Search

3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors. Due to the increasing development and understanding of Deep Neural Networks (DNNs) and the availability of large-scale human motion datasets, the human motion prediction has been remarkably advanced with a surge of interest among academia and industrial community. In this context, a comprehensive survey on 3D human motion prediction is conducted for the purpose of retrospecting and analyzing relevant works from existing released literature. In addition, a pertinent taxonomy is constructed to categorize these existing approaches for 3D human motion prediction. In this survey, relevant methods are categorized into three categories: human pose representation , network structure design , and prediction target. We systematically review all relevant journal and conference papers in the field of human motion prediction since 2015, which are presented in detail based on proposed categorizations in this survey. Furthermore, the outline for the public benchmark datasets, evaluation criteria, and performance comparisons are respectively presented in this paper. The limitations of the state-of-the-art methods are discussed as well, hoping for paving the way for future explorations. [ABSTRACT FROM AUTHOR]

Graph neural networks are widely employed in diverse domains; however, they confront the peril of privacy infringement. To address this concern, federated learning emerges as a privacy-preserving approach that avoids sharing data for model training, effectively resolving the issue of privacy leakage in graph neural networks. The rapid advancement of federated neural networks has spurred the demand for more potent tools to enhance model performance owing to the concealed correlation information amongst federated learning participants. However, the structural attributes of federated graph neural networks render them vulnerable to inference attacks, reconstruction attacks, inversion attacks, and the like, potentially endangering privacy. This study delves into the intricacies of privacy-preserving within federated graph neural networks. Firstly, it introduces the architecture and variants of federated graph neural networks, analyzes the privacy risks encountered by these networks from four perspectives, and elucidates three primary attack methods. In accordance with the privacy-preserving mechanism of federated graph neural networks, it summarizes the privacy-preserving techniques and synthesizes the existing strategies from four perspectives: encryption methods, perturbation methods, anonymization, and hybrid methods. Furthermore, it summarily presents the prevailing framework for preserving privacy in neural networks. Ultimately, this paper examines the challenges and outlines future research directions pertaining to federated graph neural network technology. • This study investigates the privacy leakage risks of FedGNNs, summarizing and analyzing these risks and attack methods to provide a multifaceted investigation for privacy-preserving FedGNNs. • It collates cutting-edge research results and classifies protection mechanisms into encryption-based, perturbation-based, anonymization-based, and hybrid techniques, detailing their advantages and shortcomings. • The paper proposes future research directions for building robust, interpretable, efficient, fair, inductive, and comprehensive FedGNNs. [ABSTRACT FROM AUTHOR]

In recent years, multi-agent reinforcement learning techniques have been widely used and evolved in the field of artificial intelligence. However, traditional reinforcement learning methods have limitations such as long training time, large sample data requirements, and highly delayed rewards. Therefore, this paper systematically and specifically studies the MARL algorithm. Firstly, this paper uses Citespace software to visually analyze the existing literature on multi-agent reinforcement learning and briefly indicates the research hotspots and key research directions in this field. Secondly, the applications of traditional reinforcement learning algorithms under two task objects, namely single-agent and multi-agent systems, are described in detail. Then, the paper highlights the diverse applications, challenges, and corresponding solutions of MARL algorithmic techniques in the field of MAS. Finally, the paper points out future research directions based on the existing limitations of the algorithm. Through this paper, readers will gain a systematic and in-depth understanding of MARL algorithms and how they can be utilized to better address the various challenges posed by MAS. [ABSTRACT FROM AUTHOR]

With the popularization of computer technology, the number of malware has increased dramatically in recent years. Some malware can threaten the network security of users by downloading and installing, and even spreading widely on the Internet, causing consequences such as private data leakage in the operating system, extortion, and network paralysis. In order to deal with these threats, researchers analyze malicious samples through various analysis techniques, which are usually divided into static and dynamic analysis based on the principle of whether the code needs to be executed or not. This paper analyzes in detail several classical methods of feature extraction in malware detection techniques. With the technological development of artificial intelligence, deep learning is gradually being introduced into malware detection, which does not require the identification of professional security personnel and greatly improves the generalization ability of detection. In the paper, text-based detection methods, image visualization-based detection, and graph structure-based detection techniques are reviewed according to different feature extraction methods. In addition, the paper compares 26 datasets that have been commonly used in recent years applied in the research field and explains the main contents and specifications of the datasets. Finally, a summary and outlook of the malware research field is given. [ABSTRACT FROM AUTHOR]

Federated learning has emerged as an effective paradigm to achieve privacy-preserving collaborative learning among different parties. Compared to traditional centralized learning that requires collecting data from each party, in federated learning, only the locally trained models or computed gradients are exchanged, without exposing any data information. As a result, it is able to protect privacy to some extent. In recent years, federated learning has become more and more prevalent and there have been many surveys for summarizing related methods in this hot research topic. However, most of them focus on a specific perspective or lack the latest research progress. In this paper, we provide a systematic survey on federated learning, aiming to review the recent advanced federated methods and applications from different aspects. Specifically, this paper includes four major contributions. First, we present a new taxonomy of federated learning in terms of the pipeline and challenges in federated scenarios. Second, we summarize federated learning methods into several categories and briefly introduce the state-of-the-art methods under these categories. Third, we overview some prevalent federated learning frameworks and introduce their features. Finally, some potential deficiencies of current methods and several future directions are discussed. [ABSTRACT FROM AUTHOR]

Modern and new integrated technologies have changed the traditional systems by using more advanced machine learning, artificial intelligence methods, new generation standards, and smart and intelligent devices. The new integrated networks like the Internet of Things (IoT) and 5G standards offer various benefits and services. However, these networks have suffered from multiple object detection, localization, and classification issues. Conventional Neural Networks (CNN) and their variants have been adopted for object detection, classification, and localization in IoT networks to create autonomous devices to make decisions and perform tasks without human intervention and helpful to learn in-depth features. Motivated by these facts, this paper investigates existing object detection and recognition techniques by using CNN models used in IoT networks. This paper presents a Conventional Neural Networks for 5G-Enabled Internet of Things Network (CNN-5GIoT) model for moving and static objects in IoT networks after a detailed comparison. The proposed model is evaluated with existing models to check the accuracy of real-time tracking. The proposed model is more efficient for real-time object detection and recognition than conventional methods. [ABSTRACT FROM AUTHOR]

Knowledge Graph (KG) stores human knowledge facts in an intuitive graphical structure but faces challenges such as incomplete construction or inability to handle new knowledge. Knowledge Graph Reasoning (KGR) can make KGs more accurate, complete, and trustworthy to support various artificial intelligence applications better. Currently, the popular KGR methods are based on graph neural networks (GNNs). Recent studies have shown that hybrid logic rules and synergized pre-trained language models (PLMs) can enhance the GNN-based KGR methods. These methods mainly focus on data sparsity, insufficient knowledge evolution patterns, multi-modal fusion, and few-shot reasoning. Although many studies have been conducted, there are still few review papers that comprehensively summarize and explore KGR methods related to GNNs, logic rules, and PLMs. Therefore, this paper provides a comprehensive review of GNNs and PLMs for KGR based on a large number of high-quality papers. To present a clear overview of KGR, we propose a general framework. Specifically, we first introduce the KG preparation. Then we provide an overview of KGR methods, in which we categorize KGR methods into GNNs-based, logic rules-enhanced, and pre-trained language models-enhanced KGR methods. Furthermore, we also compare and analyze the GNN-based KGR methods in two scenarios. Moreover, we also present the application of KGR in different fields. Finally, we discuss the current challenges and future research directions for KGR. • Proposing the general framework for knowledge graph reasoning. • Systematic review of GNNs and PLMs for knowledge graph reasoning. • Performance evaluation and in-depth analysis of knowledge graph reasoning methods. • Practical application of knowledge graph reasoning methods in various fields. • Identifying current challenges and future directions in knowledge graph reasoning. [ABSTRACT FROM AUTHOR]

This paper engages in a comprehensive investigation concerning the application of Explainable Artificial Intelligence (xAI) within the context of deep learning and Artificial Intelligence, with a specific focus on its implications for cybersecurity. Firstly, the paper gives an overview of xAI techniques and their significance and benefits when applied in cybersecurity. Subsequently, the authors methodically delineate their systematic mapping study, which serves as an investigative tool for discerning the potential trajectory of the field. This strategic methodological framework lets one identify the future research directions and opportunities that underlie the integration of xAI within the realm of Deep Learning, Artificial Intelligence, and cybersecurity, which are described in-depth. Then, the paper brings together all the gathered insights from this extensive investigation and closes with final conclusions. • Application of xAI in Network Intrusion Detection. • Research directions in integrating xAI with cybersecurity. • Guide for developing impactful xAI solutions. [ABSTRACT FROM AUTHOR]

Low computational cost artificial intelligence (AI) models are vital in promoting the accessibility of real-time medical services in underdeveloped areas. The recent Once-For-All (OFA) network (without retraining) can directly produce a set of sub-network designs with Progressive Shrinking (PS) algorithm; however, the training resource and time inefficiency downfalls are apparent in this method. In this paper, we propose a new OFA training algorithm, namely the Progressive Expansion (ProX) to train the medical image analysis model. It is a reversed paradigm to PS, where technically we train the OFA network from the minimum configuration and gradually expand the training to support larger configurations. Empirical results showed that the proposed paradigm could reduce training time up to 68%; while still being able to produce sub-networks that have either similar or better accuracy compared to those trained with OFA-PS on ROCT (classification), BRATS and Hippocampus (3D-segmentation) public medical datasets. The code implementation for this paper is accessible at: https://github.com/shin-wl/ProX-OFA. [ABSTRACT FROM AUTHOR]

Structure from motion (SFM), a research hotspot in the intelligent transportation field (including autonomous driving, environmental perception and augmented reality (AR) for artificial intelligence terminals), can automatically recover ego-motion state estimations and 3D scene reconstructions from multiple images or video sequences. Most existing vision methods operate offline in indoor scenes, and their reconstruction accuracies greatly depend on the tracking lifetimes and accuracies of feature points. Reprojection matrix and redundant regression noise computations are exponential disasters for the calculation and reconstruction drift of large-scale scenes. This paper proposes a quadruple tripatch-wise modular architecture (QTMA) for autonomous vehicle stereo image sequences that decomposes rigid scenes into nonrigid motion-segmented pieces for reconstruction. An advanced energy function for salient image features is established by combining multiple feature types with weighted finite-element mesh. Closed quadruple annular matching and relocation are performed via multiresolution pyramid images. The proposed incremental integral-mapping calculation method and unique tree-like stacked storage containers prolong the tracking lifetimes of consecutive frames and ensure the spatiotemporal consistency and robustness of the homonymous image features in different subsequences. Experimental results verify the effectiveness of this architecture for different transportation scenes; the frame rate processing speed reaches 30 fps, the calculation accuracy regarding the path distance difference reaches 99.49%, and the estimation results regarding the maximum speeds of motion are closer to the ground truth. The translation error of the motion pose is 0.0136%, and the rotation error is 0.0035 [deg/m], which has more yaw stability than the existing state-of-the-art methods. Furthermore, in the reconstructed point cloud quality demonstration, the mean value of roughness is reduced by 40.127%, the mean value of density is improved by 27.701%, and the accuracy reaches 91.149% within a certain distance tolerance. This paper has significant theoretical research value and application potential for positioning, path tracking, and navigation in adaptive cruise control (ACC) and advanced driver assistance systems (ADAS). [ABSTRACT FROM AUTHOR]

The purpose of this paper is to give an overview of various well known medical image registration techniques with a special focus on registration between anatomical and functional medical images. Examples of anatomical medical images (AMI) are Computer Tomography (CT), Magnetic Resonance Images (MRI), X-ray radiographs and ultrasound etc. whereas Positron Emission Tomography (PET), Single Photon Emission Tomography (SPECT) and fMRI are examples of functional medical images (FMI). Irrespective of such types (AMI or FMI), every case can be considered as a medical imaging modality. All these modalities are widely used by clinicians to study the structure/functionality of human body parts for diagnosis and treatment. It is frequently required to combine PET/SPECT with CT/MRI to simultaneous study the metabolic and molecular information received through PET/SPECT with fine anatomical details observed by CT/MRI. This concurrent study will help in the diagnosis and localization of many diseases like cancer, blockage in coronary arteries and brain-related diseases like Parkinson, Alzheimer etc. Further, in many cases, clinicians are required to co-register one or more anatomical images with functional images, for example, ultrasound-guided biopsy fused with PET and MRI. This registration can be done either at the hardware level or at the software level. The introduction of integrated PET-CT machine increases the acceptability of hardware-based registration systems as compared to software-based methods among the medics. One possible reason for this is the lack of validation of results achieved through software-based registration methods. On the other hand, software-based registration methods also have many advantages over the hardware-based registration systems like lesser exposure to radiation and no need for new investment on hardware etc. In this paper, both the methods with their merits and demerits are discussed in detail. [ABSTRACT FROM AUTHOR]

• Novel distributional RL algorithm based on unconstrained monotonic neural networks. • Monotonicity ensures the validity of the random return probability distribution. • Methodology to learn different representations of the random return distribution. • Empirical comparison of the probability metrics commonly used in distributional RL. • Critical approximation highlighted for the extensively used Wasserstein distance. The distributional reinforcement learning (RL) approach advocates for representing the complete probability distribution of the random return instead of only modelling its expectation. A distributional RL algorithm may be characterised by two main components, namely the representation of the distribution together with its parameterisation and the probability metric defining the loss. The present research work considers the unconstrained monotonic neural network (UMNN) architecture, a universal approximator of continuous monotonic functions which is particularly well suited for modelling different representations of a distribution. This property enables the efficient decoupling of the effect of the function approximator class from that of the probability metric. The research paper firstly introduces a methodology for learning different representations of the random return distribution (PDF, CDF and QF). Secondly, a novel distributional RL algorithm named unconstrained monotonic deep Q-network (UMDQN) is presented. To the authors' knowledge, it is the first distributional RL method supporting the learning of three , valid and continuous representations of the random return distribution. Lastly, in light of this new algorithm, an empirical comparison is performed between three probability quasi-metrics, namely the Kullback–Leibler divergence, Cramer distance, and Wasserstein distance. The results highlight the main strengths and weaknesses associated with each probability metric together with an important limitation of the Wasserstein distance. [ABSTRACT FROM AUTHOR]

Clustering validation and identifying the optimal number of clusters are crucial in expert and intelligent systems. However, the commonly used cluster validity indices (CVI) are not relevant enough to measure data structures. They do not embed the necessary mechanisms to be as effective as that of the clustering algorithm used to give the clustering results. This paper proposes a novel CVI called PDBI (Partitioning Davies-Bouldin Index) initially inspired from the native idea of the Davies-Bouldin Index (DBI). PDBI is based on a strategy that consists in dividing each cluster into sub-clusters that redefine the concepts of internal homogeneity and cluster separation via the integration of sophisticated mechanisms. This strategy makes it possible to process a relevant CVI even in the case of complex data structures and in presence of clusters with noisy patterns. PDBI is deterministic, runs independently of a given clustering algorithm and generates a normalized score between 0 and 1. Numerous tests were carried out using 2-dimensional benchmark data sets and data generated in higher dimensions with consistent ground truths. The experimental comparisons with the state-of-the-art validity indices demonstrate the efficiency of the proposal in discovering the true number of clusters and dealing with various sorts of data sets. The PDBI demonstration as well as illustrations can be found on the author's website 1 1 A demonstration is available at: http://r-riad.net/ [ABSTRACT FROM AUTHOR]

The connection between humans and digital technologies has been documented extensively in the past decades but needs to be evaluated through the current global pandemic. Artificial Intelligence(AI), with its two strands, Machine Learning (ML) and Semantic Reasoning, has proven to be a great solution to provide efficient ways to prevent, diagnose and limit the spread of COVID-19. IoT solutions have been widely proposed for COVID-19 disease monitoring, infection geolocation, and social applications. In this paper, we investigate the usage of the three technologies for handling the COVID-19 pandemic. For this purpose, we surveyed the existing ML applications and algorithms proposed during the pandemic to detect COVID-19 disease using symptom factors and image processing. The survey includes existing approaches including semantic technologies and IoT systems for COVID-19. Based on the survey result, we classified the main challenges and the solutions that could solve them. The study proposes a conceptual framework for pandemic management and discusses challenges and trends for future research. [ABSTRACT FROM AUTHOR]

Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the interplay between natural and artificial computation. A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence. Moreover, this paper aims to provide a complete analysis and some relevant discussions of the current trends and insights within several theoretical and application fields covered in the essay, from theoretical models in artificial intelligence and machine learning to the most prospective applications in robotics, neuroscience, brain computer interfaces, medicine and society, in general. [ABSTRACT FROM AUTHOR]

Implementing associative memory experiments with nanoscale memristors is an interesting subject, which can allow robots to mimic human thinking. This paper is concerned with a new emotion model of memristor-based neural network and its circuit implementation. The model has three inputs and two outputs, which can feel happy when it receives good news or feel sad when it receives bad news. Unknown news can be recognized through associative memory, which simulates human emotions. Associative learning and three kinds of forgetting process together make up the full-function emotion model. In addition, the Ag/AgInSbTe/Ta-based model closely related to the actual physical properties of memristors is used to design synaptic structures. The circuits of memristor-based neural networks are also simplified. Furthermore, the new emotion model is able to adjust the changing rate of emotion. The process reflects the fact that humans learn the same thing faster at the second time, compared with the first time. Finally, PSPICE is used to simulate all the circuits of the emotion model. The presented emotion model in this paper offers more possibilities for designing intelligent machines. [ABSTRACT FROM AUTHOR]

Image classification, which is a fundamental element of Computer Vision (CV) and Artificial Intelligence (AI), has been researched intensively in numerous domains and embedded in many products. However, with the exponential increase in the number of images and the complexity of the required tasks, deep-learning classification algorithms demand more intensive resources and computational power to train the models and update the massive number of parameters. Quantum computing is a new research technology with a promising capability of exponential speed up and operational parallelization with its unique phenomena including superposition and entanglement. Researchers have already started utilizing Quantum Deep Learning (QDL) and Quantum Machine Learning (QML) in image classification. Yet, to our knowledge, there exists no comprehensive published literature review on quantum image classification. Therefore, this paper analyzes the advances in this field by dividing the studies based on a unique taxonomy, discussing the limitations, summarizing essential aspects of each research, and finally, emphasizing the gaps, challenges, and recommendations. One of the key challenges presented in the paper is that quantum computers are in the Noisy Intermediate-Scale Quantum (NISQ) era, where they contain a limited number of noisy qubits, therefore challenging complex quantum classifiers and complex images from advanced datasets. This research recommends constructing a novel quantum image encoding method that adapts to the available number of qubits and enables RGB images as a critical contribution to the existing research. [ABSTRACT FROM AUTHOR]

The abundance of artificial intelligence AI algorithms and growing computing power has brought a disruptive revolution to the smart medical industry. Its powerful data abstraction and representation capabilities enable the modeling of hundreds of millions of medical data, such as sub-Computed Tomography tumor identification, retinal lesion screening, and survival curve analysis. However, all of these applications demonstrate AI's use of unimodal data for specific tasks. In contrast, clinicians deal with multi-modal data from multiple sources when diagnosing, performing prognostic assessments, and deciding on treatment plans. These requirements have facilitated the development of multi-modal AI solutions and improved the performance of AI models in handling complex medical scenarios and data. In this paper, we provide an overview of the current state of the art and research in multi-modal biomedical AI, including applications, data, methods, and analytics. Additionally, we summarize potential research directions for multi-modal AI technologies in the future of healthcare. • Multi-modal medical AI aims to process and link diverse data types to benefit healthcare and society. • Various data pre-processing methods are outlined to prepare multi-modal data for model training. • Multi-modal data fusion strategies are discussed, including data-level, feature-level, decision-level, and model-level fusion. • Several multi-modal applications and related biomedical tasks are summarized. • The paper highlights future challenges in technology, data, and privacy. [ABSTRACT FROM AUTHOR]

• First paper to summarize existing adversarial examples attacks in the object detection field. • We innovatively classify the attacking models by the characteristic of object detection tasks which can be treated as a multitasking process. • The comparison between the two main processes of attacking object detection is generalized. • Analyzed different results for attacking regression and positioning processes in object detection tasks. Deep learning plays a critical role in the applications of artificial intelligence. The trend of processing images or videos as input data and pursuing execution efficiency in practical applications is unstoppable. However, the vulnerability due to the complex structure of deep networks makes it at risk of attacks. Object detection, as the significant product impacted by the deep learning frame, corresponds to this weakness implicated by its multiple-tasks property. Besides, these applications involving object detection techniques are integrated deeply into our lives, potentially leading to unimaginable loss. Adversarial example attacks, as the mainstream attack method, provide an efficacious and comprehensible idea to generate perturbation. In this survey, we review the existing adversarial example attacks in object detection tasks and inductively discuss the similarity and differences among these approaches. Finally, we construct this survey for discussing the attacks in the object detection field and point out the possible direction for adversarial defenses in future studies. [ABSTRACT FROM AUTHOR]

Precision Agriculture (PA) promises to boost crop productivity while reducing agricultural costs and environmental footprints, and therefore is attracting ever-increasing interests in both academia and industry. This management strategy is underpinned by various advanced technologies including Unmanned Aerial Vehicle (UAV) sensing systems and Artificial Intelligence (AI) perception algorithms. In particular, due to their unique advantages such as a low cost, high spatio-temporal resolutions, flexibility, automation functions and minimized risk of operation, UAV sensing systems have been extensively applied in many civilian applications including PA since 2010. In parallel, AI algorithms (deep learning since 2012 in particular) are also drawing ever-increasing attention in different fields, since they are able to analyse an unprecedented volume/velocity/variety of data (semi-) automatically, which are also becoming computationally practical with the advancements of cloud computing, Graphics Processing Units and parallel computing. In this survey paper, therefore, a thorough review is performed on recent use of UAV sensing systems (e.g., UAV platforms, external sensing units) and AI algorithms (mainly supervised learning algorithms) in PA applications throughout the crop life-cycle, as well as the challenges and prospects for future development of UAVs and AI in agriculture sector. It is envisioned that this review is able to provide a timely technical reference, demystifying and promoting research, deployment and successful exploitation of AI empowered UAV perception systems for PA, and therefore contributing to addressing future agricultural and human nutrition challenges. [ABSTRACT FROM AUTHOR]

Deep reinforcement learning has shown useful in the field of robotics but the black-box nature of deep neural networks impedes the applicability of deep reinforcement learning agents for real-world tasks. This is addressed in the field of explainable artificial intelligence, by developing explanation methods that aim to explain such agents to humans. Model trees as surrogate models have proven useful for producing explanations for black-box models used in real-world robotic applications, in particular, due to their capability of providing explanations in real time. In this paper, we provide an overview and analysis of available methods for building model trees for explaining deep reinforcement learning agents solving robotics tasks. We find that multiple outputs are important for the model to be able to grasp the dependencies of coupled output features, i.e. actions. Additionally, our results indicate that introducing domain knowledge via a hierarchy among the input features during the building process results in higher accuracies and a faster building process. [ABSTRACT FROM AUTHOR]

• Multimodal Pre-trained models with document layout, vision-text and audio-text domains as input. • Collection of common multimodal downstream applications with related datasets. • Modality feature embedding strategies. • Cross-modality alignment pre-training tasks for different multimodal domains. • Variations of the audio-text cross-modal learning architecture. With the broad industrialization of Artificial Intelligence(AI), we observe a large fraction of real-world AI applications are multimodal in nature in terms of relevant data and ways of interaction. Pre-trained big models have been proven as the most effective framework for joint modeling of multi-modality data. This paper provides a thorough account of the opportunities and challenges of Transformer-based multimodal pre-trained model (PTM) in various domains. We begin by reviewing the representative tasks of multimodal AI applications, ranging from vision-text and audio-text fusion to more complex tasks such as document layout understanding. We particularly address the new multi-modal research domain of document layout understanding. We further analyze and compare the state-of-the-art Transformer-based multimodal PTMs from multiple aspects, including downstream applications, datasets, input feature embedding, and model architectures. In conclusion, we summarize the key challenges of this field and suggest several future research directions. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This paper investigates the specific properties of Explainable Artificial Intelligence (xAI), particularly when implemented in AI/ML models across high-stakes sectors, in this case cybersecurity. The authors execute a comprehensive systematic review of xAI properties, various evaluation metrics, and existing frameworks to assess their utility and relevance. Subsequently, the experimental sections evaluate selected xAI techniques against these metrics, delivering key insights into their practical utility and effectiveness. The findings highlight that the proliferation of metrics enhances the understanding of xAI systems but simultaneously exposes challenges such as metric duplication, inefficacy, and confusion. These issues underscore the pressing need for standardized evaluation frameworks to streamline their application and strengthen their effectiveness, thereby improving the overall utility of xAI in critical domains. • Bridging xAI theory and practice. • Systematic review of xAI metrics and frameworks. • Experimental evaluation of various xAI explanations. • The results show many metrics are ine2ective. • The abundance of metrics has pros and cons. [ABSTRACT FROM AUTHOR]

Deep Neural Networks achieve outstanding results; however, their reliance on a static environment with fixed data poses challenges in dynamic scenarios where data continuously evolves. Being capable of learning, adapting, and generalizing continually in a scalable, successful, and efficient manner is crucial for the sustainable development of AI systems. The classical solution of retraining the model using both old and new data is time-consuming and expensive. Continual Learning tackles the problem of learning new data distributions without the need for retraining from scratch. Furthermore, the task of recognizing unlabeled images using previously acquired knowledge becomes challenging, particularly when the new data needs to be incrementally annotated without starting the training process from scratch. To gain a deeper understanding of how "Black Box" neural networks make decisions, it is important to visualize components inside the model that affect the error rate throughout the decision-making process. The Continual Self-Learning model on label-less historical digits yields increasingly perceptive interpretations. This paper aims to establish a literature review of the latest advances in continual learning for computer vision tasks, to articulate catastrophic forgetting using Explainable Artificial Intelligence on both split MNIST and the historical digit dataset DIDA, and to shed light on important but still understudied topics. [ABSTRACT FROM AUTHOR]

Accurate and reliable automatic segmentation of lesion areas in gastroscopy images can assist endoscopists in making diagnoses and reduce the possibility of missed or incorrect diagnoses. This paper presents a two-stage framework for segmenting gastroscopy images, which aims to improve the accuracy of medical image segmentation tasks using limited datasets. The proposed framework consists of two stages: the Image Enhancement Stage and the Lesion Segmentation Stage. First, in the Image Enhancement Stage, an image enhancement solution called TDC-Enhance is proposed to enrich the original small-scale gastroscopy image dataset. This solution performs Texture Enhancement, Detail Enhancement, and Color Enhancement on the original images. Then, in the Lesion Segmentation Stage, a multi-path automatic segmentation network for gastroscopy images, named DynaSiam, is introduced. DynaSiam comprises a Dependent Encoder, a Shared Encoder, and a Fusion Decoder. It learns feature information related to the lesion region by encoding the different enhanced images obtained in the Image Enhancement Stage as inputs to the multi-path network. Additionally, a Dynamic Feature Interaction (DFI) block is designed to capture and learn deeper image information, thereby improving the segmentation performance of the model. The experimental results show that the proposed method achieves a 90.80% mIoU, 92.71% Dice coefficient and 96.31% Accuracy. Other performance metrics also indicate the best performance, suggesting that the proposed model has significant potential for clinical analysis and diagnosis. Code and implementation details can be found on GitHub: https://github.com/kyasulee/DynaSiam. [ABSTRACT FROM AUTHOR]

Artificial intelligence, and especially deep neural networks, have evolved substantially in the recent years, infiltrating numerous domains of applications, often greatly impactful to society's well-being. As a result, the need to understand how these models operate in depth and to access explanations of their decisions has become more vital than ever. Tending to this demand, the following paper aims to provide a thorough overview of the methods that have so far been developed to explain deep neural networks. Key aspects of explainability are defined and a straightforward classification of existing approaches is introduced, along with numerous examples. The task of realizing these methods on hardware is also discussed to complete the understanding of their application. [ABSTRACT FROM AUTHOR]

Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models. [ABSTRACT FROM AUTHOR]

Green artificial intelligence (AI) is more environmentally friendly and inclusive than conventional AI, as it not only produces accurate results without increasing the computational cost but also ensures that any researcher with a laptop can perform high-quality research without the need for costly cloud servers. This paper discusses green AI as a pivotal approach to enhancing the environmental sustainability of AI systems. Described are AI solutions for eco-friendly practices in other fields (green-by AI), strategies for designing energy-efficient machine learning (ML) algorithms and models (green-in AI), and tools for accurately measuring and optimizing energy consumption. Also examined are the role of regulations in promoting green AI and future directions for sustainable ML. Underscored is the importance of aligning AI practices with environmental considerations, fostering a more eco-conscious and energy-efficient future for AI systems. • Green AI emphasizes sustainable and energy-efficient AI and ML models. • Strategies for designing energy-efficient systems are explored (green-in AI). • Also explored are AI approaches to enhancing eco-friendly practices (green-by AI). • Several options exist for green AI innovations in algorithm and hardware optimization. • Future trends are discussed. [ABSTRACT FROM AUTHOR]

Person re-identification has gained significant attention in recent years due to its numerous practical applications in video surveillance. However, while artificial intelligence and deep learning methods have enabled substantial progress in particular aspects of this domain, putting together those individual advances to generate practical systems remains a computer vision challenge. Existing methods are typically designed assuming the target person's images are captured under uniform, stable conditions with similar lighting levels, but this assumption may not hold in real-world scenarios, such as outdoor monitoring over 24 h, as image quality can vary considerably throughout day and night. In this paper, we propose a framework that incorporates image enhancement techniques to improve the performance of a person re-identification model. The proposed approach achieves a significant improvement in a demanding re-identification dataset, raising the mAP from 9.0% using a zero-shot baseline to 65.8% through the combined use of low-light image enhancement methods and noise reduction. [ABSTRACT FROM AUTHOR]

As an important branch of emerging artificial intelligence algorithms, multi-agent reinforcement learning (MARL) has shown strong performance in collaborative environments. It can utilize multiple agents to find the optimal set of strategies for solving sequential decision problem through trial-and-error. One of the main challenges facing multi-agent system is the non-stationarity problem, which brings poor convergence and seriously affects its performance. Clustering is a commonly used unsupervised analytical method in machine learning, which aims to group samples with similar internal properties into the same cluster. In this paper, we propose a MARL clustering algorithm based on silhouette coefficient (SC-MARLC), and use the trial-and-error strategy to find the best cluster groups. In SC-MARLC, we establish a mapping relationship between multi-agent and samples, construct a novel clustering model based on MARL, and design a good clustering subset structure based on the sample silhouette coefficient. The designed structure is helpful for multi-agent system to solve the non-stationary problem. Finally, we compare the performance of SC-MARLC with 11 existing clustering algorithms on fifteen public datasets. The results show that the new clustering algorithm performs best on ten datasets. [Display omitted] [ABSTRACT FROM AUTHOR]

In this paper, a novel Fault Detection and Isolation (FDI) method for Proton Exchange Membrane (PEM) electrolyzers is presented. The challenge of limited availability of labeled fault data is addressed through the utilization of Bond Graphs (BG) and Self-Supervised Learning (SSL). The Linear Fractional Transformation-Bond Graph (LFT-BG) model is employed to generate uncertain residuals and pseudo labels, enabling the training of a deep neural network through self-supervised learning. Additionally, the BG-XAI method is introduced, leveraging eXplainable AI (XAI) and structural equations from Bond Graphs to provide explanations for the decisions made by the deep learning model. The superior performance of the proposed approach, particularly in dealing with limited labeled data, is demonstrated through comparative assessments against various state-of-the-art SSL methods. The demo code of the proposed method is available in this repository: https://github.com/mohan696matlab/SSL_based_Hybrid_FDI. • Uses LFT-bond graph model to generate residuals and pseudo labels for pre-training. • Introduces BG-XAI, a novel explainable AI technique using occlusion. • The proposed hybrid FDI is applied to a PEM electrolyzer stack, showing superior performance. • It deals with limited labeled fault data in renewable energy, offering a reliable solution for diagnosis. [ABSTRACT FROM AUTHOR]

The development of explainability methods for Convolutional Neural Networks (CNNs), under the growing framework of e x plainable Artificial Intelligence (xAI) for image understanding, is crucial due to neural networks success in contrast with their black box nature. However, usual methods focus on image visualizations and are inadequate to analyze the encoded contextual information (that captures the spatial dependencies of pixels considering their neighbors), as well as to explain the evolution of learning across layers without degrading the information. To address the latter, this paper presents a novel explanatory method based on the study of the latent representations of CNNs through their topology, and supported by Topological Data Analysis (TDA). For each activation layer after a convolution, the pixel values of the activation maps along the channels are considered latent space points. The persistent homology of this data is summarized via persistence landscapes, called Latent Landscapes. This provides a global view of how contextual information is being encoded, its variety and evolution, and allows for statistical analysis. The applicability and effectiveness of our approach is demonstrated by experiments conducted with CNNs trained on distinct datasets: (1) two U-Net segmentation models on RGB and pseudo-multiband images (generated by considering vegetation indices) from the agricultural benchmark CRBD were evaluated, in order to explain the difference in performance; and (2) a VGG-16 classification network on CIFAR-10 (RGB) was analyzed, showing how the information evolves within the network. Moreover, comparisons with state-of-the-art methods (Grad-CAM and occlusion) prove the consistency and validity of our proposal. It offers novel insights into the decision making process and helps to compare how models learn. • Design a novel topology-based explanatory method for Convolutional Neural Networks. • The topology of latent spaces is related to the variety of encoded information. • Discussing in detail the learning process and its relationship to performance. • Statistical analysis of the results obtained to further interpret the networks. [ABSTRACT FROM AUTHOR]

In the last decade it became increasingly apparent the inability of technical metrics such as accuracy, sustainability, and non-regressiveness to well characterize the behavior of intelligent systems. In fact, they are nowadays requested to meet also ethical requirements such as explainability, fairness, robustness, and privacy increasing our trust in their use in the wild. Of course often technical and ethical metrics are in tension between each other but the final goal is to be able to develop a new generation of more responsible and trustworthy machine learning. In this paper, we focus our attention on machine learning algorithms and associated predictive models, questioning for the first time, from a theoretical perspective, if it is possible to simultaneously guarantee their performance in terms of both technical and ethical metrics towards machine learning algorithms that we can trust. In particular, we will investigate for the first time both theory and practice of deterministic and randomized algorithms and associated predictive models showing the advantages and disadvantages of the different approaches. For this purpose we will leverage the most recent advances coming from the statistical learning theory: Complexity-Based Methods, Distribution Stability, PAC-Bayes, and Differential Privacy. Results will show that it is possible to develop consistent algorithms which generate predictive models with guarantees on multiple trustworthiness metrics. • AI is nowadays requested to optimize both technical and ethical metrics. • Focus on ML algorithms and associated models (both deterministic and randomized). • We prove that it is possible to develop consistent algorithms and models. • We bound generalization in terms of both technical and ethical metrics. • We leverage the most recent advances coming from the statistical learning theory. [ABSTRACT FROM AUTHOR]

With the exponential expansion of Internet information, technology that combines big data and artificial intelligence has gradually developed. Pre-trained large-scale language models with the transformer architecture as the core have begun to be used in daily life, resulting in the huge market of MLaaS. leading to the significant market of Machine Learning as a Service (MLaaS). Although MLaaS brings huge benefits to users, it requires receiving users' data for processing, which includes many sensitive data. While MLaaS offers considerable benefits, it necessitates processing users' data, which includes much sensitive data.Therefore, the problem of privacy data leakage has also been exposed. In this article paper, we propose a novel language model secure inference scheme based on secure multi-party computation (MPC) technology. This solution involves three non-colluding parties: the data provider, the model provider, and the computing power provider. Compared with direct inference on pre-trained large models, the proposed security inference framework improves the inference speed by 1.55–6.25 times. Our findings demonstrate that, when compared to conventional inference methods on pre-trained large-scale models, our approach significantly enhances inference efficiency, achieving speed improvements ranging from 1.55 to 6.25 times. [Display omitted] • We propose an efficient privacy preserving language model inference framework. • We propose a user privacy leakage protection scheme in the outsourcing scenario. • Compare to existing secure frameworks, our speed increases by 1.55–6.25 times. [ABSTRACT FROM AUTHOR]

• We review artificial intelligence applications of brain image preprocessing. • We investigate several commonly seen brain diseases and survey their intelligence-based methods. • We discuss AI's future in brain disease studies. Brain diseases threaten hundreds of thousands of people over the world. Medical imaging techniques such as MRI and CT are employed for various brain disease studies. As artificial intelligence succeeded in image analysis, scientists employed artificial intelligence, especially deep learning technologies, to assist brain disease studies. The AI applications for brain disease studies can be divided into two categories. The first category is preprocessing, including denoising, registration, skull-stripping, intensity normalization, and data augmentation. The second category is the clinical application that contains lesion segmentation, disease detection, grade classification, and outcome prediction. In this survey, we reviewed over one hundred representative papers on how to apply AI to brain disease studies. We first introduced AI-based preprocessing for brain disease studies. Second, we reviewed the influential works of AI-based brain disease studies. At last, we also discussed three development trends in the future. We hope this survey will inspire both expert-level researchers and entry-level beginners. [ABSTRACT FROM AUTHOR]

Recent artificial intelligence-based methods have shown great promise in the use of neural networks for real-time detection of transmission line faults and estimation of their locations. The expansion of power systems including transmission lines with various lengths have made the fault detection, classification, and location estimation process more challenging. Transmission line datasets are stream data which are continuously collected by various sensors and hence, require generalized and fast fault diagnosis approaches. Newly collected datasets including voltages and currents for faulty and non-faulty situations might not have adequate and accurate labels that are useful to train neural networks. In this paper, a novel transfer learning framework based on a pre-trained LeNet-5 convolutional neural network is proposed. This method is able to diagnose faults for different transmission line lengths and impedances by transferring the knowledge from a source convolutional neural network to predict a dissimilar target dataset. By transferring this knowledge, faults from various transmission lines, even without sufficient data samples with labels, can be diagnosed faster and more efficiently than the existing methods. To prove the feasibility and effectiveness of this methodology, seven different datasets that include various lengths of transmission lines are used. The robustness of the proposed methodology against the generator voltage fluctuations, variations in fault locations, fault inception angle, fault resistance, and phase difference between the two generators are well studied to prove the reliability of this technique for fault diagnosis of transmission lines. [ABSTRACT FROM AUTHOR]

Abstract In this paper, some new p -stability criteria and boundedness results of reaction–diffusion BAM neural networks are derived by way of fixed point theorem, Laplacian semigroup theory and L ∞-estimate technique, which are novel against those of the previous related literature. Since the T–S fuzzy impulsive reaction–diffusion neural networks was investigated by previous literature, the main difficulty of this paper is to find out a novel method to give simpler conclusions than existing results. Finally, a numerical example is presented to illustrate the effectiveness and feasibility of the proposed methods. [ABSTRACT FROM AUTHOR]

Abstract In this paper, we present a multi-view transfer learning model named Multi-view Transfer Discriminative Model (MTDM) for both image and text classification tasks. Transfer learning, which aims to learn a robust classifier for the target domain using data from a different distribution, has been proved to be effective in many real-world applications. However, most of the existing transfer learning methods map across domain data into a high-dimension space which the distance between domains is closed. This strategy always fails in the multi-view scenario. On the contrary, the multi-view learning methods are also difficult to extend in the transfer learning settings. One of our goals in this paper is to develop a model which can perform better in both multi-view and transfer learning settings. On the one hand, the problem of multi-view is implemented by the paradigm of learning using privileged information (LUPI), which could guarantee the principle of complementary and consensus. On the other hand, the model adequately utilizes the source domain data to build a robust classifier for the target domain. We evaluate our model on both image and text classification tasks and show the effectiveness compared with other baseline approaches. [ABSTRACT FROM AUTHOR]

Neuromorphic computing realizes low-latency and low-power computing by emulating the neural structure and operation of the human brain, and is considered a key research area for third-generation artificial intelligence. However, current neuromorphic computing faces the problems of huge synaptic memory consumption and complex neuron calculations. This paper proposes a batch normalization (BN)-free weight-binarized SNN based on hardware-saving IF neurons to reduce storage requirements and improve the computational efficiency of neuromorphic computing. Hardware-friendly backpropagation through time (BPTT)-based algorithm and SG function are proposed to calculate the gradients of the "integrate" process and "fire" process of IF neuron, respectively. Weight binarization is carried out during training to reduce storage requirements, and spatio-temporal batch normalization (BN) operations are introduced to ensure high performance. During inference, a simple adaptive-threshold IF neuron model is proposed to achieve the effect equivalent to the computationally expensive spatio-temporal BN operation without any performance loss. The proposed BN-free binarized SNNs based on hardware-saving IF neuron achieves competitive accuracies of 99.36%, 94.79%, 90.39%, and 67.10% on the N-MNIST, DvsGesture, N-TIDIGITS18, and DVS-CIFAR10 datasets, respectively, which are comparable to full-precision SNNs, but the weight sizes are significantly reduced by ∼ 97%. Furthermore, robustness experiments show that the binary SNN is more robust to weight noise than the full-precision SNN. This paper presents an efficient algorithm-hardware co-design paradigm for hardware-friendly and high-performance neuromorphic computing. [ABSTRACT FROM AUTHOR]

Synthetic data generation (SDG) research has been ongoing for some time with promising results in different application domains, including healthcare, biometrics and energy consumption. The need for a robust SDG solution to capitalise on advances in Big Data and AI technology has never been greater to enable access to useful data while ensuring reasonable privacy protections. This paper presents a systematic review from the last 5 years (2016–2021) to analyse and report on recent approaches in synthetic tabular data generation (STDG) with a focus on the healthcare application context to preserve patient privacy, paying special attention to the contribution of Generative Adversarial Networks (GAN). In total 34 publications have been retrieved and analysed. A classification of approaches has been proposed and the performance of GAN-based approaches has been extensively analysed. From the systematic review it has been concluded that there is no universal method or metric to evaluate and benchmark the performance of various approaches and that further research is needed to improve the generalisability of GANs to find a model that works optimally across tabular healthcare data. [ABSTRACT FROM AUTHOR]

• An image-based poetry generation model with the unsupervised method. • The proposed model can generate diverse poetry from images. • The model combines reinforcement learning and contrastive learning methods. Automatic poetry generation represents a typical exhibition of artificial intelligence creativity, and the cross-modal generation methods reveal a promising direction for improvement. Although previous methods have made some progress, they still suffer from the following challenges: (1) lack of annotated multimodal Chinese poetry datasets; (2) insufficient diversity of generated poetry; (3) inadequate semantic consistency between images and poems. In this paper, we propose a novel Unsupervised Image to Poetry Model (UI2P) with a newly designed generative adversarial network to address the above issues. Specifically, the unsupervised learning framework eliminates the dependence on annotated multimodal poetry datasets. We present a contrastive learning approach to optimize the diversity of generated poems. Furthermore, a consistency strategy is developed, including constructing a modern-classical concept dictionary to ensure semantic coherence between poems and images. Extensive experiments are conducted on the CCPC dataset, and the results with both automatic and manual evaluations demonstrate the superiority of our model compared with several state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Smart home applications are pervasive and have gained popularity due to the overwhelming use of Internet of Things (IoT). The revolution in IoT technologies made homes more convenient, efficient and perhaps more secure. The need to advance smart home technology is necessary at this stage as IoT is abundantly used in automation industry. However, most of the proposed solutions are lacking in certain key areas of the system i.e., high interoperability, data independence, privacy, and optimization in general. The use of machine learning algorithms requires high-end hardware and are usually deployed on servers, where computation is convenient, but at the cost of bandwidth. However, more recently edge AI enabled systems are being proposed to shift the computation burden from the server side to the client side enabling smart devices. In this paper, we take advantage of the edge AI enabled technology to propose a fully featured cohesive system for smart home based on IoT and edge computing. The proposed system makes use of industry standards adopted for fog computing as well as providing robust responses from connected IoT sensors in a typical smart home. The proposed system employs edge devices as a computational platform in terms of reducing energy costs and provides security, while remotely controlling all appliances behind a secure gateway. A case study of human fall detection is evaluated by a custom lightweight deep neural network architecture implemented over the edge device of the proposed framework. The case study was validated using the Le2i dataset. During the training, the early stopping threshold was achieved with 98% accuracy for training set and 94% for validation set. The model size of the network was 6.4 MB which is significantly lower than other networks with similar performance. [ABSTRACT FROM AUTHOR]

With the rapid development of cloud computing, Internet of things and artificial intelligence, human–computer interaction (HCI) is playing an increasingly important role in the daily life. As an important component of HCI, hand gesture recognition (HGR) system is usually combined with edge computing server, utilizing machine learning, including neural network, decision tree, integrated learning, to achieve low latency and high reliability service. High precision HGR with low computational complexity is prerequisite for the commercialization of gesture recognition. Therefore, this paper proposed a high-precision parameter correction algorithm based on the established scattered-point model and the outlier detection scheme, and a recognition algorithm with multivariable decision tree is then presented for the dynamic hand gestures. The experimental results show that the proposed algorithms can improve the recognition accuracy and effectively reduce the running time, which is conducive to algorithm transplantation and model deployment in edge servers. [ABSTRACT FROM AUTHOR]

The smartphone-based human activity recognition (HAR) provides abundant healthcare guidance for telemedicine and clinic treatment. The continually increasing daily activities cause many difficulties for recognition and labeling. Although multimodal data fusion and artificial intelligence (AI) techniques can solve these problems, big data collection and labeling are still heavy. This paper proposes a remarkable depth data-guided framework based on smartphones for complex HAR and automatic labeling. The hardware platform is utilized to collect information of depth vision from the Microsoft Kinect camera and Inertial Measurement Unit (IMU) signals from the smartphone simultaneously. This framework consists of five clustering layers and deep learning (DL) based classification model to identify 12 complex daily activities. The results show that the hierarchical k-medoids (Hk-medoids) algorithm obtains the labels with high accuracy (93.89 %). Furthermore, the performance evaluation of the DCNN model is evaluated better by comparing it with other machine learning (ML) and DL methods. [ABSTRACT FROM AUTHOR]

Edge computing and artificial intelligence (AI), especially deep learning algorithms, are gradually intersecting to build the novel system, namely edge intelligence. However, the development of edge intelligence systems encounters several challenges, and one of these challenges is the computational gap between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of new techniques and optimization methods were proposed in the past years: lightweight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods, applicable to edge systems, are proposed, a holistic review would enable edge computing engineers and the community to understand the state-of-the-art deep learning techniques that are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search, and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions. [ABSTRACT FROM AUTHOR]

In recent years, AI-assisted video editing has shown promising applications. Understanding and analyzing camera language accurately is fundamental in video editing, guiding subsequent editing and production processes. However, many existing methods for camera language analysis overlook computational efficiency and deployment requirements in favor of improving classification accuracy. Consequently, they often fail to meet the demands of scenarios with limited computing power, such as mobile devices. To address this challenge, this paper proposes an efficient multi-task camera language analysis pipeline based on shared representations. This approach employs a multi-task learning architecture with hard parameter sharing, enabling different camera language classification tasks to utilize the same low-level feature extraction network, thereby implicitly learning feature representations of the footage. Subsequently, each classification sub-task independently learns the high-level semantic information corresponding to the camera language type. This method significantly reduces computational complexity and memory usage while facilitating efficient deployment on devices with limited computing power. Furthermore, to enhance performance, we introduce a dynamic task priority strategy and a conditional dataset downsampling strategy. The experimental results demonstrate that achieved a comprehensive accuracy surpassing all previous methods. Moreover, training time was reduced by 66.33%, inference cost decreased by 59.85%, and memory usage decreased by 31.95% on the 2-task dataset MovieShots; on the 4-task dataset AVE, training time was reduced by 95.34%, inference cost decreased by 97.23%, and memory usage decreased by 61.21%. [ABSTRACT FROM AUTHOR]

In this paper, we introduce DP-EBM*, an enhanced utility version of the Differentially Private Explainable Boosting Machine (DP-EBM). DP-EBM* offers predictions for both classification and regression tasks, providing inherent explanations for its predictions while ensuring the protection of sensitive individual information via Differential Privacy. DP-EBM* has two major improvements over DP-EBM. Firstly, we develop an error measure to assess the efficiency of using privacy budget, a crucial factor to accuracy, and optimize this measure. Secondly, we propose a feature pruning method, which eliminates less important features during the training process. Our experimental results demonstrate that DP-EBM* outperforms the state-of-the-art differentially private explainable models. [ABSTRACT FROM AUTHOR]