Mediaboss Marketing

Zhu, F., Luo, G. Q., Liao, Z., Dai, X. W. & Wu, K. Compact dual-mode bandpass filters based on half-mode substrate-integrated waveguide cavities. IEEE Microw. Wirel. Compon. Lett. 31(5), 441444 (2021).

Article ADS Google Scholar

Erman, F., Koziel, S., Hanafi, E., Soboh, R. & Szczepanski, S. Miniaturized metal-mountable U-shaped inductive-coupling-fed UHF RFID tag antenna with defected microstrip surface. IEEE Access 10, 4730147308 (2022).

Article Google Scholar

Zhang, H. et al. A low-profile compact dual-band L-shape monopole antenna for microwave thorax monitoring. IEEE Ant. Wirel. Propag. Lett. 19(3), 448452 (2020).

Article ADS Google Scholar

Matos, D., da Cruz Jordo, M. D., Correia, R. & Carvalho, N. B. Millimeter-wave BiCMOS backscatter modulator for 5 G-IoT applications. IEEE Microw. Wirel. Compon. Lett. 31(2), 173176 (2021).

Article Google Scholar

Hu, Y.-Y., Sun, S. & Xu, H. Compact collinear quasi-Yagi antenna array for wireless energy harvesting. IEEE Access 8, 3530835317 (2020).

Article Google Scholar

Li, Q., Chen, X., Chi, P. & Yang, T. Tunable bandstop filter using distributed coupling microstrip resonators with capacitive terminal. IEEE Microw. Wirel. Compon. Lett. 30(1), 3538 (2020).

Article Google Scholar

Liu, M. & Lin, F. Two-section broadband couplers with wide-range phase differences and power-dividing ratios. IEEE Microw. Wirel. Compon. Lett. 31(2), 117120 (2021).

Article ADS Google Scholar

Gmez-Garca, R., Rosario-De Jesus, J. & Psychogiou, D. Multi-band bandpass and bandstop RF filtering couplers with dynamically-controlled bands. IEEE Access 6, 3232132327 (2018).

Article Google Scholar

Zhang, R. & Peroulis, D. Mixed lumped and distributed circuits in wideband bandpass filter application for spurious-response suppression. IEEE Microw. Wirel. Compon. Lett. 28(11), 978980 (2018).

Article Google Scholar

He, Z. & Liu, C. A compact high-efficiency broadband rectifier with a wide dynamic range of input power for energy harvesting. IEEE Microw. Wirel. Compon. Lett. 30(4), 433436 (2020).

Article Google Scholar

Jiang, Z. H., Gregory, M. D. & Werner, D. H. Design and experimental investigation of a compact circularly polarized integrated filtering antenna for wearable biotelemetric devices. IEEE Trans. Biomedical Circuits Syst. 10(2), 328338 (2016).

Article Google Scholar

Kracek, J., vanda, M., Mazanek, M. & Machac, J. Implantable semi-active UHF RFID tag with inductive wireless power transfer. IEEE Ant. Wirel. Propag. Lett. 15, 16571660 (2016).

Article ADS Google Scholar

Firmansyah, T., Alaydrus, M., Wahyu, Y., Rahardjo, E. T. & Wibisono, G. A highly independent multiband bandpass filter using a multi-coupled line stub-SIR with folding structure. IEEE Access 8, 8300983026 (2020).

Article Google Scholar

Chen, S. et al. A frequency synthesizer based microwave permittivity sensor using CMRC structure. IEEE Access 6, 85568563 (2018).

Article Google Scholar

Zhu, Y., Wang, J., Hong, J., Chen, J.-X. & Wu, W. Two- and three-way filtering power dividers with harmonic suppression using triangle patch resonator. IEEE Trans. Circuits Syst. I Regul. Pap. 68(12), 50075017 (2021).

Article Google Scholar

Wei, F., Jay Guo, Y., Qin, P. & Wei Shi, X. Compact balanced dual- and tri-band bandpass filters based on stub loaded resonators. IEEE Microw. Wirel. Compon. Lett. 25(2), 7678 (2015).

Article Google Scholar

Koziel, S. & Bandler, J. W. Space mapping with multiple coarse models for optimization of microwave components. IEEE Microw. Wirel. Compon. Lett. 18, 13 (2008).

Article Google Scholar

Chione, G. & Pirola, M. Microwave Electronics (Cambridge University Press, 2018).

Google Scholar

Ullah, U., Al-Hasan, M., Koziel, S. & Ben Mabrouk, I. Series-slot-fed circularly polarized multiple-input-multiple-output antenna array enabling circular polarization diversity for 5G 28-GHz indoor applications. IEEE Trans. Ant. Prop. 69(9), 56075616 (2021).

Article ADS Google Scholar

Zhu, Y. & Dong, Y. A novel compact wide-stopband filter with hybrid structure by combining SIW and microstrip technologies. IEEE Microw. Wirel. Compon. Lett. 31(7), 841844 (2021).

Article Google Scholar

Koziel, S., Pietrenko-Dabrowska, A. & Plotka, P. Reduced-cost microwave design closure by multi-resolution EM simulations and knowledge-based model management. IEEE Access 9, 116326116337 (2021).

Article Google Scholar

Feng, F. et al. Parallel gradient-based EM optimization for microwave components using adjoint- sensitivity-based neuro-transfer function surrogate. IEEE Trans. Microw. Theory Techn. 68(9), 36063620 (2020).

Article ADS Google Scholar

Kolda, T. G., Lewis, R. M. & Torczon, V. Optimization by direct search: new perspectives on some classical and modern methods. SIAM Rev. 45, 385482 (2003).

Article ADS MathSciNet Google Scholar

Shen, Z., Xu, K., Mbongo, G. M., Shi, J. & Yang, Y. Compact balanced substrate integrated waveguide filter with low insertion loss. IEEE Access 7, 126111126115 (2019).

Article Google Scholar

Li, Y., Ren, P. & Xiang, Z. A dual-passband frequency selective surface for 5G communication. IEEE Antennas Wirel. Propag. Lett. 18(12), 25972601 (2019).

Article ADS Google Scholar

Abdullah, M. & Koziel, S. Supervised-learning-based development of multi-bit RCS-reduced coding metasurfaces. IEEE Trans. Microw. Theory Tech. 70(1), 264274 (2021).

Article ADS Google Scholar

Blankrot, B. & Heitzinger, C. Efficient computational design and optimization of dielectric metamaterial structures. IEEE J. Multiscale Multiphysics Comp. Tech. 4, 234244 (2019).

Article ADS Google Scholar

Ma, Y., Yang, S., Chen, Y., Qu, S.-W. & Hu, J. Pattern synthesis of 4-D irregular antenna arrays based on maximum-entropy model. IEEE Trans. Antennas Propag. 67(5), 30483057 (2019).

Article ADS Google Scholar

Tang, M., Chen, X., Li, M. & Ziolkowski, R. W. Particle swarm optimized, 3-D-printed, wideband, compact hemispherical antenna. IEEE Antennas Wirel. Propag. Lett. 17(11), 20312035 (2018).

Article ADS Google Scholar

Li, H., Jiang, Y., Ding, Y., Tan, J. & Zhou, J. Low-sidelobe pattern synthesis for sparse conformal arrays based on PSO-SOCP optimization. IEEE Access 6, 7742977439 (2018).

Article Google Scholar

Zhang, H., Bai, B., Zheng, J. & Zhou, Y. Optimal design of sparse array for ultrasonic total focusing method by binary particle swarm optimization. IEEE Access 8, 111945111953 (2020).

Article Google Scholar

Rayas-Sanchez, J. E., Koziel, S. & Bandler, J. W. Advanced RF and microwave design optimization: A journey and a vision of future trends. IEEE J. Microw. 1(1), 481493 (2021).

Article Google Scholar

Abdullah, M. & Koziel, S. A novel versatile decoupling structure and expedited inverse-model-based re-design procedure for compact single-and dual-band MIMO antennas. IEEE Access 9, 3765637667 (2021).

Article Google Scholar

Jin, H., Zhou, Y., Huang, Y. M., Ding, S. & Wu, K. Miniaturized broadband coupler made of slow-wave half-mode substrate integrated waveguide. IEEE Microw. Wirel. Compon. Lett. 27(2), 132134 (2017).

Article Google Scholar

Martinez, L., Belenguer, A., Boria, V. E. & Borja, A. L. Compact folded bandpass filter in empty substrate integrated coaxial line at S-Band. IEEE Microw. Wirel. Compon. Lett. 29(5), 315317 (2019).

Article Google Scholar

Shum, K. M., Luk, W. T., Chan, C. H. & Xue, Q. A UWB bandpass filter with two transmission zeros using a single stub with CMRC. IEEE Microw. Wirel. Compon. Lett. 17(1), 4345 (2007).

Article ADS Google Scholar

Li, X. & Luk, K. M. The grey wolf optimizer and its applications in electromagnetics. IEEE Trans. Antennas Propag. 68(3), 21862197 (2020).

Article ADS Google Scholar

Luo, X., Yang, B. & Qian, H. J. Adaptive synthesis for resonator-coupled filters based on particle swarm optimization. IEEE Trans. Microw. Theory Tech. 67(2), 712725 (2019).

Article ADS Google Scholar

Majumder, A., Chatterjee, S., Chatterjee, S., Sinha Chaudhari, S. & Poddar, D. R. Optimization of small-signal model of GaN HEMT by using evolutionary algorithms. IEEE Microw. Wirel. Compon. Lett. 27(4), 362364 (2017).

Article Google Scholar

Oyelade, O. N., Ezugwu, A.E.-S., Mohamed, T. I. A. & Abualigah, L. Ebola optimization search algorithm: A new nature-inspired metaheuristic optimization algorithm. IEEE Access 10, 1615016177 (2022).

Article Google Scholar

Milner, S., Davis, C., Zhang, H. & Llorca, J. Nature-inspired self-organization, control, and optimization in heterogeneous wireless networks. IEEE Trans. Mobile Comput. 11(7), 12071222 (2012).

Article Google Scholar

Zhao, Q. & Li, C. Two-stage multi-swarm particle swarm optimizer for unconstrained and constrained global optimization. IEEE Access 8, 124905124927 (2020).

Article Google Scholar

Jiacheng, L. & Lei, L. A hybrid genetic algorithm based on information entropy and game theory. IEEE Access 8, 3660236611 (2020).

Article Google Scholar

Zhao, Z., Wang, X., Wu, C. & Lei, L. Hunting optimization: A new framework for single objective optimization problems. IEEE Access 7, 3130531320 (2019).

Article Google Scholar

Zhang, Q. & Liu, L. Whale optimization algorithm based on Lamarckian learning for global optimization problems. IEEE Access 7, 3664236666 (2019).

Article Google Scholar

Ismaeel, A. A. K., Elshaarawy, I. A., Houssein, E. H., Ismail, F. H. & Hassanien, A. E. Enhanced elephant herding optimization for global optimization. IEEE Access 7, 3473834752 (2019).

Article Google Scholar

Wang, P., Rao, Y. & Luo, Q. An effective discrete grey wolf optimization algorithm for solving the packing problem. IEEE Access 8, 115559115571 (2020).

Article Google Scholar

Liu, F., Liu, Y., Han, F., Ban, Y. & Jay Guo, Y. Synthesis of large unequally spaced planar arrays utilizing differential evolution with new encoding mechanism and cauchy mutation. IEEE Trans. Antennas Propag. 68(6), 44064416 (2020).

Article ADS Google Scholar

Kovaleva, M., Bulger, D. & Esselle, K. P. Comparative study of optimization algorithms on the design of broadband antennas. IEEE J. Multiscale Multiphysics Comput. Tech. 5, 8998 (2020).

Article ADS Google Scholar

Ghorbaninejad, H. & Heydarian, R. New design of waveguide directional coupler using genetic algorithm. IEEE Microw. Wirel. Compon. Lett. 26(2), 8688 (2016).

Article Google Scholar

More here:
Machine-learning-based global optimization of microwave passives with variable-fidelity EM models and response ... - Nature.com

The FE-related traits and genomic information were obtained for 1,156 animals from an experimental breeding program at the Beef Cattle Research Center (Institute of Animal Science IZ).

Animals were from an experimental breeding program at the Beef Cattle Research Center at the Institute of Animal Science (IZ) in Sertozinho, So Paulo, Brazil. Since the 1980s, the experimental station has maintained three selection herds: Nellore control (NeC) with animals selected for yearling body weight (YBW) with a selection differential close to zero, within birth year and herd, while Nellore Selection (NeS) and Nellore Traditional (NeT) animals are selected for the YBW with a maximum selection differential, also within birth year and herd25. In the NeT herd, sires from commercial herds or NeS eventually were used in the breeding season, while the NeC and NeS were closed herds (only sires from the same herd were used in the breeding season), with controlled inbreeding rate by planned matings. In addition, the NeT herd has been selected for lower residual feed intake (RFI) since 2013. In the three herds, the animal selection is based on YBW measured at 378days of age in young bulls.

The FE-related traits were evaluated on 1156 animals born between 2004 and 2015 in a feeding efficiency trial, in which they were either housed in individual pens (683 animals) or group pens equipped with the GrowSafe feeding system (473 animals), with animals grouped by sex. From those, 146 animals were from the NeC herd (104 young bulls and 42 heifers), 300 from the NeS herd (214 young bulls and 86 heifers), and 710 from the NeT herd (483 young bulls and 227 heifers). Both feeding trials comprised at least 21 days for adaptation to the feedlot diet and management and at least 56 days for the data collection period. The young bull and heifers showed an average age at the end of the feeding trial was 36627.5 and 38445.4 days, respectively.

A total of 780 animals were genotyped with the Illumina BovineHD BeadChip assay (770k, Illumina Inc., San Diego, CA, USA), while 376 animals were genotyped with the GeneSeek Genomic Profiler (GGP Indicus HD, 77K). The animals genotyped with the GGP chip were imputed to the HD panel using FImpute v.326 with an expected accuracy higher than 0.97. Autosomal SNP markers with a minor allele frequency (MAF) lower than 0.10 and a significant deviation from HardyWeinberg equilibrium (P105) were removed, and markers and samples with call rate lower than 0.95 were also removed. An MAF lower than 10% was used to remove genetic markers with lower significance and noise information in a stratified population. After this quality control procedure, genotypes from 1,024 animals and 305,128 SNP markers remained for GS analyses. Population substructure was evaluated using a principal component analysis (PCA) based on the genomic relationship matrix using the ade4 R package (Supplementary Figure S1)27.

Animals were weighed without fasting at the beginning and end of the feeding trial, as well as every 14 days during the experimental period. The mixed ration (dry corn grain, corn silage, soybean, urea, and mineral salt) was offered ad libitum and formulated with 67% of total digestible nutrients (TDN) and 13% of crude protein (CP), aiming for an average daily gain (ADG) of 1.1kg.

The following feed efficiency-related traits were evaluated: ADG, dry matter intake (DMI), feed efficiency (FE), and RFI. In the individual pens, the orts were weighed daily in the morning before the feed delivery to calculate the daily dietary intake. In the group pens, the GrowSafe feeding system automatically recorded the feed intake. Thus, the DMI (expressed as kg/day) was estimated as the feed intake by each animal with subsequent adjustments for dry matter content. ADG was estimated as the slope of the linear regression of body weight (BW) on feeding trial days, and the FE was expressed as the ratio of ADG and DMI. Finally, RFI was calculated within each contemporary group (CG), as the difference between the observed and expected feed intake considering the average metabolic body weight (MBW) and ADG of each animal (Koch et al., 1963) as follows:

$$DMI=CG+ {beta }_{0}+{beta }_{1}ADG+{beta }_{2}MBW+varepsilon$$

where ({beta }_{0}) is the model intercept, ({beta }_{1}) and ({beta }_{2}) are the linear regression coefficients for (ADG) and ({MBW=BW}^{0.75}), respectively, and (varepsilon) is the residual of the equation representing the RFI estimate.

The contemporary groups (CG) were defined by sex, year of birth, type of feed trial pen (individual or collective) and selection herd. Phenotypic observations with values outside the interval of3.5 standard deviations below and above the mean of each CG for each trait were excluded, and the number of animals per CG ranged from 10 to 70.

The (co)variance components and heritability for FE-related traits were estimated considering a multi-trait GBLUP (MTGBLUP) as follows:

$$mathbf{y}=mathbf{X}{varvec{upbeta}}+mathbf{Z}mathbf{a}+mathbf{e},$$

Where ({varvec{y}}) is the matrix of phenotypic FE-related traits (ADG, FE, DMI, and RFI) of dimension Nx4 (N individuals andfour traits); ({varvec{upbeta}}) is the vector of fixed effects, linear and quadratic effects of cow age, and linear effect of animals age at the beginning of the test; (mathbf{a}) is the vector of additive genetic effects (breeding values) of animal, and (mathbf{e}) is a vector with the residual terms. The (mathbf{X}) and (mathbf{Z}) are the incidence matrices related to fixed (b) and random effects (a), respectively. It was assumed that the random effects of animals and residuals were normally distributed, as (mathbf{a}sim {text{N}}(0,mathbf{G}otimes {mathbf{S}}_{mathbf{a}})) and (mathbf{e}sim {text{N}}(0,mathbf{I}otimes {mathbf{S}}_{mathbf{e}})), where (mathbf{G}) is the additive genomic relationship matrix between genotyped individuals according to VanRaden28, (mathbf{I}) is an identity matrix,is the Kronecker product, and ({mathbf{S}}_{mathbf{a}}=left[begin{array}{ccc}{upsigma }_{{text{a}}1}^{2}& cdots & {upsigma }_{mathrm{a1,4}}\ vdots & ddots & vdots \ {upsigma }_{mathrm{a1,4}}& cdots & {upsigma }_{{text{a}}4}^{2}end{array}right]) and ({mathbf{S}}_{mathbf{e}}=left[begin{array}{ccc}{upsigma }_{{text{e}}1}^{2}& cdots & {upsigma }_{mathrm{e1,4}}\ vdots & ddots & vdots \ {upsigma }_{mathrm{e1,4}}& cdots & {upsigma }_{{text{e}}4}^{2}end{array}right]) are the additive genetic and residual (co)variance matrices, respectively. The G matrix was obtained according to VanRaden28: (mathbf{G}=frac{mathbf{M}{mathbf{M}}^{mathbf{^{prime}}}}{2sum_{{text{j}}=1}^{{text{m}}}{{text{p}}}_{{text{j}}}left(1-{{text{p}}}_{{text{j}}}right)}) where (mathbf{M}) is the SNP marker matrix with codes 0, 1, and 2 for genotypes AA, AB, and BB adjusted for allele frequency expressed as (2{{text{p}}}_{{text{j}}}), and ({{text{p}}}_{{text{j}}}) is the frequency of the second allele jth SNP marker.

The analyses were performed using the restricted maximum likelihood (REML) method through airemlf90 software29. The predictf90 software29 was used to obtain the phenotypes adjusted for the fixed effects and covariates (({{text{y}}}^{*}={text{y}}-{text{X}}widehat{upbeta })). The adjusted phenotypes were used as the response variable in the genomic predictions.

Tthe GEBVs accuracy (({{text{Acc}}}_{{text{GEBV}}})) in the whole population, was calculated based on prediction error variance (PEV) and the genetic variance for each FE-related trait (({upsigma }_{{text{a}}}^{2})) using the following equation30: ({text{Acc}}=1-sqrt{{text{PEV}}/{upsigma }_{{text{a}}}^{2}}) .

A forward validation scheme was applied for computing the prediction accuracies using machine learning and parametric methods, splitting the dataset based on year of birth, with animals born between 2004 and 2013 assigned as the reference population (n=836) and those born in 2014 and 2015 (n=188) as the validation set. For ML approaches, we randomly split the training dataset into fivefold to train the models.

Genomic prediction for FE-related traits considering the STGBLUP can be described as follows:

$${mathbf{y}}^{mathbf{*}}={varvec{upmu}}+mathbf{Z}mathbf{a}+mathbf{e}$$

where ({mathbf{y}}^{mathbf{*}}) is the Nx1 vector of adjusted phenotypic values for FE-related traits, (upmu) is the model intercept, (mathbf{Z}) is the incidence connecting observations; (mathbf{a}) is the vector of predicted values, assumed to follow a normal distribution given by ({text{N}}(0,{mathbf{G}}sigma_{a}^{2})) and (mathbf{e}) is the Nx1 vector of residual values considered normally distributed as ({text{N}}(0,mathbf{I}{upsigma }_{{text{e}}}^{2})), in which I is an identity matrix, ({upsigma }_{{text{e}}}^{2}) is the residual variance. The STGBLUP model was performed using blupf90+software29.

Genomic prediction for FE-related traits considering MTGBLUP can be described as follows:

$${mathbf{y}}^{mathbf{*}}={varvec{upmu}}+mathbf{Z}mathbf{a}+mathbf{e}$$

where ({mathbf{y}}^{mathbf{*}}) is the matrix of adjusted phenotypes of dimension Nx4, (upmu) is the trait-specific intercept vector, (mathbf{Z}) is the incidence matrix for the random effect; (mathbf{a}) is an Nx4 matrix of predicted values, assumed to follow a normal distribution given by ({text{MVN}}(0,{mathbf{G}} otimes {mathbf{S}}_{{mathbf{a}}})) where ({mathbf{S}}_{mathbf{a}}) represents genetic (co)variance matrix for the FE-related traits (44). The residual effects (e) were considered normally distributed as ({text{MVN}}(0,mathbf{I}otimes {mathbf{S}}_{mathbf{e}})) in which I is an identity matrix, and ({mathbf{S}}_{mathbf{e}}) is the residual (co)variance matrix for FE-related traits (44). The MTGBLUP was implemented in the BGLR R package14 considering a Bayesian GBLUP with a multivariate Gaussian model with an unstructured (co)variance matrix between traits (({mathbf{S}}_{mathbf{a}})) using Gibbs sampling with 200,000 iterations, including 20,000 samples as burn-in and thinning interval of 5 cycles. Convergence was checked by visual inspection of trace plots and distribution plots of the residual variance.

Five Bayesian regression models with different priors were used for GS analyses: Bayesian ridge regression (BRR), Bayesian Lasso (BL), BayesA, BayesB, and BayesC. The Bayesian algorithms for GS were implemented using the R package BGLR version 1.0914. The BGLR default priors were used for all models, with 5 degrees of freedom (dfu), a scale parameter (S), and . The Bayesian analyses were performed considering Gibbs sampling chains of 200,000 iterations, with the first 20,000 iterations excluded as burn-in and a sampling interval of 5 cycles. Convergence was checked by visual inspection of trace plots and distribution plots of the residual variance. For Bayesian regression methods, the general model can be described as follows:

$${mathbf{y}}^{mathbf{*}}=upmu +sum_{{text{w}}=1}^{{text{p}}}{{text{x}}}_{{text{iw}}}{{text{u}}}_{{text{w}}}+{{text{e}}}_{{text{i}}}$$

where (upmu) is the model intercept; ({{text{x}}}_{{text{iw}}}) is the genotype of the ith animal at locus w (coded as 0, 1, and 2); ({{text{u}}}_{{text{w}}}) is the SNP marker effect (additive) of the w-th SNP (p=305,128); and ({{text{e}}}_{{text{i}}}) is the residual effect associated with the observation of ith animal, assumed to be normally distributed as (mathbf{e}sim {text{N}}(0,{mathbf{I}upsigma }_{{text{e}}}^{2})).

The BRR method14 assumes a Gaussian prior distribution for the SNP markers (({{text{u}}}_{{text{w}}})), with a common variance ({(upsigma }_{{text{u}}}^{2})) across markers so that ({text{p}}left({{text{u}}}_{1},dots ,{{text{u}}}_{{text{w}}}|{upsigma }_{{text{u}}}^{2}right)=prod_{{text{w}}=1}^{{text{p}}}{text{N}}({{text{u}}}_{{text{w}}}{|0,upsigma }_{{text{u}}}^{2})). The variance of SNP marker effects is assigned a scaled-inverse Chi-squared distribution [({text{p}})(({upsigma }_{{text{u}}}^{2})={upchi }^{-2}({upsigma }_{{text{u}}}^{2}|{{text{df}}}_{{text{u}}},{{text{S}}}_{{text{u}}}))], and the residual variance is also assigned a scaled-inverse Chi-squared distribution with degrees of freedom (dfe)and scale parameters (Se).

Bayesian Lasso (BL) regression31 used an idea from Tibshirani32 to connect the LASSO (least absolute shrinkage and selection operator) method with the Bayesian analysis. In the BL, the source of variation is split intoresidual term(({upsigma }_{{text{e}}}^{2}))and variation due to SNP markers (({upsigma }_{{{text{u}}}_{{text{w}}}}^{2})). The prior distribution for the additive effect of the SNP marker (left[{text{p}}left({{text{u}}}_{{text{w}}}|{uptau }_{{text{j}}}^{2},{upsigma }_{{text{e}}}^{2}right)right]) follows a Gaussian distribution with marker-specific prior variance given by ({text{p}}left({{text{u}}}_{{text{w}}}|{uptau }_{{text{j}}}^{2},{upsigma }_{{text{e}}}^{2}right)=prod_{{text{w}}=1}^{{text{p}}}{text{N}}({{text{u}}}_{{text{w}}}left|0,{uptau }_{{text{j}}}^{2}{upsigma }_{{text{e}}}^{2}right)). This prior distribution leads to marker-specific shrinkage of their effect, whose their extent depends on the variance parameters (left({uptau }_{{text{j}}}^{2}right)). The variance parameters (left({uptau }_{{text{j}}}^{2}right)) is assigned as exponential independent and identically distributed prior,({text{p}}left( {{uptau }_{{text{j}}}^{2} left| {uplambda } right.} right) = mathop prod limits_{{{text{j}} = 1}}^{{text{p}}} {text{Exp}}left( {{uptau }_{{text{j}}}^{2} left| {{uplambda }^{2} } right.} right)) and the square lambda regularization parameter (({uplambda }^{2})) follows a Gamma distribution (({text{p}}left({uplambda }^{2}right)={text{Gamma}}({text{r}},uptheta ))), where r and (uptheta) are the rate and shape parameters, respectively31. Thus, the marginal prior for SNP markers is given by a double exponential (DE) distribution as follows: ({text{p}}left( {{text{u}}_{{text{w}}} left| {uplambda } right.} right) = int {{text{N}}left( {{text{u}}_{{text{w}}} left| {0,{uptau }_{{text{j}}}^{2} ,{upsigma }_{{text{e}}}^{2} } right.} right){text{Exp}}left( {{uptau }_{{text{j}}}^{2} left| {{uplambda }^{2} } right.} right)}), where the DE distribution places a higher density at zero and thicker tails, inducing stronger shrinkage of estimates for markers with relatively small effect and less shrinkage for markers with substantial effect. The residual variance (({upsigma }_{{text{e}}}^{2})) is specified as a scaled inverse chi-squared prior density, with degrees of freedom dfe and scale parameter Se.

BayesA method14,33 considers Gaussian distribution with null mean as prior for SNP marker effects (({{text{u}}}_{{text{w}}})), and a SNP marker-specific variance (({upsigma }_{{text{w}}}^{2})). The variance associated with each marker effect assumes a scaled inverse chi-square prior distribution, ({text{p}}left({upsigma }_{{text{w}}}^{2}right)={upchi }^{-2}left({upsigma }_{{text{w}}}^{2}|{{text{df}}}_{{text{u}}},{{text{S}}}_{{text{u}}}^{2}right)), with degrees of freedom (({{text{df}}}_{{text{u}}})) and scale parameter (({{text{S}}}_{{text{u}}}^{2})) treated as known14. Thus, BayesA places a t-distribution for the markers effects, i.e., ({text{p}}left({{text{u}}}_{{text{w}}}|{{text{df}}}_{{text{u}}},{{text{S}}}^{2}right)={text{t}}left(0,{{text{df}}}_{{text{u}}},{{text{S}}}_{{text{u}}}^{2}right)), providing a thicker-tail distribution compared to the Gaussian, allowing a higher probability of moderate to large SNP effects.

BayesB assumes that a known proportion of SNP markers have a null effect (i.e., a point of mass at zero), and a subset of markers with a non-null effect that follow univariate t-distributions3,12, as follows:

$${text{p}}left({{text{u}}}_{{text{w}}}|{text{df}},uppi ,{{text{df}}}_{{text{u}}},{S}_{B}^{2}right)=left{begin{array}{cc}0& mathrm{with probability pi }\ {text{t}}left({{text{u}}}_{{text{w}}}|{{text{df}}}_{{text{u}}},{S}_{B}^{2}right)& mathrm{with probability }left(1-uppi right)end{array}right.$$

where (uppi) is the proportion of SNP markers with null effect, and (1-uppi) is the probability of SNP markers with non-null effect contributing to the variability of the FE-related trait3. Thus, the prior distribution assigned to SNP with non-null effects is a scaled inverse chi-square distribution.

BayesC method34 assumes a spikeslab prior for marker effects, which refers to a mixture distribution comprising a fixed amount with probability (uppi) of SNP markers have a null effect, whereas a probability of 1 of markers have effects sampled from a normal distribution. The prior distribution is as follows:

$${text{p}}left({{text{u}}}_{{text{w}}},{upsigma }_{{text{w}}}^{2},uppi right)=left{prod_{{text{j}}=1}^{{text{w}}}left[uppi left({{text{u}}}_{{text{w}}}=0right)+left(1-uppi right){text{N}}(0,{upsigma }_{{text{w}}}^{2})right]*{upchi }^{-2}left({upsigma }_{{text{w}}}^{2}|{{{text{df}}}_{{text{u}}},mathrm{ S}}_{{text{B}}}^{2}right)*upbeta (uppi |{{text{p}}}_{0},{uppi }_{0}right},$$

Where ({upsigma }_{{text{w}}}^{2}) is the common variance for marker effect, ({{text{df}}}_{{text{u}}}) and ({{text{S}}}_{{text{B}}}^{2}) are the degrees of freedom and scale parameter, respectively, ({{text{p}}}_{0}) and ({uppi }_{0})[0,1] are the prior shape parameters of the beta distribution.

Two machine learning (ML) algorithms were applied for genomic prediction: Multi-layer Neural Network (MLNN) and support vector regression (SVR). The ML approaches were used to alleviate the standard assumption adopted in the linear methods, which restrict to additive genetic effects of markers without considering more complex gene action modes. Thus, ML methods are expected to improve predictive accuracy for different target traits. To identify the best combination of hyperparameters (i.e., parameters that must be tuned to control the learning process to obtain a model with optimal performance) in the supervised ML algorithms (MLNN and SVR), we performed a random grid search by splitting the reference population from the forward scheme into five-folds35.

In MLNN, handling a large genomic dataset, such as 305,128 SNPs, is difficult due to the large number of parameters that need to be estimated, leading to a significant increase in computational demand36. Therefore, an SNP pre-selection strategy based on GWAS results in the training population using an MTGBLUP method (Fig.1A) was used to reduce the number of markers to be considered as input on the MLNN. In addition, this strategy can remove noise information in the genomic data set. In this study, the traits displayed major regions explaining a large percentage of genetic variance, which makes using pre-selected markers useful37.

(A) Manhattan plot for percentage of genetic variance explained by SNP-marker estimated through multi-trait GWAS in training population to be used as pre-selection strategies for multi-layer neural network. (B) General representation of neural networks with two hidden layers used to model nonlinear dependencies between trait and SNP marker information. The input layer ((X={x}_{i,p})) considered in the neural network refers to the SNP marker information (coded as 0, 1, and 2) of the ith animal. The selected node represents the initial weight ((W={w}_{p})), assigned as random values between -0.5 and 0.5, connecting each input node to the first hidden layer and in the second layer the ({w}_{up}) refers to the output weight from the first hidden layer, b represents the bias which helps to control the values in the activation function. The output ((widehat{y})) layer represents a weighted sum of the input features mapped in the second layer.

The MLNN model can be described as a two-step regression38. The MLNN approach consists of three different layer types: input layer, hidden layer, and output layer. The input layer receives the input data, i.e., SNP markers. The hidden layer contains mapping processing units, commonly called neurons, where each neuron in the hidden layer computes a non-linear function (activation) of the weighted sum of nodes on the previous layer. Finally, the output layer provides the outcomes of the MLNN. Our proposed MLNN architecture comprises two fully connected hidden layers schematically represented in Fig.1B. The input layer in MLNN considered SNP markers that explained more than 0.125% of the genetic variance for FE-related traits (Fig.1A;~15k for ADG and DMI, and~16k for FE and RFI). The input covariate (X={{x}_{p}}) contains pre-selected SNP markers (p) with a dimension Nxp (N individuals and p markers). The pre-selected SNP markers are combined with each k neuron (with k=1, , Nr) through the weight vector ((W)) in the hidden layer and then summed with a neuron-specific bias (({b}_{k})) for computing the linear score for the neuron k as:({Z}_{i}^{[1]}=f({{b}_{k}}^{[1]}+X{W}^{[1]})) (Fig.1B). Subsequently, this linear score transformed using an activation function (fleft(.right)) to map k neuron-specific scores and produce the first hidden layer output ((fleft({z}_{1,i}right))). In the second-hidden layer, each neuron k receives a net input coming from hidden layer 1 as: ({Z}_{i}^{[2]}={{b}_{k}}^{left[2right]}+{Z}_{i}^{[1]}{W}^{[2]}), where ({W}^{[2]}) represents the weight matrix of dimension k x k (knumber of neurons) connecting the ({Z}_{i}^{[1]}) into the second hidden layer, and ({{b}_{k}}^{left[2right]}) is a bias term in hidden layer 2. Then, the activation function is applied to map the kth hidden neuron unit in the second hidden layer and generate the output layer as ({V}_{2,i}=fleft({z}_{2,i}right)). In the MLNN, a hyperbolic tangent activation function (({text{tanh}}left({text{x}}right)={{text{e}}}^{{text{x}}}-{{text{e}}}^{-{text{x}}}/{{text{e}}}^{{text{x}}}+{{text{e}}}^{-{text{x}}})) was adopted in the first and second layers, providing greater flexibility in the MLNN39.

The prediction of the adjusted FE-related trait was obtained as follows38:

$${mathbf{y}}^{mathbf{*}}=mathbf{f}left(mathbf{b}+{mathbf{V}}_{2,mathbf{i}}{mathbf{W}}_{0}right)+mathbf{e}$$

where ({mathbf{y}}^{mathbf{*}}) represents the target adjusted feed efficiency-related trait for the ith animal; (k) the number of neurons considered in the model and assumed the same in the first and second layer; ({mathbf{W}}_{0}) represents the weight from the k neuron in layer 2, (mathbf{b}) is related to the bias parameter. The optimal weights used in MLNN were obtained by minimizing the mean square error of prediction in the training subset40.

The MLNN model was implemented using the R package h2o (https://github.com/h2oai/h2o-3), with the random grid search using the h2o.grid function (https://cran.r-project.org/web/packages/h2o) to determine the number of neurons to maximize the prediction accuracy. We used the training population split into fivefold to assess the best neural network architecture and then apply it in the disjoint validation set41,42. We considered a total of 1000 epochs36, numbers of neurons ranging from 50 to 2500 with intervals of 100, and applied a dropout ratio of 0.2 and regularization L1 and L2 parameters as 0.0015 and 0.0005, respectively. In this framework, the MLNN was performed using two hidden layers of neural networks with the number of neurons (k) of 750 for ADG, 1035 for DMI, 710 for FE, and 935 for RFI obtained during the training process.

Support vector regression (SVR) is a kernel-based supervised learning technique used for regression analysis43. In the context of GS, the SVR uses linear models to implement nonlinear regression by mapping the predictor variables (i.e., SNP marker) in the feature space using different kernel functions (linear, polynomial, or radial basis function) to predict the target information, e.g., adjusted phenotype the GS44. SVR can map linear or nonlinear relationships between phenotypes and SNP markers depending on the kernel function. The best kernel function mapping genotype to phenotype (linear, polynomial, and radial basis) was determined using the training subset split into fivefold. The radial basis function (RBF) was chosen as it outperformed the linear and polynomial (degree equal 2) kernels in the training process, increasing 8.25% in predictive ability and showing the lowest MSE.

The general model for SVR using a RBF function can be described as38,45: ({mathbf{y}}_{mathbf{i}}^{mathbf{*}}=mathbf{b}+mathbf{h}{left(mathbf{m}right)}^{mathbf{T}}mathbf{w}+mathbf{e}), where (mathbf{h}{left(mathbf{m}right)}^{mathbf{T}}) represents the kernel radial basis function used to transform the original predictor variables, i.e. SNP marker information (({text{m}})), (b) denotes the model bias, and (w) represents the unknown regression weight vector. In the SVR, the learn function (mathbf{h}{left(mathbf{m}right)}^{mathbf{T}}) was given by minimizing the loss function. The SVR was fitted using an epsilon-support vector regression that ignores residual absolute value ((left|{y}_{i}^{*}-{widehat{y}}_{i}^{*}right|)) smaller than some constant () and penalize larger residuals46.

The kernel RBF function considered in the SVR follows the form: (mathbf{h}{left(mathbf{m}right)}^{mathbf{T}}=mathbf{exp}left(-{varvec{upgamma}}{Vert {mathbf{m}}_{mathbf{i}}-{mathbf{m}}_{mathbf{j}}Vert }^{2}right)), where the ({varvec{upgamma}}) is a gamma parameter to quantity the shapes of the kernel functions, (m)and({m}_{i}) are the vectors of predictor variables for labels i and j. The main parameters in SVR are the cost parameter (({text{C}})), gamma parameter (({varvec{upgamma}})), and epsilon ((upepsilon)). The parameters ({text{C}}) and (upepsilon) were defined using the training data set information as proposed by Cherkasky and Ma47: ({text{C}}={text{max}}left(left|overline{{{text{y}} }^{*}}+3{upsigma }_{{{text{y}}}^{*}}right|,left|overline{{{text{y}} }^{*}}-3{upsigma }_{{{text{y}}}^{*}}right|right)) and (upepsilon =3{upsigma }_{{{text{y}}}^{*}}left(sqrt{{text{ln}}left({text{n}}right)/{text{n}}}right)), in which the (overline{{{text{y}} }^{*}}) and ({upsigma }_{{{text{y}}}^{*}}) are the mean and the standard deviation of the adjusted FE-related traits on the training population, and n represents the number of animals in the training set. The gamma () was determined through a random search of values varying from 0 to 5, using the training folder split into fivefold. The better-trained SVR model considered the parameter of 2.097 for ADG, 0.3847 for DMI, 0.225 for FE, and 1.075 for RFI. The SVR was implemented using the e1071 R package48.

Prediction accuracy (acc) of the different statistical approaches was assessed by Pearsons correlation between adjusted phenotypes (({{text{y}}}^{*})) and their predicted values (({widehat{{text{y}}}}_{{text{i}}}^{*})) on the validation set, and root mean squared error (RMSE). The prediction bias was assessed using the slope of the linear regression of ({widehat{y}}_{i}^{*}) on ({{text{y}}}^{*}), for each model. The Hotelling-Williams test49 was used to assess the significance level of the difference in the predictive ability of Bayesian methods (BayesA, BayesB, BayesC, BL, and BRR), MTGBLUP, and machine learning (MLNN and SVR) against STGBLUP. The similarity between the predictive performance of the different models was assessed using Wards hierarchical clustering method with an Euclidian distance analysis. The relative difference (RD) in the predictive ability was measured as ({text{RD}}=frac{({{text{r}}}_{{text{m}}}-{{text{r}}}_{{text{STGBLUP}}})}{{{text{r}}}_{{text{STGBLUP}}}}times 100), where ({{text{r}}}_{{text{m}}}) represents the acc of each alternative approach (SVR, MLNN, and MTGBLUP, or Bayesian regression modelsBayesA, BayesB, BayesC, BL, and BRR), and ({{text{r}}}_{{text{STGBLUP}}}) is the predictive ability obtained using the STGBLUP method.

The animal procedures and data sampling presented in this study were approved and performed following the Animal Care and Ethical Committee recommendations of the So Paulo State University (UNESP), School of Agricultural and Veterinary Science (protocol number 18.340/16).

Read this article:
Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in ... - Nature.com

Pycaret is an open source, low-code Machine Learning library based on Python. This solution automates the end-to-end machine learning workflow. By automating tasks and managing ML models, PyCaret speeds up the experimentation cycle. As a result, data scientists are much more productive and able to develop even more powerful machine learning models.

PyCaret is more than just a Python-based ML library. And for good reason, it encompasses several machine learning libraries and frameworks. For example: scikit-learn, XGBoost, LightGBM, CatBoost, spaCy, Optuna, Hyperopt, Ray, etc.

Best of all, its a ready-to-deploy Python library. In other words, every step of an ML experience can be reproduced from one environment to another.

Good to know: PyCaret also integrates with many other solutions, such as Microsoft Power BI, Tableau, Alteryx and KNIME. So you can add a layer of machine learning to all your business intelligence work. And its easy to do.

See the original post here:
PyCaret: Everything you need to know about this Python library - DataScientest

State Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia Washington Washington D.C. West Virginia Wisconsin Wyoming Puerto Rico US Virgin Islands Armed Forces Americas Armed Forces Pacific Armed Forces Europe Northern Mariana Islands Marshall Islands American Samoa Federated States of Micronesia Guam Palau Alberta, Canada British Columbia, Canada Manitoba, Canada New Brunswick, Canada Newfoundland, Canada Nova Scotia, Canada Northwest Territories, Canada Nunavut, Canada Ontario, Canada Prince Edward Island, Canada Quebec, Canada Saskatchewan, Canada Yukon Territory, Canada

Zip Code

Country United States of America US Virgin Islands United States Minor Outlying Islands Canada Mexico, United Mexican States Bahamas, Commonwealth of the Cuba, Republic of Dominican Republic Haiti, Republic of Jamaica Afghanistan Albania, People's Socialist Republic of Algeria, People's Democratic Republic of American Samoa Andorra, Principality of Angola, Republic of Anguilla Antarctica (the territory South of 60 deg S) Antigua and Barbuda Argentina, Argentine Republic Armenia Aruba Australia, Commonwealth of Austria, Republic of Azerbaijan, Republic of Bahrain, Kingdom of Bangladesh, People's Republic of Barbados Belarus Belgium, Kingdom of Belize Benin, People's Republic of Bermuda Bhutan, Kingdom of Bolivia, Republic of Bosnia and Herzegovina Botswana, Republic of Bouvet Island (Bouvetoya) Brazil, Federative Republic of British Indian Ocean Territory (Chagos Archipelago) British Virgin Islands Brunei Darussalam Bulgaria, People's Republic of Burkina Faso Burundi, Republic of Cambodia, Kingdom of Cameroon, United Republic of Cape Verde, Republic of Cayman Islands Central African Republic Chad, Republic of Chile, Republic of China, People's Republic of Christmas Island Cocos (Keeling) Islands Colombia, Republic of Comoros, Union of the Congo, Democratic Republic of Congo, People's Republic of Cook Islands Costa Rica, Republic of Cote D'Ivoire, Ivory Coast, Republic of the Cyprus, Republic of Czech Republic Denmark, Kingdom of Djibouti, Republic of Dominica, Commonwealth of Ecuador, Republic of Egypt, Arab Republic of El Salvador, Republic of Equatorial Guinea, Republic of Eritrea Estonia Ethiopia Faeroe Islands Falkland Islands (Malvinas) Fiji, Republic of the Fiji Islands Finland, Republic of France, French Republic French Guiana French Polynesia French Southern Territories Gabon, Gabonese Republic Gambia, Republic of the Georgia Germany Ghana, Republic of Gibraltar Greece, Hellenic Republic Greenland Grenada Guadaloupe Guam Guatemala, Republic of Guinea, Revolutionary People's Rep'c of Guinea-Bissau, Republic of Guyana, Republic of Heard and McDonald Islands Holy See (Vatican City State) Honduras, Republic of Hong Kong, Special Administrative Region of China Hrvatska (Croatia) Hungary, Hungarian People's Republic Iceland, Republic of India, Republic of Indonesia, Republic of Iran, Islamic Republic of Iraq, Republic of Ireland Israel, State of Italy, Italian Republic Japan Jordan, Hashemite Kingdom of Kazakhstan, Republic of Kenya, Republic of Kiribati, Republic of Korea, Democratic People's Republic of Korea, Republic of Kuwait, State of Kyrgyz Republic Lao People's Democratic Republic Latvia Lebanon, Lebanese Republic Lesotho, Kingdom of Liberia, Republic of Libyan Arab Jamahiriya Liechtenstein, Principality of Lithuania Luxembourg, Grand Duchy of Macao, Special Administrative Region of China Macedonia, the former Yugoslav Republic of Madagascar, Republic of Malawi, Republic of Malaysia Maldives, Republic of Mali, Republic of Malta, Republic of Marshall Islands Martinique Mauritania, Islamic Republic of Mauritius Mayotte Micronesia, Federated States of Moldova, Republic of Monaco, Principality of Mongolia, Mongolian People's Republic Montserrat Morocco, Kingdom of Mozambique, People's Republic of Myanmar Namibia Nauru, Republic of Nepal, Kingdom of Netherlands Antilles Netherlands, Kingdom of the New Caledonia New Zealand Nicaragua, Republic of Niger, Republic of the Nigeria, Federal Republic of Niue, Republic of Norfolk Island Northern Mariana Islands Norway, Kingdom of Oman, Sultanate of Pakistan, Islamic Republic of Palau Palestinian Territory, Occupied Panama, Republic of Papua New Guinea Paraguay, Republic of Peru, Republic of Philippines, Republic of the Pitcairn Island Poland, Polish People's Republic Portugal, Portuguese Republic Puerto Rico Qatar, State of Reunion Romania, Socialist Republic of Russian Federation Rwanda, Rwandese Republic Samoa, Independent State of San Marino, Republic of Sao Tome and Principe, Democratic Republic of Saudi Arabia, Kingdom of Senegal, Republic of Serbia and Montenegro Seychelles, Republic of Sierra Leone, Republic of Singapore, Republic of Slovakia (Slovak Republic) Slovenia Solomon Islands Somalia, Somali Republic South Africa, Republic of South Georgia and the South Sandwich Islands Spain, Spanish State Sri Lanka, Democratic Socialist Republic of St. Helena St. Kitts and Nevis St. Lucia St. Pierre and Miquelon St. Vincent and the Grenadines Sudan, Democratic Republic of the Suriname, Republic of Svalbard & Jan Mayen Islands Swaziland, Kingdom of Sweden, Kingdom of Switzerland, Swiss Confederation Syrian Arab Republic Taiwan, Province of China Tajikistan Tanzania, United Republic of Thailand, Kingdom of Timor-Leste, Democratic Republic of Togo, Togolese Republic Tokelau (Tokelau Islands) Tonga, Kingdom of Trinidad and Tobago, Republic of Tunisia, Republic of Turkey, Republic of Turkmenistan Turks and Caicos Islands Tuvalu Uganda, Republic of Ukraine United Arab Emirates United Kingdom of Great Britain & N. Ireland Uruguay, Eastern Republic of Uzbekistan Vanuatu Venezuela, Bolivarian Republic of Viet Nam, Socialist Republic of Wallis and Futuna Islands Western Sahara Yemen Zambia, Republic of Zimbabwe

Link:
VictoriaMetrics Machine Learning takes monitoring to the next level - The Bakersfield Californian

Increasingly-sophisticated AI tools are driving a renewed focus on dynamic creative optimisation, as marketers look to further leverage their datasets. To that end, in this contributed article, John Tigg, EVP, global client partnerships at Yieldmo, outlines the five key ingredients for effective use of machine learning in optimising creative formats, alongside notable challenges in the field.

Advertisers spend a lot of time and resources designing the perfect creative to capture the attention of their target audience. Frequently, however, they leave the very last and critically important step - where the creative and the user finally interact - to chance. This is the moment at which the creative format is determined, and its also the vital moment that determines whether an advertisers hard work and planning pays off as a good user experience.

The right creative format amplifies, without altering, the core underlying creative to produce a unique interactive experience. An intelligent creative format drives engagement with customers and improves a variety of key advertiser KPIs, including brand awareness and recall, attention, consideration, shoppability, site visits, and more.

For every opportunity that exists to serve a creative to a user, there are many possible creative format experiences. The final form of the creative format should not be the same in every scenario; it should be a product of the multitude of factors that converge at the moment the user and the creative meet.

The right creative format selection is everything when it comes to a successful user experience, but its also a challenge for advertisers: How does one choose the optimal format for their creative, given that millions of permutations of different intersecting factors define every ad opportunity?

Today, this last mile of optimisation is an interesting problem that machine learning (ML) is well-positioned to help solve. Lets examine why thats the case and what marketers need to know to ensure theyre building or selecting strong tools capable of elevating their creative performance.

Every ad opportunity represents a unique intersection of the advertiser, the context, and the user. Each of these components is defined by a collection of attributes, each of which can have hundreds, thousands, or millions of values. Why so many values? Consider:

The complexity of each ad opportunity positions machine learning (ML) as an ideal solution when it comes to creative format optimisation. Machine learning, a subset of AI, is an exciting field that allows us to make increasingly accurate multivariate predictions about what will happen using large volumes of historical data. It can find patterns in this data, make rapid and accurate decisions, and is effective at overcoming ambiguity and sparsity. Machine learning can uncover unexpected and unspecified truth conditions (features) and can make good predictions under novel circumstances.

These unexpected and unspecified features are especially powerful when comparing ML to the human-driven optimisation we often see in the ad tech industry. Machine learning provides a flexible toolbox for many types of problems, and the problem of choosing the optimal creative format for each ad opportunity is no exception.

To deliver the best format experience for your creative every time your ad serves, there are five critical ingredients that should be present within your dynamic creative optimisation tool, as derived from our whitepaper, "Elevating Creative Performance with Dynamic Format Optimization (DFO) and Artificial Intelligence (AI)".

This might sound obvious, but the first essential ingredient to strong creative format optimisation is ensuring the tool has access to a broad selection of formats that can independently improve advertiser outcomes at serve time.

For a ML model to predict the best format experience, you must have a mechanism to process, transform, and store large volumes of data. The data used to train the model must meet the following criteria:

To model successfully, a tool must start with a clear use case with a well understood and defined problem. In our case, thats determining the best creative format to serve in real time. To build a reliable, consistent, and explainable process for model selection, you must have a process to:

To ensure your models are up to date, you need a robust infrastructure that can automate pipelines and collect, prepare, and score training data. Among other features, this infrastructure should be able to assemble customised models for new campaigns, refresh models at least daily, update models based on recent performance, track versions and monitor models, and provide for a robust experimentation framework (i.e., a/b/c/d tests).

Finally, to deploy predictions into a real-time decisioning system, advertisers should build or look for tools that include the following features:

The right creative format can significantly impact the success of advertising campaigns. By applying machine learning (ML) to the creative format challenge, you can optimise the creative format for each ad opportunity automatically and improve user engagement with your brand by delivering the best creative experience at every unique moment in time, to each individual customer.

Whether you are looking to build your own ML capabilities or leverage an out-of-the-box solution, youll want to ensure your solution covers the above key ingredients. If youre looking to spin up something lighter weight but still capture a lot of value from format optimisation, there are some great options out there:

Most importantly, if you dont know who your exchange partners are, find out. If you dont know what value your exchanges are providing you, ask. If they cant prove their value, replace them with an exchange that is consistently building and innovating to help you succeed.

Finally, keep testing! When budgets get tight, make sure to fight for your testing budgets. No one knows what the next year will hold, but when the industry and economy changes (as it always does), you dont want to be stuck with solutions that have lost their edge.

Original post:
How Marketers Can Elevate Creative Performance with AI-Driven Format Optimisation - ExchangeWire