scholarly journals An MDP-Based Lifter Assignment Algorithm for Inter-Line Transportation in Semiconductor Fabrication

2021 ◽  
Author(s):  
Kyohong Shin ◽  
Hoon Jang ◽  
Hae Joong Kim
Keyword(s):  
Semiconductor Device ◽  
Operating Costs ◽  
Assignment Method ◽  
Current State ◽  
Assignment Algorithm ◽  
Proposed Model ◽  
Markov Decision ◽  
Tournament Selection ◽  
Semiconductor Fabrication ◽  
Resource Capacity

Abstract As semiconductor device geometries continue to shrink, the semiconductor manufacturing process becomes increasingly complex. This usually results in unbalanced utilization of machines and decreases overall productivity. One way to resolve such a problem is to share the resource capacity between different lines divided by floors. To this end, designing an efficient lifter assignment method to more efficiently manage transfer requests (TRs) of wafer lots to different floors is required. Motivated by this, our study addresses the assignment of lifters for delivering wafer lots to different floors. Unlike previous studies, which consider the current state of the system, our study considers both the current and possible future states of the system. We formulate an optimization model based on the Markov decision process. Then, we design an efficient method as a solution using both clustering and tournament selection methods. Experiments based on historical data confirm the effectiveness of the proposed algorithm in reducing travel times and delivery delays compared to the benchmark rules in practice. Sensitivity analysis demonstrates the robustness of the proposed model as the number of TRs increased. The proposed approach is expected to yield significant economic savings in both operating costs and labor.

scholarly journals BEHAVIORAL FUNCTIONS IMPLEMENTATION ON SPIKING NEURAL NETWORKS

2021 ◽  
Vol 20 (3) ◽  
pp. 591-622
Author(s):  
Anton Korsakov ◽  
Aleksandr Bakhshiev ◽  
Lyubov Astapova ◽  
Lev Stankevich
Keyword(s):  
Neural Networks ◽  
Conditioned Reflex ◽  
Negative Reinforcement ◽  
Input Pulse ◽  
Compartmental Models ◽  
Structural Adaptation ◽  
Spike Model ◽  
Current State ◽  
Proposed Model ◽  
Spiking Model

The question of behavioral functions modeling of animals (in particular, the modeling and implementation of the conditioned reflex) is considered. The analysis of the current state of neural networks with the possibility of structural reconfiguration is carried out. The modeling is carried out by means of neural networks, which are built on the basis of a compartmental spiking model of a neuron with the possibility of structural adaptation to the input pulse pattern. The compartmental spike model of a neuron is able to change its structure (the size of the cell body, the number and length of dendrites, the number of synapses) depending on the incoming pulse pattern at its inputs. A brief description of the compartmental spiking model of a neuron is given, and its main features are noted in terms of the possibility of its structural reconfiguration. The method of structural adaptation of the compartmental spiking model of the neuron to the input pulse pattern is described. To study the work of the proposed model of a neuron in a network, the choice of a conditioned reflex as a special case of the formation of associative connections is justified as an example. The structural scheme and algorithm of formation of a conditioned reflex with both positive and negative reinforcement are described. The article presents a step-by-step description of experiments on the associative connection’s formation in general and conditioned reflex (both with positive and negative reinforcement), in particular. The conclusion is made about the prospects of using spiking compartmental models of neurons to improve the efficiency of the implementation of behavioral functions in neuromorphic control systems. Further promising directions for the development of neuromorphic systems based on spiking compartmental models of the neuron are considered.

scholarly journals Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax

2019 ◽  
Author(s):  
Yinfei Yang ◽  
Gustavo Hernandez Abrego ◽  
Steve Yuan ◽  
Mandy Guo ◽  
Qinlan Shen ◽  
...  
Keyword(s):  
United Nations ◽  
State Of The Art ◽  
Cosine Similarity ◽  
Retrieval Task ◽  
Parallel Corpus ◽  
Similar Performance ◽  
Second Stage ◽  
Current State ◽  
Proposed Model ◽  
Document Level

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN) parallel corpus retrieval task. In all the languages tested, the system achieves P@1 of 86% or higher. We use pairs retrieved by our approach to train NMT models that achieve similar performance to models trained on gold pairs. We explore simple document-level embeddings constructed by averaging our sentence embeddings. On the UN document-level retrieval task, document embeddings achieve around 97% on P@1 for all experimented language pairs. Lastly, we evaluate the proposed model on the BUCC mining task. The learned embeddings with raw cosine similarity scores achieve competitive results compared to current state-of-the-art models, and with a second-stage scorer we achieve a new state-of-the-art level on this task.

scholarly journals Water Retention in Nature-Based Solutions—Assessment of Potential Economic Effects for Local Social Groups

Water ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3347
Author(s):  
Zwoździak Jerzy ◽  
Szałata Łukasz ◽  
Zwoździak Anna ◽  
Kwiecińska Kornelia ◽  
Byelyayev Maksym
Keyword(s):  
Climate Change ◽  
Water Retention ◽  
Economic Effect ◽  
Social Groups ◽  
Economic Effects ◽  
Operating Costs ◽  
Current State ◽  
The Impact

The upcoming trends related to climate change are increasing the level of interest of social groups in solutions for the implementation and the realization of activities that will ensure the change of these trends and can reduce the impact on the environment, including the health of the community exposed to these impacts. The implementation of solutions aimed at improving the quality of the environment requires taking into account not only the environmental aspects but also the economic aspect. Taking into account the analysis of solutions changing the current state of climate change, the article focuses on the analysis of the potential economic effect caused by the implementation of nature-based solutions (NBSs) in terms of reducing the operating costs related to water retention for local social groups. The analysis is based on a case study, one of the research projects studying nature-based solutions, created as part of the Grow Green project (H2020) in Wrocław in 2017–2022. The results of the analysis are an observed potential positive change in economic effects, i.e., approximately 85.90% of the operating costs related to water retention have been reduced for local social groups by NBSs.

scholarly journals Regularized Evolution for Image Classifier Architecture Search

2019 ◽  
Vol 33 ◽  
pp. 4780-4789 ◽  
Author(s):  
Esteban Real ◽  
Alok Aggarwal ◽  
Yanping Huang ◽  
Quoc V. Le
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Simple Method ◽  
Current State ◽  
Network Topologies ◽  
Comparable Accuracy ◽  
Tournament Selection ◽  
Complex Architecture ◽  
First Time

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier— AmoebaNet-A—that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-theart 83.9% top-1 / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.

scholarly journals Current State and Development Prospects of Autonomous Haulage at Surface Mines

2020 ◽  
Vol 174 ◽  
pp. 01028
Author(s):  
Yuri Voronov ◽  
Artyom Voronov ◽  
Daulet Makhambayev
Keyword(s):  
Human Factor ◽  
Surface Mining ◽  
Operating Costs ◽  
Existing Problems ◽  
Surface Mines ◽  
Current State ◽  
Constituent Elements ◽  
Further Development ◽  
Development Prospects

Autonomous (or unmanned) haulage systems have been used in surface mining for more than 10 years. Most of the equipment at such mines is remotely controlled by electronics, for which they are sometimes called “smart mines”. The elimination of the “human factor” from the pro- duction process should theoretically increase its safety and productivity, as well as reduce the operating costs of its implementation. However, despite the obvious advantages of this technology, it is not spreading as fast as ex- pected. This suggests that there are a number of problems that limit its de- velopment. In this paper, a review and analysis of the experience in the in- dustrial implementation of autonomous haulage in surface mining is car- ried out in order to identify existing problems and possible directions for their further development. The prerequisites, a brief history and some im- portant results of the introduction of autonomous haulage systems in sur- face mining, their main types and constituent elements are outlined, as well as the existing problems and expected directions of their development are highlighted.

Optimizing maintenance decisions in railway wheelsets: A Markov decision process approach

2018 ◽  
Vol 233 (2) ◽  
pp. 285-300 ◽  
Author(s):  
Joaquim AP Braga ◽  
António R Andrade
Keyword(s):  
Markov Decision Process ◽  
Decision Process ◽  
Transition Matrices ◽  
Technical Standards ◽  
Current State ◽  
Markov Transition ◽  
Markov Decision ◽  
Maintenance Decisions ◽  
Markov Transition Matrices

This article models the decision problem of maintaining railway wheelsets as a Markov decision process, with the aim to provide a way to support condition-based maintenance for railway wheelsets. A discussion on the role of the railway wheelsets is provided, as well as some background on the technical standards that guide maintenance decisions. A practical example is explored with the estimation of Markov transition matrices for different condition states that depend on the wheelset diameter, its mileage since last turning action (or renewal) and the damage occurrence. Bearing in mind all the possible maintenance actions, an optimal strategy is achieved, providing a map of best actions depending on the current state of the wheelset.

scholarly journals Image Restoration by a Mixed High-Order Total Variation and l1 Regularization Model

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Jianguang Zhu ◽  
Kai Li ◽  
Binbin Hao
Keyword(s):  
Total Variation ◽  
High Order ◽  
Variational Model ◽  
Total Variation Regularization ◽  
Current State ◽  
Model Combining ◽  
Alternating Direction ◽  
Proposed Model ◽  
Sharp Edges ◽  
Thresholding Algorithm

Total variation regularization is well-known for recovering sharp edges; however, it usually produces staircase artifacts. In this paper, in order to overcome the shortcoming of total variation regularization, we propose a new variational model combining high-order total variation regularization and l1 regularization. The new model has separable structure which enables us to solve the involved subproblems more efficiently. We propose a fast alternating method by employing the fast iterative shrinkage-thresholding algorithm (FISTA) and the alternating direction method of multipliers (ADMM). Compared with some current state-of-the-art methods, numerical experiments show that our proposed model can significantly improve the quality of restored images and obtain higher SNR and SSIM values.

scholarly journals Incoming Work-In-Progress Prediction in Semiconductor Fabrication Foundry Using Long Short-Term Memory

2019 ◽  
Vol 2019 ◽  
pp. 1-16
Author(s):  
Tze Chiang Tin ◽  
Kang Leng Chiew ◽  
Siew Chee Phang ◽  
San Nah Sze ◽  
Pei San Tan
Keyword(s):  
Preventive Maintenance ◽  
Short Term Memory ◽  
Operational Reliability ◽  
Statistical Forecasting ◽  
Work In Progress ◽  
Dependent Behavior ◽  
Proposed Model ◽  
Forecasting Method ◽  
Semiconductor Fabrication ◽  
Maintenance Activities

Preventive maintenance activities require a tool to be offline for long hour in order to perform the prescribed maintenance activities. Although preventive maintenance is crucial to ensure operational reliability and efficiency of the tool, long hour of preventive maintenance activities increases the cycle time of the semiconductor fabrication foundry (Fab). Therefore, this activity is usually performed when the incoming Work-in-Progress to the equipment is forecasted to be low. The current statistical forecasting approach has low accuracy because it lacks the ability to capture the time-dependent behavior of the Work-in-Progress. In this paper, we present a forecasting model that utilizes machine learning method to forecast the incoming Work-In-Progress. Specifically, our proposed model uses LSTM to forecast multistep ahead incoming Work-in-Progress prediction to an equipment group. The proposed model's prediction results were compared with the results of the current statistical forecasting method of the Fab. The experimental results demonstrated that the proposed model performed better than the statistical forecasting method in both hit rate and Pearson’s correlation coefficient, r.

scholarly journals A Dictionary Learning Method with Total Generalized Variation for MRI Reconstruction

2016 ◽  
Vol 2016 ◽  
pp. 1-13 ◽  
Author(s):  
Hongyang Lu ◽  
Jingbo Wei ◽  
Qiegen Liu ◽  
Yuhao Wang ◽  
Xiaohua Deng
Keyword(s):  
Dictionary Learning ◽  
Image Features ◽  
Sparse Regularization ◽  
Oil Painting ◽  
Total Generalized Variation ◽  
Splitting Technique ◽  
Current State ◽  
Alternating Direction ◽  
Proposed Model ◽  
Generalized Variation

Reconstructing images from their noisy and incomplete measurements is always a challenge especially for medical MR image with important details and features. This work proposes a novel dictionary learning model that integrates two sparse regularization methods: the total generalized variation (TGV) approach and adaptive dictionary learning (DL). In the proposed method, the TGV selectively regularizes different image regions at different levels to avoid oil painting artifacts largely. At the same time, the dictionary learning adaptively represents the image features sparsely and effectively recovers details of images. The proposed model is solved by variable splitting technique and the alternating direction method of multiplier. Extensive simulation experimental results demonstrate that the proposed method consistently recovers MR images efficiently and outperforms the current state-of-the-art approaches in terms of higher PSNR and lower HFEN values.

Sign in / Sign up

Export Citation Format

Share Document