Abstract Siamese Neural Networks (SNNs) have shown promise in addressing a variety of tasks, even with limited data availability. However, their adoption is hindered by the lack of transparency in their decision-making processes. A key challenge in explaining SNNs lies in the absence of an inverse mapping between high-dimensional input feature vectors and the low-dimensional embedding space. Therefore, computing direct distances between input features becomes meaningless. Existing autoencoder-based explanation methods face several limitations. These include poor image reconstruction quality due to insufficient data and the omission of final distance layer of the SNN during the explanation process. While the Siamese Network Explainer (SINEX) can explain audio and grayscale images, it does not support RGB images. To overcome these challenges, we propose a method called Features Distance-based eXplanation (FDbX). This approach identifies salient features using ridge regression, trained on perturbed SLIC-segmented images. To enhance the selection of important features, we incorporate Bayesian analysis, which assigns importance scores to features. To provide a comprehensive explanation of the decision route, we construct a mathematical model that represents important features and their Hamming distances as a bipartite graph. In this graph, nodes represent features and edges denote distances between feature pairs. The resulting explanation heatmaps highlight critical image segments, offering more intuitive and visually informative explanations than existing methods. We evaluate stability and faithfulness of our method using stability indices such as $$R^2$$ and mean squared error. To the best of our knowledge, this is the first work to introduce Variable and Coefficient Stability Indices for image datasets.

Abstract Events are usually embedded in latent topics and the extraction of these latent topics are enabled by event detection algorithms. Unsupervised algorithms like Clustering algorithms are very useful for detecting events but with requirements which may not be relevant or easy to determine when using unstructured textual social media data. For instance, some algorithms are required to be used on specific data shapes, but determining the shape of an unstructured data may not be practical aside from the high level of noise in the data. Many of the existing algorithms work well with structured data, however, some of these algorithms can be adapted to unstructured data with the caveat that cluster formations may not contain consistent contextual information. We propose a novel Multi-Cycle Recursive Clustering Algorithm (MCRCA), able to sequentially eliminate noise, resulting in high homogeneous cluster formations. MCRCA does not require the initial specification of clusters numbers as the estimated number of clusters can be deduced at convergence. Our algorithm out-performs the classical LDA and K-Means algorithms in forming highly homogeneous clusters, context-wise.

Detection and prevention of fraudulent transactions in e-commerce platforms have always been the focus of transaction security systems. However, due to the concealment of e-commerce, it is not easy to capture attackers solely based on the historic order information. Many works try to develop technologies to prevent frauds, which have not considered the dynamic behaviors of users from multiple perspectives. This leads to an inefficient detection of fraudulent behaviors. To this end, this article proposes a novel fraud detection method that integrates machine learning and process mining models to monitor real-time user behaviors. First, we establish a process model concerning the business-to-customer (B2C) e-commerce platform, by incorporating the detection of user behaviors. Second, a method for analyzing abnormalities that can extract important features from event logs is presented. Then, we feed the extracted features to a support vector machine (SVM)-based classification model that can detect fraud behaviors. We demonstrate the effectiveness of our method in capturing dynamic fraudulent behaviors in e-commerce systems through the experiments.

Abstract With the development of edge computing and artificial intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume. The edge intelligence (EI) has led to the emergence of edge devices in various application domains. The EI can provide efficient services to delay‐sensitive applications, where the edge devices are deployed as edge nodes to host the majority of execution, which can effectively manage services and improve service discovery efficiency. The multilevel index model is a well‐known model used for indexing service, such a model is being introduced and optimized in the edge environments to efficiently services discovery while managing large volumes of data. However, effectively updating the multilevel index model by adding new services timely and precisely in the dynamic edge computing environments is still a challenge. Addressing this issue, this article proposes a designated key selection method to improve the efficiency of adding services in the multilevel index models. Our experimental results show that in the partial index and the full index of multilevel index model, our method reduces the service addition time by around 84% and 76%, respectively when compared with the original key selection method and by around 78% and 66%, respectively when compared with the random selection method. Our proposed method significantly improves the service addition efficiency in the multilevel index model, when compared with existing state‐of‐the‐art key selection methods, without compromising the service retrieval stability to any notable level.

A substantial amount of research has been carried out in Explainable Artificial Intelligence (XAI) models, especially in those which explain the deep architectures of neural networks. A number of XAI approaches have been proposed to achieve trust in Artificial Intelligence (AI) models as well as provide explainability of specific decisions made within these models. Among these approaches, global interpretation methods have emerged as the prominent methods of explainability because they have the strength to explain every feature and the structure of the model. This survey attempts to provide a comprehensive review of global interpretation methods that completely explain the behaviour of the AI models. We present a taxonomy of the available global interpretations models and systematically highlight the critical features and algorithms that differentiate them from local as well as hybrid models of explainability. Through examples and case studies from the literature, we evaluate the strengths and weaknesses of the global interpretation models and assess challenges when these methods are put into practice. We conclude the paper by providing the future directions of research in how the existing challenges in global interpretation methods could be addressed and what values and opportunities could be realized by the resolution of these challenges.

With the access of massive mobile devices, spectrum resources are becoming increasingly scarce. How to effectively and securely utilize the limited spectrum resources has become a fundamental challenge for future mobile communication systems. Focusing on intelligent sensing and sharing, this article proposes a blockchain-based two-stage secure spectrum intelligent sensing and sharing auction mechanism (BISA), which selects appropriate base stations to form a consortium blockchain to guarantee secure and efficient spectrum auction with low complexity. In the first stage, a reverse-auction-based incentive mechanism is presented to provide bidding strategies for the primary users (PUs) and secondary users (SUs) selecting the PU that maximizes the utility. In the second stage, a unit-utility-based auction algorithm is proposed to achieve a stable match between PUs and SUs. PUs will select the SU with the maximum unit utility to complete the auction. Then, the transaction records are formed into blocks and uploaded to guarantee the security of transactions. Simulation results show that, compared with the existing methods, the proposed BISA increases the total utility and throughput of SUs by 216.4% and 189.3%, respectively.

Medical information systems (MIS) play a vital role in managing and scheduling medical resources to underpin healthcare services, which has become more critically important during major public health emergencies. During the Covid-19 pandemic, MIS is facing significant challenges to cope with the surge in demands of medical resources, resulting in more deaths and wider spreading of the disease. Our research examines how to allocate and utilize the medical resources across hospitals in a more accurate, and effective way to mitigate medical resource shortages and sustain the resource provisions. This paper mainly investigated the hospital’s supply-and-demand problems for medical resources under major public health emergencies by analyzing the allocation of medical staff resources. Furthermore, a formal method based on the Colored Petri Nets (CPN) has been proposed to model and characterize the medical business process and resource scheduling tasks. The experiments demonstrate that our approach can correctly and efficiently complete the dynamical scheduling process for surging requests.

Data intensive studies in the domain of accelerator-based High Energy Physics, HEP, have become increasingly more achievable due to the emergence of machine learning with high-performance computing and big data technologies. In recent years, the intricate nature of physics tasks and data has prompted the use of more complex learning methods. To accurately identify physics of interest, and draw conclusions against proposed theories, it is crucial that these machine learning predictions are explainable. For it is not enough to accept an answer based on accuracy alone, but it is important in the process of physics discovery to understand exactly why an output was generated. That is, completeness of a solution is required. In this paper, we survey the application of machine learning methods to a variety of accelerator-based tasks in a bid to understand what role interpretability plays within this area. The main contribution of this paper is to promote the need for explainable artificial intelligence, XAI, for the future of machine learning in HEP.

The diversity and proliferation of Knowledge bases have made data integration one of the key challenges in the data science domain. The imperfect representations of entities, particularly in graphs, add additional challenges in data integration. Graph dependencies (GDs) were investigated in existing studies for the integration and maintenance of data quality on graphs. However, the majority of graphs contain plenty of duplicates with high diversity. Consequently, the existence of dependencies over these graphs becomes highly uncertain. In this paper, we proposed graph probabilistic dependencies (GPDs) to address the issue of uncertainty over these large-scale graphs with a novel class of dependencies for graphs. GPDs can provide a probabilistic explanation for dealing with uncertainty while discovering dependencies over graphs. Furthermore, a case study is provided to verify the correctness of the data integration process based on GPDs. Preliminary results demonstrated the effectiveness of GPDs in terms of reducing redundancies and inconsistencies over the benchmark datasets.

Internet of People (IoP), which focuses on personal information collection by a wide range of the mobile applications, is the next frontier for Internet of Things. Nowadays, people become more and more dependent on the Internet, increasingly receiving and sending information on social networks (e.g., Twitter, etc.); thus social networks play a decisive role in IoP. Therefore, community discovery has emerged as one of the most challenging problems in social networks analysis. To this end, many algorithms have been proposed to detect communities in static networks. However, microblogging social networks are extremely dynamic in both content distribution and topological structure. In this paper, we propose a model for efficient evolutionary user interest community discovery which employs a nature-inspired genetic algorithm to improve the quality of community discovery. Specifically, a preprocessing method based on hypertext induced topic search improves the quality of initial users and posts, and a label propagation method is used to restrict the conditions of the mutation process to further improve the efficiency and effectiveness of user interest community detection. Finally, the experiments on the real datasets validate the effectiveness of the proposed model.

Real-time data processing applications demand dynamic resource provisioning and efficient service discovery, which is particularly challenging in resource-constraint edge computing environments. Network embedding techniques can potentially aid effective resource discovery services in edge environments, by achieving a proximity-preserving representation of the network resources. Most of the existing techniques of network embedding fail to capture accurate proximity information among the network nodes and further lack exploiting information beyond the second-order neighbourhood. This paper leverages artificial intelligence for network representation and proposes a deep learning model, named inductive content augmented network embedding (ICANE), which integrates the network structure and resource content attributes into a feature vector. Secondly, a hierarchical aggregation approach is introduced to explicitly learn the network representation through sampling the nodes and aggregating features from the higher-order neighbourhood. A semantic proximity search model is then designed to generate the top-k ranking of relevant nodes using the learned network representation. Experiments conducted on real-world datasets demonstrate the superiority of the proposed model over the existing popular methods in terms of resource discovery and the query resolving performance.

Online social networks (OSNs) have attracted millions of users worldwide over the last decade. In response to a series of urgent issues faced by existing OSNs, such as information overload, single-point failure, and the privacy issue, this paper introduces a self-organized decentralized OSN (SDOSN) over a social overlay resembling real-life social graph. The social overlay considers social relationship and semantic content of users and focuses on the key OSNs functionality of efficient information dissemination and service discovery. Then a swarm intelligence search method is proposed to facilitate adaptive learning and effective service discovery in decentralized environments. Our evaluation, performed in simulation over a real-world dataset, shows that the proposed approach achieves better performance comparing with the state-of-the-art methods on different network structures.

Internet of Things (IoT) connects billions of devices in an Internet-like structure. Each device encapsulated as a real-world service which provides functionality and exchanges information with other devices. This large-scale information exchange results in new interactions between things and people. Unlike traditional web services, internet of services is highly dynamic and continuously changing due to constant degrade, vanish and possibly reappear of the devices, this opens a new challenge in the process of resource discovery and selection. In response to increasing numbers of services in the discovery and selection process, there is a corresponding increase in number of service consumers and consequent diversity of quality of service (QoS) available. Increase in both sides’ leads to the diversity in the demand and supply of services, which would result in the partial match of the requirements and offers. This paper proposed an IoT service ranking and selection algorithm by considering multiple QoS requirements and allowing partially matched services to be counted as a candidate for the selection process. One of the applications of IoT sensory data that attracts many researchers is transportation especially emergency and accident services which is used as a case study in this paper. Experimental results from real-world services showed that the proposed method achieved significant improvement in the accuracy and performance in the selection process.

With the rapid increase of growth and development in cloud computing it is clear to see that it is becoming a common trend within the industry leading to the adoption by businesses and Information Technology (IT) users alike. Coupled with this trend comes a vast amount of academic research into the cloud computing industry covering most aspects but still leaving some untouched. There is, however, a gap in the academic research for this specific area with current studies focusing on very specific performance issues without considering a general overview of performance. This paper demonstrates the importance of understanding the need to benchmark cloud platforms in order to gain a performance overview of the platforms which one may be integrating into a production environment. This paper investigates the performance of two open source cloud platforms, Open Stack and Cloud Stack. The performance testing is strictly focused on the platforms themselves other than the underlying elements. Therefore, the platforms have both been tested on a mutual hyper visor and mutual available resources. The experiment results demonstrate the advantages of performing cloud management platform benchmarking.