Effective Detection Method Research Articles

Rapid and nondestructive identification of rice storage year using hyperspectral technology

Rice is the main staple food for more than half of the world's population. Consumption of long-stored rice will have adverse effects on the human body. Here, we proposed the near-infrared (NIR) hyperspectral imaging (HSI) technique to distinguish rice from different storage years. Multiplicative Scatter Correction (MSC), Standard Normalize Variate (SNV) and 1st Derivative (1st) were used for the pretreatment of HSI data. In order to reduce dimensional spectral features, Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (tSNE) were used for data visualization. Besides, spectral characteristic wavelengths were extracted by competitive adaptive reweighted sampling (CARS) and least absolute shrinkage and selection operator (Lasso). Simultaneously, the textural features of rice were analyzed by Local Binary Pattern (LBP), Gray-Level Co-occurrence Matrix (GLCM) and Tamura algorithms. In order to realize feature fusion of spectra and texture, Support Vector Machine (SVM) model was optimized using the Whale optimization algorithm (WOA) and Extreme Gradient Boosting (XGBoost) model were established based on spectral features and textural features. Compared to other models, feature fusion model showed an excellent result with an accuracy of 98.89%. Experimental results suggested that HSI technology can be served as an effective method for rice detection.

Benchmarking UMI-aware and standard variant callers for low frequency ctDNA variant detection

BackgroundCirculating tumour DNA (ctDNA) is a subset of cell free DNA (cfDNA) released by tumour cells into the bloodstream. Circulating tumour DNA has shown great potential as a biomarker to inform treatment in cancer patients. Collecting ctDNA is minimally invasive and reflects the entire genetic makeup of a patient’s cancer. ctDNA variants in NGS data can be difficult to distinguish from sequencing and PCR artefacts due to low abundance, particularly in the early stages of cancer. Unique Molecular Identifiers (UMIs) are short sequences ligated to the sequencing library before amplification. These sequences are useful for filtering out low frequency artefacts. The utility of ctDNA as a cancer biomarker depends on accurate detection of cancer variants.ResultsIn this study, we benchmarked six variant calling tools, including two UMI-aware callers for their ability to call ctDNA variants. The standard variant callers tested included Mutect2, bcftools, LoFreq and FreeBayes. The UMI-aware variant callers benchmarked were UMI-VarCal and UMIErrorCorrect. We used both datasets with known variants spiked in at low frequencies, and datasets containing ctDNA, and generated synthetic UMI sequences for these datasets. Variant callers displayed different preferences for sensitivity and specificity. Mutect2 showed high sensitivity, while returning more privately called variants than any other caller in data without synthetic UMIs – an indicator of false positive variant discovery. In data encoded with synthetic UMIs, UMI-VarCal detected fewer putative false positive variants than all other callers in synthetic datasets. Mutect2 showed a balance between high sensitivity and specificity in data encoded with synthetic UMIs.ConclusionsOur results indicate UMI-aware variant callers have potential to improve sensitivity and specificity in calling low frequency ctDNA variants over standard variant calling tools. There is a growing need for further development of UMI-aware variant calling tools if effective early detection methods for cancer using ctDNA samples are to be realised.

Quantitative assessment of double-cone seal leakage in canned reactor coolant pump based on double-cone ring stress

The double-cone seal is a crucial component of the canned reactor coolant pump (RCP), serving as a vital barrier to prevent coolant leakage. Its sealing status directly impacts the operational safety of the RCP. Given the intricate operational conditions and rigorous sealing requirements of RCP, there is a dearth of effective detection methods for minor leakage of double-cone seal. To address this issue, a quantitative assessment method for the leakage of double-cone seal based on double-cone ring stress is proposed. In this paper, the functional relationship between the double-cone ring stress and the specific pressure of the gasket seal is first derived. Subsequently, a leakage rate assessment model based on the double-cone ring stress is proposed by combining with the leakage rate expression of the metal gasket connection structure. Finally, the feasibility of the proposed method for the leakage detection of double-cone seal is verified by finite element simulation and leakage simulation test. The results demonstrate that the proposed method is capable of detecting small leakage conditions with a leakage rate in the order of 1 × 10−4 cm3·s−1, which is sufficient for the micro-leakage detection of double-cone seal.

Maximizing Breast Cancer Detection Through Screening: A Comparative Analysis of Imaging-Based Approaches

Introduction/BackgroundThis study estimates the percentage of detectable breast cancers in the screening population that could be found with primary and supplemental screening, and provides cost estimates for population wide supplemental screening in the U.S. Materials and MethodsPublished estimates on cancer detection rates of 2D mammography, tomosynthesis (DBT), whole breast ultrasound (US), molecular breast imaging (MBI), contrast-enhanced mammography (CEM), and MRI, the number of mammograms conducted in the United States in 2023, and the proportion of dense breast tissue, were utilized. The maximum number of detectable cancers was projected from incremental cancer detection rates of the most sensitive supplemental screening method. The proportion of cancers detectable for each modality was calculated. In 2023, Medicare reimbursement rates were used to estimate supplemental screening costs. ResultsOut of 469,437 detectable cancers, 2D mammography could detect 190,531 (41%), leaving 278,906 undetected. Adding supplemental screening could detect a combined 220,165 cancers (47%) with DBT, 237,596 (51%) with US, 331,727 (71%) with MBI, 377,049 (80%) with CEM and 469,437 (100%) with MRI. The imaging cost in US dollars to provide supplemental screening to all individuals with dense breasts in 2023 was $933M for tomosynthesis, $1.84B for US, $3.87B for CEM, $4.16B for MBI, and $6.36B for MRI. ConclusionThe study highlights potential benefits from supplemental breast cancer screening, suggesting the combination of mammography and breast MRI offers the most effective detection method though at the highest imaging cost. These findings provide valuable insights to guide future research and inform decision-making in supplemental breast cancer screening strategies.

Remora‐CNN: A Novel and Effective Method for Rice Leaf Disease Detection and Classification

ABSTRACTFor millions of people worldwide, rice is one of the main food crops. Nevertheless, while being grown, rice is susceptible to many diseases. Most rice plant diseases are influenced by biotic and abiotic factors, including nematodes, viroids, fungus, viruses, bacteria, and other microorganisms, as well as temperature and other environmental factors. Thus, an automatic early classification of leaf disease is necessary to improve the rice yield. In this paper, for identifying and categorizing the rice leaf disease, a convolutional neural network (CNN) model is used, and the CNN is trained using the Remora Optimization Algorithm (ROA). A better classification outcome is attained by performing the segmentation process using K‐means with the Fractional Tangential‐Spherical Kernel (FTSK) algorithm. Furthermore, the developed Remora Optimization‐ Convolutional Neural Network (Remora‐CNN) method achieved the optimal performance based on the testing accuracy, sensitivity and specificity of 0.925, 0.931, and 0.941 using the Rice Leaf Disease Image Samples Dataset.

Defect Recognition and Classification Using Ultrasonic Scattered Signals Based on Convolutional Neural Network

Abstract Carbon Fiber Reinforced Polymer (CFRP) is widely used in the aerospace, aircraft, and railway industries because of its remarkable advantages, such as its lightweight and high strength. Detecting and identifying defects in CFRP is crucial for ensuring its secure and efficient use. Ultrasonic non-destructive testing is one of the most practical and effective methods for defect detection and identification. The ultrasonic scattered signals of defects, which contain abundant defect feature information, are advantageous for defect recognition and classification. However, the anisotropy and inhomogeneity of CFRP, which lead to a low signal-to-noise ratio and poor image quality, pose challenges in flaw recognition. To address the issue, this paper proposes using Convolutional Neural Networks (CNN) methods for defect classification, which can adequately extract information from ultrasonic scattered signals directly. The scattering signals from various types of defects in CFRP, including the different sizes of holes and folds, were selected as inputs for CNN models. Different network models combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) with 1D-CNN were employed to classify and identify defect signals. To generate sufficient input sample signals, the data sets were further enlarged by incorporating noise into the original signals. The experimental results showed that using the 1D-LSTM-CNN and 1D-GRU-CNN network models can reduce computational resources while ensuring the accuracy of defect recognition.

On-Line Analysis of Cigarette Smoke Based on Microwave Plasma Torch Mass Spectrometry.

Cigarette smoke contains a large number of chemicals, including both flavor components and harmful substances. The mainstream smoke (MSS) generated by smoking is directly inhaled by individuals, making it crucial to establish an effective method for smoke detection and analysis. One promising technique for analyzing smoke is MPT-MS (Microwave plasma torch mass spectrometry). This approach offers several advantages in accurately detecting the composition of cigarette smoke. By combining MPT-MS with a smoke pumping device, we can achieve real-time online detection of smoke components. We successfully detected 22 flavor compounds present in the smoke. These compounds contribute to the distinct taste of cigarettes. Moreover, we identified 2 polycyclic aromatic hydrocarbons (PAHs) in the smoke. PAHs are known carcinogens and are of great concern in terms of their potential health risks. The successful detection and identification of flavor compounds and PAHs using our method confirm the online detection capability of MPT-MS. This approach provides an efficient and reliable means for analyzing the complex composition of cigarette smoke. By utilizing MPT-MS, we can gain valuable insights into the chemical composition of cigarette smoke and can inform the development of strategies and policies aimed at reducing the harmful effects of smoking and protecting public health.

Research on Silage Corn Forage Quality Grading Based on Hyperspectroscopy

Corn silage is the main feed in the diet of dairy cows and other ruminant livestock. Silage corn feed is very susceptible to spoilage and corruption due to the influence of aerobic secondary fermentation during the silage process. At present, silage quality testing of corn feed mainly relies on the combination of sensory evaluation and laboratory measurement. The sensory review method is difficult to achieve precision and objectivity, while the laboratory determination method has problems such as cumbersome testing procedures, time-consuming, high cost, and damage to samples. In this study, the external sensory quality grading model for different qualities of silage corn feed was established using hyperspectral data. To explore the feasibility of using hyperspectral data for external sensory quality grading of corn silage, a hyperspectral system was used to collect spectral data of 200 corn silage samples in the 380–1004 nm band, and the samples were classified into four grades: excellent, fair, medium, and spoiled according to the German Agricultural Association (DLG) standard for sensory evaluation of silage samples. Three algorithms were used to preprocess the fodder hyperspectral data, including multiplicative scatter correction (MSC), standard normal variate (SNV), and S–G convolutional smoothing. To reduce the redundancy of the spectral data, variable combination population analysis (VCPA) and competitive adaptive reweighted sampling (CARS) were used for feature wavelength selection, and linear discriminant analysis (LDA) algorithm was used for data dimensionality reduction, constructing random forest classification (RFC), convolutional neural networks (CNN) and support vector machines (SVM) models. The best classification model was derived based on the comparison of the model results. The results show that SNV-LDA-SVM is the optimal algorithm combination, where the accuracy of the calibration set is 99.375% and the accuracy of the prediction set is 100%. In summary, combined with hyperspectral technology, the constructed model can realize the accurate discrimination of the external sensory quality of silage corn feed, which provides a reliable and effective new non-destructive testing method for silage corn feed quality detection.

A difunctional NMR&CD probe for specific detection and enantiomeric recognition of biothiols in complex mixtures

BackgroundBiothiols are important for numerous cellular processes, such as resisting oxidative stress and protecting cell health. Their abnormal levels and molecular configurations have been associated with various diseases. So, establishing an effective and reliable method for the specific detection and enantiomeric discrimination of diverse biothiols is highly meaningful. ResultsWe have developed a new NMR and CD probe using 1,4-dinitroimidazole, specifically targeting the thiol group. This probe allows for the specific detection and enantiomeric recognition of biothiols in complex mixtures. We achieved this by identifying the distinguishable 1H NMR signals of 2nd in imidazole-ring of the resulting 4NI-biothiols in the downfield region at 7–8 ppm and newly discovered induced CD signals within 290-430 nm. Using this probe, the limits of detection of Cys, GSH, and Hcy, the recovery rates, and the concentration of GSH extracted from HEK293T cells were determined by measuring the unique downfield 1H NMR signals. Moreover, Cys, GSH, and Hcy can be discriminated simultaneously in complicated samples at a pH range of 2–3.5. Furthermore, this probe can also be utilized to sense chiral thiol-drugs. SignificanceThis method offers a cost-effective and accurate sensing solution for the specific detection of biothiols in complex mixtures, with stereochemical recognition.

Graph neural network based phishing account detection in Ethereum

Abstract In recent years, the widespread adoption of Ethereum-based transactions, such as cryptocurrencies and blockchain technologies, have revolutionized the way financial transactions are conducted. These decentralized and transparent systems offer numerous advantages, including enhanced security, immutability, and reduced transaction costs. However, alongside their benefits, Ethereum-based transactions have also attracted the attention of malicious actors seeking to exploit unsuspecting users through phishing scams. Phishing scams have thus become frequent in this scenario. Therefore, it is required to implement an effective and reliable phishing scam detection method. In this paper, we present the implementation of a highly efficient detection method by carrying out a graph-like data network formation, over which we then apply models that are based on graph neural networks like Magnet Link Prediction and Graph AutoEncoder Pathfinder Discovery Network Algorithm (GAE_PDNA). This helps in extracting useful information from the nodes of the graph. After relevant embeddings have been obtained, the classification of the phishing account is performed using AdaBoost classifier that helps in complex decision-making and detects the accounts related to the phishing scams. Our best model attains a precision of 0.99 and an F1 score of 0.99. Highlights

Temporal Feature Prediction in Audio–Visual Deepfake Detection

The rapid growth of deepfake technology, generating realistic manipulated media, poses a significant threat due to potential misuse. Therefore, effective detection methods are urgently needed to prevent malicious use, as current approaches often focus on single modalities or the simple fusion of audio–visual signals, limiting their accuracy. To solve this problem, we propose a deepfake detection scheme based on bimodal temporal feature prediction, which innovatively introduces the idea of temporal feature prediction into the audio–video bimodal deepfake detection task, aiming at fully exploiting the temporal laws of audio–visual modalities. First, pairs of adjacent audio–video sequence clips are used to construct input quadruples, and a dual-stream network is employed to extract temporal feature representations from video and audio, respectively. A video prediction module and an audio prediction module are designed to capture the temporal inconsistencies within each single modality by predicting future temporal features and comparing them with reference features. Then, a projection layer network is designed to align the audio–visual features, using contrastive loss functions to perform contrastive learning and maximize the differences between real and fake video modalities. Experiments on the FakeAVCeleb dataset demonstrate superior performance with an accuracy of 84.33% and an AUC of 89.91%, outperforming existing methods and confirming the effectiveness of our approach in deepfake detection.

Outlier detection using local density and global structure

Outlier detection, a critical process for enhancing data quality, has been applied to a broad spectrum of real-world applications. This study introduces a novel and effective outlier detection method that incorporates both local density and global structural information. Specifically, we employ the concept of potential energy, a well-established principle in physics, to represent local densities or neighbor distributions of data. Additionally, we also exploit the notion of hubness, a measure explored in network science, to further capture global structural information of data. To facilitate this, we construct a strongly connected digraph by introducing a virtual node along with an associated set of virtual edges. This digraph underpins a tailored Markov random walk process that is used to estimate the hubness scores of data objects. Subsequently, the importance degrees of data objects are estimated according to their potential energies and hubness scores. The data objects with lower importance degrees are deemed to be outliers. Extensive experiments conducted on thirteen publicly accessible real-world datasets against nine popular outlier detection algorithms show that the proposed method achieved encouraging and competitive performance in comparing the state-of-the-art outlier detection algorithms.

Electrochemical Sensors for Antibiotic Detection: A Focused Review with a Brief Overview of Commercial Technologies.

Antimicrobial resistance (AMR) poses a significant threat to global health, powered by pathogens that become increasingly proficient at withstanding antibiotic treatments. This review introduces the factors contributing to antimicrobial resistance (AMR), highlighting the presence of antibiotics in different environmental and biological matrices as a significant contributor to the resistance. It emphasizes the urgent need for robust and effective detection methods to identify these substances and mitigate their impact on AMR. Traditional techniques, such as liquid chromatography-mass spectrometry (LC-MS) and immunoassays, are discussed alongside their limitations. The review underscores the emerging role of biosensors as promising alternatives for antibiotic detection, with a particular focus on electrochemical biosensors. Therefore, the manuscript extensively explores the principles and various types of electrochemical biosensors, elucidating their advantages, including high sensitivity, rapid response, and potential for point-of-care applications. Moreover, the manuscript investigates recent advances in materials used to fabricate electrochemical platforms for antibiotic detection, such as aptamers and molecularly imprinted polymers, highlighting their role in enhancing sensor performance and selectivity. This review culminates with an evaluation and summary of commercially available and spin-off sensors for antibiotic detection, emphasizing their versatility and portability. By explaining the landscape, role, and future outlook of electrochemical biosensors in antibiotic detection, this review provides insights into the ongoing efforts to combat the escalating threat of AMR effectively.

Establishment and methodological evaluation of a rapid detection method for Cryptococcus neoformans and Cryptococcus gattii species complexes based on CRISPR-Cas12a technology

PurposeThe opportunistic pathogens causing Cryptococcal meningitis are Cryptococcus neoformans and Cryptococcus gattii species complexes. At present, clinical detection methods for this condition include culture, ink staining, and cryptococcal antigen detection. In addition, enzyme-linked immunosorbent assay (ELISA), polymerase chain reaction (PCR), and real-time quantitative PCR (qPCR) can be applied for the detection of Cryptococcus. Nevertheless, these methods cannot achieve point-of-care detection (POCT); thus, there is a pressing need to establish a fast, sensitive, and effective detection method. MethodsRecombinase polymerase amplification (RPA) and clustered regularly spaced short palindromic repeat (CRISPR) techniques are effective tools for achieving rapid POCT. In this study, RPA was combined with CRISPR-Cas12a to establish a fast, sensitive, and specific detection method for cryptococcal meningitis. ResultsThis study included RPA-Cas12a fluorescence detection and RPA-Cas12a immunochromatographic detection, which can be performed within 50 min. Moreover, the detection limit was as low as 102 copies/μL. Interestingly, the developed method demonstrated satisfactory specificity and no cross-reactivity with other fungi and bacteria. 36 clinical samples were tested, and the consistency between the test results and those obtained using the commonly used clinical culture method was 100 %. ConclusionIn this study, a rapid detection method for Cryptococcus neoformans and Cryptococcus gattii species complexes was developed based on CRISPR-Cas12a technology, characterized by its high sensitivity and specificity, ease of use, and cost-effectiveness, making it suitable for on-site detection.

Flexible control and trajectory planning of medical two-arm surgical robot.

This paper introduces the flexible control and trajectory planning medical two-arm surgical robots, and employs effective collision detection methods to ensure the safety and precision during tasks. Firstly, the DH method is employed to establish relative rotation matrices between coordinate systems, determining the relative relationships of each joint link. A neural network based on a multilayer perceptron is proposed to solve FKP problem in real time. Secondly, a universal interpolator based on Non-Uniform Rational B-Splines (NURBS) is developed, capable of handling any geometric shape to ensure smooth and flexible motion trajectories. Finally, we developed a generalized momentum observer to detect external collisions, eliminating the need for external sensors and thereby reducing mechanical complexity and cost. The experiments verify the effectiveness of the kinematics solution and trajectory planning, demonstrating that the improved momentum torque observer can significantly reduce system overshoot, enabling the two-arm surgical robot to perform precise and safe surgical tasks under algorithmic guidance.

Aggregation‐induced emission biomarkers for early detection of orthopaedic implant failure

AbstractIn recent years, the substantial increase in total joint replacements for treating degenerative joint disease has heightened concerns regarding implant loosening and failure. This is especially critical as more young patients are undergoing both initial and subsequent joint replacement procedures. These complications often necessitate additional revision surgeries. Unfortunately, current clinical practices lack effective methods for the early detection of implant failure, and there is a noticeable absence of strategies utilizing molecular markers to identify post‐surgery implant issues. This article critically assesses the potential of aggregation‐induced emission (AIE) biomarkers in detecting molecular markers relevant to implant failure. It begins by outlining the pathogenesis of implant loosening and identifying pertinent molecular markers. The study then delves into how AIE luminogens (AIEgens) can play a crucial role in detecting processes such as osteogenesis and osteoclastogenesis. Notably, it discusses the utilization of AIEgens in detecting key molecular markers, including TNF‐α, osteocalcin, and urinary N‐terminal telopeptide. The prospect of AIE biomarkers for the early detection of bone loss and implant failure presents a promising avenue for enhancing our understanding of skeletal health and improving clinical outcomes through timely intervention and personalized treatment approaches. Ongoing research and development in this area are crucial for translating AIE‐based technologies into practical tools for optimizing bone health management.

Integrating automated machine learning and metabolic reprogramming for the identification of microplastic in soil: A case study on soybean

The accumulation of polyethylene microplastic (PE-MPs) in soil can significantly impact plant quality and yield, as well as affect human health and food chain cycles. Therefore, developing rapid and effective detection methods is crucial. In this study, traditional machine learning (ML) and H2O automated machine learning (H2O AutoML) were utilized to offer a powerful framework for detecting PE-MPs (0.1 %, 1 %, and 2 % by dry soil weight) and the co-contamination of PE-MPs and fomesafen (a common herbicide) in soil. The development of the framework was based on the results of the metabolic reprogramming of soybean plants. Our study stated that traditional ML exhibits lower accuracy due to the challenges associated with optimizing complex parameters. H2O AutoML can accurately distinguish between clean soil and contaminated soil. Notably, H2O AutoML can detect PE-MPs as low as 0.1 % (with 100 % accuracy) and co-contamination of PE-MPs and fomesafen (with 90 % accuracy) in soil. The VIP and SHAP analyses of the H2O AutoML showed that PE-MPs and the co-contamination of PE-MPs and fomesafen significantly interfered with the antioxidant system and energy regulation of soybean. We hope this study can provide a reliable scientific basis for sustainable development of the environment.

Wearable bracelet and machine learning for remote diagnosis and pandemic infection detection

The COVID-19 pandemic has highlighted that effective early infection detection methods are essential, as they play a critical role in controlling the epidemic spread. In this work, we investigate the use of wearable sensors in conjunction with machine learning (ML) techniques for pandemic infection detection. We work on designing a wristband that measures various vital parameters such as temperature, heart rate, and SPO2, and transmits them to a mobile application using Bluetooth Low Energy. The accuracy of the wristband measurements is shown to be within 10% of the readings of existing commercial products. The measured data can be used and analyzed for various purposes. To benefit from the existing online datasets related to COVID-19, we use this pandemic as an example in our work. Hence, we also develop ML-based models that use the measured vital parameters along with cough sounds in order to determine whether a case is COVID-19 positive or not. The proposed models are shown to achieve remarkable results, exceeding 90% accuracy. One of our proposed models exceeds 96% performance in terms of accuracy, precision, recall, and F1-Score. The system lends itself reasonably for amendment to deal with future pandemics by considering their specific features and designing the ML models accordingly. Furthermore, we design and develop a mobile application that shows the data collected from the wristband, records cough sounds, runs the ML model, and provides feedback to the user about their health status in a user-friendly, intuitive manner. A successful deployment of such an approach would decrease the load on hospitals and prevent infection from overcrowded spaces inside the hospital.

Covalent-Organic Frameworks for Selective and Sensitive Detection of Antibiotics from Water.

As the consumption of antibiotics rises, they have generated some negative impacts on organisms and the environment because they are often unable to be effectively degraded, and seeking effective detection methods is currently a challenge. Covalent-organic frameworks (COFs) are new types of crystalline porous crystals created based on the strong covalent interactions between blocked monomers, and COFs demonstrate great potential in the detection of antibiotics from aqueous solutions because of their large surface area, adjustable porosity, recyclability, and predictable structure. This review aims to present state-of-the-art insights into COFs (properties, classification, synthesis methods, and functionalization). The key mechanisms for the detection of antibiotics and the application performance of COFs in the detection of antibiotics from water are also discussed, followed by the challenges and opportunities for COFs in future research.

A Robust and Efficient Method for Effective Facial Keypoint Detection

Facial keypoint detection technology faces significant challenges under conditions such as occlusion, extreme angles, and other demanding environments. Previous research has largely relied on deep learning regression methods using the face’s overall global template. However, these methods lack robustness in difficult conditions, leading to instability in detecting facial keypoints. To address this challenge, we propose a joint optimization approach that combines regression with heatmaps, emphasizing the importance of local apparent features. Furthermore, to mitigate the reduced learning capacity resulting from model pruning, we integrate external supervision signals through knowledge distillation into our method. This strategy fosters the development of efficient, effective, and lightweight facial keypoint detection technology. Experimental results on the CelebA, 300W, and AFLW datasets demonstrate that our proposed method significantly improves the robustness of facial keypoint detection.