Search Results (3,354)

The COVID-19 virus caused unprecedented global disruption. There have been millions of cases and deaths reported worldwide. Accurate prediction of COVID-19 trends is crucial for effective decision-making, resource allocation, and policy formulation. ML has been shown to be an excellent method for projecting the virus’s growth and impact as it can analyze vast datasets, discover trends, and develop predictive models. This study examines the use of various machine learning techniques for the prediction of COVID-19 such as time series analysis, regression models, and classification techniques. This paper further addresses the problems and constraints of applying the ML model to this context and suggests possible enhancements for future forecasting endeavors. The overall intention of this work is to enlighten people as to how this ML-based method contributes to pandemic forecasting in terms of improvements in pandemic preparation and response schemes. Full article

Early detection of pest damage and accurate assessment of fruit ripeness are essential for improving the quality, productivity, and sustainability of citrus production. Moreover, precisely assessing ripeness is crucial for establishing the optimal harvest time, preserving fruit quality, and enhancing yield. The simultaneous and precise early detection of pest damage and assessment of fruit ripeness greatly enhance the efficacy of contemporary agricultural decision support systems. This study presents a lightweight deep learning model based on an optimized YOLO12n-Seg architecture for the simultaneous detection of ripeness stages (unripe and fully ripe) and pest damage caused by Red Scale (Aonidiella aurantii). The model is based on an improved version of YOLO12n-Seg, where the backbone and head layers were retained, but the neck was modified with a GhostConv block to reduce parameter size and improve computational efficiency. Additionally, a Global Attention Mechanism (GAM) was incorporated to strengthen the model’s focus on target-relevant features and reduce background noise. The improvement procedure improved both the ability to gather accurate spatial information in several dimensions and the effectiveness of focusing on specific target object areas utilizing the attention mechanism. Experimental results demonstrated high accuracy on test data, with mAP@0.5 = 0.980, mAP@0.95 = 0.960, precision = 0.961, and recall = 0.943, all achieved with only 2.7 million parameters and a training time of 2 h and 42 min. The model offers a reliable and efficient solution for real-time, integrated pest detection and fruit classification in precision agriculture. Full article

Weakly supervised video anomaly detection (WSVAD) aims to identify unusual events using only video-level labels. However, current methods face several key challenges, including ineffective modelling of complex temporal dependencies, indistinct feature boundaries between visually similar normal and abnormal events, and high false alarm rates caused by an inability to distinguish salient events from complex background noise. This paper proposes a novel method that systematically enhances feature representation and discrimination to address these challenges. The proposed method first builds robust temporal representations by employing a hierarchical multi-scale temporal encoder and a position-aware global relation network to capture both local and long-range dependencies. The core of this method is the dual-stream attention-enhanced memory network, which achieves precise discrimination by learning distinct normal and abnormal patterns via dual memory banks, while utilising bidirectional spatial attention to mitigate background noise and focus on salient events before memory querying. The models underwent a comprehensive evaluation utilising solely RGB features on two demanding public datasets, UCF-Crime and XD-Violence. The experimental findings indicate that the proposed method attains state-of-the-art performance, achieving 87.43% AUC on UCF-Crime and 85.51% AP on XD-Violence. This result demonstrates that the proposed “attention-guided prototype matching” paradigm effectively resolves the aforementioned challenges, enabling robust and precise anomaly detection. Full article

Neurogenic bladder is a debilitating condition caused by neurological dysfunction that impairs urinary control, often requiring timed intermittent catheterisation. Although effective, intermittent catheterisation is invasive, uncomfortable, and associated with infection risks, reducing patients’ quality of life. SafeBladder is a low-cost wearable device developed to enable real-time, non-invasive bladder volume monitoring using near-infrared spectroscopy (NIRS) and machine learning algorithms. The prototype employs LEDs and photodetectors to measure light attenuation through abdominal tissues. Bladder filling was simulated through experimental tests using stepwise water additions to containers and tissue-mimicking phantoms, including silicone and porcine tissue. Machine learning models, including Linear Regression, Support Vector Regression, and Random Forest, were trained to predict volume from sensor data. The results showed the device is sensitive to volume changes, though ambient light interference affected accuracy, suggesting optimal use under clothing or in low-light conditions. The Random Forest model outperformed others, with a Mean Absolute Error (MAE) of 25 ± 4 mL and $R^2$ of 0.90 in phantom tests. These findings support SafeBladder as a promising, non-invasive solution for bladder monitoring, with clinical potential pending further calibration and validation in real-world settings. Full article

Improving the decoding accuracy of biological signals has been a research focus for decades to advance health, automation, and robotic industries. However, challenges like inter-subject variability, data scarcity, and multifunctional variability cause low decoding accuracy, thus hindering the practical deployment of biological signal paradigms. This paper proposes a multifunctional biological signals network (Multi-BioSig-Net) that addresses the aforementioned issues by devising a novel blind few-shot learning (FSL) technique to quickly adapt to multiple target domains without needing a pre-trained model. Specifically, our proposed multimodal similarity extractor (MMSE) and self-multiple domain adaptation (SMDA) modules address data scarcity and inter-subject variability issues by exploiting and enhancing the similarity between multimodal samples and quickly adapting the target domains by adaptively adjusting the parameters’ weights and position, respectively. For multifunctional learning, we proposed inter-function discriminator (IFD) that discriminates the classes by extracting inter-class common features and then subtracts them from both classes to avoid false prediction of the proposed model due to overfitting on the common features. Furthermore, we proposed a holistic-local fusion (HLF) module that exploits contextual-detailed features to adapt the scale-varying features across multiple functions. In addition, fractal dimension estimation (FDE) was employed for the classification of left-hand motor imagery (LMI) and right-hand motor imagery (RMI), confirming that proposed method can effectively extract the discriminative features for this task. The effectiveness of our proposed algorithm was assessed quantitatively and statistically against competent state-of-the-art (SOTA) algorithms utilizing three public datasets, demonstrating that our proposed algorithm outperformed SOTA algorithms. Full article

The accurate monitoring of short-term bathymetric changes in shallow waters is essential for effective coastal management and planning. Machine Learning (ML) applied to Unmanned Aerial Vehicle (UAV)-based multispectral imagery offers a rapid and cost-effective solution for bathymetric surveys. However, models based solely on multispectral imagery are inherently limited by confounding factors such as shadow effects, poor water quality, and complex seafloor textures, which obscure the spectral–depth relationship, particularly in heterogeneous coastal environments. To address these issues, we developed a hybrid bathymetric inversion model that integrates digital surface model (DSM) data—providing high-resolution topographic information—with ML applied to UAV-based multispectral imagery. The model training was supported by multibeam sonar measurements collected from an Unmanned Surface Vehicle (USV), ensuring high accuracy and adaptability to diverse underwater terrains. The study area, located around Lazarus Island, Singapore, encompasses a sandy beach slope transitioning into seagrass meadows, coral reef communities, and a fine-sediment seabed. Incorporating DSM-derived topographic information substantially improved prediction accuracy and correlation, particularly in complex environments. Compared with linear and bio-optical models, the proposed approach achieved accuracy improvements exceeding 20% in shallow-water regions, with performance reaching an R² > 0.93. The results highlighted the effectiveness of DSM integration in disentangling spectral ambiguities caused by environmental variability and improving bathymetric prediction accuracy. By combining UAV-based remote sensing with the ML model, this study presents a scalable and high-precision approach for bathymetric mapping in complex shallow-water environments, thereby enhancing the reliability of UAV-based surveys and supporting the broader application of ML in coastal monitoring and management. Full article

The temperature rise in mass concrete structures, caused by the exothermic process of cement hydration and concurrent heat exchange with the environment, results in thermal gradients between the core and outer layers of the structure. These gradients generate tensile stresses that may exceed the early age tensile strength of concrete, leading to cracking. Therefore, reliable prediction of the temperature rise and associated thermal gradients is essential for assessing the risk of early age thermal cracking. Traditional methods for predicting temperature development rely on numerical simulations and simplified analytical approaches, which are often time-consuming and impractical for rapid engineering assessments. This paper proposes a machine learning-based (ML) approach to predict temperature rise and thermal gradients in mass concrete. The dataset was generated using the analytical CIRIA C766 method, enabling systematic selection and gradation of key factors, which is nearly impossible using measurements collected from full-scale structures and is essential for identifying an effective ML model. Three regression models, linear regression, decision tree, and XGBoost were trained and evaluated on simulated datasets that included concrete mix parameters and environmental conditions. Among these, the XGBoost model achieved the highest accuracy in predicting the maximum temperature rise and the temperature differential between the core and surface of the analysed element. The results confirm the suitability of ML models for reliable thermal response prediction. Furthermore, ML models can provide a usable alternative to conventional methods, offering both tools to thermal control strategies and insight into the influence of input factors on temperature in early age mass concrete. Full article

During high-altitude simulation tests, the accurate reproduction of environmental conditions directly affects the ability to reliably evaluate the engine’s performance under simulated high-altitude conditions. Traditional physical models, though interpretable, often fall short in handling nonlinear dynamics and time-delayed effects caused by disturbances such as abrupt flow rate fluctuations. For this problem, this work proposes a novel hybrid modeling framework that integrates physical principles with deep learning architectures. The proposed approach incorporates three key innovations. First, a physics-guided residual learning scheme is introduced, where the theoretical outlet temperature derived from energy conservation laws and assumptions of symmetric inlet mixing serves as a prior, and a data-driven model corrects residual deviations. Second, a multiscale feature extraction module is constructed by combining a Transformer with DWT, capturing both long-term regularities and short-term fluctuations that often exhibit quasi-symmetric patterns in structured systems. Third, a perturbation-aware memory structure is designed, fusing a Transformer branch for long-term dependency modeling with an extended LSTM (xLSTM) branch for short-term dynamic sensitivity. The experimental results on real-world test datasets demonstrate that the proposed hybrid model significantly outperforms traditional physical models. Specifically, it achieves an MAPE of 0.0156 and a R² of 0.9867, indicating high predictive accuracy. The model not only achieves superior prediction accuracy but also preserves physical interpretability, making it a promising solution for intelligent control in industrial mixing systems. Full article

The success of current entity alignment (EA) tasks largely depends on the supervision information provided by labeled data. Considering the cost of labeled data, most supervised methods are challenging to apply in practical scenarios. Therefore, an increasing number of works based on contrastive learning, active learning, or other deep learning techniques have been developed, to solve the performance bottleneck caused by the lack of labeled data. However, existing unsupervised EA methods still face certain limitations; either their modeling complexity is high or they fail to balance the effectiveness and practicality of alignment. To overcome these issues, we propose a learnable convolutional attention network for unsupervised entity alignment, named LCA-UEA. Specifically, LCA-UEA performs convolution operations before the attention mechanism, ensuring the acquisition of structural information and avoiding the superposition of redundant information. Then, to efficiently filter out invalid neighborhood information of aligned entities, LCA-UEA designs a relation structure reconstruction method based on potential matching relations, thereby enhancing the usability and scalability of the EA method. Notably, a similarity function based on consistency is proposed to better measure the similarity of candidate entity pairs. Finally, we conducted extensive experiments on three datasets of different sizes and types (cross-lingual and monolingual) to verify the superiority of LCA-UEA. Experimental results demonstrate that LCA-UEA significantly improved alignment accuracy, outperforming 25 supervised or unsupervised methods, and improving by 6.4% in Hits@1 over the best baseline in the best case. Full article

Background/Objectives: Dementia is a leading cause of cognitive decline, with significant challenges for early detection and timely intervention. The lack of effective, user-centred technologies further limits clinical response, particularly in underserved areas. This study aimed to develop and describe a co-design process for creating a Diagnostic and Statistical Manual of Mental Disorders (DSM-5)-compliant, AI-powered Smart Assistant (SmartApp) to monitor neurocognitive decline, while ensuring accessibility, clinical relevance, and responsible AI integration. Methods: A co-design framework was applied using a novel combination of Agile principles and the Double Diamond Model (DDM). More than twenty iterative Scrum sprints were conducted, involving key stakeholders such as clinicians (psychiatrist, psychologist, physician), designers, students, and academic researchers. Prototype testing and design workshops were organised to gather structured feedback. Feedback was systematically incorporated into subsequent iterations to refine functionality, usability, and clinical applicability. Results: The iterative process resulted in a SmartApp that integrates a DSM-5-based screening tool with 24 items across key cognitive domains. Key features include longitudinal tracking of cognitive performance, comparative visual graphs, predictive analytics using a regression-based machine learning module, and adaptive user interfaces. Workshop participants reported high satisfaction with features such as simplified navigation, notification reminders, and clinician-focused reporting modules. Conclusions: The findings suggest that combining co-design methods with Agile/DDM frameworks provides an effective pathway for developing AI-powered clinical tools as per responsible AI standards. The SmartApp offers a clinically relevant, user-friendly platform for dementia screening and monitoring, with potential to support vulnerable populations through scalable, responsible digital health solutions. Full article

Accurate color measurement is crucial for ensuring reliable sensing performance in vision-based applications. However, existing color measurement methods suffer from illumination variability, operational complexity, and perceptual subjectivity. In this study, dental color measurement, with its strict perceptual and spectral fidelity demands, is adopted to validate the proposed method. Using self-made resin-permeated ceramic teeth, this study proposes a deep-learned end-to-end spectral reflectance prediction framework to achieve snapshot teeth spectral reflectance from RGB images under complex light sources in the fundamental spectral domain through the construction of a physically interpretable network that enables physically informed feature fusion. A dual-attention modular-information fusion neural network is developed to recover the spectral reflectance directly from the RGB image for natural teeth and ceramics across multiple scenarios. A dataset containing 4000 RGB–hyperspectral image pairs is built from a self-designed optical system with complex illumination conditions. Results confirm that the proposed framework demonstrates effective performance in predicting teeth spectral reflectance with an MSE of 0.0024 and an SSIM of 0.8724. This method achieves high-accuracy color measurement while avoiding the color mismatch caused by metamerism, which empowers various advanced applications including optical property characterization, 3D surface reconstruction, and computer-aided restorative design. Full article

Grassland aboveground biomass (AGB) serves as a critical indicator of ecosystem productivity and carbon cycling, playing a pivotal role in ecosystem functioning. The advances in hyperspectral and terrestrial Light Detection and Ranging (LiDAR) data have provided new opportunities for grassland AGB monitoring, but current research remains predominantly focused on data-driven machine learning models. The black-box nature of such approaches resulted in a lack of clear interpretation regarding the coupling relationships between these two data types in grassland AGB estimation. For grassland aboveground fresh biomass, the theoretical estimation can be decomposed into either the product of planar density (PD) and plot area or the product of stereoscopic density (SD) and grassland community volume. Based on this theory, our study developed a semi-mechanistic remote sensing model for grassland AGB estimation by integrating hyperspectral-derived biomass density with extracted structural parameters from terrestrial LiDAR. Initially, we built hyperspectral estimation models for both PD and SD of grassland fresh AGB using PLSR. Subsequently, by integrating the inversion results with grassland quadrat area and community volume measurements, respectively, we achieved quadrat-scale remote sensing estimation of grassland AGB. Finally, we conducted comparative accuracy assessments of both methods across different phenological stages to evaluate their performance differences. Our results demonstrated that SD, which incorporated structural features, could be more precisely estimated (R² = 0.90, nRMSE = 7.92%, Bias% = 0.01%) based on hyperspectral data compared to PD (R² = 0.79, nRMSE = 10.19%, Bias% = −7.25%), with significant differences observed in their respective responsive spectral bands. PD showed greater sensitivity to shortwave infrared regions, while SD exhibited stronger associations with visible, red-edge, and near-infrared bands. Although both methods achieved comparable overall AGB estimation accuracy (PD-based: R² = 0.79, nRMSE = 10.19%, Bias% = −7.25%; SD-based: R² = 0.82, nRMSE = 10.58%, Bias% = 1.86%), the SD-based approach effectively mitigated the underestimation of high biomass values caused by spectral saturation effects and also demonstrated superior and more stable performance across different growth periods (R² > 0.6). This work provided concrete physical meaning to the integration of hyperspectral and LiDAR data for grassland AGB monitoring and further suggested the potential of multi-source remote sensing data fusion in estimating grassland AGB. The findings offered theoretical foundations for developing large-scale grassland AGB monitoring models using airborne and spaceborne remote sensing platforms. Full article

To improve the tracking accuracy and the adaptability of intelligent vehicles in various road conditions, an adaptive model predictive controller combining reinforcement learning is proposed in this paper. Firstly, to solve the problem of control accuracy decline caused by a fixed prediction time domain, a low-computational-cost adaptive prediction horizon strategy based on a two-dimensional Gaussian function is designed to realize the real-time adjustment of prediction time domain change with vehicle speed and road curvature. Secondly, to address the problem of tracking stability reduction under complex road conditions, the Deep Q-Network (DQN) algorithm is used to adjust the weight matrix of the Model Predictive Control (MPC) algorithm; then, the convergence speed and control effectiveness of the tracking controller are improved. Finally, hardware-in-the-loop tests and real vehicle tests are conducted. The results show that the proposed adaptive predictive horizon controller (DQN-AP-MPC) solves the problem of poor control performance caused by fixed predictive time domain and fixed weight matrix values, significantly improving the tracking accuracy of intelligent vehicles under different road conditions. Especially under variable curvature and high-speed conditions, the proposed controller reduces the maximum lateral error by 76.81% compared to the unimproved MPC controller, and reduces the average absolute error by 64.44%. The proposed controller has a faster convergence speed and better trajectory tracking performance when tested on variable curvature road conditions and double lane roads. Full article

Extracting road network information from satellite remote sensing images is an effective method of dealing with dynamic changes in road networks. At present, the use of deep learning methods to automatically segment road networks from remote sensing images has become mainstream. However, existing methods often produce fragmented extraction results. This is usually caused by insufficient feature extraction and occlusion. In order to solve these problems, we propose an enhanced feature extraction and multi-branch occlusion discrimination network (EFMOD-Net) based on an encoder–decoder architecture. Firstly, a multi-directional feature extraction (MFE) module was proposed as the input for the network, which utilizes multi-directional strip convolution for feature extraction to better capture the linear features of the road. Subsequently, an enhanced feature extraction (EFE) module was designed to enhance the performance of the model in the feature extraction stage by using a dual-branch structure. The proposed multi-branch occlusion discrimination (MOD) module combines the attention mechanism and strip convolution to learn the topological relationship between pixels, enhance the network’s detection of occlusion and complex backgrounds, and reduce the generation of road debris. On the public dataset, the proposed method is compared with other SOTA methods. The experimental results show that the network designed in this paper achieves an IoU of 64.73 and 63.58 on the DeepGlobe and CHN6-CUG datasets, respectively, which is 1.66% and 1.84% higher than the IoU of performance-based methods. The proposed method combines multi-directional bar convolution and a multi-branch structure for road extraction, which provides a new idea for linear object segmentation in complex backgrounds that could be applied directly to urban renewal, disaster assessment, and other application scenarios. Full article

Physically simulated attack experiments were conducted using LED lights of different colors, the You Look Only Once (YOLO) v5 model, and the German Traffic Sign Recognition Benchmark (GTSRB) dataset. We attacked and interfered with the traffic sign detection model and tested the model’s recognition performance when it was interfered with by LED lights. The model’s accuracy in identifying objects was calculated with the interference. We conducted a series of experiments to test the interference effects of colored lighting. The attack with different colored lights caused a certain degree of interference to the machine learning model, which affected the self-driving vehicle’s ability to recognize traffic signs. It caused the self-driving system to fail to detect the existence of the traffic sign or commit recognition errors. To defend from this attack, we fed back the traffic signs into the training dataset and re-trained the machine learning model. This enabled the machine learning model to resist related attacks and avoid disturbance. Full article