1,721,011 research outputs found
A Q-Learning-based method applied to stochastic resource constrained project scheduling with new project arrivals
No full textIn many resource-constrained project scheduling problems (RCPSP), the set of candidate projects is not fixed a priori but evolves with time. For example, while performing an initial set of projects according to a certain decision policy, a new promising project can emerge. To make an appropriate resource allocation decision for such a problem, project cancellation and resource idling decisions should complement the conventional scheduling decisions. In this study, the problem of stochastic RCPSP (sRCPSP) with dynamic project arrivals is addressed with the added flexibility of project cancellation and resource idling. To solve the problem, a Q-Learning-based approach is adopted. To use the approach, the problem is formulated as a Markov Decision Process with appropriate definitions of states, including information state and action variables. The Q-Learning approach enables us to derive an empirical state transition rules from simulation data so that analytical calculations of potentially exorbitantly complicated state transition rules can be circumvented. To maximize the advantage of using the empirically learned state transition rules, special type of actions including project cancellation and resource idling, which are difficult to incorporate into heuristics, were randomly added in the simulation. The random actions are filtered during the Q-Value iteration and properly utilized in the online decision making to maximize the total expected reward. Copyright (C) 2007 John Wiley & Sons, Ltd
Machine learning: Overview of the recent progresses and implications for the process systems engineering field
No full textMachine learning (ML) has recently gained in popularity, spurred by well-publicized advances like deep learning and widespread commercial interest in big data analytics. Despite the enthusiasm, some renowned experts of the field have expressed skepticism, which is justifiable given the disappointment with the previous wave of neural networks and other AI techniques. On the other hand, new fundamental advances like the ability to train neural networks with a large number of layers for hierarchical feature learning may present significant new technological and commercial opportunities. This paper critically examines the main advances in deep learning. In addition, connections with another ML branch of reinforcement learning are elucidated and its role in control and decision problems is discussed. Implications of these advances for the fields of process and energy systems engineering are also discussed. (C) 2017 Elsevier Ltd. All rights reserved.
Identifying the interacting positions of a protein using Boolean learning and support vector machines
No full textIt is known that in the three-dimensional structure of a protein, certain amino acids can interact with each other in order to provide structural integrity or aid in its catalytic function. If these positions are mutated the loss of this interaction usually leads to a non-functional protein. Directed evolution experiments, which probe the sequence space of a protein through mutations in search for an improved variant, frequently result in such inactive sequences. In this work, we address the use of machine learning algorithms, Boolean learning and support vector machines (SVMs), to find such pairs of amino acid positions. The recombination method of imparting mutations was simulated to create in silico sequences that were used as training data for the algorithms. The two algorithms were combined together to develop an approach that weighs the structural risk as well as the empirical risk to solve the problem. This strategy was adapted to a multi-round framework of experiments where the data generated in the present round is used to design experiments for the next round to improve the generated library, as well as the estimation of the interacting positions. It is observed that this strategy can greatly improve the number of functional variants that are generated as well as the average number of mutations that can be made in the library. (c) 2006 Published by Elsevier Ltd
Proactive Scheduling Strategy Applied to Decoking Operations of an Industrial Naphtha Cracking Furnace System
No full textThe scheduling of decoking operations in a naphtha cracking furnace system is an important issue to ethylene producers, because excessive coke deposits inside the furnace coils can negatively impact plant safety and productivity. For optimal scheduling, accurate online estimation of the thickness of the deposited coke is essential. In practice, the coke thickness can be estimated from various furnace operating Variables, but measurement errors and unexpected changes in the coke growth rate cause significant uncertainties in the estimation. Errors in the coke thickness estimate manifest themselves as gaps between the model prediction and actual measured values of key operating variables such as the pressure drop and the tube temperature. To handle the potential conflicts in an established schedule caused by the uncertainties, we propose to use a "proactive" scheduling strategy. In "reactive" scheduling, rescheduling is performed whenever an unexpected operational problem causes an unscheduled decoking operation, thus making a standing schedule no longer viable. On the other hand, in the "proactive" scheduling strategy, model information, as well as measurement information, are used to determine appropriate rescheduling points before actual operational problems arise. Under the proposed proactive scheduling strategy, the model predictions of the pressure drop and the tube temperature are compared against their measurements while the plant is operating according to a current decoking schedule. Whenever the gap between the model prediction and the measurement is larger than a given threshold value, the model is updated based on the measurements and the scheduling problem is solved again with the updated model information. The new scheduling solution is applied to the operation until the next scheduling point is found. This proactive scheduling procedure is applied to a simulated system of multiple furnaces. The advantages of the proactive scheduling strategy, in terms of productivity and risk management, are shown by comparing it with a reactive scheduling strategy and a heuristic decoking strategy over a large number of scenarios.
Carbon - Right out of Thin Air
No full textMatthew Realff, from the Georgia Tech School of Chemical & Biomolecular Engineering joins us to discuss our environmental carbon problem and some unique solutions, such as carbon removal from air
Pooling for improved screening of combinatorial libraries for directed evolution
No full textFollowing diversity generation in combinatorial protein engineering, a significant amount of effort is expended in screening the library for improved variants. Pooling, or combining multiple cells into the same assay well when screening, is a means to increase throughput and screen a larger portion of the library with less time and effort. We have developed and validated a Monte Carlo simulation model of pooling and used it to screen a library of beta-galactosidase mutants randomized in the active site to increase their activity toward fucosides. Here, we show that our model can successfully predict the number of highly improved mutants obtained via pooling and that pooling does increase the number of good mutants obtained. In unpooled conditions, we found a total of three mutants with higher activity toward p-nitrophenyl-beta-D-fucoside than that of the wild-type beta-galactosidase, whereas when pooling 10 cells per well we found a total of approximately 10 improved mutants. In addition, the number of "supermutants", those with the highest activity increase, was also higher when pooling was used. Pooling is a useful tool for increasing the efficiency of screening combinatorial protein engineering libraries
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
