Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.

Stability mechanism and control of the pumpable supports in longwall recovery room

The load-bearing performance(LBP)of pumpable supports(PPS)is crucial for the stability of longwall pre-driven recovery room(PRR)surrounding rock.However,the unbalanced bearing coefficient(UBC)of the PPS(undertaking unequal load along the mining direction)has not been investigated.A mechanical model of the PRR was established,considering the main roof cantilever beam structure,to derive an assessment formula for the load,the failure criteria,and the UBC of the PPS.Subsequently,the generation mechanisms,and influencing factors of the UBC were revealed.Global sensitivity analysis shows that the main roof hanging length(l_(2))and the spacing between the PPS(r)significantly impact the UBC.A novel design of the PPS and the coupling control technology were proposed and applied to reduce the UBC of the PPS in the adjacent longwall PRR.Monitor results showed no failure of the PPS at the test site,with the UBC(ζ)reduced to 1.1 consistent with the design value(1.15)basically,fully utilizing the collaborative LBP of the PPS.Finally,the maximum roof-to-floor convergence of the PRR was 234 mm,effectively controlling the stability of the surrounding rock of the PRR and ensuring the mining equipment recovery.

Physiological and molecular mechanisms of cytokinin involvement in nitrate-mediated adventitious root formation in apples

Potassium nitrate(KNO_(3))promotes adventitious root(AR)formation in apple stem cuttings.However,evidence for the possible involvement of cytokinin(CK)in KNO_(3)-mediated AR formation in apples is still lacking.In this study,we cultured GL-3 apple microshoots in different treatment combinations.While the T1(KNO_(3)9.4 mmol L^(-1)+6-benzyl adenine(6-BA)2.22μmol L^(-1))and T3(6-BA 2.22μmol L^(-1))treatments completely inhibited AR formation,the control,T2(KNO_(3)9.4 mmol L^(-1)),and T4(KNO_(3)9.4 mmol L^(-1)+lovastatin(Lov)1.24μmol L^(-1))treatments developed ARs.However,T4-treated microshoots developed fewer and shorter ARs,indicating that optimum CK synthesis is needed for normal AR growth.This also suggests that these fewer and shorter ARs developed because of the presence of KNO_(3) in the same medium.The anatomy of the stem basal part indicated that the inhibition of CK biosynthesis delayed AR primordia formation.The endogenous levels of indole-3-acetic acid(IAA)and zeatin riboside(ZR)were higher in T2-treated microshoots,while the abscisic acid(ABA),gibberellic acid 3(GA_(3)),and brassinosteroid(BR)levels were higher in T4-treated microshoots.The expression levels of MdNRT1.1and MdNRT2.1 were higher in T2-treated microshoots at 3 and 8 days,while MdRR2 and MdCKX5 were higher at 8 and 16 days,respectively.Furthermore,higher IAA levels increased MdWOX11 expression,which in turn increased MdLBD16 and MdLBD29 expression in response to T2.The combined expression of these genes stimulated adventitious rooting by upregulating cell cycle-related genes(MdCYCD1;1 and MdCYCD3;1)in response to T2 treatment.This study shows that specific genes and hormonal pathways contribute to KNO_(3)-CK-mediated adventitious rooting in apples.

Re-usable Cd_(0.9)Zn_(0.1)S-ZnO@C/PVDF piezo-photocatalytic film with exceptional hydrogen evolution capability triggered by the synergetic advantages of piezoelectricity and S-Scheme heterojunction

Piezoelectric materials have advantages of fine-tuning photocatalytic performance through harvesting mechanical energy and open a new avenue in facilitating green catalytic reaction.Herein,polyvinylidene fluoride(PVDF),a flexible piezoelectric material,was introduced to synthesize a novel Cd_(0.9)Zn_(0.1)S-ZnO@C/PVDF(CZS-ZO@C/PVDF)piezo-photocatalytic film by spin coating and immersion phase conversion method.Benefiting from the piezoelectricity of PVDF and the internal electric field(IEF)of CZS-ZO@C Step-scheme(S-Scheme)heterojunction,CZS-ZO@C/PVDF was able to induce a hydrogen generation rate of 34.9 mmol g^(−1)h^(−1)activated by ultrasound and visible light(U-L),which is∼17.5 times of Cd_(0.9)Zn_(0.1)S/PVDF(CZS/PVDF)and∼7.4 times of the photocatalysis rate activated by visible light only(L).Piezoelectric measurements and COMSOL simulation illustrated the excellent piezoelectricity of CZS-ZO@C/PVDF film,which exhibits a piezoelectric coefficient(d33)of 9.9 pm V−1 and a piezoelectric potential of 874 mV(under 0.5 MPa).The reaction mechanism for the exceptional piezo-photocatalytic performance was finally disclosed through density functional theory(DFT)calculation and electrochemical tests.This study enriches the application scope of piezoelectric materials in sustainable energy catalysis and provides a new direction to develop efficient piezoelectric photocatalysts.

一种基于血液检测的诊断和预测HBV相关疾病的弹性方法

Chronic hepatitis B virus(HBV)infection,which threatens global public health,is a major contributor to liver-related morbidity and mortality.Examinations for liver diseases related to chronic HBV infection-including laboratory tests,ultrasounds,computed tomography(CT),and liver biopsies-may take up medical resources,particularly since they overlap in most instances.Thus,there is an urgent need to establish an economical and effective diagnosis method in order to streamline the medical process for HBV-related disea ses.Using complex network models constructed based on clinical blood tests,we provide such a method by defining the novel measure of functional resilience to assess patients’liver conditions.By combining network models and dynamics,we discovered the pivotal items and their corresponding thresholds,which can guide further research on preventing disease deterioration in critical states of these diseases.The macro-averaged precision of our method,functional resilience,is84.74%,whereas the macro-averaged precision of physicians’experience without assistance from imaging or biopsy is 55.63%.From an economic perspective,our approach could save the equivalent of at least30 USD per visit for most Chinese patients and at least 400 USD per visit for most US patients,compared with general diagnostic methods.Globally,this will add to savings of at least 10.5 billion USD annually.Our method can comprehensively evaluate the condition of patients’livers and help avert the waste of medical resources during the diagnosis of liver disease by reducing excessive imaging exams.

Rational construction of CuFe_(2)O_(4)@C/Cd_(0.9)Zn_(0.1)S S-scheme heterojunction photocatalyst for extraordinary photothermal-assisted photocatalytic H_(2) evolution

Rational design of photocatalyst to maximize the use of sunlight is one of the issues to be solved in photocatalysis technology.In this study,the CuFe_(2)O_(4)@C/Cd_(0.9)Zn_(0.1)S(CFO@C/CZS)S-scheme photocatalyst with photothermal effect was synthesized by ultrasonic self-assembly combined with calcination.The dark CFO@C absorbed visible light and partly converted into heat to promote the hydrogen evolution reaction.The presence of heterojunctions inhibited the photogenerated electron-hole recombination.The graphite-carbon layer provided a stable channel for electron transfer,and the presence of magnetic CFO made recycle easier.Under the action of photothermal assistance and heterojunction,the hydrogen evolution rate of the optimal CFO@C/CZS was 80.79 mmol g^(-1) h^(-1),which was 2.55 times and 260.61 times of that of pure CZS and CFO@C,respectively.Notably,the composite samples also exhibit excellent stability and a wide range of environmental adaptability.Through experimental tests and first-principles simulation calculation methods,the plausible mechanism of photoactivity enhancement was proposed.This work provided a feasible strategy of photothermal assistance for the development of heterojunction photocatalysts with distinctive hydrogen evolution.

Mouse KL2 is a unique MTSE involved in chromosome-based spindle organization and regulated by multiple kinases during female meiosis

Microtubule-severing enzymes(MTSEs)play important roles in mitosis and meiosis of the primitive organisms.However,their roles in mammalian female meiosis,which accounts for over 80%of gamete-originated human reproductive diseases,remain unexplored.In the current study,we reported that katanin-like 2(KL2)was the only MTSE concentrating at chromosomes.Furthermore,the knockdown of KL2 significantly reduced the chromosome-based increase in the microtubule(MT)polymer,increased aberrant kinetochore-MT(K-MT)attachment,delayed meiosis,and severely affected normal fertility.We demonstrated that the inhibition of aurora B,a key kinase for correcting aberrant K-MT attachment,significantly eliminated KL2 expression from chromosomes.Additionally,KL2 interacted with phosphorylated eukaryotic elongation factor-2 kinase,and they competed for chromosome binding.Phosphorylated KL2 was also localized at spindle poles,with its phosphorylation regulated by extracellular signal-regulated kinase 1/2.In summary,the current study reveals a novel function of MTSEs in mammalian female meiosis and demonstrates that multiple kinases coordinate to regulate the levels of KL2 at chromosomes.

Analysis on the development of chemically-improved soil in railway engineering

Purpose-Explore the development trend of chemically-improved soil in railway engineering.Design/methodology/approach–In this paper,the technical standards home and abroad were analyzed.Laboratory test,field test and monitoring were carried out.Findings–The performance design system of the chemically-improved soil should be established.Originality/value–On the basis of the performance design,the test methods and standards for various properties of chemically-improved soil should be established to evaluate the improvement effect and control the engineering quality.

Clinical feasibility of laparoscopic left lateral segment liver resection with magnetic anchor technique:The first clinical study from China

BACKGROUND Magnetic anchor technique(MAT)has been applied in laparoscopic cholecystectomy and laparoscopic appendectomy,but has not been reported in laparoscopic partial hepatectomy.AIM To evaluate the feasibility of the MAT in laparoscopic left lateral segment liver resection.METHODS Retrospective analysis was conducted on the clinical data of eight patients who underwent laparoscopic left lateral segment liver resection assisted by MAT in our department from July 2020 to November 2021.The Y-Z magnetic anchor devices(Y-Z MADs)was independently designed and developed by the author of this paper,which consists of the anchor magnet and magnetic grasping apparatus.Surgical time,intraoperative blood loss,intraoperative accidents,operator experience,postoperative incision pain score,postoperative complications,and other indicators were evaluated and analyzed.RESULTS All eight patients underwent a MAT-assisted laparoscopic left lateral segment liver resection,including three patients undertaking conventional 5-port and five patients having a transumbilical single-port operation.The mean operation time was 138±34.32 min(range 95-185 min)and the mean intraoperative blood loss was 123±88.60 mL(range 20-300 mL).No adverse events occurred during the operation.The Y-Z MADs showed good workability and maneuverability in both tissue and organ exposure.In particular,the operators did not experience either a“chopstick”or“sword-fight”effect in the single-port laparoscopic operation.CONCLUSION The results show that the MAT is safe and feasible for laparoscopic left lateral segment liver resection,especially,exhibits its unique abettance for transumbilical single-port laparoscopic left lateral segment liver resection.

岜沙苗族聚落及村寨建筑的地域适应性特征

苗族聚落及村寨建筑在我国传统聚落和建筑中独具特色,建造体系成熟,蕴含丰富的地域适应性营造技术和绿色经验,极具研究价值。以位于黔东南地区的岜沙苗寨为例,从地理环境、气候条件、民俗文化等方面对岜沙苗族聚落及村寨建筑的地域适应性特征进行分析,以期对传统聚落的传承、保护和发展以及对适应地域环境的现代绿色建筑的营造有所启示。

基于BP神经网络的通用机打发票字符的识别

针对通用机打发票字符提取效率低、工作量大的特点,结合BP神经网络设计了一套通用机打发票识别系统。系统主要由图像获取部分和图像处理部分组成,图像获取部分以硬件为主,包括相机、镜头、光源、载物平台;图像处理部分将采集的图片进行预处理,提取出字符的HOG特征,并通过BP神经网络进行训练与识别。实验结果表明:系统鲁棒性好,识别率达到96.9%,能有效完成通用机打发票字符的提取。

我国国防特色学科人才培养效果评价体系研究--基于FAHP-BP方法

加强国防学科建设作为高校培养新型国防科技人才的一个重要途径,如何科学有效的评估各国防特学学科人才培养效果成为亟待解决的问题。本文的研究构建了国防特色学科人才培养效果评估指标体系,并将模糊层次分析法与BP神经网络相结合的方法应用于国防特色人才培养效果评估。同时以第二批国防特色学科为例,对我国国防特色学科人才培养效果进行评价与分析。实验结果发现:不同高校之间的国防学科建设水平存在差异,且同一高校的不同学科建设之间存在明显不平衡的现象。基于评估结果,本文就国防特色学科发展提出相关建设性意见。

基于ARM的车载定位系统设计与实现

为获取及时、准确的车辆位置信息,研究基于ARM Cortex-A7嵌入式处理器架构以及Android的车载定位系统。以车载定位为应用背景,提供了整个系统的软/硬件解决方案,实现了及时、准确的车载定位功能。首先对项目背景、系统框架作了简单介绍,提出了系统的软/硬件性能指标,确定了器件选型,随后介绍了系统的软/硬件设计方案,包括原理图设计、PCB设计及系统软件流程等,最后对整个系统进行了测试,结果表明:系统运行稳定,能够精确实现定位功能。

Estimating survival benefit of adjuvant therapy based on a Bayesian network prediction model in curatively resected advanced gallbladder adenocarcinoma

BACKGROUND The factors affecting the prognosis and role of adjuvant therapy in advanced gallbladder carcinoma(GBC)after curative resection remain unclear.AIM To provide a survival prediction model to patients with GBC as well as to identify the role of adjuvant therapy.METHODS Patients with curatively resected advanced gallbladder adenocarcinoma(T3 and T4)were selected from the Surveillance,Epidemiology,and End Results database between 2004 and 2015.A survival prediction model based on Bayesian network(BN)was constructed using the tree-augmented na?ve Bayes algorithm,and composite importance measures were applied to rank the influence of factors on survival.The dataset was divided into a training dataset to establish the BN model and a testing dataset to test the model randomly at a ratio of 7:3.The confusion matrix and receiver operating characteristic curve were used to evaluate the model accuracy.RESULTS A total of 818 patients met the inclusion criteria.The median survival time was 9.0 mo.The accuracy of BN model was 69.67%,and the area under the curve value for the testing dataset was 77.72%.Adjuvant radiation,adjuvant chemotherapy(CTx),T stage,scope of regional lymph node surgery,and radiation sequence were ranked as the top five prognostic factors.A survival prediction table was established based on T stage,N stage,adjuvant radiotherapy(XRT),and CTx.The distribution of the survival time(>9.0 mo)was affected by different treatments with the order of adjuvant chemoradiotherapy(cXRT)>adjuvant radiation>adjuvant chemotherapy>surgery alone.For patients with node-positive disease,the larger benefit predicted by the model is adjuvant chemoradiotherapy.The survival analysis showed that there was a significant difference among the different adjuvant therapy groups(log rank,surgery alone vs CTx,P<0.001;surgery alone vs XRT,P=0.014;surgery alone vs cXRT,P<0.001).CONCLUSION The BN-based survival prediction model can be used as a decision-making support tool for advanced GBC patients.Adjuvant chemoradiotherapy is expected to improve the survival significantly for patients with node-positive disease.

Environmental Adaptive Control of a Snake-like Robot With Variable Stiffness Actuators

This work investigates adaptive stiffness control and motion optimization of a snake-like robot with variable stiffness actuators. The robot can vary its stiffness by controlling magnetorheological fluid(MRF) around actuators. In order to improve the robot's physical stability in complex environments, this work proposes an adaptive stiffness control strategy. This strategy is also useful for the robot to avoid disturbing caused by emergency situations such as collisions. In addition, to obtain optimal stiffness and reduce energy consumption, both torques of actuators and stiffness of the MRF braker are considered and optimized by using an evolutionary optimization algorithm. Simulations and experiments are conducted to verify the proposed adaptive stiffness control and optimization methods for a variable stiffness snake-like robots.

Chinese consensus on management of tyrosine kinase inhibitor-associated side effects in gastrointestinal stromal tumors

Tyrosine kinase inhibitors(TKIs) have improved the overall survival of patients with gastrointestinal stromal tumors(GISTs), but their side effects can impact dose intensity and, consequently, the clinical benefit. To date, no guideline or consensus has been published on the TKI-associated adverse reactions. Therefore, the Chinese Society of Surgeons for Gastrointestinal Stromal Tumor of the Chinese Medical Doctor Association organized an expert panel discussion involving representatives from gastrointestinal surgery, medical oncology, cardiology, dermatology, nephrology, endocrinology, and ophthalmology to consider the systemic clinical symptoms, molecular and cellular mechanisms, and treatment recommendations of GISTs. Here, we present the resultant evidence-and experience-based consensus to guide the management of TKI-associated side events in clinical practice.

PAd-shRNA-PTN reduces pleiotrophin of pancreatic cancer cells and inhibits neurite outgrowth of DRG

AIM:To investigate the silencing effects of pAdshRNA-pleiotrophin(PTN) on PTN in pancreatic cancer cells,and to observe the inhibition of pAd-shRNA-PTN on neurite outgrowth from dorsal root ganglion(DRG) neurons in vitro.METHODS:PAd-shRNA-PTN was used to infect pancreatic cancer BxPC-3 cells;assays were conducted for knockdown of the PTN gene on the 0th,1st,3rd,5th,7th and 9th d after infection using immunocytochemistry,real-time quantitative polymerase chain reaction(PCR),and Western blotting analysis.The morphologic changes of cultured DRG neurons were observed by mono-culture of DRG neurons and co-culture with BXPC-3 cells in vitro.RESULTS:The real-time quantitative PCR showed that the inhibition rates of PTN mRNA expression in the BxPC-3 cells were 20%,80%,50% and 25% on the 1st,3rd,5th and 7th d after infection.Immunocytochemistry and Western blotting analysis also revealed the same tendency.In contrast to the control,the DRG neurons co-cultured with the infected BxPC-3 cells shrunk;the number and length of neurites were significantly decreased.CONCLUSION:Efficient and specific knockdown of PTN in pancreatic cancer cells and the reduction in PTN expression resulted in the inhibition of neurite outgrowth from DRG neurons.

Performance improvement of magneto-acousto-electrical tomography for biological tissues with sinusoid-Barker coded excitation

By combining magnetics, acoustics and electrics, the magneto-acoustic-electrical tomography（MAET） proves to possess the capability of differentiating electrical impedance variation and thus improving the spatial resolution. However,the signal-to-noise ratio（SNR） of the collected MAET signal is still unsatisfactory for biological tissues with low-level electrical conductivity. In this study, the formula of MAET measurement with sinusoid-Barker coded excitation is derived and simplified for a planar piston transducer. Numerical simulations are conducted for a four-layered gel phantom with the 13-bit sinusoid-Barker coded excitation, and the performances of wave packet recovery with side-lobe suppression are improved by using the mismatched compression filter, which is also demonstrated by experimentally measuring a three-layered gel phantom. It is demonstrated that comparing with the single-cycle sinusoidal excitation, the amplitude of the driving signal can be reduced greatly with an SNR enhancement of 10 dB using the 13-bit sinusoid-Barker coded excitation. The amplitude and polarity of the wave packet filtered from the collected MAET signal can be used to achieve the conductivity derivative at the tissue boundary. In this study, we apply the sinusoid-Barker coded modulation method and the mismatched suppression scheme to MAET measurement to ensure the safety for biological tissues with improved SNR and spatial resolution, and suggest the potential applications in biomedical imaging.

The promises and challenges of patient-derived tumor organoids in drug development and precision oncology

In the era of precision medicine,cancer researchers and oncologists are eagerly searching for more realistic,cost effective,and timely tumor models to aid drug development and precision oncology.Tumor models that can faithfully recapitulate the histological and molecular characteristics of various human tumors will be extremely valuable in increasing the successful rate of oncology drug development and discovering the most efficacious treatment regimen for cancer patients.Two‐dimensional(2D)cultured cancer cell lines,genetically engineered mouse tumor(GEMT)models,and patient‐derived tumor xenograft(PDTX)models have been widely used to investigate the biology of various types of cancers and test the efficacy of oncology drug candidates.However,due to either the failure to faithfully recapitulate the complexity of patient tumors in the case of 2D cultured cancer cells,or high cost and untimely for drug screening and testing in the case of GEMT and PDTX,new tumor models are urgently needed.The recently developed patient‐derived tumor organoids(PDTO)offer great potentials in uncovering novel biology of cancer development,accelerating the discovery of oncology drugs,and individualizing the treatment of cancers.In this review,we will summarize the recent progress in utilizing PDTO for oncology drug discovery.In addition,we will discuss the potentials and limitations of the current PDTO tumor models.

Cooperative maneuver decision making for multi-UAV air combat based on incomplete information dynamic game

Cooperative autonomous air combat of multiple unmanned aerial vehicles(UAVs)is one of the main combat modes in future air warfare,which becomes even more complicated with highly changeable situation and uncertain information of the opponents.As such,this paper presents a cooperative decision-making method based on incomplete information dynamic game to generate maneuver strategies for multiple UAVs in air combat.Firstly,a cooperative situation assessment model is presented to measure the overall combat situation.Secondly,an incomplete information dynamic game model is proposed to model the dynamic process of air combat,and a dynamic Bayesian network is designed to infer the tactical intention of the opponent.Then a reinforcement learning framework based on multiagent deep deterministic policy gradient is established to obtain the perfect Bayes-Nash equilibrium solution of the air combat game model.Finally,a series of simulations are conducted to verify the effectiveness of the proposed method,and the simulation results show effective synergies and cooperative tactics.