Search

This study presents an uncertainty-aware stacked neural networks model for the reliable classification of COVID-19 from radiological images. The model addresses the critical gap in uncertainty-aware modeling by focusing on accurately identifying confidently correct predictions while alerting users to confidently incorrect and uncertain predictions, which can promote trust in automated systems. The architecture integrates uncertainty quantification methods, including Monte Carlo dropout and ensemble techniques, to enhance predictive reliability by assessing the certainty of diagnostic predictions. Within a two-tier model framework, the tier one model generates initial predictions and associated uncertainties, which the second tier model uses to produce a trust indicator alongside the diagnostic outcome. This dual-output model not only predicts COVID-19 cases but also provides a trust flag, indicating the reliability of each diagnosis and aiming to minimize the need for retesting and expert verification. The effectiveness of this approach is demonstrated through extensive experiments on the COVIDx CXR-4 dataset, showing a novel approach in identifying and handling confidently incorrect cases and uncertain cases, thus enhancing the trustworthiness of automated diagnostics in clinical settings., Comment: 15 pages, 7 figures, 6 tables

Understanding emotions is a fundamental aspect of human communication. Integrating audio and video signals offers a more comprehensive understanding of emotional states compared to traditional methods that rely on a single data source, such as speech or facial expressions. Despite its potential, multimodal emotion recognition faces significant challenges, particularly in synchronization, feature extraction, and fusion of diverse data sources. To address these issues, this paper introduces a novel transformer-based model named Audio-Video Transformer Fusion with Cross Attention (AVT-CA). The AVT-CA model employs a transformer fusion approach to effectively capture and synchronize interlinked features from both audio and video inputs, thereby resolving synchronization problems. Additionally, the Cross Attention mechanism within AVT-CA selectively extracts and emphasizes critical features while discarding irrelevant ones from both modalities, addressing feature extraction and fusion challenges. Extensive experimental analysis conducted on the CMU-MOSEI, RAVDESS and CREMA-D datasets demonstrates the efficacy of the proposed model. The results underscore the importance of AVT-CA in developing precise and reliable multimodal emotion recognition systems for practical applications., Comment: 38 Pages, 9 Tables, 12 Figures

In the rapidly evolving optimization and metaheuristics domains, the efficacy of algorithms is crucially determined by the benchmark (test) functions. While several functions have been developed and derived over the past decades, little information is available on the mathematical and visual description, range of suitability, and applications of many such functions. To bridge this knowledge gap, this review provides an exhaustive survey of more than 300 benchmark functions used in the evaluation of optimization and metaheuristics algorithms. This review first catalogs benchmark and test functions based on their characteristics, complexity, properties, visuals, and domain implications to offer a wide view that aids in selecting appropriate benchmarks for various algorithmic challenges. This review also lists the 25 most commonly used functions in the open literature and proposes two new, highly dimensional, dynamic and challenging functions that could be used for testing new algorithms. Finally, this review identifies gaps in current benchmarking practices and suggests directions for future research.

Clustering in dynamic environments is of increasing importance, with broad applications ranging from real-time data analysis and online unsupervised learning to dynamic facility location problems. While meta-heuristics have shown promising effectiveness in static clustering tasks, their application for tracking optimal clustering solutions or robust clustering over time in dynamic environments remains largely underexplored. This is partly due to a lack of dynamic datasets with diverse, controllable, and realistic dynamic characteristics, hindering systematic performance evaluations of clustering algorithms in various dynamic scenarios. This deficiency leads to a gap in our understanding and capability to effectively design algorithms for clustering in dynamic environments. To bridge this gap, this paper introduces the Dynamic Dataset Generator (DDG). DDG features multiple dynamic Gaussian components integrated with a range of heterogeneous, local, and global changes. These changes vary in spatial and temporal severity, patterns, and domain of influence, providing a comprehensive tool for simulating a wide range of dynamic scenarios.

Matching identical products present in multiple product feeds constitutes a crucial element of many tasks of e-commerce, such as comparing product offerings, dynamic price optimization, and selecting the assortment personalized for the client. It corresponds to the well-known machine learning task of entity matching, with its own specificity, like omnipresent unstructured data or inaccurate and inconsistent product descriptions. This paper aims to present a new philosophy to product matching utilizing a semi-supervised clustering approach. We study the properties of this method by experimenting with the IDEC algorithm on the real-world dataset using predominantly textual features and fuzzy string matching, with more standard approaches as a point of reference. Encouraging results show that unsupervised matching, enriched with a small annotated sample of product links, could be a possible alternative to the dominant supervised strategy, requiring extensive manual data labeling.

In machine learning, the exponential growth of data and the associated ``curse of dimensionality'' pose significant challenges, particularly with expansive yet sparse datasets. Addressing these challenges, multi-view ensemble learning (MEL) has emerged as a transformative approach, with feature partitioning (FP) playing a pivotal role in constructing artificial views for MEL. Our study introduces the Semantic-Preserving Feature Partitioning (SPFP) algorithm, a novel method grounded in information theory. The SPFP algorithm effectively partitions datasets into multiple semantically consistent views, enhancing the MEL process. Through extensive experiments on eight real-world datasets, ranging from high-dimensional with limited instances to low-dimensional with high instances, our method demonstrates notable efficacy. It maintains model accuracy while significantly improving uncertainty measures in scenarios where high generalization performance is achievable. Conversely, it retains uncertainty metrics while enhancing accuracy where high generalization accuracy is less attainable. An effect size analysis further reveals that the SPFP algorithm outperforms benchmark models by large effect size and reduces computational demands through effective dimensionality reduction. The substantial effect sizes observed in most experiments underscore the algorithm's significant improvements in model performance., Comment: 45 pages, 44 figures, 26 tables

As optimization challenges continue to evolve, so too must our tools and understanding. To effectively assess, validate, and compare optimization algorithms, it is crucial to use a benchmark test suite that encompasses a diverse range of problem instances with various characteristics. Traditional benchmark suites often consist of numerous fixed test functions, making it challenging to align these with specific research objectives, such as the systematic evaluation of algorithms under controllable conditions. This paper introduces the Generalized Numerical Benchmark Generator (GNBG) for single-objective, box-constrained, continuous numerical optimization. Unlike existing approaches that rely on multiple baseline functions and transformations, GNBG utilizes a single, parametric, and configurable baseline function. This design allows for control over various problem characteristics. Researchers using GNBG can generate instances that cover a broad array of morphological features, from unimodal to highly multimodal functions, various local optima patterns, and symmetric to highly asymmetric structures. The generated problems can also vary in separability, variable interaction structures, dimensionality, conditioning, and basin shapes. These customizable features enable the systematic evaluation and comparison of optimization algorithms, allowing researchers to probe their strengths and weaknesses under diverse and controllable conditions.

This document introduces a set of 24 box-constrained numerical global optimization problem instances, systematically constructed using the Generalized Numerical Benchmark Generator (GNBG). These instances cover a broad spectrum of problem features, including varying degrees of modality, ruggedness, symmetry, conditioning, variable interaction structures, basin linearity, and deceptiveness. Purposefully designed, this test suite offers varying difficulty levels and problem characteristics, facilitating rigorous evaluation and comparative analysis of optimization algorithms. By presenting these problems, we aim to provide researchers with a structured platform to assess the strengths and weaknesses of their algorithms against challenges with known, controlled characteristics. For reproducibility, the MATLAB source code for this test suite is publicly available.

With the surge in data generation, both vertically (i.e., volume of data) and horizontally (i.e., dimensionality), the burden of the curse of dimensionality has become increasingly palpable. Feature selection, a key facet of dimensionality reduction techniques, has advanced considerably to address this challenge. One such advancement is the Boruta feature selection algorithm, which successfully discerns meaningful features by contrasting them to their permutated counterparts known as shadow features. However, the significance of a feature is shaped more by the data's overall traits than by its intrinsic value, a sentiment echoed in the conventional Boruta algorithm where shadow features closely mimic the characteristics of the original ones. Building on this premise, this paper introduces an innovative approach to the Boruta feature selection algorithm by incorporating noise into the shadow variables. Drawing parallels from the perturbation analysis framework of artificial neural networks, this evolved version of the Boruta method is presented. Rigorous testing on four publicly available benchmark datasets revealed that this proposed technique outperforms the classic Boruta algorithm, underscoring its potential for enhanced, accurate feature selection., Comment: 8 pages, 4 figures, 8 tables, 4 algorithms

The Internet of Things (IoT) is regarded as an improved communication system that has revolutionized traditional lifestyles. To function successfully, IoT requires a combination of cloud, fog, and edge computing architectures. Few studies have addressed cloud, fog, and edge computing simultaneously, comparing them and their issues, although several studies have looked into ways of integrating IoT with either one or two computing systems. Thus, this review provides a thorough understanding of IoT integration with these three computing architectures, as well as their respective applications and limitations. It also highlights the advantages, unresolved issues, future opportunities and directions of IoT integration with the computing systems to advance the IoT. IoT can use the Cloud's almost limitless resources to overcome technology restrictions, such as data processing, storage, and transmission. While edge computing can outperform cloud computing in many circumstances, IoT and edge computing become increasingly integrated as IoT devices increase. Cloud computing also poses a few issues, including managing time-sensitive IoT applications like video gaming, simulation, and streaming, which can be addressed by fog computing integrated with IoT. Due to the proximity of fog computing resources to the edge, data transfers and communication delays to the cloud can be reduced as a result of combining the two. The integration of IoT with cloud, fog, and edge computing will create new business prototypes and opportunities. Since IoT has the potential to greatly enhance connectivity infrastructure as an inevitable component of the future internet, further study is needed before it can be fully integrated., Comment: 69 pages, 6 tables, 3 figures

Deep learning (DL) enables the development of computer models that are capable of learning, visualizing, optimizing, refining, and predicting data. In recent years, DL has been applied in a range of fields, including audio-visual data processing, agriculture, transportation prediction, natural language, biomedicine, disaster management, bioinformatics, drug design, genomics, face recognition, and ecology. To explore the current state of deep learning, it is necessary to investigate the latest developments and applications of deep learning in these disciplines. However, the literature is lacking in exploring the applications of deep learning in all potential sectors. This paper thus extensively investigates the potential applications of deep learning across all major fields of study as well as the associated benefits and challenges. As evidenced in the literature, DL exhibits accuracy in prediction and analysis, makes it a powerful computational tool, and has the ability to articulate itself and optimize, making it effective in processing data with no prior training. Given its independence from training data, deep learning necessitates massive amounts of data for effective analysis and processing, much like data volume. To handle the challenge of compiling huge amounts of medical, scientific, healthcare, and environmental data for use in deep learning, gated architectures like LSTMs and GRUs can be utilized. For multimodal learning, shared neurons in the neural network for all activities and specialized neurons for particular tasks are necessary., Comment: 64 pages, 3 figures, 3 tables

Given the exponential expansion of the internet, the possibilities of security attacks and cybercrimes have increased accordingly. However, poorly implemented security mechanisms in the Internet of Things (IoT) devices make them susceptible to cyberattacks, which can directly affect users. IoT forensics is thus needed for investigating and mitigating such attacks. While many works have examined IoT applications and challenges, only a few have focused on both the forensic and security issues in IoT. Therefore, this paper reviews forensic and security issues associated with IoT in different fields. Future prospects and challenges in IoT research and development are also highlighted. As demonstrated in the literature, most IoT devices are vulnerable to attacks due to a lack of standardized security measures. Unauthorized users could get access, compromise data, and even benefit from control of critical infrastructure. To fulfil the security-conscious needs of consumers, IoT can be used to develop a smart home system by designing a FLIP-based system that is highly scalable and adaptable. Utilizing a blockchain-based authentication mechanism with a multi-chain structure can provide additional security protection between different trust domains. Deep learning can be utilized to develop a network forensics framework with a high-performing system for detecting and tracking cyberattack incidents. Moreover, researchers should consider limiting the amount of data created and delivered when using big data to develop IoT-based smart systems. The findings of this review will stimulate academics to seek potential solutions for the identified issues, thereby advancing the IoT field., Comment: 77 pages, 5 figures, 5 tables

Many real-world optimization problems possess dynamic characteristics. Evolutionary dynamic optimization algorithms (EDOAs) aim to tackle the challenges associated with dynamic optimization problems. Looking at the existing works, the results reported for a given EDOA can sometimes be considerably different. This issue occurs because the source codes of many EDOAs, which are usually very complex algorithms, have not been made publicly available. Indeed, the complexity of components and mechanisms used in many EDOAs makes their re-implementation error-prone. In this paper, to assist researchers in performing experiments and comparing their algorithms against several EDOAs, we develop an open-source MATLAB platform for EDOAs, called Evolutionary Dynamic Optimization LABoratory (EDOLAB). This platform also contains an education module that can be used for educational purposes. In the education module, the user can observe a) a 2-dimensional problem space and how its morphology changes after each environmental change, b) the behaviors of individuals over time, and c) how the EDOA reacts to environmental changes and tries to track the moving optimum. In addition to being useful for research and education purposes, EDOLAB can also be used by practitioners to solve their real-world problems. The current version of EDOLAB includes 25 EDOAs and three fully-parametric benchmark generators. The MATLAB source code for EDOLAB is publicly available and can be accessed from [https://github.com/EDOLAB-platform/EDOLAB-MATLAB]., Comment: This work was submitted to ACM Transactions on Mathematical Software on December 7, 2022

In recent decades, social network anonymization has become a crucial research field due to its pivotal role in preserving users' privacy. However, the high diversity of approaches introduced in relevant studies poses a challenge to gaining a profound understanding of the field. In response to this, the current study presents an exhaustive and well-structured bibliometric analysis of the social network anonymization field. To begin our research, related studies from the period of 2007-2022 were collected from the Scopus Database then pre-processed. Following this, the VOSviewer was used to visualize the network of authors' keywords. Subsequently, extensive statistical and network analyses were performed to identify the most prominent keywords and trending topics. Additionally, the application of co-word analysis through SciMAT and the Alluvial diagram allowed us to explore the themes of social network anonymization and scrutinize their evolution over time. These analyses culminated in an innovative taxonomy of the existing approaches and anticipation of potential trends in this domain. To the best of our knowledge, this is the first bibliometric analysis in the social network anonymization field, which offers a deeper understanding of the current state and an insightful roadmap for future research in this domain., Comment: 73 pages, 28 figures

Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (I) metric-based, (II) memory-based, (III), and learning-based methods. Finally, current challenges and insights for future researches are discussed.

In earthquake-prone zones, the seismic performance of reinforced concrete cantilever (RCC) retaining walls is significant. In this study, the seismic performance was investigated using horizontal and vertical pseudo-static coefficients. To tackle RCC weights and forces resulting from these earth pressures, 26 constraints for structural strengths and geotechnical stability along with 12 geometric variables are associated with each design. These constraints and design variables form a constraint optimization problem with a twelve-dimensional solution space. To conduct effective search and produce sustainable, economical, lightweight RCC designs robust against earthquake hazards, a novel adaptive fuzzy-based metaheuristic algorithm is applied. The proposed method divides the search space to sub-regions and establishes exploration, information sharing, and exploitation search capabilities based on its novel search components. Further, fuzzy inference systems were employed to address parameterization and computational cost evaluation issues. It was found that the proposed algorithm can achieve low-cost, low-weight, and low CO2 emission RCC designs under nine seismic conditions in comparison with several classical and best-performing design optimizers., Comment: There are six figures, 51 pages, and 12 tables in the revised manuscript that has recently been resubmitted to the Journal of Computational Science

Graph Neural Networks (GNNs) are a family of graph networks inspired by mechanisms existing between nodes on a graph. In recent years there has been an increased interest in GNN and their derivatives, i.e., Graph Attention Networks (GAT), Graph Convolutional Networks (GCN), and Graph Recurrent Networks (GRN). An increase in their usability in computer vision is also observed. The number of GNN applications in this field continues to expand; it includes video analysis and understanding, action and behavior recognition, computational photography, image and video synthesis from zero or few shots, and many more. This contribution aims to collect papers published about GNN-based approaches towards computer vision. They are described and summarized from three perspectives. Firstly, we investigate the architectures of Graph Neural Networks and their derivatives used in this area to provide accurate and explainable recommendations for the ensuing investigations. As for the other aspect, we also present datasets used in these works. Finally, using graph analysis, we also examine relations between GNN-based studies in computer vision and potential sources of inspiration identified outside of this field., Comment: 2022 International Joint Conference on Neural Networks (IJCNN), 2022

Soil erosion is a significant threat to the environment and long-term land management around the world. Accelerated soil erosion by human activities inflicts extreme changes in terrestrial and aquatic ecosystems, which is not fully surveyed/predicted for the present and probable future at field-scales (30-m). Here, we estimate/predict soil erosion rates by water erosion, (sheet and rill erosion), using three alternative (2.6, 4.5, and 8.5) Shared Socioeconomic Pathway and Representative Concentration Pathway (SSP-RCP) scenarios across the contiguous United States. Field Scale Soil Erosion Model (FSSLM) estimations rely on a high resolution (30-m) G2 erosion model integrated by satellite- and imagery-based estimations of land use and land cover (LULC), gauge observations of long-term precipitation, and scenarios of the Coupled Model Intercomparison Project Phase 6 (CMIP6). The baseline model (2020) estimates soil erosion rates of 2.32 Mg ha 1 yr 1 with current agricultural conservation practices (CPs). Future scenarios with current CPs indicate an increase between 8% to 21% under different combinations of SSP-RCP scenarios of climate and LULC changes. The soil erosion forecast for 2050 suggests that all the climate and LULC scenarios indicate either an increase in extreme events or a change in the spatial location of extremes largely from the southern to the eastern and northeastern regions of the United States.

This presented study provides a novel analysis of scholarly literature on constraint handling techniques for single-objective and multi-objective population-based algorithms according to the most relevant journals, keywords, authors, and articles. The paper reviews the main ideas of the most state-of-the-art constraint handling techniques in multi-objective population-based optimization, and then the study addresses the bibliometric analysis in the field. The extracted papers include research articles, reviews, book/book chapters, and conference papers published between 2000 and 2020 for the analysis. The results indicate that the constraint handling techniques for multi-objective optimization have received much less attention compared with single-objective optimization. The most promising algorithms for such optimization were determined to be genetic algorithms, differential evolutionary algorithms, and particle swarm intelligence., Comment: 38 pages, 16643 words

To solve complex real-world problems, heuristics and concept-based approaches can be used in order to incorporate information into the problem. In this study, a concept-based approach called variable functioning Fx is introduced to reduce the optimization variables and narrow down the search space. In this method, the relationships among one or more subset of variables are defined with functions using information prior to optimization; thus, instead of modifying the variables in the search process, the function variables are optimized. By using problem structure analysis technique and engineering expert knowledge, the $Fx$ method is used to enhance the steel frame design optimization process as a complex real-world problem. The proposed approach is coupled with particle swarm optimization and differential evolution algorithms and used for three case studies. The algorithms are applied to optimize the case studies by considering the relationships among column cross-section areas. The results show that $Fx$ can significantly improve both the convergence rate and the final design of a frame structure, even if it is only used for seeding.

This manuscript introduces a new socio-inspired metaheuristic technique referred to as Leader-Advocate-Believer based optimization algorithm (LAB) for engineering and global optimization problems. The proposed algorithm is inspired by the AI-based competitive behaviour exhibited by the individuals in a group while simultaneously improving themselves and establishing a role (Leader, Advocate, Believer). LAB performance in computational time and function evaluations are benchmarked using other metaheuristic algorithms. Besides benchmark problems, the LAB algorithm was applied for solving challenging engineering problems, including abrasive water jet machining, electric discharge machining, micro-machining processes, and process parameter optimization for turning titanium alloy in a minimum quantity lubrication environment. The results were superior to the other algorithms compared such as Firefly Algorithm, Variations of Co-hort Intelligence, Genetic Algorithm, Simulated Annealing, Particle Swarm Optimisation, and Multi-Cohort Intelligence. The results from this study highlighted that the LAB outperforms the other algorithms in terms of function evaluations and computational time. The prominent features of the LAB algorithm along with its limitations are also discussed., Comment: NIL

Advancements in smart vehicle design have enabled the creation of Internet of Vehicle (IoV) technologies that can utilize the information provided by various sensors and wireless communication to perform complex functionality. Many of these functionalities rely on high computational power and low latency. Mobile Edge Computing (MEC) technologies have been proposed as a way to meet these requirements, as their proximity and decentralization provide unique benefits for networks like real-time communication, higher throughput, and flexibility. Diverse challenges to the process of offloading data in a MEC-enabled IoV network have emerged, such as offloading reliability in highly mobile environments, security for users within the same network, and energy management to keep users from being disincentivized to participate in the network. This article surveys research studies that use AI as part of the data offloading process, categorized based on four main issues: reliability, security, energy management, and service seller profit. Afterward, this article discusses challenges and future perspectives for IoV technologies.