A branch and bound method in a permutation flow shop with blocking and setup times

In this paper it is presented an improvement of the branch and bound algorithm for the permutation flow shop problem with blocking-in-process and setup times with the objective of minimizing the total flow time and tardiness, which is known to be NP-Hard when there are two or more machines involved. With that objective in mind, a new machine-based lower bound that exploits some structural properties of the problem. A database with 27 classes of problems, varying in number of jobs (n) and number of machines (m) was used to perform the computational experiments. Results show that the algorithm can deal with most of the problems with less than 20 jobs in less than one hour. Thus, the method proposed in this work can solve the scheduling of many applications in manufacturing environments with limited buffers and separated setup times.

Intrinsic instability of the dysbiotic microbiome revealed through dynamical systems inference at scale

Despite the importance of microbial dysbiosis in human disease, the phenomenon remains poorly understood. We provide the first comprehensive and predictive model of dysbiosis at ecosystem-scale, leveraging our new machine learning method for efficiently inferring compact and interpretable dynamical systems models. Coupling this approach with the most densely temporally sampled interventional study of the microbiome to date, using microbiota from healthy and dysbiotic human donors that we transplanted into mice subjected to antibiotic and dietary interventions, we demonstrate superior predictive performance of our method over state-of-the-art techniques. Moreover, we demonstrate that our approach uncovers intrinsic dynamical properties of dysbiosis driven by destabilizing competitive cycles, in contrast to stabilizing interaction chains in the healthy microbiome, which have implications for restoration of the microbiome to treat disease.

Estimation of Photometric Redshifts. I. Machine-learning Inference for Pan-STARRS1 Galaxies Using Neural Networks

We present a new machine-learning model for estimating photometric redshifts with improved accuracy for galaxies in Pan-STARRS1 data release 1. Depending on the estimation range of redshifts, this model based on neural networks can handle the difficulty for inferring photometric redshifts. Moreover, to reduce bias induced by the new model's ability to deal with estimation difficulty, it exploits the power of ensemble learning. We extensively examine the mapping between input features and target redshift spaces to which the model is validly applicable to discover the strength and weaknesses of the trained model. Because our trained model is well calibrated, our model produces reliable confidence information about objects with non-catastrophic estimation. While our model is highly accurate for most test examples residing in the input space, where training samples are densely populated, its accuracy quickly diminishes for sparse samples and unobserved objects (i.e., unseen samples) in training. We report that out-of-distribution (OOD) samples for our model contain both physically OOD objects (i.e., stars and quasars) and galaxies with observed properties not represented by training data. The code for our model is available at https://github.com/GooLee0123/MBRNN for other uses of the model and retraining the model with different data.

LFO2: An Enhanced Version of Learning-From-OPT Caching Algorithm

Recent machine learning-based caching algorithm have shown promise. Among them, Learning-FromOPT (LFO) is the state-of-the-art supervised learning caching algorithm. LFO has a parameter named Window Size, which defines how often the algorithm generates a new machine-learning model. While using a small window size allows the algorithm to be more adaptive to changes in request behaviors, experimenting with LFO revealed that the performance of LFO suffers dramatically with small window sizes. This paper proposes LFO2, an improved LFO algorithm, which achieves high object hit ratios (OHR) with small window sizes. This results show a 9% OHR increase with LFO2. As the next step, the machine-learning parameters will be investigated for tuning opportunities to further enhance performance.

Machine Learning for Health: Algorithm Auditing & Quality Control

Developers proposing new machine learning for health (ML4H) tools often pledge to match or even surpass the performance of existing tools, yet the reality is usually more complicated. Reliable deployment of ML4H to the real world is challenging as examples from diabetic retinopathy or Covid-19 screening show. We envision an integrated framework of algorithm auditing and quality control that provides a path towards the effective and reliable application of ML systems in healthcare. In this editorial, we give a summary of ongoing work towards that vision and announce a call for participation to the special issue Machine Learning for Health: Algorithm Auditing & Quality Control in this journal to advance the practice of ML4H auditing.