Search

Object detection technology is a popular research direction which is widely used in areas such as autonomous driving and medical diagnosis. At this stage mobile devices often have limited storage resources to deploy large object detection networks and need to meet real-time requirements. This paper proposes a lightweight and efficient object detection model based on YOLOv4, first using the lightweight network GhostNet to extract image features and reduce the number of parameters and computation of the backbone structure; then combining AFmodule and Meta-ACON activation function to enhance the feature extraction capability of the backbone network, which strengthen the mode's ability to capture image spatial feature information; this paper also designs the RL-PAFPN feature fusion structure is with the Reslayer module to further improve the model's ability to extract and fuse image features. By comparing other mainstream object detection models, the YOLOv4-Ghost-AMR network in this paper has less computation and fewer parameters, and the accuracy of the model reaches 86.83%, which is suitable for deployment in mobile devices with limited storage. The model proposed in this paper can be applied to medical, traffic and fault detection fields, which changes the traditional manual detection method and saves manpower and time costs, achieving high precision real-time object detection. [ABSTRACT FROM AUTHOR]

In this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. This issue leads to the degradation of localisation accuracy and robustness. Firstly, we employ a lightweight YOLO-Tiny network to enhance both detection accuracy and system speed. Secondly, we integrate the YOLO-Tiny network into the ORB-SLAM3 system to extract semantic information from the images and initiate the elimination of dynamic feature points. Subsequently, we augment this approach by incorporating geometric constraints between neighbouring frames to further eliminate dynamic feature points. Then, the former is supplemented by combining the geometric constraints between neighbouring frames to further eliminate dynamic feature points. Experiments on the TUM dataset demonstrate that the algorithm in this paper can improve the Relative Pose Error (RPE) by up to 95.12% and the Absolute Trajectory Error (ATE) by up to 99.01% in high dynamic sequences compared to ORB-SLAM3. The effectiveness of dynamic feature point elimination is evident, leading to significantly improved localisation accuracy. [ABSTRACT FROM AUTHOR]

Through the digitalisation of Civil Trials and the implementation of the Telematic Civil Process framework, the Italian Ministry of Justice has amassed a wealth of data covering all facets of modern Trials. While data availability has surged, the focus now lies in actively analysing this data to optimise Trials and curtail their duration. This paper, with a strong emphasis on its outcomes, delves into the analysis of data from the Court of Livorno. It seeks to pinpoint specific events within the Trial workflow that significantly extend Trial durations. Notably, Domain Experts have identified a set of events, intending to validate their pivotal role in recognising critical Trials. Leveraging Machine Learning techniques, the paper evaluates multiple binary classifiers to proactively identify potentially critical Trials, empowering Judges to mitigate future issues. The study has yielded a remarkable 80% accuracy rate in predicting Trials exceeding acceptable duration thresholds. [ABSTRACT FROM AUTHOR]

This paper proposes a particle-based nonlinear elastic object simulation technique for virtual surgery. Particle-based techniques are used to model and simulate nonlinear elastic objects, such as the skin and internal organs. This enables the simulation to consider various factors, such as location, direction, and depth, when making incisions in the organs. However, the issue with this method is that it can only simulate precisely cut tissue during incision. Objects with elasticity, such as tissue, require the generation of complex debris during incision. This paper proposes a particle-based elastic object simulation technique to model the debris from torn tissue when making an incision in the organs. It can predict where the tissue will tear based on the maximum shear stress (MSS) theory and Tresca's yield criterion when the force applied to the tissue exceeds the maximum stress. Newly generated particles at the predicted location are remeshed with nearby particles. We verified the superiority of our proposed method over traditional particle-based methods by accurately representing more complex debris and comparing the results of incisions in the same area of the body. This allows various incision types, such as stab wounds and lacerations, to be simulated. [ABSTRACT FROM AUTHOR]

Crowdsourcing takes advantage of human intelligence to solve complex problems that computers cannot handle. People actively participate in computational tasks for rewards, especially those that are relatively simple for humans but challenging for computers. However, most traditional crowdsourcing systems must rely on a central organisation to handle the work associated with crowdsourcing. This may lead to privacy and security issues such as information leakage, single point of attack and unfair judgement. Meanwhile, the high service fees of existing central crowdsourcing platforms will reduce people's motivation to participate in crowdsourcing tasks. Consequently, PrivBCS is proposed in this paper, a blockchain-based decentralised crowdsourcing system that does not rely on third-party agencies and requires only low transaction fees. In this paper, PrivBCS protects the confidentiality of crowdsourcing data and the identity privacy of participants by cryptographic means, such as Paillier, El-Gamal and CPABE. It selects the most suitable worker to perform tasks by setting access control policies on task data and matching workers' attributes while ensuring the anonymity of workers' identity. Considering that the data volume of crowdsourcing tasks may be large and there is a certain upper limit to the block capacity of the blockchain, an on-chain and off-chain collaborative storage scheme is proposed, which can increase the throughput of the blockchain system and improve its scalability to a certain extent. In PrivBCS, we implement the transaction process of crowdsourcing tasks through smart contracts. The experimental results and security analysis in this paper demonstrate the effectiveness, efficiency, and feasibility of PrivBCS. [ABSTRACT FROM AUTHOR]

Image super-resolution reconstruction is one of the methods to improve resolution by learning the inherent features and attributes of images. However, the existing super-resolution models have some problems, such as missing details, distorted natural texture, blurred details and too smooth after image reconstruction. To solve the above problems, this paper proposes a Multi-scale Dual-Attention based Residual Dense Generative Adversarial Network (MARDGAN), which uses multi-branch paths to extract image features and obtain multi-scale feature information. This paper also designs the channel and spatial attention block (CSAB), which is combined with the enhanced residual dense block (ERDB) to extract multi-level depth feature information and enhance feature reuse. In addition, the multi-scale feature information extracted under the three-branch path is fused with global features, and sub-pixel convolution is used to restore the high-resolution image. The experimental results show that the objective evaluation index of MARDGAN on multiple benchmark datasets is higher than other methods, and the subjective visual effect is better. This model can effectively use the original image information to restore the super-resolution image with clearer details and stronger authenticity. [ABSTRACT FROM AUTHOR]

The traditional convolutional neural network (CNN) has a limited receptive field and cannot accurately identify the importance of each channel, making it difficult to solve increasingly complex network security problems. To solve these problems, this paper combines ResNeXt with the Efficient Channel Attention (ECA) module and the Contextual Transformer (COT) block to construct a model to assess network conditions. The optimal hyperparameters of the model are selected by the Harris Hawks Optimization (HHO) algorithm. The model can accurately obtain the importance of each channel to assign weights to each channel while making full use of the rich contexts among neighbour keys, effectively enhancing the convolutional neural network. Furthermore, this paper calculates the network security situation value (NSSV) of the adopted datasets based on attack impact. Lastly, experiments on two cybersecurity datasets show that the comprehensive performance of the model on the three indicators of accuracy, precision and F-scores, as well as network security situation assessment, are superior to other models. [ABSTRACT FROM AUTHOR]

The autonomous driving algorithm studied in this paper makes a ground vehicle capable of sensing its environment via visual images and moving safely with little or no human input. Due to the limitation of the computing power of end side devices, the autonomous driving algorithm should adopt a lightweight model and have high performance. Conditional imitation learning has been proved an efficient and promising policy for autonomous driving and other applications on end side devices due to its high performance and offline characteristics. In driving scenarios, the images captured in different weathers have different styles, which are influenced by various interference factors, such as illumination, raindrops, etc. These interference factors bring challenges to the perception ability of deep models, thus affecting the decision-making process in autonomous driving. The first contribution of this paper is to investigate the performance gap of driving models under different weather conditions. Following the investigation, we utilise StarGAN-V2 to translate images from source domains into the target clear sunset domain. Based on the images translated by StarGAN-V2, we propose Conditional Imitation Learning with ResNet backbone named Star-CILRS. The proposed method is able to convert an image to multiple styles using only one single model, making our method easier to deploy on end side devices. Visualization results show that Star-CILRS can eliminate some environmental interference factors. Our method outperforms other methods and the success rate values in different tasks are 98%, 74%, and 22%, respectively. [ABSTRACT FROM AUTHOR]

Morphological segmentation is a basic task in agglutinative language information processing, dividing words into the smallest semantic unit morphemes. There are two types of morphological segmentation: canonical segmentation and surface segmentation. As a typical agglutinative language, Uyghur usually uses statistical-based methods in canonical segmentation, which relies on the artificial extraction of features. In surface segmentation, the artificial feature extraction process is avoided by using the neural network. However, to date, no model can provide both segmentation results in Uyghur without adding features. In addition, morphological segmentation is usually regarded as a sequence annotation task, so label imbalance easily occurs in datasets. Given the above situation, this paper proposes an improved labelling scheme that joins morphological boundary labels and voice harmony labels for the two kinds of segmentation simultaneously. Then, a convolution network and attention mechanism are added to capture local and global features, respectively. Finally, morphological segmentation is regarded as a sequence labeling task of character sequences. Due to the problem of label proportion imbalance and noise in the dataset, a focal loss function with label smoothing is used. The experimental results show that the F1 values of canonical segmentation and surface segmentation achieve the best results. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) are widely used in various military and civilian applications. UAV mission scheduling is a key issue in UAV applications and a central topic in UAV research. UAV task scheduling should include several constraints into consideration, such as completion time constraint, flight distance constraint, and resource consumption constraint. Furthermore, UAV task scheduling should be studied within the traditional framework of combinatorial optimisation. In this paper, we consider optimal mission scheduling for heterogeneous UAVs with completion time, flight distance, and resource consumption constraints. The contributions of the paper are summarised as follows. We define two combinatorial optimisation problems, namely, the NFTM (number of finished tasks maximisation) problem and the RFTM (reward of finished tasks maximisation) problem. We construct an algorithmic framework for both NFTM and RFTM problems, so that our heuristic algorithms (four for NFTM and two for RFTM) can be presented in a unified way. We derive upper bounds for optimal solutions, so that our heuristic solutions can be compared with optimal solutions. We experimentally evaluate the performance of our heuristic algorithms. To the best of our knowledge, this is the first paper studying UAV mission scheduling with time, distance, and resource constraints as combinatorial optimisation problems. [ABSTRACT FROM AUTHOR]

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 trade-off 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. [ABSTRACT FROM AUTHOR]

As a foundation task of natural language processing, text classification is widely used in information retrieval, public opinion analysis, and other related tasks. Facing the problem of sparse features of Chinese short texts, which affects the classification accuracy of Chinese short texts, this paper proposes a Chinese short text classification method based on the Character Frequency Sub-word Enhancement (CFSE), which can effectively improve the classification accuracy of Chinese short texts. First, the initial Chinese-character sequence is mapped to the corresponding Character Frequency Sub-word (CFS) sequence based on the global character1 frequency information. Second, the relationship features among data are extracted based on BiLSTM-Att processing CFS sequence, and the semantic features of the initial Chinese-character sequence are obtained through ERNIE. Finally, these two kinds of features are fused and input into the text classifier to obtain the classification results. Experimental results show that the proposed method can improve the classification accuracy of Chinese short texts. [ABSTRACT FROM AUTHOR]

Online reviews contain comparative opinions that reveal the competitive relationships of related products, help identify the competitiveness of products in the marketplace, and influence consumers' purchasing choices. The Class Sequence Rule (CSR) method, which is previously commonly used to identify the comparative relations of reviews, suffers from low recognition efficiency and inaccurate generation of rules. In this paper, we improve on the CSR method by proposing a hybrid CSR method, which utilises dependency relations and the part-of-speech to identify frequent sequence patterns in customer reviews, which can reduce manual intervention and reinforce sequence rules in the relation mining process. Such a method outperforms CSR and other CSR-based models with an F-value of 84.67%. In different experiments, we find that the method is characterised by less time-consuming and efficient in generating sequence patterns, as the dependency direction helps to reduce the sequence length. In addition, this method also performs well in implicit relation mining for extracting comparative information that lacks obvious rules. In this study, the optimal CSR method is applied to automatically capture the deeper features of comparative relations, thus improving the process of recognising explicit and implicit comparative relations. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

With the rapid growth of Internet data traffic, the means of malicious attack become more diversified. The single modal intrusion detection model cannot fully exploit the rich feature information in the massive network traffic data, resulting in unsatisfactory detection results. To address this issue, this paper proposes a multimodal hybrid parallel network intrusion detection model (MHPN). The proposed model extracts network traffic features from two modalities: the statistical information of network traffic and the original load of traffic, and constructs appropriate neural network models for each modal information. Firstly, a two-branch convolutional neural network is combined with Long Short-Term Memory (LSTM) network to extract the spatio-temporal feature information of network traffic from the original load mode of traffic, and a convolutional neural network is used to extract the feature information of traffic statistics. Then, the feature information extracted from the two modalities is fused and fed to the CosMargin classifier for network traffic classification. The experimental results on the ISCX-IDS 2012 and CIC-IDS-2017 datasets show that the MHPN model outperforms the single-modal models and achieves an average accuracy of 99.98 $ \% $ %. The model also demonstrates strong robustness and a positive sample recognition rate. [ABSTRACT FROM AUTHOR]

This paper presents MoCoUTRL: a Momentum Contrastive Framework for Unsupervised Text Representation Learning. This model improves two aspects of recently popular contrastive learning algorithms in natural language processing (NLP). Firstly, MoCoUTRL employs multi-granularity semantic contrastive learning objectives, enabling a more comprehensive understanding of the semantic features of samples. Secondly, MoCoUTRL uses a dynamic dictionary to act as the approximately ground-truth representation for each token, providing the pseudo labels for token-level contrastive learning. The MoCoUTRL can extend the use of pre-trained language models (PLM) and even large-scale language models (LLM) into a plug-and-play semantic feature extractor that can fuel multiple downstream tasks. Experimental results on several publicly available datasets and further theoretical analysis validate the effectiveness and interpretability of the proposed method in this paper. [ABSTRACT FROM AUTHOR]

The proliferation of location-based service applications has led to a substantial surge in the amount of life trajectory data produced by mobile devices. And these data frequently contain confidential personal details. Simultaneously, the corresponding relatively lagging privacy protection technology and the improper trajectory data handling method will make tremendous problems with privacy breach. Therefore, this paper presents a trajectory privacy data publishing scheme, denoted as LORDP, which is based on local optimisation and R-tree. The proposed scheme aims to handle sensitive data while improves trajectory protection effectiveness. Firstly, the scheme combines the LKC-privacy model requirement to filter out the minimum violating sequences set, to reduce data sensitivity and the amount of injected noise. Secondly, R-tree is constructed based on trajectory similarity. Finally, Laplacian noise is added to the R-tree's leaf nodes constrained by differential privacy. The experiments show that the proposed LORDP algorithm significantly enhances the utility of data compared to other algorithms, and reduces the loss rate of about approximately 2% for per trajectory data, which shows that the present algorithm is extremely effective. [ABSTRACT FROM AUTHOR]

The cost control challenge in construction and installation projects has always been a critical concern for construction entities. The complexity of task collaboration among various equipment and nodes during the installation process leads to extended construction duration, resulting in increased construction costs. To address this issue, this paper proposes a heuristic two-stage optimal deployment approach called MERD. The MERD approach incorporates intelligent computing principles from computer science into the resource scheduling of the construction process, modelling the installation scheduling problem into a combinatorial optimisation problem. Designing the probability method based on Bayes theorem, the MERD approach carries out an installation provisioning mechanism to optimise personnel and device allocation in the selected area. As a result, the MERD approach minimises construction hours and reduces labour costs in the construction process. Experimental results demonstrate the effectiveness and efficiency of the MERD approach in reducing work time and cost in engineering projects. [ABSTRACT FROM AUTHOR]

The present paper aims to propose a new learning and interpretation method called "impartial competitive learning", meaning that all participants in a competition should be winners. Due to its importance, the impartiality is forced to be realised even by increasing the corresponding cost in terms of the strength of weights. For the first approximation, three types of impartial competition can be developed: componential, computational, and collective competition. In the componential competition, every weight should have an equal chance on average to win the competition. In the computational competition, all computational procedures should have an equal chance to be applied sequentially in learning. In collective computing for interpretation, all network configurations, obtained by learning, have an equal chance to participate in a process of interpretation, representing one of the most idealised forms of impartiality. The method was applied to a well-known second-language-learning data set. The intuitive conclusion, stressed in the specific science, could not be extracted by the conventional natural language processing methods, because they can deal only with word frequency. The present method tried to extract a main feature beyond the word frequency by competing connection weights and computational procedures impartially, followed by collective and impartial competition for interpretation. [ABSTRACT FROM AUTHOR]

Microservices architecture is a new paradigm for application development. The problem of optimising the performance of microservice architectures from a non-functional perspective is a typical Nondeterministic Polynomial (NP) problem. Therefore, aiming to quantify the non-functional requirements of computing microservice systems, while solving the problem of latency in computing the best combination of services with the maximum QoS objective function value, this paper proposes a microservice combination approach based on the QoS model and a CGWO algorithm for optimisation computation for this model. The experimental results verify that the error rate of the method is only 0.528% on the non-functional combination optimisation problem, and the computational efficiency of the algorithm increases by 97.29% when the complexity of the problem search space increases, while CGWO improves 65.97% and 81.25% respectively in the accuracy of optimisation compared to the prototype of the algorithm (GWO), and has a stable optimisation performance, aspect. It proves that the research in this paper has a high advantage in automatically searching for the best QoS for the microservice combination problem. [ABSTRACT FROM AUTHOR]

Logistics tracking and positioning is a critical part of the discrete digital workshop, which is widely applied in many fields (e.g. industry and transport). However, it is distinguished by dispersed manufacturing machinery, frequent material flows, and complicated noise environments. The positioning accuracy of the conventional radio frequency positioning approach is severely impacted. The latest panoramic vision positioning technology relies on binocular cameras. And that cannot be used for monocular cameras in industrial scenarios. This paper proposes a monocular vision positioning method based on YOLOv7 and coordinate transformation to solve the problem of positioning accuracy in the digital workshop. Positioning beacons are placed on the top of the moving vehicle with a uniform height. The coordinate position of the beacon on the image is obtained through the YOLOv7 model based on transfer learning. Then, coordinate transformation is applied to obtain the real space coordinates of the vehicle. Experimental results show that the proposed single-eye vision system can improve the positioning accuracy of the digital workshop. The code and pre-trained models are available on . [ABSTRACT FROM AUTHOR]

Porcelain insulators play an important role in power transmission lines. It is of great significance to improve the accuracy of diagnosis of porcelain insulators' discharge state and ensure the reliability of power supply. Therefore, this paper presents a diagnosis method of polluted discharge state of porcelain insulator based on GA-optimised CNN network structure. Firstly, the artificial pollution discharge test of porcelain insulator is carried out. According to the characteristics of leakage current, the discharge development process is divided into five stages: normal state, initial discharge, through discharge, flashover and flashover completion. GA algorithm is used to optimise the parameters of CNN model, and several single models are established simultaneously to compare the progress with the proposed model. The results show that GA has the advantages of global optimisation, less adjustment parameters, etc. It can automatically select the best structure of CNN network, avoid the problem of poor performance of artificial selection of CNN network structure, reduce the time required for parameter selection, and improve the accuracy of diagnosis of polluted discharge state of porcelain insulators, with the diagnosis accuracy as high as 99.2%. The results show that the discharge state of porcelain insulator surface can be judged by leakage current. [ABSTRACT FROM AUTHOR]

In colposcopy-assisted diagnosis, the difference between the different lesion grades of colposcopic images is small, and the visual similarity is high. Therefore, it is a very challenging task to accurately diagnose cervical lesions through colposcopic images. This paper proposes a new risk assessment net of cervical lesions in colposcopic images (RACNet). The RACNet mainly consists of two parts. At first, the location and grade of lesions in different scales are detected through a multi-scale detection network. Then, these lesions are classified by designing a multi-branch convolutional neural network (CNN) to improve the performance of risk assessment. The RACNet was compared with the most advanced methods and colposcopists under the same condition. The experimental results show that the RACNet in this paper is superior to other methods, with an accuracy rate of 84.5%, which is 15% higher than the average level of colposcopists. It can provide clinicians with auxiliary diagnosis and reduce missed diagnosis and misdiagnosis. [ABSTRACT FROM AUTHOR]

Model incremental updating enhances the initial model by analysing discrepancy parts of the system to improve the model's adaptability for new scenarios. These discrepancy components originate from the deviation between the increasing business process operational state and the outdated original planning model. Considerable domain-specific knowledge is required to determine the threshold points for selecting appropriate activities, but process analysts rarely know each scenario's domain knowledge. Moreover, most analytical processes only focussed on the control flow level. Aiming at these issues, this paper proposes a Hybrid Behavioural and Resource Trusted intervals Updating algorithm (BI&RI Updating) for model enhancement based on control level and resource level of online event streams. First, analyse the reference model to construct multi-perspective trusted interval constraints in the offline stage. From a control-flow perspective, the behavioural relationships between activities are researched using a deep clustering approach. Moreover, from a data-flow standpoint, resource co-occurrence relationships are analysed based on association rules. Next, the incremental update algorithm in online scenarios is proposed to update the model by filtering the event streams and iteratively optimising the trusted intervals. Finally, the proposed algorithm is implemented based on the PM4PY framework and evaluated using real logs with both outcome model quality and execution efficiency. The results show that the algorithm can execute quickly and improve the quality of the model even in a non-ideal state where the logs contain noise. [ABSTRACT FROM AUTHOR]

With the development of IoT technology, more and more IoT devices are connected to the network. Due to the hardware constraints of IoT devices themselves, it is difficult for developers to embed security software into them. Therefore, it is better to protect IoT devices at the traffic level. The effect of malicious traffic detection based on neural networks is promising. Still, the slow computation brings some difficulties to deploying AI-based detection systems on edge servers. Time Convolutional Network (TCN) is a high-speed neural network suitable for massively parallel computation. In this paper, we propose Multi-class S-TCN, an improved network supporting multiple classifications based on TCN for the practical needs of IoT scenarios. Besides, we implement a complete IoT traffic security detection procedure based on deep packet inspection and protocol analysis. The proposed Multi-class S-TCN significantly improves the detection speed without degrading the detection effect. Experiments show that this work has better detection performance and faster detection speed compared to existing approaches, proving the effectiveness of the proposed detection flow and Multi-class S-TCN in IoT scenarios. [ABSTRACT FROM AUTHOR]

Network abnormal traffic detection can monitor the network environment in real time by extracting and analysing network traffic characteristics, and plays an important role in network security protection. In order to solve the problems that the existing detection methods cannot fully learn the spatio-temporal characteristics of data, the classification accuracy is not high, and the detection time and accuracy are susceptible to the influence of redundant data in the sample. Thus, this paper proposes a network abnormal detection method (PCSS) integrating principal component analysis (PCA) and single-stage headless face detector algorithms (SSH). PCSS applies the PCA algorithm to the data preprocessing to eliminate the interference of redundant data. At the same time, PCSS also combines feature fusion and SSH to enhance the feature extraction of unclear features data, and effectively improve the detection speed and accuracy. Simulation experiments based on IDS2017 and IDS2012 data sets are carried out in this paper. Experimental results show that PCSS is obviously superior to other detection models in detection speed and accuracy, which provides a new method for efficiently detecting traffic attacks. [ABSTRACT FROM AUTHOR]

Since 2005, the deep learning community has had access to input graphs to their models. So, the natural language processing (NLP) community started using this technique to process text. However, a challenge that the graph neural networks (GNN) may encounter is the sensibility to representation format. Since different graphs can represent the same text, the model's performance may change depending on the representation used. Even though many practitioners have this intuition, only some works touch on this aspect of GNN. Therefore, we explore twelve different text representation strategies that build graphs from text and apply them to the same GNN to investigate how different graphs may affect the results. We divide these strategies into four groups: reading order, dependency-based, binary tree, and graph of words. From these groups, we created the binary tree group for this paper. Nevertheless, in our tests, we observed that the dependency-based representations tend to achieve better performance: The dependency-based methods allow us to stay competitive in five relevant datasets and beat the state-of-the-art in another dataset. These results suggest that performing representation tuning can be a valuable technique to improve a deep learning model. [ABSTRACT FROM AUTHOR]

Studying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, and substantial advances have been made in the EEG-based classification of emotions. However, using different EEG features and complementarity to discriminate other emotions is still challenging. Most existing models extract a single temporal feature from the EEG signal while ignoring the crucial temporal dynamic information, which, to a certain extent, constrains the classification capability of the model. To address this issue, we propose an Attention-Based Depthwise Parameterized Convolutional Gated Recurrent Unit (AB-DPCGRU) model and validate it with the mixed experiment on the SEED and SEED-IV datasets. The experimental outcomes revealed that the accuracy of the model outperforms the existing state-of-the-art methods, which confirmed the superiority of our approach over currently popular emotion recognition models. [ABSTRACT FROM AUTHOR]

Compiler optimization presents a formidable challenge, seeking to enhance code quality through various techniques. One significant obstacle is the phase-ordering problem, where the sequence of optimization algorithms can impact code quality and potentially lead to performance deterioration. While machine learning has shown promise in addressing this issue, it still encounters limitations in certain scenarios. Instruction Sink is a machine-independent optimization that segregates instructions like modulo and division into separate basic blocks. This separation prevents the application of the machine-dependent optimization called Division-Modulo Combine at the backend, which could otherwise lead to a decline in program performance. However, reordering these optimizations to avoid conflicts can prove to be challenging. In this paper, we propose an algorithm to enhance Instruction Sink, resolving the blocking problem, and implements it within the LLVM optimizer. Leveraging the modularity of LLVM enables us to tackle all affected back-end issues simultaneously. To assess the effectiveness of our algorithm, we conduct a comprehensive evaluation focusing on feasibility, compatibility, and targeted improvements. The results demonstrate that our approach effectively addresses the blocking problem without conflicting with other optimization algorithms, solely impacting problematic instructions while leaving normal ones unaffected. [ABSTRACT FROM AUTHOR]

The continuing prominence of machine learning has led to an increased focus on enhancing the inference performance of edge devices to reduce latency and improve efficiency. Two widely adopted strategies for accelerating computational performance are quantisation and the utilisation of AI hardware accelerators. Each type of accelerator or inference engine offers distinct advantages, with accelerators primarily designed to optimise neural network operations. In this paper, we present an innovative method for integrating TVM's quantisation flow with the MediaTek Neuropilot AI accelerator. We outline the process of converting the TVM relay intermediate-representation quantised neural network dialect model to a tensor-oriented quantisation format, with the aim of harnessing the full potential of both TVM and MediaTek NeuroPilot. This integration enables more efficient neural network inference while preserving the accuracy of the results. We assessed the effectiveness of our proposed integration by conducting a series of experiments and comparing the performance of our approach with that of TVM equipped with an autotuning mechanism. The findings indicate that our approach substantially outperforms TVM in both floating-point model inference and quantised model inference, with inference speedups of up to 11× and up to 70×, respectively. These results underscore the potential of our approach in accelerating AI performance across a diverse range of applications and edge devices. Moreover, a key contribution of our work is providing a valuable practical method for other hardware companies interested in integrating TVM with their own accelerators to achieve performance gains. [ABSTRACT FROM AUTHOR]

Contingency analysis (CA) is one of the essential tools for the optimal design and security assessment of a reliable power system. However, its computational requirements rise with the growth of distributed generations in the interconnected power system. As CA is a complex and computationally intensive problem, it requires a fast and accurate calculation to ensure the secure operation. Therefore, efficient mathematical modelling and parallel programming are key to efficient static security analysis. This paper proposes a parallel algorithm for static CA that uses both central processing units (CPUs) and graphical processing units (GPUs). To enhance the accuracy, AC load flow is used, and parallel computation of load flow is done simultaneously, with efficient screening and ranking of the critical contingencies. We perform extensive experiments to evaluate the efficacy of the proposed algorithm. As a result, we establish that the proposed parallel algorithm with high-performance computing (HPC) computing is much faster than the traditional algorithms. Furthermore, the HPC experiments were conducted using the national supercomputing facility, which demonstrates the proposed algorithm in the context of N−1 and N−2 static CA with immense power systems, such as the Indian northern regional power grid (NRPG) 246-bus and the polish 2383-bus networks. [ABSTRACT FROM AUTHOR]

Mapping-based cross-domain recommendation (CDR) can effectively tackle the cold-start problem in traditional recommender systems. However, existing mapping-based CDR methods ignore data-sparse users in the source domain, which may impact the transfer efficiency of their preferences. To this end, this paper proposes a novel method named Neighbor Interaction-based Personalized Transfer for Cross-Domain Recommendation (NIPT-CDR). This proposed method mainly contains two modules: (i) an intra-domain item supplementing module and (ii) a personalised feature transfer module. The first module introduces neighbour interactions to supplement the potential missing preferences for each source domain user, particularly for those with limited observed interactions. This approach comprehensively captures the preferences of all users. The second module develops an attention mechanism to guide the knowledge transfer process selectively. Moreover, a meta-network based on users' transferable features is trained to construct personalised mapping functions for each user. The experimental results on two real-world datasets show that the proposed NIPT-CDR method achieves significant performance improvements compared to seven baseline models. The proposed model can provide more accurate and personalised recommendation services for cold-start users. [ABSTRACT FROM AUTHOR]

Reliable evaluation of damage in vehicles is a primary concern in the insurance industry. Consequently, solutions enhanced with Artificial Intelligence (AI) have become the norm. During the assessment, precise damage segmentation plays a crucial role. Dent is a type of damage that can commonly occur in vehicles. It is difficult to pinpoint and tends to blend in with the background. This paper proposes a novel loss function to improve dent segmentation accuracy in vehicle insurance claims. Centre and Pixel-based Weighted DICE (CPW-DICE) is a loss function that performs pixel-based weighting. The CPW-DICE aims to concentrate on the centre of the dent damage to lessen faulty segmentations. CPW-DICE generates a weight mask during training by employing ground truth (GT) and prediction masks. Simultaneously, the weight mask is incorporated into DICE loss. Experiments conducted on our comprehensive internal dataset show a 3% improvement in Intersection over Union (IoU) score for three state-of-the-art (SOTA) approaches compared to DICE loss. Finally, CPW-DICE is evaluated in similar tasks to demonstrate its benefits beyond car damage segmentation. [ABSTRACT FROM AUTHOR]

Due to the advantages of all-weather capability and high resolution, synthetic aperture radar (SAR) image ship detection has been widely applied in the military, civilian, and other domains. However, SAR-based ship detection suffers from limitations such as strong scattering of targets, multiple scales, and background interference, leading to low detection accuracy. To address these limitations, this paper presents a novel SAR ship detection method, NAS-YOLOX, which leverages the efficient feature fusion of the neural architecture search feature pyramid network (NAS-FPN) and the effective feature extraction of the multi-scale attention mechanism. Specifically, NAS-FPN replaces the PAFPN in the baseline YOLOX, greatly enhances the fusion performance of the model's multi-scale feature information, and a dilated convolution feature enhancement module (DFEM) is designed and integrated into the backbone network to improve the network's receptive field and target information extraction capabilities. Furthermore, a multi-scale channel-spatial attention (MCSA) mechanism is conceptualised to enhance focus on target regions, improve small-scale target detection, and adapt to multi-scale targets. Additionally, extensive experiments conducted on benchmark datasets, HRSID and SSDD, demonstrate that NAS-YOLOX achieves comparable or superior performance compared to other state-of-the-art ship detection models and reaches best accuracies of 91.1% and 97.2% on AP0.5, respectively. [ABSTRACT FROM AUTHOR]

In the real world, the spread of various epidemics can be modelled using the SEIR disease transmission model. Early detection and prevention of susceptible individuals is an effective method of controlling the spread of infectious viruses. This paper presents a study that detects susceptible community on a hospital contact network, which encompasses patients, nurses, doctors and managers. The goal of our work is to identify susceptible communities with patients and healthcare workers, and analyse the independent contact networks of various roles to determine the high-influence nodes within the hospital contact network. If these high-influence nodes are part of the susceptible community, they should be the focus of observation to prevent the spread of the virus. The proposed model combines social network analysis method and machine learning method with the disease transmission model. This study employs the classic overlapping community detection method CPM for community detection and the PageRank algorithm to rank node influence. The experimental results, obtained from real-world hospital contact networks over a 4-day period, demonstrate the effectiveness of the model. [ABSTRACT FROM AUTHOR]

The Dual-motor multi-gear coupling powertrain (DMCP) has the potential to improve transmission system efficiency and driving comfort, but its complex structure and multiple working modes present challenges. The switching between different modes is easy to cause longitudinal biggish vehicle jerk. To address these issues,this paper introduces the Deep Deterministic Policy Gradient (DDPG) algorithm in the design of an Energy Management Strategy (EMS) that minimises total drive power consumption. And the number of working modes is divided and simplified. The process of switching dual motor and single motor to single motor is introduced in detail. The simulation results using AMESim and MATLAB show that the energy management strategy can effectively improve the economy, achieve no power interruption during mode switching, shift impact is less than 8m/s3, and output torque is remains stable. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are an emerging military and civilian technology that uses sensors. Sensor networks are hierarchical and chaotic in remote, unmonitored sites. Wireless sensor networks pose unique security threats due to their public location and wireless transmission. WSNs are vulnerable to various routing attacks, including Black holes, Sybil, sinkholes and wormholes. In this paper, we proposed advanced intrusion detection systems based on hybrid machine learning (AIDS-HML) in wireless sensor networks to identify and classify attacks. Hybrid machine learning classifiers identify wireless sensor network dangers. Benchmark datasets are used to compare the proposed model to baseline models in terms of precision, recall, f1-score, and accuracy. The scheme is trained and evaluates prediction models. This confirms that the detection accuracy achieved 99.80% using the NSL-KDD benchmark dataset based on hybrid random forest and extreme gradient boost (RF-XGB). The hybrid cluster labelling K-Means (CLK-M) s achieved better classification accuracy of 100% using UNSW_NB15, and CICIDS2017 benchmark datasets for binary classification of label attacks. Different attack detection metrics were compared against various benchmark datasets to evaluate the quality of this work. The proposed system is efficient in simulations for feature extraction and route discovery and detection attacks achieving an accuracy of 99.46%. [ABSTRACT FROM AUTHOR]

Food-oriented cross-modal retrieval aims to retrieve relevant recipes given food images or vice versa. The modality semantic gap between recipes and food images (text and image modalities) is the main challenge. Though several studies are introduced to bridge this gap, they still suffer from two major limitations: 1) The simple embedding concatenation only can capture the simple interactions rather than complex interactions between different recipe components. 2) The image feature extraction based on convolutional neural networks only considers the local features and ignores the global features of an image, as well as the interactions between different extracted features. This paper proposes a novel method based on Latent Component Weight Factors and Global Information (LCWF-GI) to learn the robust recipe and image representations for food-oriented cross-modal retrieval. This proposed method integrates the textual embeddings of different recipe components into a compact embedding to represent the recipes with the latent component-specific weight factors. A transformer encoder is utilised to capture the intra-modality interactions and the importance of different extracted image features for enhanced image representations. Finally, the bi-directional triplet loss is further used to perform retrieval learning. Experimental results on the Recipe 1M dataset show that our LCWF-GI method achieves competent improvements. [ABSTRACT FROM AUTHOR]

Node importance evaluation is a hot issue in complex network analysis. Existing node importance evaluation methods are mainly oriented to homogeneous networks, which ignore the heterogeneity of node types and edges. We propose an MLN critical node evaluation method based on graph convolution. In this paper, we generate the feature matrix of nodes. Considering the diversity of node types in the network, we design an adapted node sampling method based on the meta path. An MLN node embedding model is constructed based on a graph convolutional network (MGC). Besides, the negative sampling technique is used to complete MGC training. Metrics of critical node evaluation are constructed by combining the node embedding vectors and local structural features to evaluate the node's importance. The experimental results show that the proposed method has better evaluation accuracy than the K-Shell algorithm (K-Shell), K-shell-based gravity model ranking algorithm (KSDG), the Page Rank algorithm in MLN (PR), influence maximization based on network embedding (IMNE) and the node ranking algorithm based on information entropy (ERM). [ABSTRACT FROM AUTHOR]

MISRA-C is a writing specification for the C programming language defined by the Motor Industry Software Reliability Association (MISRA). It establishes a set of rules to enhance the development of software that is safe, reliable, and portable. MISRA-C is widely adopted by industries such as aerospace, defense and security, telecommunications, and medical device manufacturers. We developed a static detector of code's compliance with MISRA-C's single-translation-unit rules. The code checker is based on the GNU Compiler Collection (GCC). This paper describes the strategies underlying the detector's design and implementation. For the tested benchmarks, the proposed checker is demonstrated to correctly assess compliance with or violation of all single-translation-unit rules. It can also obtain more accurate and more complete results than Cppcheck, a popular open-source checker. The source code can be downloaded from . [ABSTRACT FROM AUTHOR]

Traffic matrices (TMs) are essential for managing networks. Getting the whole TMs is difficult because of the high measurement cost. Several recent studies propose sparse measurement schemes to reduce the cost, which involve taking measurements on only a subset of origin and destination pairs (OD pairs) and inferring data for unmeasured OD pairs through matrix completion. However, existing sparse network measurement schemes suffer from the problems of high computation costs and low recovery quality. This paper investigates the coherence feature of real traffic flow data traces (Abilene and GÈANT). Both data sets are high coherence, with column coherence greater than row coherence. According to the coherence feature of both data sets, we propose our Redundant Row Subspace-based Matrix Completion (RRS-MC). RRS-MC involves several techniques. Firstly, we design an algorithm to identify subspace rows (OD pairs) from historical data. Secondly, based on the identified subspace rows, we design our sampling scheduling algorithm, which takes full measurement samples in subspace rows while taking partial measurement samples in the remaining rows. Moreover, we propose a redundant sampling rule prevent the recovery accuracy decrease caused by the subspace rows varying. Finally, we design a completion algorithm to recover the partially measured rows. We conduct extensive experiments. Results indicate that the proposed scheme is superior to the state-of-the-art sampling and completion scheme in computation costs and recovery accuracy. [ABSTRACT FROM AUTHOR]

Cloud data auditing is essential to ensure the integrity of cloud data. The main idea of cloud auditing is to entrust the audit task to a third-party auditor (TPA) with powerful computing ability. However, TPA may lead to data leakage and become the single point of failure. Recently, blockchain has been introduced to solve these problems by TPA. However, the dynamic storage structure developed by traditional cloud storage does not apply to the blockchain. This paper proposes a blockchain-based collaborative public auditing scheme for dynamic data. We design the cloud service provider(CSP) to generate a challenge set using the latest block hash. It does not need to interact with the blockchain in the challenge phase, dramatically reducing communication overhead. In addition, considering economic factors, we allow users to seek partners to reduce audit costs. The EigenTrust model evaluates the reputation of each user's audit behaviour, effectively avoiding the probability of malicious users participating. For data update, we introduce the Pseudo Index Linked List(PIL) index management structure, which reduces the size of the index management structure to adapt to the blockchain's characteristics and makes the update operation have a constant time complexity. Through a complete security analysis and performance evaluation, we proved the security and effectiveness of the scheme. [ABSTRACT FROM AUTHOR]

In the age of big data, recipe recommendation is of great significance. It can recommend recipes in line with the user's eating habits in massive data. Compared with other recommendation tasks, recipe recommendation is influenced by multiple aspects and requires fine-grained learning to obtain entity representations. Therefore, the traditional recommendation method cannot meet people's requirements. In this paper, we propose the Collaborative Knowledge Propagation Graph Attention Network for Recipes Recommendation (CGRS). This method designs collaborative information propagation to make full use of user interaction and recipe attribute information to meet the needs of multiple influencing factors. Use the graph attention feature learning network to obtain the high-order feature information of the entity to meet the demand for fine-grained representation. Specifically, the method first obtains the multi-hop triplet sets of users and recipes through a collaborative message propagation strategy. Then utilises a graph attention feature learning layer to learn the topological proximity structure features of the triplet sets. Obtain high-level semantic information of entities by superimposing network layers. Design an attention aggregator at the prediction layer to refine the embedding representation of entities. Finally predict the user-recipe interaction probability. Experimental results prove the advancement and effectiveness of CGRS. [ABSTRACT FROM AUTHOR]

Most studies on privacy in machine learning have primarily focused on supervised learning, with little research on privacy concerns in reinforcement learning. However, our study has demonstrated that observation information can be extracted through trajectory analysis. In this paper, we propose a variable information inference attack targeting the observation space of policy models, which is categorised into two types: observed value inference attack and observed variable inference. Our algorithm has demonstrated a high success rate in privacy inference attacks for both types of observation information. [ABSTRACT FROM AUTHOR]

The deep integration of Internet of Medical Things (IoMT) and Artificial intelligence makes the further development of intelligent medical services possible, but privacy leakage and data security problems hinder its wide application. Although the combination of IoMT and federated learning (FL) can achieve no direct access to the original data of participants, FL still can't resist inference attacks against model parameters and the single point of failure of the central server. In addition, malicious clients can disguise as benign participants to launch poisoning attacks, which seriously compromises the accuracy of the global model. In this paper, we design a new privacy protection framework (BFG) for decentralized FL using blockchain, differential privacy and Generative Adversarial Network. The framework can effectively avoid a single point of failure and resist inference attacks. In particular, it can limit the success rate of poisoning attacks to less than 26%. Moreover, the framework alleviates the storage pressure of the blockchain, achieves a balance between privacy budget and global model accuracy, and can effectively resist the negative impact of node withdrawal. Simulation experiments on image datasets show that the BFG framework has a better combined performance in terms of accuracy, robustness and privacy preservation. [ABSTRACT FROM AUTHOR]

Object detection is a challenging task that requires a large amount of labeled data to train high-performance models. However, labeling huge amounts of data is expensive, making it difficult to train a good detector with limited labeled data. Existing approaches mitigate this issue via active learning or semi-supervised learning, but there is still room for improvement. In this paper, we propose a novel active learning method for deep object detection that fully exploits unlabeled data by combining the benefits of active learning and semi-supervised learning. Our method first trains an initial model using limited labeled data, then uses self-training and data augmentation strategies to train a semi-supervised model using labeled and unlabeled data. We then select query samples based on informativeness and representativeness from the unlabeled data to further improve the model through semi-supervised training. Experimental results on commonly used object detection datasets demonstrate the effectiveness of our approach, outperforming state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In contemporary society people constantly are facing situations that influence appearance of serious diseases. For the development of intelligent decision support systems and services in medical and health domains, it is necessary to collect huge amount of patients' complex data. Patient's multimodal data must be properly prepared for intelligent processing and obtained results should be presented in a friendly way to the physicians/caregivers to recommend tailored actions that will improve patients' quality of life. Advanced artificial intelligence approaches like machine/deep learning, federated learning, explainable artificial intelligence open new paths for more quality use of medical and health data in future. In this paper, we will focus on presentation of a part of a novel Open AI Architecture for cancer patients that is devoted to intelligent medical data management. Essential activities are data collection, proper design and preparation of data to be used for training machine learning predictive models. Another key aspect is oriented towards intelligent interpretation and visualisation of results about patient's quality of life obtained from machine learning models. The Architecture has been developed as a part of complex project in which 15 institutions from 8 European countries have been participated. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) is an active research area in affective computing. Recognizing emotions from speech signals helps to assess human behaviour, which has promising applications in the area of human-computer interaction. The performance of deep learning-based SER methods relies heavily on feature learning. In this paper, we propose SCAR-NET, an improved convolutional neural network, to extract emotional features from speech signals and implement classification. This work includes two main parts: First, we extract spectral, temporal, and spectral-temporal correlation features through three parallel paths; and then split-convolve-aggregate residual blocks are designed for multi-branch deep feature learning. The features are refined by global average pooling (GAP) and pass through a softmax classifier to generate predictions for different emotions. We also conduct a series of experiments to evaluate the robustness and effectiveness of SCAR-NET which can achieve 96.45%, 83.13%, and 89.93% accuracy on the speech emotion datasets EMO-DB, SAVEE, and RAVDESS. These results show the outperformance of SCAR-NET. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has generated massive data in the healthcare sector in recent years, encouraging researchers and scientists to uncover the underlying facts. Mining interesting patterns in the large COVID-19 corpora is very important and useful for the decision makers. This paper presents a novel approach for uncovering interesting insights in large datasets using ontologies and BERT models. The research proposes a framework for extracting semantically rich facts from data by incorporating domain knowledge into the data mining process through the use of ontologies. An improved Apriori algorithm is employed for mining semantic association rules, while the interestingness of the rules is evaluated using BERT models for semantic richness. The results of the proposed framework are compared with state-of-the-art methods and evaluated using a combination of domain expert evaluation and statistical significance testing. The study offers a promising solution for finding meaningful relationships and facts in large datasets, particularly in the healthcare sector. [ABSTRACT FROM AUTHOR]