Search

This paper proposes a set of five ethical principles, together with seven high-level messages, as a basis for responsible robotics. The Principles of Robotics were drafted in 2010 and published online in 2011. Since then the principles have influenced, and continue to influence, a number of initiatives in robot ethics but have not, to date, been formally published. This paper remedies that omission. [ABSTRACT FROM PUBLISHER]

This paper proposes a way of understanding the confluence of the enactive approach to cognition and musicology in a wider sense. The implication is that existing socio-cultural approaches to meaning in music – whereby music is seen as a total social phenomenon, and the naturalistic view of music cognition may be articulated via the life-mind continuum proposed by enactivism. On the one hand, discussions on embodied music cognition are presented with the opportunity to overcome their de facto individualism in a principled, naturalistic way. On the other hand, for the socio-cultural-historical approaches the opportunity seems to be to move beyond the biology-culture divide without submitting to reductionism. A wider explanatory unit is presented. The explanatory utility ofembodimentis examined in relation to the wider frame ofsocial-lifein dialectical fashion. A definition ofmusickingis sketched considering it as an instance of processes ofsocial-life.This paper signals a direction to take, yet methodologies, results, and homologies with other disciplines are left open to further discussion. [ABSTRACT FROM PUBLISHER]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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 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]

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]

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]

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]

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 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 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]

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]

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]

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]

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 mobile healthcare (mHealth) is a promising and fascinating paradigm, which can dramatically improve the quality of healthcare delivery by providing remote diagnosis and medical record sharing. Now, the mHealth faces serious challenges such as data leakage and unauthorised access currently. Attribute-based encryption (ABE) which has been employed for mHealth is an excellent cryptographic primitive of securing data sharing. However, there are still some security and efficiency issues in the ABE-based data sharing scheme for mHealth. Firstly, the explicit storage of access policy may expose the privacy of users. Secondly, the computation cost is high, especially in the mHealth with IoT devices. Thirdly, the authentication of access rights to shared data is usually performed by the centralised third parties or IoT devices with limited resources. To handle the above issues, this paper presents a privacy-preserving and efficient data sharing scheme. The scheme partially hides access policy to protect user's privacy, and introduces an offline mechanism in key generation and encryption phase to improve efficiency of mHealth. Furthermore, it also provides decentralised and trusted authentication of data access right based on blockchain. The security proofs and the experiment results demonstrate that the presented scheme has better security and efficiency. [ABSTRACT FROM AUTHOR]

In recent years, numerous studies have applied deep reinforcement learning (DRL) algorithms to vision-guided unmanned aerial systems. However, DRL is not good at training deep networks in an end-to-end manner due to data inefficiency and lack of direct supervision signals. This paper provides a visual information dimension reduction scheme with representation learning as the visual perception module, which reduces the dimensions of high-dimensional visual information and retains its features related to UAV navigation. Combining such state representation learning with the DRL model can effectively reduce the complexity of the neural network required by DRL. Based on this scheme, we design three motion control models with a monocular camera as the main sensor and train them to control UAVs for obstacle avoidance tasks in a simulated environment. Experiments show that all these models achieve high obstacle avoidance ability after a certain period of training. In addition, one of them also enables the monocular vision guidance system to avoid obstacles in the blind spot of side vision. [ABSTRACT FROM AUTHOR]

A graph G is a fractional $ (a,b,n) $ (a , b , n) -critical graph if removing any n vertices from G, the resulting subgraph still admits a fractional $ [a,b] $ [ a , b ] -factor. In this paper, we determine the exact tight isolated toughness bound for fractional $ (a,b,n) $ (a , b , n) -critical graphs. To be specific, a graph G is fractional $ (a,b,n) $ (a , b , n) -critical if $ \delta (G)\ge a+n $ δ (G) ≥ a + n and $ I(G)>a-1+\frac {n+1}{n_{a,b}} $ I (G) > a − 1 + n + 1 n a , b , where $ n_{a,b}\ge 2 $ n a , b ≥ 2 is an integer satisfies $ (n_{a,b}-1)a\le b\le n_{a,b}a-1 $ (n a , b − 1) a ≤ b ≤ n a , b a − 1. Furthermore, the sharpness of bounds is showcased by counterexamples. Our contribution improves a result from [W. Gao, W. Wang, and Y. Chen, Tight isolated toughness bound for fractional $ (k,n) $ (k , n) -critical graphs, Discrete Appl. Math. 322 (2022), 194–202] which established the tight isolated toughness bound for fractional $ (k,n) $ (k , n) -critical graphs. [ABSTRACT FROM AUTHOR]

Offloading data to cloud storage has changed the way people live and work, which reduces data management costs and increases productivity. People can use their devices to download data from cloud storage regardless of location and time. It means that data can be shared across domains through cloud storage. However, offloading data to cloud storage brings convenience as well as various challenges, such as how to solve the performance bottleneck of cloud storage and how to achieve secure data sharing in cloud storage. Blockchain has played an important role in secure data sharing based on its tamper-evident nature. In this paper, a blockchain-assisted data sharing scheme is proposed which implements the detection of deduplicated data and completes the ciphertext combination after deduplication. In order to verify the legitimacy of the ciphertext, blockchain is used to assist in verifying the ciphertext based on its tamper-evident nature. Furthermore, partial ciphertext parameters are calculated at free time to improve server operation efficiency. Finally, we simulated all algorithm of the proposed scheme on the PBC library and the results show that it achieves a balance between usability and performance. [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]

Formulating dialogue policy as a reinforcement learning (RL) task enables a dialogue system to act optimally by interacting with humans. However, typical RL-based methods normally suffer from challenges such as sparse and delayed reward problems. Besides, with user goal unavailable in real scenarios, the reward estimator is unable to generate reward reflecting action validity and task completion. Those issues may slow down and degrade the policy learning significantly. In this paper, we present a novel scheduled knowledge distillation framework for dialogue policy learning, which trains a compact student reward estimator by distilling the prior knowledge of user goals from a large teacher model. To further improve the stability of dialogue policy learning, we propose to leverage self-paced learning to arrange meaningful training order for the student reward estimator. Comprehensive experiments on Microsoft Dialogue Challenge and MultiWOZ datasets indicate that our approach significantly accelerates the learning speed, and the task-completion success rate can be improved from 0.47%∼9.01% compared with several strong baselines. [ABSTRACT FROM AUTHOR]

The orthogonal projection method has made significant progress in text classification, especially in generating discriminative features. This method obtains more pure and suitable for classification features by projecting text features onto the orthogonal direction of common features (which are not helpful for classification and actually confuse performance). However, this approach requires an additional branch network to generate these common features, which reduces the flexibility of this method compared to representation optimisation methods such as self-attention mechanisms, as it requires significant modification of the base network structure to use. To address this issue, this paper proposes the Inversed Attention Orthogonal Projection Module (IAOPM). IAOPM uses inversed attention (IA) to iteratively reverse the attention map on text features, encouraging the network to remove discriminating features from the text features and obtain potential common features. Unlike the original orthogonal projection method, IAOPM can extract common features within a single network without any branch networks, increasing the flexibility of the orthogonal projection method. We also use an orthogonal loss to ensure the quality of the common features during training, so IAOPM also has better purity performance than the original method. Experiments show that text classification models based on IAOPM outperform the baseline models, self-attention mechanisms, and the original orthogonal projection method on multiple text classification datasets with an average accuracy increase of 1.02%, 0.44%, and 0.52%, respectively. [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]

For autonomous vehicles, free-space detection is an essential part of visual perception. With the development of multi-modal convolutional neural networks (CNNs) in recent years, the performance of driving scene semantic segmentation algorithms has been dramatically improved. Therefore most free-space detection algorithms are developed based on multiple sensors. However, multi-modal CNNs have high data throughput and contain a large number of computationally intensive convolution calculations, limiting their feasibility for real-time applications. Field Programmable Gate Arrays (FPGAs) provide a unique combination of flexibility, performance, and low power for these problems to accommodate multi-modal data and the computational acceleration of different compression algorithms. Network lightweight methods offer great assurance for facilitating the deployment of CNNs on such resource-constrained devices. In this paper, we propose a network lightweight method for a multi-modal free-space detection algorithm. We first propose an FPGA-friendly multi-modal free-space detection lightweight network. It comprises operators that FPGA prefers and achieves a $ 95.54\% $ 95.54 % MaxF score on the test set of KITTI-Road free-space detection tasks and 81 ms runtime when running on 700 W GPU devices. Then we present a pruning approach for this network to reduce the number of parameters in case the complete model exceeds the FPGA chip memory. The pruning is in two parts. For the feature extractors, we propose a data-dependent filter pruner according to the principle that the low-rank feature map contains less information. To not compromise the integrity of the multi-modal information, the pruner is independent for each modality. For the segmentation decoder, we apply a channel pruning approach to remove redundant parameters. Finally, we implement our designs on an FPGA board using 8-bit quantisation, and the accelerator achieves outstanding performance. A real-time application of scene segmentation on KITTI-Road is used to evaluate our algorithm, and the model achieves a $ 94.39\% $ 94.39 % MaxF score and minimum 14 ms runtime on 20W FPGA devices. [ABSTRACT FROM AUTHOR]

The exclusion operator is a key component in separating the search territory of each population in multi-population optimisation algorithms for unconstraint continues dynamic optimisation problems (DOPs) with the aim of maintaining the overall diversity of the population and avoiding redundant search. Although extensively used by the researchers, the role of exclusion has been barely studied in detail. Therefore, in this paper, we solely study the role of exclusion as a part of multi-population methods in DOPs. For this purpose, a comprehensive review of the various exclusion strategies reported in the literature is provided. Four strategies are also introduced to reduce the shortcomings of exclusion operator. Experimental results show that proposed strategies compared to other schemes such as reinitialized midpoint check, hill-valley detection with three checkpoints, and merging information of collided populations have the same or even higher ability to improve the performance of the multi-swarm PSO algorithms in moving peaks benchmark. [ABSTRACT FROM AUTHOR]

Water Wave Optimisation algorithm (WWO) is a new swarm-based metaheuristic inspired by shallow wave models for global optimisation. In this paper, an enhanced WWO, which combines with multiple assistant strategies (EWWO), is proposed. First, the random opposition-based learning (ROBL) mechanism is introduced to generate the initial population with high quality. Second, a new modified operation is designed and embedded into propagation operation to balance the global exploration and the local exploitation. Third, the covariance matrix self-adaptation evolution strategy (CMA-ES) is employed by the refraction operation to further strengthen the local exploitation. Furthermore, the diversity of the population is maintained in the evolution process by using a crossover operator. The experiment results based on CEC 2017 benchmarks indicate that the EWWO outperforms the state-of-the-art variant algorithms of the WWO and the standard WWO. [ABSTRACT FROM AUTHOR]

The present paper aims to extend the potential learning method to overcome the problem of collective interpretation, which aims to interpret multi-layered neural networks by compressing them into the simplest ones. In the process of compression, positive, negative, and complicated weights have had unfavourable effects for interpretation. To deal with the problems of collective interpretation, the potential learning is extended only to use positive weights. In addition, to obtain more appropriate weights for interpretation, the number of candidate weights for higher potentialities is first increased as much as possible. Then, from among many candidates, more appropriate weights are selected as more important ones. This extended potentiality learning is expected to produce more stable and more simple representations for easy interpretation. The extended method was applied to three datasets, namely, an artificial dataset, a real eye-tracking dataset, and a student evaluation dataset. In all cases, it was observed that the selectivity of connection weights could be increased. Correspondingly, the majority of connection weights became positive, and the collective weights were quite similar to the regression coefficients of the logistic regression analysis. Finally, for the third dataset (student evaluations), the extended method could extract more explicit input-output relations, compared with the logistic regression analysis, while improving generalisation performance. [ABSTRACT FROM AUTHOR]

In this paper, we develop a numerical method for solving the delay optimal control problems of fractional-order. The fractional derivatives are considered in the Caputo sense. The process begins with the assumption that the problem is first transformed into an equivalent problem with a fractional dynamical system without delay, using a Padé approximation. We then try to approximate the solution of the Hamiltonian conditions based on the Pontryagin minimum principle. The main feature is to implement nonlinear polynomial expansions in a neural network adaptive structure. The transfer functions of the employed neural network follow a fractional power series. The proposed technique does not use sigmoid or hyperbolic tangent nonlinear transfer functions commonly adopted in conventional neural networks at the output. Instead, linear transfer functions are employed which lead to explicit fractional power series formulae for the fractional optimal control problem. To do this, we use trial solutions for the states, Lagrange multipliers and control functions where these trial solutions are constructed by fractional power series neural network model. We then minimise the error function using an unconstrained optimisation scheme where weight parameters (or coefficients of the series) and biases associated with all neurons are unknown. Some numerical examples are given to illustrate the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Feature selection is an important task to improve the classifier's accuracy and to decrease the problem size. A number of methodologies have been presented for feature selection problems using metaheuristic algorithms. In this paper, an improved self-adaptive inertia weight particle swarm optimisation with local search and combined with C4.5 classifiers for feature selection algorithm is proposed. In this proposed algorithm, the gradient base local search with its capacity of helping to explore the feature space and an improved self-adaptive inertia weight particle swarm optimisation with its ability to converge a best global solution in the search space. Experimental results have verified that the SIW-APSO-LS performed well compared with other state of art feature selection techniques on a suit of 16 standard data sets. [ABSTRACT FROM AUTHOR]

Vertex colouring is among the most important problems in graph theory which has been widely applied across different real-world problems. In vertex colouring problem (VCP), the goal is to assign a distinct colour to each vertex of the graph in such a way that no two adjacent vertices have the same colour. This paper presents a fuzzy irregular cellular automaton (FICA) for finding a near-optimal solution for the VCP. FICA is an extension fuzzy cellular automaton (FCA) in which the cells of the automaton can be arranged in an irregular structure. The aim of the proposed method is to reap the benefits of both FCA and irregular cellular automata while minimising their drawbacks. To evaluate the proposed method, various computer simulations have been conducted on a variety of graphs. The results suggest that the proposed method is able to achieve better results in terms of the minimum number of required colours and the execution time of the algorithm, compared to other peer algorithms. [ABSTRACT FROM AUTHOR]

For the sake of enhancing the identification ability of current network and meeting the needs of the high accuracy of distinguishing similar small objects (foliage) in the complex scenes, this paper proposes a modified region-based fully convolutional network which adopts Inception V3 accompanying with residual connection as the main framework. Incorporating deep residual learning module into Inception V3 can not only save the computational cost by factorising convolutions, but also mitigate the vanishing gradients causing the increasing depth of the network. Additionally, this combination can alleviate the degradation problem in the process of extracting features and providing proposals. Experimental results show that the modified approach can identify out different leaves with similar characteristics in one scene, and demonstrate the superiority of our proposed approach over some state-of-the-art deep neural networks, when it comes to recognise foliage in complicated environments. [ABSTRACT FROM AUTHOR]

This paper reports an extension of the program MEXICA, an automatic plot generator. The purpose of this project is to build a framework that permits studying the relations between MEXICA's processes, its knowledge structures and the features of the produced narratives. We describe a methodology to analyse the features of the agent's knowledge-base, to further establish correlations between such features and a set of general characteristics of the tales that they produce. Next, we make use of those correlations to forecast some properties of the future tales to be developed by different MEXICAs agents with different knowledge-bases. For this task, we introduce the S-graphs, representations of the similarity and organisation of the knowledge-structures. The results we obtained indicate that we are able to correctly forecast some of the features of tales to be produced; however, much more work is required. [ABSTRACT FROM AUTHOR]

In this paper, we propose a multi-objective differential evolution-based filter approach for feature selection that interconnects fuzzy- and kernel-based information theory measures to find feature subsets that are optimal responses to the targets. In contrast to the existing filter approaches using the principles of information theory and rough set theory, our approach can be applied to continuous datasets without discretisation. Moreover, our study is the first in the literature that employs fuzzy and kernel measures to form a filter criterion for feature selection, to our knowledge. We prove various favourable results using a variety of benchmark datasets and also demonstrate that our approach can better search the dimensionality space to reach maximum predictive of the response. [ABSTRACT FROM AUTHOR]