Artificial Intelligence Review最新文献

The discovery of non-coding RNAs (ncRNAs) has expanded our comprehension of RNAs’ inherent nature and capabilities. The intricate three-dimensional structures assumed by RNAs dictate their specific functions and molecular interactions. However, the limited number of mapped structures, partly due to experimental constraints of methods such as nuclear magnetic resonance (NMR), highlights the importance of in silico prediction solutions. This is particularly crucial in potential applications in therapeutic drug discovery. In this context, machine learning (ML) methods have emerged as prominent candidates, having previously demonstrated prowess in solving complex challenges across various domains. This review focuses on analyzing the development of ML-based solutions for RNA structure prediction, specifically oriented toward recent advancements in the deep learning (DL) domain. A systematic analysis of 33 works reveals insights into the representation of RNA structures, secondary structure motifs, and tertiary interactions. The review highlights current trends in ML methods used for RNA structure prediction, demonstrates the growing research involvement in this field, and summarizes the most valuable findings.

Satellite imagery is a significant and attractive area in remote sensing applications, widely applied in monitoring, managing, and tracking natural disasters. Due to the proliferation of commercial satellites, there is an increasing availability of high-resolution satellite images. However, the ubiquity of image editing tools and the advancement of image processing technologies have made satellite image forgery relatively easy, allowing for the arbitrary addition, removal, or modification of target objects. In recent years, satellite image forgery has caused significant negative effects and potential threats to the nation, society, and individuals, drawing the attention of many scholars. Although forensics of satellite image tampering is an emerging research field that offers new insights into the field of information security, there has been a scarcity of comprehensive surveys in this area. This paper aims to fill this gap and investigates recent advances in satellite image forensics, focusing on tampering strategies and forensic methodologies. First, we discuss the concept of satellite images, the definition of satellite image forgery from global and local perspectives, and the datasets commonly used for satellite image forensics. We then detail each tampering detection and localization method, including their characteristics, advantages, disadvantages, and performance in detection or localization across various notable datasets. We also compare some representative forensic networks using evaluation metrics and public datasets. Finally, the anticipated future directions for satellite image forgery forensics are discussed.

A fundamental obstacle to healthcare transformation continues to be the acquisition of knowledge and insightful data from complex, high dimensional, and heterogeneous biological data. As technology has improved, a wide variety of data sources, including omics data, imaging data, and health records, have been available for use in healthcare research contexts. Electronic health records (EHRs), which are digitalized versions of medical records, have given researchers a significant chance to create computational methods for analyzing healthcare data. EHR systems typically keep track of all the data relating to a patient’s medical history, including clinical notes, demographic background, and diagnosis details. EHR data can offer valuable insights and support doctors in making better decisions related to disease and diagnostic forecasts. As a result, several academics use deep learning to forecast diseases and track health trajectories in EHR. Recent advances in deep learning technology have produced innovative and practical paradigms for building end-to-end learning models. However, scholars have limited access to online HER databases, and there is an inherent need to address this issue. This research examines deep learning models, their architectures, and readily accessible EHR online databases. The goal of this paper is to examine how various architectures, models, and databases differ in terms of features and usability. It is anticipated that the outcomes of this review will lead to the development of more robust deep learning models that facilitate medical decision-making processes based on EHR data and inform efforts to support the selection of architectures, models, and databases for specific research purposes.

This survey reviews different research on question analysis, including other comparative studies of question analysis approaches and an evaluation of the questions by different NLP techniques that are used in question interpretation and categorization. Among these key findings noted includes the assessment of deep learning models such as M-BiGRU-CNN and M-TF-IDF, which come with high precision and accuracy when applied with the effectiveness of use in dealing with the complexities involved in a language. Some of the most mature machine learning algorithms, for example, SVM or logistic regression, remain powerful models, especially on the classification task, meaning that the latter continues to be relevant. This study further underlines the applicability of rule-based or hybrid methodologies in certain linguistic situations, and it must be said that custom design solutions are required. We could recommend, on this basis, directing future work towards the integration of these hybrid systems and towards the definition of more general methodologies of evaluation that are in line with the constant evolution of NLP technologies. It revealed that the underlying challenges and barriers in the domain are very complex syntactic and dialectic variations, unavailability of software tools, very critical standardization in Arabic datasets, benchmark creation, handling of translated data, and the integration of Large Language Models (LLMs). The paper discusses the lack of identity and processing of such structures through online systems for comparison. This comprehensive review highlights not only the diversified potential for the capabilities of NLP techniques in refining question analysis but also the potential way of great promises for further enhancements and improvements in this progressive domain.

Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility, adaptability, dynamism, faster training, information sharing, and model compression. Hypernets have shown promising results in a variety of deep learning problems, including continual learning, causal inference, transfer learning, weight pruning, uncertainty quantification, zero-shot learning, natural language processing, and reinforcement learning. Despite their success across different problem settings, there is currently no comprehensive review available to inform researchers about the latest developments and to assist in utilizing hypernets. To fill this gap, we review the progress in hypernets. We present an illustrative example of training deep neural networks using hypernets and propose categorizing hypernets based on five design criteria: inputs, outputs, variability of inputs and outputs, and the architecture of hypernets. We also review applications of hypernets across different deep learning problem settings, followed by a discussion of general scenarios where hypernets can be effectively employed. Finally, we discuss the challenges and future directions that remain underexplored in the field of hypernets. We believe that hypernetworks have the potential to revolutionize the field of deep learning. They offer a new way to design and train neural networks, and they have the potential to improve the performance of deep learning models on a variety of tasks. Through this review, we aim to inspire further advancements in deep learning through hypernetworks.

Credit risk assessment (CRA) plays an important role in credit decision-making process of financial institutions. Today, developing big data analysis and machine learning methods have marked a new era in credit risk estimation. In recent years, using machine learning methods in credit risk estimation has emerged as an alternative method for financial institutions. The past demographic and financial data of the person whose CRA will be performed is important for creating an automatic artificial intelligence credit score prediction model based on machine learning. It is also necessary to use features correctly to create accurate machine learning models. This article aims to investigate the effects of dimensionality reduction and data splitting steps on the performance of classification algorithms widely used in the literature. In our study, dimensionality reduction was performed using Principal Component Analysis (PCA). Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Naive Bayes (NB) algorithms were chosen for classification. Percentage splitting (PER, 66–34%) and k-fold (k = 10) cross-validation techniques were used when dividing the data set into training and test data. The results obtained were evaluated with accuracy, recall, F1 score, precision, and AUC metrics. German data set was used in this study. The effect of data splitting and dimension reduction on the classification of CRA systems was examined. The highest ACC in PER and CV data splitting was obtained with the RF algorithm. Using data splitting methods and PCA, the highest accuracy was observed with RF and the highest AUC with NB, with 13 PCs in which 80% of the variance was obtained. As a result, the data set consisting of a total of 20 features, expressed by 13 PCs, achieved similar or higher success than the results obtained from the original data set.

The study of insect behavior, particularly that of honey bees, has a broad scope and significance. Tracking bee flying patterns grants much helpful information about bee behavior. However, tracking a small yet fast-moving object, such as a bee, is difficult. Hence, we present artificial intelligence, machine-learning-based bee recognition, and tracking systems to assist the researcher in studying the bee’s behavior. To develop a machine learning system, a labeled database is required for model training. To address this, we implemented an automated system for analyzing and labeling bee videos. This labeled database served as the foundation for two distinct bee-tracking solutions. The first solution (planar bee tracking system) tracked individual bees in closed mazes using a neural network. The second solution (spatial bee tracking system) utilized a neural network and a tracking algorithm to identify and track flying bees in open environments. Both systems tackle the challenge of tracking small-bodied creatures with rapid and diverse movement patterns. Although we applied these systems to entomological cognition research in this paper, their relevance extends to general insect research and developing tracking solutions for small organisms with swift movements. We present the complete architecture and detailed methodologies to facilitate the utilization of these models in future research endeavors. Our approach is a simple and inexpensive method that contributes to the growing number of image-analysis tools used for tracking animal movement, with future potential applications under less sterile field conditions. The tools presented in this paper could assist the study of movement ecology, specifically in insects, by providing accurate movement specifications. Following the movement of pollinators or natural enemies, for example, greatly contributes to the study of pollination or biological control, respectively, in natural and agro-ecosystems.

A recently developed algorithm inspired by natural processes, known as the Artificial Gorilla Troops Optimizer (GTO), boasts a straightforward structure, unique stabilizing features, and notably high effectiveness. Its primary objective is to efficiently find solutions for a wide array of challenges, whether they involve constraints or not. The GTO takes its inspiration from the behavior of Gorilla Troops in the natural world. To emulate the impact of gorillas at each stage of the search process, the GTO employs a flexible weighting mechanism rooted in its concept. Its exceptional qualities, including its independence from derivatives, lack of parameters, user-friendliness, adaptability, and simplicity, have resulted in its rapid adoption for addressing various optimization challenges. This review is dedicated to the examination and discussion of the foundational research that forms the basis of the GTO. It delves into the evolution of this algorithm, drawing insights from 112 research studies that highlight its effectiveness. Additionally, it explores proposed enhancements to the GTO’s behavior, with a specific focus on aligning the geometry of the search area with real-world optimization problems. The review also introduces the GTO solver, providing details about its identification and organization, and demonstrates its application in various optimization scenarios. Furthermore, it provides a critical assessment of the convergence behavior while addressing the primary limitation of the GTO. In conclusion, this review summarizes the key findings of the study and suggests potential avenues for future advancements and adaptations related to the GTO.

Over the last few years Literature-based Discovery (LBD) has regained popularity as a means to enhance the scientific research process. The resurgent interest has spurred the development of supervised and semi-supervised machine learning models aimed at making previously implicit connections between scientific concepts/entities within often extensive bodies of literature explicit—i.e., suggesting novel scientific hypotheses. In doing so, understanding the temporally evolving interactions between these entities can provide valuable information for predicting the future development of entity relationships. However, existing methods often underutilize the latent information embedded in the temporal aspects of the interaction data. Motivated by applications in the food domain—where we aim to connect nutritional information with health-related benefits—we address the hypothesis-generation problem using a temporal graph-based approach. Given that hypothesis generation involves predicting future (i.e., still to be discovered) entity connections, in our view the ability to capture the dynamic evolution of connections over time is pivotal for a robust model. To address this, we introduce THiGER, a novel batch contrastive temporal node-pair embedding method. THiGER excels in providing a more expressive node-pair encoding by effectively harnessing node-pair relationships. Furthermore, we present THiGER-A, an incremental training approach that incorporates an active curriculum learning strategy to mitigate label bias arising from unobserved connections. By progressively training on increasingly challenging and high-utility samples, our approach significantly enhances the performance of the embedding model. Empirical validation of our proposed method demonstrates its effectiveness on established temporal-graph benchmark datasets, as well as on real-world datasets within the food domain.

Deep neural networks (DNNs) have proven explicit contributions in making autonomous driving cars and related tasks such as semantic segmentation, motion tracking, object detection, sensor fusion, and planning. However, in challenging situations, DNNs are not generalizable because of the inherent domain shift due to the nature of training under the i.i.d. assumption. The goal of semantic segmentation is to preserve information from a given image into multiple meaningful categories for visual understanding. Particularly for semantic segmentation, pixel-wise annotation is extremely costly and not always feasible. Domain generalization for semantic segmentation aims to learn pixel-level semantic labels from multiple source domains and generalize to predict pixel-level semantic labels on multiple unseen target domains. In this survey, for the first time, we present a comprehensive review of DG for semantic segmentation. we present a comprehensive summary of recent works related to domain generalization in semantic segmentation, which establishes the importance of generalizing to new environments of segmentation models. Although domain adaptation has gained more attention in segmentation tasks than domain generalization, it is still worth unveiling new trends that are adopted from domain generalization methods in semantic segmentation. We cover most of the recent and dominant DG methods in the context of semantic segmentation and also provide some other related applications. We conclude this survey by highlighting the future directions in this area.