Real-time Detection Research Articles

Discovery of anti-tumor agent targeted MetAP-2 using a special turn-on fluorescent probe

Methionine aminopeptidase 2 (MetAP-2) catalyzes the removal of methionine from the amino-terminus of proteins or peptides and is a known target for anti-tumor therapy. In this study, we developed an enzyme-activated fluorescent probe, DDAO-BMT, specifically for the real-time detection of endogenous MetAP-2. This probe enables the determination of extracellular MetAP-2 activity and visual monitoring of intracellular MetAP-2. Additionally, Sappan Lignum was identified as an active herbal medicine against MetAP-2, with brazilin identified as its key active constituent. Brazilin also exhibited a significant anti-tumor effect, including the inhibition on proliferation, migration, and invasion of tumor cells, and the preliminary mechanism of its activity against cancer has been elucidated. The use of this probe facilitates the monitoring of endogenous MetAP-2 in complex biological system, aiding in the discovery of novel active compounds for cancer treatment.

A cationic AIE luminutesogen TBPD2+-6C as a potential bacterial detection agent and bactericide for plants bacterium

The rise of plant bacterial pathogens poses a significant threat to the yield and quality of essential food crops and cash crops globally. Our research introduced a versatile cationic AIE fluorescent probe for detecting and eliminutesating plant bacteria. With its unique aggregation-induced emission property, TBPD2+-6C can effectively detect plant bacteria by causing a fluorescence quenching effect and enables bacterial imaging under green fluorescence channels. Additionally, TBPD2+-6C demonstrates outstanding antibacterial effectiveness, with EC50 values of 0.27, 3.86, 0.47, and 11.5 μg/mL against Xanthomonas oryzae pv. oryzicola (Xoc), X. oryzae pv. oryzae (Xoo), Pseudomonas syringae pv. actinidiae (Psa), and X. axonopodis pv. citri (Xac), respectively. In vivo testing against Xoc revealed TBPD2+-6C showed better activity than commercial thiodiazole copper (TC) and bismerthiazol (BT). Furthermore, the investigation into the antibacterial mechanism revealed that the cationic compound can effectively integrate into the bacterial membrane, disrupt the membrane structure, trigger ROS accumulation, and inhibit biofilm formation. In conclusion, the development of multifunctional, broad-spectrum antimicrobial system molecular designs for rapid real-time detection, imaging, and elimination of resistant microbes could play a vital role in combating pathogens.

Galla chinensis residue-derived carbon dots for sensitive detection of doxorubicin hydrochloride and cell imaging

As an antibiotic, the imbalance of the concentration of doxycycline hydrochloride (DOX) can cause many harms, so real-time detection of the DOX content is crucial. In this study, Galla chinensis residue (GCR) was used as a carbon source, m-phenylenediamine was used as an N-doping agent, and blue-green fluorescent carbon dots (N-GCRCDs) were prepared by a simple hydrothermal synthesis method, with a high quantum yield of 27.31 %. Under optimized conditions, a specific fluorescent probe was established to detect DOX. The addition of DOX resulted in a significant decrease in fluorescence intensity, with a detection range of 5.7–114.9 μM and the detection limit was 1.38 μM. Finally, the feasibility of this method was validated in human urine and the experimental results exhibited a DOX recovery rate of 97.45–104.41 % and an RSD of 0.91–2.64 %. The quenching mechanism was mainly attributed to the inner filter effect and static quenching. Furthermore, the potential application of N-GCRCDs in cells was studied and biocompatibility was evaluated using HepG2 cells, which showed low toxicity at concentrations of 0–50 μg/mL and successful application for HepG2 cell imaging. This study provides reference for resource utilization of GCR and quantitative detection of antibiotics.

The Real-Time Detection of Defects in Nuclear Power Pipeline Thermal Insulation Glass Fiber by Deep-Learning

The Real-Time Detection of Defects in Nuclear Power Pipeline Thermal Insulation Glass Fiber by Deep-Learning

Hydrogel loop-mediated isothermal amplification for ultra-fast diagnosis of Helicobacter pylori in stool samples without nucleic acid extraction

BackgroundThe gastrointestinal diseases caused by Helicobacter pylori (H. pylori) infection made the accurate detection of H. pylori infection more important. Non-invasive methods, such as molecular diagnostic methods, had become a promising method for detection of H. pylori. Stool samples combined with loop-mediated isothermal amplification (LAMP), showed potential practicability for real-time detection. However, complex nucleic acid extraction steps were required to remove the large numbers of amplification inhibitors in stool samples before LAMP reaction. And the limited number of H. pylori made the detection with long reaction time and low sensitivity. The problems mentioned above were urgently to be solved. ResultsIn this study, we proposed a strategy for ultra-rapid sensitive detection of H. pylori in stool samples by hydrogel LAMP (hLAMP) without extraction. The hydrogel was combined with stool samples after simple thermal cracking, and amplification spaces were formed in its nanopore structures by nano-localization. The LAMP reaction was accelerated by nano space-localization. Besides, this method based on hLAMP could specifically and sensitively detect as low as 100 CFU/mL H. pylori within 40 min from sampling to result due to good anti-inhibition effect on complex samples of hydrogel. The whole process involved sample simple disposal for 10 min and LAMP reaction for 30 min. Furthermore, the excellent anti-inhibition mechanism of hydrogel was discussed, and the mechanism of hydrogel accelerating LAMP was explored. SignificanceThis is the first application of that hydrogel and LAMP systematically combined to detect H. pylori in stool samples. The developed method had been verified in actual clinical applications that the accuracy rate reached 88.9% compared with routine histopathology. And it also provided a potential idea for the diagnosis and prevention of H. pylori.

Adaptive Transformer-Based Multi-Modal Image Fusion for Real-Time Medical Diagnosis and Object Detection

In recent years, medical diagnosis and object detection have been significantly enhanced by the integration of multi-modal image fusion techniques. This study proposes an Adaptive Transformer-Based Multi-Modal Image Fusion (AT-MMIF) framework designed for real-time medical diagnosis and object detection. The framework employs a Transformer architecture to capture both global and local feature correlations across multiple imaging modalities, including MRI, CT, PET, and X-ray, for more accurate diagnostic results and faster object detection in medical imagery. The fusion process incorporates spatial and frequency-domain information to improve the clarity and detail of the output images, enhancing diagnostic accuracy. The adaptive attention mechanism within the Transformer dynamically adjusts to the relevant features of different image types, optimizing fusion in real time. This leads to an improved sensitivity (98.5%) and specificity (96.7%) in medical diagnosis. Additionally, the model significantly reduces false positives and negatives, with an F1 score of 97.2% in object detection tasks. The AT-MMIF framework is further optimized for real-time processing with an average inference time of 120 ms per image and a model size reduction of 35% compared to existing multi-modal fusion models. By leveraging the strengths of Transformer architectures and adaptive learning, the proposed framework offers a highly efficient and scalable solution for real-time medical diagnosis and object detection in various clinical settings, including radiology, oncology, and pathology.

Lossy Mode Resonance Optical Fiber Enhanced by Electrochemical-Molecularly Imprinted Polymers for Glucose Detection.

Noninvasive glucose sensors are emergent intelligent sensors for analyzing glucose concentration in body fluids within invasion-free conditions. Conventional glucose sensors are often limited by a number of issues such as invasive and real-time detection, creating challenges in continuously characterizing biomarkers or subtle binding dynamics. In this study, we introduce an efficient lossy mode resonance (LMR) optical fiber sensor incorporating the molecularly imprinted polymers (MIPs) to amplify glucose molecules. A molecularly imprinted recognition platform is created on an LMR sensor surface through a convenient one-step electrochemical (EC) polymerization method, in which 3-Aminophenylboric acid and glucose serve as the functional monomer and template molecule, respectively. LMR resonance wavelength shift induced by the coupling of the optical lossy mode and the fiber core mode is employed as the parameter to characterize biomolecules. Due to its high sensitivity to surrounding environment changes, a limit of detection (LOD) of 4.62 × 10-2 μmol/L for glucose can be achieved by this optical fiber sensor. Additionally, the prepared EC-MIPs LMR sensor is capable of detecting glucose molecules in human saliva samples with high accuracy, endowing its potential for practical applications.

TERTmonitor Efficacy and Performance in Detecting Mutations by Droplet Digital PCR

Background: The screening of TERT promoter (TERTp) mutations is essential in cancer research and diagnostics, due to its prevalence in tumours associated with low self-renewal rates. TERTmonitor is a diagnosis kit primarily designed for real-time qPCR qualitative detection of −124C>T and −146C>T TERTp mutations, which are highly prevalent in several malignancies, particularly in bladder carcinoma. Objective: This study aims to investigate TERTmonitor performance in droplet digital PCR (ddPCR) in urine samples from bladder cancer patients. Methods: A total of 45 urine samples were examined by real-time qPCR and ddPCR techniques, and their performances were compared. Results: TERTmonitor had similar performance in both real-time qPCR and ddPCR platforms. Specifically, the methods exhibited a concordance rate of 95.45% and 90% for −124C>T and −146C>T mutations, respectively. Importantly, an enhanced sensitivity in certain scenarios was exhibited by ddPCR when compared to real-time qPCR, detecting mutations that the latter failed to identify in approximately 4.55% and 10% of the samples for −124C>T and −146C>T mutations, respectively. This enhanced sensitivity of ddPCR was particularly evident in samples with low-frequency mutations. Conclusions: The findings highlight the usefulness of TERTmonitor for cancer surveillance either in real-time qPCR or ddPCR platforms.

Spiking Neural Networks for Real-Time Pedestrian Street-Crossing Detection Using Dynamic Vision Sensors in Simulated Adverse Weather Conditions

This study explores the integration of Spiking Neural Networks (SNNs) with Dynamic Vision Sensors (DVSs) to enhance pedestrian street-crossing detection in adverse weather conditions—a critical challenge for autonomous vehicle systems. Utilizing the high temporal resolution and low latency of DVSs, which excel in dynamic, low-light, and high-contrast environments, this research evaluates the effectiveness of SNNs compared to traditional Convolutional Neural Networks (CNNs). The experimental setup involved a custom dataset from the CARLA simulator, designed to mimic real-world variability, including rain, fog, and varying lighting conditions. Additionally, the JAAD dataset was adopted to allow for evaluations using real-world data. The SNN models were optimized using Temporally Effective Batch Normalization (TEBN) and benchmarked against well-established deep learning models, concerning their accuracy, computational efficiency, and energy efficiency in complex weather conditions. This study also conducted a comprehensive analysis of energy consumption, highlighting the significant reduction in energy usage achieved by SNNs when processing DVS data. The results indicate that SNNs, when integrated with DVSs, not only reduce computational overhead but also dramatically lower energy consumption, making them a highly efficient choice for real-time applications in autonomous vehicles (AVs).

Research on Pavement Defect Detection Algorithm Based on SEM-YOLOv8n

Automated detection and identification of pavement distresses is essential for timely pavement repair. Subtle pavement defects and multiple defects detection is a challenging task under complex background. With the deepening of the deep learning network, some subtle features tend to disappear and are more difficult to detect under the influence of the complex background. To solve the above problems, this paper proposes the SEM-YOLOv8n pavement defect detection algorithm. Firstly, SPD-Conv is used to replace the traditional convolution, which is conducive to retaining more defect detail information in the image and improving the detection ability of subtle defects; then an efficient multi-scale attention mechanism is added to the fusion network, so that the network suppresses the background information and focuses more on the defect information. Finally, MPDIoU is introduced as a loss function, which optimizes the minimum perpendicular distance between the predicted bounding box and the real bounding box and improves the localization ability, thus improving the accuracy of the network. Finally, the effectiveness of the proposed network is verified on the IRRDD dataset, and the results show that the method achieves 91.9% (Precision), 91.3% (Recall), and 71.3% (mAP) for the classification and detection of road multi-scale minor defects, which meets the demand of real-time road defect detection.

Underground Cable Fault Detection

Underground cables play a crucial role in delivering electricity, ensuring a dependable power supply in both urban and industrial regions. However, detecting and resolving faults in these cables can be difficult due to their hidden placement. This project aims to develop an effective underground cable fault detection system that accurately identifies fault locations, reducing downtime. The system will combine electrical principles with modern sensing technologies to detect faults such as short circuits, open circuits, and insulation issues. By injecting a small current into the cable and analyzing the resulting voltage drop, the system will calculate the distance to the fault from the measurement point. Using a microcontroller along with sensors and signal processing units, it will determine and display the fault location in kilometers. Real-time fault detection will significantly decrease maintenance time and costs by quickly locating problem areas, enabling faster repairs and reducing power outages. This project aims to improve the efficiency and reliability of power transmission systems. Additionally, the system can be integrated with communication technologies for remote monitoring, allowing utility companies to detect and manage faults from centralized control centers.

DeployFusion: A Deployable Monocular 3D Object Detection with Multi-Sensor Information Fusion in BEV for Edge Devices.

To address the challenges of suboptimal remote detection and significant computational burden in existing multi-sensor information fusion 3D object detection methods, a novel approach based on Bird's-Eye View (BEV) is proposed. This method utilizes an enhanced lightweight EdgeNeXt feature extraction network, incorporating residual branches to address network degradation caused by the excessive depth of STDA encoding blocks. Meantime, deformable convolution is used to expand the receptive field and reduce computational complexity. The feature fusion module constructs a two-stage fusion network to optimize the fusion and alignment of multi-sensor features. This network aligns image features to supplement environmental information with point cloud features, thereby obtaining the final BEV features. Additionally, a Transformer decoder that emphasizes global spatial cues is employed to process the BEV feature sequence, enabling precise detection of distant small objects. Experimental results demonstrate that this method surpasses the baseline network, with improvements of 4.5% in the NuScenes detection score and 5.5% in average precision for detection objects. Finally, the model is converted and accelerated using TensorRT tools for deployment on mobile devices, achieving an inference time of 138 ms per frame on the Jetson Orin NX embedded platform, thus enabling real-time 3D object detection.

Adaptive Security Paradigms: The Role of Al in Safeguarding Distributed Data Across Multi-cloud Platforms

The proliferation of multi-cloud infrastructures in modern data management strategies has introduced complex security challenges that traditional measures struggle to address effectively. This article investigates the potential of AI-powered security frameworks to enhance distributed data protection across diverse cloud environments. By leveraging advanced machine learning algorithms and predictive analytics, these frameworks offer real-time threat detection, adaptive access controls, and intelligent encryption management. The article examines the key components of AI-driven security systems, including automated anomaly detection and behavior analysis, and their integration with existing security protocols. Through a series of case studies and real-world applications, we demonstrate the efficacy of these frameworks in identifying vulnerabilities, initiating proactive security measures, and maintaining compliance with industry regulations. Our findings indicate that AI-powered security frameworks provide a scalable, adaptive, and robust solution for safeguarding distributed data assets in the dynamic landscape of multi-cloud infrastructures. However, the research also acknowledges potential limitations and ethical considerations, paving the way for future advancements in this critical area of cybersecurity.

Wireless Network Security Prediction Using Machine Learning and Graph Neural Networks

Abstract: We study the application of graph neural networks and machine learning in the prediction of risks to wireless networks. Advanced predictive methods are necessary, since mere security measures cannot thwart the rising complexity of cyber-attacks. In the present work, we will use a hybrid model that combines several machine learning methods to reduce false negatives and positives and improve accuracy in the prediction of risks to wireless networks. Models are trained and validated with large amounts of data that include the performance indicators for accuracy, precision, recall, F1-score, and AUC-ROC. From this, it is also seen that the hybrid model performs much better than the standard models in real-time threat detection. The impact of the size of the dataset on the performance of the model was also studied, and it has come out that larger datasets improve predictive powers significantly. The result demonstrated that the latest advancements in machine learning techniques can lead to important improvements in the security of wireless networks.

AI-powered IoT and UAV systems for real-time detection and prevention of illegal logging

Illegal logging poses a significant threat to environmental conservation, contributing to deforestation, ecosystem disruption, and economic losses. Traditional detection methods, such as ground patrols and satellite imagery, are often ineffective, expensive, and time-consuming. This paper introduces a novel Unmanned Aerial Vehicles (UAV)-based IoT system for chainsaw noise detection and prevention. The system uses low-cost IoT nodes with microphones and microcontrollers to detect chainsaw sounds via a Convolutional Neural Network (CNN) model. These nodes reduce power consumption, allowing the battery to last at least 8 years. Detected chainsaw sounds are transmitted to a LoRaWAN gateway and forwarded to a cloud server. The cloud server processes the data and dispatches a drone equipped with a camera to the site. The drone streams live video to the cloud, where AI algorithms analyze the footage for human presence. If detected, the drone activates sound and light alarms to deter illegal logging. Experimental results show that IoT nodes can detect chainsaw sounds up to 100 m, with the CNN model achieving an accuracy of 99.37 % and a loss of 0.0185. Comparisons with Logistic Regression, Decision Tree, Random Forest, and SVM demonstrated the superior performance of CNN. This UAV-IoT system offers a fast, reliable, scalable, and real-time solution for detecting and preventing illegal logging. Leveraging advanced AI and IoT technologies, this system enhances environmental monitoring and conservation efforts. It represents a significant step forward in the fight against illegal logging, providing a practical, effective, and sustainable solution.

무인 점포 실시간 이상 행동 감지를 위한 Transformer 기반지능형 CCTV 시스템

The rapid expansion of unmanned retail stores has raised critical security concerns, thereby necessitating the development and implementation of robust protective measures. The absence of real-time monitoring systems in these environments has heightened the vulnerability to risks such as theft and property damage. Although closed-circuit television (CCTV) systems have been deployed to retrospectively investigate criminal activities, these systems are often insufficient in preventing incidents. This study introduces a Transformer-based intelligent CCTV system designed for the real-time detection of anomalous behaviors within unmanned retail environments. Unlike conventional systems that rely on basic machine learning models, our proposed system leverages human joint position data extracted from CCTV footage to classify a range of anomalous behaviors, including theft, falls, and property damage. Additionally, extensive hyperparameter optimization was performed to maximize the model's effectiveness in these specific environments. Our System enhances the system's usability by enabling real-time identification of anomalous behavior, complete with location data, timestamps, and corresponding video frame sequences.

Industry Monitoring & Security System Using IoT

This paper presents an IoT-based industrial monitoring and security system using the NodeMCU ESP8266 and multiple sensors (MQ2, flame sensor, DHT11, LDR module, PZEM-004T) for real-time detection of hazards like gas leaks, fires, and electrical overloads. The system automates lighting and machinery control, sending alerts via Telegram for immediate response. It is cost-effective, scalable, and modular, ensuring reliable operation through a stabilized power supply, making it suitable for diverse industrial applications.

Real-time crop row detection using computer vision- application in agricultural robots.

The goal of achieving autonomous navigation for agricultural robots poses significant challenges, mostly arising from the substantial natural variations in crop row images as a result of weather conditions and the growth stages of crops. The processing of the detection algorithm also must be significantly low for real-time applications. In order to address the aforementioned requirements, we propose a crop row detection algorithm that has the following features: Firstly, a projective transformation is applied to transform the camera view and a color-based segmentation is employed to distinguish crop and weed from the background. Secondly, a clustering algorithm is used to differentiate between the crop and weed pixels. Lastly, a robust line-fitting approach is implemented to detect crop rows. The proposed algorithm is evaluated throughout a diverse range of scenarios, and its efficacy is assessed in comparison to four distinct existing solutions. The algorithm achieves an overall intersection over union (IOU) of 0.73 and exhibits robustness in challenging scenarios with high weed growth. The experiments conducted on real-time video featuring challenging scenarios show that our proposed algorithm exhibits a detection accuracy of over 90% and is a viable option for real-time implementation. With the high accuracy and low inference time, the proposed methodology offers a viable solution for autonomous navigation of agricultural robots in a crop field without damaging the crop and thus can serve as a foundation for future research.

Lightweight and efficient deep learning models for fruit detection in orchards

The accurate recognition of apples in complex orchard environments is a fundamental aspect of the operation of automated picking equipment. This paper aims to investigate the influence of dense targets, occlusion, and the natural environment in practical application scenarios. To this end, it constructs a fruit dataset containing different scenarios and proposes a real-time lightweight detection network, ELD(Efficient Lightweight object Detector). The EGSS(Efficient Ghost-shuffle Slim module) module and MCAttention(Mix channel Attention) are proposed as innovative solutions to the problems of feature extraction and classification. The attention mechanism is employed to construct a novel feature extraction network, which effectively utilizes the low-latitude feature information, significantly enhances the fine-grained feature information and gradient flow of the model, and improves the model’s anti-interference ability. Eliminate redundant channels with SlimPAN to further compress the network and optimise functionality. The network as a whole employs the Shape-IOU loss function, which considers the influence of the bounding box itself, thereby enhancing the robustness of the model. Finally, the target detection accuracy is enhanced through the transfer of knowledge from the teacher’s network through knowledge distillation, while ensuring that the overall network is sufficiently lightweight. The experimental results demonstrate that the ELD network, designed for fruit detection, achieves an accuracy of 87.4%. It has a relatively low number of parameters (4.3×105\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$4.3 \ imes 10^5$$\\end{document}), a GLOPs of only 1.7, and a high FPS of 156. This network can achieve high accuracy while consuming fewer computational resources and performing better than other networks.

Low-cost portable sensor for rapid and sensitive detection of Pb2+ ions using capacitance sensing integrated with microfluidic enrichment.

Lead ion (Pb2+) pollution is a critical global issue due to its ability to accumulate in the human body, resulting in severe health problems. Despite extensive research efforts devoted to the detection of Pb2+ contamination, practical, rapid, and field-deployable sensors for Pb2+ is yet to be developed to effectively safeguard the environment and public health. Herein, a label-free affinity-based sensing device is developed based on printed circuit board (PCB) for low-cost, easy-to-use, and real-time on-site detection of Pb2+ ions. The sensors are prepared by forming a self-assembled monolayer of glutathione (GSH) on the surface of gold-plated PCB electrodes, which serves as a molecular probe to recognize Pb2+. Rapid and sensitive detection is achieved by using capacitance sensing integrated with microfluidic enrichment. The sensor's interfacial capacitance is used to indicate specific binding, while the capacitance reading process simultaneously induces alternating current electrothermal (ACET) acceleration of analyte's travel towards the probes. Thus, the enrichment and detection are integrated into a single step, making pre-concentration unnecessary and shortening the assay time to 30s. This Pb2+ sensor has demonstrated one of the lowest limits of detection reported so far (1.85 fM) with a linear range of 0.01-10pM. To evaluate the sensor's specificity, non-target metal ions are tested, all showing negligible responses. Testing of tap water sample also yields reasonable results, validating the sensor's robustness. The above-mentioned features, together with a commercial portable readout, make this sensor well-suited for point-of-use Pb2+ detection at low cost.