Adaptive Neighborhood Research Articles

Adaptive group Riemannian manifold learning for hyperspectral image classification

Hyperspectral image classification is an important topic in the field of remote sensing. However, the high dimensionality and high spatial-spectral correlation of hyperspectral image will easily lead to poor classification performance due to the Hughes phenomenon. In this paper, we proposed a adaptive group local Riemannian embedding, called AGLRE, to extract the spatial and spectral features from hyperspectral image. It firstly mapped original data into a Riemannian manifold by constructing region covariance matrices for each pixel of hyperspectral image. And the multiple local tangent space on Riemannian manifold were learned by adaptive neighbourhood strategy. Lastly, the local linear embedding was applied to reduce the dimensionality and merge multiple tangent space into a global coordinate. Experimental results on public hyperspectral data set showed that the proposed method can achieve higher classification performance than other competing algorithms.

Semi-supervised Entity Alignment via Relation-based Adaptive Neighborhood Matching

Many recent studies of Entity Alignment (EA) use Graph Neural Networks (GNNs) to aggregate the neighborhood features of entities and achieve better performance. However, aligned entities in real Knowledge Graphs (KGs) usually have non-isomorphic neighborhood structures due to the different data sources of KGs. Therefore, it is insufficient to simply compare the global direct neighborhood of aligned entities, which may also become a variable for the EA judgment. In this paper, we propose a Relation-based Adaptive Neighborhood Matching method ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RANM</i> ), which matches larger range and higher confidence neighborhoods for aligned entities based on relation matching instead of alignment seeds. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RANM</i> first uses alignment seeds to construct the best relation matching set, and then performs local direct neighborhood matching and feature aggregation on the candidate alignments. To obtain high-quality entity embeddings, we design a variant attention mechanism based on heterogeneous graphs, which considers the heterogeneity of relations in KGs. We also adopt a bi-directional iterative co-training to further improve the performance. Extensive experiments on three well-known datasets show our method significantly outperforms 14 state-of-the-art methods, and is 3.01-11.5% higher than the best-performing baselines in Hits@1. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RANM</i> also shows high performance on the long-tailed entities and the dataset with less alignment seeds.

A Hybrid Heuristic Algorithm for Solving COVID-19’s Social Distancing at Universities Campus

Social distancing during COVID-19 has become one of the most important measures in reducing the risks of the spread of the virus. Implementing these measures at universities is crucial and directly related to the physical attendance of the populations of students, professors, employees, and other members on campus. This research proposes an automated scheduling approach that can help universities and schools comply with the social distancing regulations by providing assistance in avoiding huge assemblages of people. Furthermore, this paper proposes a novel course timetable-scheduling scheme based on four main constraints. First, a distance of two meters must be maintained between each student inside the classroom. Second, no classrooms should contain more than 20% of their regular capacity. Third, there would be no back-to-back classes. Lastly, no lectures should be held simultaneously in adjacent classrooms. The proposed approach was implemented using a variable neighborhood search (VNS) approach with an adaptive neighborhood structure (AD-NS) to resolve the problem of scheduling course timetables at Al-Ahlyyia Amman University. However, the experimental results show that the proposed techniques outperformed the standard VNS tested on university course timetabling benchmark dataset ITC2007-Track3. Meanwhile, the approach was tested using datasets collected from the faculty of information technology at Al-Ahlyyia Amman University (Jordan). Where the results showed that, the proposed technique could help educational institutes to resume their regular operations while complying with the social distancing guidelines.

Multi granularity based label propagation with active learning for semi-supervised classification

Semi-supervised learning (SSL) methods, which exploit both the labeled and unlabeled data, have attracted a lot of attention. One of the major categories of SSL methods, graph-based semi-supervised learning (GBSSL) learns labels of unlabeled data on an adjacency graph, where neighborhood sparse graph is often used to reduce computational complexity. However, the neighborhood size is difficult to set. Instead of assigning a concrete value of neighborhood size, we propose a new label propagation algorithm called multi granularity based label propagation (MGLP) and developed from the view of granular computing. In MGLP, labels of unlabeled data are learned by two classic label propagation processes with diverse neighborhood size k, where granular computing delivers a guiding strategy to leverage multiple level neighborhood information granules, and three-way decision acts as an active learning strategy to select the unlabeled data for further annotating. Through the iterative procedures of label propagating, data annotating and data subset updating, the ultimate pseudo label accuracy of unlabeled data may be higher. Theoretically, the accuracy of pseudo labels is enhanced in some scenarios. Experimentally, the results of simulation studies on ten benchmark datasets, show that the proposed method MGLP can rise pseudo labels accuracy by 8.6% than LP (label propagation), 6.5% than LNP (linear neighborhood propagation), 6.4% than LPSN (label propagation through sparse neighborhood), 4.5% than Adaptive-NP (adaptive neighborhood propagation) and 4.6% than CRLP (consensus rate-based label propagation). It also provides a novel way to annotate data.

Balancing and scheduling assembly lines with human-robot collaboration tasks

In light of the Industry 5.0 trend towards human-centric and resilient industries, human-robot collaboration (HRC) assembly lines can be used to enhance productivity and workers’ well-being, provided that the optimal allocation of tasks and available resources can be determined. This study investigates the assembly line balancing problem (ALBP), considering HRC. This problem, abbreviated ALBP-HRC, arises in advanced manufacturing systems, where humans and collaborative robots share the same workplace and can simultaneously perform tasks in parallel or in collaboration. Driven by the need to solve the more complex assembly line-balancing problems found in the automotive industry, this study aims to address the ALBP-HRC with the cycle time and the number of operators (humans and robots) as the primary and secondary objective, respectively. In addition to the traditional ALBP constraints, the human and robot characteristics, in terms of task times, allowing multiple humans and robots at stations, and their joint/collaborative tasks are formulated into a new mixed-integer linear programming (MILP) model. A neighborhood-search simulated annealing (SA) is proposed with customized solution representation and neighborhood search operators designed to fit into the problem characteristics. Furthermore, the proposed SA features an adaptive neighborhood selection mechanism that enables the SA to utilize its exploration history to dynamically choose appropriate neighborhood operators as the search evolves. The proposed MILP and SA are implemented on real cases taken from the automotive industry where stations are designed for HRC. The computational results over different problems show that the adaptive SA produces promising solutions compared to the MILP and other swarm intelligence algorithms, namely genetic algorithm, particle swarm optimization, and artificial bee colony. The comparisons of human/robot versus HRC settings in the case study indicate significant improvement in the productivity of the assembly line when multiple humans and robots with collaborative tasks are permissible at stations.

Adaptive neighborhood size and effective geometric features selection for 3D scattered point cloud classification

Classification of 3D scatter and unorganized point cloud (PC) is an ongoing hard problem due to high redundancy, unbalanced sampling density, and large data structure of PC. Geometric and spectral features derived from the PC are generally used for classification. In this paper, an Omnivariance based adaptive neighborhood size selection method and a new feature set composed of 14 features are proposed for extraction of geometric features for each individual point within the local neighborhood. Performance of 8 modern classifiers with different strategies (i.e., boosting, ensemble, and deep learning etc.) were evaluated on the Oakland, Vaihingen, and ISPRS datasets. These 3 datasets are identified by 5, 9, and 2 distinct object classes, respectively. The results were compared with different neighborhood size selection methods (i.e., eigenentropy based, fixed number of the k-nearest neighbors) and feature set (i.e., 21 features). Only 3D local features were employed to classify datasets with varying characteristics and properties. The proposed optimum neighbor selection method and feature set provided the best statistical results with Auto-Encoder classifier (the overall accuracies are over 85%, 60% and, 90% the Oakland, Vaihingen, and ISPRS datasets, respectively). Especially for the ISPRS dataset, the Auto-Encoder obtained over 94%, 90%, and 93% precision, recall, and f-score, respectively.

EEG fading data classification based on improved manifold learning with adaptive neighborhood selection

In electroencephalogram (EEG) signal analysis, data fading problem exists from signal production to collection by brain-computer interface (BCI) device, which can be raised by BCI device deficiency, dynamic network limitation and subject issue. EEG data fading problem changes the distribution of data, which results in the movement of the cluster center and fuzzy class boundary after feature extraction with negative effects in EEG classification results. To decrease the adverse influence of data fading, a novel fading data classification method based on manifold learning and adaptive neighborhood selection is proposed in this paper to mitigate this adverse effect of data fading. In the proposed method, after neighborhood selection according to local linearity, data are mapped into manifold space through local tangent space alignment (LTSA) for dimensionality reduction. The method is carried out on BCI Competition 2008 – Graz data set A of four-class EEG data of motor imagery (MI) experiments. The experimental results are compared with conventional LTSA and indicate that the proposed method effectively improves the classification accuracy of fading data.

Joint neighborhood preserving and projected clustering for feature extraction

Neighborhood reconstruction is proved effective for dimensionality reduction because of the preservation of manifold structure. Conventional neighborhood preserving embedding (NPE) method first learns the affinity relationship or reconstruction relationship in the original space, and then learns the projection matrix to preserve the learned local information in low-dimensional space. However, the pre-learned manifold information may be inaccurate due to the noises and irrelevant features in real-world data. The performance of dimensionality reduction would be influenced as well. Besides, NPE and its variants only aim to preserve the local reconstruction relationship but ignore the fuzzy membership relationship between samples and cluster prototypes. To address these issues, we propose an adaptive neighborhood preserving discriminant projection model, where sparse reconstruction coefficients are updated in the process of dimensionality reduction to eliminate the influence of noises and irrelevant features. Meanwhile, we also learn the fuzzy membership relationships between data points and cluster prototypes to gather the samples belonging to the same class together in low-dimensional space. Neighborhood reconstruction learning and clustering are seamlessly connected in the learned subspace. To solve this model, an iterative algorithm is developed. The experimental results of recognition accuracy show the superiorities of the proposed methods over the state-of-the-arts.

Research on LRP Integration of E-Commerce Logistics under the Background of Integration of Collection and Distribution

The distribution network composed of location and route is an important part of e-commerce logistics. With the continuous improvement of e-commerce requirements for logistics level, the practice of planning logistics network only from the perspective of the network location or the vehicle route can no longer meet the actual demand. In addition to the comprehensive consideration of the location-routing problem, the reverse logistics caused by customers’ returning goods should be taken into account. In this paper, the destruction and reorganization strategy of adaptive large-scale neighborhood search algorithm was introduced into the traditional genetic algorithm, so as to conduct research on the logistics location-routing problem under the background of integration of collection and distribution. Finally, the effectiveness of the optimized genetic algorithm was verified by Matlab tools and the existing bench-marking data set of the location-routing problem, which provided reference for the planning and decision-making of logistics enterprises.

IMOEA/D to optimize job release problem for a reentrant hybrid flow shop

In a reentrant production system, an effective job release policy is helpful to increase output and keep the work in process (WIP) in an acceptable level. This study mainly focuses on the job release problem in a reentrant hybrid flow shop (RHFS-JRP). First, to increase output and reduce jobs’ waiting time, a mathematical model is formulated to minimize the difference between the actual output and the target output and the total waiting time of jobs jointly. Second, an improved multi-objective evolutionary algorithm based on decomposition (IMOEA/D) is proposed to solve the RHFS-JRP. Third, to generate job release plans effectively, a dual chromosome encoding method indicating release quantities and release intervals is proposed. Fourth, the WIP control mechanism based decoding algorithm is proposed to reduce the total waiting time of jobs without affecting output. Fifth, to avoid falling into the local optimum and ensure the diversity of the population, an adaptive neighborhood updating strategy is proposed. Finally, numerical experiments are performed and the results show that the IMOEA/D can solve the RHFS-JRP effectively.

Adaptive large neighborhood search for mixed integer programming

Large Neighborhood Search (LNS) heuristics are among the most powerful but also most expensive heuristics for mixed integer programs (MIP). Ideally, a solver adaptively concentrates its limited computational budget by learning which LNS heuristics work best for the MIP problem at hand. To this end, this work introduces Adaptive Large Neighborhood Search (ALNS) for MIP, a primal heuristic that acts as a framework for eight popular LNS heuristics such as Local Branching and Relaxation Induced Neighborhood Search (RINS). We distinguish the available LNS heuristics by their individual search spaces, which we call auxiliary problems. The decision which auxiliary problem should be executed is guided by selection strategies for the multi armed bandit problem, a related optimization problem during which suitable actions have to be chosen to maximize a reward function. In this paper, we propose an LNS-specific reward function to learn to distinguish between the available auxiliary problems based on successful calls and failures. A second, algorithmic enhancement is a generic variable fixing prioritization, which ALNS employs to adjust the subproblem complexity as needed. This is particularly useful for some LNS problems which do not fix variables by themselves. The proposed primal heuristic has been implemented within the MIP solver SCIP. An extensive computational study is conducted to compare different LNS strategies within our ALNS framework on a large set of publicly available MIP instances from the MIPLIB and Coral benchmark sets. The results of this simulation are used to calibrate the parameters of the bandit selection strategies. A second computational experiment shows the computational benefits of the proposed ALNS framework within the MIP solver SCIP.

An ALNS algorithm for the static dial-a-ride problem with ride and waiting time minimization

The paper investigates the static dial-a-ride problem with ride and waiting time minimization. This is a new problem setting of significant practical relevance because several ride-sharing providers launched in recent years in large European cities. In contrast to the standard dial-a-ride problem, these providers focus on the general public. Therefore, they are amongst others in competition with taxis and private cars, which makes a more customer-oriented objective necessary. We present an adaptive large neighbourhood search (ALNS) as well as a dynamic programming algorithm (DP), which are tested in comprehensive computational studies. Although the DP can only be used for a single tour and, due to the computational effort, as a restricted version or for small instances, the ALNS also works efficiently for larger instances. The results indicate that ride-sharing proposals may help to solve the trade-off between individual transport, profitability of the provider, and reduction of traffic and pollution.

Multi-Depot Joint Distribution Vehicle Routing Problem Considering Energy Consumption with Time-Dependent Networks

This paper studies the multi-depot joint distribution vehicle routing problem considering energy consumption with time-dependent networks (MDJDVRP-TDN). Aiming at the multi-depot joint distribution vehicle routing problem where the vehicle travel time depends on the variation characteristics of the road network speed in the distribution area, considering the influence of the road network on the vehicle speed and the relationship between vehicle load and fuel consumption, a multi-depot joint distribution vehicle routing optimization model is established to minimize the sum of vehicle fixed cost, fuel consumption cost and time window penalty cost. Traditional vehicle routing problems are modeled based on symmetric graphs. In this paper, considering the influence of time-dependent networks on routes optimization, modeling is based on asymmetric graphs, which increases the complexity of the problem. A hybrid genetic algorithm with variable neighborhood search (HGAVNS) is designed to solve the model, in which the nearest neighbor insertion method and Logistic mapping equation are used to generate the initial solution firstly, and then five neighborhood structures are designed to improve the algorithm. An adaptive neighborhood search times strategy is used to balance the diversification and depth search of the population. The effectiveness of the designed algorithm is verified through several groups of numerical instances with different scales. The research can enrich the relevant theoretical research of multi-depot vehicle routing problems and provide the theoretical basis for transportation enterprises to formulate reasonable distribution schemes.

Adaptive local neighborhood range based firefly algorithm for link prediction

Adaptive local neighborhood range based firefly algorithm for link prediction

Robust Fuzzy Clustering Algorithm Based on Adaptive Neighbors

In pattern recognition, fuzzy logic is widely used in unsupervised classification or clustering methods. Fuzzy c-means (FCM) clustering algorithm is a typical dynamic clustering algorithm of the fuzzy c-means algorithm based on the error square sum criterion. It introduces fuzzy membership and optimizes the objective function to obtain each sample point for all classes. The membership degree of the center is used to automatically classify the data sample. However, the FCM algorithm is susceptible to the noise points and outliers, and the unbalanced data structure reduces the generalization performance of the algorithm. In this paper, we propose a fuzzy c-means clustering algorithm with adaptive neighbors weight learning. Through adaptive neighborhood robust weight learning, an adaptive weight vector with robustness and sparsity is obtained. During the optimization, we only activate the k samples with the shortest distance to the cluster center and eliminate extreme noise samples to improve the global robustness and sparsity of the algorithm. Finally, empirical analysis verifies the superiority and effectiveness of the proposed clustering method.

Adaptive neighborhood selection based on locally linear embedding for the degradation index construction of traction motor bearing

The degradation index construction is significant for bearing degradation assessment which ensures the reliability of machines. Statistical features extracted from vibration signals contain abundant information about the bearing operation state, but not all features have good characterization ability. Therefore, a multi-criteria weighted evaluation criterion is introduced to select features that can properly describe degradation assessment. To construct a more effective and reliable degradation index from the high-dimensional feature set, an adaptive neighborhood selection algorithm based on locally linear embedding (ANS-LLE) is proposed in this paper. The initial neighborhood parameters are determined based on cosine similarity analysis. Then neighborhood parameters are adjusted based on the analysis of sample distribution density and manifold curvature. The effectiveness of the proposed method is validated by an accelerated life experiment and a fault simulation experiment. The results show that the proposed method can effectively describe the bearing degradation process, and ANS-LLE performs better compared with comparison methods.

Advanced loading constraints for 3D vehicle routing problems

Given automated order systems, detailed characteristics of items and vehicles enable the detailed planning of deliveries including more efficient and safer loading of distribution vehicles. Many vehicle routing approaches ignore complex loading constraints. This paper focuses on the comprehensive evaluation of loading constraints in the context of combined Capacitated Vehicle Routing Problem and 3D Loading (3L-CVRP) and its extension with time windows (3L-VRPTW). To the best of our knowledge, this paper considers the currently largest number of loading constraints meeting real-world requirements and reducing unnecessary loading efforts for both problem variants. We introduce an approach for the load bearing strength of items ensuring a realistic load distribution between items. Moreover, we provide a new variant for the robust stability constraint enabling better performance and higher stability. In addition, we consider axle weights of vehicles to prevent overloaded axles for the first time for the 3L-VRPTW. Additionally, the reachability of items, balanced loading and manual unloading of items are taken into account. All loading constraints are implemented in a deepest-bottom-left-fill algorithm, which is embedded in an outer adaptive large neighbourhood search tackling the Vehicle Routing Problem. A new set of 600 instances is created, published and used to evaluate all loading constraints in terms of solution quality and performance. The efficiency of the hybrid algorithm is evaluated by three well-known instance sets. We outperform the benchmarks for most instance sets from the literature. Detailed results and the implementation of loading constraints are published online.

Cooperative MASS path planning for marine man overboard search

In a Man Overboard (MOB) incident, a quick and effective Search and Rescue (SAR) operation is crucial to increase the survival probability of the victim. Determining the search area and planning paths for the rescue ships are essential for efficient SAR operation. The search area's determination requires the prediction of the missing person, facing the challenges of lacking information about the accurate position and time of falling and the influence of environmental disturbances. Two main aims of path planning for SAR operation are quick arrival at the search area and coverage search with high cumulative Possibility of Success (POS). Many path planning algorithms have been proposed. Most of them aim at finding the shortest paths, which meet the goal of quick arrival. However, the path planning for maximizing POS of finding the person is still lacking. Besides, compared to an individual ship, a fleet of cooperative Maritime Autonomous Surface Ships (MASS) can significantly increase the POS and reduce SAR personnel's risk in a time-sensitive SAR operation. Therefore, in this paper, we propose a cooperative path planning framework to search for the missing person in a MOB incident using a fleet of fully autonomous MASS. The framework is divided into three modules, i.e., position prediction, target tracking, and coverage search. Firstly, the stochastic particle simulation method is used to predict the missing person's position considering the environment forecasting data, which determines the search area. Secondly, an adaptive greedy search algorithm is applied to tracking the drifting predicted area. Thirdly, the coverage search algorithm is designed with an adaptive neighborhood and evaluation function for increasing the cumulative POS in a limited time. Moreover, the path is smoothed by the Line-of-Sight algorithm and the kinematic interpolation method. Simulation experiments and sensitivity analysis are carried out to demonstrate the effectiveness of the proposed framework.

An algorithm to identify the appropriate size of a neighbourhood when analysing spatially distributed field experiments by local cokriging

Farm management decisions based on multiple treatments or yield differences with measurable statistical uncertainty are effective and popular. The “oft” (on-farm-tools) software developed in this study provides an easy access to identify local neighbourhood points for non-collocated multiple treatment response differences. Methods for analysing multiple treatments based on multivariate geostatistics are generally computationally expensive for relatively large samples, such as data coming from modern sensors. Localised methods for multiple treatments reduce the computational complexity and can address local variability; however, their performance depends on the choice of the number of neighbours. A common practice for localised methods is to pre-specify a neighbourhood radius or number of neighbourhood samples based on analyst or farmer experience while tolerating the computational costs. Hence, introducing the “oft” package, we propose an adaptive neighbourhood point algorithm to identify the neighbouring samples for the localised analysis in order to achieve a good balance between computation time and accuracy. We explore an experimental case study dataset obtained from a vineyard in Langhorne Creek, South Australia, which is a particular application of the general problem of the neighbourhood selection for localised multivariate geostatistics.

Refraction error correction of Airborne LiDAR Bathymetry data considering sea surface waves

Airborne Light Detection And Ranging (LiDAR) Bathymetry (ALB) has an unparalleled advantage in integrated sea-land measurements, especially in the acquisition of topographic data in shallow water areas. Sea surface waves are an important factor affecting the quality of ALB data. This paper presents a method that strictly corrects the sea surface wave-induced refraction error for each seabed laser pulse without any complex modeling of the sea surface. In this method, an adaptive neighborhood selection method is first used to calculate the normal sea surface at the moment when a laser pulse enters the water, and then a laser pulse refraction error correction model considering sea surface waves is constructed. The distance condition equation, the angle condition equation and the coplanar condition equation are established based on Snell's law and the geometric relationship among the incident laser pulse, the normal vector of the wavy sea surface and the actual refracted ray in order to calculate the coordinates of each laser point at the seabed after refraction error correction. The experimental results show that sea surface waves have a significant impact on the three-dimensional point cloud coordinates of the underwater topography. Even in calm sea conditions, the plane coordinate displacement error of the seabed point caused by the sea surface waves may reach the meter level, and the depth coordinate displacement error can also exceed 0.2 m. The corrected displacement errors of the planimetric coordinates are significantly greater than the corrected displacement errors of the depth coordinates, which can effectively improve the quality of the ALB data.