Diverse breast masses in size, shape and place make accurate image segmentation more challenging in a unified deep-learning network.Therefore, based on the U-net network, an adaptive automatic whole-field segmentation network (AWDS-net) for characterising diverse breast masses is proposed to assist more accurate and fast medical diagnosis in this paper.In the encoder part of AWDS-net, a small mass extraction mechanism (SMEM) is designed to better retain fine-grained small mass location information, while a spatial pyramid module (SPM) is added to capture multi-scale context and high-resolution image information.In the decoder part, an attention gate (AG) mechanism is inserted to make the model automatically focus on the useful target region information, so that the extracted feature information can be used to build a symmetric encoderdecoder structure for automatic segmentation network of multiple masses in the full field of view.The experimental results on an opensource breast cancer dataset digital database for mammography (DDSM) show that compared with U-net, Attention-Unet, R2U-Net, and SegNet, the proposed AWDS-net achieves, up to higher image segmentation metrics of 3.16% accuracy, 20.59% sensitivity, 5.23% specificity,10.27%precision, 15.08% IoU and 14.21% F1-score with acceptable training time.

The canonical video action recognition methods usually label categories with numbers or one-hot vectors and train neural networks to classify a fixed set of predefined categories, thereby constraining their ability to recognise complex actions and transferable ability to unseen concepts.In contrast, cross-modal learning can improve the performance of individual modalities.Based on the facts that a better action recogniser can be built by reading the statements used to describe actions, we exploited the recent multimodal foundation model CLIP for action recognition.In this study, an effective Vision-Language action recognition adaptation was implemented based on few-shot examples spanning different modalities.We added semantic information to action categories by treating textual and visual label as training examples for action classifier construction rather than simply labelling them with numbers.Due to the different importance of words in text and video frames, simply averaging all sequential features may result in ignoring keywords or key video frames.To capture sequential and hierarchical representation, a weighted token-wise interaction mechanism was employed to exploit the pair-wise correlations adaptively.Extensive experiments with public datasets show that cross-modal action recognition learning helps for downstream action images classification, in other words, the proposed method can train better action classifiers by reading the sentences describing action itself.The method proposed in this study not only reaches good generalisation and zero-shot/few-shot transfer ability on Out of Distribution (OOD) test sets, but also performs lower computational complexity due to the lightweight interaction mechanism with 84.15% Top-1 accuracy on the Kinetics-400.

Safety-critical systems play a significant role in industrial domains, and their complexity is increasing with advanced technologies such as Artificial Intelligence (AI). To provide efficient services, safety-critical systems that integrate AI applications are always built based on Linux, where Linux offers massive amounts of features and an incredibly perfect software ecosystem for AI applications. Since Linux is a pre-existing complex software system, different research programmes aim to pave the way for developing Linux-based safety-critical systems. Still, only some focus on the system calls for file operations. However, the execution path of a system call is effectively non-deterministic in Linux kernel space, which challenges the test coverage-based verification recommended by the functional safety standards. This research analyzes the influence of system state on Linux kernel path variability from two perspectives: file system type and system load. Therefore, an online data collection system for system call execution paths was constructed based on Ftrace, network file system (NFS), and MD5 hash function, uniquely identifying the system call execution path. The collected data were processed and analysed in this study. Evaluations show that the number of function execution paths of the system calls relevant to file systems increased with the increase in system load but would eventually be stable. Additionally, the function execution paths of the system call varied in different file systems. Based on the evaluations, the results of this work can provide advice for analyzing Linux-based safety-critical systems. In addition, the method introduced in this research can also provide support for the verification of Linux-based safety-critical systems.

The penaeid shrimp farming industry is experiencing rapid growth. To reduce costs and labour, automation techniques such as counting and size estimation are increasingly being adopted. Feeding based on the degree of stomach fullness can significantly reduce food waste and water contamination. Therefore, we propose an intelligent shrimp farming system that includes shrimp detection, measurement of approximated shrimp length, shrimp quantity, and two methods for determining the degree of digestive tract fullness. We introduce AR-YOLOv5 (Angular Rotation YOLOv5) in the system to enhance both shrimp growth and the environmental sustainability of shrimp farming. Our experiments were conducted in a real shrimp farming environment. The length and quantity are estimated based on the bounding box, and the level of stomach fullness is approximated using the ratio of the shrimp´s digestive tract to its body size. In terms of detection performance, our proposed method achieves a precision rate of 97.70%, a recall rate of 91.42%, a mean average precision of 94.46%, and an F1-score of 95.42% using AR-YOLOv5. Furthermore, our stomach fullness determined method achieves an accuracy of 88.8%, a precision rate of 91.7%, a recall rate of 90.9%, and an F1-score of 91.3% in real shrimp farming environments.

Online transaction fraud has become increasingly rampant due to the convenience of mobile payment. Fraud detection is critical to ensure the security of online transactions. With the development of graph neural network, researchers have applied it to the field of fraud detection. The existing fraud detection methods will solve the class imbalance by sampling, but they do not fully consider the various imbalances in the heterogeneous graph, and the data imbalance will directly affect the performance of the model. This work proposes a hybrid graph neural network model for online fraud detection to address this issue. The three types of imbalance in online transactions are feature imbalance, category imbalance, and relation imbalance, and they are all addressed in the proposed model. The entities with the feature most closely related to the fraudsters will be determined for the feature imbalance, and samples will be taken for further identification in the subsequent training phase. The hybrid model then uses under-sampling in combination with the long-distance sampling to find nodes with high similarity of features for the category imbalance. Finally, we propose a reward/punishment mechanism based on reinforcement learning for relation imbalance, which uses the threshold created by training as the sampling weight between relations. This paper conducts experiments on the public datasets Amazon and Yelp. The experimental results show that the model proposed is 5.61% higher than the best model in the comparison model on Amazon dataset, and 1.58% higher on Yelp dataset.

This paper focuses on exploring and comparing different machine learning algorithms in the context of diabetes management.The aim is to understand their characteristics, mathematical foundations, and practical implications specifically for predicting blood glucose levels.The study provides an overview of the algorithms, with a particular emphasis on deep learning techniques such as Long Short-Term Memory Networks.Efficiency is a crucial factor in practical machine learning applications, especially in the context of diabetes management.Therefore, the paper investigates the tradeoff between accuracy, resource utilisation, time consumption, and computational power requirements, aiming to identify the optimal balance.By analysing these algorithms, the research uncovers their distinct behaviours and highlights their dissimilarities, even when their analytical underpinnings may appear similar.

Third-party APIs have been widely used to develop various applications.As the number of third-party APIs grows, it becomes increasingly challenging to quickly find suitable APIs that meet users' requirements.Inspired by recommender systems, API recommendation methods have been proposed to address this issue.However, previous API recommendation methods are insufficient in utilising the high-order interactions between users and APIs, and thus have limited performance.Based on the model of lightweight graph convolutional neural network, this paper proposes an effective API recommendation method by exploiting both low-order and high-order interactions between users and APIs.It first learns the embedding of users and APIs from the user-API interaction graph, and then adopts a weighted summation operator to aggregate the embeddings learned from different propagation layers for API recommendation.Extensive experiments are conducted on a real dataset with 160,309 API users and 21,031 Web APIs, and the results show that our method has significantly better precision and recall than other state-of-the-art methods.

Aspect-level sentiment classification, a significant task of fine-grained sentiment analysis, aims to identify the sentimental information expressed in each aspect of a given sentence The existing methods combine global features and local structures to obtain good classification results. However, the introduction of global features will bring noise and reduce the classification accuracy. To solve this problem, a new method is proposed, named GP-GCN. In our proposed method, the global feature is further simplified to reduce the noise . The local structures and global features obtained by orthogonal feature projection are introduced into aspect-level sentiment classification. First, the simplified global feature structures of text are built. Through orthogonal projection, GCN not only weakens the dependency of the graph node in updating process but also reduces the dependency between node and corpus. Next, syntactic dependency structure and sentence sequence information are utilised to mine the local dependency structure of sentences. A percentage-based multi-headed attention mechanism is proposed to measure the critical output of GCN, which can better represent sentences for given aspects. Finally, location coding is input to simulate aspect-specific representations between each aspect and its context such that the text becomes more discriminative in sentiment classification. The experimental results show that the proposed method effectively improves the accuracy of text sentiment classification.

Stocks price prediction is a current hot spot with great promise and challenges. Recently, there have been many stock price prediction methods. However, the prediction accuracy of these methods is still far from satisfactory. In this paper, we propose a stock price prediction method that incorporates multiple data sources and the investor sentiment, which can be called S_I_LSTM. Firstly, we crawl multiple data sources on the Internet and preprocess them respectively. These data involve stock historical data, technical indicators, and non-traditional data sources, such as stock posts and financial news. Then, we use the sentiment analysis method based on convolutional neural network for the non-traditional data, which can calculate the investors' sentiment index. Finally, we combine sentiment index, technical indicators and stock historical transaction data as the feature set of stock price prediction and adopt the long short-term memory network for predicting the China Shanghai A-share market. The experiments show that the predicted stock closing price is closer to the true closing price than the single data source, and the mean absolute error can achieve 2.386835, which is better than traditional methods. We verified the effectiveness on the real data sets of five listed companies.

Entity and relation extraction has been widely studied in natural language processing, and some joint methods have been proposed in recent years. However, existing studies still suffer from two problems. Firstly, the token space information has been fully utilized in those studies, while the label space information is underutilized. However, a few preliminary works have proven that the label space information could contribute to this task. Secondly, the performance of relevant entities detection is still unsatisfactory in entity and relation extraction tasks. In this paper, a new model GANCE (Gated and Attentive Network Collaborative Extracting) is proposed to address these problems. Firstly, GANCE exploits the label space information by applying a gating mechanism, which could improve the performance of the relation extraction. Then, two multi-head attention modules are designed to update the token and token-label fusion representation. In this way, the relevant entities detection could be solved. Experimental results demonstrate that GANCE has better accuracy than several competitive approaches in terms of entity recognition and relation extraction on the CoNLL04 dataset at 90.32% and 73.59%, respectively. Moreover, the F1 score of relation extraction increased by 1.24% over existing approaches in the ADE dataset.

Clustering ensemble, also referred to as consensus clustering, has emerged as a method of combining an ensemble of different clusterings to derive a final clustering that is of better quality and robust than any single clustering in the ensemble. Normally clustering ensemble algorithms in the literature combine all the clusterings without learning the ensemble. But by learning the ensemble, one can define the merit of a clustering or even a cluster in it, in forming a quality consensus. In this work, we propose a cluster-level surprisal measure to define the merit of a clustering that reflects both levels of agreement as well as disagreement among clusters. Using the proposed measure of merit, we devise a polynomial heuristics that judiciously selects a subset of clusterings from the ensemble that contribute positively in forming the consensus. We also empirically show that consensus achieved by our proposed method performs better in terms of quality compared to well-known clustering ensemble algorithms on different benchmark datasets.

Network coding remarkably improves network performance and transmission efficiency for multi-cast. Nevertheless, as its inherent defect, it is vulnerable to pollution attacks, bringing in a severe decrease of the network performance. In the proposed work, a novel approach is put forwarded, which can rapidly identify and isolate the malicious nodes from the networks as early as possible. On the one hand, we raise a secure infrastructure, on the other hand, we advocate a secure transmission protocol to verify every received packet. Theoretical analysis and experimental results demonstrate that the proposed scheme has the optimal performance in terms of security, network delay and network throughput.

Selecting suitable web services based on the quality-of-service (QoS) is essential for developing high-quality service-oriented applications. A critical step in this direction is acquiring accurate, personalised QoS values of web services. As the number of web services is enormous and the QoS data are highly sparse, improving the accuracy of QoS prediction has become a challenging issue recently. In this study, we propose a novel QoS prediction model, called neural fusion matrix factorisation, wherein we combine neural networks and matrix factorisation to perform non-linear collaborative filtering for latent feature vectors of users and services. Moreover, we consider context bias and employ multi-task learning to reduce prediction error and improve the predicted performance. Furthermore, we conducted extensive experiments in a large-scale real-world QoS dataset, and the experimental results verify the effectiveness of our proposed method.

Online social networks (OSNs) are nowadays an important field of applications thanks to the recent surge in online interaction. However, the illegal disclosure of user's private data can cause damaging consequences and even threaten the safety of users' life. The privacy issues of OSNs have become a matter of great concern for many people. In recent years, there are some research works to address this privacy issue, yet they do not always focus on providing the normal social network services for users, such as data sharing, data retrieval and data access services. Therefore, it is a challenge to ensure the security of sensitive data while providing efficient and privacy-preserving social network services for users. In this paper, we propose a novel blockchain-based privacy-preserving framework for online social networks, called BPP. Combined blockchain and public-key cryptography technique, the BPP framework can achieve secure data sharing, data retrieving, and data accessing with fairness and without worrying about potential damage to users' interest. Specifically, based on blockchain and public key encryption with keyword search technique, a secure, fair and efficient keyword search algorithm is proposed, with which the BBP framework realises privacy preservation of user's query and then obtain accurate query results with assurance and without needing for any further verification operation in online social network. Finally, we implement a prototype of our framework and deploy it to a locally simulated network. The extensive experiments and security analysis demonstrate the security, efficacy and efficiency of our proposed framework.