Search

During early embryogenesis, the transcription factor SOX17 contributes to hepato-pancreato-biliary system formation and vascular-hematopoietic emergence. To better understand Sox17 function in the developing endoderm and endothelium, we developed a dual-color temporal lineage-tracing strategy in mice combined with single-cell RNA sequencing to analyze 6934 cells from Sox17-expressing lineages at embryonic days 9.0-9.5. Our analyses showed 19 distinct cellular clusters combined from all 3 germ layers. Differential gene expression, trajectory and RNA-velocity analyses of endothelial cells revealed a heterogenous population of uncommitted and specialized endothelial subtypes, including 2 hemogenic populations that arise from different origins. Similarly, analyses of posterior foregut endoderm revealed subsets of hepatic, pancreatic, and biliary progenitors with overlapping developmental potency. Calculated gene-regulatory networks predict gene regulons that are dominated by cell type-specific transcription factors unique to each lineage. Vastly different Sox17 regulons found in endoderm versus endothelial cells support the differential interactions of SOX17 with other regulatory factors thereby enabling lineage-specific regulatory actions.

Different infant diets have strong effects on child development and may engender variations in fecal microbiota and metabolites. The objective of this study was to evaluate the effect of an infant formula containing sn-2 palmitate on fecal microbiota and metabolites in healthy term infants. The study involved three groups as indicated below. Investigational: the group fed a formula containing high sn-2 palmitate for 16 weeks. Control: the group fed a formula using a regular vegetable oil for 16 weeks. Breastfed: the group fed breast milk for 16 weeks. Fecal samples were collected at 8 weeks (

Pre-ozonation of wastewater extended the number of ceramic membrane microfiltration cycles but low dose in situ ozonation dramatically improved the wastewater filtration runtime.

In this paper, we investigate the detection problem for a massive machine-type communication (mMTC) system that has correlated user activities. Two deep learning assisted algorithms are proposed to exploit the user activity correlation to facilitate channel estimation and user identification. Due to the dependency among user activities, conventional element-wise minimum mean square error (MMSE) denoiser used in the orthogonal approximate message passing (OAMP) algorithm cannot achieve satisfying performance during the two-step iterative process. Therefore, we propose a deep learning modified OAMP (DL-mOAMP) algorithm, which iteratively modifies the user activity ratio via exploiting the user activity correlation in the MMSE denoiser based on the estimated sequence during each OAMP iteration. Moreover, given a specific false alarm probability, a constant threshold employed in the conventional user identification is not optimal in the presence of user activity correlation. Thus, we propose a neural network framework that is dedicated to the user identification (DL-mOAMP-UI algorithm), which minimizes the missed detection probability under a pre-determined false alarm probability. Numerical results show that the proposed DL-mOAMP algorithm provides a substantial mean squared error performance gain compared to the conventional OAMP algorithm and the DL-mOAMP-UI algorithm can further improve the user identification accuracy of an mMTC system.

This paper proposes a node-classified redundant decoding (NC-RD) algorithm based on the received sequence’s channel reliability for high-density parity-check (HDPC) codes. Two preprocessing steps are proposed prior decoding. The variable nodes of the parity-check matrix are firstly classified by the $k$ -median algorithm based on the number of shortest cycles associated with each variable node before decoding. Then, by searching among the automorphism group of the HDPC codes, we generate a list of permutations for bit positions by computing and sorting the permutation reliability metrics. The redundant decoder conducts the message-passing decoding according to the sorted permutations, which limit the unreliable information propagation for each permutation. Besides proposing a list decoding algorithm on top of the NC-RD algorithm to augment the decoder’s performance, we show that the NC-RD algorithm can be transformed into a neural network system. More specifically, multiplicative tuneable weights are attached to the decoding messages to optimize the decoding performance. Simulation results of BCH codes over the AWGN channels show that the NC-RD algorithm provides a performance gain compared to the random redundant decoding algorithm. Additional decoding performance gain can be obtained by both the list decoding method and the neural network “learned” NC-RD algorithm.

Experimentation and Measurement (E&M) capabilities allow organizations to accurately assess the impact of new propositions and to experiment with many variants of existing products. However, until now, the question of measuring the measurer, or valuing the contribution of an E&M capability to organizational success has not been addressed. We tackle this problem by analyzing how, by decreasing estimation uncertainty, E&M platforms allow for better prioritization. We quantify this benefit in terms of expected relative improvement in the performance of all new propositions and provide guidance for how much an E&M capability is worth and when organizations should invest in one.

Digital technology organizations routinely use online experiments (e.g. A/B tests) to guide their product and business decisions. In e-commerce, we often measure changes to transaction- or item-based business metrics such as Average Basket Value (ABV), Average Basket Size (ABS), and Average Selling Price (ASP); yet it remains a common pitfall to ignore the dependency between the value/size of transactions/items during experiment design and analysis. We present empirical evidence on such dependency, its impact on measurement uncertainty, and practical implications on A/B test outcomes if left unmitigated. By making the evidence available, we hope to drive awareness of the pitfall among experimenters in e-commerce and hence encourage the adoption of established mitigation approaches. We also share lessons learned when incorporating selected mitigation approaches into our experimentation analysis platform currently in production., Comment: To appear in WWW '23 Companion. 5 pages, 4 figures, 2 tables. The experiment code and results on the two publicly available datasets are available on GitHub/Zenodo: https://doi.org/10.5281/zenodo.7659092. This version supersedes a previous working paper with a different title

A deep learning assisted sum-product detection algorithm (DL-SPDA) for faster-than-Nyquist (FTN) signaling is proposed in this paper. The proposed detection algorithm works on a modified factor graph which concatenates a neural network function node to the variable nodes of the conventional FTN factor graph to approach the maximum a posterior probabilities (MAP) error performance. In specific, the neural network performs as a function node in the modified factor graph to deal with the residual intersymbol interference (ISI) that is not considered by the conventional detector with a limited complexity. We modify the updating rule in the conventional sum-product algorithm so that the neural network assisted detector can be complemented to a turbo equalization receiver. Furthermore, we propose a compatible training technique to improve the detection performance of the proposed DL-SPDA with turbo equalization. In particular, the neural network is optimized in terms of the mutual information between the transmitted sequence and the extrinsic information. We also investigate the maximum-likelihood bit error rate (BER) performance of a finite length coded FTN system. Simulation results show that the error performance of the proposed algorithm approaches the MAP performance, which is consistent with the analytical BER.

Experimentation and Measurement (E&M) capabilities allow organizations to accurately assess the impact of new propositions and to experiment with many variants of existing products. However, until now, the question of measuring the measurer, or valuing the contribution of an E&M capability to organizational success has not been addressed. We tackle this problem by analyzing how, by decreasing estimation uncertainty, E&M platforms allow for better prioritization. We quantify this benefit in terms of expected relative improvement in the performance of all new propositions and provide guidance for how much an E&M capability is worth and when organizations should invest in one.

A deep learning assisted sum-product detection algorithm (DL-SPA) for faster-than-Nyquist (FTN) signaling is proposed in this paper. The proposed detection algorithm concatenates a neural network to the variable nodes of the conventional factor graph of the FTN system to help the detector converge to the a posterior probabilities based on the received sequence. More specifically, the neural network performs as a function node in the modified factor graph to deal with the residual intersymbol interference (ISI) that is not modeled by the conventional detector with a limited number of ISI taps. We modify the updating rule in the conventional sum-product algorithm so that the neural network assisted detector can be complemented to a Turbo equalization. Furthermore, a simplified convolutional neural network is employed as the neural network function node to enhance the detector's performance and the neural network needs a small number of batches to be trained. Simulation results have shown that the proposed DL-SPA achieves a performance gain up to 2.5 dB with the same bit error rate compared to the conventional sum-product detection algorithm under the same ISI responses., 5 pages, 7 figures, accepted by IEEE ITW 2019

The size of a website’s active user base directly affects its value. Thus, it is important to monitor and influence a user’s likelihood to return to a site. Essential to this is predicting when a user will return. Current state of the art approaches to solve this problem come in two flavors: (1) Recurrent Neural Network (RNN) based solutions and (2) survival analysis methods. We observe that both techniques are severely limited when applied to this problem. Survival models can only incorporate aggregate representations of users instead of automatically learning a representation directly from a raw time series of user actions. RNNs can automatically learn features, but can not be directly trained with examples of non-returning users who have no target value for their return time. We develop a novel RNN survival model that removes the limitations of the state of the art methods. We demonstrate that this model can successfully be applied to return time prediction on a large e-commerce dataset with a superior ability to discriminate between returning and non-returning users than either method applied in isolation. Code related to this paper is available at: https://github.com/grobgl/rnnsm.

This paper proposes a new iterative soft-decision decoding algorithm which combines list decoding and adaptive belief propagation (ABP) algorithm for short Reed-Solomon (RS) codes. The proposed algorithm generates a list of codewords by restarting the decoder with log-likelihood ratio saturations to the dynamically selected suspicious bits based on an up-to-date best decoded codeword. The suspicious bits are selected according to a joint evaluation of the decoded codeword and the initial channel information. The damping coefficient used in the ABP decoder is set to be proportional to the channel noise variance to achieve a proper convergence speed for the decoder at different SNRs. The performance of the proposed algorithm for short RS codes is investigated. It shows that the proposed algorithm brings a considerable coding gain for short RS codes over additive white Gaussian noise channels.

We describe the Customer LifeTime Value (CLTV) prediction system deployed at ASOS.com, a global online fashion retailer. CLTV prediction is an important problem in e-commerce where an accurate estimate of future value allows retailers to effectively allocate marketing spend, identify and nurture high value customers and mitigate exposure to losses. The system at ASOS provides daily estimates of the future value of every customer and is one of the cornerstones of the personalised shopping experience. The state of the art in this domain uses large numbers of handcrafted features and ensemble regressors to forecast value, predict churn and evaluate customer loyalty. Recently, domains including language, vision and speech have shown dramatic advances by replacing handcrafted features with features that are learned automatically from data. We detail the system deployed at ASOS and show that learning feature representations is a promising extension to the state of the art in CLTV modelling. We propose a novel way to generate embeddings of customers, which addresses the issue of the ever changing product catalogue and obtain a significant improvement over an exhaustive set of handcrafted features., Comment: 10 pages, 11 figures

OBJECTIVE: Children are vulnerable to diet inadequacies, which may affect immune function. Our objective was to determine if a follow-up formula (FUF) containing DHA, the prebiotics PDX and GOS, and yeast β-glucan affects incidence of respiratory infections and diarrheal disease in healthy children. METHODS: In a double-blind, randomized, controlled, prospective trial, 3-4 year old children were fed 3 servings per day of either a FUF with 25 mg DHA, 1.2 g PDX/GOS, and 8.7 mg yeast β-glucan per serving or an unfortified, cow’s milk-based beverage (control) for 28 weeks. Fecal and blood samples were collected to assess immune markers and iron/zinc status. Incidence of acute respiratory infections (ARI), diarrheal disease, and antibiotic treatment were obtained from medical records. RESULTS: The FUF group had fewer episodes and shorter duration of ARI (mean days [SE]; control = 4.3 [0.2]; FUF = 3.5 [0.2]; P = .007), less antibiotic use (n [%]; control = 21 [14%]; FUF = 8 [5%]; P = .01), and fewer missed days of day care due to illness. No diarrheal disease was diagnosed in either group. The FUF group had higher interleukin-10 and white blood cell count at the end of the study. There were no differences in hemoglobin, serum ferritin and zinc, or fecal secretory immunoglobulin A. CONCLUSIONS: Daily consumption of a FUF was associated with fewer episodes and shorter duration of ARI, as well as less antibiotic use. The children who consumed the FUF had increased interleukin-10 and white blood cells, suggesting an antiinflammatory mechanism and/or an increase of effector immune cells.