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.

Recent advancements in telecommunications and the tactile Internet have paved the way for studying human senses through haptic technology. Haptic technology enables tactile sensations and control using virtual reality (VR) over a network. Researchers are developing various haptic devices to allow for real-time tactile sensation, which can be used in various industries, telesurgery, and other mission-critical operations. One of the main criteria of such devices is extremely low latency, as low as 1 ms. Although researchers are attempting to develop haptic devices with low latency, there remains a need to improve latency and robustness to hand sizes. In this paper, a low-latency haptic open glove (LLHOG) based on a rotary position sensor and min-max scaling (MMS) filter is proposed to realize immersive VR interaction. The proposed device detects finger flexion/extension and adduction/abduction motions using two position sensors located in the metacarpophalangeal (MCP) joint. The sensor data are processed using an MMS filter to enable low latency and ensure high accuracy. Moreover, the MMS filter is used to process object handling control data to enable hand motion-tracking. Its performance is evaluated in terms of accuracy, latency, and robustness to finger length variations. We achieved a very low processing delay of 145.37 μs per finger and overall hand motion-tracking latency of 4 ms. Moreover, we tested the proposed glove with 10 subjects and achieved an average mean absolute error (MAE) of ${3.091}^{\circ }$ for flexion/extension, and ${2.068}^{\circ }$ for adduction/abduction. The proposed method is therefore superior to the existing methods in terms of the above factors for immersive VR interaction.

Remote sensing technology has been modernized by artificial intelligence, which has made it possible for deep learning algorithms to extract useful information from images. However, overfitting and lack of uncertainty quantification, high-resolution images, information loss in traditional feature extraction, and background information retrieval for detected objects limit the use of deep learning models in various remote sensing applications. This paper proposes a Bayes by backpropagation (BBB)-based system for scene-driven identification and information retrieval in order to overcome the above-mentioned problems. We present the Bayes R-CNN, a two-stage object detection technique to reduce overfitting while also quantifying uncertainty for each object recognized within a given image. To extract features more successfully, we replace the traditional feature extraction model with our novel Multi-Resolution Extraction Network (MRENet) model. We propose the multi-level feature fusion module (MLFFM) in the inner lateral connection and a Bayesian Distributed Lightweight Attention Module (BDLAM) to reduce information loss in the feature pyramid network (FPN). In addition, our system incorporates a Bayesian image super-resolution model which enhances the quality of the image to improve the prediction accuracy of the Bayes R-CNN. Notably, MRENet is used to classify the background of the detected objects to provide detailed interpretation of the object. Our proposed system is comprehensively trained and assessed utilizing the state-of-the-art DIOR and HRSC2016 datasets. The results demonstrate our system’s ability to detect and retrieve information from remote sensing scene images.

Background/Objectives: The research addresses algorithmic bias in deep learning models for cardiovascular risk prediction, focusing on fairness across demographic and socioeconomic groups to mitigate health disparities. It integrates fairness-aware algorithms, susceptible carrier-infected-recovered (SCIR) models, and interpretability frameworks to combine fairness with actionable AI insights supported by robust segmentation and classification metrics. Methods: The research utilised quantitative 3D/4D heart magnetic resonance imaging and tabular datasets from the Cardiac Atlas Project’s (CAP) open challenges to explore AI-driven methodologies for mitigating algorithmic bias in cardiac imaging. The SCIR model, known for its robustness, was adapted with the Capuchin algorithm, adversarial debiasing, Fairlearn, and post-processing with equalised odds. The robustness of the SCIR model was further demonstrated in the fairness evaluation metrics, which included demographic parity, equal opportunity difference ($0.037$), equalised odds difference ($0.026$), disparate impact ($1.081$), and Theil Index ($0.249$). For interpretability, YOLOv5, Mask R-CNN, and ResNet18 were implemented with LIME and SHAP. Bias mitigation improved disparate impact ($0.80$ to $0.95$), reduced equal opportunity difference ($0.20$ to $0.05$), and decreased false favourable rates for males ($0.0059$ to $0.0033$) and females ($0.0096$ to $0.0064$) through balanced probability adjustment. Results: The SCIR model outperformed the SIR model (recovery rate: $1.38$ vs $0.83$) with a $-10\%$ transmission bias impact. Parameters ($\beta =0.5$, $\delta =0.2$, $\gamma =0.15$) reduced susceptible counts to $2.53\times {10}^{-12}$ and increased recovered counts to $9.98$ by $t=50$. YOLOv5 achieved high Intersection over Union (IoU) scores ($94.8\%$, $93.7\%$, $80.6\%$ for normal, severe, and abnormal cases). Mask R-CNN showed $82.5\%$ peak confidence, while ResNet demonstrated a $10.4\%$ accuracy drop under noise. Performance metrics (IoU: $0.91$–$0.96$, Dice: $0.941$–$0.980$, Kappa: $0.95$) highlighted strong predictive accuracy and reliability. Conclusions: The findings validate the effectiveness of fairness-aware algorithms in addressing cardiovascular predictive model biases. The integration of fairness and explainable AI not only promotes equitable diagnostic precision but also significantly reduces diagnostic disparities across vulnerable populations. This reduction in disparities is a key outcome of the research, enhancing clinical trust in AI-driven systems. The promising results of this study pave the way for future work that will explore scalability in real-world clinical settings and address limitations such as computational complexity in large-scale data processing.

Human emotion plays a significant role in mental well-being, and recognizing these emotions in daily life is essential. With the advancement of artificial intelligence, affective computing has paved the way for effective applications in enhancing emotional states in everyday life. In practical daily-life scenarios, data sources that can be collected through simple and low-cost wearables contribute to recognizing emotions in daily routines. Heart rate and speech data can be easily collected from affordable smartwatches without any other human intervention. Heart rate data, directly correlated with physiological response, and speech data, with its rich expressiveness, together yield a robust indicator of the human’s emotional condition. We conduct multimodal emotion recognition (MER), integrating heart rate-based emotion recognition (HER) and speech-based emotion recognition (SER) through a score-based fusion method. Our proposed MER achieves an overall accuracy of 84.22%, surpassing single-modality models with accuracies of 57.65% for HER and 80.38% for SER. The findings highlight the practicality of utilizing emotion-related data sources collected conveniently with smartwatches, thereby enhancing emotion tracking accessibility in daily life scenarios. Furthermore, integrating these modalities proves more effective in capturing emotions than using a single modality. Moreover, our system’s lightweight architecture facilitates easy expansion to incorporate additional modalities, ensuring durable precision even when not all modalities are sensed, making it versatile and pragmatic.