traditional approach, the proposed 3PH-MVR method considers multiple weather parameters and determines a more robust base temperature, thus improving the prediction accuracy of HDD with higher average R2 value at 0.86 than that of univariate regression (0.82).

The reinforcement learning method for occupant behavior in building control:A review

Occupant behavior in buildings has been considered the major source of uncertainty for assessing energy con-sumption and building performance.Modeling frameworks are usually built to accomplish a certain task,but the stochasticity of the occupant makes it difficult to apply that experience to a similar but distinct environment.For complex and dynamic environments,the development of smart devices and computing power makes intelligent control methods for occupant behaviors more viable.It is expected that they will make a substantial contribution to reducing global energy consumption.Among these control techniques,the reinforcement learning(RL)method seems distinctive and applicable.The success of the reinforcement learning method in many artificial intelligence applications has given an explicit indication of how this method might be used to model and adjust occupant behavior in building control.Fruitful algorithms complement each other and guarantee the quality of the opti-mization.However,the examination of occupant behavior based on reinforcement learning methodologies is not well established.The way that occupant interacts with the RL agent is still unclear.This study briefly reviews the empirical applications using reinforcement learning,how they have contributed to shaping the modeling paradigms and how they might suggest a future research direction.

Generating hourly electricity demand data for large-scale single-family buildings by a decomposition-recombination method

Household electricity demand has substantial impacts on local grid operation,energy storage and the energy per-formance of buildings.Hourly demand data at district or urban level helps stakeholders understand the demand patterns from a granular time scale and provides robust evidence in energy management.However,such type of data is often expensive and time-consuming to collect,process and integrate.Decisions built upon smart meter data have to deal with challenges of privacy and security in the whole process.Incomplete data due to confiden-tiality concerns or system failure can further increase the difficulty of modeling and optimization.In addition,methods using historical data to make predictions can largely vary depending on data quality,local building envi-ronment,and dynamic factors.Considering these challenges,this paper proposes a statistical method to generate hourly electricity demand data for large-scale single-family buildings by decomposing time series data and recom-bining them into synthetics.The proposed method used public data to capture seasonality and the distribution of residuals that fulfill statistical characteristics.A reference building was used to provide empirical parameter settings and validations for the studied buildings.An illustrative case in a city of Sweden using only annual total demand was presented for deploying the proposed method.The results showed that the proposed method can mimic reality well and represent a high level of similarity to the real data.The average monthly error for the best month reached 15.9%and the best one was below 10%among 11 tested months.Less than 0.6%improper synthetic values were found in the studied region.