Search

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence (AI), deep learning is widely used in various industries. At CRYPTO 2019, researchers used deep learning to analyze the block cipher for the first time and constructed a differential neural network distinguisher to meet a certain accuracy. In this paper, a mixture differential neural network distinguisher using ResNet is proposed to further improve the accuracy by exploring the mixture differential properties. Experiments are conducted on SIMON32/64, and the accuracy of the 8-round mixture differential neural network distinguisher is improved from 74.7% to 92.3%, compared with that of the previous differential neural network distinguisher. The prediction accuracy of the differential neural network distinguisher is susceptible to the choice of the specified input differentials, whereas the mixture differential neural network distinguisher is less affected by the input difference and has greater robustness. Furthermore, by combining the probabilistic expansion of rounds and the neutral bit, the obtained mixture differential neural network distinguisher is extended to 11 rounds, which can realize the 12-round actual key recovery attack on SIMON32/64. With an appropriate increase in the time complexity and data complexity, the key recovery accuracy of the mixture differential neural network distinguisher can be improved to 55% as compared to 52% of the differential neural network distinguisher. The mixture differential neural network distinguisher proposed in this paper can also be applied to other lightweight block ciphers. [ABSTRACT FROM AUTHOR]

With developments in global economic integration and the increase in future economic uncertainty, it is imperative to have the ability to predict future capital in relation to financial capital inflow and outflow predictions to ensure capital optimization is within a controllable range within the current macroeconomic environment and situation. This paper proposes an automated capital prediction strategy for the capital supply chain using time series analysis artificial intelligence methods. Firstly, to analyze the fluctuation and tail risk of the financial characteristics, the paper explores the financial characteristics for measuring the dynamic VaR from the perspectives of volatility, tail, and peak with the Bayesian peaks over threshold (POT) model. Following this, in order to make the modeling more refined, the forecast targets are split before modeling with seasonal Autoregressive Integrated Moving Average (ARIMA) models and Prophet models. Finally, the time series modeling of the wavelet Long Short-Term Memory (LSTM) model is carried out using a two-part analysis method to determine the linear separated wavelet and non-linear embedded wavelet parts to predict strong volatility in financial capital. Taking the user capital flow of the Yu'e Bao platform, the results prove the feasibility and prediction accuracy of the innovative model proposed. [ABSTRACT FROM AUTHOR]

This paper aims to discuss the implementation of data analysis and information management for elderly nursing care from a data-driven perspective. It addresses the current challenges of in-home caregivers, providing a basis for decision making in analyzing nursing service content and evaluating job performance. The characteristics of caregivers' activities were analyzed during the design of a wearable device-wearing scheme and a sensor data collection system. XGBoost, SVM, and Random Forest models were used in the experiments, with the Cuckoo search algorithm employed to optimize the XGBoost model parameters. Based on the control group experiment, it was confirmed that the XGBoost model, after adjusting the parameters using the Cuckoo search algorithm, exhibited better recognition performance than the SVM and RandomForest models, and the accuracy reached 0.9438. Wearable devices present high recognition accuracy in caregiver activity recognition research, which greatly improves the inspection of caregivers' work and further promotes the completion of services. This study actively explores the applications of information technology and artificial intelligence theory to address practical problems and effectively promote the digitalization and intelligent development of the elderly nursing care industry. [ABSTRACT FROM AUTHOR]

With the rapid development of artificial intelligence technology, data-driven advanced models have provided new ideas and means for airfoil aerodynamic optimization. As the advanced models update and iterate, many useful explorations and attempts have been made by researchers on the integrated application of artificial intelligence and airfoil aerodynamic optimization. In this paper, many critical aerodynamic optimization steps where data-driven advanced models are employed are reviewed. These steps include geometric parameterization, aerodynamic solving and performance evaluation, and model optimization. In this way, the improvements in the airfoil aerodynamic optimization area led by data-driven advanced models are introduced. These improvements involve more accurate global description of airfoil, faster prediction of aerodynamic performance, and more intelligent optimization modeling. Finally, the challenges and prospect of applying data-driven advanced models to aerodynamic optimization are discussed. [ABSTRACT FROM AUTHOR]

As a classical combinatorial optimization problem, the traveling salesman problem (TSP) has been extensively investigated in the fields of Artificial Intelligence and Operations Research. Due to being NP-complete, it is still rather challenging to solve both effectively and efficiently. Because of its high theoretical significance and wide practical applications, great effort has been undertaken to solve it from the point of view of intelligent search. In this paper, we propose a two-stage probe-based search optimization algorithm for solving both symmetric and asymmetric TSPs through the stages of route development and a self-escape mechanism. Specifically, in the first stage, a reasonable proportion threshold filter of potential basis probes or partial routes is set up at each step during the complete route development process. In this way, the poor basis probes with longer routes are filtered out automatically. Moreover, four local augmentation operators are further employed to improve these potential basis probes at each step. In the second stage, a self-escape mechanism or operation is further implemented on the obtained complete routes to prevent the probe-based search from being trapped in a locally optimal solution. The experimental results on a collection of benchmark TSP datasets demonstrate that our proposed algorithm is more effective than other state-of-the-art optimization algorithms. In fact, it achieves the best-known TSP benchmark solutions in many datasets, while, in certain cases, it even generates solutions that are better than the best-known TSP benchmark solutions. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of the Internet of Things, large-scale botnet attacks have occurred frequently and have become an important challenge to network security. As artificial intelligence technology continues to evolve, intelligent detection solutions for botnets are constantly emerging. Although graph neural networks are widely used for botnet detection, directly handling large-scale botnet data becomes inefficient and challenging as the number of infected hosts increases and the network scale expands. Especially in the process of node level learning and inference, a large number of nodes and edges need to be processed, leading to a significant increase in computational complexity and posing new challenges to network security. This paper presents a novel approach that can accurately identify diverse intricate botnet architectures in extensive IoT networks based on the aforementioned circumstance. By utilizing GraphSAINT to process large-scale IoT botnet graph data, efficient and unbiased subgraph sampling has been achieved. In addition, a solution with enhanced information representation capability has been developed based on the Graph Isomorphism Network (GIN) for botnet detection. Compared with the five currently popular graph neural network (GNN) models, our approach has been tested on C2, P2P, and Chord datasets, and higher accuracy has been achieved. [ABSTRACT FROM AUTHOR]

Network disintegration is a fundamental issue in the field of complex networks, with its core in identifying critical nodes or sets and removing them to weaken network functionality. The research on this problem has significant strategic value and has increasingly attracted attention, including in controlling the spread of diseases and dismantling terrorist organizations. In this paper, we focus on the problem of network disintegration with discrete entity resources from the attack view, that is, optimizing resource allocation to maximize the effect of network disintegration. Specifically, we model the network disintegration problem with limited entity resources as a nonlinear optimization problem and prove its NP-hardness. Then, we design a method based on deep reinforcement learning (DRL), Net-Cracker, which transforms the two-stage entity resource and network node selection task into a single-stage object selection problem. Extensive experiments demonstrate that compared with the benchmark algorithm, Net-Cracker can improve the solution quality by about 8∼62%, while enabling a 30-to-160-fold speed up. Net-Cracker also exhibits strong generalization ability and can find better results in a near real-time manner even when the network scale is much larger than that in training data. [ABSTRACT FROM AUTHOR]

Motorbikes are an integral part of transportation in emerging countries, but unfortunately, motorbike users are also one the most vulnerable road users (VRUs) and are engaged in a large number of yearly accidents. So, motorbike detection is very important for proper traffic surveillance, road safety, and security. Most of the work related to bike detection has been carried out to improve accuracy. If this task is not performed in real-time then it loses practical significance, but little to none has been reported for its real-time implementation. In this work, we have looked at multiple real-time deployable cost-efficient solutions for motorbike detection using various state-of-the-art embedded edge devices. This paper discusses an investigation of a proposed methodology on five different embedded devices that include Jetson Nano, Jetson TX2, Jetson Xavier, Intel Compute Stick, and Coral Dev Board. Running the highly compute-intensive object detection model on edge devices (in real-time) is made possible by optimization. As a result, we have achieved inference rates on different devices that are twice as high as GPUs, with only a marginal drop in accuracy. Secondly, the baseline accuracy of motorbike detection has been improved by developing a custom network based on YoloV5 by introducing sparsity and depth reduction. Dataset augmentation has been applied at both image and object levels to enhance robustness of detection. We have achieved 99% accuracy as compared to the previously reported 97% accuracy, with better FPS. Additionally, we have provided a performance comparison of motorbike detection on the different embedded edge devices, for practical implementation. [ABSTRACT FROM AUTHOR]

This paper studies the application of artificial intelligence to milling machines, focusing specifically on identifying the inputs (features) required for predicting surface roughness. Previous studies have extensively reviewed and presented useful features for surface roughness prediction. However, applying research findings to actual operational factories can be challenging due to the additional costs of sensor installations and the diverse environments present in each factory setting. To address these issues, in this paper, we introduced effective features for predicting surface roughness in situations where additional sensors are not installed in the existing environment. These features include feed per tooth,  F z ; material removal rate, Q; and the load information. These features are suitable for use in highly constrained environments where separate sensor installation is not required, making it possible to apply the research findings in various factory environments. Additionally, to efficiently select the optimal subset for surface roughness prediction among subsets formed by available features, we apply causality to the feature selection method, proposing an approach called causality-driven efficient feature selection. The experimental results demonstrate that the features introduced in this paper are quite suitable for predicting surface roughness and that the proposed feature selection approach is more effective and efficient compared to existing selection methods. [ABSTRACT FROM AUTHOR]

Employee attrition and high turnover have become critical challenges faced by various sectors in today's competitive job market. In response to these pressing issues, organizations are increasingly turning to artificial intelligence (AI) to predict employee attrition and implement effective retention strategies. This paper delves into the application of explainable AI (XAI) in identifying potential employee turnover and devising data-driven solutions to address this complex problem. The first part of the paper examines the escalating problem of employee attrition in specific industries, analyzing the detrimental impact on organizational productivity, morale, and financial stability. The second section focuses on the utilization of AI techniques to predict employee attrition. AI can analyze historical data, employee behavior, and various external factors to forecast the likelihood of an employee leaving an organization. By identifying early warning signs, businesses can intervene proactively and implement personalized retention efforts. The third part introduces explainable AI techniques which enhance the transparency and interpretability of AI models. By incorporating these methods into AI-based predictive systems, organizations gain deeper insights into the factors driving employee turnover. This interpretability enables human resources (HR) professionals and decision-makers to understand the model's predictions and facilitates the development of targeted retention and recruitment strategies that align with individual employee needs. [ABSTRACT FROM AUTHOR]

As a new abstract computational model in evolutionary transfer optimization (ETO), single-objective to multi-objective optimization (SMO) is conducted at the macroscopic level rather than the intermediate level for specific algorithms or the microscopic level for specific operators; this method aims to develop systems with a profound grasp of evolutionary dynamic and learning mechanism similar to human intelligence via a "decomposition" style (in the abstract of the well-known "Transformer" article "Attention is All You Need", they use "attention" instead). To the best of our knowledge, it is the first work of SMO for discrete cases because we extend our conference paper and inherit its originality status. In this paper, by implementing the abstract SMO in specialized memetic algorithms, key knowledge from single-objective problems/tasks to the multi-objective core problem/task can be transferred or "gathered" for permutation flow shop scheduling problems, which will reduce the notorious complexity in combinatorial spaces for multi-objective settings in a straight method; this is because single-objective tasks are easier to complete than their multi-objective versions. Extensive experimental studies and theoretical results on benchmarks (1) emphasize our decomposition root in mathematical programming, such as Lagrangian relaxation and column generation; (2) provide two "where to go" strategies for both SMO and ETO; and (3) contribute to the mission of building safe and beneficial artificial general intelligence for manufacturing via evolutionary computation. [ABSTRACT FROM AUTHOR]

With the continuous development of artificial intelligence technology and the exponential growth in the number of images, image detection and recognition technology is becoming more widely used. Image knowledge management is extremely urgent. The data source of a knowledge graph is not only the text and structured data but also the visual or auditory data such as images, video, and audio. How to use multimodal information to build an information management platform is a difficult problem. In this paper, a method is proposed to construct the result of image recognition as a knowledge graph. First of all, based on the improvement in the BlendMASK algorithm, the hollow convolution kernel is added. Secondly, the effect of image recognition and the relationships between all kinds of information are analyzed. Finally, the image knowledge graph is constructed by using the relationship between the image entities. The contributions of this paper are as follows. (1) The hollow convolution kernel is added to reduce the loss from extracting feature information from high-level feature images. (2) In this paper, a method is proposed to determine the relationship between entities by dividing the recognition results of entities in an image with a threshold, which makes it possible for the relationships between images to be interconnected. The experimental results show that this method improves the accuracy and F1 value of the image recognition algorithm. At the same time, the method achieves integrity in the construction of a multimodal knowledge graph. [ABSTRACT FROM AUTHOR]

With the expansion of the Internet of Things (IoT) and artificial intelligence (AI) technologies, multilingual scenarios are gradually increasing, and applications based on multilingual resources are also on the rise. In this process, apart from the need for the construction of multilingual resources, privacy protection issues like data privacy leakage are increasingly highlighted. Comparable corpus is important in multilingual language information processing in IoT. However, the multilingual comparable corpus concerning privacy preserving is rare, so there is an urgent need to construct a multilingual corpus resource. This paper proposes a method for constructing a privacy-preserving multilingual comparable corpus, taking Chinese–Uighur–Tibetan IoT based news as an example, and mapping the different language texts to a unified language vector space to avoid sensitive information, then calculates the similarity between different language texts and serves as a comparability index to construct comparable relations. Through the decision-making mechanism of minimizing the impossibility, it can identify a comparable corpus pair of multilingual texts based on chapter size to realize the construction of a privacy-preserving Chinese–Uighur–Tibetan comparable corpus (CUTCC). Evaluation experiments demonstrate the effectiveness of our proposed provable method, which outperforms in accuracy rate by 77%, recall rate by 34% and F value by 47.17%. The CUTCC provides valuable privacy-preserving data resources support and language service for multilingual situations in IoT. [ABSTRACT FROM AUTHOR]

Due to its simplicity, accuracy, and adaptability, Crimp Force Monitoring (CFM) has long been the standard for fault detection in wiring harness manufacturing. However, it necessitates frequent reconfigurations based on the variability in materials, dependency on operator skill, and high costs of implementation, and thus reconfiguration presents significant challenges. To solve these problems, this paper introduces a fault detection system that employs an Artificial Intelligence (AI) classification model to enhance the performance and cost-efficiency of the quality control process of wiring harness manufacturing. Since there are no labeled data to train the classification model at the onset of manufacturing, a small number of normal data from each production run are manually extracted to train the model. To address the constraint of the limited available data, the system generates synthetic data from normal data, simulating potential defects by using Regional Selective Data Scaling (RSDS). This innovative method performs upscaling or downscaling on specific regions of the original data to produce synthetic abnormal data, which enables the fault detection system to efficiently train its classification model with a dataset consisting solely of normal operation data. [ABSTRACT FROM AUTHOR]

Language barriers and the communication difficulties of individuals with developmental disabilities are two major causes of communication problems that societies worldwide encounter. A particularly challenging group is hearing-impaired people who have difficulties with communication, reading, writing, learning, and social interactions, which have a substantial impact on their quality of life. This article focuses on detailing a Serbian Sign Language alphabet database and the method for creating it in order to provide a foundation for answering the various societal challenges of persons who use the Serbian language. In front of a computer camera, 41 people performed Serbian Sign Language sign movements that replicated the Serbian alphabet for this study's aims. Hand and body key points were identified using the recorded video clips, and the numerical values of the identified key points were then stored in a database for further processing. In total, 8.346 video clips of people making recognized hand gestures were gathered, processed, classed, and archived. This paper provides a thorough technique that may be applied to comparable tasks and details the process of constructing a dataset based on Serbian Sign Language alphabet signs. This dataset was created using custom-made Python 3.11 software. Data regarding dynamic video clips that capture entire subject movement were incorporated into this dataset to fill in the gaps in other similar efforts based on static photographs. Thus, the purpose of this investigation is to employ innovative technology to support the community of hearing-impaired people in areas such as general inclusion, education, communication, and empowerment. [ABSTRACT FROM AUTHOR]

In the evolving landscape of targeted marketing, integrating deep learning (DL) and explainable AI (XAI) offers a promising avenue for enhanced customer segmentation. This paper introduces a groundbreaking approach, DeepLimeSeg, which synergizes DL methodologies with Lime-based Explainability to segment customers effectively. The approach employs a comprehensive mathematical model to harness demographic data, behavioral patterns, and purchase histories, categorizing customers into distinct clusters aligned with their preferences and needs. A pivotal component of this research is the mathematical underpinning of the DeepLimeSeg approach. The Lime-based Explainability module ensures that the segmentation results are accurate and interpretable. The mathematical rigor facilitates businesses tailoring their marketing strategies with precision, optimizing sales outcomes. To validate the efficacy of DeepLimeSeg, we employed two real-world datasets: Mall-Customer Segmentation Data and an E-Commerce dataset. A comparative analysis between DeepLimeSeg and the traditional Recency, Frequency, and Monetary (RFM) analysis is presented. The RFM analysis, grounded in its mathematical modeling, segments customers based on purchase recency, frequency, and monetary value. Our preprocessing involved computing RFM scores for each customer, followed by K-means clustering to delineate customer segments. Empirical results underscored the superiority of DeepLimeSeg over other models in terms of MSE, MAE, and R 2 metrics. Specifically, the model registered an MSE of 0.9412, indicative of its robust predictive accuracy concerning the spending score. The MAE value stood at 0.9874, signifying minimal deviation from actual values. This paper accentuates the importance of mathematical modeling in enhancing customer segmentation. The DeepLimeSeg approach, with its mathematical foundation and explainable AI integration, paves the way for businesses to make informed, data-driven marketing decisions. [ABSTRACT FROM AUTHOR]

With technological transformations such as big data, blockchain, artificial intelligence, and cloud computing, digital techniques are infiltrating the field of finance. Digital finance (DF) is a resource-saving and environmentally friendly innovative financial service. It shows great green attributes and can drive the flow of financial resources towards environmentally-friendly enterprises, thereby promoting green low-carbon circular development (GLCD). However, few studies have explored the coupling mechanism between DF and GLCD. To fill this gap, this paper explores the effect of DF on GLCD, and established a mediating effect model to investigate the mechanism of DF in promoting GLCD. Additionally, this paper established a random forest model and a CatBoost model based on machine learning to examine the relative importance of DF and the factors affecting GLCD. The results show that DF has significant positive effects on GLCD, and technological innovation plays a key role in the effect of DF on GLCD; meanwhile, the effect of DF on GLCD shows nonlinear features with an increasing "marginal effect"; moreover, both DF and conventional factors have significant impacts on GLCD. Our study highlights the effect of DF on GLCD and underscores the importance of developing policies for DF and GLCD. This study provides an empirical basis and path reference for DF to achieve "carbon peak, carbon neutralization" in China. [ABSTRACT FROM AUTHOR]

Digital twin is the digital representation of an entity, and it drives Industry 4.0. This paper presents a bibliometric analysis of digital twin in the supply chain to help researchers, industry practitioners, and academics to understand the trend, development, and focus of the areas of digital twin in the supply chain. This paper found several key clusters of research, including the designing of a digital twin model, integration of a digital twin model, application of digital twin in quality control, and digital twin in digitalization. In the embryonic stage of research, digital twin was tested in the production line with limited optimization. In the development stage, the importance of digital twin in Industry 4.0 was observed, as big data, machine learning, Industrial Internet of Things, blockchain, edge computing, and cloud-based systems complemented digital twin models. Digital twin was applied to improve sustainability in manufacturing and production logistics. In the current prosperity stage with high annual publications, the recent trends of this topic focus on the integration of deep learning, data models, and artificial intelligence for digitalization. This bibliometric analysis also found that the COVID-19 pandemic drove the start of the prosperity stage of digital twin research in the supply chain. Researchers in this field are slowly moving towards applying digital twin for human-centric systems and mass personalization to prepare to transit to Industry 5.0. [ABSTRACT FROM AUTHOR]

The use of intelligent systems in clinical diagnostics has evolved, integrating statistical learning and knowledge-based representation models. Two recent works propose the identification of risk factors for the diagnosis of obstructive sleep apnea (OSA). The first uses statistical learning to identify indicators associated with different levels of the apnea-hypopnea index (AHI). The second paper combines statistical and symbolic inference approaches to obtain risk indicators (Statistical Risk and Symbolic Risk) for a given AHI level. Based on this, in this paper we propose a new intelligent system that considers different AHI levels and generates risk pairs for each level. A learning-based model generates Statistical Risks based on objective patient data, while a cascade of fuzzy expert systems determines a Symbolic Risk using symptom data from patient interviews. The aggregation of risk pairs at each level involves a fuzzy expert system with automatically generated fuzzy rules using the Wang-Mendel algorithm. This aggregation produces an Apnea Risk indicator for each AHI level, allowing discrimination between OSA and non-OSA cases, along with appropriate recommendations. This approach improves variability, usefulness, and interpretability, increasing the reliability of the system. Initial tests on data from 4400 patients yielded AUC values of 0.74–0.88, demonstrating the potential benefits of the proposed intelligent system architecture. [ABSTRACT FROM AUTHOR]

This study aims to understand the development trends and research structure of articles on artificial intelligence (AI) and information processing in the past 10 years. In particular, this study analyzed 13,294 papers published from 2012 to 2021 in the Web of Science, used the bibliometric analysis method to visualize the data of the papers, and drew a scientific knowledge map. By exploring the development of mainstream journals, author and country rankings, keyword evolution, and research field rankings in the past 10 years, this study uncovered key trends affecting AI progress and information processing that provide insights and serve as an important reference for future AI research and information processing. The results revealed a gradual increase in publications over the past decade, with explosive growth after 2020. The most prolific researchers in this field were Xu, Z.S.; Pedrycz, W.; Herrera-Viedma, E.; the major contributing countries were China, the USA, and Spain. In the AI and information processing research, keywords including "Deep learning", "Machine learning", and "Feature extraction" are components that play a crucial role. Additionally, the most representative research areas were "Engineering", "Operations Research and Management Science", and "Automation Control Systems". Overall, this study used bibliometric analysis to provide an overview of the latest trends in artificial intelligence and information processing. Although AI and information processing have been applied to various research areas, many other sub-topics can be further applied. Based on the findings, this study presented research insights and proposed suggestions for future research directions on AI and information processing. [ABSTRACT FROM AUTHOR]

Applied computing and artificial intelligence methods have been attracting growing interest in recent years due to their effectiveness in solving technical problems. Hao et al. [[14]] present an unsupervised fault diagnosis methodology to leverage the generated MPCs of different working conditions to diagnose the actual unlabeled MPCs. The paper by Ainapure et al. [[17]] proposes a new cross-domain fault diagnosis method with enhanced robustness. The paper by Saeed et al. [[1]] proposes an approach to building an AutoML data-dependent CNN model (DeepPCANet) customized for DR screening automatically. [Extracted from the article]

Deep learning, which is a subfield of machine learning, has opened a new era for the development of neural networks. The auto-encoder is a key component of deep structure, which can be used to realize transfer learning and plays an important role in both unsupervised learning and non-linear feature extraction. By highlighting the contributions and challenges of recent research papers, this work aims to review state-of-the-art auto-encoder algorithms. Firstly, we introduce the basic auto-encoder as well as its basic concept and structure. Secondly, we present a comprehensive summarization of different variants of the auto-encoder. Thirdly, we analyze and study auto-encoders from three different perspectives. We also discuss the relationships between auto-encoders, shallow models and other deep learning models. The auto-encoder and its variants have successfully been applied in a wide range of fields, such as pattern recognition, computer vision, data generation, recommender systems, etc. Then, we focus on the available toolkits for auto-encoders. Finally, this paper summarizes the future trends and challenges in designing and training auto-encoders. We hope that this survey will provide a good reference when using and designing AE models. [ABSTRACT FROM AUTHOR]

Currently, digitalization and digital transformation are actively expanding into various areas of human activity, and researchers are identifying urgent problems and offering new solutions regarding digital environments in industry [[1]], economics [[3]], medicine [[5]], ecology [[7]], education [[9]], etc. Conclusions The purpose of this Special Issue was to attract high-quality new papers in the field of applied and computational mathematics for digital environments, offering original solutions to various problems that are relevant and in demand in various fields of human activity. 10.3390/math10224297 21 Demidova L.A. A Novel Approach to Decision-Making on Diagnosing Oncological Diseases Using Machine Learning Classifiers Based on Datasets Combining Known and/or New Generated Features of a Different Nature. I hope that these selected research papers are recognized as important and meaningful by the international scientific community and can form the basis for further research in the field of applied and computational mathematics for digital environments, solving complex problems in various disciplines and application areas. [Extracted from the article]

With the rapid growth of the software industry, the software supply chain (SSC) has become the most intricate system in the complete software life cycle, and the security threat situation is becoming increasingly severe. For the description of the SSC, the relevant research mainly focuses on the perspective of developers, lacking a comprehensive understanding of the SSC. This paper proposes a chain portrait framework of the SSC based on a resource perspective, which comprehensively depicts the threat model and threat surface indicator system of the SSC. The portrait model includes an SSC threat model and an SSC threat indicator matrix. The threat model has 3 levels and 32 dimensions and is based on a generative artificial intelligence model. The threat indicator matrix is constructed using the Attack Net model comprising 14-dimensional attack strategies and 113-dimensional attack techniques. The proposed portrait model's effectiveness is verified through existing SSC security events, domain experts, and event visualization based on security analysis models. [ABSTRACT FROM AUTHOR]

The study of intelligent game-playing has gained tremendous attention in the past few decades. The recent development of artificial intelligence (AI) players (e.g., the Go player AlphaGo) has made intelligent game-playing even more prominent in both academia and industry. The performance of state-of-the-art AI players benefits greatly from machine learning techniques, based on which, players can make estimations and decisions even without understanding the games. Although AI machines show great superiority over humans in terms of data processing and complex computation, there remains a vast distance between artificial intelligence and human intelligence with respect to the abilities of context understanding and reasoning. In this paper, we explore the theoretical foundation of intelligent game-playing from a logical perspective. The proposed logic, by considering the computational limits in practical game-playing, drops the ideal assumptions in existing logics for the classical game model. We show that under logical framework, the basis of decision-making for agents in game scenarios can be formally represented and analyzed. Moreover, by characterizing the solutions of games, this logic is able to formalize players' rational decision-making during practical game-playing. [ABSTRACT FROM AUTHOR]

Image captioning has become a hot topic in artificial intelligence research and sits at the intersection of computer vision and natural language processing. Most recent imaging captioning models have adopted an "encoder + decoder" architecture, in which the encoder is employed generally to extract the visual feature, while the decoder generates the descriptive sentence word by word. However, the visual features need to be flattened into sequence form before being forwarded to the decoder, and this results in the loss of the 2D spatial position information of the image. This limitation is particularly pronounced in the Transformer architecture since it is inherently not position-aware. Therefore, in this paper, we propose a simple coordinate-based spatial position encoding method (CSPE) to remedy this deficiency. CSPE firstly creates the 2D position coordinates for each feature pixel, and then encodes them by row and by column separately via trainable or hard encoding, effectively strengthening the position representation of visual features and enriching the generated description sentences. In addition, in order to reduce the time cost, we also explore a diagonal-based spatial position encoding (DSPE) approach. Compared with CSPE, DSPE is slightly inferior in performance but has a faster calculation speed. Extensive experiments on the MS COCO 2014 dataset demonstrate that CSPE and DSPE can significantly enhance the spatial position representation of visual features. CSPE, in particular, demonstrates BLEU-4 and CIDEr metrics improved by 1.6% and 5.7%, respectively, compared with a baseline model without sequence-based position encoding, and also outperforms current sequence-based position encoding approaches by a significant margin. In addition, the robustness and plug-and-play ability of the proposed method are validated based on a medical captioning generation model. [ABSTRACT FROM AUTHOR]

This paper reports the filamentation of hollow Gaussian beams of the first, second, third, and fourth orders during propagation in a cubic and quintic nonlinear medium. Due to spatial modulation instability, the hollow Gaussian beams split to form either co-centric circular filaments or ultrashort pulses. It is found that the properties of the nonlinear medium used for propagation have a strong influence on certain characteristics of the formed filaments, such as peak intensity and pulse width. This correlation between the system parameters of the medium and filament characteristics represents a method for calculating the system parameters of the medium. This investigation can be helpful in the development of a hollow Gaussian beam-based artificial intelligence system that can be used to measure the system parameters of the studied nonlinear medium. [ABSTRACT FROM AUTHOR]

The development of artificial intelligence systems assumes that a machine can independently generate an algorithm of actions or a control system to solve the tasks. To do this, the machine must have a formal description of the problem and possess computational methods for solving it. This article deals with the problem of optimal control, which is the main task in the development of control systems, insofar as all systems being developed must be optimal from the point of view of a certain criterion. However, there are certain difficulties in implementing the resulting optimal control modes. This paper considers an extended formulation of the optimal control problem, which implies the creation of such systems that would have the necessary properties for its practical implementation. To solve it, an adaptive synthesized optimal control approach based on the use of numerical methods of machine learning is proposed. Such control moves the control object, optimally changing the position of the stable equilibrium point in the presence of some initial position uncertainty. As a result, from all possible synthesized controls, one is chosen that is less sensitive to changes in the initial state. As an example, the optimal control problem of a quadcopter with complex phase constraints is considered. To solve this problem, according to the proposed approach, the control synthesis problem is firstly solved to obtain a stable equilibrium point in the state space using a machine learning method of symbolic regression. After that, optimal positions of the stable equilibrium point are searched using a particle swarm optimization algorithm using the source functional from the initial optimal control problem statement. It is shown that such an approach allows for generating the control system automatically by computer, basing this on the formal statement of the problem and then directly implementing it onboard as far as the stabilization system has already been introduced. [ABSTRACT FROM AUTHOR]

In recent years, the latest maintenance modelling techniques that adopt the data-based method, such as machine learning (ML), have brought about a broad range of useful applications. One of the major challenges in the automotive industry is the early detection of component failure for quick response, proper action, and minimizing maintenance costs. A vital component of an automobile system is an air pressure system (APS). Failure of APS without adequate and quick responses may lead to high maintenance costs, loss of lives, and component damages. This paper addresses classification problem where we detect whether a fault does or does not belong to APS. If a failure occurs in APS, it is classified as positive class; otherwise, it is classified as negative class. Hence, in this paper, we propose broad embedded logistic regression (BELR). The proposed BELR is applied to predict APS failure. It combines a broad learning system (BLS) and logistic regression (LogR) classifier as a fusion model. The proposed approach capitalizes on the strength of BLS and LogR for a better APS failure prediction. Additionally, we employ the BLS's feature-mapped nodes for extracting features from the input data. Additionally, we use the enhancement nodes of the BLS to enhance the features from feature-mapped nodes. Hence, we have features that can assist LogR for better classification performances, even when the data is skewed to the positive class or negative class. Furthermore, to prevent the curse of dimensionality, a common problem with high-dimensional data sets, we utilize principal component analysis (PCA) to reduce the data dimension. We validate the proposed BELR using the APS data set and compare the results with the other robust machine learning classifiers. The commonly used evaluation metrics, namely Recall, Precision, an F1-score, to evaluate the model performance. From the results, we validate that performance of the proposed BELR. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a key enabler technology that recently received significant attention from the scientific community across the globe. It helps transform everyone's life by connecting physical and virtual devices with each other to offer staggering benefits, such as automation and control, higher productivity, real-time information access, and improved efficiency. However, IoT devices and their accumulated data are susceptible to various security threats and vulnerabilities, such as data integrity, denial-of-service, interception, and information disclosure attacks. In recent years, the IoT with blockchain technology has seen rapid growth, where smart contracts play an essential role in validating IoT data. However, these smart contracts can be vulnerable and degrade the performance of IoT applications. Hence, besides offering indispensable features to ease human lives, there is also a need to confront IoT environment security attacks, especially data integrity attacks. Toward this aim, this paper proposed an artificial intelligence-based system model with a dual objective. It first detects the malicious user trying to compromise the IoT environment using a binary classification problem. Further, blockchain technology is utilized to offer tamper-proof storage to store non-malicious IoT data. However, a malicious user can exploit the blockchain-based smart contract to deteriorate the performance IoT environment. For that, this paper utilizes deep learning algorithms to classify malicious and non-malicious smart contracts. The proposed system model offers an end-to-end security pipeline through which the IoT data are disseminated to the recipient. Lastly, the proposed system model is evaluated by considering different assessment measures that comprise the training accuracy, training loss, classification measures (precision, recall, and F1 score), and receiver operating characteristic (ROC) curve. [ABSTRACT FROM AUTHOR]

This paper discusses using unsupervised learning in classifying particle-like dispersion. The problem is relevant to various applications, including virus transmission and atmospheric pollution. The Reduce Uncertainty and Increase Confidence (RUN-ICON) algorithm of unsupervised learning is applied to particle spread classification. The algorithm classifies the particles with higher confidence and lower uncertainty than other algorithms. The algorithm's efficiency remains high also when noise is added to the system. Applying unsupervised learning in conjunction with the RUN-ICON algorithm provides a tool for studying particles' dynamics and their impact on air quality, health, and climate. [ABSTRACT FROM AUTHOR]

In the increasingly complex domain of Korean voice phishing attacks, advanced detection techniques are paramount. Traditional methods have achieved some degree of success. However, they often fail to detect sophisticated voice phishing attacks, highlighting an urgent need for enhanced approaches to improve detection performance. Addressing this, we have designed and implemented a novel artificial neural network (ANN) architecture that successfully combines data-centric and model-centric AI methodologies for detecting Korean voice phishing attacks. This paper presents our unique hybrid architecture, consisting of a 1-dimensional Convolutional Neural Network (1D CNN), a Bidirectional Long Short-Term Memory (BiLSTM), and Hierarchical Attention Networks (HANs). Our evaluations using the real-world KorCCVi v2 dataset demonstrate that the proposed architecture effectively leverages the strengths of CNN and BiLSTM to extract and learn contextually rich features from word embedding vectors. Additionally, implementing word and sentence attention mechanisms from HANs enhances the model's focus on crucial features, considerably improving detection performance. Achieving an accuracy score of 99.32% and an F1 score of 99.31%, our model surpasses all baseline models we trained, outperforms several existing solutions, and maintains comparable performance to others. The findings of this study underscore the potential of hybrid neural network architectures in improving voice phishing detection in the Korean language and pave the way for future research. This could involve refining and expanding upon this model to tackle increasingly sophisticated voice phishing strategies effectively or utilizing larger datasets. [ABSTRACT FROM AUTHOR]

Success in student learning is the primary aim of the educational system. Artificial intelligence utilizes data and machine learning to achieve excellence in student learning. In this paper, we exploit several machine learning techniques to estimate early student performance. Two main simulations are used for the evaluation. The first simulation used the Traditional Machine Learning Classifiers (TMLCs) applied to the House dataset, and they are Gaussian Naïve Bayes (GNB), Support Vector Machine (SVM), Decision Tree (DT), Multi-Layer Perceptron (MLP), Random Forest (RF), Linear Discriminant Analysis (LDA), and Quadratic Discriminant Analysis (QDA). The best results were achieved with the MLP classifier with a division of 80% training and 20% testing, with an accuracy of 88.89%. The fusion of these seven classifiers was also applied and the highest result was equal to the MLP. Moreover, in the second simulation, the Convolutional Neural Network (CNN) was utilized and evaluated on five main datasets, namely, House, Western Ontario University (WOU), Experience Application Programming Interface (XAPI), University of California-Irvine (UCI), and Analytics Vidhya (AV). The UCI dataset was subdivided into three datasets, namely, UCI-Math, UCI-Por, and UCI-Fused. Moreover, the AV dataset has three targets which are Math, Reading, and Writing. The best accuracy results were achieved at 97.5%, 99.55%, 98.57%, 99.28%, 99.40%, 99.67%, 92.93%, 96.99%, and 96.84% for the House, WOU, XAPI, UCI-Math, UCI-Por, UCI-Fused, AV-Math, AV-Reading, and AV-Writing datasets, respectively, under the same protocol of evaluation. The system demonstrates that the proposed CNN-based method surpasses all seven conventional methods and other state-of-the-art-work. [ABSTRACT FROM AUTHOR]

In this paper, a mathematical model is presented to identify the direct dynamic coefficients (kxx, kzz, cxx, czz) of a pressurized bearing in a rotor-bearing system. The presented mathematical model for online identification is the result of the application of the algebraic identification approach to a two-degree-of-freedom rotor-bearing model. The proposed identification model requires only the vibration response as the input data. The performance of the model was assessed by theoretically and experimentally testing the proposed identifier at different shaft frequencies and, for the experimental test, a pressurized bearing that has hydrodynamic and hydrostatic characteristics at a support pressure of 10 psi was considered. The working fluid is Chevron GST 32 oil. The results show negligible differences between the vibration response of the experimental rotor and those obtained numerically using the identified direct dynamic coefficients of the pressurized bearing. In addition, it is observed that the algebraic identifier determines the identified parameters in a time less than 0.2 s. The proposed identifier can be used in other types of bearings, which is a great advantage over other identifiers. [ABSTRACT FROM AUTHOR]

Machine learning, a subfield of artificial intelligence, emphasizes the creation of algorithms capable of learning from data and generating predictions. However, in actuarial science, the interpretability of these models often presents challenges, raising concerns about their accuracy and reliability. Explainable artificial intelligence (XAI) has emerged to address these issues by facilitating the development of accurate and comprehensible models. This paper conducts a comparative analysis of various XAI approaches for tackling distinct data-driven insurance problems. The machine learning methods are evaluated based on their accuracy, employing the mean absolute error for regression problems and the accuracy metric for classification problems. Moreover, the interpretability of these methods is assessed through quantitative and qualitative measures of the explanations offered by each explainability technique. The findings reveal that the performance of different XAI methods varies depending on the particular insurance problem at hand. Our research underscores the significance of considering accuracy and interpretability when selecting a machine-learning approach for resolving data-driven insurance challenges. By developing accurate and comprehensible models, we can enhance the transparency and trustworthiness of the predictions generated by these models. [ABSTRACT FROM AUTHOR]

This paper presents the development of a novel algorithm for unsupervised learning called RUN-ICON (Reduce UNcertainty and Increase CONfidence). The primary objective of the algorithm is to enhance the reliability and confidence of unsupervised clustering. RUN-ICON leverages the K-means++ method to identify the most frequently occurring dominant centres through multiple repetitions. It distinguishes itself from existing K-means variants by introducing novel metrics, such as the Clustering Dominance Index and Uncertainty, instead of relying solely on the Sum of Squared Errors, for identifying the most dominant clusters. The algorithm exhibits notable characteristics such as robustness, high-quality clustering, automation, and flexibility. Extensive testing on diverse data sets with varying characteristics demonstrates its capability to determine the optimal number of clusters under different scenarios. The algorithm will soon be deployed in real-world scenarios, where it will undergo rigorous testing against data sets based on measurements and simulations, further proving its effectiveness. [ABSTRACT FROM AUTHOR]

The viral spread of online content can lead to unexpected consequences such as extreme opinions about a brand or consumers' enthusiasm for a product. This makes the prediction of viral content's future popularity an important problem, especially for digital marketers, as well as for managers of social platforms. It is not surprising that conventional methods, which heavily rely on either hand-crafted features or unrealistic assumptions, are insufficient in dealing with this challenging problem. Even state-of-art graph-based approaches are either inefficient to work with large-scale cascades or unable to explain what spread mechanisms are learned by the model. This paper presents a temporal-spatial cascade convolutional learning framework called ViralGCN, not only to address the challenges of existing approaches but also to try to provide some insights into actual mechanisms of viral spread from the perspective of artificial intelligence. We conduct experiments on the real-world dataset (i.e., to predict the retweet popularity of micro-blogs on Weibo). Compared to the existing approaches, ViralGCN possesses the following advantages: the flexible size of the input cascade graph, a coherent method for processing both structural and temporal information, and an intuitive and interpretable deep learning architecture. Moreover, the exploration of the learned features also provides valuable clues for managers to understand the elusive mechanisms of viral spread as well as to devise appropriate strategies at early stages. By using the visualization method, our approach finds that both broadcast and structural virality contribute to online content going viral; the cascade with a gradual descent or ascent-then-descent evolving pattern at the early stage is more likely to gain significant eventual popularity, and even the timing of users participating in the cascade has an effect on future popularity growth. [ABSTRACT FROM AUTHOR]

Artificial intelligence plays a significant role in traffic-accident detection. Traffic accidents involve a cascade of inadvertent events, making traditional detection approaches challenging. For instance, Convolutional Neural Network (CNN)-based approaches cannot analyze temporal relationships among objects, and Recurrent Neural Network (RNN)-based approaches suffer from low processing speeds and cannot detect traffic accidents simultaneously across multiple frames. Furthermore, these networks dismiss background interference in input video frames. This paper proposes a framework that begins by subtracting the background based on You Only Look Once (YOLOv5), which adaptively reduces background interference when detecting objects. Subsequently, the CNN encoder and Transformer decoder are combined into an end-to-end model to extract the spatial and temporal features between different time points, allowing for a parallel analysis between input video frames. The proposed framework was evaluated on the Car Crash Dataset through a series of comparison and ablation experiments. Our framework was benchmarked against three accident-detection models to evaluate its effectiveness, and the proposed framework demonstrated a superior accuracy of approximately 96%. The results of the ablation experiments indicate that when background subtraction was not incorporated into the proposed framework, the values of all evaluation indicators decreased by approximately 3%. [ABSTRACT FROM AUTHOR]

In recent years, churn rates in industries such as finance have increased, and the cost of acquiring new users is more than five times the cost of retaining existing users. To improve the intelligent prediction accuracy of customer churn rate, artificial intelligence is gradually used. In this paper, the bidirectional long short-term memory convolutional neural network (BiLSTM-CNN) model is integrated with recurrent neural networks (RNNs) and convolutional neural networks (CNNs) in parallel, which well solves the defective problem that RNNs and CNNs run separately, and it also solves the problem that the output results of a long short-term memory network (LSTM) layer in a densely-connected LSTM-CNN (DLCNN) model will ignore some local information when input to the convolutional layer. In order to explore whether the attention bidirectional long short-term memory convolutional neural network (AttnBLSTM-CNN) model can perform better than BiLSTM-CNN, this paper uses bank data to compare the two models. The experimental results show that the accuracy of the AttnBiLSTM-CNN model is improved by 0.2%, the churn rate is improved by 1.3%, the F1 value is improved by 0.0102, and the AUC value is improved by 0.0103 compared with the BLSTM model. Therefore, introducing the attention mechanism into the BiLSTM-CNN model can further improve the performance of the model. The improvement of the accuracy of the user churn prediction model can warn of the possibility of user churn in advance and take effective measures in advance to prevent user churn and improve the core competitiveness of financial institutions. [ABSTRACT FROM AUTHOR]

Our research objective is to improve the Huffman coding efficiency by adjusting the data using a Poisson distribution, which avoids the undefined entropies too. The scientific value added by our paper consists in the fact of minimizing the average length of the code words, which is greater in the absence of applying the Poisson distribution. Huffman Coding is an error-free compression method, designed to remove the coding redundancy, by yielding the smallest number of code symbols per source symbol, which in practice can be represented by the intensity of an image or the output of a mapping operation. We shall use the images from the PASCAL Visual Object Classes (VOC) to evaluate our methods. In our work we use 10,102 randomly chosen images, such that half of them are for training, while the other half is for testing. The VOC data sets display significant variability regarding object size, orientation, pose, illumination, position and occlusion. The data sets are composed by 20 object classes, respectively: aeroplane, bicycle, bird, boat, bottle, bus, car, motorbike, train, sofa, table, chair, tv/monitor, potted plant, person, cat, cow, dog, horse and sheep. The descriptors of different objects can be compared to give a measurement of their similarity. Image similarity is an important concept in many applications. This paper is focused on the measure of similarity in the computer science domain, more specifically information retrieval and data mining. Our approach uses 64 descriptors for each image belonging to the training and test set, therefore the number of symbols is 64. The data of our information source are different from a finite memory source (Markov), where its output depends on a finite number of previous outputs. When dealing with large volumes of data, an effective approach to increase the Information Retrieval speed is based on using Neural Networks as an artificial intelligent technique. [ABSTRACT FROM AUTHOR]

With increased network downsizing and cost minimization in deployment of neural network (NN) models, the utilization of edge computing takes a significant place in modern artificial intelligence today. To bridge the memory constraints of less-capable edge systems, a plethora of quantizer models and quantization techniques are proposed for NN compression with the goal of enabling the fitting of the quantized NN (QNN) on the edge device and guaranteeing a high extent of accuracy preservation. NN compression by means of post-training quantization has attracted a lot of research attention, where the efficiency of uniform quantizers (UQs) has been promoted and heavily exploited. In this paper, we propose two novel non-uniform quantizers (NUQs) that prudently utilize one of the two properties of the simplest UQ. Although having the same quantization rule for specifying the support region, both NUQs have a different starting setting in terms of cell width, compared to a standard UQ. The first quantizer, named the simplest power-of-two quantizer (SPTQ), defines the width of cells that are multiplied by the power of two. As it is the case in the simplest UQ design, the representation levels of SPTQ are midpoints of the quantization cells. The second quantizer, named the modified SPTQ (MSPTQ), is a more competitive quantizer model, representing an enhanced version of SPTQ in which the quantizer decision thresholds are centered between the nearest representation levels, similar to the UQ design. These properties make the novel NUQs relatively simple. Unlike UQ, the quantization cells of MSPTQ are not of equal widths and the representation levels are not midpoints of the quantization cells. In this paper, we describe the design procedure of SPTQ and MSPTQ and we perform their optimization for the assumed Laplacian source. Afterwards, we perform post-training quantization by implementing SPTQ and MSPTQ, study the viability of QNN accuracy and show the implementation benefits over the case where UQ of an equal number of quantization cells is utilized in QNN for the same classification task. We believe that both NUQs are particularly substantial for memory-constrained environments, where simple and acceptably accurate solutions are of crucial importance. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) has been recently recognized as an essential aid for human traders. The advantages of the AI systems over human traders are that they can analyze an extensive data set from different sources in a fraction of a second and perform actual high-frequency trading (HFT) that can take advantage of market anomalies and price differences. This paper reviews the most important papers published in recent years that use the most advanced techniques to forecast financial asset trends and answer the question of whether those techniques can be used to successfully trade the complex financial markets. All systems use deep learning (DL) and machine learning (ML) protocols to explore nonobvious correlations and phenomena that influence the probability of trading success. Their predictions are based on linear or nonlinear models often combined with social media investors' sentiment derivations or pattern recognitions. Most of the reviewed papers have proven the successful ability of their developed system to trade the financial markets. [ABSTRACT FROM AUTHOR]

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load's consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy. [ABSTRACT FROM AUTHOR]

Cracks are widespread in infrastructure that are closely related to human activity. It is very popular to use artificial intelligence to detect cracks intelligently, which is known as crack detection. The noise in the background of crack images, discontinuity of cracks and other problems make the crack detection task a huge challenge. Although many approaches have been proposed, there are still two challenges: (1) cracks are long and complex in shape, making it difficult to capture long-range continuity; (2) most of the images in the crack dataset have noise, and it is difficult to detect only the cracks and ignore the noise. In this paper, we propose a novel method called Transformer-based Multi-scale Fusion Model (TransMF) for crack detection, including an Encoder Module (EM), Decoder Module (DM) and Fusion Module (FM). The Encoder Module uses a hybrid of convolution blocks and Swin Transformer block to model the long-range dependencies of different parts in a crack image from a local and global perspective. The Decoder Module is designed with symmetrical structure to the Encoder Module. In the Fusion Module, the output in each layer with unique scales of Encoder Module and Decoder Module are fused in the form of convolution, which can release the effect of background noise and strengthen the correlations between relevant context in order to enhance the crack detection. Finally, the output of each layer of the Fusion Module is concatenated to achieve the purpose of crack detection. Extensive experiments on three benchmark datasets (CrackLS315, CRKWH100 and DeepCrack) demonstrate that the proposed TransMF in this paper exceeds the best performance of present baselines. [ABSTRACT FROM AUTHOR]

Machine learning model sharing markets have emerged as a popular platform for individuals and companies to share and access machine learning models. These markets enable more people to benefit from the field of artificial intelligence and to leverage its advantages on a broader scale. However, these markets face challenges in designing effective incentives for model owners to share their models, and for model users to provide honest feedback on model quality. This paper proposes a novel game theoretic framework for machine learning model sharing markets that addresses these challenges. Our framework includes two main components: a mechanism for incentivizing model owners to share their models, and a mechanism for encouraging the honest evaluation of model quality by the model users. To evaluate the effectiveness of our framework, we conducted experiments and the results demonstrate that our mechanism for incentivizing model owners is effective at encouraging high-quality model sharing, and our reputation system encourages the honest evaluation of model quality. [ABSTRACT FROM AUTHOR]

This paper applies a new artificial intelligence architecture, the temporal fusion transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows for visualizing persistent temporal patterns and identifying significant events and different regimes. Third, it provides quantile regressions and permits training the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country has domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future. [ABSTRACT FROM AUTHOR]

Over the past few decades, the mathematical community has accumulated a significant amount of pure mathematical data, which has been analyzed through supervised, semi-supervised, and unsupervised machine learning techniques with remarkable results, e.g., artificial neural networks, support vector machines, and principal component analysis. Therefore, we consider as disruptive the use of machine learning algorithms to study mathematical structures, enabling the formulation of conjectures via numerical algorithms. In this paper, we review the latest applications of machine learning in the field of geometry. Artificial intelligence can help in mathematical problem solving, and we predict a blossoming of machine learning applications during the next years in the field of geometry. As a contribution, we propose a new method for extracting geometric information from the point cloud and reconstruct a 2D or a 3D model, based on the novel concept of generalized asymptotes. [ABSTRACT FROM AUTHOR]

Any small environmental changes in the driving environment of a traffic vehicle can become a risk factor directly leading to major safety incidents. Therefore, it is necessary to assist drivers in automatically detecting risk factors during the driving process using algorithms. However, besides making it more difficult for drivers to judge environmental changes, the performance of automatic detection networks in low illumination scenarios can also be greatly affected and cannot be used directly. In this paper, we propose a risk factor detection model based on deep learning in low illumination scenarios and test the optimization of low illumination image enhancement problems. The overall structure of this model includes dual discriminators, encoder–decoders, etc. The model consists of two main stages. In the first stage, the input low illumination scene image is adaptively converted into a standard illumination image through a lighting conversion module. In the second stage, the converted standard illumination image is automatically assessed for risk factors. The experiments show that the detection network can overcome the impact of low lighting and has high detection accuracy. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms are an important area of research in artificial intelligence. The tumbleweed optimization algorithm (TOA) is the newest metaheuristic optimization algorithm that mimics the growth and reproduction of tumbleweeds. In practice, chaotic maps have proven to be an improved method of optimization algorithms, allowing the algorithm to jump out of the local optimum, maintain population diversity, and improve global search ability. This paper presents a chaotic-based tumbleweed optimization algorithm (CTOA) that incorporates chaotic maps into the optimization process of the TOA. By using 12 common chaotic maps, the proposed CTOA aims to improve population diversity and global exploration and to prevent the algorithm from falling into local optima. The performance of CTOA is tested using 28 benchmark functions from CEC2013, and the results show that the circle map is the most effective in improving the accuracy and convergence speed of CTOA, especially in 50D. [ABSTRACT FROM AUTHOR]