Search

A relatively new goods-to-person order picking system (robotic compact storage and retrieval system, RCS/RS) has been implemented within order fulfillment centers. In such a system, robots move in x - and y -dimensions on top of a grid-based storage area to retrieve bins from stacks by "digging" in z -dimension. To transport a requested bin to a port, robots (or a robot) remove(s) all blocking bins above the requested bin and place(s) them around neighboring stacks. Defining the throughput of an RCS/RS as the number of bins processed per unit time, we analyze the time required for bins to be removed from stacks, transported to ports, returned to stacks, and placed in stacks. In making a case for considering skewness among activity levels for bins, we develop closed-form expressions to calculate the expected operation time for the movement of bins, validate the closed-form expressions using simulation, and obtain the system configuration that maximizes throughput performance (or minimizes operation time for bins) based on current practice. Then, with an objective of having an optimal RCS/RS design based on activity levels of bins, we show the significant impact on throughput when different skewness values for activity levels of the bins are incorporated into the design. [ABSTRACT FROM AUTHOR]

Cross-domain recommendation (CDR) leverages knowledge from the source domain to make recommendations for the cold-start users in the target domain. On account of fully utilizing information, various relationships among users and items are taken into account, i.e., the interaction relationship between users and their corresponding items; the relationship among users or items; and the indirect relationship between the user and items related to other users. In order to process these relationships, we propose a novel framework named Memory Pool Variational AutoEncoder (MPVAE). The main advantages of the MPVAE model lie in three aspects: (1) it generates the embedding representations that incorporate more information by a memory pool mechanism in the source and target domains; (2) it involves the relationship among users or items efficiently by the similarity measurement, further, the indirect relationship can be explicitly described, which makes full use of information in the source domain; and (3) it leverages the superiority of the probability model from the perspective of the VAE structure, which ensures generation and robustness. Comprehensive experiments on three real datasets show that the proposed model achieves remarkable superiority over several competitive CDR models. [Display omitted] • Propose MPVAE to generate embeddings that incorporate more information. • MPVAE involves various relationships among data in the source domain. • MPVAE ensures generation and robustness by the VAE structure. • Conduct extensive experiments on three datasets. [ABSTRACT FROM AUTHOR]

• Mining social media data is formulated into multi-objective optimization task. • Several objectives are modelled to maximize a profit of the summary. • The problem was grasped by utilizing the Gravitational Search Algorithm. • Significant promising results against other robust comparative methods. Short messages are one of the milestones on the web especially on social media (SM). Due to the widespread circulation of SM, it already turns into excessively painful capturing outmost relevant and significant information for certain users. One of the main motivations of this work is that many users may need an inclusive brief of all comments without reading the entire list of short messages for decision making. In this work, mining in big social media data is formulated for the first time into a multi-objective optimization (MOO) task to extract the essence of a text. Since some users may demand the brief at any moment, several groups of dissimilar short messages are established based on graph coloring mechanism. Six interesting feature are formalized to exhibit more interactive messages. A Gravitational Search Algorithm (GSA) is employed to satisfy several important objectives for generating a concise summary. The problem was picked by using the Normal Boundary Intersection (NBI) mechanism to trade-off among different features. Additionally, to satisfy real-time needs, an inventive incremental grouping task is modelled to update the existing colors. From exhaustive experimental results, the proposed approach outperformed other strong comparative methods. [ABSTRACT FROM AUTHOR]

• We focus on the order picking process optimization in the RMFS. • An integrated order and robot scheduling optimization problem is studied. • A mixed-integer non-linear programming model is formulated. • Some managerial implications for warehouses managers are proposed. The Robotic Mobile Fulfillment System (RMFS) is a parts-to-picker warehouse system where robots are used to fetch inventory goods from the storage area and transport them to the workstation. To improve the overall performance of the order picking process, this paper investigates an integrated order and robot scheduling optimization problem. We formulate this problem as a mixed-integer non-linear programming (MINLP) model with an objective of minimizing the total cost, containing the transportation cost of robots, the cost of loading and unloading operation, the incentive cost, and the penalty cost. And a Variable Neighborhood Search algorithm is presented to solve the MINLP model. Numerical experiments are conducted on 30 test cases based on real-world data to validate effectiveness of the proposed model and algorithm. Results show that the formulated model contribute to cost saving, and the proposed algorithm not only solves the model within a reasonable CPU time, but also yields near-optimal solutions with about 0.67% relative gap. Moreover, the study find that the reasonable robot configuration has a significant impact on the overall system performance. [ABSTRACT FROM AUTHOR]

• Create an efficient model to build different layout and mode of RMFS models. • Model aims at performance evaluating of both uni- and bidirectional path mode RMFS. • Obtained knowledge is useful for designing new systems with fewer experiments. The robotic mobile fulfillment system (RMFS) is a "goods to man" picking system that employs numerous automatic guided vehicles (AGVs) instead of workers to transport goods from the storage station to the picking station. Using smarter AGVs enhances the performance but also leads to layout problems and the challenge of efficiently estimating the system performance with various layouts. With the same capability of storage, the different row and column of storage position area can lead to different system performance. The number of combinations of rows and columns is huge which makes it time-consuming to compare all the combinations to find the best one, and different path modes (unidirectional path mode and bidirectional path mode) and different number of AGVs further complicate the problem. Quickly modeling and performance estimating of RMFS become the biggest challenge for logistics enterprise. In this paper, according to the modular simulation theory, an efficient model based on discrete-event system simulation is proposed for quickly constructing different RMFS layouts and estimating their performance. The model contains two independent components: a physical component and a control component. The nuclear module for physical component is the track module that forms all tracks and can be temporarily or permanently blocked to satisfy the requirements of both unidirectional and bidirectional path mode models. The main functions of the control component are routing, collision prediction, and collision avoidance. The physical and control components are independent but work together to construct and run a certain model according to the input parameters; thus, an RMFS model can be efficiently built by simply entering parameters. A series of experiments were conducted to evaluate the performance of the RMFS in different layouts with various numbers of AGVs in both the unidirectional and bidirectional path modes. The results indicated that in the same layout, the bidirectional path mode can reach the summit output with fewer AGVs. The experimental results also indicated that in a large-scale RMFS, vertically arranging the storage station on the block island and then horizontally positioning the block island can result in a higher output than other layouts. In addition, the experimental results indicated that the proposed model can quickly construct different RMFS layouts and efficiently determine the best scheme. [ABSTRACT FROM AUTHOR]

Robotic compact storage and retrieval systems (RCSRSs) are robotized automated warehousing systems that are being increasingly used in several companies around the world owing to their efficient usage of space and low cost. In RCSRSs, a vertical stacking approach is used. Thus, to retrieve a target bin, all bins located above it must be reshuffled, causing the depth-wise position of bins to change repeatedly. Therefore, the amount of work required for a robot to process bins depends heavily on the sequence in which orders are processed. In this study, we address the problem of determining the processing sequence for a given set of orders in the RCSRS. According to the complexity of this problem, we propose a rollout heuristic algorithm to find a high-quality solution within a short computation time. We also introduce several strategies to improve the performance of the proposed algorithm. Through computational experiments on random instances generated based on real-world data, we demonstrate that the proposed rollout heuristic algorithm can be effectively applied to real-world instances. • A new sequencing problem arising in the robotized automated warehouse is discussed. • A rollout heuristic algorithm is proposed to obtain high-quality solutions. • Various performance improvement strategies are introduced. • The effectiveness and efficiency of the proposed heuristic are verified. [ABSTRACT FROM AUTHOR]

Abstract: Determining the proper storage locations for potentially thousands of products is one major task that faces the warehouse manager during the design of a new warehouse or the refurbishment of existing facility. There are many factors affects the storage assignment. For example, order picking method, size and layout of the storage system, material handling system, product characteristics, demand trends, turnover rates and space requirements. Selecting appropriate storage assignment policies (i.e. random, dedicated or class-based) and routing methods (i.e. transversal, return or combined) with regards to above factors is a possible solution to tackle this problem. However, the efficiency of these policies is interdependent. This paper aims to present a simulation study of a real case regarding storage assignment problem of a manual-pick and multi-level rack warehouse. Performance of the case is measured in terms of travel distance and order retrieval time. The results of the study indicate that the key to effective implementation of a storage assignment system is to match the types of warehouse storage system and the variety of items in the customer order. Also, the use of key performance indicator should clearly reflect the needs of the warehouse. [ABSTRACT FROM AUTHOR]

Measuring text similarity is an important challenge for Chinese emergency response plans, which describe complex response processes involving four level responses and collaborative interactions among multiple departments and roles. Most existing studies focus on lexical semantic features and their results are not applicable to Chinese emergency response plans. In order to reflect process semantics of Chinese emergency response plans, a novel text similarity measure is proposed. First, an emergency response process including four sub-processes is extracted from an emergency response plan, and each emergency response sub-process is represented by three types of response tasks, i.e. regular task, message sending task and message receiving task. Next, vector representations of process elements including task statements, roles and departments are generated. Then, response task vectors that are represented by a combination of process element vectors are generated and three response task set vectors are used for emergency response sub-process representation. Finally, the similarity between sub-processes is computed as the average cosine similarity of three pairs of response task set vectors and the text similarity is the average similarity of four sub-processes. A real-world data set is collected for experimental evaluation and the results illustrate that the proposed approach performs well in distinguishing topics and levels of emergency response plans. [ABSTRACT FROM AUTHOR]

Abstract: This article describes an intelligent system called LogNet that provides advice on how to design business logistics networks. It implements its capabilities by utilizing model-based reasoning techniques. In addition, it utilizes heuristic-based searching to guide an end-user toward more effective network designs. The network design problem studied in this article addresses the warehouse facility location problem: how many warehouses are needed in a network and to which customer markets should they be assigned? LogNet enables end-users to incrementally create and test a logistics network design by using a graphical user interface. LogNet employs model-based reasoning procedures that analyze the structure of the current network design in order to offer recommendations on how to consolidate or decentralize a network. The overall goal of LogNet is to provide a flexible user interface that is capable of supporting this design task. [Copyright &y& Elsevier]

Machine learning techniques have been used frequently for volatility forecasting. However, previous studies have built these hybrid models in a form of a first-order GARCH(1,1) process by following general use for GARCH models. But the way of estimating parameters for GARCH and machine learning models differs considerably. Hence, we have investigated the effect of different model orders of the GARCH process on the volatility forecasts of Bitcoin obtained by the four most used machine learning models. Furthermore, we have proposed a stacking ensemble methodology based on GARCH hybrid models to improve the results further. The proposed stacking ensemble methodology utilizes the techniques of feature selection and feature extraction to reduce the dimension of the predictors before meta-learning. The results show that using higher model orders increases the accuracy of volatility forecasts for hybrid GARCH models. Also, the proposed stacking ensemble with LASSO produces forecasts superior to almost all hybrid models and better than the ordinary stacking ensemble. [ABSTRACT FROM AUTHOR]

• Robust system to detect people only using depth information from a frontal ToF camera. • Proposal based on biometric features of the human head. • System outperforms state-of-the-art methods in different datasets. • Proposal runs in real time using a low-cost CPU platform. This paper presents a new method for detecting people using only depth images captured by a camera in a frontal position. The approach is based on first detecting all the objects present in the scene and determining their average depth (distance to the camera). Next, for each object, a 3D Region of Interest (ROI) is processed around it in order to determine if the characteristics of the object correspond to the biometric characteristics of a human head. The results obtained using three public datasets captured by three depth sensors with different spatial resolutions and different operation principle (structured light, active stereo vision and Time of Flight) are presented. These results demonstrate that our method can run in realtime using a low-cost CPU platform with a high accuracy, being the processing times smaller than 1 ms per frame for a 512 × 424 image resolution with a precision of 99.26% and smaller than 4 ms per frame for a 1280 × 720 image resolution with a precision of 99.77%. [ABSTRACT FROM AUTHOR]

• A soft computing-based column generation heuristic for order picking is proposed. • The proposed algorithm is compared against PSA-ACO and an exact method. • Based on numerical experiments some managerial insights are proposed. At an operational level, order picking is the main activity in fulfillment centers. Motivated by and through collaboration with a third party logistic company, this study presents a novel hybrid column generation (CG), genetic algorithm (GA), and artificial neural network (ANN) heuristic for minimizing makespan in manual order picking operations. The results of column generation heuristic is compared against a mixed integer programming model solved by Gurobi, and a parallel simulated annealing and ant colony optimization (PSA-ACO) previously proposed in the literature. Through numerical experiments, the superiority of CG heuristic compared to other methods is shown, and some managerial insights regarding the relationship between makespan optimization, workload balance, picking capacity, and number of pickers in order picking operations is presented. [ABSTRACT FROM AUTHOR]

• Highlight the need for an effective approach for time-critical freight logistics. • Propose an efficient GRASP-based meta-heuristic approach. • Consolidate orders within vehicles and through transhipment points (hubs) • Demonstrate the economic and environmental benefits of this expert system. Time-critical freight logistics is an area within logistics research where the shipper's orders need to be received relatively urgently using a third party logistics (3PL) that provides a quote (bid) to the shipper within a very short period. We solved this 3PL problem by developing an effective meta-heuristic based on the Greedy Randomized Adaptive Search Procedure (GRASP). This is achieved by introducing novel attributes in the construction of the restricted candidate list while incorporating flexible and intelligent rules, some of which are inspired by expert knowledge. The approach performs order consolidation, locates transshipment points and performs an optimal assignment of shipments to the selected consolidation points dynamically and in real time. This intelligent system embeds expert knowledge within the design of neighbourhood reduction schemes and data structures to speed up the search. This is achieved by recording computed data that does not need to be recomputed again while avoiding unnecessary computations of the non-promising alternatives. The performance of this real time optimisation and scheduling tool is tested with a European 3PL company over a 13 weeks period in late 2017 resulting in a significant cost saving and a considerable reduction in CO 2 emissions. This powerful decision support system assists the 3PL company in gaining competitive leadership advantage through producing promising quotes that turn customer requests into real customer orders. [ABSTRACT FROM AUTHOR]