Benchmark Algorithms Research Articles

Specific emitter identification based on multiple sequence feature learning.

The specific emitter identification is widely used in electronic countermeasures, spectrum control, wireless network security and other civil and military fields. In response to the problems that the traditional specific emitter identification algorithm relies on a priori knowledge and has poor generalizability, and the existing specific emitter identification algorithm based on deep learning has poor feature selection and the adopted feature extraction network is not targeted, etc., the specific emitter identification algorithm based on multi-sequence feature learning is proposed. Firstly, multiple sequence features of the emitted signal of the communication radiation source are extracted, and these features are combined into multiple sequence features. Secondly, the multiple sequence fusion convolutional network is constructed to fuse and deeply extract the multiple sequence features and complete the classification of individual communication radiation sources through the classifier of neural network. The selected sequence features of this algorithm contain more and more essential RFF information, while the targeted design of the multi-sequence feature fusion learning network can effectively extract the essential RFF information. The results show that the algorithm can significantly improve the performance of SEI compared with the benchmark algorithm, with a recognition rate gain of about 17%.

GRouNdGAN: GRN-guided simulation of single-cell RNA-seq data using causal generative adversarial networks

We introduce GRouNdGAN, a gene regulatory network (GRN)-guided reference-based causal implicit generative model for simulating single-cell RNA-seq data, in silico perturbation experiments, and benchmarking GRN inference methods. Through the imposition of a user-defined GRN in its architecture, GRouNdGAN simulates steady-state and transient-state single-cell datasets where genes are causally expressed under the control of their regulating transcription factors (TFs). Training on six experimental reference datasets, we show that our model captures non-linear TF-gene dependencies and preserves gene identities, cell trajectories, pseudo-time ordering, and technical and biological noise, with no user manipulation and only implicit parameterization. GRouNdGAN can synthesize cells under new conditions to perform in silico TF knockout experiments. Benchmarking various GRN inference algorithms reveals that GRouNdGAN effectively bridges the existing gap between simulated and biological data benchmarks of GRN inference algorithms, providing gold standard ground truth GRNs and realistic cells corresponding to the biological system of interest.

Election Optimizer Algorithm: A New Meta-Heuristic Optimization Algorithm for Solving Industrial Engineering Design Problems

This paper introduces the election optimization algorithm (EOA), a meta-heuristic approach for engineering optimization problems. Inspired by the democratic electoral system, focusing on the presidential election, EOA emulates the complete election process to optimize solutions. By simulating the presidential election, EOA introduces a novel position-tracking strategy that expands the scope of effectively solvable problems, surpassing conventional human-based algorithms, specifically, the political optimizer. EOA incorporates explicit behaviors observed during elections, including the party nomination and presidential election. During the party nomination, the search space is broadened to avoid local optima by integrating diverse strategies and suggestions from within the party. In the presidential election, adequate population diversity is maintained in later stages through further campaigning between elite candidates elected within the party. To establish a benchmark for comparison, EOA is rigorously assessed against several renowned and widely recognized algorithms in the field of optimization. EOA demonstrates superior performance in terms of average values and standard deviations across the twenty-three standard test functions and CEC2019. Through rigorous statistical analysis using the Wilcoxon rank-sum test at a significance level of 0.05, experimental results indicate that EOA consistently delivers high-quality solutions compared to the other benchmark algorithms. Moreover, the practical applicability of EOA is assessed by solving six complex engineering design problems, demonstrating its effectiveness in real-world scenarios.

A Multi-Objective Pigeon-Inspired Optimization Algorithm for Community Detection in Complex Networks

Community structure is a very interesting attribute and feature in complex networks, which has attracted scholars’ attention and research on community detection. Many single-objective optimization algorithms have been migrated and modified to serve community detection problems. Due to the limitation of resolution, the final algorithm implementation effect is not ideal. In this paper, a multi-objective community detection method based on a pigeon-inspired optimization algorithm, MOPIO-Net, is proposed. Firstly, the PIO algorithm is discretized in terms of the solution space representation, position, and velocity-updating strategies to adapt to discrete community detection scenarios. Secondly, by minimizing the two objective functions of community score and community fitness at the same time, the community structure with a tight interior and sparse exterior is obtained. Finally, for the misclassification caused by boundary nodes, a mutation strategy is added to improve the accuracy of the final community recognition. Experiments on synthetic and real networks verify that the proposed algorithm is more accurate in community recognition compared to 11 benchmark algorithms, confirming the effectiveness of the proposed method.

Mixed-batch scheduling to minimize total tardiness using deep reinforcement learning

This study addresses the issue of scheduling batch machine to minimize total tardiness. Vacuum heat treatment allows multiple jobs to be processed as a batch, as long as they do not exceed the machine's weight and size limits; the weight and size of the jobs both impact the batch processing time. By considering the differences in the release time and due date for each job, a mixed-integer linear programming model is developed and validated using small-scale instances. To tackle large-scale scheduling problems, an intelligent algorithm based on deep reinforcement learning is proposed. Double deep Q-learning networks are designed, and the environmental state feature matrix is extracted as input parameters for the networks. Four job-sorting rules and three scheduling time windows are defined, resulting in twelve action rules within the action space. The most suitable action rule is dynamically selected based on the current batch's environmental status during the scheduling process. Through extensive comparison using large-scale random data, the proposed algorithm demonstrates significantly improved scheduling performance compared to the benchmark algorithms.

Optimization of Energy Efficiency for Federated Learning over Unmanned Aerial Vehicle Communication Networks

Federated learning (FL) is considered a promising machine learning technique that has attracted increasing attention in recent years. Instead of centralizing data in one location for training a global model, FL allows the model training to occur on user devices, such as smartphones, IoT devices, or local servers, thereby respecting data privacy and security. However, implementing FL in wireless communication faces a significant challenge due to the inherent unpredictability and constant fluctuations in channel characteristics. A key challenge in implementing FL over wireless communication lies in optimizing energy efficiency. This holds significant importance, especially considering user devices with restricted power resources. On the other hand, unmanned aerial vehicle (UAV) technologies present a cost-effective solution owing to flexibility and mobility compared to terrestrial base stations. Consequently, the deployment of UAV communication in FL is viewed as a potential approach to deal with the energy efficiency challenge. In this paper, we address the problem of minimizing the total energy consumption of all user equipment (UE) during the training phase of FL over a UAV communication network. Our proposed system facilitates UE to operate concurrently at the same time and frequency, thereby improving bandwidth utilization efficiently. In this paper, we address the problem of minimizing the total energy consumption during the training phase of FL over a UAV communication network. To deal with the proposed nonconvex problem, we propose a novel alternating optimization approach by dividing the problem into two suboptimal problems. We then develop iterative algorithms based on the inner approximation method, yielding at least one locally optimal solution. The numerical results demonstrate the superiority of the proposed algorithm in solving the proposed problem compared to other benchmark algorithms, particularly in determining the optimal trajectory of the UAVs. In addition, we conduct extensive experiments to evaluate how different parameter settings affect performance after implementing the proposed optimization approaches for deploying FL within the UAV communication system. These analyses yield valuable insights into the comparative effectiveness of the proposed optimization algorithms concerning overall energy consumption reduction.

Absolute Value Inequality SVM for the PU Learning Problem

Positive and unlabeled learning (PU learning) is a significant binary classification task in machine learning; it focuses on training accurate classifiers using positive data and unlabeled data. Most of the works in this area are based on a two-step strategy: the first step is to identify reliable negative examples from unlabeled examples, and the second step is to construct the classifiers based on the positive examples and the identified reliable negative examples using supervised learning methods. However, these methods always underutilize the remaining unlabeled data, which limits the performance of PU learning. Furthermore, many methods require the iterative solution of the formulated quadratic programming problems to obtain the final classifier, resulting in a large computational cost. In this paper, we propose a new method called the absolute value inequality support vector machine, which applies the concept of eccentricity to select reliable negative examples from unlabeled data and then constructs a classifier based on the positive examples, the selected negative examples, and the remaining unlabeled data. In addition, we apply a hyperparameter optimization technique to automatically search and select the optimal parameter values in the proposed algorithm. Numerical experimental results on ten real-world datasets demonstrate that our method is better than the other three benchmark algorithms.

Integrated approach to generate artificial samples with low tumor fraction for somatic variant calling benchmarking

BackgroundHigh-throughput sequencing (HTS) has become the gold standard approach for variant analysis in cancer research. However, somatic variants may occur at low fractions due to contamination from normal cells or tumor heterogeneity; this poses a significant challenge for standard HTS analysis pipelines. The problem is exacerbated in scenarios with minimal tumor DNA, such as circulating tumor DNA in plasma. Assessing sensitivity and detection of HTS approaches in such cases is paramount, but time-consuming and expensive: specialized experimental protocols and a sufficient quantity of samples are required for processing and analysis. To overcome these limitations, we propose a new computational approach specifically designed for the generation of artificial datasets suitable for this task, simulating ultra-deep targeted sequencing data with low-fraction variants and demonstrating their effectiveness in benchmarking low-fraction variant calling.ResultsOur approach enables the generation of artificial raw reads that mimic real data without relying on pre-existing data by using NEAT, a fine-grained read simulator that generates artificial datasets using models learned from multiple different datasets. Then, it incorporates low-fraction variants to simulate somatic mutations in samples with minimal tumor DNA content. To prove the suitability of the created artificial datasets for low-fraction variant calling benchmarking, we used them as ground truth to evaluate the performance of widely-used variant calling algorithms: they allowed us to define tuned parameter values of major variant callers, considerably improving their detection of very low-fraction variants.ConclusionsOur findings highlight both the pivotal role of our approach in creating adequate artificial datasets with low tumor fraction, facilitating rapid prototyping and benchmarking of algorithms for such dataset type, as well as the important need of advancing low-fraction variant calling techniques.

Improved differential optimization algorithm for multi-satellite joint earth observation scheduling

The mission completion rate is an important evaluation criterion in the multi-satellite joint observation scheduling problem. This paper proposes a model to address this issue to maximize the mission completion rate. The task requirements and constraints were analyzed with the constellation’s ocean surveillance task as the background. According to the characteristics of the solution space, an improved differential teaching-learning-based optimization is proposed. The proposed algorithm employs a probability-based discretization method and a difference-based individual updating strategy. Simulation experiments demonstrate the effectiveness of the method by improving the task completion rate and convergence speed compared to the benchmark algorithm in the given test case.

BYO: A Unified Framework for Benchmarking Large-Scale Graph Containers

A fundamental building block in any graph algorithm is a graph container - - a data structure used to represent the graph. Ideally, a graph container enables efficient access to the underlying graph, has low space usage, and supports updating the graph efficiently. In this paper, we conduct an extensive empirical evaluation of graph containers designed to support running algorithms on large graphs. To our knowledge, this is the first apples-to-apples comparison of graph containers rather than overall systems, which include confounding factors such as differences in algorithm implementations and infrastructure. We measure the running time of 10 highly-optimized algorithms across over 20 different containers and 10 graphs. Somewhat surprisingly, we find that the average algorithm running time does not differ much across containers, especially those that support dynamic updates. Specifically, a simple container based on an off-the-shelf B-tree is only 1.22× slower on average than a highly optimized static one. Moreover, we observe that simplifying a graph-container Application Programming Interface (API) to only a few simple functions incurs a mere 1.16× slowdown compared to a complete API. Finally, we also measure batch-insert throughput in dynamic-graph containers for a full picture of their performance. To perform the benchmarks, we introduce BYO, a unified framework that standardizes evaluations of graph-algorithm performance across different graph containers. BYO extends the Graph Based Benchmark Suite (Dhulipala et al. 18), a state-of-the-art graph algorithm benchmark, to easily plug into different dynamic graph containers and enable fair comparisons between them on a large suite of graph algorithms. While several graph algorithm benchmarks have been developed to date, to the best of our knowledge, BYO is the first system designed to benchmark graph containers.

Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments

The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.

Efficient statistical QoT-aware resource allocation in EONs over the C+L-band: a multi-period and low-margin perspective

Recently, multi-band elastic optical networks (MB-EONs) have been considered a viable solution to increase the transmission bandwidth in optical networks. To improve spectral efficiency and reduce the blocking ratio, the general signal-to-noise ratio (GSNR) as a quality-of-transmission (QoT) metric must be accurately calculated in the routing, modulation level, and spectrum assignment algorithms used in elastic optical networks (EONs). The interference prediction methods commonly used for single-band EONs are not efficient in the case of MB-EONs because of the inter-channel stimulated Raman scattering impact and their wide spectrum. In this paper, we propose a statistical method to predict the interference noise in C+L-band EONs considering multi-period planning. The proposed algorithm, which utilizes the predicted total number of channels (PTNC) on each link for given requests, is a low-margin, fast, and cost-effective method. Additionally, the proposed PTNC algorithm can also be used for single-period planning. Our simulation results indicate that the proposed PTNC algorithm combines the advantages of both studied benchmark algorithms. It has a low complexity order and execution time that are comparable to those of the fully loaded algorithm, which is currently employed by the network operators. However, this benchmark does not achieve the best spectral efficiency. Furthermore, the PTNC method and the other benchmark that determines margin through an exhaustive search, referred to as margin exhaustive search (MES), achieve remarkable spectral efficiency and residual capacity with fewer transceivers, resulting in lower capital expenditure requirements. Nevertheless, the MES algorithm may not be practical due to the requirement of reconfiguring established lightpaths and its high complexity order, particularly in multi-period planning.

Deterministic Lightweight VM placement for HANDLING resource constraint issues in the cloud

The virtual machines (VMs) placement is the subject of current cloud computing research. This study proposes the energy-constrained VM placement technique to address the issue of placing location limits on VMs to satisfy their requirements throughout the VM placement process. Each virtual machine (VM) can only be installed on one of the designated candidate physical machines (PMs) that have sufficient processing power, additionally, in order to satisfy the communication requirements of the associated VMs, there must be sufficient bandwidth between the selected PMs. Choosing where to put a virtual machine (VM) is a crucial task. It involves finding the best physical server or computer to host the VM. Picking the right host is essential for making sure the cloud system uses power wisely, uses resources effectively, and supports good quality of service. This work explore the problem of imposing constraints on the placements of VMs in cloud computing (CC) and offer an alternative perspective on VM placement. This work provides a novel algorithm based on this unique viewpoint to produce the required outcome. To show how successful the proposed Deterministic Lightweight VM placement (DLVMP) is, we run and examine several simulations. The outcomes demonstrate that our technique achieves reduced computing time and improved performance. Simulation results show that the proposed model functions and performs better in terms of blocking probability and computing time than other benchmark algorithms.

Research on a Capsule Network Text Classification Method with a Self-Attention Mechanism

Convolutional neural networks (CNNs) need to replicate feature detectors when modeling spatial information, which reduces their efficiency. The number of replicated feature detectors or labeled training data required for such methods grows exponentially with the dimensionality of the data being used. On the other hand, space-insensitive methods are difficult to encode and express effectively due to the limitation of their rich text structures. In response to the above problems, this paper proposes a capsule network (self-attention capsule network, or SA-CapsNet) with a self-attention mechanism for text classification tasks, wherein the capsule network itself, given the feature with the symmetry hint on two ends, acts as both encoder and decoder. In order to learn long-distance dependent features in sentences and encode text information more efficiently, SA-CapsNet maps the self-attention module to the feature extraction layer of the capsule network, thereby increasing its feature extraction ability and overcoming the limitations of convolutional neural networks. In addition, in this study, in order to improve the accuracy of the model, the capsule was improved by reducing its dimension and an intermediate layer was added, enabling the model to obtain more expressive instantiation features in a given sentence. Finally, experiments were carried out on three general datasets of different sizes, namely the IMDB, MPQA, and MR datasets. The accuracy of the model on these three datasets was 84.72%, 80.31%, and 75.38%, respectively. Furthermore, compared with the benchmark algorithm, the model’s performance on these datasets was promising, with an increase in accuracy of 1.08%, 0.39%, and 1.43%, respectively. This study focused on reducing the parameters of the model for various applications, such as edge and mobile applications. The experimental results show that the accuracy is still not apparently decreased by the reduced parameters. The experimental results therefore verify the effective performance of the proposed SA-CapsNet model.

When Optimization Meets AI: An Intelligent Approach for Network Disintegration with Discrete Resource Allocation

Network disintegration is a fundamental issue in the field of complex networks, with its core in identifying critical nodes or sets and removing them to weaken network functionality. The research on this problem has significant strategic value and has increasingly attracted attention, including in controlling the spread of diseases and dismantling terrorist organizations. In this paper, we focus on the problem of network disintegration with discrete entity resources from the attack view, that is, optimizing resource allocation to maximize the effect of network disintegration. Specifically, we model the network disintegration problem with limited entity resources as a nonlinear optimization problem and prove its NP-hardness. Then, we design a method based on deep reinforcement learning (DRL), Net-Cracker, which transforms the two-stage entity resource and network node selection task into a single-stage object selection problem. Extensive experiments demonstrate that compared with the benchmark algorithm, Net-Cracker can improve the solution quality by about 8∼62%, while enabling a 30-to-160-fold speed up. Net-Cracker also exhibits strong generalization ability and can find better results in a near real-time manner even when the network scale is much larger than that in training data.

Multi-objective genetic algorithm embedded with reinforcement learning for petrochemical melt-flow-index production scheduling

In the petrochemical industry, product type conversion can cause capacity loss and produce transition products, leading to waste. Our study aims to minimize these transition products and tardiness in meeting customer due dates. We introduce the Engineering Experience Heuristic (EEH), which utilizes scheduling reference sheets to identify key production traits and constraints, thereby generating efficient schedules. Further building on the EEH, we propose a non-dominated sorting genetic algorithm II enhanced with reinforcement learning (NSGAeRL) to address the multi-objective scheduling optimization problem. The incorporation of reinforcement learning (RL), particularly through a model-based Markov Decision Process (MDP), allows for the dynamic adjustment of genetic algorithm (GA) parameters, including crossover and mutation mechanisms, based on the optimal policy derived from RL. We validate our proposed methodologies through empirical studies and numerical experiments. The results demonstrate that NSGAeRL outperforms standard benchmarking algorithms, offering superior performance in minimizing transition products and scheduling tardiness.

Topological benchmarking of algorithms to infer gene regulatory networks from single-cell RNA-seq data.

In recent years, many algorithms for inferring gene regulatory networks from single-cell transcriptomic data have been published. Several studies have evaluated their accuracy in estimating the presence of an interaction between pairs of genes. However, these benchmarking analyses do not quantify the algorithms' ability to capture structural properties of networks, which are fundamental, e.g., for studying the robustness of a gene network to external perturbations. Here, we devise a three-step benchmarking pipeline called STREAMLINE that quantifies the ability of algorithms to capture topological properties of networks and identify hubs. To this aim, we use data simulated from different types of networks as well as experimental data from three different organisms. We apply our benchmarking pipeline to four inference algorithms and provide guidance on which algorithm should be used depending on the global network property of interest. STREAMLINE is available at https://github.com/ScialdoneLab/STREAMLINE. The data generated in this study are available at https://doi.org/10.5281/zenodo.10710444.

Multi-Criteria Framework for Routing on Access Land: A Case Study on Dartmoor National Park

Creating routes across open areas is challenging due to the absence of a defined routing network and the complexity of the environment, in which multiple criteria may affect route choice. In the context of urban environments, research has found Visibility and Spider-Grid subgraphs to be effective approaches that generate realistic routes. However, the case studies presented typically focus on plazas or parks with defined entry and exit points; little work has been carried out to date on creating routes across open areas in rural settings, which are complex environments with varying terrain and obstacles and undefined entry or exit points. To address this gap, this study proposes a method for routing across open areas based on a Spider-Grid subgraph using queen contiguity. The method leverages a Weighted Sum–Dijkstra’s algorithm to allow multiple criteria such as surface condition, total time, and gradient to be considered when creating routes. The method is tested on the problem of routing across two areas of Dartmoor National Park, United Kingdom. The generated routes are compared with benchmark algorithms and real paths created by users of the Ordnance Survey’s Maps App. The generated routes are found to be more realistic than those of the benchmark methods and closer to the real paths. Furthermore, the routes are able to bypass hazards and obstacles while still providing realistic and flexible routes to the user.

A comprehensive benchmark of graph-based genetic variant genotyping algorithms on plant genomes for creating an accurate ensemble pipeline.

Although sequencing technologies have boosted the measurement of the genomic diversity of plant crops, it remains challenging to accurately genotype millions of genetic variants, especially structural variations, with only short reads. In recent years, many graph-based variation genotyping methods have been developed to address this issue and tested for human genomes. However, their performance in plant genomes remains largely elusive. Furthermore, pipelines integrating the advantages of current genotyping methods might be required, considering the different complexity of plant genomes. Here we comprehensively evaluate eight such genotypers in different scenarios in terms of variant type and size, sequencing parameters, genomic context, and complexity, as well as graph size, using both simulated and real data sets from representative plant genomes. Our evaluation reveals that there are still great challenges to applying existing methods to plants, such as excessive repeats and variants or high resource consumption. Therefore, we propose a pipeline called Ensemble Variant Genotyper (EVG) that can achieve better genotyping performance in almost all experimental scenarios and comparably higher genotyping recall and precision even using 5× reads. Furthermore, we demonstrate that EVG is more robust with an increasing number of graphed genomes, especially for insertions and deletions. Our study will provide new insights into the development and application of graph-based genotyping algorithms. We conclude that EVG provides an accurate, unbiased, and cost-effective way for genotyping both small and large variations and will be potentially used in population-scale genotyping for large, repetitive, and heterozygous plant genomes.

Multi-objective electricity generation expansion planning towards renewable energy policy objectives under uncertainties

Conventional petrol vehicles emit a substantial quantity of greenhouse gases, leading to increasingly serious global warming problems. The expansion and development of renewable power generation technologies is conducive in promoting the use of electric vehicles, which are more environmentally friendly. This paper proposes a multi-objective power expansion model considering renewable energy policy objectives. The model regards the problem as a multi-period optimisation task, taking the newly installed capacity and the power generation capacity of each power generation technology as decision variables, and simulating the uncertain factors in the planning process using Geometric Brownian Motion and Monte Carlo approaches. The optimisation objective of the model is to minimise expected costs, reduce risk and environmental impacts, and incorporate changing policy objectives into the constraints to meet policy makers’ expectations for renewable energy development. Then, a decentralised target search-based multi-objective evolutionary algorithm is proposed to solve the model. Its effectiveness is verified by a numerical example using real data from the Chinese power system. The experimental results show that the proposed algorithm exhibits improved performance compared with benchmark algorithms and provides high quality and diverse Pareto-optimal solutions to decision makers. Finally, the optimal plans for power expansion and generation mix under different preferences and policy objectives are discussed and corresponding recommendations are made.