Machine learning has been developed dramatically and witnessed a lot of applications in various fields over the past few years. This boom originated in 2009, when a new model emerged, that is, the ...deep artificial neural network, which began to surpass other established mature models on some important benchmarks. Later, it was widely used in academia and industry. Ranging from image analysis to natural language processing, it fully exerted its magic and now become the state-of-the-art machine learning models. Deep neural networks have great potential in medical imaging technology, medical data analysis, medical diagnosis and other healthcare issues, and is promoted in both pre-clinical and even clinical stages. In this review, we performed an overview of some new developments and challenges in the application of machine learning to medical image analysis, with a special focus on deep learning in photoacoustic imaging.
The aim of this review is threefold: (i) introducing deep learning with some important basics, (ii) reviewing recent works that apply deep learning in the entire ecological chain of photoacoustic imaging, from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.
Conventional reconstruction algorithms (e.g., delay-and-sum) used in photoacoustic imaging (PAI) provide a fast solution while many artifacts remain, especially for limited-view with ill-posed ...problem. In this paper, we propose a new convolutional neural network (CNN) framework Y-Net: a CNN architecture to reconstruct the initial PA pressure distribution by optimizing both raw data and beamformed images once. The network combines two encoders with one decoder path, which optimally utilizes more information from raw data and beamformed image. We compared our result with some ablation studies, and the results of the test set show better performance compared with conventional reconstruction algorithms and other deep learning method (U-Net). Both in-vitro and in-vivo experiments are used to validated our method, which still performs better than other existing methods. The proposed Y-Net architecture also has high potential in medical image reconstruction for other imaging modalities beyond PAI.
Collaborative Filtering Recommender Systems face data sparsity and cold‐start issues, leading to a decrease in their recommendation performance. Therefore, numerous researchers have integrated ...knowledge graphs and graph convolutional networks into recommender systems to enhance their performance. Through an analysis of previous knowledge graph convolutional network recommendation systems, the following problems have been identified: (1) Some graph convolutional networks only consider the neighborhood aggregation of items while neglecting the neighborhood aggregation of users. (2) User rating differences are not taken into account. To tackle these problems, a Bilateral Attention Mechanism Graph Convolutional Network Recommender Model is proposed. This model effectively captures high‐order neighborhood information for both items and users by utilizing bipartite attention mechanisms on the knowledge graph and interaction graph. Additionally, it incorporates the influence of user ratings on items. Finally, it aggregates item and user information with neighborhood information to predict user ratings for items. The validity of this model was verified through experimental analysis and comparative evaluation of its performance against SPGCN, CACF on the MovieLens‐20M, Book‐Crossing, and Last.FM datasets.
Employee scheduling aims to assign employees to shifts to satisfy daily workload and constraints. Some employee scheduling problems and their variants have been proven NP-hard, and a series of works ...have been done. However, the existing algorithms consider the fixed work time, which may cause plenty of overstaffing and understaffing phenomenons. Hence, this paper proposes a fast-flexible strategy based approach (FFS) to solve it. FFS introduces the idea of soft work time, which allows the work time of employees can be adjusted in a range. Based on this, we set the flextime strategy to decide the specific work time of each employee every day. Besides, FFS adopts a pairwise-allocated strategy and proficiency average matrix to boost its efficiency and effectiveness. Finally, the extensive experimental evaluation shows that FFS is more effective and efficient than the baselines for solving the employee scheduling problem considering soft work time.
In this era of information overload, to better provide personalized content services to users, recommendation systems have greatly improved the efficiency of information distribution. Graph ...Convolution Network(GCN), which is one of the representative works of graph structure aggregation processing, works by node convolution with the help of the Laplacian matrix of the graph and weighted combination of neighbor node information according to the outgoing and incoming degrees of neighbor nodes to obtain the representation of the current node. However, the mainstream GCN models nowadays do not take into account data augmentation of metadata and the fact that each node plays different roles with different importance and weights, thus making the recommendation performance limited. To better solve the above problems, we propose the IcaGCN model, which can perform data augmentation and calculate node weights in modules, and is a convenient plug-and-play method. Finally, extensive experimental results on four real-world datasets have shown the effectiveness and robustness of the proposed model. Especially on the Amazon-Book dataset, our IcaGCN has improved by 6.32%, 42.29%, and 12.38% in Recall@20, MRR@20, and NDCG@20, respectively, compared to other existing state-of-the-art models. We also provide source code and data to reproduce the experimental results available at https://github.com/PersonZ1223/IcaGCN.git
In the blockchain system, mining pools are popular for miners to work collectively and obtain more revenue. Nowadays, there are consensus attacks that threaten the efficiency and security of mining ...pools. As a new type of consensus attack, the Fork After Withholding (FAW) attack can cause huge economic losses to mining pools. Currently, there are a few evaluation tools for FAW attacks, but it is still difficult to evaluate the FAW attack protection capability of target mining pools. To address the above problem, this paper proposes a novel evaluation framework for FAW attack protection of the target mining pools in blockchain systems. In this framework, we establish the revenue model for mining pools, including honest consensus revenue, block withholding revenue, successful fork revenue, and consensus cost. We also establish the revenue functions of target mining pools and other mining pools, respectively. In particular, we propose an efficient computing power allocation optimization algorithm (CPAOA) for FAW attacks against multiple target mining pools. We propose a model-solving algorithm based on improved Aquila optimization by improving the selection mechanism in different optimization stages, which can increase the convergence speed of the model solution and help find the optimal solution in computing power allocation. Furthermore, to greatly reduce the possibility of falling into local optimal solutions, we propose a solution update mechanism that combines the idea of scout bees in an artificial bee colony optimization algorithm and the constraint of allocating computing power. The experimental results show that the framework can effectively evaluate the revenue of various mining pools. CPAOA can quickly and accurately allocate the computing power of FAW attacks according to the computing power of the target mining pool. Thus, the proposed evaluation framework can effectively help evaluate the FAW attack protection capability of multiple target mining pools and ensure the security of the blockchain system.
Blockchain has become one of the key techniques for the security of the industrial internet. However, the blockchain is vulnerable to FAW (Fork after Withholding) attacks. To protect the industrial ...internet from FAW attacks, this paper proposes a novel FAW attack protection algorithm (FAWPA) based on the behavior of blockchain miners. Firstly, FAWPA performs miner data preprocessing based on the behavior of the miners. Then, FAWPA proposes a behavioral reward and punishment mechanism and a credit scoring model to obtain cumulative credit value with the processed data. Moreover, we propose a miner’s credit classification mechanism based on fuzzy C-means (FCM), which combines the improved Aquila optimizer (AO) with strong solving ability. That is, FAWPA combines the miner’s accumulated credit value and multiple attack features as the basis for classification, and optimizes cluster center selection by simulating Aquila’s predation behavior. It can improve the solution update mechanism in different optimization stages. FAWPA can realize the rapid classification of miners’ credit levels by improving the speed of identifying malicious miners. To evaluate the protective effect of the target mining pool, FAWPA finally establishes a mining pool and miner revenue model under FAW attack. The simulation results show that FAWPA can thoroughly and efficiently detect malicious miners in the target mining pool. FAWPA also improves the recall rate and precision rate of malicious miner detection, and it improves the cumulative revenue of the target mining pool. The proposed algorithm performs better than ND, RSCM, AWRS, and ICRDS.
The increase in car ownership has brought convenience to people's lives, but it has also led to a sharp increase in pedestrian–vehicle conflicts. Such conflicts can be avoided by braking when ...pedestrians in front of the car are detected. However, frequent braking reduces driving comfort and travel efficiency. Considering that pedestrian–vehicle conflicts always occur when pedestrians cross the road, this study proposes a multi‐factor fusion network (MFFN) to anticipate pedestrians' crossing intentions. MFFN contains a dual‐channel action recognition sub‐network to robustly identify pedestrians' actions by adaptively fusing pedestrians' skeleton and representation characteristics. Afterward, object‐level and semantic‐level perception of traffic scenes are realised by a hierarchical graph attention network and a lightweight semantic segmentation method, respectively. These hierarchical environmental contexts can provide critical clues for identifying pedestrians' crossing intentions. Then, a self‐attention mechanism is used to integrate various factors and produce intention identification results. The proposed MFFN is evaluated on public datasets PIE and JAAD. Experimental results show that the proposed method can accurately and reliably identify pedestrian crossing intentions. The accuracy, F1 score, AUC, and precision indicators on JAAD/PIE datasets are 0.912/0.876, 0.813/0.806, 0.896/0.889, and 0.802/0.788, respectively.
Understanding agents’ motion behaviors under complex scenes is crucial for intelligent autonomous moving systems (like delivery robots and self-driving cars). It is challenging duo to the inherent ...uncertain of future trajectories and the large variation in the scene layout. However, most recent approaches ignored or underutilized the scenario information. In this work, a Multi-Granularity Scenarios Understanding framework, MGSU, is proposed to explore the scene layout from different granularity. MGSU can be divided into three modules: (1) A coarse-grained fusion module uses the cross-attention to fuse the observed trajectory with the semantic information of the scene. (2) The inverse reinforcement learning module generates optimal path strategy through grid-based policy sampling and outputs multiple scene paths. (3) The fine-grained fusion module integrates the observed trajectory with the scene paths to generate multiple future trajectories. To fully explore the scene information and improve the efficiency, we present a novel scene-fusion Transformer, whose encoder is used to extract scene features and the decoder is used to fuse scene and trajectory features to generate future trajectories. Compared with the current state-of-the-art methods, our method decreases the ADE errors by 4.3% and 3.3% by gradually integrating different granularity of scene information on SDD and NuScenes, respectively. The visualized trajectories demonstrate that our method can accurately predict future trajectories after fusing scene information.