Artificial Intelligence Review最新文献

There should be some improvements to increase the performance of Metaverse investments. However, businesses need to focus on the most important actions to provide cost effectiveness in this process. In summary, a new study is needed in which a priority analysis is made for the performance indicators of Metaverse investments. Accordingly, this study aims to evaluate the main determinants of the performance of the metaverse investments. Within this context, a novel model is created that has four different stages. The first stage is related to the prioritizing the experts with artificial intelligence-based decision-making method. Secondly, missing evaluations are estimated by expert recommendation system. Thirdly, the criteria are weighted with Quantum picture fuzzy rough sets-based (QPFR) M-Step-wise Weight Assessment Ratio Analysis (SWARA). Finally, investment decision-making priorities are ranked by QPFR VIKOR (Vlse Kriterijumska Optimizacija Kompromisno Resenje). The main contribution of this study is the integration of the artificial intelligence methodology to the fuzzy decision-making approach for the purpose of computing the weights of the decision makers. Owing to this condition, the evaluations of these people are examined according to their qualifications. This situation has a positive contribution to make more effective evaluations. Organizational effectiveness is found to be the most important factor in improving the performance of metaverse investments. Similarly, it is also identified that it is important for businesses to ensure technological improvements in the development of Metaverse investments. On the other side, the ranking results indicate that regulatory framework is the most critical alternative in this regard.

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP domain. In this work, we consider a few-shot continual active learning setting where labeled data are inadequate, and unlabeled data are abundant but with a limited annotation budget. We exploit meta-learning and propose a method, called Meta-Continual Active Learning. This method sequentially queries the most informative examples from a pool of unlabeled data for annotation to enhance task-specific performance and tackles continual learning problems through a meta-objective. Specifically, we employ meta-learning and experience replay to address inter-task confusion and catastrophic forgetting. We further incorporate textual augmentations to avoid memory over-fitting caused by experience replay and sample queries, thereby ensuring generalization. We conduct extensive experiments on benchmark text classification datasets from diverse domains to validate the feasibility and effectiveness of meta-continual active learning. We also analyze the impact of different active learning strategies on various meta continual learning models. The experimental results demonstrate that introducing randomness into sample selection is the best default strategy for maintaining generalization in meta-continual learning framework.

Recently, machine learning has been very useful in solving diverse tasks with drones, such as autonomous navigation, visual surveillance, communication, disaster management, and agriculture. Among these machine learning, two representative paradigms have been widely utilized in such applications: supervised learning and reinforcement learning. Researchers prefer to use supervised learning, mostly based on convolutional neural networks, because of its robustness and ease of use but yet data labeling is laborious and time-consuming. On the other hand, when traditional reinforcement learning is combined with the deep neural network, it can be a very powerful tool to solve high-dimensional input problems such as image and video. Along with the fast development of reinforcement learning, many researchers utilize reinforcement learning in drone applications, and it often outperforms supervised learning. However, it usually requires the agent to explore the environment on a trial-and-error basis which is high cost and unrealistic in the real environment. Recent advances in simulated environments can allow an agent to learn by itself to overcome these drawbacks, although the gap between the real environment and the simulator has to be minimized in the end. In this sense, a realistic and reliable simulator is essential for reinforcement learning training. This paper investigates various drone simulators that work with diverse reinforcement learning architectures. The characteristics of the reinforcement learning-based drone simulators are analyzed and compared for the researchers who would like to employ them for their projects. Finally, we shed light on some challenges and potential directions for future drone simulators.

As the degree of automotive intelligence increases, gesture recognition is gaining more attention in human-vehicle interaction. However, existing gesture recognition methods are computationally intensive and perform poorly in multi-modal sensor scenarios. This paper proposes a novel network structure, AL-MobileNet (MobileNet with Attention and Lightweight Modules), which can quickly and accurately estimate 2D gestures in RGB and infrared (IR) images. The innovations of this paper are as follows: Firstly, to enhance multi-modal data, we created a synthetic IR dataset based on real 2D gestures and employed a coarse-to-fine training approach. Secondly, to speed up the model's computation on edge devices, we introduced a new lightweight computational module called the Split Channel Attention Block (SCAB). Thirdly, to ensure the model maintains accuracy in large datasets, we incorporated auxiliary networks and Angle-Weighted Loss (AWL) into the backbone network. Experiments show that AL-MobileNet requires only 0.4 GFLOPs of computational power and 1.2 million parameters. This makes it 1.5 times faster than MobileNet and allows for quick execution on edge devices. AL-MobileNet achieved a running speed of up to 28 FPS on the Ambarella CV28. On both general datasets and our dataset, our algorithm achieved an average PCK0.2 score of 0.95. This indicates that the algorithm can quickly generate accurate 2D gestures. The demonstration of the algorithm can be reviewed in gesturebaolong.

Due to the progress in image processing and Artificial Intelligence (AI), it is now possible to develop automated tool for the early detection and diagnosis of Alzheimer’s Disease (AD). Handcrafted techniques developed so far, lack generality, leading to the development of deep learning (DL) techniques, which can extract more relevant features. To cater for the limited labelled datasets and requirement in terms of high computational power, transfer learning models can be adopted as a baseline. In recent years, considerable research efforts have been devoted to developing machine learning-based techniques for AD detection and classification using medical imaging data. This survey paper comprehensively reviews the existing literature on various methodologies and approaches employed for AD detection and classification, with a focus on neuroimaging techniques such as structural MRI, PET, and fMRI. The main objective of this survey is to analyse the different transfer learning models that can be used for the deployment of deep convolution neural network for AD detection and classification. The phases involved in the development namely image capture, pre-processing, feature extraction and selection are also discussed in the view of shedding light on the different phases and challenges that need to be addressed. The research perspectives may provide research directions on the development of automated applications for AD detection and classification.

Cloud computing is an emerging technology composed of several key components that work together to create a seamless network of interconnected devices. These interconnected devices, such as sensors, routers, smartphones, and smart appliances, are the foundation of the Internet of Everything (IoE). Huge volumes of data generated by IoE devices are processed and accumulated in the cloud, allowing for real-time analysis and insights. As a result, there is a dire need for load-balancing and task-scheduling techniques in cloud computing. The primary objective of these techniques is to divide the workload evenly across all available resources and handle other issues like reducing execution time and response time, increasing throughput and fault detection. This systematic literature review (SLR) aims to analyze various technologies comprising optimization and machine learning algorithms used for load balancing and task-scheduling problems in a cloud computing environment. To analyze the load-balancing patterns and task-scheduling techniques, we opted for a representative set of 63 research articles written in English from 2014 to 2024 that has been selected using suitable exclusion-inclusion criteria. The SLR aims to minimize bias and increase objectivity by designing research questions about the topic. We have focused on the technologies used, the merits-demerits of diverse technologies, gaps within the research, insights into tools, forthcoming opportunities, performance metrics, and an in-depth investigation into ML-based optimization techniques.

Accurately assessing suicide risk is a critical concern in mental health care. Traditional methods, which often rely on self-reporting and clinical interviews, are limited by their subjective nature and may overlook non-verbal cues. This study introduces an innovative approach to suicide risk assessment using facial image analysis. The Suicidal Visual Indicators Prediction (SVIP) Framework leverages EfficientNetb0 and ResNet architectures, enhanced through Bayesian optimization techniques, to detect nuanced facial expressions indicating mental state. The models’ interpretability is improved using GRADCAM, Occlusion Sensitivity, and LIME, which highlight significant facial regions for predictions. Using datasets DB1 and DB2, which consist of full and cropped facial images from social media profiles of individuals with known suicide outcomes, the method achieved 67.93% accuracy with EfficientNetb0 on DB1 and up to 76.6% accuracy with a Bayesian-optimized Support Vector Machine model using ResNet18 features on DB2. This approach provides a less intrusive, accessible alternative to video-based methods and demonstrates the substantial potential for early detection and intervention in mental health care.

Machine learning and medical diagnostic studies often struggle with the issue of class imbalance in medical datasets, complicating accurate disease prediction and undermining diagnostic tools. Despite ongoing research efforts, specific characteristics of medical data frequently remain overlooked. This article comprehensively reviews advances in addressing imbalanced medical datasets over the past decade, offering a novel classification of approaches into preprocessing, learning levels, and combined techniques. We present a detailed evaluation of the medical datasets and metrics used, synthesizing the outcomes of previous research to reflect on the effectiveness of the methodologies despite methodological constraints. Our review identifies key research trends and offers speculative insights and research trajectories to enhance diagnostic performance. Additionally, we establish a consensus on best practices to mitigate persistent methodological issues, assisting the development of generalizable, reliable, and consistent results in medical diagnostics.

In today’s cyber environment, threats such as data breaches, cyberattacks, and unauthorized access threaten national security, critical infrastructure, and financial stability. This research addresses the challenging task of protecting critical infrastructure from insider threats because of the high level of trust and access these individuals typically receive. Insiders may obtain a system administrator’s password through close observation or by deploying software to gather the information. To solve this issue, an innovative artificial intelligence-based methodology is proposed to identify a user by their password’s keystroke dynamics. This paper also introduces a new Gabor Filter Matrix Transformation method to transform numerical values into images by revealing the behavioral pattern of password typing. A siamese neural network (SNN) with the branches of convolutional neural networks is utilized for image comparison, aiming to detect unauthorized attempts to access critical infrastructure systems. The network analyzes the unique features of a user’s password timestamps transformed into images and compares them with previously submitted user passwords. The obtained results indicate that transforming the numerical values of keystroke dynamics into images and training an SNN leads to a lower equal error rate (EER) and higher user authentication accuracy than those previously reported in other studies. The methodology is validated on publicly available keystroke dynamics collections, the CMU and GREYC-NISLAB datasets, which collectively comprise over 30,000 password samples. It achieves the lowest EER value of 0.04545 compared to state-of-the-art methods for transforming non-image data into images. The paper concludes with a discussion of findings and potential future directions.

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language machine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation systems.