Search Results (23)

Inspired by real-world logistics scenarios, in this paper, we introduce a new variant of the Orienteering Problem known as the Multi-zone Orienteering Problem with Time Windows (MzOPTW). In the MzOPTW, customers are situated in distinct zones, each with multiple entrances and exits. Each customer has specific time window requirements; access to them will generate certain profits. This problem is to simultaneously determine which zones and customers to visit, select the zonal entrances and exits, and generate the routes for visiting each zone and its customers, all while maximizing total profits within a limited time frame. To tackle the MzOPTW, this paper develops an integer programming model. There are significant computational challenges in the strong interdependencies among zone selection, customer selection within zones, entrance and exit selection for each zone, the sequence of visits to zones and customers, and arrival and stay times. To address these challenges, this paper proposes a learning-enhanced metaheuristic algorithm called the Hybrid Ant Colony Optimization (HACO) algorithm, which incorporates Pointer Network learning. The HACO algorithm combines the global search capabilities of a population-based algorithm with the parallel decision-making abilities of the Pointer Network learning model. Additionally, a method to optimize zonal stay time limits is proposed to further enhance the solution. Experimental results demonstrate that the HACO algorithm outperforms comparative algorithms, achieving better solutions in 73% of the instances within the same time frame. Furthermore, the proposed optimization method for zonal stay time limits results in improvements in 78% of instances. Full article

In the context of China’s accelerating maritime judicial digitization, automatic summarization of lengthy and terminology-rich judgment documents has become a critical need for improving legal efficiency. Focusing on the task of automatic summarization for Chinese maritime judgment documents, we propose HybridSumm, an “extraction–abstraction” hybrid summarization framework that integrates a maritime judgment lexicon to address the unique characteristics of maritime legal texts, including their extended length and dense domain-specific terminology. First, we construct a specialized maritime judgment lexicon to enhance the accuracy of legal term identification, specifically targeting the complexity of maritime terminology. Second, for long-text processing, we design an extractive summarization model that integrates the RoBERTa-wwm-ext pre-trained model with dilated convolutional networks and residual mechanisms. It can efficiently identify key sentences by capturing both local semantic features and global contextual relationships in lengthy judgments. Finally, the abstraction stage employs a Nezha-UniLM encoder–decoder architecture, augmented with a pointer–generator network (for out-of-vocabulary term handling) and a coverage mechanism (to reduce redundancy), ensuring that summaries are logically coherent and legally standardized. Experimental results show that HybridSumm’s lexicon-guided two-stage framework significantly enhances the standardization of legal terminology and semantic coherence in long-text summaries, validating its practical value in advancing judicial intelligence development. Full article

In practical applications, the clarity of analog dial images is often compromised due to factors such as lighting conditions, leading to low precision and poor segmentation of dial scales and pointers. This results in segmentation outcomes that fail to meet the real-time requirements of substation inspection systems. To address these challenges, we propose an improved U-Net segmentation algorithm. The key innovation of our approach is the insertion of a layer-hopping connection module between the Encoder and Decoder to capture feature information across multiple scales, enhancing semantic expressiveness and optimizing feature fusion. Additionally, we replace traditional convolution operations with wavelet convolution, which improves the network’s ability to capture low-frequency information, essential for understanding the overall dial structure. An adaptive attention mechanism is also incorporated in the upsampling stage of the network, enabling the model to dynamically focus on salient features, further improving generalization. These improvements enable the network to more accurately detect target regions within dial images, significantly enhancing segmentation accuracy and robustness. Experimental results demonstrate that the proposed method outperforms traditional U-Net models in segmentation tasks, achieving superior precision in segmenting scales and pointers, effectively addressing issues of low precision and poor segmentation, and making it suitable for real-time substation inspection systems. Full article

In real-world logistics scenarios, the complexities often surpass what traditional Capacitated Vehicle Routing Problem (CVRP) models can effectively address. For instance, when there is an excess of goods and limited vehicles, traditional CVRP models frequently fail to yield feasible solutions. Additionally, the time sensitivity of goods and the large scale of vehicles and goods in practical logistics scenarios present significant challenges for efficient problem-solving. This underscores the urgent need to develop a novel CVRP model that is better suited for logistics scenarios and enhances the scalability of CVRP. To address these limitations, we propose a flexible CVRP model, referred to as Flexible CVRP, which modifies the optimization objectives and constraints. This allows CVRP to provide a sensible solution even when no feasible solution exists in the traditional sense. To tackle the challenges posed by large-scale problems, we leverage the Memory Pointer Network (MemPtrN). This approach enables the modeling of solution strategies, offering strong generalization capabilities and mitigating the explosive growth in complexity to some extent. Compared to commonly used heuristic algorithms, our method achieves superior solution quality for large-scale problems. Specifically, when addressing large-scale scenarios, the MemPtrN outperforms Google’s OR-Tools solver, heuristic algorithms, enhanced evolutionary algorithms, and other reinforcement learning methods in terms of both solution speed and quality. Full article

With the rapid increase in the number of Earth Observation Satellites (EOSs), research on autonomous mission scheduling has become increasingly critical for optimizing satellite sensor operations. While most existing studies focus on static environments or initial planning states, few address the challenge of dynamic request replanning for real-time sensor management. In this paper, we tackle the problem of multi-satellite rapid mission replanning under dynamic batch-arrival observation requests. The objective is to maximize overall observation revenue while minimizing disruptions to the original scheme. We propose a framework that integrates stochastic master-satellite mission allocation with single-satellite replanning, supported by reactive scheduling policies trained via deep reinforcement learning. Our approach leverages mission sequence modeling with attention mechanisms and time-attitude-aware rotary positional encoding to guide replanning. Additionally, scalable embeddings are employed to handle varying volumes of dynamic requests. The mission allocation phase efficiently generates assignment solutions using a pointer network, while the replanning phase introduces a hybrid action space for direct task insertion. Both phases are formulated as Markov Decision Processes (MDPs) and optimized using the PPO algorithm. Extensive simulations demonstrate that our method significantly outperforms state-of-the-art approaches, achieving a 15.27% higher request insertion revenue rate and a 3.05% improvement in overall mission revenue rate, while maintaining a 1.17% lower modification rate and achieving faster computational speeds. This demonstrates the effectiveness of our approach in real-world satellite sensor applications. Full article

Combinatorial optimization on temporal graphs is critical for summarizing dynamic networks in various fields, including transportation, social networks, and biology. Among these problems, the Minimum Timeline Cover (MinTCover) problem, aimed at identifying minimal activity intervals for representing temporal interactions, remains underexplored in the context of advanced machine learning techniques. Existing heuristic and approximate methods, while effective in certain scenarios, struggle with capturing complex temporal dependencies and scalability in dense, large-scale networks. Addressing this gap, this paper introduces DLMinTC+, a novel deep learning-based algorithm for solving the MinTCover problem. The proposed method integrates Graph Neural Networks for structural embedding, Transformer-based temporal encoding, and Pointer Networks for activity interval selection, coupled with an iterative adjustment algorithm to ensure valid solutions. Key contributions include (i) demonstrating the efficacy of deep learning for temporal combinatorial optimization, achieving superior accuracy and efficiency over state-of-the-art heuristics, and (ii) advancing the analysis of temporal knowledge graphs by incorporating robust, time-sensitive embeddings. Extensive evaluations on synthetic and real-world datasets highlight DLMinTC+’s ability to achieve significant coverage size reduction while maintaining generalization, offering a scalable and precise solution for complex temporal networks. Full article

To address the issue of efficiently reusing the massive amount of unstructured knowledge generated during the handling of track circuit equipment faults and to automate the construction of knowledge graphs in the railway maintenance domain, it is crucial to leverage knowledge extraction techniques to efficiently extract relational triplets from fault maintenance text data. Given the current lag in joint extraction technology within the railway domain and the inefficiency in resource utilization, this paper proposes a joint extraction model for track circuit entities and relations, integrating Global Pointer and tensor learning. Taking into account the associative characteristics of semantic relations, the nesting of domain-specific terms in the railway sector, and semantic diversity, this research views the relation extraction task as a tensor learning process and the entity recognition task as a span-based Global Pointer search process. First, a multi-layer dilate gated convolutional neural network with residual connections is used to extract key features and fuse the weighted information from the 12 different semantic layers of the RoBERTa-wwm-ext model, fully exploiting the performance of each encoding layer. Next, the Tucker decomposition method is utilized to capture the semantic correlations between relations, and an Efficient Global Pointer is employed to globally predict the start and end positions of subject and object entities, incorporating relative position information through rotary position embedding (RoPE). Finally, comparative experiments with existing mainstream joint extraction models were conducted, and the proposed model’s excellent performance was validated on the English public datasets NYT and WebNLG, the Chinese public dataset DuIE, and a private track circuit dataset. The F1 scores on the NYT, WebNLG, and DuIE public datasets reached 92.1%, 92.7%, and 78.2%, respectively. Full article

In recent years, as cybersecurity threats have become increasingly severe and cyberattacks have occurred frequently, higher requirements have been put forward for cybersecurity protection. Therefore, the Named Entity Recognition (NER) technique, which is the cornerstone of Cyber Threat Intelligence (CTI) analysis, is particularly important. However, most existing NER studies are limited to recognizing single-layer flat entities, ignoring the possible nested entities in CTI. On the other hand, most of the existing studies focus on English CTIs, and the existing models performed poorly in a limited number of Chinese CTI studies. Given the above challenges, we propose in this paper a novel unified model, RBTG, which aims to identify flat and nested entities in Chinese CTI effectively. To overcome the difficult boundary recognition problem and the direction-dependent and distance-dependent properties in Chinese CTI NER, we use Global Pointer as the decoder and TENER as the encoder layer, respectively. Specifically, the Global Pointer layer solves the problem of the insensitivity of general NER methods to entity boundaries by utilizing the relative position information and the multiplicative attention mechanism. The TENER layer adapts to the Chinese CTI NER task by introducing an attention mechanism with direction awareness and distance awareness. Meanwhile, to cope with the complex feature capture of hierarchical structure and dependencies among Chinese CTI nested entities, the TENER layer solves the problem by following the structure of multiple self-attention layers and feed-forward network layers superimposed on each other in the Transformer. In addition, to fill the gap in the Chinese CTI nested entity dataset, we further apply the Large Language Modeling (LLM) technique and domain knowledge to construct a high-quality Chinese CTI nested entity dataset, CDTinee, which consists of six entity types selected from STIX, including nearly 4000 entity types extracted from more than 3000 threatening sentences. In the experimental session, we conduct extensive experiments on multiple datasets, and the results show that the proposed model RBTG outperforms the baseline model in both flat NER and nested NER. Full article

With the rapid growth in space-imaging demands, the scheduling problem of multiple agile optical satellites has become a crucial problem in the field of on-orbit satellite applications. Because of the considerable solution space and complicated constraints, the existing methods suffer from a huge computation burden and a low solution quality. This paper establishes a mathematical model of this problem, which aims to maximize the observation profit rate and realize the load balance, and proposes a multi-pointer network to solve this problem, which adopts multiple attention layers as the pointers to construct observation action sequences for multiple satellites. In the proposed network, a local feature-enhancement strategy, a remaining time-based decoding sorting strategy, and a feasibility-based task selection strategy are developed to improve the solution quality. Finally, extensive experiments verify that the proposed network outperforms the comparison algorithms in terms of solution quality, computation efficiency, and generalization ability and that the proposed three strategies significantly improve the solving ability of the proposed network. Full article

This article begins with an interdisciplinary review of a hydrodynamic approach to understanding the origins and nature of macroscopic quantum phenomena in high-temperature superconductivity, superfluidity, turbulence and biological systems. Building on this review, we consider new theoretical insights into the origin and nature of pointer states and their role in the emergence of quantum systems. The approach includes a theory of quantum coherence underpinned by turbulence, generated by a field of pointer states, which take the form of recirculating, spin-1/2 vortices (toroids), interconnected via a cascade of spin-1 vortices. Decoherence occurs when the bosonic network connecting pointer states is disrupted, leading to their localisation. Building further on this work, we explore how quantum particles (in the form of different vortex structures) could emerge as the product of a causal dynamic process, within a turbulent (fractal) spacetime. The resulting particle structures offer new insights into intrinsic spin, the probabilistic nature of the wave function and how we might consider pointer states within the standard “point source” representation of a quantum particle, which intuitively requires a more complexed description. Full article

Chinese spelling errors are commonplace in our daily lives, which might be caused by input methods, optical character recognition, or speech recognition. Due to Chinese characters’ phonetic and visual similarities, the Chinese spelling check (CSC) is a very challenging task. However, the existing CSC solutions cannot achieve good spelling check performance since they often fail to fully extract the contextual information and Pinyin information. In this paper, we propose a novel CSC framework based on multi-label annotation (MLSL-Spell), consisting of two basic phases: spelling detection and correction. In the spelling detection phase, MLSL-Spell uses the fusion vectors of both character-based pre-trained context vectors and Pinyin vectors and adopts the sequence labeling method to explicitly label the type of misspelled characters. In the spelling correction phase, MLSL-Spell uses Masked Language Mode (MLM) model to generate candidate characters, then performs corresponding screenings according to the error types, and finally screens out the correct characters through the XGBoost classifier. Experiments show that the MLSL-Spell model outperforms the benchmark model. On SIGHAN 2013 dataset, the spelling detection F1 score of MLSL-Spell is 18.3% higher than that of the pointer network (PN) model, and the spelling correction F1 score is 10.9% higher. On SIGHAN 2015 dataset, the spelling detection F1 score of MLSL-Spell is 11% higher than that of Bert and 15.7% higher than that of the PN model. And the spelling correction F1 of MLSL-Spell score is 6.8% higher than that of PN model. Full article

Modern models have shown impressive capabilities in visual reasoning tasks. However, the interpretability of their decision-making processes remains a challenge, causing uncertainty in their reliability. In response, we present the Multimodal Selective Generation Network (MSGeN), a novel approach to enhancing interpretability and transparency in visual reasoning. MSGeN can generate explanations that seamlessly integrate diverse modal information, providing a comprehensive and intuitive understanding of its decisions. The model consists of five collaborative components: (1) the Multimodal Encoder, which encodes and fuses input data; (2) the Reasoner, which is responsible for generating stepwise inference states; (3) the Selector, which is utilized for selecting the modality for each step’s explanation; (4) the Speaker, which generates natural language descriptions; and (5) the Pointer, which produces visual cues. These components work harmoniously to generate explanations enriched with natural language context and visual cues. Our extensive experimentation demonstrates that MSGeN surpasses existing multimodal explanation generation models across various metrics, including BLEU, METEOR, ROUGE, CIDEr, SPICE, and Grounding. We also show detailed visual examples highlighting MSGeN’s ability to generate comprehensive and coherent explanations, showcasing its effectiveness through practical case studies. Full article

An abstractive summarization model based on the joint-attention mechanism and a priori knowledge is proposed to address the problems of the inadequate semantic understanding of text and summaries that do not conform to human language habits in abstractive summary models. Word vectors that are most relevant to the original text should be selected first. Second, the original text is represented in two dimensions—word-level and sentence-level, as word vectors and sentence vectors, respectively. After this processing, there will be not only a relationship between word-level vectors but also a relationship between sentence-level vectors, and the decoder discriminates between word-level and sentence-level vectors based on their relationship with the hidden state of the decoder. Then, the pointer generation network is improved using a priori knowledge. Finally, reinforcement learning is used to improve the quality of the generated summaries. Experiments on two classical datasets, CNN/DailyMail and DUC 2004, show that the model has good performance and effectively improves the quality of generated summaries. Full article

It is well known that the one-dimensional cutting stock problem (1DCSP) is a combinatorial optimization problem with nondeterministic polynomial (NP-hard) characteristics. Heuristic and genetic algorithms are the two main algorithms used to solve the cutting stock problem (CSP), which has problems of small scale and low-efficiency solutions. To better improve the stability and versatility of the solution, a mathematical model is established, with the optimization objective of the minimum raw material consumption and the maximum remaining material length. Meanwhile, a novel algorithm based on deep reinforcement learning (DRL) is proposed in this paper. The algorithm consists of two modules, each designed for different functions. Firstly, the pointer network with encoder and decoder structure is used as the policy network to utilize the underlying mode shared by the 1DCSP. Secondly, the model-free reinforcement learning algorithm is used to train network parameters and optimize the cutting sequence. The experimental data show that the one-dimensional cutting stock algorithm model based on deep reinforcement learning (DRL-CSP) can obtain the approximate satisfactory solution on 82 instances of 3 data sets in a very short time, and shows good generalization performance and practical application potential. Full article

DNA sequence variants (single nucleotide polymorphisms or variants, SNPs/SNVs; copy number variants, CNVs) associated to neurodevelopmental disorders (NDD) and traits often map on putative transcriptional regulatory elements, including, in particular, enhancers. However, the genes controlled by these enhancers remain poorly defined. Traditionally, the activity of a given enhancer, and the effect of its possible alteration associated to the sequence variants, has been thought to influence the nearest gene promoter. However, the obtainment of genome-wide long-range interaction maps in neural cells chromatin challenged this view, showing that a given enhancer is very frequently not connected to the nearest promoter, but to a more distant one, skipping genes in between. In this Perspective, we review some recent papers, who generated long-range interaction maps (by HiC, RNApolII ChIA-PET, Capture-HiC, or PLACseq), and overlapped the identified long-range interacting DNA segments with DNA sequence variants associated to NDD (such as schizophrenia, bipolar disorder and autism) and traits (intelligence). This strategy allowed to attribute the function of enhancers, hosting the NDD-related sequence variants, to a connected gene promoter lying far away on the linear chromosome map. Some of these enhancer-connected genes had indeed been already identified as contributive to the diseases, by the identification of mutations within the gene’s protein-coding regions (exons), validating the approach. Significantly, however, the connected genes also include many genes that were not previously found mutated in their exons, pointing to novel candidate contributors to NDD and traits. Thus, long-range interaction maps, in combination with DNA variants detected in association with NDD, can be used as “pointers” to identify novel candidate disease-relevant genes. Functional manipulation of the long-range interaction network involving enhancers and promoters by CRISPR-Cas9-based approaches is beginning to probe for the functional significance of the identified interactions, and the enhancers and the genes involved, improving our understanding of neural development and its pathology. Full article