Optimal Route Planning for Truck–Drone Delivery Using Variable Neighborhood Tabu Search Algorithm

The optimal delivery route problem for truck–drone delivery is defined as a traveling salesman problem with drone (TSP-D), which has been studied in a wide range of previous literature. However, most of the existing studies ignore truck waiting time at rendezvous points. To fill this gap, this paper builds a mixed integer nonlinear programming model subject to time constraints and route constraints, aiming to minimize the total delivery time. Since the TSP-D is non-deterministic polynomial-time hard (NP-hard), the proposed model is solved by the variable neighborhood tabu search algorithm, where the neighborhood structure is changed by point exchange and link exchange to expand the tabu search range. A delivery network with 1 warehouse and 23 customer points are employed as a case study to verify the effectiveness of the model and algorithm. The 23 customer points are visited by three truck–drones. The results indicate that truck–drone delivery can effectively reduce the total delivery time by 20.1% compared with traditional pure-truck delivery. Sensitivity analysis of different parameters shows that increasing the number of truck–drones can effectively save the total delivery time, but gradually reduce the marginal benefits. Only increasing either the truck speed or drone speed can reduce the total delivery time, but not to the greatest extent. Bilateral increase of truck speed and drone speed can minimize the delivery time. It can clearly be seen that the proposed method can effectively optimize the truck–drone delivery route and improve the delivery efficiency.

MODIFIED CORRELATION WEIGHT K-NEAREST NEIGHBOR CLASSIFIER USING TRAINING DATASET CLEANING METHOD

In pattern recognition, the k-Nearest Neighbor (kNN) algorithm is the simplest non-parametric algorithm. Due to its simplicity, the model cases and the quality of the training data itself usually influence kNN algorithm classification performance. Therefore, this article proposes a sparse correlation weight model, combined with the Training Data Set Cleaning (TDC) method by Classification Ability Ranking (CAR) called the CAR classification method based on Coefficient-Weighted kNN (CAR-CWKNN) to improve kNN classifier performance. Correlation weight in Sparse Representation (SR) has been proven can increase classification accuracy. The SR can show the 'neighborhood' structure of the data, which is why it is very suitable for classification based on the Nearest Neighbor. The Classification Ability (CA) function is applied to classify the best training sample data based on rank in the cleaning stage. The Leave One Out (LV1) concept in the CA works by cleaning data that is considered likely to have the wrong classification results from the original training data, thereby reducing the influence of the training sample data quality on the kNN classification performance. The results of experiments with four public UCI data sets related to classification problems show that the CAR-CWKNN method provides better performance in terms of accuracy.

Multi-Objective Casting Production Scheduling Problem by a Neighborhood Structure Enhanced Discrete NSGA-II: An Application from Real-World Workshop

Casting production scheduling problem (CPSP) has attracted increasing research attention in recent years to facilitate the profits, efficiency, and environment issues of casting industry. Casting is often characterized by the properties of intensive energy consumption and complex process routes, which motivate the in-depth investigation on construction of practical multi-objective scheduling models and development of effective algorithms. In this paper, for the first time, the multi-objective casting production scheduling problem (MOCPSP) is constructed to simultaneously minimize objectives of defective rate, makespan, and total energy consumption. Moreover, a neighborhood structure enhanced discrete NSGA-II (N-NSGA-II) is designed to better cope with the proposed MOCPSP. In the N-NSGA-II, the advantage of selection mechanism of NSGA-II is fully utilized for selecting non-dominate solution, three neighborhood structures are elaborately designed to strengthen the ability of the local search, and a novel solution generating approach is proposed to increase the diversity of solutions for global search. Finally, a real-world case is illustrated to evaluate the performance of the N-NSGA-II. Computational results show that the proposed N-NSGA-II obtains a wider range of non-dominated solutions with better quality compared to other well-known multi-objective algorithms.

A Wale Optimization Algorithm for Distributed Flow Shop with Batch Delivery

In this study, a distributed flow shop scheduling problem with batch delivery constraints is investigated. The objective is to minimize the makespan and energy consumptions simultaneously. To this end, a hybrid algorithm combining the wale optimization algorithm (WOA) with local search heuristics is developed. In the proposed algorithm, each solution is represented by three vectors, namely a job scheduling sequence vector, batch assignment vector, and a factory assignment vector. Then, an efficient neighborhood structure is applied in the proposed algorithm to enhance search abilities. Furthermore, the simulated annealing algorithm and clustering method are embedded to improve the global search abilities of the algorithm. Finally, 30 instances are generated based on realistic application to test the performance of the algorithm. After detailed comparisons with three efficient algorithms, i.e., ABC-Y, ICA-K, and IWOA NS , the superiority of the proposed algorithm is verified.

Coastal Landform Constrains Dispersal in Mangroves

Mangrove forests are dynamic ecosystems found along low-lying coastal plains along tropical, subtropical, and some warm-temperate coasts, predominantly on tidal flats fringing deltas, estuaries, bays, and oceanic atolls. These landforms present varied hydrodynamic and geomorphological settings for mangroves to persist and could influence the extent of within-site propagule transport and subsequent local regeneration. In this study, we examined how different landform characteristics may influence local genetic diversity, kinship, and neighborhood structure of mangrove populations. To do so, we considered independent populations of Avicennia marina, one of the most abundant and widespread mangrove species, located in estuarine and coastal bay environments spread across the Western Indian Ocean region. A transect approach was considered to estimate kinship-based fine-scale spatial genetic structure using 15 polymorphic microsatellite markers in 475 adult A. marina trees from 14 populations. Elevated kinship values and significant fine-scale structure up to 30, 60, or 90 m distances were detected in sheltered systems void of river discharge, suggesting a setting suitable for very local propagule retention and establishment within a neighborhood. Slopes of a linear regression over restricted distance within 150 m were significantly declining in each sheltered transect. Contrastingly, such a spatial structure has not been detected for A. marina transects bordering rivers in the estuarine systems considered, or alongside partially sheltered creeks, suggesting that recruitment here is governed by unrelated carried-away mixed-origin propagules. South African populations showed strong inbreeding levels. In general, we have shown that A. marina populations can locally experience different modes of propagule movement, explained from their position in different coastal landforms. Thus, the resilience of mangroves through natural regeneration is achieved by different responses in coastal landforms characterized by different hydrodynamic conditions, which can be important information for their management and protection within the variety of coastal environments.

Automated extraction of buildings from IKONOS imagery by integrating spectral and spatial information

Very High Resolution (VHR) imagery is becoming indispensable in urban mapping and land management. But owing to its characteristics, traditional spectral-based building extraction methods are not appropriate. This thesis presents an automated spectral-spatial integration extraction approach to extract two-dimensional roof outlines of urban buildings from IKONOS imagery. It substantially improves accuracy, compared with the well-known Extraction and Classification for Homogenous Objects (ECHO) and Iterative Self-Organizing Data Analysis Technique (ISODATA). With spectral-based Multi-peak Supervised Segmentation (MSS), the approach generates first stage classification. In the second stage, the original colour image and the first stage result are fed into a spatial structure classifier. With analysis of overlapped neighborhood's degree of membership to classes, homogeneity and cross-neighborhood structure, the first stage classification is significantly improved. Finally, buildings are extracted with post-processing. Compared with ISODATA, Signature Editor and ECHO, unique contributions are three new algorithms: MSS, Overlapped Neighborhood Analysis, and Cross-neighborhood Structure Detection.

Automated extraction of buildings from IKONOS imagery by integrating spectral and spatial information

Very High Resolution (VHR) imagery is becoming indispensable in urban mapping and land management. But owing to its characteristics, traditional spectral-based building extraction methods are not appropriate. This thesis presents an automated spectral-spatial integration extraction approach to extract two-dimensional roof outlines of urban buildings from IKONOS imagery. It substantially improves accuracy, compared with the well-known Extraction and Classification for Homogenous Objects (ECHO) and Iterative Self-Organizing Data Analysis Technique (ISODATA). With spectral-based Multi-peak Supervised Segmentation (MSS), the approach generates first stage classification. In the second stage, the original colour image and the first stage result are fed into a spatial structure classifier. With analysis of overlapped neighborhood's degree of membership to classes, homogeneity and cross-neighborhood structure, the first stage classification is significantly improved. Finally, buildings are extracted with post-processing. Compared with ISODATA, Signature Editor and ECHO, unique contributions are three new algorithms: MSS, Overlapped Neighborhood Analysis, and Cross-neighborhood Structure Detection.

Converting tabular data into images for deep learning with convolutional neural networks

Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.

Multi-Objective GRASP for Maximizing Diversity

This work presents a novel greedy randomized adaptive search procedure approach for dealing with the maximum diversity problem from a multi-objective perspective. In particular, five of the most extended diversity metrics were considered, with the aim of maximizing all of them simultaneously. The metrics considered have been proven to be in conflict, i.e., it is not possible to optimize one metric without deteriorating another one. Therefore, this results in a multi-objective optimization problem where a set of efficient solutions that are diverse with respect to all the metrics at the same time must be obtained. A novel adaptation of the well-known greedy randomized adaptive search procedure, which has been traditionally used for single-objective optimization, was proposed. Two new constructive procedures are presented to generate a set of efficient solutions. Then, the improvement phase of the proposed algorithm consists of a new efficient local search procedure based on an exchange neighborhood structure that follows a first improvement approach. An effective exploration of the exchange neighborhood structure is also presented, to firstly explore the most promising ones. This feature allowed the local search proposed to limit the size of the neighborhood explored, resulting in an efficient exploration of the solution space. The computational experiments showed the merit of the proposed algorithm, when comparing the obtained results with the best previous method in the literature. Additionally, new multi-objective evolutionary algorithms derived from the state-of-the-art were also included in the comparison, to prove the quality of the proposal. Furthermore, the differences found were supported by non-parametric statistical tests.