Search

Academic search engines have been widely used to access academic papers, where users' information needs are explicitly represented as search queries. Some modern recommender systems have taken one step further by predicting users' information needswithout the presence of an explicit query. In this article,we examine an academic paper recommender that sends out paper recommendations in email newsletters, based on the users' browsing history on the academic search engine. Specifically, we look at users who regularly browse papers on the search engine, and we sign up for the recommendation newsletters for the first time. We address the task of reranking the recommendation candidates that are generated by a production system for such users. We face the challenge that the users on whom we focus have not interacted with the recommender system before, which is a common scenario that every recommender system encounters when new users sign up. We propose an approach to reranking candidate recommendations that utilizes both paper content and user behavior. The approach is designed to suit the characteristics unique to our academic recommendation setting. For instance, content similarity measures can be used to find the closest match between candidate recommendations and the papers previously browsed by the user. To this end, we use a knowledge graph derived from paper metadata to compare entity similarities (papers, authors, and journals) in the embedding space. Since the users on whom we focus have no prior interactions with the recommender system, we propose a model to learn a mapping from users' browsed articles to user clicks on the recommendations. We combine both content and behavior into a hybrid reranking model that outperforms the production baseline significantly, providing a relative 13% increase in Mean Average Precision and 28% in Precision@1. Moreover, we provide a detailed analysis of the model components, highlighting where the performance boost comes from. The obtained insights reveal useful components for the reranking process and can be generalized to other academic recommendation settings as well, such as the utility of graph embedding similarity. Also, recent papers browsed by users provide stronger evidence for recommendation than historical ones. [ABSTRACT FROM AUTHOR]

The growing number of publications in the field of artificial intelligence highlights the need for researchers to enhance their efficiency in searching for relevant articles. Most paper recommendation models either rely on simplistic citation relationships among papers or focus on content-based approaches, both of which overlook interactions within academic networks. To address the aforementioned problem, knowledge graph embedding (KGE) methods have been used for citation recommendations because recent research proves that graph representations can effectively improve recommendation model accuracy. However, academic networks are dynamic, leading to changes in the representations of users and items over time. The majority of KGE-based citation recommendations are primarily designed for static graphs, thus failing to capture the evolution of dynamic knowledge graph (DKG) structures. To address these challenges, we introduced the evolving knowledge graph embedding (EKGE) method. In this methodology, evolving knowledge graphs are input into time-series models to learn the patterns of structural evolution. The model has the capability to generate embeddings for each entity at various time points, thereby overcoming limitation of static models that require retraining to acquire embeddings at each specific time point. To enhance the efficiency of feature extraction, we employed a multiple attention strategy. This helped the model find recommendation lists that are closely related to a user's needs, leading to improved recommendation accuracy. Various experiments conducted on a citation recommendation dataset revealed that the EKGE model exhibits a 1.13% increase in prediction accuracy compared to other KGE methods. Moreover, the model's accuracy can be further increased by an additional 0.84% through the incorporation of an attention mechanism. [ABSTRACT FROM AUTHOR]

In recent years, ride-hailing services have emerged as a popular means of transportation for the residents of urban areas. There is an inequality in the spatio-temporal distribution of demand and supply, which requires the proper recommendation of routes to drivers in order to guide them towards riders optimally. This paper provides a review of different route recommendation strategies that have been applied in ride-hailing platforms with the main focus on fairness, and environmental issues. It is important to consider the environmental aspects of route recommendation systems as the transportation sector is one of the major sources of air pollution and has reduced the life expectancy of people around the globe. Moreover, there is an unfair distribution of resources and opportunities among the drivers and riders of the platform which has affected their long-term sustainability in the market. In this paper, we highlight the critical challenges and opportunities inherent in the design of green and fair route recommendation systems and indicate some possible directions for future research. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other areas. Secondly, we answer the 'where' and 'how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing the performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey [ABSTRACT FROM AUTHOR]

Vessel trajectory prediction is the key to maritime applications such as traffic surveillance, collision avoidance, anomaly detection, and so on. Making predictions more precisely requires a better understanding of the moving trend for a particular vessel since the movement is affected by multiple factors like marine environment, vessel type, and vessel behavior. In this paper, we propose a model named VesNet, based on the attentional seq2seq framework, to predict vessel future movement sequence by observing the current trajectory. Firstly, we extract the route patterns from the raw AIS data during preprocessing. Then, we design a multi-task learning structure to learn how to implement route pattern classification and vessel trajectory prediction simultaneously. By comparing with representative baseline models, we find that our VesNet has the best performance in terms of long-term prediction precision. Additionally, VesNet can recognize the route pattern by capturing the implicit moving characteristics. The experimental results prove that the proposed multi-task learning assists the vessel trajectory prediction mission. [ABSTRACT FROM AUTHOR]

Conceptual modeling is an important part of information systems development and use that involves identifying and representing relevant aspects of reality. Although the past decades have experienced continuous digitalization of services and products that impact business and society, conceptual modeling efforts are still required to support new technologies as they emerge. This paper surveys research on conceptual modeling over the past five decades and shows how its topics and trends continue to evolve to accommodate emerging technologies, while remaining grounded in basic constructs. We survey over 5,300 papers that address conceptual modeling topics from the 1970s to the present, which are collected from 35 multidisciplinary journals and conferences, and use them as the basis from which to analyze the progression of conceptual modeling. The important role that conceptual modeling should play in our evolving digital world is discussed, and future research directions proposed. [ABSTRACT FROM AUTHOR]

Centralized networks inevitably exhibit single points of failure that malicious actors regularly target. Decentralized networks are more resilient if numerous participants contribute to the network's functionality. Most decentralized networks employ incentive mechanisms to coordinate the participation and cooperation of peers and thereby ensure the functionality and security of the network. This article systematically reviews incentive mechanisms for decentralized networks and networked systems by covering 165 prior literature reviews and 178 primary research papers published between 1993 and October 2022. Of the considered sources, we analyze 11 literature reviews and 105 primary research papers in detail by categorizing and comparing the distinctive properties of the presented incentive mechanisms. The reviewed incentive mechanisms establish fairness and reward participation and cooperative behavior. We review work that substitutes central authority through independent and subjective mechanisms run in isolation at each participating peer and work that applies multiparty computation. We use monetary, reputation, and service rewards as categories to differentiate the implementations and evaluate each incentive mechanism's data management, attack resistance, and contribution model. Further, we highlight research gaps and deficiencies in reproducibility and comparability. Finally, we summarize our assessments and provide recommendations to apply incentive mechanisms to decentralized networks that share computational resources. [ABSTRACT FROM AUTHOR]

The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multifaceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practices of more than 300 papers published in the past 7 years at major AI and ML conferences that introduce an XAI method. We find that one in three papers evaluate exclusively with anecdotal evidence, and one in five papers evaluate with users. This survey also contributes to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. Our systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark, and compare new and existing XAImethods. The Co-12 categorization scheme and our identified evaluation methods open up opportunities to include quantitative metrics as optimization criteria during model training to optimize for accuracy and interpretability simultaneously. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) and Machine Learning (ML) are effectively utilized in various complicated challenges in healthcare, industry, and academia. The Internet of Drones (IoD) has lately cropped up due to high adjustability to a broad range of unpredictable circumstances. In addition, Unmanned Aerial Vehicles (UAVs) could be utilized efficiently in a multitude of scenarios, including rescue missions and search, farming, mission-critical services, surveillance systems, and so on, owing to technical and realistic benefits such as low movement, the capacity to lengthen wireless coverage zones, and the ability to attain places unreachable to human beings. In many studies, IoD and UAV are utilized interchangeably. Besides, drones enhance the efficiency aspects of various network topologies, including delay, throughput, interconnectivity, and dependability. Nonetheless, the deployment of drone systems raises various challenges relating to the inherent unpredictability of the wireless medium, the high mobility degrees, and the battery life that could result in rapid topological changes. In this paper, the IoD is originally explained in terms of potential applications and comparative operational scenarios. Then, we classify ML in the IoD-UAV world according to its applications, including resource management, surveillance and monitoring, object detection, power control, energy management, mobility management, and security management. This research aims to supply the readers with a better understanding of (1) the fundamentals of IoD/UAV, (2) the most recent developments and breakthroughs in this field, (3) the benefits and drawbacks of existing methods, and (4) areas that need further investigation and consideration. The resultssuggest that the Convolutional Neural Networks (CNN) method is the most often employed ML method in publications. According to research, most papers are on resource and mobility management. Most articles have focused on enhancing only one parameter, with the accuracy parameter receiving the most attention. Also, Python is the most commonly used language in papers, accounting for 90% of the time. Also, in 2021, it has the most papers published. [ABSTRACT FROM AUTHOR]

Recent applications of autonomous agents and robots have brought attention to crucial trust-related challenges associated with the current generation of artificial intelligence (AI) systems. AI systems based on the connectionist deep learning neural network approach lack capabilities of explaining their decisions and actions to others, despite their great successes. Without symbolic interpretation capabilities, they are ‘black boxes’, which renders their choices or actions opaque, making it difficult to trust them in safety-critical applications. The recent stance on the explainability of AI systems has witnessed several approaches to eXplainable Artificial Intelligence (XAI); however, most of the studies have focused on data-driven XAI systems applied in computational sciences. Studies addressing the increasingly pervasive goal-driven agents and robots are sparse at this point in time. This paper reviews approaches on explainable goal-driven intelligent agents and robots, focusing on techniques for explaining and communicating agents’ perceptual functions (e.g., senses, vision) and cognitive reasoning (e.g., beliefs, desires, intentions, plans, and goals) with humans in the loop. The review highlights key strategies that emphasize transparency, understandability, and continual learning for explainability. Finally, the paper presents requirements for explainability and suggests a road map for the possible realization of effective goal-driven explainable agents and robots. [ABSTRACT FROM AUTHOR]

The Dynamic Mode Decomposition (DMD) is a method for computational analysis of nonlinear dynamical systems in data driven scenarios. Based on high fidelity numerical simulations or experimental data, the DMD can be used to reveal the latent structures in the dynamics or as a forecasting or a model order reduction tool. The theoretical underpinning of the DMD is the Koopman operator on a Hilbert space of observables of the dynamics under study. This paper describes a numerically robust and versatile variant of the DMD and its implementation using the state-of-the-art dense numerical linear algebra software package LAPACK. The features of the proposed software solution include residual bounds for the computed eigenpairs of the DMD matrix, eigenvectors refinements and computation of the eigenvectors of the Exact DMD, compressed DMD for efficient analysis of high dimensional problems that can be easily adapted for fast updates in a streaming DMD. Numerical analysis is the bedrock of numerical robustness and reliability of the software, that is tested following the highest standards and practices of LAPACK. Important numerical topics are discussed in detail and illustrated using numerous numerical examples. [ABSTRACT FROM AUTHOR]

The Dynamic Mode Decomposition (DMD) is a versatile and increasingly popular method for data driven analysis of dynamical systems that arise in a variety of applications in, e.g., computational fluid dynamics, robotics or machine learning. In the framework of numerical linear algebra, it is a data driven Rayleigh-Ritz procedure applied to a DMD matrix that is derived from the supplied data. In some applications, the physics of the underlying problem implies hermiticity of the DMD matrix, so the general DMD procedure is not computationally optimal. Furthermore, it does not guarantee important structural properties of the Hermitian eigenvalue problem and may return non-physical solutions. This paper proposes a software solution to the Hermitian (including the real symmetric) DMD matrices, accompanied with a numerical analysis that contains several fine and instructive numerical details. The eigenpairs are computed together with their residuals, and perturbation theory provides error bounds for the eigenvalues and eigenvectors. The software is developed and tested using the LAPACK package. [ABSTRACT FROM AUTHOR]

The Sparse Grids Matlab Kit provides a Matlab implementation of sparse grids, and can be used for approximating high-dimensional functions and, in particular, for surrogate-model-based uncertainty quantification. It is lightweight, high-level and easy to use, good for quick prototyping and teaching; however, it is equipped with some features that allow its use also in realistic applications. The goal of this paper is to provide an overview of the data structure and of the mathematical aspects forming the basis of the software, as well as comparing the current release of our package to similar available software. [ABSTRACT FROM AUTHOR]

Graph representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate graph representation vectors that capture the structure and features of large graphs accurately. This is especially important because the quality of the graph representation vectors will affect the performance of these vectors in downstream tasks such as node classification, link prediction and anomaly detection. Many techniques have been proposed for generating effective graph representation vectors, which generally fall into two categories: traditional graph embedding methods and graph neural network (GNN)–based methods. These methods can be applied to both static and dynamic graphs. A static graph is a single fixed graph, whereas a dynamic graph evolves over time and its nodes and edges can be added or deleted from the graph. In this survey, we review the graph-embedding methods in both traditional and GNN-based categories for both static and dynamic graphs and include the recent papers published until the time of submission. In addition, we summarize a number of limitations of GNNs and the proposed solutions to these limitations. Such a summary has not been provided in previous surveys. Finally, we explore some open and ongoing research directions for future work. [ABSTRACT FROM AUTHOR]

The pedestrian attribute recognition aims to generate a structured description of pedestrians, which serves an important role in surveillance. Current works usually assume that the images and the specific pedestrian states, including pedestrian occlusion and pedestrian orientation, are given. However, we argue that the current works ignore the guidance of the pedestrian state and cannot achieve the appropriate performance since the appearance feature will become unreliable due to the variance of the pedestrian state, which is common in practice. Therefore, this paper proposes the Explicit State Representation (ExSR) Guided Pedestrian Attribute Recognition to improve the accuracy through state learning and attribute fusion among frames. Firstly, the pedestrian state is explicitly represented by concatenating the pedestrian orientation and occlusion, which can be accurately determined via analyzing the pose. Secondly, the state-aware pedestrian attribute fusion method is proposed and divided into two cases, namely the inter-state case and the intra-state case. In the intra-state case, the appearance feature will remain stable and the attribute relations are propagated to refine. The method of exploiting attribute relations within a single frame is the Graph Neural Network. In the inter-state case, the state changes, the attribute relationship propagation is prevented, and the advantages of attribute recognition in each frame are complemented to make a reliable judgment on the invisible region. The experimental results demonstrate that the ExSR outperforms the state-of-the-art methods on two public databases, benefiting from the explicit introduction of the state into the attribute recognition. [ABSTRACT FROM AUTHOR]

The security and privacy of smart home systems, particularly from a home user's perspective, have been a very active research area in recent years. However, via a meta-review of 52 review papers covering related topics (published between 2000 and 2021), this article shows a lack of a more recent literature review on user perspectives of smart home security and privacy since the 2010s. This identified gap motivated us to conduct a systematic literature review (SLR) covering 126 relevant research papers published from 2010 to 2021. Our SLR led to the discovery of a number of important areas where further research is needed; these include holisticmethods that consider a more diverse and heterogeneous range of home devices, interactions between multiple home users, complicated data flowbetween multiple home devices and home users, some less studied demographic factors, and advanced conceptual frameworks. Based on these findings, we recommended key future research directions, e.g., research for a better understanding of security and privacy aspects in different multi-device and multi-user contexts, and a more comprehensive ontology on the security and privacy of the smart home covering varying types of home devices and behaviors of different types of home users. [ABSTRACT FROM AUTHOR]

Honeyword (or decoy password) based authentication, first introduced by Juels and Rivest in 2013, has emerged as a security mechanism that can provide security against server-side threats on the password-files. From the theoretical perspective, this security mechanism reduces attackers' efficiency to a great extent as it detects the threat on a password-file so that the system administrator can be notified almost immediately as an attacker tries to take advantage of the compromised file. This paper aims to present a comprehensive survey of the relevant research and technological developments in honeyword-based authentication techniques. We cover twenty-three techniques related to honeyword, reported under different research articles since 2013. This survey paper helps the readers to (i) understand how honeyword based security mechanism works in practice, (ii) get a comparative view on the existing honeyword based techniques, and (iii) identify the existing gaps that have yet to be filled and the emergent research opportunities. [ABSTRACT FROM AUTHOR]

While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data. However, user behavior data is observational rather than experimental. This makes various biases widely exist in the data, including but not limited to selection bias, position bias, exposure bias, and popularity bias. Blindly fitting the data without considering the inherent biases will result in many serious issues, e.g., the discrepancy between offline evaluation and online metrics, hurting user satisfaction and trust on the recommendation service, and so on. To transform the large volume of research models into practical improvements, it is highly urgent to explore the impacts of the biases and perform debiasing when necessary. When reviewing the papers that consider biases in RS, we find that, to our surprise, the studies are rather fragmented and lack a systematic organization. The terminology “bias” is widely used in the literature, but its definition is usually vague and even inconsistent across papers. This motivates us to provide a systematic survey of existing work on RS biases. In this paper, we first summarize seven types of biases in recommendation, along with their definitions and characteristics. We then provide a taxonomy to position and organize the existing work on recommendation debiasing. Finally, we identify some open challenges and envision some future directions, with the hope of inspiring more research work on this important yet less investigated topic. [ABSTRACT FROM AUTHOR]

With the growing sophistication of malware, the need to devise improved malware detection schemes is crucial. The packing of executable files, which is one of the most common techniques for code protection, has been repurposed for code obfuscation by malware authors as a means of evading malware detectors (mainly static analysis-based detectors). This paper provides statistics on the use of packers based on an extensive analysis of 24,000 PE files (both malicious and benign files) for the past 10 years, which allowed us to observe trends in packing use during that time and showed that packing is still widely used in malware. This paper then surveys 23 methods proposed in academic research for the detection and classification of packed portable executable (PE) files and highlights various trends in malware packing. The paper highlights the differences between the methods and their abilities to detect and identify various aspects of packing. A taxonomy is presented, classifying the methods as static, dynamic, and hybrid analysis-based methods. The paper also sheds light on the increasing role of machine learning methods in the development of modern packing detection methods. We analyzed and mapped the different packing methods and identified which of them can be countered by the detection methods surveyed in this paper. [ABSTRACT FROM AUTHOR]

Emotion recognition technology through analyzing the EEG signal is currently an essential concept in Artificial Intelligence and holds great potential in emotional health care, human-computer interaction, multimedia content recommendation, etc. Though there have been several works devoted to reviewing EEG-based emotion recognition, the content of these reviews needs to be updated. In addition, those works are either fragmented in content or only focus on specific techniques adopted in this area but neglect the holistic perspective of the entire technical routes. Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic. We review the recent representative works in the EEG-based emotion recognition research and provide a tutorial to guide the researchers to start from the beginning. The scientific basis of EEG-based emotion recognition in the psychological and physiological levels is introduced. Further, we categorize these reviewed works into different technical routes and illustrate the theoretical basis and the research motivation, which will help the readers better understand why those techniques are studied and employed. At last, existing challenges and future investigations are also discussed in this paper, which guides the researchers to decide potential future research directions. [ABSTRACT FROM AUTHOR]

Clustering approaches are extensively used by many areas such as IR, Data Integration, Document Classification, Web Mining, Query Processing, and many other domains and disciplines. Nowadays, much literature describes clustering algorithms on multivariate data sets. However, there is limited literature that presented them with exhaustive and extensive theoretical analysis as well as experimental comparisons. This experimental survey paper deals with the basic principle, and techniques used, including important characteristics, application areas, run-time performance, internal, external, and stability validity of cluster quality, etc., on five different data sets of eleven clustering algorithms. This paper analyses how these algorithms behave with five different multivariate data sets in data representation. To answer this question, we compared the efficiency of eleven clustering approaches on five different data sets using three validity metrics-internal, external, and stability and found the optimal score to know the feasible solution of each algorithm. In addition, we have also included four popular and modern clustering algorithms with only their theoretical discussion. Our experimental results for only traditional clustering algorithms showed that different algorithms performed different behavior on different data sets in terms of running time (speed), accuracy and, the size of data set. This study emphasized the need for more adaptive algorithms and a deliberate balance between the running time and accuracy with their theoretical as well as implementation aspects. [ABSTRACT FROM AUTHOR]

Data confidentiality is a central concern in modern computer systems and services, as sensitive data from users and companies are being increasingly delegated to such systems. Several hardware-based mechanisms have been recently proposed to enforce security guarantees of sensitive information. Hardware-based isolated execution environments are a class of such mechanisms, in which the operating system and other low-level components are removed from the trusted computing base. One of such mechanisms is the Intel Software Guard Extensions (Intel SGX), which creates the concept of enclave to encapsulate sensitive components of applications and their data. Despite being largely applied in several computing areas, SGX has limitations and performance issues that must be addressed for the development of secure solutions. This text brings a categorized literature review of the ongoing research on the Intel SGX architecture, discussing its applications and providing a classification of the solutions that take advantage of SGX mechanisms. We analyze and categorize 293 papers that rely on SGX to provide integrity, confidentiality, and privacy to users and data, regarding different contexts and goals. We also discuss research challenges and provide future directions in the field of enclaved execution, particularly when using SGX. [ABSTRACT FROM AUTHOR]

In line with the general trend in artificial intelligence research to create intelligent systems that combine learning and symbolic components, a new sub-area has emerged that focuses on combining Machine Learning components with techniques developed by the SemanticWeb community--SemanticWebMachine Learning (SWeML). Due to its rapid growth and impact on several communities in thepast two decades, there is a need to better understand the space of these SWeML Systems, their characteristics, and trends. Yet, surveys that adopt principled and unbiased approaches are missing. To fill this gap, we performed a systematic study and analyzed nearly 500 papers published in the past decade in this area, where we focused on evaluating architectural and application-specific features. Our analysis identified a rapidly growing interest in SWeML Systems, with a high impact on several application domains and tasks. Catalysts for this rapid growth are the increased application of deep learning and knowledge graph technologies. By leveraging the in-depth understanding of this area acquired through this study, a further key contribution of this article is a classification system for SWeML Systems that we publish as ontology. [ABSTRACT FROM AUTHOR]

Promotional videos are rapidly becoming a popularmedium for persuading people to change their behaviours in many settings (e.g., online shopping, social enterprise initiatives). Today, such videos are often produced by professionals, which is a time-, labour- and cost-intensive undertaking. In order to produce such contents to support large applications (e.g., e-commerce), the field of artificial intelligence (AI)-empowered persuasive video generation (AIPVG) has gained traction in recent years. This field is interdisciplinary in nature, which makes it challenging for new researchers to grasp. Currently, there is no comprehensive survey of AIPVG available. In this paper, we bridge this gap by reviewing key AI techniques that can be utilized to automatically generate persuasive videos. We offer a first-of-its-kind taxonomy which divides AIPVG into three major steps: (1) visual material understanding, which extracts information from the visual materials (VMs) relevant to the target of promotion; (2) visual storyline generation, which shortlists and arranges highquality VMs into a sequence in order to compose a storyline with persuasive power; and (3) post-production, which involves background music generation and still image animation to enhance viewing experience. We also introduce the evaluation metrics and datasets commonly adopted in the field of AIPVG. We analyze the advantages and disadvantages of the existing works belonging to the above-mentioned steps, and discuss interesting potential future research directions. [ABSTRACT FROM AUTHOR]

Data-driven algorithms are only as good as the data they work with, while datasets, especially social data, often fail to represent minorities adequately. Representation Bias in data can happen due to various reasons, ranging from historical discrimination to selection and sampling biases in the data acquisition and preparation methods. Given that "bias in, bias out," one cannot expect AI-based solutions to have equitable outcomes for societal applications, without addressing issues such as representation bias. While there has been extensive study of fairness in machine learning models, including several review papers, bias in the data has been less studied. This article reviews the literature on identifying and resolving representation bias as a feature of a dataset, independent of how consumed later. The scope of this survey is bounded to structured (tabular) and unstructured (e.g., image, text, graph) data. It presents taxonomies to categorize the studied techniques based on multiple design dimensions and provides a side-by-side comparison of their properties. There is still a long way to fully address representation bias issues in data. The authors hope that this survey motivates researchers to approach these challenges in the future by observing existing work within their respective domains. [ABSTRACT FROM AUTHOR]

Sentiment analysis has come long way since it was introduced as a natural language processing task nearly 20 years ago. Sentiment analysis aims to extract the underlying attitudes and opinions toward an entity. It has become a powerful tool used by governments, businesses, medicine, marketing, and others. The traditional sentiment analysis model focuses mainly on text content. However, technological advances have allowed people to express their opinions and feelings through audio, image and video channels. As a result, sentiment analysis is shifting from unimodality to multimodality. Multimodal sentiment analysis brings new opportunities with the rapid increase of sentiment analysis as complementary data streams enable improved and deeper sentiment detection which goes beyond text-based analysis. Audio and video channels are included in multimodal sentiment analysis in terms of broadness. People have been working on different approaches to improve sentiment analysis system performance by employing complex deep neural architectures. Recently, sentiment analysis has achieved significant success using the transformer-based model. This paper presents a comprehensive study of different sentiment analysis approaches, applications, challenges, and resources then concludes that it holds tremendous potential. The primary motivation of this survey is to highlight changing trends in the unimodality to multimodality for solving sentiment analysis tasks. [ABSTRACT FROM AUTHOR]

Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a few or even zero samples remains a serious challenge. In this context, we extensively investigated 200+ FSL papers published in top journals and conferences in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL with a fresh perspective and to provide an impartial comparison of the strengths and weaknesses of existing work. To avoid conceptual confusion, we first elaborate and contrast a set of relevant concepts including few-shot learning, transfer learning, and meta-learning. Then, we inventively extract prior knowledge related to few-shot learning in the form of a pyramid, which summarizes and classifies previous work in detail from the perspective of challenges. Furthermore, to enrich this survey, we present in-depth analysis and insightful discussions of recent advances in each subsection. What is more, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into technology trends and potential future research opportunities to guide FSL follow-up research. [ABSTRACT FROM AUTHOR]

Context: Software regression testing refers to rerunning test cases after the system under test is modified, ascertaining that the changes have not (re-)introduced failures. Not all researchers' approaches consider applicability and scalability concerns, and not many have produced an impact in practice. Objective: One goal is to investigate industrial relevance and applicability of proposed approaches. Another is providing a live review, open to continuous updates by the community. Method: A systematic review of regression testing studies that are clearly motivated by or validated against industrial relevance and applicability is conducted. It is complemented by follow-up surveys with authors of the selected papers and 23 practitioners. Results: A set of 79 primary studies published between 2016-2022 is collected and classified according to approaches and metrics. Aspects relative to their relevance and impact are discussed, also based on their authors' feedback. All the data are made available from the live repository that accompanies the study. Conclusions: While widely motivated by industrial relevance and applicability, not many approaches are evaluated in industrial or large-scale open-source systems, and even fewer approaches have been adopted in practice. Some challenges hindering the implementation of relevant approaches are synthesized, also based on the practitioners' feedback. [ABSTRACT FROM AUTHOR]

Underwater computer vision has attracted increasing attention in the research community due to the recent advances in underwater platforms such as of rovers, gliders, autonomous underwater vehicles (AUVs), and the like, that now make possible the acquisition of vast amounts of imagery and video for applications such as biodiversity assessment, environmental monitoring, and search and rescue. Despite growing interest, underwater computer vision is still a relatively under-researched area, where the attention in the literature has been paid to the use of computer vision techniques for image restoration and reconstruction, where image formation models and image processing methods are used to recover colour corrected or enhanced images. This is due to the notion that these methods can be used to achieve photometric invariants to perform higher-level vision tasks such as shape recovery and recognition under the challenging and widely varying imaging conditions that apply to underwater scenes. In this paper, we review underwater computer vision techniques for image reconstruction, restoration, recognition, depth, and shape recovery. Further, we review current applications such as biodiversity assessment, management and protection, infrastructure inspection and AUVs navigation, amongst others. We also delve upon the current trends in the field and examine the challenges and opportunities in the area. [ABSTRACT FROM AUTHOR]

Deep person generation has attracted extensive research attention due to its wide applications in virtual agents, video conferencing, online shopping, and art/movie production. With the advancement of deep learning, visual appearances (face, pose, cloth) of a person image can be easily generated on demand. In this survey, we first summarize the scope of person generation, and then systematically review recent progress and technical trends in identity-preserving deep person generation, covering three major tasks: talking-head generation (face), pose-guided person generation (pose), and garment-oriented person generation (cloth). More than two hundred papers are covered for a thorough overview, and the milestone works are highlighted to witness the major technical breakthrough. Based on these fundamental tasks, many applications are investigated, e.g., virtual fitting, digital human, and generative data augmentation. We hope this survey could shed some light on the future prospects of identity-preserving deep person generation, and provide a helpful foundation for full applications towards the digital human. [ABSTRACT FROM AUTHOR]

Video Object Segmentation (VOS) methods have made many breakthroughs with the help of the continuous development and advancement of deep learning. However, the deep learning model is vulnerable to malicious adversarial attacks, which mislead the model to make wrong decisions by adding adversarial perturbation that humans cannot perceive to the input image. Threats to deep learning models remind us that video object segmentation methods are also vulnerable to attacks, thereby threatening their security. Therefore, we study adversarial attacks on the VOS task to better identify the vulnerabilities of the VOS method, which in turn provides an opportunity to improve its robustness. In this paper, we propose an attention-guided adversarial attack method, which uses spatial attention blocks to capture features with global dependencies to construct correlations between consecutive video frames, and performs multipath aggregation to effectively integrate spatial-temporal perturbation, thereby guiding the deconvolution network to generate adversarial examples with strong attack capability. Specifically, the class loss function is designed to enable the deconvolution network to better activate noise in other regions and suppress the activation related to the object class based on the enhanced feature map of the object class. At the same time, attentional feature loss is designed to enhance the transferability against attack. The experimental results on the DAVIS dataset show that the proposed attention-guided adversarial attack method can significantly reduce the segmentation accuracy of OSVOS, and the J&F mean on DAVIS 2016 can reach 73.6% drop rate. The generated adversarial examples are also highly transferable to other video object segmentation models. [ABSTRACT FROM AUTHOR]

Resource allocation systems (RASs) belong to a kind of discrete event system commonly seen in the industry. In such systems, available resources are allocated to concurrently running processes to optimize some performance criteria. Search strategies in the reachability graph (RG) of a timed Petri net (PN) attracted much attention in the past decades to cope with RAS scheduling problems (RSPs), since PNs are very suitable to model and analyze RASs and their RGs fully reflect systems’ behavior. However, there has been no existing related survey and review paper till now. In this work, we present a tutorial and comprehensive literature survey of RG-based RSP methods. Many state-of-the-art RG-based RAS scheduling strategies are reviewed and summarized. First, we present a framework of RSPs and classify RSPs and their PNs in terms of resource usage and net structures. The differences and relations among the PNs are also given. Then, we introduce timed PN construction methods for RSPs and scheduling objectives and search strategies for RG-based RSPs. Next, we summarize different heuristic functions adopted in a frequently used A ∗ search to solve RG-based RSPs. Finally, we discuss some important future research directions and open issues. [ABSTRACT FROM AUTHOR]

Information technology (IT) departments are increasingly challenged to replace legacy applications with novel public cloud software as a service (SaaS) to innovate the organization’s business processes. The resulting hybrid cloud is formed by integrating the added SaaS with existing IT services. The decision to adopt SaaS in such a hybrid cloud service composition requires appropriate consideration of the respective service level agreements (SLA) to ensure the proper execution of the supported business process. Previous studies focused strongly on cloud service selection or SLA negotiation rather than functionally desired SaaS adoption from the perspective of the hybrid cloud provider as integrator. This research paper identifies economic and technical issues in hybrid cloud arising from SaaS adoption and discusses challenges and existing solutions. A structured literature survey revealed that 52 issues in 36 identified publications are transferable to our context. These issues were classified in six different challenges. We were able to explore the relations between solution artifacts of various challenges and provide guidance for future research concerning hybrid clouds. The relations between the challenges are also found to vary in their research maturity and offer promising fields for further research. [ABSTRACT FROM AUTHOR]

Current sensor technologies facilitate device-free and non-invasive monitoring of target activities and infrastructures to ensure a safe and inhabitable environment. Device-free techniques for sensing the surrounding environment are an emerging area of research where a target does not need to carry or attach any device to provide information about its motion or the surrounding environment. Consequently, there has been an increasing interest in device-free sensing. Seismic sensors are extremely effective tools for gathering target motion information. In this paper, we provide a comprehensive overview of the seismic sensor-based devicefree sensing process and highlight the key techniques within the research field.We classify the existing literature into three categories, viz., (i) target detection, (ii) target localization, and (iii) target identification, and activity recognition. The techniques in each category are divided into multiple subcategories in a structured manner to comprehensively discuss the details.We also discuss the challenges associated with contemporary cutting-edge research and suggest potential solutions. [ABSTRACT FROM AUTHOR]

Humans’ ability to transfer knowledge through teaching is one of the essential aspects for human intelligence. A human teacher can track the knowledge of students to customize the teaching on students’ needs. With the rise of online education platforms, there is a similar need for machines to track the knowledge of students and tailor their learning experience. This is known as the Knowledge Tracing (KT) problem in the literature. Effectively solving the KT problem would unlock the potential of computer-aided education applications such as intelligent tutoring systems, curriculum learning, and learning materials’ recommendation. Moreover, from a more general viewpoint, a student may represent any kind of intelligent agents including both human and artificial agents. Thus, the potential of KT can be extended to any machine teaching application scenarios which seek for customizing the learning experience for a student agent (i.e., a machine learning model). In this paper, we provide a comprehensive survey for the KT literature. We cover a broad range of methods starting from the early attempts to the recent state-of-the-art methods using deep learning, while highlighting the theoretical aspects of models and the characteristics of benchmark datasets. Besides these, we shed light on key modelling differences between closely related methods and summarize them in an easy-to-understand format. Finally, we discuss current research gaps in the KT literature and possible future research and application directions. [ABSTRACT FROM AUTHOR]

Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural Networks (DNN). It offers many significant opportunities for improving DNN performance and efficiency and has been explored in a large body of work. These studies have scattered in many venues across several years. The targets they focus on range from images to videos and texts, and the techniques they use to detect and exploit data redundancy also vary in many aspects. There is not yet a systematic examination and summary of the many efforts, making it difficult for researchers to get a comprehensive view of the prior work, the state of the art, differences and shared principles, and the areas and directions yet to explore. This article tries to fill the void. It surveys hundreds of recent papers on the topic, introduces a novel taxonomy to put the various techniques into a single categorization framework, offers a comprehensive description of the main methods used for exploiting data redundancy in improving multiple kinds of DNNs on data, and points out a set of research opportunities for future exploration. [ABSTRACT FROM AUTHOR]

Although there are methods of artificial intelligence (AI) applied to virtual reality (VR) solutions, there are few studies in the literature. Thus, to fill this gap, we performed a systematic literature review of these methods. In this review, we apply a methodology proposed in the literature that locates existing studies, selects and evaluates contributions, analyses, and synthesizes data. We used Google Scholar and databases such as Elsevier’s Scopus, ACM Digital Library, and IEEE Xplore Digital Library. A set of inclusion and exclusion criteria were used to select documents. The results showed that when AI methods are used in VR applications, the main advantages are high efficiency and precision of algorithms. Moreover, we observe that machine learning is the most applied AI scientific technique in VR applications. In conclusion, this paper showed that the combination of AI and VR contributes to new trends, opportunities, and applications for human-machine interactive devices, education, agriculture, transport, 3D image reconstruction, and health. We also concluded that the usage of AI in VR provides potential benefits in other fields of the real world such as teleconferencing, emotion interaction, tourist services, and image data extraction. [ABSTRACT FROM AUTHOR]

With the increasing interest in the content creation field in multiple sectors such as media, education, and entertainment, there is an increased trend in the papers that use AI algorithms to generate content such as images, videos, audio, and text. Generative Adversarial Networks (GANs) is one of the promising models that synthesizes data samples that are similar to real data samples. While the variations of GANs models in general have been covered to some extent in several survey papers, to the best of our knowledge, this is the first paper that reviews the state-of-the-art video GANs models. This paper first categorizes GANs review papers into general GANs review papers, image GANs review papers, and special field GANs review papers such as anomaly detection, medical imaging, or cybersecurity. The paper then summarizes the main improvements in GANs that are not necessarily applied in the video domain in the first run but have been adopted in multiple video GANs variations. Then, a comprehensive review of video GANs models are provided under two main divisions based on existence of a condition. The conditional models are then further classified according to the provided condition into audio, text, video, and image. The paper concludes with the main challenges and limitations of the current video GANs models. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) are becoming one of the main technological supports for commercial applications, embracing many domains ranging from human safety to the medical field, agriculture and environment, multimedia production, and even commercial delivery. This rise in popularity, however, is causing an increasing interest from criminals, making UAVs the target of new attacks. To fully characterize the current UAV cybersecurity landscape, we perform a complete literature review, digging into drone security historic facts and scientific studies on the matter, reviewing specialized articles and scientific papers focusing on cybersecurity threats and gaps in the context of small UAVs in commercial applications. Being a recent research and development area, most of the articles have been published between 2016 and 2020 as a direct consequence of the increase of security concerns and interest in the drone field. Papers in this review deal with UAV cyberthreats and related vulnerabilities, identifying flaws experimented in a lab or describing incidents detected in the field. Communication, sensors, and system misconfigurations are among the most important threat vectors, while sensor spoofing/jamming and malware DoS/control are among the most cited threats. Threat vectors permit depicting a complete overview of the topic and potential countermeasures known to date, with related gap analysis, also accounting for the recent Unmanned Aircraft System evolution toward ad hoc or cloud-based UAV networks. Countermeasures include the adoption of traditional communication encryption and standard protocols, GPS spoofing/jamming mitigation, encryption and privacy-aware implementations, and counter-malware techniques, to name the most adopted. It also emerges that often attacks are simply ported or adapted from other attacks in similar domains, while peculiar attacks still remain such as targeted physical attacks, specific UAV malware, and GPS spoofing/jamming. [ABSTRACT FROM AUTHOR]

Equation-based modelling is a powerful approach to tame the complexity of large-scale simulation problems. Equation-based tools automatically translate models into imperative languages. When confronted with nowadays' problems, however, well assessed model translation techniques exhibit scalability issues that are particularly severe when models contain very large arrays. In fact, such models can be made very compact by enclosing equations into looping constructs, but reflecting the same compactness into the translated imperative code is nontrivial. In this paper, we face this issue by concentrating on a key step of equations-to-code translation, the equation/variable matching. We first show that an efficient translation of models with (large) arrays needs awareness of their presence, by defining a figure of merit to measure how much the looping constructs are preserved along the translation. We then show that the said figure of merit allows to define an optimal array-aware matching, and as our main result, that the so stated optimal array-aware matching problem is NP-complete. As an additional result, we propose a heuristic algorithm capable of performing array-aware matching in polynomial time. The proposed algorithm can be proficiently used by model translator developers in the implementation of efficient tools for large-scale system simulation. [ABSTRACT FROM AUTHOR]

There has been a trend of moving from simply de-identification to providing extended data control to their owner (e.g., data portability and right to be forgotten), partly due to the introduction of the General Data Protection Regulation (GDPR). Hence, in this paper, we survey the literature to provide an in-depth understanding of the existing approaches for personal data control (e.g., we observe that most existing approaches are generally designed to facilitate compliance), as well as the privacy regulations in Europe, United Kingdom, California, South Korea, and Japan. Based on the review, we identify the associated technical requirements, as well as a number of research gaps and potential future directions (e.g., the need for transparent processing of personal data and establishment of clear procedure in ensuring personal data control). [ABSTRACT FROM AUTHOR]

The need for remote tools for healthcare monitoring has never been more apparent. Camera measurement of vital signs leverages imaging devices to compute physiological changes by analyzing images of the human body. Building on advances in optics, machine learning, computer vision, and medicine, these techniques have progressed significantly since the invention of digital cameras. This article presents a comprehensive survey of camera measurement of physiological vital signs, describing the vital signs that can be measured and the computational techniques for doing so. I cover both clinical and non-clinical applications and the challenges that need to be overcome for these applications to advance from proofs of concept. Finally, I describe the current resources (datasets and code) available to the research community and provide a comprehensivewebpage (https://cameravitals.github.io/) with links to these resource and a categorized list of all papers referenced in this article. [ABSTRACT FROM AUTHOR]

Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models. [ABSTRACT FROM AUTHOR]

State-separating proofs (SSP) is a recent methodology for structuring game-based cryptographic proofs in a modular way, by using algebraic laws to exploit the modular structure of composed protocols. While promising, this methodology was previously not fully formalized and came with little tool support. We address this by introducing SSProve, the first general verification framework for machine-checked state-separating proofs. SSProve combines high-level modular proofs about composed protocols, as proposed in SSP, with a probabilistic relational program logic for formalizing the lower-level details, which together enable constructing machine-checked cryptographic proofs in the Coq proof assistant. Moreover, SSProve is itself fully formalized in Coq, including the algebraic laws of SSP, the soundness of the program logic, and the connection between these two verification styles. To illustrate SSProve, we use it to mechanize the simple security proofs of ElGamal and pseudo-randomfunction–based encryption. We also validate the SSProve approach by conducting two more substantial case studies: First, we mechanize an SSP security proof of the key encapsulation mechanism–data encryption mechanism (KEM-DEM) public key encryption scheme, which led to the discovery of an error in the original paper proof that has since been fixed. Second, we use SSProve to formally prove security of the sigma-protocol zero-knowledge construction, and we moreover construct a commitment scheme from a sigma-protocol to compare with a similar development in CryptHOL. We instantiate the security proof for sigma-protocols to give concrete security bounds for Schnorr’s sigma-protocol. [ABSTRACT FROM AUTHOR]

Area under the ROC curve, a.k.a. AUC, is a measure of choice for assessing the performance of a classifier for imbalanced data. AUC maximization refers to a learning paradigm that learns a predictive model by directly maximizing its AUC score. It has been studied for more than two decades dating back to late 90s, and a huge amount of work has been devoted to AUC maximization since then. Recently, stochastic AUC maximization for big data and deep AUC maximization (DAM) for deep learning have received increasing attention and yielded dramatic impact for solving real-world problems. However, to the best our knowledge, there is no comprehensive survey of related works for AUC maximization. This article aims to address the gap by reviewing the literature in the past two decades. We not only give a holistic view of the literature but also present detailed explanations and comparisons of different papers from formulations to algorithms and theoretical guarantees. We also identify and discuss remaining and emerging issues for DAM and provide suggestions on topics for future work. [ABSTRACT FROM AUTHOR]

Quantum computing is the latest revolution in computing and will probably come to be seen as an advance as important as the steam engine or the information society. In the last few decades, our understanding of quantum computers has expanded and multiple efforts have been made to create languages, libraries, tools, and environments to facilitate their programming. Nonetheless, quantum computers are complex systems at the bottom of a stack of layers that programmers need to understand. Hence, efforts towards creating quantum programming languages and computing environments that can abstract low-level technology details have become crucial steps to achieve a useful quantum computing technology. However, most of these environments still lack many of the features that would be desirable, such as those outlined in The Talavera Manifesto for Quantum Software Engineering and Programming. For advancing quantum computing, we will need to develop quantum software engineering techniques and tools to ensure the feasibility of this new type of quantum software. To contribute to this goal, this paper provides a review of the main quantum software components and platforms. We also propose a set of quality requirements for the development of quantum software platforms and the conduct of their quality assessment. [ABSTRACT FROM AUTHOR]

Remote electronic voting, often called online or Internet voting, has been subject to research for the last four decades. It is regularly discussed in public debates, especially in the context of enabling voters to conveniently cast their ballot from home using their personal devices. Since these devices are not under the control of the electoral authority and could be potentially compromised, this setting is referred to as an "uncontrolled environment" for which special security assumptions have to be considered. This paper employs general election principles to derive cryptographic, technical, and organizational requirements for remote electronic voting. Based on these requirements, we have extended an existing methodology to assess online voting schemes and develop a corresponding reference attacker model to support the preparation of tailored protection profiles for different levels of elections. After presenting a broad survey of different voting schemes, we use this methodology to assess and classify those schemes comparatively by leveraging four election-specific attacker models. [ABSTRACT FROM AUTHOR]

Humans are increasingly integrated with devices that enable the collection of vast unstructured opinionated data. Accurately analysing subjective information from this data is the task of sentiment analysis (an actively researched area in NLP). Deep learning provides a diverse selection of architectures to model sentiment analysis tasks and has surpassed other machine learning methods as the foremast approach for performing sentiment analysis tasks. Recent developments in deep learning architectures represent a shift away from Recurrent and Convolutional neural networks and the increasing adoption of Transformer language models. Utilising pre-trained Transformer language models to transfer knowledge to downstream tasks has been a breakthrough in NLP. This survey applies a task-oriented taxonomy to recent trends in architectures with a focus on the theory, design and implementation. To the best of our knowledge, this is the only survey to cover state-of-the-art Transformer-based language models and their performance on the most widely used benchmark datasets. This survey paper provides a discussion of the open challenges in NLP and sentiment analysis. The survey covers five years from 1st July 2017 to 1st July 2022. [ABSTRACT FROM AUTHOR]

The outstanding performance of deep neural networks has promoted deep learning applications in a broad set of domains. However, the potential risks caused by adversarial samples have hindered the large-scale deployment of deep learning. In these scenarios, adversarial perturbations, imperceptible to human eyes, significantly decrease the model's final performance. Many papers have been published on adversarial attacks and their countermeasures in the realm of deep learning. Most focus on evasion attacks, where the adversarial examples are found at test time, as opposed to poisoning attacks where poisoned data is inserted into the training data. Further, it is difficult to evaluate the real threat of adversarial attacks or the robustness of a deep learning model, as there are no standard evaluation methods. Hence, with this article, we review the literature to date. Additionally, we attempt to offer the first analysis framework for a systematic understanding of adversarial attacks. The framework is built from the perspective of cybersecurity to provide a lifecycle for adversarial attacks and defenses. [ABSTRACT FROM AUTHOR]