Massive Search Space Research Articles

SmartFixture: Physics-guided reinforcement learning for automatic fixture layout design in manufacturing systems

Fixture layout design critically impacts the shape deformation of large-scale sheet parts and the quality of the final product in the assembly process. The existing works focus on developing Mathematical-Optimization (MO)-based methods to generate the optimal fixture layout via interacting with Finite Element Analysis (FEA)-based simulations or its surrogate models. Their limitations can be summarized as memorylessness and lack of scalability. Memorylessness indicates that the experience in designing the fixture layout for one part is usually not transferable to others. Scalability becomes an issue for MO-based methods when the design space of fixtures is large. Furthermore, the surrogate models might have limited representation capacity when modeling high-fidelity simulations. To address these limitations, we propose a learning-based framework, SmartFixture, to design the fixture layout by training a Reinforcement learning agent through direct interaction with the FEA-based simulations. The advantages of the proposed framework include: (i) it is generalizable to design fixture layouts for unseen scenarios after offline training; (ii) it is capable of finding the optimal fixture layout over a massive search space. Experiments demonstrate that the proposed framework consistently generates the best fixture layouts that receive the smallest shape deformations on the sheet parts with different initial shape variations.

Evolutionary algorithms simulating molecular evolution: a new field proposal.

The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins-the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared with the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein "vocabulary." A major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago or have never evolved (yet). By merging evolutionary algorithms, machine learning, and bioinformatics, we can develop highly customized "designer proteins." We dub the new subfield of computational evolution, which employs evolutionary algorithms with DNA string representations, biologically accurate molecular evolution, and bioinformatics-informed fitness functions, Evolutionary Algorithms Simulating Molecular Evolution.

Biomarker discovery with quantum neural networks: a case-study in CTLA4-activation pathways

BackgroundBiomarker discovery is a challenging task due to the massive search space. Quantum computing and quantum Artificial Intelligence (quantum AI) can be used to address the computational problem of biomarker discovery from genetic data.MethodWe propose a Quantum Neural Networks architecture to discover genetic biomarkers for input activation pathways. The Maximum Relevance-Minimum Redundancy criteria score biomarker candidate sets. Our proposed model is economical since the neural solution can be delivered on constrained hardware.ResultsWe demonstrate the proof of concept on four activation pathways associated with CTLA4, including (1) CTLA4-activation stand-alone, (2) CTLA4-CD8A-CD8B co-activation, (3) CTLA4-CD2 co-activation, and (4) CTLA4-CD2-CD48-CD53-CD58-CD84 co-activation.ConclusionThe model indicates new genetic biomarkers associated with the mutational activation of CLTA4-associated pathways, including 20 genes: CLIC4, CPE, ETS2, FAM107A, GPR116, HYOU1, LCN2, MACF1, MT1G, NAPA, NDUFS5, PAK1, PFN1, PGAP3, PPM1G, PSMD8, RNF213, SLC25A3, UBA1, and WLS. We open source the implementation at: https://github.com/namnguyen0510/Biomarker-Discovery-with-Quantum-Neural-Networks.

Graph Transformer with Convolution Parallel Networks for Predicting Single and Binary Component Adsorption Performance of Metal-Organic Frameworks.

Metal-organic frameworks (MOFs) are considered one of the most important materials for carbon capture and storage (CCS) due to the advantages of porosity, multifunction, diverse structure, and controllable chemical composition. With the continuous development of artificial intelligence (AI) technology, more and more machine learning models are used to identify MOFs with high performance within a massive search space. However, current works have yet to form a model that uses graph-structured data only, which can predict the adsorption properties of single and binary components. In this work, we proposed and developed a graph transformer, combined with convolution parallel networks, called GC-Trans. The model can accurately and efficiently predict the adsorption performance of MOFs under the single- and binary-component adsorption conditions using only the features of the crystal diagram as inputs. By extracting and fusing local and global feature information, the model has stronger expression and generalization abilities. Thus, we used it to screen the ARC-MOF database and analyze the MOF structures that meet the target requirements. Additionally, to demonstrate the transferability of the model, we applied transfer learning methods to predict the CO2/CH4 separations and CH4 uptake, both of which showed good predictive performance.

Optimization of design variables and control rules in field development under uncertainty: A case of intelligent wells and CO2 water alternating gas injection

This paper focuses on life-cycle optimization of oil field development plan under uncertainty. The optimization problem included a wide range of design variables and control rules related to wells and platform in a realistic benchmark case (UNISIM–II–D) with a known ground truth reservoir model, UNISIM–II–R, that resembles Brazilian pre-salt fractured carbonate reservoirs in their early development stage. The design variables were the number and location of wells, the fluid processing capacity of the platform, and the location of internal control valves (ICVs), whereas the control rules were the setting of ICVs, production and injection rates, and the duration of the water-alternating-gas (WAG-CO2) cycle. An iterative sequential optimization framework was developed to deal with the massive search space and complex parameterization. The optimization further took into consideration the subsurface, operational and economic uncertainties, and used iterative discrete Latin hypercube method as the search algorithm. The robust optimization was carried out on a subset of representative models derived from the reduction of a large ensemble of data-assimilated models. As a low-fidelity representation of the compositional fluid model, a black-oil model was used to reduce simulation runtime. To validate our optimization framework, we applied the optimal development strategy to the ensemble of compositional simulation models, as well as the ground truth model. The true model's responses were within the ranges predicted by the compositional ensemble, confirming the optimization framework's reliability. The general methodology developed in this study, as well as our findings, can be used to optimize other similar real-world complex and high-risk field development projects, and are especially useful in closed-loop field development and management practices.

Deep generative models for peptide design.

Computers can already be programmed for superhuman pattern recognition of images and text. For machines to discover novel molecules, they must first be trained to sort through the many characteristics of molecules and determine which properties should be retained, suppressed, or enhanced to optimize functions of interest. Machines need to be able to understand, read, write, and eventually create new molecules. Today, this creative process relies on deep generative models, which have gained popularity since powerful deep neural networks were introduced to generative model frameworks. In recent years, they have demonstrated excellent ability to model complex distribution of real-word data (e.g., images, audio, text, molecules, and biological sequences). Deep generative models can generate data beyond those provided in training samples, thus yielding an efficient and rapid tool for exploring the massive search space of high-dimensional data such as DNA/protein sequences and facilitating the design of biomolecules with desired functions. Here, we review the emerging field of deep generative models applied to peptide science. In particular, we discuss several popular deep generative model frameworks as well as their applications to generate peptides with various kinds of properties (e.g., antimicrobial, anticancer, cell penetration, etc). We conclude our review with a discussion of current limitations and future perspectives in this emerging field.

A Bounded Exhaustive Search Technique for Optimal Phasor Measurement Unit Placement in Power Grids

This paper proposes a technique to determine the possible optimal placement of the phasor measurement unit (PMU) in power grids for normal operating conditions. All possible combinations of PMU placement, including infeasible combinations, are typically considered in finding the optimal solution, which could be a massive search space. An integer search algorithm called the bounded search technique is introduced to reduce the search space in solving a minimum number of PMU allocations whilst maintaining full system observability. The proposed technique is based on connectivity and symmetry constraints that can be derived from the observability matrix. As the technique is coupled with the exhaustive technique, the technique is called the bounded exhaustive search (BES) technique. Several IEEE test systems, namely, IEEE 9-bus, IEEE 14-bus, IEEE 24-bus and IEEE 30-bus, are considered to showcase the performance of the proposed technique. An initial Monte Carlo simulation was carried out to evaluate the capability of the bounded search technique in providing a smaller feasible search space. The effectiveness of the BES technique in terms of computational time is compared with the existing exhaustive technique. Results demonstrate that the search space can be reduced tremendously, and the computational burden can be eased, when finding the optimal PMU placement in power grids.

Guiding Monte Carlo Tree Search by Scripts in Real-Time Strategy Games

In Real-Time Strategy (RTS) games, the action space grows combinatorially with respect to the number of units. With limited computing budget between actions, methods like Monte Carlo Tree Search (MCTS) tend to get lost in the massive search space. An interesting line of existing work is to incorporate human knowledge in the form of scripts. In this paper, we investigate different possibilities for incorporating scripts into the tree policy while still maintaining the convergence guarantees of MCTS. We also report experiments on incorporating the scripts into the playout policy, which showed that unbiased bots perform better than biased bots.

An innovative four-layer heuristic for scheduling multi-mode projects under multiple resource constrains

In this paper, an innovative four-layer heuristic is presented for scheduling multi-mode projects under multiple resource constraints. For this purpose, a biased-random sampling technique, a local search, a decomposition method, and an evolutionary search mechanism, each in a separate layer, are combined, with each layer passing its output to the next layer for improvement. The procedure has been designed based on the fact that what makes the scheduling of multi-mode projects hard to solve is a massive search space of modes compounded with the starting times of activities. That is why the procedure is aimed at balancing explorationversusexploitation in searching a massive search space. On the one hand, it exploits promising areas further and, on the other hand, it searches unexplored areas for expanding its range. Since the first layer provides an initial solution, and each of the other three layers can either improve the result of its previous layer or keep it unchanged, solutions never deteriorate and hence promising areas are exploited. Moreover, unexplored areas are searched effectively because each layer explores solution space differently than its previous layer. Based on whether or not an improvement each layer can make to the result of its previous layer, the effect of the corresponding layer on the performance of the procedure has been measured.

Toward continuous pattern detection over evolving large graph with snapshot isolation

This paper studies continuous pattern detection over large evolving graphs, which plays an important role in monitoring-related applications. The problem is challenging due to the large size and dynamic updates of graphs, the massive search space of pattern detection and inconsistent query results on dynamic graphs. This paper first introduces a snapshot isolation requirement, which ensures that the query results come from a consistent graph snapshot instead of a mixture of partial evolving graphs. Second, we propose an SSD (single sink directed acyclic graph) plan friendly to vertex-centric-distributed graph processing frameworks. SSD plan can guide the message transformation and transfer among graph vertices, and determine the satisfaction of the pattern on graph vertices for the sink vertex. Third, we devise strategies for major steps in the SSD evaluation, including the location of valid messages to achieve snapshot isolation, AO-List to determine the satisfaction of transition rule over dynamic graph, and message-on-change policy to reduce outgoing messages. The experiments on billion-edge graphs using Giraph, an open source implementation of Pregel, illustrate the efficiency and effectiveness of our method.

Probabilistic Biological Network Alignment

Interactions between molecules are probabilistic events. An interaction may or may not happen with some probability, depending on a variety of factors such as the size, abundance, or proximity of the interacting molecules. In this paper, we consider the problem of aligning two biological networks. Unlike existing methods, we allow one of the two networks to contain probabilistic interactions. Allowing interaction probabilities makes the alignment more biologically relevant at the expense of explosive growth in the number of alternative topologies that may arise from different subsets of interactions that take place. We develop a novel method that efficiently and precisely characterizes this massive search space. We represent the topological similarity between pairs of aligned molecules (i.e., proteins) with the help of random variables and compute their expected values. We validate our method showing that, without sacrificing the running time performance, it can produce novel alignments. Our results also demonstrate that our method identifies biologically meaningful mappings under a comprehensive set of criteria used in the literature as well as the statistical coherence measure that we developed to analyze the statistical significance of the similarity of the functions of the aligned protein pairs.

Algorithms for Joint Spectrum Allocation and Cooperation Set Partition in Cognitive Radio Networks

The coexistence of multi-primary users and multi-secondary users in cooperative cognitive radio networks motivate the study to propose a joint spectrum allocation and cooperation set partition problem, which so far has not been addressed before. The problem is formulated as a 0-1 integer non-linear programming model. Due to its NP-hardness, the study proposes a suboptimal Centralized Genetic Algorithm (CGA) to show its convergence by modeling it as a homogeneous finite Markov chain. The study then extends CGA to a fully Distributed Genetic Algorithm (DGA) that consists of two phases. The core techniques include a minimum dominate set based cluster partition, a spectrum pre-allocation algorithm in phase 1, and an inter-cluster cooperation set negotiation and cluster fitness refinement algorithm in phase 2. A Fast-Convergent DGA (FDGA) is also devised to reduce the system configuration time. Extensive experiments by simulations demonstrate that in terms of the fitness that reflects the performance of the proposed algorithms: (1) CGA is shown to perform as well as 92% of the optimal solution by brutal search under small network sizes; (2) As the network size increases, due to the massive search space CGA has to deal, DGA and FDGA instead outperform CGA with 20% on average when achieving the same algorithm termination condition; (3) FDGA delivers similar results as DGA while reducing the configuration time significantly, which is more suitable for large-scale networks.

A Parallel, Distributed and Associative Approach for Searching Image Patterns with Holographic Dynamics

This paper presents a new associative pattern-matching network based on a digital adaptation of optical holography. Unlike any existing neural network or associative memories, it can localize its search dynamically on any subset of the pattern space and at the same time generate a feedback on the quality of the match. Current associative memories based on neuro computing are unable to support such meta-interactions. The scheme involves adaptive ‘enfolding’ of the raw massive search space into a holograph and direct regeneration of the matched target pattern during a search. The search process is a constant-time operation compared to traditional algorithm approaches, inherently parallelizable, and is an excellent candidate for hardware or optical implementation. This new technique is expected to facilitate significantly applications that require direct pattern matching in massive image repositories in real time.Target recognition,visual query,content-based image retrieveandautomatic index-extractionare just a few of such applications.