This paper introduces MeLA, a Metacognitive LLM-Driven Architecture that presents a new paradigm for Automatic Heuristic Design (AHD). Traditional nature evolutionary methods operate directly on heuristic code. Existing prompt-evolution methods mainly optimize task descriptions before generation. In contrast, MeLA evolves the instructional prompts used during heuristic generation and focuses on reflective guidance from previous outputs. This new paradigm, termed Metacognitive Prompt Evolution , is driven by a novel metacognitive framework where the system analyzes performance feedback to systematically refine its generative strategy. MeLA’s architecture integrates a problem analyzer to construct an initial strategic prompt, an error diagnosis system to correct faulty code, and a metacognitive search engine that iteratively optimizes the prompt based on heuristic effectiveness. In comprehensive experiments across both benchmark and real-world problems, MeLA achieves competitive performance on classical tasks and demonstrates clear advantages on more complex real-world problems. Ultimately, this research demonstrates the profound potential of using cognitive science as a blueprint for AI architecture, revealing that by enabling an LLM to metacognitively regulate its problem-solving process, we unlock a more robust and interpretable path to AHD.

The robust segmentation of different targets in multiple modality images is challenging due to factors such as low contrast, variations in target size and shape, and interference from diseases, which may lead to segmentation ambiguity. In addition, the assessment of the reliability of artificial intelligence is crucial for its clinical application. This paper proposes the Online Bayesian approximation based Uncertainty-aware Network (OBU-Net) for robust ophthalmic image segmentation. Our approach introduces an efficient online Bayesian method to update a spatial uncertainty map during training continuously. Then, the Spatial Uncertainty Aware Block (SUA-B) leverages the uncertainty map to localize and prioritize attention to ambiguous regions. Additionally, we extract pixel-wise confidence from multi-scale predictions to integrate hierarchical predictions. We compare OBU-Net with state-of-the-art (SOTA) methods on six datasets. The experimental results demonstrate that our method achieves the best overall performance across different modalities and segmentation tasks, highlighting the robustness of our approach. Additionally, metamorphic testing experiments were conducted, exploring the algorithm's stability against random perturbations. Lastly, we propose an image-level uncertainty score and demonstrate its effectiveness for evaluating the model's segmentation reliability.

While visual reasoning for simple analogies has received significant attention, compositional visual relations (CVR) remain relatively unexplored due to their greater complexity. To solve CVR tasks, we propose Predictive Reasoning with Augmented Anomaly Contrastive Learning (PR-A$^{2}$CL), i.e., to identify an outlier image given three other images that follow the same compositional rules. To address the challenge of modelling abundant compositional rules, an Augmented Anomaly Contrastive Learning is designed to distil discriminative and generalizable features by maximizing similarity among normal instances while minimizing similarity between normal and anomalous outliers. More importantly, a predict-and-verify paradigm is introduced for rule-based reasoning, in which a series of Predictive Anomaly Reasoning Blocks (PARBs) iteratively leverage features from three out of the four images to predict those of the remaining one. Throughout the subsequent verification stage, the PARBs progressively pinpoint the specific discrepancies attributable to the underlying rules. Experimental results on SVRT, CVR and MC$^{2}$R datasets show that PR-A$^{2}$CL significantly outperforms state-of-the-art reasoning models.

Recently, researchers have achieved significant results in the skeleton-based action recognition. To better model the skeleton sequences, we drive the encoder to learn more discriminative representations in the self-supervised setting. We find that instead of clustering feature vectors to assign pseudo labels for samples as in DeepCluster, ranking them is a more reasonable, reliable, and efficient way to learn more effective feature representations. With this intuition, we propose a novel self-supervised learning framework,DeepRank. Specifically, we rank triplets of skeleton sequences with the ranking labels, obtained from the relative distances among them. Besides, to deeply mine complementary discriminative information that exists in different modalities of skeleton sequences, we further proposeMulti-ViewDeepRank(MV-DeepRank) to enable encoders to comprehensively learn complementary features from multiple modalities. Extensive experimental results on the NTU RGB+D, NTU RGB+D 120, PKU-MMD I, and PKU-MMD II datasets under various evaluation settings demonstrate the generality, transferability, and superiority of our proposed self-supervised learning frameworks. Notably, our frameworks surpass the previous methods that employ the same backbone networks as ours by at least 1.8% (ST-GCN) and 2.1% (STTFormer) under the finetuning setting. Additionally, DeepRank gains a significant advantage on computational complexities,$O(1)$, over the contrastive learning-based methods,$O(\rm{batch size})$, and the clustering-based methods,$O(\rm{number of clusters})$.

Routing congestion prediction expedites the closure of FPGA placement and routing (PnR). Current prediction methods employ convolutional models, taking advantage of their capacity of dealing with image-style inputs. However, these methods neglect the direct representation of circuit netlist and its information fusion with placement scheme. Moreover, the limited size of the convolutional kernel struggles to capture circuit connectivity in distant geometric regions. To address these issues, this article presents a graph-based routing congestion prediction framework that fuses the information contained in the circuit’s topological netlist and geometric placement scheme, and leverages a conditional generative adversarial network (cGAN) model to achieve optimized prediction performance compared to contemporary approaches. Our framework encompasses three key components: (1) the HeteroGraph, a heterogeneous graph that integrates a netlist subgraph and a layout subgraph by space mapping edges; (2) the HeteroGNN, a heterogeneous graph neural network that learns the latent features of both the circuit netlist and placement scheme through dual-space message-passing; and (3) the HeteroGNN-embedded cGAN, a model that combines the HeteroGNN with a cGAN for accurate FPGA routing congestion prediction. Compared to state-of-the-art approaches, our method reduces the routing congestion prediction’s root-mean-square error by 18.2% on the VTR7 benchmarks and by 15.0% on the large-scale Titan23 benchmarks. The code associated with this article can be found at https://github.com/AIPnR/FPGA_Hetero_Congestion_Prediction .

Abstract visual reasoning (AVR) is a critical ability of humans, and it has been widely studied, but arithmetic visual reasoning, a unique task in AVR to reason over number sense, is less studied in the literature. To facilitate this research, we construct a Machine Number Reasoning (MNR) dataset to assess the model's ability in arithmetic visual reasoning over number sense and spatial layouts. To solve the MNR tasks, we propose a Dual-branch Arithmetic Regression Reasoning (DARR) framework, which includes an Intra-Image Arithmetic Regression Reasoning (IIARR) module and a Cross-Image Arithmetic Regression Reasoning (CIARR) module. The IIARR includes a set of Intra-Image Regression Blocks to identify the correct number orders and the underlying arithmetic rules within individual images, and an Order Gate to determine the correct number order. The CIARR establishes the arithmetic relations across different images through a `3-to-1' regressor and a set of `2-to-1' regressors, with a Selection Gate to select the most suitable `2-to-1' regressor and a gated fusion to combine the two kinds of regressors. Experiments on the MNR dataset show that the DARR outperforms state-of-the-art models for arithmetic visual reasoning.

Solving jigsaw puzzles has been extensively studied. While most existing models focus on solving either small-scale puzzles or puzzles with no gap between fragments, solving large-scale puzzles with gaps presents distinctive challenges in both image understanding and combinatorial optimization. To tackle these challenges, we propose a framework of Evolutionary Reinforcement Learning with Multi-head Puzzle Perception (ERL-MPP) to derive a better set of swapping actions for solving the puzzles. Specifically, to tackle the challenges of perceiving the puzzle with gaps, a Multi-head Puzzle Perception Network (MPPN) with a shared encoder is designed, where multiple puzzlet heads comprehensively perceive the local assembly status, and a discriminator head provides a global assessment of the puzzle. To explore the large swapping action space efficiently, an Evolutionary Reinforcement Learning (EvoRL) agent is designed, where an actor recommends a set of suitable swapping actions from a large action space based on the perceived puzzle status, a critic updates the actor using the estimated rewards and the puzzle status, and an evaluator coupled with evolutionary strategies evolves the actions aligning with the historical assembly experience. The proposed ERL-MPP is comprehensively evaluated on the JPLEG-5 dataset with large gaps and the MIT dataset with large-scale puzzles. It significantly outperforms all state-of-the-art models on both datasets.

Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the overall semantics of an entire motion sequence in just a few words. This limits their ability to handle fine-grained motion-relevant tasks, such as understanding and controlling the movements of specific body parts. To overcome this limitation, we pioneer MG-MotionLLM, a unified motion-language model for multi-granular motion comprehension and generation. We further introduce a comprehensive multi-granularity training scheme by incorporating a set of novel auxiliary tasks, such as localizing temporal boundaries of motion segments via detailed text as well as motion detailed captioning, to facilitate mutual reinforcement for motion-text modeling across various levels of granularity. Extensive experiments show that our MG-MotionLLM achieves superior performance on classical text-to-motion and motion-to-text tasks, and exhibits potential in novel fine-grained motion comprehension and editing tasks. Project page: CVI-SZU/MG-MotionLLM

Data-driven genetic programming (GP) has proven highly effective in solving combinatorial optimization problems under dynamic and uncertain environments. A central challenge lies in fast fitness evaluations on large training datasets, especially for complex real-world problems involving time-consuming simulations. Surrogate models, like phenotypic characterization (PC)-based K-nearest neighbors (KNN), have been applied to reduce computational cost. However, the PC-based similarity measure is confined to behavioral characteristics, overlooking genotypic differences, which can limit surrogate quality and impair performance. To address these issues, this paper proposes a pheno-geno unified surrogate GP algorithm, PGU-SGP, integrating phenotypic and genotypic characterization (GC) to enhance surrogate sample selection and fitness prediction. A novel unified similarity metric combining PC and GC distances is proposed, along with an effective and efficient GC representation. Experimental results of a real-life vehicle scheduling problem demonstrate that PGU-SGP reduces training time by approximately 76% while achieving comparable performance to traditional GP. With the same training time, PGU-SGP significantly outperforms traditional GP and the state-of-the-art algorithm on most datasets. Additionally, PGU-SGP shows faster convergence and improved surrogate quality by maintaining accurate fitness rankings and appropriate selection pressure, further validating its effectiveness.

Modern neural architecture search (NAS) is inherently multi-objective balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strategy with a heuristic rule based on model size. Integrated into a framework termed SiamNAS, this design eliminates costly evaluations during the search process. Experiments on NAS-Bench-201 demonstrate the framework's ability to identify Pareto-optimal solutions with significantly reduced computational costs. The proposed SiamNAS identified a final non-dominated set containing the best architecture in NAS-Bench-201 for CIFAR-10 and the second-best for ImageNet, in terms of test error rate, within 0.01 GPU days. This proof-of-concept study highlights the potential of the proposed Siamese network surrogate model to generalise to multi-tasking optimisation, enabling simultaneous optimisation across tasks. Additionally, it offers opportunities to extend the approach for generating Sets of Pareto Sets (SOS), providing diverse Pareto-optimal solutions for heterogeneous task settings.

Most existing models for abstract visual reasoning perform poorly in compositional visual reasoning (CVR), due to complex nature of compositional rules and difficulties in distinguishing tiny rule differences between outliers and normal images. To tackle the challenges, we propose a Dual-Branch Compositional Reasoning (DBCR) model, exploiting both intra-cluster relations among the cluster of normal images and extra-cluster relations between normal images and outliers. Specifically, we design one branch of Intra-Cluster Regression Reasoning Blocks (ICR2Bs) to encapsulate common relations among normal images through hierarchical regressing reasoning, and the other branch of Contrastive Attention Reasoning Blocks (CARBs) to exploit extra-cluster differences between normal images and outliers through self-attention. Simultaneously minimizing the regression errors in ICR2Bs and maximizing the extra-cluster differences in CARBs help identify the correct cluster of normal images. Experimental results on two CVR datasets show that the proposed DBCR consistently outperforms state-of-the-art models. The code is available at https://github.com/He1mont/DBCR.

Puzzle solving has recently become a popular research topic. Existing solvers often overlook puzzles with missing pieces. The missing pieces, together with gaps between pieces, pose significant challenges, amplified by a large solution space. To tackle the challenges, we propose Co-Evolutionary Agents for Reassembling and Inpainting (CEARI), one agent to inpaint missing contents and the other to reassemble the puzzle, with a shared perception network to perceive the puzzle status. The reassembly agent utilizes an evolutionary algorithm to explore the large solution space, to discover a sequence of fragment-swapping actions to efficiently reassemble the puzzle, while the inpainting agent evolves from using a local outpainting network at the early stage to using a global inpainting network at the latter stage. Furthermore, a co-evolutionary training paradigm is designed to iteratively evolve the two agents in a coherent and collaborative manner, improving reassembly accuracy and inpainting quality simultaneously. Experimental results on three datasets show that CEARI largely outperforms state-of-the-art methods in terms of both reassembly accuracy and inpainting quality.

Abstract Visual Reasoning (AVR) entails discerning latent patterns in visual data and inferring underlying rules. Existing solutions often lack scalability and adaptability, as deep architectures tend to overfit training data, and static neural networks fail to dynamically capture diverse rules. To tackle the challenges, we propose a Dynamic and Scalable Reasoning Framework (DSRF) that greatly enhances the reasoning ability by widening the network instead of deepening it, and dynamically adjusting the reasoning network to better fit novel samples instead of a static network. Specifically, we design a Multi-View Reasoning Pyramid (MVRP) to capture complex rules through layered reasoning to focus features at each view on distinct combinations of attributes, widening the reasoning network to cover more attribute combinations analogous to complex reasoning rules. Additionally, we propose a Dynamic Domain-Contrast Prediction (DDCP) block to handle varying task-specific relationships dynamically by introducing a Gram matrix to model feature distributions, and a gate matrix to capture subtle domain differences between context and target features. Extensive experiments on six AVR tasks demonstrate DSRF’s superior performance, achieving state-of-the-art results under various settings. Code is available here: https://github.com/UNNCRoxLi/DSRF.

Video-based gait recognition suffers from potential privacy issues and performance degradation due to dim environments, partial occlusions, or camera view changes. Radar has recently become increasingly popular and overcome various challenges presented by vision sensors. To capture tiny differences in radar gait signatures of different people, a dual-branch Swin Transformer is proposed, where one branch captures the time variations of the radar micro-Doppler signature and the other captures the repetitive frequency patterns in the spectrogram. Unlike natural images where objects can be translated, rotated, or scaled, the spatial coordinates of spectrograms and CVDs have unique physical meanings, and there is no affine transformation for radar targets in these synthetic images. The patch splitting mechanism in Vision Transformer makes it ideal to extract discriminant information from patches, and learn the attentive information across patches, as each patch carries some unique physical properties of radar targets. Swin Transformer consists of a set of cascaded Swin blocks to extract semantic features from shallow to deep representations, further improving the classification performance. Lastly, to highlight the branch with larger discriminant power, an Asymmetric Attention Fusion is proposed to optimally fuse the discriminant features from the two branches. To enrich the research on radar gait recognition, a large-scale NTU-RGR dataset is constructed, containing 45,768 radar frames of 98 subjects. The proposed method is evaluated on the NTU-RGR dataset and the MMRGait-1.0 database. It consistently and significantly outperforms all the compared methods on both datasets. The codes are available at: https://github.com/wentaoheunnc/NTU-RGR . • The proposed method could well extract complementary information from both spectrograms and CVDs. • The proposed Swin-T could extract discriminant features with physical meanings. • The proposed asymmetric attention fusion could effectively combine features with known importance. • A large-scale benchmark dataset, NTU-RGR dataset, is developed to advance the radar gait recognition.

Raven's Progressive Matrices (RPMs) are frequently used in evaluating human's visual reasoning ability. Researchers have made considerable efforts in developing systems to automatically solve the RPM problem, often through a black-box end-to-end convolutional neural network for both visual recognition and logical reasoning tasks. Based on the intrinsic natures of RPM problem, we propose a Two-stage Rule-Induction Visual Reasoner (TRIVR), which consists of a perception module and a reasoning module, to tackle the challenges of real-world visual recognition and subsequent logical reasoning tasks, respectively. For the reasoning module, we further propose a “2+1” formulation that models human's thinking in solving RPMs and significantly reduces the model complexity. It derives a reasoning rule from each RPM sample, which is not feasible for existing methods. As a result, the proposed reasoning module is capable of yielding a set of reasoning rules modeling human in solving the RPM problems. To validate the proposed method on real-world applications, an RPM-like Video Prediction (RVP) dataset is constructed, where visual reasoning is conducted on RPMs constructed using real-world video frames. Experimental results on various RPM-like datasets demonstrate that the proposed TRIVR achieves a significant and consistent performance gain compared with state-of-the-art models.

Deep Reinforcement Learning (DRL)-based Dynamic Voltage Frequency Scaling (DVFS) has shown great promise for energy conservation in embedded systems. While many works were devoted to validating its efficacy or improving its performance, few discuss the feasibility of the DRL agent deployment for embedded computing. State-of-the-art approaches focus on the miniaturization of agents’ inferential networks, such as pruning and quantization, to minimize their energy and resource consumption. However, this spatial-based paradigm still proves inadequate for resource-stringent systems. In this paper, we address the feasibility from a temporal perspective, where FiDRL, a flexible invocation-based DRL model is proposed to judiciously invoke itself to minimize the overall system energy consumption, given that the DRL agent incurs non-negligible energy overhead during invocations. Our approach is three-fold: (1) FiDRL that extends DRL by incorporating the agent's invocation interval into the action space to achieve invocation flexibility; (2) a FiDRL-based DVFS approach for both inter- and intra-task scheduling that minimizes the overall execution energy consumption; and (3) a FiDRL-based DVFS platform design and an on/off-chip hybrid algorithm specialized for training the DRL agent for embedded systems. Experiment results show that FiDRL achieves 55.1% agent invocation cost reduction, under 23.3% overall energy reduction, compared to state-of-the-art approaches.

Efficient truck dispatching is crucial for optimizing container terminal operations within dynamic and complex scenarios. Despite good progress being made recently with more advanced uncertainty-handling techniques, existing approaches still have generalization issues and require considerable expertise and manual interventions in algorithm design. In this work, we present deep reinforcement learning-assisted genetic programming hyper-heuristics (DRL-GPHH) and their ensemble variant (DRL-GPEHH). These frameworks utilize a reinforcement learning agent to orchestrate a set of auto-generated genetic programming (GP) low-level heuristics, leveraging the collective intelligence, ensuring advanced robustness and an increased level of automation of the algorithm development. DRL-GPEHH, notably, excels through its concurrent integration of a GP heuristic ensemble, achieving enhanced adaptability and performance in complex, dynamic optimization tasks. This method effectively navigates traditional convergence issues of deep reinforcement learning (DRL) in sparse reward and vast action spaces, while avoiding the reliance on expert-designed heuristics. It also addresses the inadequate performance of the single GP individual in varying and complex environments and preserves the inherent interpretability of the GP approach. Evaluations across various real port operational instances highlight the adaptability and efficacy of our frameworks. Essentially, innovations in DRL-GPHH and DRL-GPEHH reveal the synergistic potential of reinforcement learning and GP in dynamic truck dispatching, yielding transformative impacts on algorithm design and significantly advancing solutions to complex real-world optimization problems.

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods. Code is available at https://github.com/UNNC-CV/EvOD/.

In regression analysis, methodologies range from black-box approaches like artificial neural networks to white-box techniques like symbolic regression. Renowned for its trans-parency and interpretability, symbolic regression has become increasingly prominent in elucidating complex data relationships. Nevertheless, its effectiveness in managing complex piecewise symbolic regression tasks poses significant challenges. This paper introduces a novel Hierarchical Cooperative Genetic Program-ming (HCGP) framework to address this issue. The HCGP model utilizes a unique hierarchical structure, incorporating dual cooperative genetic programming (GP) populations. This innovative design significantly enhances the capability to solve complex piecewise symbolic regression problems. Implementing a scenario-based GP is central to the HCGP framework, which strategically selects the appropriate underlying calculation GP. This feature enables the system to autonomously learn and adapt to complex scenarios, selecting the most suitable calculation GPs for each case. Our HCGP approach distinguishes itself from traditional and state-of-the-art methods. It demonstrates particular proficiency in modeling piecewise expressions within complex scenarios. The empirical evaluation of our model, conducted using benchmark datasets, has exhibited its superior accuracy and computational efficiency. This progress emphasizes the potential of HCGP in sophisticated data modeling and marks a substantial advancement in a hierarchical structure in complex piecewise symbolic regression.

In the last decade, the surge in global container port throughput has heightened the need for terminal efficiency. The loading process plays a crucial role in overall port performance. However, the unpredictable arrival of external trucks poses challenges for yard cranes in scheduling both internal loading tasks and external truck tasks simultaneously. Existing approaches on yard crane scheduling, considering uncertain arrivals, typically rely on prior knowledge, which often fails to fully capture the nature of the real-life uncertainties. In response, we propose an online scheduling approach guided by a two-stage decision model, eliminating the need for prior knowledge of uncertain arrival and has the ability to dynamically adapt to different scenarios. In the look-ahead stage, future tasks are filtered dynamically to eliminate undesired tasks, followed by a priority rule guided selection stage, where the task with the highest priority is selected. Genetic Programming (GP) is employed for automated evolution of priority rules without human intervention. Realistic experiments showcase the effectiveness of the proposed dynamic look-ahead method compared to static minimum and maximum look-ahead, as well as the superiority of GP-evolved priority rules compared to manually crafted priority rules in terms of both performance and simplicity. A comprehensive analysis of GP-evolved rules highlights GP's proficiency in problem understanding and rule extraction, comparable to human experts.

The shift towards transportation electrification, marked by the rising use of electric vehicles (EVs) and the development of fast charging stations (FCS), plays a crucial role in transport decarbonization initiatives. To optimize the rollout of FCS and set appropriate charging service fees (CSF)-a process referred to as the coupled FCS multi-stage bi-level operation problem (FCS-MBOP)-is essential for improving both investment and operational efficiency within the integrated power distribution and transportation network (CPTN). For operators, it's not only necessary to adapt to short-term fluctuations within the environment but also to swiftly respond to changes in the FCS layout resulting from various long-term investment decisions. To address this complexity, we introduce a dual-timescale evolutionary assist deep reinforcement learning framework, which includes two specialized agents with distinct functions: an investment agent (planner) and an operational agent (operator). The planner focuses on annual investments, evolving long-term strategies that weigh social benefits against investment costs through the use of a genetic algorithm (GA). In contrast, the operator acts on an hourly basis, fine-tuning CSF to alleviate traffic congestion and minimize the social costs, while taking into account the planner's feasible investment decisions. Leveraging the integrated capabilities of a graph neural network (GNN), long-short-term memory (LSTM), and attention mechanisms, our framework's agents are adept at extracting both temporal and spatial features and facilitating the transfer of experiences across different investment stages. Empirical evidence underscores the effectiveness of our approach, showcasing its ability to surpass conventional methodologies in delivering high-quality solutions.

Deep learning has gained significant popularity in recent years, particularly for tasks like image and speech recognition, natural language processing, and other intricate pattern recognition challenges. However, training a deep learning model involves tuning millions or even billions of parameters. Consequently, this training process becomes a large-scale optimisation problem associated with a mostly unknown but highly non-convex fitness landscape. In recent decades, advances in fitness landscape analysis have revolved around characterizing landscapes representing loss functions, with Local Optima Networks (LONs) emerging as a promising tool. This paper, while focusing on LeNet-5, leverages LON to address four key questions concerning the nature of the learning problem. We emphasize the impact of experimental conditions during the analysis phase on drawing conclusions about the problem's nature. The results shed light on parametrization and optimiser selection to enhance the analysis and comprehension of deep learning loss landscapes. In particular, we identify the presence and number of funnels in the landscape's structure, study the impact of the dataset on the nature of the problem, investigate how the choice of local search optimisers may influence conclusions about the problem's structure. Finally, sensitivity analysis was conducted on the perturbation strength of the Basin-Hopping sampling method for LON construction.

Advances in computer vision research enable human-like high-dimensional perceptual induction over analogical visual reasoning problems, such as Raven's Progressive Matrices (RPMs). In this paper, we propose a Hierarchical Perception and Predictive Analogy-Inference network (HP^2AI), consisting of three major components that tackle key challenges of RPM problems. Firstly, in view of the limited receptive fields of shallow networks in most existing RPM solvers, a perceptual encoder is proposed, consisting of a series of hierarchically coupled Patch Attention and Local Context (PALC) blocks, which could capture local attributes at early stages and capture the global panel layout at deep stages. Secondly, most methods seek for object-level similarities to map the context images directly to the answer image, while failing to extract the underlying analogies. The proposed reasoning module, Predictive Analogy-Inference (PredAI), consists of a set of Analogy-Inference Blocks (AIBs) to model and exploit the inherent analogical reasoning rules instead of object similarity. Lastly, the Squeeze-and-Excitation Channel-wise Attention (SECA) in the proposed PredAI discriminates essential attributes and analogies from irrelevant ones. Extensive experiments over four benchmark RPM datasets show that the proposed HP^2AI achieves significant performance gains over all the state-of-the-art methods consistently on all four datasets.

Sequential decision making is an important part of robotic problems that is receiving unprecedented attention from both academia and industry. Recently, Deep Reinforcement Learning (DRL) has shown its promising capabilities in decision making problems. However, traditional DRL algorithms directly operate in the space of low-level actions, when it is applied in the domain of robotics, it can easily result in an exponential growth of computational complexity and suffer from the “curse of dimensionality”, becoming less efficient as the dimensionality of the environment increases. To address this issue, a novel DRL hyper-heuristic approach is proposed in this paper. The proposed approach is tailored to align with a problem taken from a real-world competition by taking advantage of well-developed low-level heuristic actions in order to narrow the search space and speed up the convergence. This fundamental contribution is a significant step forward from earlier approaches that directly exploit the entire low-level action domain. A state augmentation scheme and a novel reward design are utilized to further improve the performance of the proposed method. Moreover, a Real-to-Sim based training framework is developed to reduce the cost of acquiring real-time data and improve the robustness of agent’s decision-making model. Numerous experimental results demonstrate our proposed method can achieve notable performance gains compared to both competitive DRL baselines and heuristic approaches of the same problem in both known environment and previously unseen scenarios.

The online bin packing problem is a well-known optimization challenge that finds application in a wide range of real-world scenarios. In the paper, we propose a novel algorithm called FuzzyPatternPack(FPP), which leverages fuzzy inference and pattern-based predictions of the distribution of item sizes in online bin packing. In comparison to traditional heuristics like BestFit(BF) and FirstFit(FF), as well as the more recent PatternPack(PaP) and ProfilePacking(PrP) algorithm based on online predictions, FPP demonstrates competitive and superior performance in solving various benchmark problems. Particularly, it excels in addressing problems with evolving distributions, making it a promising solution for real-world applications where the item sizes may change over time. This research unveils the promising potential of employing fuzzy logic to effectively address uncertainty in scheduling and planning problems.

Although 2D radar signal representations, such as spectrograms and range-Doppler maps have been widely used for target recognition, 3D time-range-Doppler (TRD) has been less studied, partially because of the difficulties in extracting features from the TRD representation, i.e., shallow 3D neural networks have limited discriminant power, but repeatedly applying 3D convolutions will lead to an oversized 3D network. A hybrid 3D–2D network architecture, Progressively-Orthogonally-Mapped EfficientNet (POMEN), is proposed to address these challenges. More specifically, the proposed POMEN utilizes 3D convolutions in the earlier stages to capture the information embedded in the sparse 3D TRD representation, and to avoid the oversized feature map caused by excessively applying 3D convolutions, we propose to progressively map the 3D features into three sets of 2D features corresponding to the range-time signature, range-Doppler map and time-Doppler signature (spectrogram), respectively. Subsequently, 2D EfficientNet blocks were designed to extract discriminant information from the three sets of 2D feature maps. This hybrid 3D–2D network design effectively extracts features from the 3D TRD representation, thereby avoiding oversized features from full-sized 3D networks and the information loss of 2D networks on 2D representations. Finally, a homogeneous gated fusion network was designed to fuse the three sets of 2D features. The proposed method was evaluated on the UGRS, MIMOGR, and mmWRWD datasets. The experimental results for all datasets demonstrate that the proposed POMEN significantly and consistently outperforms the state-of-the-art models in both 2D and 3D representations.

In many classification models, data is discretized to better estimate its distribution. Existing discretization methods often target at maximizing the discriminant power of discretized data, while overlooking the fact that the primary target of data discretization in classification is to improve the generalization performance. As a result, the data tend to be over-split into many small bins since the data without discretization retain the maximal discriminant information. Thus, we propose a Max-Dependency-Min-Divergence (MDmD) criterion that maximizes both the discriminant information and generalization ability of the discretized data. More specifically, the Max-Dependency criterion maximizes the statistical dependency between the discretized data and the classification variable while the Min-Divergence criterion explicitly minimizes the JS-divergence between the training data and the validation data for a given discretization scheme. The proposed MDmD criterion is technically appealing, but it is difficult to reliably estimate the high-order joint distributions of attributes and the classification variable. We hence further propose a more practical solution, Max-Relevance-Min-Divergence (MRmD) discretization scheme, where each attribute is discretized separately, by simultaneously maximizing the discriminant information and the generalization ability of the discretized data. The proposed MRmD is compared with the state-of-the-art discretization algorithms under the naive Bayes classification framework on 45 benchmark datasets. It significantly outperforms all the compared methods on most of the datasets.

The segmentation of blurred cell boundaries in cornea endothelium microscope images is challenging, which affects the clinical parameter estimation accuracy. Existing deep learning methods only consider pixel-wise classification accuracy and lack of utilization of cell structure knowledge. Therefore, the segmentation of the blurred cell boundary is discontinuous. This paper proposes a structural prior guided network (SPG-Net) for corneal endothelium cell segmentation. We first employ a hybrid transformer convolution backbone to capture more global context. Then, we use Feature Enhancement (FE) module to improve the representation ability of features and Local Affinity-based Feature Fusion (LAFF) module to propagate structural information among hierarchical features. Finally, we introduce the joint loss based on cross entropy and structure similarity index measure (SSIM) to supervise the training process under pixel and structure levels. We compare the SPG-Net with various state-of-the-art methods on four corneal endothelial datasets. The experiment results suggest that the SPG-Net can alleviate the problem of discontinuous cell boundary segmentation and balance the pixel-wise accuracy and structure preservation. We also evaluate the agreement of parameter estimation between ground truth and the prediction of SPG-Net. The statistical analysis results show a good agreement and correlation.

Raven’s Progressive Matrices (RPMs) have been widely used to evaluate the visual reasoning ability of humans. To tackle the challenges of visual perception and logic reasoning on RPMs, we propose a Hierarchical ConViT with Attention-based Relational Reasoner (HCV-ARR). Traditional solution methods often apply relatively shallow convolution networks to visually perceive shape patterns in RPM images, which may not fully model the long-range dependencies of complex pattern combinations in RPMs. The proposed ConViT consists of a convolutional block to capture the low-level attributes of visual patterns, and a transformer block to capture the high-level image semantics such as pattern formations. Furthermore, the proposed hierarchical ConViT captures visual features from multiple receptive fields, where the shallow layers focus on the image fine details while the deeper layers focus on the image semantics. To better model the underlying reasoning rules embedded in RPM images, an Attention-based Relational Reasoner (ARR) is proposed to establish the underlying relations among images. The proposed ARR well exploits the hidden relations among question images through the developed element-wise attentive reasoner. Experimental results on three RPM datasets demonstrate that the proposed HCV-ARR achieves a significant performance gain compared with the state-of-the-art models. The source code is available at: https://github.com/wentaoheunnc/HCV-ARR.

Jigsaw puzzle solving has recently become an emerging research area. The developed techniques have been widely used in applications beyond puzzle solving. This paper focuses on solving Jigsaw Puzzles with Large Eroded Gaps (JPwLEG). We formulate the puzzle reassembly as a combinatorial optimization problem and propose a Siamese-Discriminant Deep Reinforcement Learning (SD2RL) to solve it. A Deep Q-network (DQN) is designed to visually understand the puzzles, which consists of two sets of Siamese Discriminant Networks, one set to perceive the pairwise relations between vertical neighbors and another set for horizontal neighbors. The proposed DQN considers not only the evidence from the incumbent fragment but also the support from its four neighbors. The DQN is trained using replay experience with carefully designed rewards to guide the search for a sequence of fragment swaps to reach the correct puzzle solution. Two JPwLEG datasets are constructed to evaluate the proposed method, and the experimental results show that the proposed SD2RL significantly outperforms state-of-the-art methods.

Solving Jigsaw puzzles has recently become an emerging research topic. Traditionally, boundary similarities are utilized for puzzle reassembly. In this paper, we solve Jigsaw Puzzles of Large Eroded Gaps (JPLEG), where boundary similarities are weak and image semantics are the only feasible clues. Inspired by human strategy in solving a puzzle, we introduce the concept of puzzlet, where fragments are gradually combined to form puzzlets of different sizes until the completion of the puzzle. Two sets of Puzzlet Discriminant Networks are designed to visually perceive whether these puzzlets are correctly reassembled. The puzzle reassembly is then formulated as a combinatorial optimization problem, and solved using a genetic algorithm. The proposed method is evaluated on two large datasets, which shows that it significantly outperforms the state-of-the-art methods for puzzle solving.

In recent years, deep reinforcement learning has shown great potential in solving computer games with sequential decision-making scenarios. Hyper-heuristic is a generic search framework, capable of intelligently selecting or generating algorithms to solve a class of optimisation problems with stochastic or dynamic settings. This paper proposes a new general framework for solving online packing problems using deep reinforcement learning hyper-heuristics. Although analytical approaches can address most offline packing problems successfully, their online versions have proved much more challenging and the performance of the existing methods is often not satisfactory. In this paper, we extend a recent deep reinforcement learning hyper-heuristic framework by fusing the visual information of real-time packing with distributional information of random parameters of the problem. Computational experiments show that our method outperforms the state of the art online methods with reductions in optimality gap between 2%–19% for knapsack problem and 0.7% for the online strip packing problem. In addition, a new visual analysis presentation is also devised to better interpret the learned packing strategies, which can reveal more information than the widely used landscape analysis. As online packing problems are widely available in production environments, the proposed approach can serve as an important reference to solve other similar combinatorial optimisation problems for which visual layout inputs would aid learning.

Recently, many improved naive Bayes methods have been developed with enhanced discrimination capabilities. Among them, regularized naive Bayes (RNB) produces excellent performance by balancing the discrimination power and generalization capability. Data discretization is important in naive Bayes. By grouping similar values into one interval, the data distribution could be better estimated. However, existing methods including RNB often discretize the data into too few intervals, which may result in a significant information loss. To address this problem, we propose a semi-supervised adaptive discriminative discretization framework for naive Bayes, which could better estimate the data distribution by utilizing both labeled data and unlabeled data through pseudo-labeling techniques. The proposed method also significantly reduces the information loss during discretization by utilizing an adaptive discriminative discretization scheme, and hence greatly improves the discrimination power of classifiers. The proposed RNB+, i.e., regularized naive Bayes utilizing the proposed discretization framework, is systematically evaluated on a wide range of machine-learning datasets. It significantly and consistently outperforms state-of-the-art NB classifiers.

In a marine container terminal, truck dispatching is a crucial problem that impacts the operation efficiency of the whole port. Traditionally, this problem is formulated as an offline optimization problem, whose solutions are, however, impractical for most real-world scenarios primarily because of the uncertainties of dynamic events in both yard operations and seaside loading–unloading operations. These solutions are either unattractive or infeasible to execute. Herein, for more intelligent handling of these uncertainties and dynamics, a novel cooperative double-layer genetic programming hyper-heuristic (CD-GPHH) is proposed to tackle this challenging online optimization problem. In this new CD-GPHH, a novel scenario genetic programming (GP) approach is added on top of a traditional GP method that chooses among different GP heuristics for different scenarios to facilitate optimized truck dispatching. In contrast to traditional arithmetic GP (AGP) and GP with logic operators (LGP) which only evolve on one population, our CD-GPHH method separates the scenario and the calculation into two populations, which improved the quality of solutions in multiscenario problems while reducing the search space. Experimental results show that our CD-GPHH dominates AGP and LGP in solving a multiscenario function fitting problem as well as a truck dispatching problem in a container terminal.

Detecting 3D mask attacks to a face recognition system is challenging. Although genuine faces and 3D face masks show significantly different remote photoplethysmography (rPPG) signals, rPPG-based face anti-spoofing methods often suffer from performance degradation due to unstable face alignment in the video sequence and weak rPPG signals. To enhance the rPPG signal in a motion-robust way, a landmark-anchored face stitching method is proposed to align the faces robustly and precisely at the pixel-wise level by using both SIFT keypoints and facial landmarks. To better encode the rPPG signal, a weighted spatial-temporal representation is proposed, which emphasizes the face regions with rich blood vessels. In addition, characteristics of rPPG signals in different color spaces are jointly utilized. To improve the generalization capability, a lightweight EfficientNet with a Gated Recurrent Unit (GRU) is designed to extract both spatial and temporal features from the rPPG spatial-temporal representation for classification. The proposed method is compared with the state-of-the-art methods on five benchmark datasets under both intra-dataset and cross-dataset evaluations. The proposed method shows a significant and consistent improvement in performance over other state-of-the-art rPPG-based methods for face spoofing detection.

A competitive traveling salesmen problem is a variant of traveling salesman problem in that multiple agents compete with each other in visiting a number of cities. The agent who is the first one to visit a city will receive a reward. Each agent aims to collect as more rewards as possible with the minimum traveling distance. There is still not effective algorithms for this complicated decision making problem. We investigate an improved ant colony approach for the competitive traveling sales-men problem which adopts a time dominance mechanism and a revised pheromone depositing method to improve the quality of solutions with less computational complexity. Simulation results show that the proposed algorithm outperforms the state of art algorithms.

Naive Bayes has been widely used in many applications because of its simplicity and ability in handling both numerical data and categorical data. However, lack of modeling of correlations between features limits its performance. In addition, noise and outliers in the real-world dataset also greatly degrade the classification performance. In this paper, we propose a feature augmentation method employing a stack auto-encoder to reduce the noise in the data and boost the discriminant power of naive Bayes. The proposed stack auto-encoder consists of two auto-encoders for different purposes. The first encoder shrinks the initial features to derive a compact feature representation in order to remove the noise and redundant information. The second encoder boosts the discriminant power of the features by expanding them into a higher-dimensional space so that different classes of samples could be better separated in the higher-dimensional space. By integrating the proposed feature augmentation method with the regularized naive Bayes, the discrimination power of the model is greatly enhanced. The proposed method is evaluated on a set of machine-learning benchmark datasets. The experimental results show that the proposed method significantly and consistently outperforms the state-of-the-art naive Bayes classifiers.

Face spoofing detection against paper attack and video-replay attack has been well studied, whereas detecting 3D face mask attack remains challenging. Remote photoplethysmography (rPPG) signal is a recently developed liveness clue for face-spoofing detection. The main challenge of existing rPPG-based methods is that the signal can be easily distorted by background noise or object motion. To address this problem, in this work, we propose an rPPG-based face-spoofing detection method using multiple regions of interests (ROIs) covering entire face, and emphasize the regions containing richer rPPG signals using larger weights. The rPPG signals of these regions form a weighted spatial-temporal map. In view of the discriminant power of EfficientNet over other deep convolutional neural networks, we propose a domain-specific EfficientNet as the classification method. Extensive experiments on two databases namely 3DMAD and HKBU-Mars V2 demonstrate the superior performance of the proposed method over state-of-the-art rPPG-based face-spoofing-detection algorithms.

Particle filter (PF) has been widely used in the target state and position estimations owing to its superiority in tackling the complicated nonlinear problems with arbitrary distributions. As an advanced PF algorithm, Sequential Importance Resampling (SIR) has been widely used for indoor positioning. Since the proposal density of SIR is independent of measurement, the algorithm is vulnerable to outliers. Although the Auxiliary SIR (ASIR) overcomes this problem by performing a two-stage sampling, its positioning accuracy is degraded when the process noise in the filter is large. In order to tackle this problem, an improved ASIR named evolutionary-strategy-integrated ASIR algorithm (EASIR) is proposed in this paper for accuracy improvement in indoor positioning. Tests are carried out for assessing the positioning performance of the proposed algorithm, and positioning accuracy and computation efficiency are considered as the performance metrics in the assessment. Comparing with the SIR and ASIR, the results show that the EASIR achieves better positioning accuracy when the same number of particles are used for data processing and has better robustness when the process noise in the filter is large. Moreover, the computation efficiency of EASIR is generally affordable for real-time applications.

International and domestic maritime trade has been expanding dramatically in the last few decades, seaborne container transportation has become an indispensable part of maritime trade efficient and easy-to-use containers. As an important hub of container transport, container terminals use a range of metrics to measure their efficiency, among which the hourly container throughput (i.e., the number of twentyfoot equivalent unit containers, or TEUs) is the most important objective to improve. This paper proposes a genetic programming approach to build a dynamic truck dispatching system trained on real-world stochastic operations data. The experimental results demonstrated the superiority of this dynamic approach and the potential for practical applications.

In medical fields, text classification is one of the most important tasks that can significantly reduce human work-load through structured information digitization and intelligent decision support. Despite the popularity of learning-based text classification techniques, it is hard for human to understand or manually fine-tune the classification for better precision and recall, due to the black box nature of learning. This study proposes a novel regular expression-based text classification method making use of genetic programming (GP) approaches to evolve regular expressions that can classify a given medical text inquiry with satisfaction. Given a seed population of regular expressions (randomly initialized or manually constructed by experts), our method evolves a population of regular expressions, using a novel regular expression syntax and a series of carefully chosen reproduction operators. Our method is evaluated with real-life medical text inquiries from an online healthcare provider and shows promising performance. More importantly, our method generates classifiers that can be fully understood, checked and updated by medical doctors, which are fundamentally crucial for medical related practices.

Global positioning system (GPS) data generated from taxi trips is a valuable source of information that offers an insight into travel behaviours of urban populations with high spatio-temporal resolution. However, in its raw form, GPS taxi data does not offer information on the purpose (or intended activity) of travel. In this context, to enhance the utility of taxi GPS data sets, we propose a two-layer framework to identify the related activities of each taxi trip automatically and estimate the return trips and successive activities after the trip, by using geographic point-of-interest (POI) data and a combination of spatio-temporal clustering, Bayesian inference and Monte Carlo simulation. Two million taxi trips in New York, the United States of America, and ten million taxi trips in Shenzhen, China, are used as inputs for the two-layer framework. To validate each layer of the framework, we collect 6,003 trip diaries in New York and 712 questionnaire surveys in Shenzhen. The results show that the first layer of the framework performs better than comparable methods published in the literature, while the second layer has high accuracy when inferring return trips.

Internet hospital is a rising business thanks to recent advances in mobile web technology and high demand of health care services. Online medical services become increasingly popular and active. According to US data in 2018, 80 percent of internet users have asked health-related questions online. Numerous data is generated in unprecedented speed and scale. Those representative questions and answers in medical fields are valuable raw data sources for medical data mining. Automated machine interpretation on those sheer amount of data gives an opportunity to assist doctors to answer frequently asked medical-related questions from the perspective of information retrieval and machine learning approaches. In this work, we propose a novel two-stage framework for the semantic matching of query-level medical questions, which takes advantages of sentence similarity-based search engine techniques and Siamese inspired recent recurrent neural network. The two-stage hierarchical design optimises the performance of automatic information retrieval of user queries. Compared against the classical TFIDF search technique as a single-stage, our novel soft search technique performs significantly better. Incorporating an advanced deep learning model as the second stage can improve the results further, which we believe is the new state-of-the-art in the current problem setting with the unique medical corpus from one of the largest online healthcare provider in market.

Recognizing continuous human action is a fundamental task in many real-world computer vision applications including video surveillance, video retrieval, and human-computer interaction, etc. It requires to recognize each action performed as well as their segmentation boundaries in a continuous sequence. In previous works, great progress has been reported for single action recognition, by using deep convolutional networks. In order to further improve the performance for continuous action recognition, in this paper, we introduce a discriminative approach consisting of three modules. The first feature extraction module uses a two stream Convolutional Neural Network to capture the appearance and the short-term motion information from the raw video input. Based on the obtained features, the second classification module performs spatial and temporal recognition and then fuses the two scores from respective feature stream. In the final segmentation module, a semi-Markov Conditional Field model, capable of handling long-term action interactions, is built to partition the action sequence. As can be seen in the experimental results, our approach obtains state-of-the-art performance on public datasets including 50Salads, Breakfast, and MERL Shopping. We have also visualized the continuous actions segmentation results for more insightful discussion in the paper.

In this paper, a Mixed-Shift Vehicle Routing Problem is proposed based on a real-life container transportation problem. In a long planning horizon of multiple shifts, transport tasks are completed satisfying the time constraints. Due to the different travel distances and time of tasks, there are two types of shifts ( long shift and short shift ) in this problem. The unit driver cost for long shifts is higher than that of short shifts . A mathematical model of this Mixed-Shift Vehicle Routing Problem with Time Windows (MS-VRPTW) is established in this paper, with two objectives of minimizing the total driver payment and the total travel distance. Due to the large scale and nonlinear constraints, the exact search showed is not suitable to MS-VRPTW. An initial solution construction heuristic (EBIH) and a selective perturbation Hyper-Heuristic (GIHH) are thus developed. In GIHH, five heuristics with different extents of perturbation at the low level are adaptively selected by a high level selection scheme with the Hill Climbing acceptance criterion. Two guidance indicators are devised at the high level to adaptively adjust the selection of the low level heuristics for this bi-objective problem. The two indicators estimate the objective value improvement and the improvement direction over the Pareto Front, respectively. To evaluate the generality of the proposed algorithms, a set of benchmark instances with various features is extracted from real-life historical datasets. The experiment results show that GIHH significantly improves the quality of the final Pareto Solution Set, outperforming the state-of-the-art algorithms for similar problems. Its application on VRPTW also obtains promising results.

Travel time prediction is important for freight transportation companies. Accurate travel time prediction can help these companies make better planning and task scheduling. For several reasons, most companies are not able to obtain traffic flow data from traffic management authorities, but a large amount of trajectory data were collected everyday which has not been fully utilised. In this study, we aim to fill this gap and performed travel time predictions for freight vehicles at individual level using Gradient Boosting Regression Tree (GBRT) models. All the features were extracted or composed from vehicles' temporally sparse trajectory data. Three routes were selected for the prediction experiments. Bayesian optimisation was adopted for model fitting while the results show that both pre-start (before trip starts) and post-start (after trip starts) predictions accuracies reach above 80%. The results also show that the prediction performance can be gradually improved by adding more mean speed estimates of traveled distance from the first 5 minutes as the real-time information. And the prediction performance can be further improved by about 2% by adding more mean speed estimates even if an unusual and non-recurring events occurred at a location of a route segment. This study shows the feasibility of both pre-start and continuous post-start prediction with limited amount of temporally sparse trajectory data for real-world practice.

The Vehicle Routing Problem with Time Windows (VRPTW) consists of constructing least cost routes from a depot to a set of geographically scattered service points and back to the depot, satisfying service time interval and capacity constraints. A Variable Neighbourhood Search algorithm with Compound Neighbourhoods is proposed to solve VRPTW in this paper. A number of independent neighbourhood operators are composed into compound neighbourhood operators in a new way, to explore wider search area concerning two objectives (to minimize the number of vehicles and the total travel distance) simultaneously. Promising results are obtained on benchmark datasets

Portfolio optimization is one of the most important problems in the finance field. The traditional mean-variance model has its drawbacks since it fails to take the market uncertainty into account. In this work, we investigate a two-stage stochastic portfolio optimization model with a comprehensive set of real world trading constraints in order to capture the market uncertainties in terms of future asset prices. A hybrid approach, which integrates genetic algorithm (GA) and a linear programming (LP) solver is proposed in order to solve the model, where GA is used to search for the assets selection heuristically and the LP solver solves the corresponding sub-problems of weight allocation optimally. Scenarios are generated to capture uncertain prices of assets for five benchmark market instances. The computational results indicate that the proposed hybrid algorithm can obtain very promising solutions. Possible future research directions are also discussed.

Swarm intelligence suffers the premature convergence, which happens partially due to the solutions getting clustered together, and not diverging again. The brain storm optimization (BSO), which is a young and promising algorithm in swarm intelligence, is based on the collective behavior of human being, that is, the brainstorming process. Premature convergence also happens in the BSO algorithm. The solutions get clustered after a few iterations, which indicate that the population diversity decreases quickly during the search. A definition of population diversity in BSO algorithm to measure the change of solutions' distribution is proposed in this paper. The algorithm's exploration and exploitation ability can be measured based on the change of population diversity. Two kinds of partial re-initialization strategies are utilized to improve the population diversity in BSO algorithm. The experimental results show that the performance of the BSO is improved by these two strategies.

Portfolio optimization is an important problem based on the modern portfolio theory (MPT) in the finance field. The idea is to maximize the portfolio expected return as well as minimizing portfolio risk at the same time. In this work, we propose a combinatorial algorithm for the portfolio optimization problem with the cardinality and bounding constraints. The proposed algorithm hybridizes a metaheuristic approach (particle swarm optimization, PSO) and a mathematical programming method where PSO is used to deal with the cardinality constraints and the math programming method is used to deal with the rest of the model. Computational results are given for the benchmark datasets from the OR-library and they indicate that it is a useful strategy for this problem. We also present the solutions obtained by the CPLEX mixed integer program solver for these instances and they can be used as the criteria for the comparison of algorithms for the same problem in the future.

Recent changes in the assessment and management of risks has had the effect that greater importance has been placed on relationships between individuals and within groups to inform decision making. In this paper, we provide the theoretical underpinning for an expected utility approach to decision-making. The approach, which is presented using established evidence support logic (TESLA™), integrating the expected utilities in the forming of group decisions. The rationale and basis are described and illustrated through a hypothetical decision context of options for the disposal of animal carcasses that accumulate during disease outbreaks. The approach forms the basis for exploring the richness of risk-based decisions, and representing individual beliefs about the sufficiency of evidence they may advance in support of hypotheses.

Nurse rostering is an important search problem with many constraints. In the literature, a number of approaches have been investigated including penalty function methods to tackle these constraints within genetic algorithm frameworks. In this paper, we investigate an extension of a previously proposed stochastic ranking method, which has demonstrated superior performance to other constraint handling techniques when tested against a set of constrained optimization benchmark problems. An initial experiment on nurse rostering problems demonstrates that the stochastic ranking method is better at finding feasible solutions, but fails to obtain good results with regard to the objective function. To improve the performance of the algorithm, we hybridize it with a recently proposed simulated annealing hyper-heuristic (SAHH) within a local search and genetic algorithm framework. Computational results show that the hybrid algorithm performs better than both the genetic algorithm with stochastic ranking and the SAHH alone. The hybrid algorithm also outperforms the methods in the literature which have the previously best known results.

Asignificant amount of work has investigated inventory control problems associated with fresh produce. Much of this work has considered deteriorating inventory control with many models having been proposed for various situations. However, no researchers have specifically studied fresh produce, which has its own special characteristics. Most research categorizes fresh produce into more general deteriorating categories with random lifetimes and nondecaying utilities. However, this classification is not reasonable or practical because the freshness of an item usually plays an important role in influencing the demand for the produce. In this paper, a single-period inventory and shelf-space allocation model is proposed for fresh produce. These items usually have a very short lifetime. The demand rate is assumed to be deterministic and dependent on both the displayed inventory (the number of facings of items on the shelves) and the items' freshness condition (which decreases over time). Several problem instances of different sizes are provided and solved by a modified generalized reduced gradient algorithm.