|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Machine learning in materials informatics:recent applications and prospects显示文摘Propelled partly by the Materials Genome Initiative,and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains,informatics strategies are beginning to take shape within materials science.These approaches lead to surrogate machine learning models that enable rapid predictions based purely on past data rather than by direct experimentation or by computations/simulations in which fundamental equations are explicitly solved.Data-centric informatics methods are becoming useful to determine material properties that are hard to measure or compute using traditional methods—due to the cost,time or effort involved—but for which reliable data either already exists or can be generated for at least a subset of the critical cases.Predictions are typically interpolative,involving fingerprinting a material numerically first,and then following a mapping(established via a learning algorithm)between the fingerprint and the property of interest.Fingerprints,also referred to as“descriptors”,may be of many types and scales,as dictated by the application domain and needs.Predictions may also be extrapolative—extending into new materials spaces—provided prediction uncertainties are properly taken into account.This article attempts to provide an overview of some of the recent successful data-driven“materials informatics”strategies undertaken in the last decade,with particular emphasis on the fingerprint or descriptor choices.The review also identifies some challenges the community is facing and those that should be overcome in the near future. | Rampi Ramprasad Rohit Batra Ghanshyam Pilania Arun Mannodi-Kanakkithodi Chiho Kim | 2017 | npj Computational Materials2017，，1： | 40 |
| 2 | A universal strategy for the creation of machine learning-based atomistic force fields显示文摘Emerging machine learning(ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems.In this contribution,we outline a universal strategy to create ML-based atomistic force fields,which can be used to perform high-fidelity molecular dynamics simulations.This scheme involves(1)preparing a big reference dataset of atomic environments and forces with sufficiently low noise,e.g.,using density functional theory or higher-level methods,(2)utilizing a generalizable class of structural fingerprints for representing atomic environments,(3)optimally selecting diverse and nonredundant training datasets from the reference data,and(4)proposing various learning approaches to predict atomic forces directly(and rapidly)from atomic configurations.From the atomistic forces,accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory.Based on this strategy,we have created model ML force fields for six elemental bulk solids,including Al,Cu,Ti,W,Si,and C,and show that all of them can reach chemical accuracy.The proposed procedure is general and universal,in that it can potentially be used to generate ML force fields for any material using the same unified workflow with little human intervention.Moreover,the force fields can be systematically improved by adding new training data progressively to represent atomic environments not encountered previously. | Tran Doan Huan Rohit Batra James Chapman Sridevi Krishnan Lihua Chen Rampi Ramprasad | 2017 | npj Computational Materials2017，，1： | 10 |
| 3 | Solving the electronic structure problem with machine learning显示文摘Simulations based on solving the Kohn-Sham(KS)equation of density functional theory(DFT)have become a vital component of modern materials and chemical sciences research and development portfolios.Despite its versatility,routine DFT calculations are usually limited to a few hundred atoms due to the computational bottleneck posed by the KS equation.Here we introduce a machine-learning-based scheme to efficiently assimilate the function of the KS equation,and by-pass it to directly,rapidly,and accurately predict the electronic structure of a material or a molecule,given just its atomic configuration.A new rotationally invariant representation is utilized to map the atomic environment around a grid-point to the electron density and local density of states at that grid-point.This mapping is learned using a neural network trained on previously generated reference DFT results at millions of grid-points.The proposed paradigm allows for the high-fidelity emulation of KS DFT,but orders of magnitude faster than the direct solution.Moreover,the machine learning prediction scheme is strictly linear-scaling with system size. | Anand Chandrasekaran Deepak Kamal Rohit Batra Chiho Kim Lihua Chen Rampi Ramprasad | 2019 | npj Computational Materials2019，，1： | 10 |
| 4 | Efficacy of peroral endoscopic myotomy vs other achalasia treatments in improving esophageal function显示文摘AIM: To assess and compare the esophageal function after peroral endoscopic myotomy(POEM) vs other conventional treatments in achalasia.METHODS: Chart review of all achalasia patients who underwent POEM, laparoscopic Heller myotomy(LHM) or pneumatic dilation(PD) at our institution between January 2012 and March 2015 was performed. Patient demographics, type of achalasia, prior treatments, pre- and post-treatment timed barium swallow(TBE) and high-resolution esophageal manometry(HREM) findings were compared between the three treatment groups. Patients who had both pre- and 2 mo posttreatment TBE or HREM were included in the final analysis. TBE parameters compared were barium column height, width and volume of barium remaining at 1 and 5 min. HREM parameters compared were basal lower esophageal sphincter(LES) pressures and LES-integrated relaxation pressures(IRP). Data are presented as mean ± SD, median [25th, 75 th percentiles] or frequency(percent). Analysis of variance, KruskalWallis test, Pearsons χ~2 test and Fishers Exact tests were used for analysis.RESULTS: A total of 200 achalasia patients were included of which 36 underwent POEM, 22 underwent PD and 142 underwent LHM. POEM patients were older(55.4 ± 16.8 years vs 46.5 ± 15.7 years, P = 0.013) and had higher BMI than LHM(29.1 ± 5.9 kg/m^2 vs 26 ± 5.1 kg/m^2, P = 0.012). More number of patients in POEM and PD groups had undergone prior treatments compared to LHM group(72.2% vs 68.2% vs 44.3% respectively, P = 0.003). At 2 mo post-treatment, all TBE parameters including barium column height, width and volume remaining at 1 and 5 min improved significantly in all three treatment groups(P = 0.01 to P < 0.001) except the column height at 1 min in PD group(P = 0.11). At 2 mo post-treatment, there was significant improvement in basal LES pressure and LES-IRP in both LHM(40.5 mm Hg vs 14.5 mm Hg and 24 mm Hg vs 7.1 mm Hg respectively, P < 0.001) and POEM groups(38.7 mm Hg vs 11.4 mm Hg and 23.6 mm Hg vs 6.6 mm Hg respectively, P < 0.001). However, when the efficacy of three treatments were compared to each other in terms of improvement in TBE or HREM parameters at 2 mo, there was no significant difference(P > 0.05).CONCLUSION: POEM, PD and LHM were all effective in improving esophageal function in achalasia at shortterm. There was no difference in efficacy between the three treatments. | Madhusudhan R Sanaka Umar Hayat Prashanthi N Thota Ramprasad Jegadeesan Monica Ray Scott L Gabbard Neha Wadhwa Rocio Lopez Mark E Baker Sudish Murthy Siva Raja | 2016 | World Journal of Gastroenterology2016，22，20： | 7 |
| 5 | Factors predicting adverse short-term outcomes in patients with acute cholangitis undergoing ERCP: A single center experience显示文摘AIM: To identify potential factors that can predict adverse short-term outcomes in patients with acute cholangitis undergoing endoscopic retrograde cholangiopancreatography(ERCP). METHODS: Retrospective analysis of consecutive patients admitted to our center for acute cholangitis and underwent ERCP from 2001 to 2012. Involvement of two or more organ systems was termed as organ failure(OF). Cardiovascular failure was defined based on a systolic blood pressure of < 90 mmHg despite fluid replacement and/or requiring vasopressor treatment; respiratory failure if the Pa02 /Fi02 ratio was < 300 mmHg and/or required mechanical ventilation; coagulopathy if the platelet count was < 80; and renal insufficiency if serum creatinine was > 1.9 mg/dL. Variables associated with short term adverse clinical outcomes defined as persistent OF and/or 30-d mortality was determined. RESULTS: A total of 172 patients(median age 62 years, 56.4% female) were included. The median door to ERCP time was 17 h. Bile duct stones were the most common etiology(n = 67, 39.2%). In multivariate analysis, factors that were independently associated with persistent OF and/or 30-d mortality included American Society of Anesthesiology(ASA) physical classification score > 3(OR = 7.70; 95%CI: 2.73-24.40), presence of systemic inflammatory response syndrome(OR = 3.67; 95%CI: 1.34-10.3) and door to ERCP time greater than 72 h(OR = 3.36; 95%CI: 1.12-10.20). Door to ERCP time greater than 72 h was also associated with 70% increase in the mean length of stay(P < 0.001). Every one point increase in the ASA physical classification and every 1 mg/dL increase in the preERCP bilirubin level was associated with a 34% and 2% increase in the mean length of hospital stay, respectively. Transfer status did not impact clinical outcomes. CONCLUSION: Higher ASA physical classification and delays in ERCP are associated with adverse clinical outcomes and prolonged length of hospital stay in patients with acute cholangitis undergoing ERCP. | Udayakumar Navaneethan Norma G Gutierrez Ramprasad Jegadeesan Preethi GK Venkatesh Madhusudhan R Sanaka John J Vargo Mansour A Parsi | 2014 | World Journal of Gastrointestinal Endoscopy2014，6，3： | 7 |
| 6 | Synthesis and antimycobacterial screening of new N-(4-(5-aryl-3-(5-methyl-1,3,4-oxadiazol-2-yl)-1H-pyrazol-1-yl)phenyl)-4-amide derivatives显示文摘This article demonstrates the synthesis, characterization and the study of in vitro antitubercular activities of twenty four new N-(4-(5-aryl-3-(5-methyl-1,3,4-oxadiazol-2-yl)-1H-pyrazol-1-yl)phenyl)-4-amide derivatives(8a–x). The antitubercular activity of the compounds against Mycobacterium tuberculosis H37Rv(MTB) revealed that 2-chloro-N-(4-(5-(4-chlorophenyl)-3-(5-methyl-1,3,4-oxadiazol-2-yl)-1H-pyrazol-1-yl)phenyl)benzamide(8n) is the most promising lead molecule with a MIC of1.56 mg/m L, while the corresponding unsubstituted benzamide derivative(8o) is the next most active molecule with a MIC of 3.13 mg/m L. Interestingly, the pyrazole intermediate 5b containing chlorophenyl and N-acylcarbohydrazide substituents also showed significant activity(MIC = 3.13 mg/m L). Further, the active molecules did not show toxicity against a normal NIH 3T3 cell line, signifying their suitability for further drug development. | Nagabhushana Nayak Jurupula Ramprasad Udayakumar Dalimba Perumal Yogeeswari Dharmarajan Sriram | 2016 | Chinese Chemical Letters2016，27，3： | 2 |
| 7 | Frequency-dependent dielectric constant prediction of polymers using machine learning显示文摘The dielectric constant(ϵ)is a critical parameter utilized in the design of polymeric dielectrics for energy storage capacitors,microelectronic devices,and high-voltage insulations.However,agile discovery of polymer dielectrics with desirableϵremains a challenge,especially for high-energy,high-temperature applications.To aid accelerated polymer dielectrics discovery,we have developed a machine-learning(ML)-based model to instantly and accurately predict the frequency-dependentϵof polymers with the frequency range spanning 15 orders of magnitude.Our model is trained using a dataset of 1210 experimentally measuredϵvalues at different frequencies,an advanced polymer fingerprinting scheme and the Gaussian process regression algorithm. | Lihua Chen Chiho Kim Rohit Batra Jordan P.Lightstone Chao Wu Zongze Li Ajinkya A.Deshmukh Yifei Wang Huan D.Tran Priya Vashishta Gregory A.Sotzing Yang Cao Rampi Ramprasad | 2020 | npj Computational Materials2020，，1： | 2 |
| 8 | Noise degradation system using Wiener filter and CORDIC based FFT/IFFT processor显示文摘On augmentation of past work, an effective Wiener filter and its application for noise suppression combined with a formed CORDIC based FFT/IFFT processor with improved speed were executed. The pipelined methodology was embraced for expanding the execution of the system. The proposed Wiener filter was planned in such an approach to evacuate the iteration issues in ordinary Wiener filter. The division process was supplanted by a productive inverse and multiplication process in the proposed design. An enhanced design for matrix inverse with reduced computation complexity was executed. The wide-ranging framework processing was focused around IEEE-754 standard single precision floating point numbers. The Wiener filter and the entire system design was integrated and actualized on VIRTEX 5 FPGA stage and re-enacted to approve the results in Xilinx ISE 13.4. The results show that a productive decrease in power and area is developed by adjusting the proposed technique for speech signal noise degradation with latency of n/2 clock cycles and substantial throughput result per every 12 clock cycles for n-bit precision. The execution of proposed design is exposed to be 31.35% more effective than that of prevailing strategies. | Yasodai A Ramprasad A V | 2015 | Journal of Central South University2015，22，10： | 2 |
| 9 | Up-regulated cystic fibrosis transmembrane conductance regulator after anal stenosis in rats 显示文摘 | Ramprasad J Sood M Ludwig K | 2012 | J Pediatr Surg2012，47，3： | 1 |
| 10 | Xanthogranulomatous pyelonephritis : a Retrospective review of 16 cases 显示文摘 | Siddappa S Ramprasad K Muddegowda MK | 2011 | Korean J Uro12011，52，6： | 1 |
| 11 | Multishell carrier transport in multiwalled carbon nanotubes显示文摘 | AGRAWAL S RAGHUVEER M S RAMPRASAD R | 2007 | Nanotechnology IEEE2007，6，6： | 1 |
| 12 | ,Association of Gly82Ser polymorphism in the RAGE genewith diabetic retinopathy in type II diabetic Asian In-dian patients显示文摘 | Kumaramanickave1 G Ramprasad VL Sripriya S | 2002 | J Diabetes Complications2002，16，： | 1 |
| 13 | The sustained granulo- poietic effect of progenipoietin encapsulated in multivesieular liposomes 显示文摘 | Ramprasad MP Amini A Kararli T | 2003 | Int J Pharm2003，261，12： | 1 |
| 14 | Rage gene pro-moter polymorphisms and diabetic retinopathy in a clin-ic- based population from South India显示文摘 | Ramprasad S Radha V Mathias RA | 2007 | Eye2007，21，： | 1 |
| 15 | Information theoretic bounds on average signal transition activity显示文摘 | Ramprasad S Shanbhag N R Haji J N | | 0，，： | 1 |
| 16 | Magnetic properties of metallic ferromagnetic nanoparticle composites 显示文摘 | RAMPRASAD R ZURCHER P PETRA M | 2004 | J Appl Phys2004，96，1： | 1 |
| 17 | Quantum mechanical studies of carbonyl impurities in dielectric polyethylene显示文摘 | Huzayyin A Boggs S Ramprasad R | 2010 | IEEE Transactions on Dielectrics and Electrical Insulation2010，17，3： | 1 |
| 18 | Thyroid disorders in pregnancy Indian J Endocrinol Metab 显示文摘 | Ramprasad M Bhattacharyya SS Bhattacharyya A | 2012 | Indian J Endocrinol Metab2012，16，2： | 1 |
| 19 | Automatic inter- pretation of magnetic data using Euler deconvolution with nonlinear background显示文摘 | Dewangan P Ramprasad T Ramana M V | 2007 | Pure and Applied Geophysics2007，164，11： | 1 |
| 20 | Density functional analysis of chemical impurities in dielectric polyethylene显示文摘 | Huzayyin A Boggs S Ramprasad R | 2010 | IEEE Transactions on Dielectrics and Electrical Insulation2010，17，3： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员