Greedy Search Algorithm Research Articles

Network-based hub biomarker discovery for glaucoma

ObjectiveGlaucoma is an optic neuropathy and the leading cause of irreversible blindness worldwide. However, the early detection of glaucoma remains challenging, as chronic forms of glaucoma remain largely asymptomatic until...

Exact and Approximation Algorithms for Sparse Principal Component Analysis

Sparse principal component analysis (SPCA) is designed to enhance the interpretability of traditional principal component analysis by optimally selecting a subset of features that comprise the first principal component. Given the NP-hard nature of SPCA, most current approaches resort to approximate solutions, typically achieved through tractable semidefinite programs or heuristic methods. To solve SPCA to optimality, we propose two exact mixed-integer semidefinite programs (MISDPs) and an arbitrarily equivalent mixed-integer linear program. The MISDPs allow us to design an effective branch-and-cut algorithm with closed-form cuts that do not need to solve dual problems. For the proposed mixed-integer formulations, we further derive the theoretical optimality gaps of their continuous relaxations. Besides, we apply the greedy and local search algorithms to solving SPCA and derive their first-known approximation ratios. Our numerical experiments reveal that the exact methods we developed can efficiently find optimal solutions for data sets containing hundreds of features. Furthermore, our approximation algorithms demonstrate both scalability and near-optimal performance when benchmarked on larger data sets, specifically those with thousands of features. History: Accepted by Andrea Lodi, Area Editor for Design & Analysis of Algorithms—Discrete. Funding: This research was supported in part by the Division of Civil, Mechanical and Manufacturing Innovation [Grant 224614], the Division of Computing and Communication Foundations [Grant 2246417], and the Office of Naval Research [Grant N00014-24-1-2066]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0372 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0372 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Code and Data Repository for Exact and Approximation Algorithms for Sparse Principal Component Analysis

Sparse principal component analysis (SPCA) is designed to enhance the interpretability of traditional principal component analysis by optimally selecting a subset of features that comprise the first principal component. Given the NP-hard nature of SPCA, most current approaches resort to approximate solutions, typically achieved through tractable semidefinite programs or heuristic methods. To solve SPCA to optimality, we propose two exact mixed-integer semidefinite programs (MISDPs) and an arbitrarily equivalent mixed-integer linear program. The MISDPs allow us to design an effective branch-and-cut algorithm with closed-form cuts that do not need to solve dual problems. For the proposed mixed-integer formulations, we further derive the theoretical optimality gaps of their continuous relaxations. Besides, we apply the greedy and local search algorithms to solving SPCA and derive their first-known approximation ratios. Our numerical experiments reveal that the exact methods we developed can efficiently find optimal solutions for data sets containing hundreds of features. Furthermore, our approximation algorithms demonstrate both scalability and near-optimal performance when benchmarked on larger data sets, specifically those with thousands of features.

How to improve efficiency for prefabricated component production scheduling with worker allocation and order outsourcing?

Prefabricated building is an advanced building mode that is actively promoted in China owing to its high-efficiency, energy-saving and labour-saving characteristics. However, because of the limited production capacity and production resources of the final assembly parts production plant, it is usually impossible for a factory to accept all orders. Therefore, the factory will consider outsourcing part of the orders to reduce delay penalties. In addition, the allocation of workers in the production process will significantly affect the processing time of orders. Regarding those two issues, a production scheduling integrated optimization model, considering worker allocation and order outsourcing, is established to maximize net profit. To address the complexity of problem solving caused by the NP-hard nature of this problem, a hybrid improved genetic–accelerated iterative greedy search algorithm is developed. Finally, a numerical example is delivered to verify that the proposed algorithm has improved solution quality and convergence.

Greedy Ensemble Hyperspectral Anomaly Detection.

Hyperspectral images include information from a wide range of spectral bands deemed valuable for computer vision applications in various domains such as agriculture, surveillance, and reconnaissance. Anomaly detection in hyperspectral images has proven to be a crucial component of change and abnormality identification, enabling improved decision-making across various applications. These abnormalities/anomalies can be detected using background estimation techniques that do not require the prior knowledge of outliers. However, each hyperspectral anomaly detection (HS-AD) algorithm models the background differently. These different assumptions may fail to consider all the background constraints in various scenarios. We have developed a new approach called Greedy Ensemble Anomaly Detection (GE-AD) to address this shortcoming. It includes a greedy search algorithm to systematically determine the suitable base models from HS-AD algorithms and hyperspectral unmixing for the first stage of a stacking ensemble and employs a supervised classifier in the second stage of a stacking ensemble. It helps researchers with limited knowledge of the suitability of the HS-AD algorithms for the application scenarios to select the best methods automatically. Our evaluation shows that the proposed method achieves a higher average F1-macro score with statistical significance compared to the other individual methods used in the ensemble. This is validated on multiple datasets, including the Airport-Beach-Urban (ABU) dataset, the San Diego dataset, the Salinas dataset, the Hydice Urban dataset, and the Arizona dataset. The evaluation using the airport scenes from the ABU dataset shows that GE-AD achieves a 14.97% higher average F1-macro score than our previous method (HUE-AD), at least 17.19% higher than the individual methods used in the ensemble, and at least 28.53% higher than the other state-of-the-art ensemble anomaly detection algorithms. As using the combination of greedy algorithm and stacking ensemble to automatically select suitable base models and associated weights have not been widely explored in hyperspectral anomaly detection, we believe that our work will expand the knowledge in this research area and contribute to the wider application of this approach.

Adaptive Stacking Ensemble Techniques for Early Severity Classification of COVID-19 Patients

During outbreaks of infectious diseases, such as COVID-19, it is critical to rapidly determine treatment priorities and identify patients requiring hospitalization based on clinical severity. Although various machine learning models have been developed to predict COVID-19 severity, most have limitations, such as small dataset sizes, the limited availability of clinical variables, or a constrained classification of severity levels by a single classifier. In this paper, we propose an adaptive stacking ensemble technique that identifies various COVID-19 patient severity levels and separates them into three formats: Type 1 (low or high severity), Type 2 (mild, severe, critical), and Type 3 (asymptomatic, mild, moderate, severe, fatal). To enhance the model’s generalizability, we utilized a nationwide dataset from the South Korean government, comprising data from 5644 patients across over 100 hospitals. To address the limited availability of clinical variables, our technique employs data-driven strategies and a proposed feature selection method. This ensures the availability of clinical variables across diverse hospital environments. To construct optimal stacking ensemble models, our technique adaptively selects candidate base classifiers by analyzing the correlation between their predicted outcomes and performance. It then automatically determines the optimal multi-layer combination of base and meta-classifiers using a greedy search algorithm. To further improve the performance, we applied various techniques, including imputation of missing values and oversampling. The experimental results demonstrate that our stacking ensemble models significantly outperform existing single classifiers and AutoML approaches, with improvements of 6.42% and 8.86% in F1 and AUC scores for Type 1, 9.59% and 6.68% for Type 2, and 11.94% and 9.24% for Type 3, respectively. Consequently, our approach improves the prediction of COVID-19 severity levels and potentially assists frontline healthcare providers in making informed decisions.

Variable Selection for Hidden Markov Models with Continuous Variables and Missing Data

AbstractWe propose a variable selection method for multivariate hidden Markov models with continuous responses that are partially or completely missing at a given time occasion. Through this procedure, we achieve a dimensionality reduction by selecting the subset of the most informative responses for clustering individuals and simultaneously choosing the optimal number of these clusters corresponding to latent states. The approach is based on comparing different model specifications in terms of the subset of responses assumed to be dependent on the latent states, and it relies on a greedy search algorithm based on the Bayesian information criterion seen as an approximation of the Bayes factor. A suitable expectation-maximization algorithm is employed to obtain maximum likelihood estimates of the model parameters under the missing-at-random assumption. The proposal is illustrated via Monte Carlo simulation and an application where development indicators collected over eighteen years are selected, and countries are clustered into groups to evaluate their growth over time.

Sensor placement for data assimilation of turbulence models using eigenspace perturbations

We present an approach to sensor placement for turbulent mean flow data assimilation in the context of Reynolds-averaged Navier–Stokes (RANS) simulations. It entails generating a spatial uncertainty map through the eigenspace perturbations (ESPs) of the baseline turbulence model (e.g., the k−ω shear stress transport model) to quantify the epistemic structural errors in the model. A novel greedy search algorithm is proposed to place sensors targeting regions of highest uncertainty in the spatial uncertainty map generated from ESP. The algorithm is computationally efficient (e.g., computational cost negligible compared to a RANS solution) and is both easy to implement and tune. It involves two hyper-parameters (a constraint to avoid sensor clustering and the number of sensors) which we investigate in-depth. A variational (adjoint-based) data assimilation approach is used for flow reconstruction. The proposed strategy was tested on three two-dimensional wall-bounded flows (Reynolds number ranging 5.6×103–9.36×105) involving flow separation and reattachment. For the wall-mounted hump case, we found that data assimilation using 33 sensors with our proposed sensor placement algorithm reduced the average velocity prediction error by 60% vs 38% with a simple uniform placement of sensors. Furthermore, we found that we could achieve 61% error reduction using our algorithm with only three sensors. Notably, in all tested cases, the error reduction using our method for sensor placement was close in accuracy to the instances where the entire flow field data were used for flow reconstruction, which involved two to three orders of magnitude more data points than the placed sensors.

An Efficient Greedy Search Algorithm for High-dimensional Linear Discriminant Analysis.

High-dimensional classification is an important statistical problem that has applications in many areas. One widely used classifier is the Linear Discriminant Analysis (LDA). In recent years, many regularized LDA classifiers have been proposed to solve the problem of high-dimensional classification. However, these methods rely on inverting a large matrix or solving large-scale optimization problems to render classification rules-methods that are computationally prohibitive when the dimension is ultra-high. With the emergence of big data, it is increasingly important to develop more efficient algorithms to solve the high-dimensional LDA problem. In this paper, we propose an efficient greedy search algorithm that depends solely on closed-form formulae to learn a high-dimensional LDA rule. We establish theoretical guarantee of its statistical properties in terms of variable selection and error rate consistency; in addition, we provide an explicit interpretation of the extra information brought by an additional feature in a LDA problem under some mild distributional assumptions. We demonstrate that this new algorithm drastically improves computational speed compared with other high-dimensional LDA methods, while maintaining comparable or even better classification performance.

Greedy knot selection algorithm for restricted cubic spline regression.

Non-linear regression modeling is common in epidemiology for prediction purposes or estimating relationships between predictor and response variables. Restricted cubic spline (RCS) regression is one such method, for example, highly relevant to Cox proportional hazard regression model analysis. RCS regression uses third-order polynomials joined at knot points to model non-linear relationships. The standard approach is to place knots by a regular sequence of quantiles between the outer boundaries. A regression curve can easily be fitted to the sample using a relatively high number of knots. The problem is then overfitting, where a regression model has a good fit to the given sample but does not generalize well to other samples. A low knot count is thus preferred. However, the standard knot selection process can lead to underperformance in the sparser regions of the predictor variable, especially when using a low number of knots. It can also lead to overfitting in the denser regions. We present a simple greedy search algorithm using a backward method for knot selection that shows reduced prediction error and Bayesian information criterion scores compared to the standard knot selection process in simulation experiments. We have implemented the algorithm as part of an open-source R-package, knutar.

Task scheduling for heterogeneous agents pickup and delivery using recurrent open shop scheduling models

We study the transport-pick agents task scheduling (TPTS) problem in heterogeneous agents pickup and delivery (HAPD). Two functionally heterogeneous agent types, transport agents and pick agents, collaborate to execute multi-goal tasks subjecting to complex-schedule dependency. The objective is to plan a collective time-extended task schedule with the minimization of total completion time. To bridge the gap between robot task scheduling and general scheduling theory, a novel recurrent open shop scheduling (ROSS) problem variant with unique sequence structure is defined. New sequence and schedule models are extended to accommodate for it. Afterwards, the problem-specific append-beam-Christofides (ABC) constructive heuristic, greedy local search (GLS) and simulated annealing (SA) metaheuristic algorithms are designed accordingly. Theoretically, we rigorously analyze sequence and schedule structures, and algorithmic properties; empirically, we study the influence of different algorithm settings on a comprehensive dataset. Design guidelines and parameter settings of these algorithms are provided. The application conditions of the proposed methodology is discussed along with a baseline algorithm TEAMWISE. The proposed methodology could be utilized in various industrial heterogeneous multi-robot or collaborative human–robot systems.

A bi-criteria approach to the truck-multidrone routing problem

In the rapidly expanding field of e-commerce logistics, the optimisation of last-mile delivery solutions is paramount. This paper introduces a novel methodology that addresses this challenge by generating approximate Pareto fronts in a hybrid truck-drone delivery system. Specifically, we examine a generalized single truck multi-drone problem that allows multi-visit flight missions and rendezvous points distinct from launch locations. Our goal is providing decision-makers with a portfolio of optimal routing solutions that balance service time and environmental impact, criteria that are increasingly shaping decision-making in this domain. To achieve this, we introduce a bivector coding scheme inspired by flow-shop scheduling problems and implement a Simulated Annealing algorithm. This algorithm features an advanced stopping mechanism, negating the need for manual adjustments by utilizing a distinctive blend of a domination rate and a Kalman filter. Importantly, our framework employs an iterated greedy search algorithm to evolve from initial solutions towards identifying non-dominated solutions sets, which are then ranked using a hypervolume coefficient. To validate our methodology, we conduct a sensitivity analysis on two different size instances using a full factorial design of experiments. Our analysis reveals crucial insights into the impact of the number of drones, their autonomy, and their flight speed settings. From it, we conclude that it is a robust and adaptable framework for its practical application for obtaining Pareto fronts solutions among which picking the ultimate routing to be implemented.

Learning massive interpretable gene regulatory networks of the human brain by merging Bayesian networks.

We present the Fast Greedy Equivalence Search (FGES)-Merge, a new method for learning the structure of gene regulatory networks via merging locally learned Bayesian networks, based on the fast greedy equivalent search algorithm. The method is competitive with the state of the art in terms of the Matthews correlation coefficient, which takes into account both precision and recall, while also improving upon it in terms of speed, scaling up to tens of thousands of variables and being able to use empirical knowledge about the topological structure of gene regulatory networks. To showcase the ability of our method to scale to massive networks, we apply it to learning the gene regulatory network for the full human genome using data from samples of different brain structures (from the Allen Human Brain Atlas). Furthermore, this Bayesian network model should predict interactions between genes in a way that is clear to experts, following the current trends in explainable artificial intelligence. To achieve this, we also present a new open-access visualization tool that facilitates the exploration of massive networks and can aid in finding nodes of interest for experimental tests.

Skin cancer diagnosis (SCD) using Artificial Neural Network (ANN) and Improved Gray Wolf Optimization (IGWO)

Skin Cancer (SC) is one of the most dangerous types of cancer and if not treated in time, it can threaten the patient’s life. With early diagnosis of this disease, treatment methods can be used more effectively and the progression of the disease can be prevented. Machine Learning (ML) techniques can be utilized as a useful and efficient tool for SCD. So far, various methods for automatic SCD based on ML techniques have been presented; However, this research field still requires the application of optimal and efficient models to increase the accuracy of SCD. Therefore, in this article, a new method for SCD using a combination of optimization techniques and Artificial Neural Networks (ANNs) is presented. The proposed method includes four steps: pre-processing, segmentation, feature extraction, and classification. Image segmentation for identifying the lesion region is performed using a Kohonen neural network, where the identified region of interest (ROI) is enhanced using the Greedy Search Algorithm (GSA). The proposed method, uses a Convolutional Neural Network (CNN) for extracting features from ROIs. Also, to classify features, an ANN is used, and by the Improved Gray Wolf Optimization (IGWO) algorithm, the number of neurons and weight vector are adjusted. In this method, a probabilistic model is used to improve the convergence speed of the GWO algorithm. Based on the evaluation results, using the IGWO model to optimize the structure and weight vector of the ANN can be effective in increasing the diagnosis accuracy by at least 5%. The results of implementing the proposed method and comparing its performance with previous methods also show that this method can diagnose SC in the ISIC-2016 and ISIC-2017 databases with an average accuracy of 97.09 and 95.17%, respectively; which improves accuracy by at least 0.5% compared to other methods.

Reliability evaluation of distribution network for educational purpose: An analytical approach to results analysis

Despite the decade-long development in distribution networks, they are still unable to fulfil society's increasing need for reliable power supply. Investment is necessary for reliability enhancement, which will increase the consumer supply costs. This paper presents a new strategy to enhance the reliability of the network based on network restructuring. This study offers the cost-worth reliability indices, followed by an associated mathematical model with the objective function to reduce the well-known reliability indices Expected Interruption Cost (ECOST) and Energy Not Served (ENS). A Modified Greedy Search Algorithm (MGSA) is introduced to the network optimization for global optimal configuration. Furthermore, to make the model more efficient and realistic, the suggested approach incorporates the effects of fuse failure probability. The impact of the system's islanded operation on the reliability indices is also evaluated. The simulation results show 3.33 % reduction in System Average Frequency Index (SAIFI) as compared with the Fast Adequacy Analysis Method. The results shows that the value of ENS using the proposed MGSA compared to SA and GA improved by 100 %. The application of the proposed strategy on the distribution network connected at BUS-2 of Roy Billinton Test System (RBTS), shows the accuracy and computational effectiveness of the proposed model compared to the state-of-the-art conventional simulation-based topology-variable-based approaches.

Dynamic game optimization control for shared energy storage in multiple application scenarios considering energy storage economy

In response to poor economic efficiency caused by the single service mode of energy storage stations, a double-level dynamic game optimization method for shared energy storage systems in multiple application scenarios considering economic efficiency is proposed in this paper. By analyzing the needs of multiple stakeholders involved in grid auxiliary services, fully tap into the profitability potential of energy storage stations. The capacity of the shared energy storage system is optimized by the non-dominant sorting beluga whale optimization algorithm (NSBWOA) in the upper level, and the operation strategy under multiple scenarios is optimized by the adaptive greedy search algorithm (AGSA) in the lower level. With the goal of maximizing the gross annual total income and high-value peak regulation ratio, and minimizing the cost- income ratio, the optimal capacity configuration and operation strategy of the shared energy storage system are obtained through collaborative optimization between upper and lower level models. The effectiveness of the proposed method is verified through the simulation testing of actual operating data of a certain power grid in China. Simulation results show that the gross annual income and high-value peak regulation ratio across multiple scenarios (Scenario III) are the highest, and the cost-income ratio is at an acceptable low level, which can provide a theoretical basis for the large-scale application of energy storage systems in new power systems.

Enhancing resilience in marine propulsion systems by adopting machine learning technology for predicting failures and prioritising maintenance activities

With the rapid transition towards Industry 4.0, many industries have recognised the need to develop intelligent maintenance systems and predictive analytics tools that are able to optimise the performance of complex assets throughout their entire lifecycle. This paper adopts a machine learning (ML) technology to enhance the resilience of marine propulsion systems by predicting mean-time between failures (MTBF) and prioritising condition-based maintenance (CBM) activities. The factors considered for the analysis include a series of attributes (in total 16 features) which directly or indirectly represent the state of the system subject to degradation. From the results obtained, it is found out that the feed-forward neural network (FFNN) has the least mean square errors (MSE) and, thus, it is the most suitable method for numerical and discretized estimations. The results from a greedy search algorithm also show that two attributes of ‘gas generator rate of revolutions’ and ‘gas turbine rate of revolutions’ are the most significant parameters influencing system reliability, and therefore, they require closer monitoring. Furthermore, a decision support system (DSS) dashboard is designed to help marine propulsion system operators make informed maintenance decisions and find an improved balance in their spare parts inventory.

Lithological Classification by Hyperspectral Images Based on a Two-Layer XGBoost Model, Combined with a Greedy Algorithm

Lithology classification is important in mineral resource exploration, engineering geological exploration, and disaster monitoring. Traditional laboratory methods for the qualitative analysis of rocks are limited by sampling conditions and analytical techniques, resulting in high costs, low efficiency, and the inability to quickly obtain large-scale geological information. Hyperspectral remote sensing technology can classify and identify lithology using the spectral characteristics of rock, and is characterized by fast detection, large coverage area, and environmental friendliness, which provide the application potential for lithological mapping at a large regional scale. In this study, ZY1-02D hyperspectral images were used as data sources to construct a new two-layer extreme gradient boosting (XGBoost) lithology classification model based on the XGBoost decision tree and an improved greedy search algorithm. A total of 153 spectral bands of the preprocessed hyperspectral images were input into the first layer of the XGBoost model. Based on the tree traversal structural characteristics of the leaf nodes in the XGBoost model, three built-in XGBoost importance indexes were split and combined. The improved greedy search algorithm was used to extract the spectral band variables, which were imported into the second layer of the XGBoost model, and the bat algorithm was used to optimize the modeling parameters of XGBoost. The extraction model of rock classification information was constructed, and the classification map of regional surface rock types was drawn. Field verification was performed for the two-layer XGBoost rock classification model, and its accuracy and reliability were evaluated based on four indexes, namely, accuracy, precision, recall, and F1 score. The results showed that the two-layer XGBoost model had a good lithological classification effect, robustness, and adaptability to small sample datasets. Compared with the traditional machine learning model, the two-layer XGBoost model shows superior performance. The accuracy, precision, recall, and F1 score of the verification set were 0.8343, 0.8406, 0.8350, and 0.8157, respectively. The variable extraction ability of the constructed two-layer XGBoost model was significantly improved. Compared with traditional feature selection methods, the GREED-GFC method, when applied to the two-layer XGBoost model, contributes to more stable rock classification performance and higher lithology prediction accuracy, and the smallest number of extracted features. The lithological distribution information identified by the model was in good agreement with the lithology information verified in the field.

A Temporal Coherent Topology Optimization Approach for Assembly Planning of Bespoke Frame Structures

We present a computational framework for planning the assembly sequence of bespoke frame structures. Frame structures are one of the most commonly used structural systems in modern architecture, providing resistance to gravitational and external loads. Building frame structures requires traversing through several partially built states. If the assembly sequence is planned poorly, these partial assemblies can exhibit substantial deformation due to self-weight, slowing down or jeopardizing the assembly process. Finding a good assembly sequence that minimizes intermediate deformations is an interesting yet challenging combinatorial problem that is usually solved by heuristic search algorithms. In this paper, we propose a new optimization-based approach that models sequence planning using a series of topology optimization problems. Our key insight is that enforcing temporal coherent constraints in the topology optimization can lead to sub-structures with small deformations while staying consistent with each other to form an assembly sequence. We benchmark our algorithm on a large data set and show improvements in both performance and computational time over greedy search algorithms. In addition, we demonstrate that our algorithm can be extended to handle assembly with static or dynamic supports. We further validate our approach by generating a series of results in multiple scales, including a real-world prototype with a mixed reality assistant using our computed sequence and a simulated example demonstrating a multi-robot assembly application.

Pushing the Charging Distance Beyond Near Field by Antenna Design

Nowadays, wireless charging has become one of the most popular technologies in Internet of Things (IoT), which makes electric devices battery-free and flexible. The electromagnetic coupling in antenna design is important to push the range limits beyond the near field. Previous studies did not consider the coupling among coils and they do not work for the far-field scenarios. In this paper, we design an antenna for wireless charging that can expand the charging distance from 5 to 55 centimeters, a ten-fold improvement compared to the near-field commercial communication distance according to the simulation results. Specifically, it is practical to take into account the coupling of every two coils when we analyze the transmit power. Therefore, we first model the near-field signal propagation with higher-order factors, and establish the relationship between the geometry parameters and the transmit power. Then, since our problem is extremely non-linear, we design the Greedy Search Algorithm and narrow down the feasible region to obtain the optimal parameters of the coils that can maximize the charging distance. An Ansoft-High Frequency Structure Simulator is adopted to simulate the performance of the coil models, and the results show that square coils achieve the best performance. We also discuss the best arrangement of multiple coil antennas. The impact of the signal phase is also introduced and the best combination of signal phases from different transmit coils is analyzed.