Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial examples using hard labels obtained from the target machine learning model. This is typically realized by optimizing perturbation directions, guided by decision boundaries identified through query-intensive exact search, significantly limiting the attack success rate. This paper introduces a novel approach using the Approximation Decision Boundary (ADB) to efficiently and accurately compare perturbation directions without precisely determining decision boundaries. The effectiveness of our ADB approach (ADBA) hinges on promptly identifying suitable ADB, ensuring reliable differentiation of all perturbation directions. For this purpose, we analyze the probability distribution of decision boundaries, confirming that using the distribution's median value as ADB can effectively distinguish different perturbation directions, giving rise to the development of the ADBA-md algorithm. ADBA-md only requires four queries on average to differentiate any pair of perturbation directions, which is highly query-efficient. Extensive experiments on six well-known image classifiers clearly demonstrate the superiority of ADBA and ADBA-md over multiple state-of-the-art black-box attacks.

A key challenge in black-box adversarial attacks is the high query complexity in hard-label settings, where only the top-1 predicted label from the target deep model is accessible. In this paper, we propose a novel normal-vector-based method called Two-third Bridge Attack (TtBA). A innovative bridge direction is introduced which is a weighted combination of the current unit perturbation direction and its unit normal vector, controlled by a weight parameter $k$. We further use binary search to identify $k=k_\text{bridge}$, which has identical decision boundary as the current direction. Notably, we observe that $k=2/3 k_\text{bridge}$ yields a near-optimal perturbation direction, ensuring the stealthiness of the attack. In addition, we investigate the critical importance of local optima during the perturbation direction optimization process and propose a simple and effective approach to detect and escape such local optima. Experimental results on MNIST, FASHION-MNIST, CIFAR10, CIFAR100, and ImageNet datasets demonstrate the strong performance and scalability of our approach. Compared to state-of-the-art non-targeted and targeted attack methods, TtBA consistently delivers superior performance across most experimented datasets and deep learning models. Code is available at https://anonymous.4open.science/r/TtBA-6ECF.

The robustness of Graph Neural Networks (GNNs) has become an increasingly important topic due to their expanding range of applications. Various attack methods have been proposed to explore the vulnerabilities of GNNs, ranging from Graph Modification Attacks (GMA) to the more practical and flexible Graph Injection Attacks (GIA). However, existing methods face two key challenges: (i) their reliance on surrogate models, which often leads to reduced attack effectiveness due to structural differences and prior biases, and (ii) existing GIA methods often sacrifice attack success rates in undefended settings to bypass certain defense models, thereby limiting their overall effectiveness. To overcome these limitations, we propose QUGIA, a Query-based and Unnoticeable Graph Injection Attack. QUGIA injects nodes by first selecting edges based on victim node connections and then generating node features using a Bayesian framework. This ensures that the injected nodes are similar to the original graph nodes, implicitly preserving homophily and making the attack more unnoticeable. Unlike previous methods, QUGIA does not rely on surrogate models, thereby avoiding performance degradation and achieving better generalization. Extensive experiments on six real-world datasets with diverse characteristics demonstrate that QUGIA achieves unnoticeable attacks and outperforms state-of-the-art attackers. Our code is available at: https://anonymous.4open.science/r/QUGIA-588E/.

Community detection, a vital technology for real-world applications, uncovers cohesive node groups (communities) by leveraging both topological and attribute similarities in social networks. However, existing Graph Convolutional Networks (GCNs) trained to maximize modularity often converge to suboptimal solutions. Additionally, directly using human-labeled communities for training can undermine topological cohesiveness by grouping disconnected nodes based solely on node attributes. We address these issues by proposing a novel Topological and Attributive Similarity-based Community detection (TAS-Com) method. TAS-Com introduces a novel loss function that exploits the highly effective and scalable Leiden algorithm to detect community structures with global optimal modularity. Leiden is further utilized to refine human-labeled communities to ensure connectivity within each community, enabling TAS-Com to detect community structures with desirable trade-offs between modularity and compliance with human labels. Experimental results on multiple benchmark networks confirm that TAS-Com can significantly outperform several state-of-the-art algorithms.

Deep neural networks have become foundational in various applications but remain vulnerable to adversarial patch attacks. Crafting effective adversarial patches is inherently challenging due to the combinatorial complexity involved in jointly optimizing critical factors such as patch shape, location, number, and content. Existing approaches often simplify this optimization by addressing each factor independently, which limits their effectiveness. To tackle this significant challenge, we introduce a novel and flexible adversarial attack framework termed IMPACT (Irregular Multi-Patch Adversarial Composition based on Two-phase optimization). IMPACT uniquely enables comprehensive optimization of all essential patch factors using gradient-free methods. Specifically, we propose a novel dimensionality reduction encoding scheme that substantially lowers computational complexity while preserving expressive power. Leveraging this encoding, we further develop a two-phase optimization framework: phase 1 employs differential evolution for joint optimization of patch mask and content, while phase 2 refines patch content using an evolutionary strategy for enhanced precision. Additionally, we introduce a new aggregation algorithm explicitly designed to produce contiguous, irregular patches by merging localized regions, ensuring physical applicability. Extensive experiments demonstrate that our method significantly outperforms several state-of-the-art approaches, highlighting the critical benefit of jointly optimizing all patch factors in adversarial patch attacks.

Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adversarial robustness are primarily categorized into attack-based and certified robustness evaluation approaches. The former not only relies on specific attack algorithms but also is highly time-consuming, while the latter due to its analytical nature, is typically difficult to implement for large and complex models. A few studies evaluate model robustness based on the model’s decision boundary, but they suffer from low evaluation accuracy. To address the aforementioned issues, we propose a novel adversarial robustness evaluation metric, Robustness Difference Index (RDI), which is based on model statistical features. RDI draws inspiration from clustering evaluation by analyzing the intra-class and inter-class distances of feature vectors separated by the decision boundary to quantify model robustness. It is attack-independent and has high computational efficiency. Experiments show that, RDI demonstrates a stronger correlation with the gold-standard adversarial robustness metric of attack success rate (ASR). The average computation time of RDI is only 1/30 of the evaluation method based on the PGD attack. Our open-source code is available at: https://github.com/BUPTAIOC/RDI.

In the rapidly evolving landscape of cloud computing, scheduling complex scientific workflows poses significant challenges, particularly with constraints like budget considerations. While recent years have seen considerable research focus on budget-constrained cloud workflow scheduling, existing studies primarily concentrate on constructing solutions without delving into potential enhancements. To address this gap, our paper introduces PACP-HEFT, a modified HEFT algorithm integrating priority adjustment and task optimization to minimize makespan. Leveraging the Heterogeneous Earliest-Finish-Time (HEFT) algorithm as its foundation, PACP-HEFT incorporates two priority adjusters informed by task characteristics gleaned from task dependency topology and real-time scheduling data. Additionally, a critical task optimizer conducts thorough analyses and optimizations to reduce overall makespan. Extensive experimentation with real-world workflows underscores PACP-HEFT’s superior performance compared to contemporary algorithms. Note to Practitioners—This paper presents a deterministic approach to budget-constrained scheduling problem, with the objective of minimizing the makespan. The proposed PACP-HEFT algorithm exhibits robust solution enhancement capabilities through the utilization of two priority adjusters and a critical task optimizer. The two priority adjusters fine-tune task priorities based on characteristics extracted from task dependency topology and real-time scheduling data, while the critical task optimizer performs an in-depth analysis of scheduling solutions and optimizes critical tasks to reduce overall makespan. Real-world workflow experiments clearly highlight the superior performance of PACP-HEFT compared to state-of-the-art algorithms. Validation experiments also underscore the effectiveness of each priority adjuster and the critical task optimizer. Moreover, PACP-HEFT’s ability to rapidly reach solutions further enhances its practicality, ensuring timely scheduling outcomes. Furthermore, we assess the adaptability and transferability of these components, emphasizing their potential applicability in enhancing the performance of other scheduling algorithms. For practical applications, this algorithm can be directly applied to rapidly minimize the makespan of budget-constrained scheduling problems in the cloud. Moreover, it can be integrated into other schedulers as a solution enhancement component, offering versatility and improved scheduling efficiency.

Autonomous vehicles (AVs) are considered as next-generation delivery vehicles for logistics systems. This study proposes a dynamic Meal Delivery Routing Problem with a hybrid Rider-AV fleet (MDRP-RA). The hybrid fleet consists of riders and AVs. Each order must be fulfilled by an AV or a rider. Some orders can be delivered by riders or AVs only, while others can be delivered by both. The food of each order is one of three product segments (regular, frozen, and hot food), and each segment has a particular temperature need. An AV has multiple compartments, each of which needs to be cooled (heated) if it contains frozen (hot) food. Thus, AVs can deliver all kinds of food, while riders can deliver regular food only. A mathematical programming model is established for MDRP-RA, with the objective of minimizing the total cost, including the vehicle fixed cost, delivery fee to riders, energy consumption cost, and penalty cost for delay. An Adaptive Large Neighborhood Search based Approach (ALNS-A) is proposed to solve MDRP-RA. It involves a local search procedure with removal and insertion operators, where five operators are specifically devised for the problem. Experiments show that it can effectively solve MDRP-RA and outperforms comparative approaches.Note to Practitioners—AVs have great application potential in meal delivery since they have the advantages of saving labor costs, large capacity, and maintaining food temperature. The hybrid fleet of AVs and riders can meet diversified customer needs but brings challenges to the meal delivery route problem under a dynamic environment. This paper proposes a dynamic meal delivery routing problem with a hybrid rider-AV fleet, with the objective of minimizing the total cost. Some orders must be delivered by riders, some by AVs, and some by both. The food falls into three product segments, i.e., regular, frozen, and hot food. AVs can provide cooling or auxiliary heating to maintain the meal’s temperature. An adaptive large neighborhood search-based approach is proposed, which can provide high-quality solutions for problem instances. The approach can be embedded in takeout information platforms to realize intelligent scheduling of meal delivery.

In a parts-to-picker system, robots move racks from the storage area to picking stations where pickers pick products from the racks. This paper proposes an Order Processing and Robot Scheduling Problem (OPRSP), which optimizes order allocation, rack selection, and robot scheduling together. A mixed integer programming model is developed for OPRSP to minimize the system completion time of fulfilling a given set of customer orders. In OPRSP, customer orders are reorganized into multiple order batches, each allocated to a picking station and treated as an aggregated order. A multi-station visit policy is employed to allow one rack carried by a robot to visit multiple picking stations. A variable neighborhood search-based algorithm is proposed to solve OPRSP. Seven neighborhood structures are specifically devised for OPRSP. Some heuristic algorithms, including order batching algorithm, rack selection algorithm, order batch allocation algorithm, robot task assignment algorithm, and robot scheduling algorithm, are newly devised for initial solution generation and neighborhood structures. The superior performance of the proposed method is validated through a series of experiments and comparisons with other approaches. Experiments reveal that compared to optimizing robot scheduling only, integrating robot scheduling with order processing decisions can greatly improve picking efficiency.

Software-defined networking (SDN) allows flexible and centralized control in cloud data centers. An elastic set of distributed SDN controllers is often required to provide sufficient yet cost-effective processing capacity. However, this introduces a new challenge: Request Dispatching among the controllers by SDN switches. It is essential to design a dispatching policy for each switch to guide the request distribution. Existing policies are designed under certain assumptions, including a single centralized agent, global network knowledge, and a fixed number of controllers, which often cannot be satisfied in practice. This article proposes MADRina, Multiagent Deep Reinforcement Learning for request dispatching, to design policies with high dispatching adaptability and performance. First, we design a multiagent system to address the limitation of using a centralized agent with global network knowledge. Second, we propose a Deep Neural Network-based adaptive policy to enable request dispatching over an elastic set of controllers. Third, we develop a new algorithm to train the adaptive policies in a multiagent context. We prototype MADRina and build a simulation tool to evaluate its performance using real-world network data and topology. The results show that MADRina can significantly reduce response time by up to 30% compared to existing approaches.

In push delivery mode, a supplier determines both delivery orders of customers and vehicle routes. Some customers have small inventory capacity and rapid sale speed (called small-C/S customers). Thus, each of them needs to receive multiple deliveries in a work shift (e.g., one day). The number of deliveries and quantity of each delivery for a customer are unknown. Each delivery has a pair of accommodation time and stockout time, both of which are variable and constitute the soft time window of the delivery. This work proposes a Single-period Inventory Routing problem with split delivery and variable time windows for Small-C/S customers (SIRSC). The number of deliveries for each customer, and the quantity, time window, and arrival time of each delivery are variable. Various products that cannot be mixed can be loaded on the same truck with multiple compartments and a truck can return several times to the depot to resupply in the period. A mathematical programming model is developed for SIRSC, to minimize the sum of transportation and stockout costs. A hybrid ant colony optimization with variable neighborhood search (ACO-VNS) is proposed to solve SIRSC. A distribution network model of ACO is developed and several problem-specific neighborhood structures are designed. ACO-VNS is applied to some problem instances and a real-world gasoline delivery case. Experimental results show that it can effectively solve SIRSC, and outperforms CPLEX and other meta-heuristics.

Bus scheduling is vital for public transportation to ensure high transit service quality. In actual bus operation, buses’ travel time may change due to some uncertain factors, which makes the planned scheduling scheme fail to meet users’ actual requirements. This work proposes a Controller-based Bus Scheduling Approach (CBSA). In this approach, each departure time in a timetable is regarded as a decision point, and a controller is devised to select a bus in real-time to depart from the departure time. The controller makes a decision at each departure time to cover all departure times in a given timetable. The controller consists of a Duty Type Converter (DTC) and a Bus Selector (BS). DTC determines bus duty types to improve bus utilization, while BS selects a bus to cover the departure time. Since the controller makes decisions in a real-time manner, it can effectively handle uncertain events and factors (such as uncertain travel time). Some key parameters of the controller are optimized by a particle swarm optimizer (PSO) to improve its performance. CBSA is applied to real-world problem instances. Experimental results show that it outperforms the compared algorithms and a manual scheduling scheme. It can schedule buses in real-time to generate a high-quality scheduling solution under uncertain environments.

A transit route network design problem is a vitally important problem in the area of public transit systems. Most of studies on this problem aim to design a new transit network, which is often an infeasible option in practice since it is highly challenging to replace an existing network with a completely new one. In this paper, we propose a Multi-objective Ant Colony System-based Approach (MACSA) to adjust routes of bus lines for an existing transit network, such that transit service quality is improved while making the smallest deviation of the adjusted network from the existing one. First, all the bus lines in a network are sorted according to their performance. Then, a multi-objective ant colony system is adapted to adjust the sorted bus lines one by one. Besides traditional optimization objectives to maximize direct passenger flow and minimize line repetition coefficient, a new optimization objective (metric), termed adjustment degree, is proposed to measure the difference between adjusted bus lines and existing ones. Needleman-Wunsch algorithm is introduced to calculate the adjustment degree. A multi-pheromone updating mechanism is suggested to guide ants to search for better bus lines for each objective. MACSA is applied to benchmark problem instances and a real-world problem and compared with six approaches. Experiments show that MACSA can achieve an adjusted network with higher direct passenger flow, lower repetition coefficient and smaller adjustment degree. The adjustment degree achieved by MACSA is 1.61-53.82% smaller than that of other comparative approaches.

This work studies perishable products’ distribution using electric commercial vehicles (ECVs). Extra energy is consumed for refrigeration to keep such products from deteriorating, which shortens the limited driving range of ECVs. Besides charging at public recharging stations, their travel speed can be adjusted to improve their driving range and decrease distribution cost. We propose an Electric Vehicle Routing problem with variable vehicle speed and soft time windows for perishable products (EVRP-VS). An energy consumption rate function of refrigerated ECVs during driving is introduced into the problem. The function considers refrigeration and has a nonlinear relationship with ECV speed and weight. As long as the carriage is not empty, the vehicle needs refrigeration during driving and during its stay at customers and stations. A mathematical programming model is developed for EVRP-VS, to minimize total distribution cost, including vehicle cost, power cost, refrigeration cost, and penalty cost due to delayed delivery. An adaptive hybrid ant colony optimization (AHACO) with a two-stage speed optimization strategy is proposed to solve EVRP-VS. In the first stage, local speed optimization is used to optimize the speed of each ant (ECV) in each transfer step. In the second one, global speed optimization further optimizes the speed for each fixed route constructed by ants. AHACO is applied to many problem instances. Experimental results show that it can effectively solve EVRP-VS in comparison with CPLEX and other meta-heuristics.

Facility layout problems (FLPs) in hospitals are typically to arrange facilities or rooms along both sides of a corridor to minimize some objectives. In a hospital, very often there are center-islands to decrease the flow cost among facilities or rooms. However, these islands have not been considered before. In this article, we propose an FLP with center-islands that involves two parallel rows and center-islands. A mixed-integer program formulation is established for modeling it. A methodology for combining a multiobjective evolutionary algorithm based on decomposition (MOEA/D) and linear program is proposed to solve this problem. MOEA/D optimizes the sequence of facilities on two rows and center-islands while the linear program is embedded into MOEA/D to optimize the exact locations of center-islands. A tabu search with a local search is also integrated into MOEA/D to enhance its search capability. Experiments show that our proposed methodology can effectively solve the problem.

Bus services play a crucial role in urban transit. It is significant to achieve the fine-grained service-level passenger flow prediction (SPFP), namely to predict the total number of passengers for each service of each bus line passing through each station during the next short-term interval. However, it faces great challenges due to complex factors including inter-station and inter-line spatial dependencies, intra-station and inter-service temporal dependencies, and internal/external influences. To address these challenges, we propose a multitask deep-learning (MDL) approach, calledMDL-SPFP, to jointly predict the arriving bus service flow, line-level on-board passenger flow and line-level boarding/alighting passenger flow by leveraging well-designed deep neural networks calledARM. The MDL framework can mutually reinforce the prediction of each type of flow, and finally integrate the outputs to achieve the fine-grained service-level prediction. The ARM network combines three modules, Attention mechanism, Residual block and Multi-scale convolution, to well capture various complex non-linear spatio-temporal dependencies and influence factors. Extensive experiments based on a large-scale realistic bus operation dataset are conducted to confirm that our MDL-SPFP approach outperforms 10 state-of-the-art baselines, and improves 22.39% accuracy than the best baseline.

Planning public transportation network plays an important role in improving operational efficiency and service level. There are numerous literature on the planning of public transportation network; however, most of those works aim to plan the entire network. For big cities, planning the entire network is infeasible because it is impossible to replace the existing network with a whole new one. In this paper, we propose an ant colony optimization (ACO) based approach to adjust existing bus lines in the transportation network. ACO is used to adjust the existing bus lines one by one. To make ants in ACO able to plan new bus lines similar to existing ones, some pheromone is put on the routes of existing bus lines. As we concern the performance of the entire network, an evaluation function is devised to evaluate a bus line's route found by ACO using the performance of entire network. A penalty mechanism is introduced into the approach to avoid generating infeasible bus lines. The approach is applied to problem instances in literature as well as a real-world problem. Experimental results show that the proposed method can achieve satisfactory bus lines with low transfer rate and high direct rate.

Facility layout is vital to save operational cost and enhance production efficiency. Multirow layout is a common pattern in practical manufacturing environment. Although parallel machines are frequently implemented in practice to enhance productivity, there lacks any in-depth study on multirow layout problem with parallel machines. In this paper, its mathematical programming formulation is established to minimize material flow cost. A three-stage approach is proposed to solve it. First, a Monte Carlo heuristic is devised to optimize the sequence of machines on multiple rows. Second, a linear program is used to determine the optimal exact location of each machine. Finally, an exchange heuristic is adopted to reassign material flows among parallel machines in different machine groups. An iterative optimization strategy is suggested to execute the three stages repeatedly to improve the solution quality. This approach is applied to a number of problem instances and compared against others. The experimental results show that it is able to effectively solve this new problem and significantly decrease material flow cost. Note to Practitioners-Multirow layout is common in practical manufacturing systems in which parallel machines are often used to improve productivity, shorten production time, and guarantee some flexibility. This paper studies a multirow parallel machine layout problem that involves machine groups, each of which contains parallel machines. Solving it is to locate all machines at multiple parallel rows to minimize material flow cost. It is challenging because one needs to decompose material flows and determine exact locations of machines simultaneously. A three-stage approach is proposed to do so. It is applied to many problem instances. The results demonstrate that it works well for such layout problems with parallel machines.

Hospital department layout problems (HDLPs) are significant in enhancing service quality and reducing patients' travel distance and time. Their studies are scarce in comparison with those for facility layout problems in manufacturing systems. Existing approaches to HDLPs usually adopt simplified models and thus gain very limited applications in a real world. HDLPs typically involve multiple objectives that may conflict with each other. There have been no studies on their multiobjective heuristic approaches to our best knowledge. In this paper, we propose multiobjective tabu search (MTS) for a real-world HDLP. Beside the frequently used objective of flow cost, ensuring the closeness among certain departments is introduced as another one. A solution coding scheme is designed to represent a solution. A penalty function is devised to handle infeasible solutions. Local search is integrated into tabu search to optimize the assignment of departments. Experiment results show that MTS is able to produce Pareto solutions that outperform those of the comparative method. Compared to the actually implemented layout, solutions produced by MTS can save about 5%-15% patients' travel time (distance).

Although there exist numerous literatures on facility layout in manufacturing systems, studies on department layout in hospitals are relatively scarce. In this paper, we proposed a MOEA/D based approach for a hospital department layout problem, where three objectives are simultaneously optimized, namely patient flow cost, the closeness of departments and rearrangement cost. A constraint handling technology is introduced to deal with infeasible solutions. Experiments show that the proposed approach is able to get satisfactory Pareto solutions with lower patients' flow cost and the closeness compared to the original layout, and that the optimized layouts decrease the patients' move time, thereby improving quality of service.

Bare-bones Particle Swarm Optimization (BPSO) is a simplified PSO variant, which has shown potential performance on many multimodal optimization problems. However, BPSO is also possible to be trapped into local optima for high-dimensional and complicated optimization problems. In order to enhance the performance of BPSO, this paper presents a modified BPSO, called NMBPSO. It combined the ideas of the traditional PSO and a modified BPSO to improve the capacity of balancing exploration and exploitation during the search process. To verify the effect and benefit of the proposed algorithm, a set of well known benchmark functions are employed and compared against some competitive PSO variants. Experiment results indicate that NMBPSO performs better than the traditional PSO, BPSO and a modified BPSO algorithm.

In this paper, we propose a robust double row layout problem (RDRLP), where the material flow between any two machines may vary in different periods. A MOEA/D based solution approach is proposed to solve it. First, MOEA/D is used to find a collection of non-dominated machine sequences. Then, for each found machine sequence, MOEA/D is used to produce a set of non-dominated solutions. Finally, the final set of Pareto solutions is constructed from all the produced non-dominated solutions. The crowding-distance calculation is added to the procedure of updating the elite population to make nondominated solutions distributed uniformly. An integer coding and a real-valued coding with their corresponding crossover and mutation operators are presented. This approach is applied to a number of problem instances with 10-35 facilities and 3-5 periods. Experimental results show that the approach is able to effectively solve this problem.

It is complex and difficult to perform the vehicle scheduling of urban bus lines, which is important to reduce the operational cost and improve the quality of public transportation services. One has to assign vehicles to cover a set of trips contained in a timetable while minimizing multiple objectives that may conflict with each other. Existing approaches combine these objectives in a weighted fashion to form a single objective and then use a single-objective optimization approach to solve it. However, they can only produce one solution, and it is not easy to assign a proper weight for each objective to obtain a superior solution that can balance different objectives. In this paper, a methodology is presented to create a set of Pareto solutions for this problem. First, a set of candidate vehicle blocks is generated. Then, multiple block subsets are selected from this candidate set by an improved multiobjective genetic algorithm combined with a departure-time adjustment procedure to obtain multiple Pareto solutions. To encode a solution, we propose a coding scheme that has a relatively short coding length and low decoding complexity. This approach is applied to a real-world vehicle scheduling problem of a bus line in Nanjing, China. Experiments show that this approach is able to quickly produce satisfactory Pareto solutions that outperform the actually used experience-based solution.

Double-row layout problem (DRLP) is a new problem proposed in 2010. Different from single or multi-row layout problems, DRLP needs to determine not only the sequence of machines on both rows but also the exact location of each machine. Aiming at the dynamic environment of product processing in practice, in this paper we study DRLP under dynamic environment and propose a dynamic double-row layout problem (DDRLP) where the material flows may change over time. A mixed-integer programming model is established for the DDRLP. An improved simulated annealing (ISA) algorithm is proposed to for this problem. To represent a feasible solution, a mixed coding scheme is suggested to express the sequence of facilities and the exact location of each facility. Five operators are devised to make the ISA able to effectively solve this problem. Experiment results show that the proposed algorithm is able to find the optimal solutions for small size problem instances and outperform an exact approach (CPLEX) under limited run time for large size instances.

The single row layout problem is a common and well-studied practical facility layout problem. The problem seeks the arrangement of a fixed number of facilities along one row that minimizes the objective of total material handling cost. In this paper, a single row layout problem with shared clearance between facilities is proposed. The shared additional clearance may be considered on one or both sides of each facility. To solve this problem tabu search is combined with a heuristic rule to solve problems of realistic size. Tabu search is used to find the sequence of facilities while the heuristic rule is determines the additional clearance for each facility. The proposed solution approach is applied to several problem instances involving 10, 20 and 30 facilities, and is compared against a popular mathematical programming solver (CPLEX). Computational results show that our approach is able to obtain high quality solutions and outperforms CPLEX under limited computational time for problems of realistic sizes.

Facility layout problems have drawn much attention over the years, as evidenced by many different versions and formulations in the manufacturing context. This paper is motivated by semiconductor manufacturing, where the floor space is highly expensive (such as in a cleanroom environment) but there is also considerable material handling amongst machines. This is an integrated optimization task that considers both material movement and manufacturing area. Specifically, a new approach combining multiobjective tabu search with linear programming is proposed for an extended double row layout problem, in which the objective is to determine exact locations of machines in both rows to minimize material handling cost and layout area where material flows are asymmetric. First, a formulation of this layout problem is established. Second, an optimization framework is proposed that utilizes multiobjective tabu search and linear programming to determine a set of non-dominated solutions, which includes both sequences and positions of machines. This framework is applied to various manufacturing situations, and compared with an exact approach and a popular multiobjective genetic algorithm optimization algorithm. Experimental results show that the proposed approach is able to obtain sets of Pareto solutions that are far better than those obtained by the alternative approaches.

Cigarette production scheduling is vital in improving production efficiency and reducing supply delay. In this paper, a workflow model combined with an immune algorithm is proposed to solve this problem for improving production efficiency. First, the problem is formulated as a mixed-integer quadratically constrained programming model. Afterwards, the problem is transformed into a workflow resource allocation one. Based on this model, an immune algorithm is presented to find a set of activity priorities that are combined with dispatching rules to allocate resources. Activity priorities are represented by antibodies and evaluated by simulation runs on the workflow model. The proposed approach is applied to several production scheduling instances, and results are compared with other approaches. Experiments show that the result from the proposed approach is substantially better than those obtained from other approaches. It is demonstrated that our approach can effectively reduce production tardiness and improve efficiency.

Public clouds provide Infrastructure as a Service (IaaS) to users who do not own sufficient compute resources. IaaS achieves the economy of scale by multiplexing, and therefore faces the challenge of scheduling tasks to meet the peak demand while preserving Quality-of-Service (QoS). Previous studies proposed proactive machine purchasing or cloud federation to resolve this problem. However, the former is not economic and the latter for now is hardly feasible in practice. In this paper, we propose a resource allocation framework in which an IaaS provider can outsource its tasks to External Clouds (ECs) when its own resources are not sufficient to meet the demand. This architecture does not require any formal inter-cloud agreement that is necessary for the cloud federation. The key issue is how to allocate users' tasks to maximize the profit of IaaS provider while guaranteeing QoS. This problem is formulated as an integer programming (IP) model, and solved by a self-adaptive learning particle swarm optimization (SLPSO)-based scheduling approach. In SLPSO, four updating strategies are used to adaptively update the velocity of each particle to ensure its diversity and robustness. Experiments show that, SLPSO can improve a cloud provider's profit by 0.25%-11.56% compared with standard PSO; and by 2.37%-16.71% for problems of nontrivial size compared with CPLEX under reasonable computation time.

Vehicle scheduling problem is very important for public transport management of bus companies. Given a bus timetable, the problem is to assign vehicles according to the timetable to minimize some optimization objectives. In this paper, a cultural clonal selection algorithm based approach is proposed to automatically obtain a vehicle scheduling solution. Firstly a set of candidate blocks is generated using initial start times. Then a cultural clonal selection algorithm is proposed to choose the best subset of blocks from the block set as a scheduling solution. An initial start time based antibody encoding scheme is suggested, which has the advantages of short coding and low complexity of decoding. An objective function is designed to maximize the occurrences of start times in the final solution. An adjusting strategy for departure times of vehicles is designed to improve the final solution. The proposed approach is applied to a real-world vehicle scheduling problem of the Bus Company of Xi'an city in China to evaluate its effectiveness. Experimental results show that the approach can quickly generate reasonable scheduling solutions, which fulfill the practical vehicle scheduling demands.

A new hybrid algorithm based on Differential Evolution (DE) and Particle Swarm Optimization (PSO) is proposed in this paper for dynamic optimization problems. The multi-population strategy is used to enhance the diversity and keeps each subpopulation on a different peak, and then a hybrid operator based on DE and PSO (DEPSO) is designed to find and track the optima for each subpopulation. Using DEPSO operator, each individual in subpopulations is sequentially carried out DE and PSO operations. An exclusion scheme is proposed which integrates the distance based exclusion scheme with hill-valley function. The algorithm is applied to Moving Peaks Benchmark (MPB) problem. Experimental results show that it is significantly better in terms of averaged offline error than other state-of-the-art algorithms.

Short term traffic speed prediction is very important in intelligent transportation systems. Neural networks have been widely used for traffic speed prediction. However, the classical neural network usually lacks satisfactory generalization ability, which usually results in an imprecise prediction of traffic speed. Regularization is an essential technique to improve the generalization ability of neural network. Regularization is realized by adding a weight decay function to the energy function of the neural network. One of the key problems of the regularization technique is how to decide the parameter of the weight decay function. In this paper, the Bayesian technique is used to optimize these regularization parameters and a Bayesian regularized neural network (BRNN) used for traffic speed prediction is proposed. The speed prediction model was validated by the real-world traffic speeds of the Hangzhou city collected from the floating car system. The experimental results show that the proposed method is able to improve the generalization ability of neural networks, and can achieve better prediction results than several traditional prediction models.

Real-time traffic speed is an important element for Intelligent Transportation Systems (ITS). Getting accurate road speed is very important for transportation service and management systems. Floating car system based on traces of GPS positions is an effective way to gather accurate real-time traffic speed information of a road network. But sometimes the real-time traffic speed information may get lost unexpectedly due to device faults or storage problems. In engineering practice, the historical speed is used to make up the missing real-time speed, but this method cannot estimate the missing speed accurately. Until now, to the best of our knowledge, there is no research on dealing with the missing floating car speed data. In this paper, we propose a novel urban speed fusion method based on principle component analysis (PCA) and neural network (NN) to fuse the speeds of correlated road sections to get the missing speed of the target road section. The floating car data of the Hangzhou city were used to test our method. The experimental results demonstrate that our method outperforms other methods.

A robust scheduling method is proposed to solve uncertain scheduling problems. A set of workflow simulation models is used to model the uncertain scheduling environment, and a robust scheduling scheme is obtained by an immune algorithm to make it has good performances for each model in the model set.