Driven by the increasing demand for intelligent earth observation and large-scale scene understanding, remote sensing object detection has gained significant academic and practical importance. Despite notable progress in feature extraction and computational efficiency, many recent approaches still struggle to effectively handle issues such as detecting objects at multiple scales and preserving small targets. In this paper, an efficient remote sensing object detector called multi-scale and feature-preserving YOLO with gated attention (YOLO-MFG) is proposed to address these challenges. First, a multi-scale group shuffle attention (MGSA) module is introduced to adaptively aggregate multi-scale spatial features, improving the model’s sensitivity to objects of diverse sizes. Second, the employment of feature-preserving downsampling (FPD) enhances the downsampling process by introducing a triple-branch fusion mechanism that mitigates aliasing while jointly preserving semantics, saliency, and geometry. Finally, gated enhanced attention (GEA) is integrated to capture long-range dependencies and contextual cues crucial for remote sensing scenarios. Experimental results demonstrate that the proposed YOLO-MFG achieves a 2.9% improvement in mean average precision at an IoU threshold of 0.5 (mAP50) on the optical remote sensing dataset SIMD compared to YOLO11. In addition, the mAP50 of detection results is improved by 1.4% and 4.2% on the DIOR and NWPU VHR-10 datasets, respectively.

With the rapid development of satellite and unmanned aerial vehicle technologies, remote sensing object detection has emerged as a research hotspot. However, recent research mainly focuses on representing bounding boxes and feature extraction to improve detection accuracy without considering the inherent characteristics of remote sensing scenes. A novel remote sensing object detector based on YOLO11 with the poly kernel inception and an attentional cross-level feature fusion (YOLO-PKFF) is proposed to bridge this gap. First, the poly kernel inception network (PKINet) is introduced as the backbone network to effectively capture local and global contextual information. Second, the attentional cross-level feature fusion (ACFF) module is employed to selectively integrate low-level texture features with high-level semantic features. Finally, an enhanced inception module is integrated into the C3k2 module, improving the detection of striped objects. Experimental results demonstrate that the proposed YOLO-PKFF achieves a 3.8% improvement in mean average precision (mAP) on the DIOR optical remote sensing dataset compared to the baseline. Furthermore, YOLO-PKFF achieves mAP improvements of 6.2% and 1.2% on two additional publicly available optical remote sensing datasets, respectively.

In the field of cyberbullying detection, it is crucial to understand and analyze the structural features of media sessions. However, most studies ignore the dynamic correlation between comments and temporal information as well as temporal pattern matching among sessions. To address the problem, this study proposes a Time-User Heterogeneous Neural Interaction Network (TUHIN) model. It consists of five modules: session encoding module, comment interaction module, session-time attention module, user interaction module and aggregation module. Specifically, considering comment and temporal information, we adopt a hierarchical structure to extract features from the comment and session levels of media sessions. Then, in order to analyze the interaction patterns among users, we use graph convolutional networks to model the influential situations of users participation in media sessions. Comparing with the baseline models on public Instagram and Vine datasets, our model performs better on both Recall and F1.

The rapid development and explosive usage of social media make cyberbullying detection a major concern for society. However, many existing studies only focus on textual contents and ignore multimodal social media data, including texts, images, videos, etc. Although there are a few studies on multimodal cyberbullying detection, they suffer from the following limitations: 1) fail to extract features of each modality sufficiently; 2) largely ignore the significance of multimodal correlation for cyberbullying detection; 3) consider each social media session as independent. To address these issues, we propose a novel Multimodal Correlation and Interaction-based Cyberbullying Detection method (MCICD). Specifically, we construct a post-image co-attention sub-network to capture correlations between texts and images, and design a heterogeneous user-postimage interaction sub-network to explore dependencies among social media sessions, which contain multimodal information. Experimental results on two real-world session-level social media datasets demonstrate the effectiveness of our proposed method. Additionally, it is also verified that our method performs well on the early detection of cyberbullying.

This paper proposes a new Petri-net-based Q-learning scheduling method to schedule robotic cellular manufacturing (RCM) systems efficiently. First, we use generalized and place-timed Petri nets to model RCM systems. Then, we design a reinforcement learning method with a sparse Q-table to evaluate state-transition pairs of the net’s reachability graph. It uses the negative transition firing time as a reward for an action selection and adopts a large penalty for any encountered deadlock. In addition, it balances the state space exploration and the experience exploitation by using a dynamic ϵ-greedy policy to update the state values with an accumulative reward. Three different dynamic ϵ-greedy policies are designed for different application scenarios. Some benchmark RCM systems are tested with the proposed method and several popular PN-based online dispatching rules, such as FIFO and SRPT. Simulation results demonstrate that our method schedules RCM systems as quickly as the online dispatching rules while outperforming them in terms of schedule makespan. For readers’ reference, our source code and test data are available at https://github.com/PNOptimizer/PNQL.

Transfer learning has become a key technique in deep learning, widely adopted in the industry and academia for developing customized models, especially for specific and downstream tasks solving. Despite the prevalence of transfer learning, the target model can easily inherit defects from the source model during the learning process, such as vulnerability to backdoor attacks and adversarial attacks. Thus, this work proposes a novel approach, iterative pruning learning approach (IPLA), that reduces the inheritance of potential defects during the transfer learning process. In order to reduce the vulnerability to attacks and improve the robustness of target model, IPLA evaluates the importance of weights from the source model and retains ones that are critical to the target task, then prunes the redundant weights through an iterative pruning process. Experiments are performed on 4 datasets over 2 backbone source models. Results demonstrate the satisfactory performance of our proposed method.

This article proposes a novel anytime search method for the scheduling problem of resource allocation systems (RASs) based on Petri nets (PNs). The method combines the A$^*$search with the depth-first search to iteratively search for transition firing sequences from a start state to a goal state within the reachability graph of a place-timed PN. It usually finds a near-optimal solution quickly and continuously improves the solution until an optimal solution is reached if given more time. When compared with similar work, this method requires only one parameter and does not require any deadlock control policy. Additionally, it can handle generalized PNs with flexible routes and weighted arcs, which are common in the PN models of RASs. Experimental results on benchmark systems demonstrate the effectiveness of the proposed method.

Sharding technology is a promising solution for improving the scalability of blockchain systems. However, it faces the problem of allocating suitable trusted nodes into separate shards to satisfy security and efficiency requirements. Existing blockchain sharding methods fail to consider shard trust difference, communication latency difference, and node count difference among shards. This tends to increase the risk of a blockchain failure. This work proposes a novel blockchain sharding model for node allocation by considering shard trust difference. Its key idea is to allocate nodes of different trust levels to suitable shards to make shards have almost the same trust, such that shards’ reliability increases and blockchain failure probability decreases. To reduce the communication delay among shards, this work considers the communication latency difference and node count difference among shards. It proposes a sharding algorithm to iteratively adjust node allocations such that an optimal or near-optimal node allocation set is obtained. Simulation results show that the proposed method can effectively improve shard security and the performance of blockchain sharding compared with two state-of-the-art methods, i.e., Monoxide and Rapidchain, in terms of throughput, latency, and blockchain failure probability.

With the continuous development of consortium blockchains, the storage overhead of blocks and storage load of nodes are increasing. The existing storage models consider either low-reliability issues or high storage overhead but not both. This work proposes a storage model that combines group-based block storage with block splitting and unit encoding. The former is used to improve the reliability of a block, while the latter is adopted to reduce the storage overhead and increase the reliability of a block in a consortium blockchain. Based on this model, this work designs a storage method to minimize the storage overhead of blocks and storage load of nodes, and maximize reliability of a consortium blockchain. Experimental results show that the proposed method outperforms Multi-layer Practical Byzantine Fault Tolerance, RapidChain, and Byzantine Fault Tolerance-Store in terms of storage overhead and reliability, thus greatly advancing the field of consortium blockchains.

System scheduling is a decision-making process that plays an important role in improving the performance of robotic cellular manufacturing (RCM) systems. Timed Petri nets (PNs) are a formalism suitable for graphically and concisely modeling such systems and obtaining their reachable state graphs. Within their reachability graphs, timed PNs’ evolution and intelligent search algorithms can be combined to find an efficient operation sequence from an initial state to a goal one for the underlying systems of the nets. To schedule RCM systems, this work proposes an A* search with a new heuristic function based on timed PNs. When compared with related approaches, the proposed one can deal with token remaining time, weighted arcs, and multiple resource copies commonly seen in the PN models of RCM systems. The admissibility of the proposed heuristic function is proved. Finally, experimental results are given to show the effectiveness and efficiency of the proposed method and heuristic function.Note to Practitioners—Robotic cellular manufacturing (RCM) systems are among the most common and complicated discrete-event dynamic systems, which provide a great number of choices of resources and processing routes to allow high system productivity. Timed Petri nets (PNs) and intelligent search algorithms on their reachability graphs are ideal tools to handle the RCM scheduling problem. This work proposes an A* search method based on the evolutions of timed PNs to optimally schedule RCM systems. The proposed method can deal with token remaining time, weighted arcs, and multiple resource copies often encountered in the PN models of RCM systems.

Solving states separation problems is an important technique to obtain liveness-enforcing and optimal or near-optimal supervisors for flexible manufacturing systems based on Petri nets. It first generates the model's reachability graph and partitions it into a live zone (LZ) and a deadlock zone (DZ). Then, first-met bad markings (FBMs), which exist in DZ and are the very first entries from LZ to DZ, are forbidden by some designed place invariants (PIs) to prevent the system from entering DZ. This paper studies the reduction of the number of places to be considered in such PI designs. First, the concepts of critical transitions and critical activity places are defined, and a fast algorithm is provided to compute them. Then, the proofs of that only critical activity places need to be considered in such PI designs to forbid all FBMs and/or permit all legal markings in LZ are established.

This paper investigates several speedup techniques for a multiobjective integer linear program (ILP) used to obtain an optimal Petri net supervisor with a compressed structure for automated manufacturing systems (AMSs). An optimal supervisor can be obtained by forbidding all first-met bad markings and no legal markings of a plant net via place invariants. An iterative method to perform lexicographic multiobjective ILP is proposed to design such supervisor with a simple structure in terms of the numbers of control places and added arcs. Instead of a single ILP, several much smaller ILPs are formulated in the iterative method, and they can be solved much faster. To further reduce the ILP solution time, an efficient redundancy identification method is used. Finally, some AMS examples are provided to demonstrate the proposed speedup techniques and approaches.

For flexible manufacturing systems, this paper presents a Petri net based deadlock prevention method to obtain highly permissive and structurally minimal supervisors in the presence of uncontrollable and unobservable transitions. First, we define admissible markings which form a maximal strongly connected component (SCC) containing the initial marking and not leading outside the SCC uncontrollably. Then, an integer linear programming problem is formulated to construct a supervisor which permits all admissible markings and forbids all the very first inadmissible states from the admissible zone. It also ensures that no uncontrollable transitions are controlled and no unobservable ones are observed by the supervisor. The method can be applied to the plant nets whose crucial transitions are uncontrollable and/or unobservable. In addition, the obtained supervisors are deadlock-free, highly permissive, and structurally minimal in the presence of controllability and observability.

The theory of regions is an important method to derive an optimal and liveness-enforcing supervisor for a flexible manufacturing systems based on Petri nets. It first partitions the reachability graph into a live zone (LZ) and a deadlock zone (DZ). Then, activity places are used to construct place invariants (PIs) to prevent the system from entering DZ and permit all markings in LZ. This work studies the reduction of the number of places to be considered in the optimal PI designs. First, the concepts of critical transitions and critical activity places are defined, and an algorithm is provided to compute the sets of critical and uncritical activity places. Then, the proof of that only critical activity places need to be considered in such optimal PI designs is established.

For automated manufacturing systems (AMSs), this paper presents a Petri net based deadlock prevention method to efficiently obtain an optimal supervisor with a compressed structure in terms of control places and added arcs. The optimal supervisor can be achieved by forbidding all first-met bad markings (FBMs) and permitting all legal markings. An iterative method for a lexicographic multiobjective integer linear program (LMILP) is formulated to design such a supervisor with a simple structure. At each iteration, a place invariant is designed to obtain an optimal control place by solving an LMILP whose objectives are first to forbid as many FBMs as possible, second to minimize the number of added arcs, and third to simplify coefficients of the place invariants. Instead of a single sizable linear program, several much smaller LMILPs are formulated, which can be solved much faster. Finally, a benchmark example is used to show the efficiency and effectiveness of the approach.

Based on Petri net (PN) models of automated manufacturing systems, this paper proposes a deadlock prevention method to obtain a maximally permissive (optimal) supervisor while minimizing its structure. The optimal supervisor can be achieved by forbidding all first-met bad markings (FBMs) and permitting all legal markings in a PN model. An FBM obtained via a single transition's firing at a legal marking is a deadlock or marking that inevitably evolves into a deadlock. A lexicographic multiobjective integer programming problem with multiple objectives to be achieved sequentially is formulated to design such an optimal and structurally minimal supervisor. As a nonlinear function, the quantity of its directed arcs is minimized. A conversion method is proposed to convert the nonlinear model into a linear one. With the premise that each place in the supervisor is associated with a nonnegative place invariant, the controlled net holds all legal markings of the net model, and the supervisor has the minimal structure. Finally, some examples are used to illustrate the application of the proposed approach.

The above paper proposes a method to design optimal control places with self-loops for flexible manufacturing systems by solving an integer linear programming problem (ILPP) at each iteration. However, some constraints in the ILPP are redundant. This technical correspondence shows that they can be removed without changing the feasible region of the ILPP.