Fast Detection Research Articles

Application of machine learning for detecting and tracking turbulent structures in plasma fusion devices using ultra fast imaging.

This study explores the application of machine learning techniques for detecting and tracking plasma filaments around the boundary of magnetically confined tokamak plasmas. Plasma filaments, also called blobs, are responsible for enhanced turbulent transport across magnetic field lines, and their accurate characterization is crucial for optimizing the performance of magnetic fusion devices. We present a novel approach that combines machine learning methods applied to data obtained from ultra-fast cameras, including YOLO (You Only Look Once) for object detection, semantic segmentation, and specific tracking methods. This approach enables fast and accurate detection and tracking of filaments while overcoming the limitations of conventional methods, which are time-consuming and prone to human subjectivity. A significant advance in our study lies in the development of a method for automatically labeling a large batch of data, which greatly facilitates the training of supervised machine learning algorithms. Using these techniques, we obtained promising results demonstrating a significant improvement over conventional tracking methods, achieving a detection accuracy of up to 98.8%, while reducing the inference time per frame by 15% to 31% compared to conventional Kalman filter tracking. These results open up new perspectives for investigating turbulent phenomena in tokamaks, and could have important implications for the development of controlled nuclear fusion.

Foundation models for fast, label-free detection of glioma infiltration.

A critical challenge in glioma treatment is detecting tumour infiltration during surgery to achieve safe maximal resection1-3. Unfortunately, safely resectable residual tumour is found in the majority of patients with glioma after surgery, causing early recurrence and decreased survival4-6. Here we present FastGlioma, a visual foundation model for fast (<10 s) and accurate detection of glioma infiltration in fresh, unprocessed surgical tissue. FastGlioma was pretrained using large-scale self-supervision (around 4 million images) on rapid, label-free optical microscopy, and fine-tuned to output a normalized score that indicates the degree of tumour infiltration within whole-slide optical images. In a prospective, multicentre, international testing cohort of patients with diffuse glioma (n = 220), FastGlioma was able to detect and quantify the degree of tumour infiltration with an average area under the receiver operating characteristic curve of 92.1 ± 0.9%. FastGlioma outperformed image-guided and fluorescence-guided adjuncts for detecting tumour infiltration during surgery by a wide margin in a head-to-head, prospective study (n = 129). The performance of FastGlioma remained high across diverse patient demographics, medical centres and diffuse glioma molecular subtypes as defined by the World Health Organization. FastGlioma shows zero-shot generalization to other adult and paediatric brain tumour diagnoses, demonstrating the potential for our foundation model to be used as a general-purpose adjunct for guiding brain tumour surgeries. These findings represent the transformative potential of medical foundation models to unlock the role of artificial intelligence in the care of patients with cancer.

Comparison of CNN-Based Architectures for Detection of Different Object Classes

(1) Background: Detecting people and technical objects in various situations, such as natural disasters and warfare, is critical to search and rescue operations and the safety of civilians. A fast and accurate detection of people and equipment can significantly increase the effectiveness of search and rescue missions and provide timely assistance to people. Computer vision and deep learning technologies play a key role in detecting the required objects due to their ability to analyze big volumes of visual data in real-time. (2) Methods: The performance of the neural networks such as You Only Look Once (YOLO) v4-v8, Faster R-CNN, Single Shot MultiBox Detector (SSD), and EfficientDet has been analyzed using COCO2017, SARD, SeaDronesSee, and VisDrone2019 datasets. The main metrics for comparison were mAP, Precision, Recall, F1-Score, and the ability of the neural network to work in real-time. (3) Results: The most important metrics for evaluating the efficiency and performance of models for a given task are accuracy (mAP), F1-Score, and processing speed (FPS). These metrics allow us to evaluate both the accuracy of object recognition and the ability to use the models in real-world environments where high processing speed is important. (4) Conclusion: Although different neural networks perform better on certain types of metrics, YOLO outperforms them on all metrics, showing the best results of mAP-0.88, F1-0.88, and FPS-48, so the focus was on these models.

Antithermal-Quenching Near-Infrared Emitting Lu2SrAl4SiO12:Cr3+ Garnet-Type Phosphor for High-Resolution Nonvisual Imaging.

Near-infrared (NIR) light allows fast and nondestructive detection with deep penetration into biological tissues and is widely used in food inspection, biomedical imaging, night vision security, and other fields. Cr3+-doped NIR first region (NIR-I) phosphors have many interesting features that have attracted a lot of attention recently. However, practical issues, such as low photoluminescence quantum efficiency and poor thermal stability, need to be addressed. We synthesized Cr3+-doped Lu2SrAl4SiO12 garnet-type phosphors using a high-temperature solid-state reaction method. Under blue-light (@ 430 nm) excitation, the phosphors exhibited broadband NIR-I emission in the range of 600-1000 nm, with an emission peak at 710 nm. This system is unique, as the emission had multipeak sharp-line superposition and the Cr3+ ions were situated in a relatively strong crystal field environment, as opposed to a weak crystal field environment for other matrix. The optimal doping content of Cr3+ ions was 2 mol %, and its internal quantum efficiency was ∼76.8%. Surprisingly, this NIR phosphor showed an antithermal quenching effect, and the integrated luminescence intensity of NIR-I emission measured at 573 K was 206.3% of that measured at 303 K. We found that the antithermal quenching of NIR-I luminescence was caused by the extremely low thermal expansion coefficient and rigid structure of the Lu2SrAl4SiO12 matrix in the temperature range, as well as the weakening of electron-phonon coupling with increasing temperature. The optimized phosphor was packaged with a blue chip into a NIR phosphor-converted light-emitting diode device. The light source device showed an output power of 119.02 mW and an electro-optical conversion efficiency of 11.02% under a driving current of 300 mA. The application potential of this NIR phosphor was demonstrated in the field of high-resolution nondestructive imaging.

Fast and explainable outlier detection in geotechnical database

ABSTRACT Outlier detection is an important task in data-driven geotechnics. It is noted that many existing methods for outlier detection (e.g. Bayesian learning, neural networks) may pose computational challenge for conventional geotechnical practitioners. Towards this aspect, this study proposes a simple, fast, and explainable method for detecting outliers in geotechnical database. The principle of the method is that for a data point to be labelled as a potential outlier, the probability of observing a data point as extreme as that value should be low. To account for outliers in left-tail and right-tail, the skewness of the dataset is incorporated, and an indicator referred to as outlier score ( > 0 ) is assigned to each data point. The method also provides another indicator (referred to as dimensional outlier score) to identify which dimensions/soil properties contribute to the outlierness; hence, it is explainable. The method doesn't require any time-consuming learning or sampling procedures; hence, it is quite fast and practitioner-friendly. Multiple numerical examples are utilised to demonstrate the capability first. Finally, four publicly available geotechnical databases are utilised to demonstrate the outlier detection task. The results suggest that the outliers identified using the proposed method can be meaningful from a geotechnical point of view.

Rapid and sensitive whole cell E. coli detection using deep eutectic solvents/graphene oxide/gold nanoparticles field-effect transistor

Every year, millions of people suffer from gastrointestinal inflammation caused by E. coli. The increase of antibiotic-resistant strains and similar inflammatory and infectious syndromes symptoms have made rapid and sensitive diagnosis of this pathogen challenging. This study developed a Field-Effect Transistor based on deep eutectic solvents, graphene oxide, and gold nanoparticles (DES/GO/AuNPs-FET) to detect E. coli. Comparing the output current showed DES, which was a mixture of ethylene glycol and choline chloride, with ionic behavior, in addition to improving the electrical properties of GO, also led to the formation of AuNPs by self-assembly, which significantly increased the sensor's sensing performance. E. coli lipopolysaccharide aptamer immobilized on DES/GO/AuNPs-FET; capturing E. coli and changing the conformation caused changes in the charge carrier flow in the FET. This nanobiosensor detected E. coli in a completely selective manner in complex matrices like human blood serum. The excellent sensing performance of this nanobiosensor compared to other biosensors with a low detection limit (LOD = 3 CFU/ml), label-free, fast, and real-time detection showed that DES/GO/AuNPs-FET could be a reliable alternative to existing detection methods.

TtAgo-coupled-multiplex-digtal-RPA-CRISPR/Cas12a (TCMDC) for EGFR mutations detection

Epidermal Growth Factor Receptor (EGFR) is an important target for the early evaluation, treatment, and postoperative follow-up in non-small cell lung cancer (NSCLC). Current detection technologies suffer from extended detection time and high rate of false positive amplification. Therefore, the development of rapid, highly sensitive and specific detection methods is of great significance for improving the diagnosis and treatment of lung cancer. In this study, we proposed a fast and sensitive detection method termed Thermus thermophilus Argonaute (Ttago)-Coupled-Multiplex-digital-recombinase polymerase amplification (RPA)-Clustered regularly interspaced short palindromic repeats (CRISPR)/Cas12a (TCMDC) detection method, integrating EGFR mutation template enrichment. Based on the cleavage principle of TtAgo, the wild type (WT) template was enriched under the action of double-guide DNA. Two CRISPR RNAs, not restricted by protospacer adjacent motif (PAM) sites, were introduced to target EGFR genes. By combining RPA with CRISPR-Cas12a, we established a single-pot, ultra-sensitive (1 copy, 0.1 %), and visually detectable method for EGFR detection. We further verified the feasibility of this approach using clinical serum samples from lung cancer patients, achieving rapid (within 1 h) and visual detection of EGFR, thereby presenting a promising clinical tool for the detection of lung cancer.

LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement

In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly, we introduce C2f-GhostDynamicConv as a powerful tool. This module enhances feature extraction to represent safety helmet wearing features, aiming to improve the efficiency of computing resource utilization. Secondly, the Bi-directional Feature Pyramid (BiFPN) was employed to further enrich the feature information, integrating feature maps from various levels to achieve more comprehensive semantic information. Finally, to enhance the training speed of the model and achieve a more lightweight outcome, we introduce a novel lightweight asymmetric detection head (LADH-Head) to optimize the original YOLOv8-n’s detection head. Evaluations on the SWHD dataset confirm the effectiveness of the LG-YOLOv8 algorithm. Compared to the original YOLOv8-n algorithm, our approach achieves a mean Average Precision (mAP) of 94.1%, a 59.8% reduction in parameters, a 54.3% decrease in FLOPs, a 44.2% increase in FPS, and a 2.7 MB compression of the model size. Therefore, LG-YOLOv8 has high accuracy and fast detection speed for safety helmet detection, which realizes real-time accurate detection of safety helmets and an ideal lightweight effect.

Photonic sensor based on surface imprinted polymers for enhanced point-of-care diagnosis of bacterial urinary tract infections

Effective bacterial detection is crucial for health diagnostics, particularly for the detection of pathogenic species like Escherichia coli (E. coli), which is responsible for up to 90% of urinary tract infections (UTIs), is especially crucial. Current detection methods are time-consuming, often delaying diagnosis and treatment. This study introduces an innovative approach for rapid E. coli detection using porous silicon (PSi) substrates combined with Surface Imprinted Polymers (SIPs) for photoluminescence-based (PL-based) E. coli detection. The PSi/SIP substrates offer high sensitivity, selectivity, and a low limit of detection (LOD) without the need for natural recognition elements. These substrates, fabricated via metal-assisted chemical etching (MACE) and PDMS-based E. coli imprinting, demonstrate reliable repeatability and a fast detection. Real-time detection experiments in phosphate-buffered saline (PBS) and urine showed consistent stair-like quenching of the PL signal with increasing E. coli concentrations, achieving theoretical LODs of approximately 13 ± 2 CFU/mL in PBS and 17 ± 3 CFU/mL in urine. The substrates exhibited excellent selectivity, differentiating E. coli from other species such as Cronobacter sakazakii (C. sakazakii) and Listeria monocytogenes. The high sensitivity and reproducibility of PSi/SIP substrates, along with the ease of use and rapid detection capabilities of the resulting sensor, highlight the potential of this novel platform for point-of-care (PoC) applications in clinical diagnostics.

High-Resolution Melting PCR as a Fast and Simple Molecular Biology-Based Method for the Identification of Hypervirulent Clostridioides difficile Strains Directly in Stool Samples

Clostridioides difficile became one of the main causes of nosocomial infections in all clinical settings worldwide, especially among patients undergoing antibiotic therapy. The incidence and severity of C. difficile infections, from mild diarrhea to life-threatening pseudomembranous colitis, correlate with the spread of the hypervirulent binary toxin (CDT)-producing strains. The use of the real-time HRM-PCR method enables the identification of hypervirulent C. difficile strains directly in the diarrheal stool samples of patients suspected of being infected with this bacterium. For this purpose, the cdtA and cdtB genes encoding CDT subunits, as well as the species-specific gluD gene, were detected to identify the presence of this bacterium in the tested samples. The sensitivity, specificity, negative predictive value (NPV) and positive predictive value (PPV) of the established method were also assessed. The obtained results were compared with the results of eazyplex® C. difficile complete test (AmplexDiagnostics GmbH) based on the LAMP method, used in standard microbiological diagnostics. The values of the assessed diagnostic parameters for the detected genes ranged from 58.82% to 98.85%. The lowest value (58.82%) was obtained for the PPV of cdtB and the highest (98.85%) for the NPV of this gene. The real-time HRM-PCR method enables fast and simple detection of the investigated genes of hypervirulent C. difficile strains and, after careful optimization, may demonstrate high potential for usefulness in routine microbiological diagnostics.

A Label-Free Electrochemical Detection of Cadmium Ions Using Aptamer-Based Biosensor

Cadmium is considered one of the most toxic pollutants that can be found in water as well as in soil, which might accumulate in living organisms causing severe effects such as skeletal, cardiovascular, and respiratory diseases. Hence, it is necessary to develop methods allowing for sensitive and fast detection as well as portability. One possibility is the application of biosensors containing aptamer strands as receptor layer selective towards cadmium ions. Here, we present studies on the utilization of DNA aptamer strand for fabrication of sensing layer toward cadmium ions on gold disk macroelectrodes. It is shown that proposed aptasensor enables Cd2+ ions detection in the range from 10 to 50 nM with LOD of 9.5 nM and exhibits high selectivity towards cadmium cations with a response at least two times higher than that for interfering ions. Moreover, studies on the stability revealed that sensing layer preserved its binding properties after storage and allowed for cadmium ions detection in the range from 10 to 50 nM and the aptamer sensing layer could be regenerated and applied for another set of analysis of cadmium ions.

PV-YOLO: A lightweight pedestrian and vehicle detection model based on improved YOLOv8

With the frequent occurrence of urban traffic accidents, fast and accurate detection of pedestrian and vehicle targets has become one of the key technologies for intelligent assisted driving systems. To meet the efficiency and lightweight requirements of smart devices, this paper proposes a lightweight pedestrian and vehicle detection model based on the YOLOv8n model, named PV-YOLO. In the proposed model, receptive-field attention convolution (RFAConv) serves as the backbone network because of its target feature extraction ability, and the neck utilizes the bidirectional feature pyramid network (BiFPN) instead of the original path aggregation network (PANet) to simplify the feature fusion process. Moreover, a lightweight detection head is introduced to reduce the computational burden and improve the overall detection accuracy. In addition, a small target detection layer is designed to improve the accuracy for small distant targets. Finally, to reduce the computational burden further, the lightweight C2f module is utilized to compress the model. The experimental results on the BDD100K and KITTI datasets demonstrate that the proposed PV-YOLO can achieve higher detection accuracy than YOLOv8n and other baseline methods with less model complexity.

Green apple detection method based on multi-dimensional feature extraction network model and Transformer module

To enhance fast and accurate detection of pollution-free green apples for food safety, this paper uses the DETR network as a framework to propose a new method for pollution-free green apple detection based on a multi-dimensional feature extraction network and Transformer module. Firstly, an improved DETR network main feature extraction module adopts the ResNet18 network and replaces some residual layers with deformable convolutions (DCNv2), enabling the model to better adapt to pollution-free fruit changes at different scales and angles, while eliminating the impact of microbial contamination on fruit testing; Subsequently, the extended spatial pyramid pooling model (DSPP) and multi-scale residual aggregation module (FRAM) are integrated, which help reduce feature noise and minimize the loss of underlying features during the feature extraction process. The fusion of the two modules enhances the model’s ability to detect objects of different scales, thereby improving the accuracy of near-color fruit detection; At the same time, in order to solve the problems of slow convergence speed and large calculation amount of the basic network model, the convergence speed of the overall network model is improved by replacing the attention mechanism of Transformer. Experimental results show that compared with the original DETR model, the proposed algorithm has improved in AP, AP50 and AP75 indicators, especially in the AP50 indicator, which has the most obvious improvement reaching a detection accuracy of 97.12%. In the meantime, the trained network model is deployed on the picking robot. Compared with the original DETR network model, its average detection accuracy is as high as 96.58%, and the detection speed is increased by about 51%. Mixed sample detection tests were carried out before and after the model deployment, and the detection rate of the proposed method for non-polluted fruits reached more than 0.95. enabling the picking robot to efficiently complete the task of picking green apples. The test results show that the algorithm proposed in this article exhibits great potential in the task of detecting pollution-free near-color fruits by the picking robot. It ensures pollution-free fruit picking and the application of AI in food safety.

Strand displacement amplification combining photothermal-colorimetric dual mode test strip for ultra-sensitive detection of patulin

Patulin (PAT) is a fungal toxin often found in fruit and juice products. The sensitive and fast detection of PAT can help the control of PAT-induced health risk. However, the lack of efficient and stable antibody for PAT hindered the advancement of its test strips. Here, we constructed a nucleic acid-based lateral flow test strip (NALFTS) and used photothermal-colorimetric dual mode for the detection of PAT. The binding of PAT in samples to the aptamer on magnetic separation probe MNPs-Apt@cDNA induced the release of cDNA competitively. Subsequently, cDNA initiates strand displacement amplification (SDA), generating numerous single-strand DNA (ssDNA). These ssDNA molecules were analyzed by a test strip with photothermal-colorimetric dual signal. The developed method demonstrated a limit of detection (LOD) of 5 pg mL−1 and a quantitative range of 0.01 ∼ 320 ng mL−1 in photothermal mode, and a LOD of 0.1 ng mL−1 and a quantitative range of 0.1 ∼ 40 ng mL−1 in colorimetric mode. This SDA-NALFTS offered dual signals corroborating each other to provide more reliable results for rapid screening or accurate monitoring of PAT in juice.

Novel multi-layered MXene as laser desorption ionization mass spectrometry matrix for rapid detection of small biomolecules

Five two-dimensional multi-layered MXenes namely MO2C, Ti2C, V2C, Nb2C and Ta2C were synthesized by a one-step exfoliation process and evaluated as laser desorption ionization mass spectrometry (LDI-MS) matrices for fast detection of small biomolecules for the first time. Among them, Nb2C exhibited the best performance due to its high carrier mobility, strong photo-induced charge transfer resonance and good UV absorption ability. A simple, universal and efficient LDI-MS platform was established for small biomolecule analysis based on the Nb2C matrix. Key factors that affect LDI-MS efficacy were investigated and the established method demonstrated ultraclean MS background, high sensitivity with detection limits low to fmol level and good reproducibility. The Nb2C-based LDI-MS platform was successfully applied in the rapid determination of 13 amino acids (AAs) in human serum and 3 AAs, as potential biomarkers, were found to be significantly down-regulated in major depressive disorder patients. This work proved the feasibility of Nb2C MXene as an LDI-MS matrix and provided a promising and universal platform for the rapid detection of small molecules in biomedical research.

Novel quinoline-based chemosensor as specific fluorescence sensing of copper ions in cancer cells and for organelle-specific imaging application

This work reports a simple synthesis of a quinoline-based organic molecule, (E)-N′-((6-methoxy-2-oxo-1,2-dihydroquinolin-3-yl)methylene) picolinohydrazide (PHMQ), and its ability to distinguish Cu2+ ion. Through the use of spectroscopic and photometric titration techniques, PHMQ’s selectivity toward various cations and anions was examined. In just two minutes, PHMQ showed fast detection of Cu2+ ions, and clear spectral fluctuations proposed persistent PHMQ-Cu2+ complex formation. The calculated emission quenching constant (1.46 × 105 L/mol) and binding constant (1.25 × 104 L/mol) values suggested that strong emission quenching occurs between the PHMQ and Cu2+ ions. A linear reduction in fluorescence response was noted for Cu2+ ions concentrations between 2–26 μM, with a detection limit of 43.4 nM. Job’s plot, ESI-mass, NMR titration experiments, and density functional theory (DFT) simulations established a 1:1 stoichiometry for the PHMQ-Cu2+ complex. Additionally, PHMQ was efficaciously utilized to quantify Cu2+ ions in drinking and tap water samples and HeLa cells, illustrating durable cellular penetrability and a fluorescence ’Turn-Off’ response to Cu2+ ions. This sensor also established usefulness in mitochondrial-targeted imaging. For the detection of Cu2+ ions in biological and environmental environments, PHMQ is a promising detector due to its high sensitivity, selectivity, and quick response.

Dynamic feature and context enhancement network for faster detection of small objects

While traditional object detection methods have achieved significant success in recent years, their performance in detecting small objects in aerial remote sensing images remains unsatisfactory. Small objects often occupy only a few pixels, leading to a loss of fine-grained information. This paper proposes a dynamic feature and context enhancement network (DFCE) to address noise and pixel-level region weighting issues in small object detection. The DFCE network effectively detects small objects by dynamically selecting features within regions and establishing connections between local and global contextual information. The introduced dynamic multi-dimensional attention (DMA) module selects key information via a crossover mechanism and assigns different weights to highlight important features. Based on DMA, the regional feature processing (RFP) module and multi-dimensional pool transformer (MPT) module are developed to capture key information and contextual information, respectively. Experimental results demonstrate that the DFCE network improves average precision (AP) by 3.1%, 9%, and 2.2% on two remote sensing datasets and one conventional dataset, achieving an inference speed of 30 frames per second (FPS). Given these advancements, the DFCE model’s powerful key feature extraction and contextual association capabilities show strong potential for broader applications, including sign language recognition, defect detection in industrial settings, and more.

Transient analysis of a SIQS model with state capacities using a non-homogeneous Markov system

In this paper, a novel stochastic model is proposed to model the spread of a virus in epidemics. The model is based on a discrete-time non-homogeneous Markov system with state capacities. In order to study the distributions of the state sizes, recursive formulae for their factorial and mixed factorial moments were derived in matrix form. As a consequence, the probability mass function of each state size can be evaluated in the transient period. To avoid the computational complexity of the proposed algorithm, an alternative method for the computation of the state size distributions was recommended. The proposed Markovian approach was then tailored to the characteristics of a SIQS (susceptible-infected-quarantined-susceptible) epidemic scheme, which took into account external infections and the potential for secondary infections. This epidemic model is well-suited for describing infections in computer networks, where the quarantine capacity can be likened to the number of working people (IT professionals) available to restore an infected computer. We presented numerical examples and sensitivity analysis to illustrate the behavior and performance of the system under different scenarios and parameter values. We show that the state capacities and the infection rates have significant effects on the evolution and extinction of the epidemic. We note that the optimal number of employed technicians can be identified, aiming to keep the computer network functional. Higher internal infection rates significantly affect the sustainability of the computer network, while controlling external infections is not always feasible. On the other hand, faster detection rates and higher malware elimination rates will considerably increase the number of computers that remain operational in the long term. Consequently, the quality of services provided by IT technicians plays a crucial role in the system’s viability.

Au Nanoparticles-Trisbipyridine Ruthenium(II) Nanoaggregates as Signal-Amplifying SERS Tags for Immunoassay of cTnI.

Acute myocardial infarction (AMI) is one of the leading causes of human mortality worldwide. In the early stages of AMI, the patient's electrocardiogram (ECG) may not change, so the fast, sensitive, and accurate detection of the specific biomarker of cardiac troponin I (cTnI) is of great importance in the early diagnosis of AMI. In this work, for the first time, electrostatic nanoaggregates of negatively charged Au nanoparticles and positively charged trisbipyridine ruthenium(II) ions (i.e., (-)AuNPs|[Ru(bpy)3]2+ ENAs) as novel and signal-amplifying surface-enhanced Raman scattering (SERS) tags were synthesized in an easy and rapid (<3 min) way and applied in the highly sensitive, rapid detection of cTnI in human serum by being combined with an immunochromatographic test strip (ICTS). The synthesized (-)AuNPs|[Ru(bpy)3]2+ ENAs exhibited strong SERS activity due to the multiple Raman-active units (three bpy ligands) carried by each [Ru(bpy)3]2+ complex ion and abundant hotspots in each SERS tag. The developed (-)AuNPs|[Ru(bpy)3]2+ ENAs-based SERS-ICTS has been validated to be applicable in detection of cTnI in human serum with excellent sensing performances, such as fast testing (5 min) and a low detection limit (60 pg/mL). It is envisioned that the developed (-)AuNPs|[Ru(bpy)3]2+ ENAs-based SERS-ICTS sensor may have promising applications in point of care testing of various biomarkers in clinic. Additionally, this work may inspire the finding and the application of new types of Raman reporter molecules based on high valent metal-multi ligand coordination compounds like [Ru(bpy)3]2+.

YOLO with feature enhancement and its application in intelligent assembly

Object detection is the most important part in intelligent assembly tasks, accurate and fast detection for different targets can complete positioning and assembly tasks more automatically and efficiently. In this paper, a feature enhancement object detection model based on YOLO is proposed. Firstly, the expression ability of feature layer is enhanced through RFP (Recursive Feature Pyramid) structure. The ARSPP (Atrous Residual Spatial Pyramid Pooling) is proposed to have a further enhancement for the feature layers output by the backbone network, it improves the recognition performance for multi-scale targets of model by using different size of dilated convolution and residual connection. Finally, the contiguous pyramid features are fused and enhanced through the attention mechanism, the results are used for the input of next recursive or predictive output. The model proposed in this paper effectively improves the detection accuracy of YOLO, it has 3% MAP improvement in PASCAL VOC dataset. The validity and accuracy of the model are verified in the robot intelligent assembly recognition task.