Kernel method based human model for enhancing interactive evolutionary optimization.
Ontology highlight
ABSTRACT:
SUBMITTER: Pei Y
PROVIDER: S-EPMC4386548 | biostudies-other | 2015
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Spaced repetition is a technique for efficient memorization which uses repeated review of content following a schedule determined by a spaced repetition algorithm to improve long-term retention. However, current spaced repetition algorithms are simple rule-based heuristics with a few hard-coded parameters. Here, we introduce a flexible representation of spaced repetition using the framework of marked temporal point processes and then address the design of spaced repetition algorithms with provable guarantees as an optimal control problem for stochastic differential equations with jumps. For two well-known human memory models, we show that, if the learner aims to maximize recall probability of the content to be learned subject to a cost on the reviewing frequency, the optimal reviewing schedule is given by the recall probability itself. As a result, we can then develop a simple, scalable online spaced repetition algorithm, MEMORIZE, to determine the optimal reviewing times. We perform a large-scale natural experiment using data from Duolingo, a popular language-learning online platform, and show that learners who follow a reviewing schedule determined by our algorithm memorize more effectively than learners who follow alternative schedules determined by several heuristics.
| S-EPMC6410796 | biostudies-literature
Project description:Kernel mapping is one of the most used approaches to intrinsically derive nonlinear classifiers. The idea is to use a kernel function which maps the original nonlinearly separable problem to a space of intrinsically larger dimensionality where the classes are linearly separable. A major problem in the design of kernel methods is to find the kernel parameters that make the problem linear in the mapped representation. This paper derives the first criterion that specifically aims to find a kernel representation where the Bayes classifier becomes linear. We illustrate how this result can be successfully applied in several kernel discriminant analysis algorithms. Experimental results, using a large number of databases and classifiers, demonstrate the utility of the proposed approach. The paper also shows (theoretically and experimentally) that a kernel version of Subclass Discriminant Analysis yields the highest recognition rates.
| S-EPMC3149884 | biostudies-literature
Project description:Improving dose calculation accuracy is crucial in intensity-modulated radiation therapy (IMRT). We have developed a method for generating a phase-space-based dose kernel for IMRT planning of lung cancer patients.Particle transport in the linear accelerator treatment head of a 21EX, 6 MV photon beam (Varian Medical Systems, Palo Alto, CA) was simulated using the EGSnrc/BEAMnrc code system. The phase space information was recorded under the secondary jaws. Each particle in the phase space file was associated with a beamlet whose index was calculated and saved in the particle's LATCH variable. The DOSXYZnrc code was modified to accumulate the energy deposited by each particle based on its beamlet index. Furthermore, the central axis of each beamlet was calculated from the orientation of all the particles in this beamlet. A cylinder was then defined around the central axis so that only the energy deposited within the cylinder was counted. A look-up table was established for each cylinder during the tallying process. The efficiency and accuracy of the cylindrical beamlet energy deposition approach was evaluated using a treatment plan developed on a simulated lung phantom.Profile and percentage depth doses computed in a water phantom for an open, square field size were within 1.5% of measurements. Dose optimized with the cylindrical dose kernel was found to be within 0.6% of that computed with the nontruncated 3D kernel. The cylindrical truncation reduced optimization time by approximately 80%.A method for generating a phase-space-based dose kernel, using a truncated cylinder for scoring dose, in beamlet-based optimization of lung treatment planning was developed and found to be in good agreement with the standard, nontruncated scoring approach. Compared to previous techniques, our method significantly reduces computational time and memory requirements, which may be useful for Monte-Carlo-based 4D IMRT or IMAT treatment planning.
| S-EPMC3344881 | biostudies-other
Project description:At the dawn of a new era in label-free quantitation on high-resolution MS instruments, classical methods such as iTRAQ continue to provide very useful insights in comparative proteomics. The potential to multiplex samples makes this reporter-based labeling technique highly suited for method optimization as demonstrated here by a set of standard series. Instead of studying ratios of annotated proteins, we propose an alternative method, based on the analysis of the average reporter ratios of all the spectra from a sample or a large distinct subset herein. This strategy circumvents the bias, associated with the annotation and iTRAQ quantitation, leading to increased adequacy in measuring yield differences between workflows. As gel electrophoresis prior to MS analysis is highly beneficial, for example, as a fractionation step, the approach was applied to evaluate the influence of several parameters of the established in-gel digestion protocol. We quantified the negative effect of SYPRO Ruby staining and the positive effect of gel fixation prior to digestion on peptide yield. Finally, we emphasize the benefits of adding CaCl2 and ACN to a tryptic in-gel digest, resulting in an up to tenfold enhanced peptide recovery and fewer trypsin missed cleavages.
| S-EPMC4413792 | biostudies-other
Project description:BackgroundIn many applications of bioinformatics, data stem from distinct heterogeneous sources. One of the well-known examples is the identification of drug-target interactions (DTIs), which is of significant importance in drug discovery. In this paper, we propose a novel framework, manifold optimization based kernel preserving embedding (MOKPE), to efficiently solve the problem of modeling heterogeneous data. Our model projects heterogeneous drug and target data into a unified embedding space by preserving drug-target interactions and drug-drug, target-target similarities simultaneously.ResultsWe performed ten replications of ten-fold cross validation on four different drug-target interaction network data sets for predicting DTIs for previously unseen drugs. The classification evaluation metrics showed better or comparable performance compared to previous similarity-based state-of-the-art methods. We also evaluated MOKPE on predicting unknown DTIs of a given network. Our implementation of the proposed algorithm in R together with the scripts that replicate the reported experiments is publicly available at https://github.com/ocbinatli/mokpe .
| S-EPMC10324162 | biostudies-literature
Project description:In the current study, based on the national fire statistics from 2003 to 2017, we analyzed the 24-hour occurrence regularity of fire in China to study the occurrence regularity and influencing factors of fire and provide a reference for scientific and effective fire prevention. The results show that the frequency of fire is low from 0 to 6 at night, accounting for about 13.48%, but the death toll due to fire is relatively high, accounting for about 39.90%. Considering the strong seasonal characteristics of the time series of monthly fire frequency, the SARIMA model predicts the fire frequency. According to the characteristics of time series data and prediction results, an optimized Seasonal Autoregressive Integrated Moving Average Model (SARIMA) model based on Quantile outlier detection method and similar mean interpolation method is proposed, and finally, the optimal model is constructed as SARIMA (1,1,1) (1,1,1) 12 for prediction. The results show that: according to the optimized SARIMA model to predict the number of fires in 2018 and 2019, the root mean square error of the fitting results is 2826.93, which is less than that of the SARIMA model, indicating that the improved SARIMA model has a better fitting effect. The accuracy of the results is increased by 11.5%. These findings verified that the optimized SARIMA model is an effective improvement for the series with quantile outliers, and it is more suitable for the data prediction with seasonal characteristics. The research results can better mine the law of fire aggregation and provide theoretical support for fire prevention and control work of the fire department.
| S-EPMC8352067 | biostudies-literature
Project description:High dimensionality and small sample sizes, and their inherent risk of overfitting, pose great challenges for constructing efficient classifiers in microarray data classification. Therefore a feature selection technique should be conducted prior to data classification to enhance prediction performance. In general, filter methods can be considered as principal or auxiliary selection mechanism because of their simplicity, scalability, and low computational complexity. However, a series of trivial examples show that filter methods result in less accurate performance because they ignore the dependencies of features. Although few publications have devoted their attention to reveal the relationship of features by multivariate-based methods, these methods describe relationships among features only by linear methods. While simple linear combination relationship restrict the improvement in performance. In this paper, we used kernel method to discover inherent nonlinear correlations among features as well as between feature and target. Moreover, the number of orthogonal components was determined by kernel Fishers linear discriminant analysis (FLDA) in a self-adaptive manner rather than by manual parameter settings. In order to reveal the effectiveness of our method we performed several experiments and compared the results between our method and other competitive multivariate-based features selectors. In our comparison, we used two classifiers (support vector machine, [Formula: see text]-nearest neighbor) on two group datasets, namely two-class and multi-class datasets. Experimental results demonstrate that the performance of our method is better than others, especially on three hard-classify datasets, namely Wang's Breast Cancer, Gordon's Lung Adenocarcinoma and Pomeroy's Medulloblastoma.
| S-EPMC4105478 | biostudies-literature
Project description:Water shortages have become a serious issue, so the importance of developing innovative cellulose-based superabsorbent polymer (SAP) was experimentally assessed as an environmentally friendly alternative to acrylate-based SAPs for the optimization of water consumption. The development of a biodegradable superabsorbent hydrogel composite based on a graft copolymer of carboxymethyl cellulose (CMC) and mixtures of different comonomers such as an acrylamide-co-acrylic acid-co-2-acrylamido-2-methylpropanesulfonic acid (Am-co-AA-co-AMPS) CMC-g-TerPoly interpenetrating network was characterized by infrared spectroscopy (FT-IR), scan electron microscopy (SEM), atomic force microscope (AFM), thermal gravimetric analysis (TGA), and swelling capacity in different aqueous media. The optimized CMC-g-(TerPoly) composite showing outstanding superabsorbance with high water retention, the ratio of constituents, temperature, and pH effect on equilibrium swelling have been optimized by using multistage response surface methodology (RSM). In distilled water (d-water), the equilibrium water absorption capacity (EW) of the synthesized composite hydrogels (SAP-IPN1) is 1200 g (d-water/1g hydrogel) which is superior to any other commercial polyacrylate SAP hydrogels, while in saline water the EW is 650 g (s-water/1g hydrogel). The performance of the SAP-IPN for water retention was evaluated by studying several swelling/deswelling cycle measurements. The prepared SAP-IPN hydrogels were found to show pH and salt solution dependence on the swelling behavior. The new SAP-IPN can work with commercial SAP, which is recommended for application as a water reservoir in arid land for irrigation for agriculture purposes.
| S-EPMC8928555 | biostudies-literature
Project description:A computational model of underground metabolism and laboratory evolution experiments were employed to examine the role of enzyme promiscuity in the acquisition and optimization of growth on predicted non-native substrates in E. coli K-12 MG1655. After as few as 20 generations, the evolving populations repeatedly acquired the capacity to grow on five predicted novel substrates--D-lyxose, D-2-deoxyribose, D-arabinose, m-tartrate, and monomethyl succinate--none of which could support growth in wild-type cells. Promiscuous enzyme activities played key roles in multiple phases of adaptation. Potential mechanisms for optimizing growth on the non-native carbon sources were explored by analyzing the transcriptomes of initial and endpoint populations.
2018-05-14 | GSE114358 | GEO
Project description:The analysis of cancer genomic data has long suffered "the curse of dimensionality." Sample sizes for most cancer genomic studies are a few hundreds at most while there are tens of thousands of genomic features studied. Various methods have been proposed to leverage prior biological knowledge, such as pathways, to more effectively analyze cancer genomic data. Most of the methods focus on testing marginal significance of the associations between pathways and clinical phenotypes. They can identify informative pathways but do not involve predictive modeling. In this article, we propose a Pathway-based Kernel Boosting (PKB) method for integrating gene pathway information for sample classification, where we use kernel functions calculated from each pathway as base learners and learn the weights through iterative optimization of the classification loss function. We apply PKB and several competing methods to three cancer studies with pathological and clinical information, including tumor grade, stage, tumor sites and metastasis status. Our results show that PKB outperforms other methods and identifies pathways relevant to the outcome variables.
| S-EPMC6770716 | biostudies-literature