Search Results (1,049)

The palm-vein recognition system has garnered attention as a biometric technology due to its resilience to external environmental factors, protection of personal privacy, and low risk of external exposure. However, with recent advancements in deep learning-based generative models for image synthesis, the quality and sophistication of fake images have improved, leading to an increased security threat from counterfeit images. In particular, palm-vein images acquired through near-infrared illumination exhibit low resolution and blurred characteristics, making it even more challenging to detect fake images. Furthermore, spoof detection specifically targeting palm-vein images has not been studied in detail. To address these challenges, this study proposes the Fourier-gated feature-fusion network (FGFNet) as a novel spoof detector for palm-vein recognition systems. The proposed network integrates masked fast Fourier transform, a map-based gated feature fusion block, and a fast Fourier convolution (FFC) attention block with global contrastive loss to effectively detect distortion patterns caused by generative models. These components enable the efficient extraction of critical information required to determine the authenticity of palm-vein images. In addition, fractal dimension estimation (FDE) was employed for two purposes in this study. In the spoof attack procedure, FDE was used to evaluate how closely the generated fake images approximate the structural complexity of real palm-vein images, confirming that the generative model produced highly realistic spoof samples. In the spoof detection procedure, the FDE results further demonstrated that the proposed FGFNet effectively distinguishes between real and fake images, validating its capability to capture subtle structural differences induced by generative manipulation. To evaluate the spoof detection performance of FGFNet, experiments were conducted using real palm-vein images from two publicly available palm-vein datasets—VERA Spoofing PalmVein (VERA dataset) and PLUSVein-contactless (PLUS dataset)—as well as fake palm-vein images generated based on these datasets using a cycle-consistent generative adversarial network. The results showed that, based on the average classification error rate, FGFNet achieved 0.3% and 0.3% on the VERA and PLUS datasets, respectively, demonstrating superior performance compared to existing state-of-the-art spoof detection methods. Full article

The aim of this study is to assess endothelial progenitor cells (EPCs) and circulating endothelial cells (CECs) at the time of type 1 diabetes (T1D) recognition concerning patients’ clinical state, remaining insulin secretion, and further partial remission (PR) occurrence. We recruited 45 children that were admitted to hospital due to newly diagnosed T1D (median age 10.8 yrs), and 20 healthy peers as a control group. EPC and CEC levels were measured at disease onset in PBMC isolated from whole peripheral blood with the use of flow cytometry. Clinical data regarding patients’ condition, C-peptide secretion, and further PR prevalence were analyzed. T1D-diagnosed patients presented higher EPC levels than the control group (p = 0.026), while no statistical differences in CEC levels and EPC/CEC ratio were observed. Considering only T1D patients, those with better clinical conditions presented lower EPCs (p = 0.021) and lower EPC/CEC ratios (p = 0.0002). Patients with C-peptide secretion within a normal range at disease onset presented lower EPC/CEC ratios (p = 0.027). Higher levels of EPCs were observed more frequently in patients with higher glucose, decreased fasting C-peptide, and lower stimulated C-peptide (all p < 0.05). The presence of DKA was related to higher EPC/CEC ratios (p = 0.034). Significantly higher levels of CECs were observed in patients who presented partial remission of the disease at 6 months after diagnosis (p = 0.03) only. In the study group, positive correlations of CECs with age, BMI at onset, and BMI in following years were observed. EPC/CEC ratios correlated positively with glucose levels at hospital admission and negatively with age, BMI, pH, and stimulated C-peptide level. We reveal a new potential for the application of EPCs and CECs as biomarkers, reflecting both endothelial injury and reconstruction processes in children with T1D. There is a need for further research in order to reduce cardiovascular risk in children with T1D. Full article

With the increasing sophistication of network attacks, machine learning (ML)-based methods have showcased promising performance in attack detection. However, ML-based methods often suffer from high false rates when tackling encrypted malicious traffic. To break through these bottlenecks, we propose EFTransformer, an encrypted flow transformer framework which inherits semantic perception and multi-scale feature fusion, can robustly and efficiently detect encrypted malicious traffic, and make up for the shortcomings of ML in the context of modeling ability and feature adequacy. EFTransformer introduces a channel-level extraction mechanism based on quintuples and a noise-aware clustering strategy to enhance the recognition ability of traffic patterns; adopts a dual-channel embedding method, using Word2Vec and FastText to capture global semantics and subword-level changes; and uses a Transformer-based classifier and attention pooling module to achieve dynamic feature-weighted fusion, thereby improving the robustness and accuracy of malicious traffic detection. Our systematic experiments on the ISCX2012 dataset demonstrate that EFTransformer achieves the best detection performance, with an accuracy of up to 95.26%, a false positive rate (FPR) of 6.19%, and a false negative rate (FNR) of only 5.85%. These results show that EFTransformer achieves high detection performance against encrypted malicious traffic. Full article

With the advancement of information technology, human activity recognition (HAR) has been widely applied in fields such as intelligent surveillance, health monitoring, and human–computer interaction. As a crucial component of HAR, facial recognition plays a key role, especially in vision-based activity recognition. However, current facial recognition models on the market perform poorly in handling blurry images and dynamic scenarios, limiting their effectiveness in real-world HAR applications. This study aims to construct a fast and accurate facial recognition model based on novel adversarial learning and deblurring theory to enhance its performance in human activity recognition. The model employs a generative adversarial network (GAN) as the core algorithm, optimizing its generation and recognition modules by decomposing the global loss function and incorporating a feature pyramid, thereby solving the balance challenge in GAN training. Additionally, deblurring techniques are introduced to improve the model’s ability to handle blurry and dynamic images. Experimental results show that the proposed model achieves high accuracy and recall rates across multiple facial recognition datasets, with an average recall rate of 87.40% and accuracy rates of 81.06% and 79.77% on the YTF, IMDB-WIKI, and WiderFace datasets, respectively. These findings confirm that the model effectively addresses the challenges of recognizing faces in dynamic and blurry conditions in human activity recognition, demonstrating significant application potential. Full article

In this paper, screen-printed ion-selective electrodes combined with single-walled carbon nanotubes (SWCNTs) and gold nanoparticles (AuNPs) were used to rapidly and accurately measure serum Ca²⁺ concentration. Due to the susceptibility of cows to hypocalcemia after delivery, this disease can affect the health of cows and reduce milk production. Therefore, the development of an economical and swift detection method holds paramount importance for facilitating early diagnosis and subsequent treatment. In this study, by combining the high electrical conductivity and large surface area of SWCNTs with the strong catalytic activity of AuNPs, a SWCNTs/AuNPs composite with high sensitivity and good stability was prepared, achieving efficient selective recognition and signal conversion of Ca²⁺. The experimental results indicate that the screen-printed electrode modified with SWCNTs/AuNPs exhibited excellent performance in the determination of Ca²⁺ concentration. Its linear response range is 10^−5.5–10⁻¹ M, covering the normal and pathological concentration range of Ca²⁺ in cow blood, and the detection limit is far below the clinical detection requirements. In addition, the electrode also has good anti-interference ability and fast response time (about 15 s), showing good performance in the range of 5–45 °C. In practical applications, the combination of the electrode and portable detection equipment can realize the field rapid determination of cow blood Ca²⁺ concentration. This method is easy to operate, cost-effective, and easy to promote, providing strong technical support for the health management of dairy farms. Full article

Every day humans interact with smartphones that have embedded sensors that enable the tracking of changing physical activities of the device owner. However, several problems arise with the recognition of multiple activities (such as walking, sitting, running, and other) on smartphones. Firstly, most of the devices do not recognize some activities well, such as walking upstairs or downstairs. Secondly, recognition algorithms are embedded into smartphone software and are static, unless updated. In this case, a recognition algorithm must be re-trained with training data of a specific size. Thus, an adaptive (also known as, online or incremental) learning algorithm would be useful in this situation. In this work, an adaptive learning and classification algorithm based on hidden Markov models (HMMs) is applied to human activity recognition, and an architecture model for smartphones is proposed. To create a self-learning method, a technique that involves building an incremental algorithm in a maximal likelihood framework has been developed. The adaptive algorithms created enable fast self-learning of the model parameters without requiring the device to store data obtained from sensors. It also does not require sending gathered data to a server over the network for additional processing, making them autonomous and independent from outside systems. Experiments involving the modeling of various activities as separate HMMs with different numbers of states, as well as modeling several activities connected to one HMM, were performed. A public dataset called the Activity Recognition Dataset was considered for this study. To generalize the results, different performance metrics were used in the validation of the proposed algorithm. Full article

Proper nutrition is a fundamental aspect to maintaining overall health and well-being, influencing both physical and social aspects of human life; an unbalanced or inadequate diet can lead to various nutritional deficiencies and chronic health conditions. In today’s fast-paced world, monitoring nutritional intake has become increasingly important, particularly for those with specific dietary needs. While smartphone-based applications using image recognition have simplified food tracking, they still rely heavily on user interaction and raise concerns about practicality and privacy. To address these limitations, this paper proposes a novel, compact spectroscopic sensing platform for automatic beverage recognition. The system utilizes the AS7265x commercial sensor to capture the spectral signature of beverages, combined with a K-Nearest Neighbors (KNN) machine learning algorithm for classification. The approach is designed for integration into everyday objects, such as smart glasses or cups, offering a noninvasive and user-friendly alternative to manual tracking. Through optimization of both the sensor configuration and KNN parameters, we identified a reduced set of four wavelengths that achieves over 96% classification accuracy across a diverse range of common beverages. This demonstrates the potential for embedding accurate, low-power, and cost-efficient sensors into Internet of Things (IoT) devices for real-time nutritional monitoring, reducing the need for user input while enhancing accessibility and usability. Full article

Fluorescent chemosensors are increasingly becoming relevant in recognition chemistry due to their sensitivity, selectivity, fast response time, real-time detection capability, and low cost. Boronic acids have been reported for the recognition of mycolactone, the cytotoxin responsible for tissue damage in Buruli ulcer disease. A library of fluorescent arylboronic acid chemosensors with various signaling moieties with certain beneficial photophysical characteristics (i.e., aminoacridine, aminoquinoline, azo, BODIPY, coumarin, fluorescein, and rhodamine variants) and a recognition moiety (i.e., boronic acid unit) were rationally designed and synthesised using combinatorial approaches, purified, and fully characterised using a set of complementary spectrometric and spectroscopic techniques such as NMR, LC-MS, FT-IR, and X-ray crystallography. In addition, a complete set of basic photophysical quantities such as absorption maxima (λ_abs^max), emission maxima (λ_em^max), Stokes shift (∆λ), molar extinction coefficient (ε), fluorescence quantum yield (Φ_F), and brightness were determined using UV-vis absorption and fluorescence emission spectroscopy techniques. The synthesised arylboronic acid chemosensors were investigated as chemosensors for mycolactone detection using the fluorescent-thin layer chromatography (f-TLC) method. Compound 7 (with a coumarin core) emerged the best (λ_abs^max = 456 nm, λ_em^max = 590 nm, ∆λ = 134 nm, ε = 52816 M⁻¹cm⁻¹, Φ_F = 0.78, and brightness = 41,197 M⁻¹cm⁻¹). Full article

Deep learning (DL) has shown great capability in remote sensing and automatic target recognition (ATR). However, huge computational costs and power consumption are challenging the development of current DL methods. Optical neural networks have recently been proposed to provide a new mode to replace artificial neural networks. Here, we develop a residual optronic convolutional neural network (res-OPCNN) for synthetic aperture radar (SAR) recognition tasks. We implement almost all computational operations in optics and significantly decrease the network computational costs. Compared with digital DL methods, res-OPCNN offers ultra-fast speed, low computation complexity, and low power consumption. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate the lightweight nature of the optronic method and its feasibility for SAR target recognition. Full article

The rapid urbanization and technological advancements in the United Arab Emirates (UAE) have placed its modern architectural heritage from the 1970s and 1980s at increasing risk of being unrecognized and lost, particularly in Dubai following the discovery of oil. This research addresses the critical need for the documentation and heritage representation of Dubai’s modern heritage, a city undergoing rapid transformation within a globalized urban landscape. Focusing on the Nasser Rashid Lootah Building (Toyota Building), an iconic early 1970s residential high-rise representing the modern architecture of Dubai and a significant milestone in its architectural history, this study explores a replicable and cost-effective approach to digitally document and conserve urban heritage under threat. The existing building was meticulously documented and analyzed to highlight its enduring value within the fast-changing urban fabric. Through the innovative combination of drone photography, ground-based photography, and HBIM, a high-resolution 3D model and a semantically organized HBIM prototype were generated. This research demonstrates a replicable measure for identifying architectural values, understanding modernist design typologies, and raising local community awareness about Dubai’s modern heritage. Ultimately, this study contributes toward developing recognition criteria and guiding efforts in documenting modern high-rise buildings as vital heritage worthy of recognition, documentation, and future conservation in the UAE. Full article

Feature matching is crucial in image recognition. However, blurring caused by illumination changes often leads to deviations in local appearance-based similarity, resulting in ambiguous or false matches—an enduring challenge in computer vision. To address this issue, this paper proposes a method named MultS-ORB (Multistage Oriented FAST and Rotated BRIEF). The proposed method preserves all the advantages of the traditional ORB algorithm while significantly improving feature matching accuracy under illumination-induced blurring. Specifically, it first generates initial feature matching pairs using KNN (K-Nearest Neighbors) based on descriptor similarity in the Hamming space. Then, by introducing a local motion smoothness constraint, GMS (Grid-Based Motion Statistics) is applied to filter and optimize the matches, effectively reducing the interference caused by blurring. Afterward, the PROSAC (Progressive Sampling Consensus) algorithm is employed to further eliminate false correspondences resulting from illumination changes. This multistage strategy yields more accurate and reliable feature matches. Experimental results demonstrate that for blurred images affected by illumination changes, the proposed method improves matching accuracy by an average of 75%, reduces average error by 33.06%, and decreases RMSE (Root Mean Square Error) by 35.86% compared to the traditional ORB algorithm. Full article

Background: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive dysfunction and working memory impairment, with early hippocampal damage being a prominent feature. Transcranial magneto-acoustic stimulation (TMAS) has been shown to target specific brain regions for neuroregulation. Methods: This study investigated the effects of TMAS on cognitive function, working memory, and hippocampal CA3 neural rhythms in AD rats by specifically stimulating the hippocampal region. Results: The novel object recognition test and T-maze test were employed to assess behavioral performance, while time-frequency analyses were conducted to evaluate memory-related activity, neural synchronization, and cross-frequency phase-amplitude coupling. TMAS significantly improved cognitive and working memory deficits in AD rats, enhancing long-term memory performance. Additionally, the abnormal energy levels observed in the θ and γ rhythm power spectra of the CA3 region were markedly restored, suggesting the recovery of normal neural function. This improvement was accompanied by a partial resurgence of neural activity, indicating enhanced inter-neuronal communication. Furthermore, the previously damaged coupling between the θ-fast γ and θ-slow γ rhythms was successfully improved, resulting in a notable enhancement of synchronized activity. Conclusions: These findings suggest that TMAS effectively alleviates cognitive and working memory impairments in AD rats and may provide experimental support for developing new treatments for AD. Full article

This paper explores cleaner and techno-economically viable solutions to provide electricity, heat, and cooling using green hydrogen (H₂) and green ammonia (NH₃) across the entire decarbonized value chain. We propose integrating a 100% hydrogen-fueled internal combustion engine (e.g., Jenbacher JMS 420) as a stationary backup solution and comparing its performance with other backup technologies. While electrochemical storage systems, or battery energy storage systems (BESSs), offer fast and reliable short-term energy buffering, they lack flexibility in relocation and typically involve higher costs for extended backup durations. Through five case studies, we highlight that renewable-based energy supply requires additional capacity to bridge longer periods of undersupply. Our results indicate that, for cost reasons, battery–electric solutions alone are not economically feasible for long-term backup. Instead, a more effective system combines both battery and hydrogen storage, where batteries address daily fluctuations and hydrogen engines handle seasonal surpluses. Despite lower overall efficiency, gas engines offer favorable investment and operating costs in backup applications with low annual operating hours. Furthermore, the inherent fuel flexibility of combustion engines eventually will allow green ammonia-based backup systems, particularly as advancements in small-scale thermal cracking become commercially available. Future studies will address CO₂ credit recognition, carbon taxes, and regulatory constraints in developing more effective dispatch and master-planning solutions. Full article

Pupil detection is a key technology in fields such as human–computer interaction, fatigue driving detection, and medical diagnosis. Existing pupil detection algorithms still face challenges in maintaining robustness under variable lighting conditions and occlusion scenarios. In this paper, we propose a novel pupil detection algorithm, ViMSA, based on the ViM model. This algorithm introduces weighted feature fusion, aiming to enable the model to adaptively learn the contribution of different feature patches to the pupil detection results; combines ViM with the MSA (multi-head self-attention) mechanism), aiming to integrate global features and improve the accuracy and robustness of pupil detection; and uses FFT (Fast Fourier Transform) to convert the time-domain vector outer product in MSA into a frequency–domain dot product, in order to reduce the computational complexity of the model and improve the detection efficiency of the model. ViMSA was trained and tested on nearly 135,000 pupil images from 30 different datasets, demonstrating exceptional generalization capability. The experimental results demonstrate that the proposed ViMSA achieves 99.6% detection accuracy at five pixels with an RMSE of 1.67 pixels and a processing speed exceeding 100 FPS, meeting real-time monitoring requirements for various applications including operation under variable and uneven lighting conditions, assistive technology (enabling communication with neuro-motor disorder patients through pupil recognition), computer gaming, and automotive industry applications (enhancing traffic safety by monitoring drivers’ cognitive states). Full article

To enhance pulsar candidate recognition performance and improve model generalization, this paper proposes the cross-feature hybrid associative prior network (CFHAPNet). CFHAPNet incorporates a novel architecture and strategies to integrate multi-class heterogeneous feature subimages from each candidate into multi-channel data processing. By implementing cross-attention mechanisms and other enhancements for multi-view feature interactions, the model significantly strengthens its ability to capture fine-grained image texture details and weak prior semantic information. Through comparative analysis of feature weight similarity between subimages and average fusion weights, CFHAPNet efficiently identifies and filters genuine pulsar signals from candidate images collected across astronomical observatories. Additionally, refinements to the original loss function enhance convergence, further improving recognition accuracy and stability. To validate CFHAPNet’s efficacy, we compare its performance against several state-of-the-art methods on diverse datasets. The results demonstrate that under similar data scales, our approach achieves superior recognition performance. Notably, on the FAST dataset, the accuracy, recall, and F1-score reach 97.5%, 98.4%, and 98.0%, respectively. Ablation studies further reveal that the proposed enhancements improve overall recognition performance by approximately 5.6% compared to the original architecture, achieving an optimal balance between recognition precision and computational efficiency. These improvements make CFHAPNet a strong candidate for future large-scale pulsar surveys using new sensor systems. Full article